From 0461a4149836c792d186027c8c859637a4cfb11a Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 9 Dec 2014 21:38:05 +0000
Subject: spi: Pump transfers inside calling context for spi_sync()

If we are using the standard SPI message pump (which all drivers should be
transitioning over to) then special case the message enqueue and instead of
starting the worker thread to push messages to the hardware do so in the
context of the caller if the controller is idle. This avoids a context
switch in the common case where the controller has a single user in a
single thread, for short PIO transfers there may be no need to context
switch away from the calling context to complete the transfer.

The code is a bit more complex than is desirable in part due to the need
to handle drivers not using the standard queue and in part due to handling
the various combinations of bus locking and asynchronous submission in
interrupt context.

It is still suboptimal since it will still wake the message pump for each
transfer in order to schedule idling of the hardware and if multiple
contexts are using the controller simultaneously a caller may end up
pumping a message for some random other thread rather than for itself,
and if the thread ends up deferring due to another context idling the
hardware then it will just busy wait.  It can, however, have the benefit
of aggregating power up and down of the hardware when a caller performs
a series of transfers back to back without any need for the use of
spi_async().

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index a6ef2a8e6de..4e6db75e946 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -260,6 +260,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @pump_messages: work struct for scheduling work to the message pump
  * @queue_lock: spinlock to syncronise access to message queue
  * @queue: message queue
+ * @idling: the device is entering idle state
  * @cur_msg: the currently in-flight message
  * @cur_msg_prepared: spi_prepare_message was called for the currently
  *                    in-flight message
@@ -425,6 +426,7 @@ struct spi_master {
 	spinlock_t			queue_lock;
 	struct list_head		queue;
 	struct spi_message		*cur_msg;
+	bool				idling;
 	bool				busy;
 	bool				running;
 	bool				rt;
-- 
cgit v1.2.3-70-g09d2


From 6b127c71fbdd3daacfd8b9f80b8e6ebfb70a889e Mon Sep 17 00:00:00 2001
From: Sujith Manoharan <c_manoha@qca.qualcomm.com>
Date: Wed, 10 Dec 2014 21:26:10 +0530
Subject: mac80211: Move IEEE80211_TX_CTL_PS_RESPONSE

Move IEEE80211_TX_CTL_PS_RESPONSE to info->control.flags since
this is used only in the TX path (by ath9k). This frees up
a bit which can be used for other purposes.

Signed-off-by: Sujith Manoharan <c_manoha@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath9k/xmit.c | 6 ++++--
 include/net/mac80211.h                | 6 +++---
 net/mac80211/sta_info.c               | 7 ++++---
 3 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index e9bd02c2e84..4caee66e5f7 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -2259,7 +2259,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 	struct ath_txq *txq = txctl->txq;
 	struct ath_atx_tid *tid = NULL;
 	struct ath_buf *bf;
-	bool queue, skip_uapsd = false;
+	bool queue, skip_uapsd = false, ps_resp;
 	int q, ret;
 
 	if (vif)
@@ -2268,6 +2268,8 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 	if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)
 		txctl->force_channel = true;
 
+	ps_resp = !!(info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE);
+
 	ret = ath_tx_prepare(hw, skb, txctl);
 	if (ret)
 	    return ret;
@@ -2310,7 +2312,7 @@ int ath_tx_start(struct ieee80211_hw *hw, struct sk_buff *skb,
 	if (txctl->an && queue)
 		tid = ath_get_skb_tid(sc, txctl->an, skb);
 
-	if (!skip_uapsd && (info->flags & IEEE80211_TX_CTL_PS_RESPONSE)) {
+	if (!skip_uapsd && ps_resp) {
 		ath_txq_unlock(sc, txq);
 		txq = sc->tx.uapsdq;
 		ath_txq_lock(sc, txq);
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 58d719ddaa6..b36e60d4c51 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -505,8 +505,6 @@ struct ieee80211_bss_conf {
  * @IEEE80211_TX_CTL_DONTFRAG: Don't fragment this packet even if it
  *	would be fragmented by size (this is optional, only used for
  *	monitor injection).
- * @IEEE80211_TX_CTL_PS_RESPONSE: This frame is a response to a poll
- *	frame (PS-Poll or uAPSD).
  *
  * Note: If you have to add new flags to the enumeration, then don't
  *	 forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary.
@@ -542,7 +540,6 @@ enum mac80211_tx_info_flags {
 	IEEE80211_TX_STATUS_EOSP		= BIT(28),
 	IEEE80211_TX_CTL_USE_MINRATE		= BIT(29),
 	IEEE80211_TX_CTL_DONTFRAG		= BIT(30),
-	IEEE80211_TX_CTL_PS_RESPONSE		= BIT(31),
 };
 
 #define IEEE80211_TX_CTL_STBC_SHIFT		23
@@ -552,11 +549,14 @@ enum mac80211_tx_info_flags {
  *
  * @IEEE80211_TX_CTRL_PORT_CTRL_PROTO: this frame is a port control
  *	protocol frame (e.g. EAP)
+ * @IEEE80211_TX_CTRL_PS_RESPONSE: This frame is a response to a poll
+ *	frame (PS-Poll or uAPSD).
  *
  * These flags are used in tx_info->control.flags.
  */
 enum mac80211_tx_control_flags {
 	IEEE80211_TX_CTRL_PORT_CTRL_PROTO	= BIT(0),
+	IEEE80211_TX_CTRL_PS_RESPONSE		= BIT(1),
 };
 
 /*
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index a42f5b2b024..db8b07ac6b1 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1243,10 +1243,11 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 	 * ends the poll/service period.
 	 */
 	info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER |
-		       IEEE80211_TX_CTL_PS_RESPONSE |
 		       IEEE80211_TX_STATUS_EOSP |
 		       IEEE80211_TX_CTL_REQ_TX_STATUS;
 
+	info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE;
+
 	if (call_driver)
 		drv_allow_buffered_frames(local, sta, BIT(tid), 1,
 					  reason, false);
@@ -1395,8 +1396,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 			 * STA may still remain is PS mode after this frame
 			 * exchange.
 			 */
-			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER |
-				       IEEE80211_TX_CTL_PS_RESPONSE;
+			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
+			info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE;
 
 			/*
 			 * Use MoreData flag to indicate whether there are
-- 
cgit v1.2.3-70-g09d2


From 5cf16616e152dd5c274a65954c77f64892d025a8 Mon Sep 17 00:00:00 2001
From: Sujith Manoharan <c_manoha@qca.qualcomm.com>
Date: Wed, 10 Dec 2014 21:26:11 +0530
Subject: mac80211: Fix accounting of multicast frames

Since multicast frames are marked as no-ack, using
IEEE80211_TX_STAT_ACK to check if they have been
successfully transmitted by the driver is incorrect
since a driver can choose to ignore transmission status
for no-ack frames. This results in incorrect accounting
for such frames.

To fix this issue, this patch introduces a new flag
that can be used by drivers to indicate error-free
transmission of no-ack frames.

Signed-off-by: Sujith Manoharan <c_manoha@qca.qualcomm.com>
[add a note about not setting the flag for non-no-ack frames]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 6 ++++++
 net/mac80211/status.c  | 9 ++++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index b36e60d4c51..b24ef577aed 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -505,6 +505,11 @@ struct ieee80211_bss_conf {
  * @IEEE80211_TX_CTL_DONTFRAG: Don't fragment this packet even if it
  *	would be fragmented by size (this is optional, only used for
  *	monitor injection).
+ * @IEEE80211_TX_STAT_NOACK_TRANSMITTED: A frame that was marked with
+ *	IEEE80211_TX_CTL_NO_ACK has been successfully transmitted without
+ *	any errors (like issues specific to the driver/HW).
+ *	This flag must not be set for frames that don't request no-ack
+ *	behaviour with IEEE80211_TX_CTL_NO_ACK.
  *
  * Note: If you have to add new flags to the enumeration, then don't
  *	 forget to update %IEEE80211_TX_TEMPORARY_FLAGS when necessary.
@@ -540,6 +545,7 @@ enum mac80211_tx_info_flags {
 	IEEE80211_TX_STATUS_EOSP		= BIT(28),
 	IEEE80211_TX_CTL_USE_MINRATE		= BIT(29),
 	IEEE80211_TX_CTL_DONTFRAG		= BIT(30),
+	IEEE80211_TX_STAT_NOACK_TRANSMITTED	= BIT(31),
 };
 
 #define IEEE80211_TX_CTL_STBC_SHIFT		23
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index bb146f377ee..d64037c9672 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -664,13 +664,15 @@ void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
 	struct ieee80211_supported_band *sband;
 	int retry_count;
 	int rates_idx;
-	bool acked;
+	bool acked, noack_success;
 
 	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
 
 	sband = hw->wiphy->bands[info->band];
 
 	acked = !!(info->flags & IEEE80211_TX_STAT_ACK);
+	noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED);
+
 	if (pubsta) {
 		struct sta_info *sta;
 
@@ -696,7 +698,7 @@ void ieee80211_tx_status_noskb(struct ieee80211_hw *hw,
 		rate_control_tx_status_noskb(local, sband, sta, info);
 	}
 
-	if (acked) {
+	if (acked || noack_success) {
 		    local->dot11TransmittedFrameCount++;
 		    if (!pubsta)
 			    local->dot11MulticastTransmittedFrameCount++;
@@ -856,7 +858,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 	 * Fragments are passed to low-level drivers as separate skbs, so these
 	 * are actually fragments, not frames. Update frame counters only for
 	 * the first fragment of the frame. */
-	if (info->flags & IEEE80211_TX_STAT_ACK) {
+	if ((info->flags & IEEE80211_TX_STAT_ACK) ||
+	    (info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) {
 		if (ieee80211_is_first_frag(hdr->seq_ctrl)) {
 			local->dot11TransmittedFrameCount++;
 			if (is_multicast_ether_addr(hdr->addr1))
-- 
cgit v1.2.3-70-g09d2


From 848955ccf0bdf42fff33e021a76f6daec98fe59b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 11 Nov 2014 12:48:42 +0100
Subject: mac80211: move U-APSD enablement to vif flags

In order to let drivers have more dynamic U-APSD support,
move the enablement flag to the virtual interface driver
flags. This lets drivers not only set it up differently
for different interfaces, but also enable/disable on the
fly if needed.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath10k/mac.c       |  3 ++-
 drivers/net/wireless/cw1200/main.c          |  1 -
 drivers/net/wireless/cw1200/sta.c           |  1 +
 drivers/net/wireless/iwlwifi/mvm/mac80211.c | 13 ++++++-------
 drivers/net/wireless/ti/wl1251/main.c       |  5 ++---
 drivers/net/wireless/ti/wlcore/main.c       |  2 +-
 include/net/mac80211.h                      | 15 +++++++--------
 net/mac80211/debugfs.c                      |  2 --
 net/mac80211/main.c                         |  4 ----
 net/mac80211/mlme.c                         |  7 ++++++-
 10 files changed, 25 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index c4005670cba..2619db1e3e7 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -2871,6 +2871,8 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 	int bit;
 	u32 vdev_param;
 
+	vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD;
+
 	mutex_lock(&ar->conf_mutex);
 
 	memset(arvif, 0, sizeof(*arvif));
@@ -5024,7 +5026,6 @@ int ath10k_mac_register(struct ath10k *ar)
 	ar->hw->flags = IEEE80211_HW_SIGNAL_DBM |
 			IEEE80211_HW_SUPPORTS_PS |
 			IEEE80211_HW_SUPPORTS_DYNAMIC_PS |
-			IEEE80211_HW_SUPPORTS_UAPSD |
 			IEEE80211_HW_MFP_CAPABLE |
 			IEEE80211_HW_REPORTS_TX_ACK_STATUS |
 			IEEE80211_HW_HAS_RATE_CONTROL |
diff --git a/drivers/net/wireless/cw1200/main.c b/drivers/net/wireless/cw1200/main.c
index 3e78cc3ccb7..0da6e423da6 100644
--- a/drivers/net/wireless/cw1200/main.c
+++ b/drivers/net/wireless/cw1200/main.c
@@ -282,7 +282,6 @@ static struct ieee80211_hw *cw1200_init_common(const u8 *macaddr,
 		    IEEE80211_HW_SUPPORTS_PS |
 		    IEEE80211_HW_SUPPORTS_DYNAMIC_PS |
 		    IEEE80211_HW_REPORTS_TX_ACK_STATUS |
-		    IEEE80211_HW_SUPPORTS_UAPSD |
 		    IEEE80211_HW_CONNECTION_MONITOR |
 		    IEEE80211_HW_AMPDU_AGGREGATION |
 		    IEEE80211_HW_TX_AMPDU_SETUP_IN_HW |
diff --git a/drivers/net/wireless/cw1200/sta.c b/drivers/net/wireless/cw1200/sta.c
index 5b84664db13..a1e3237c0be 100644
--- a/drivers/net/wireless/cw1200/sta.c
+++ b/drivers/net/wireless/cw1200/sta.c
@@ -213,6 +213,7 @@ int cw1200_add_interface(struct ieee80211_hw *dev,
 	/* __le32 auto_calibration_mode = __cpu_to_le32(1); */
 
 	vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER |
+			     IEEE80211_VIF_SUPPORTS_UAPSD |
 			     IEEE80211_VIF_SUPPORTS_CQM_RSSI;
 
 	mutex_lock(&priv->conf_mutex);
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 31a5b3f4266..346331d3c69 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -326,6 +326,8 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	hw->radiotap_vht_details |= IEEE80211_RADIOTAP_VHT_KNOWN_STBC |
 		IEEE80211_RADIOTAP_VHT_KNOWN_BEAMFORMED;
 	hw->rate_control_algorithm = "iwl-mvm-rs";
+	hw->uapsd_queues = IWL_MVM_UAPSD_QUEUES;
+	hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP;
 
 	/*
 	 * Enable 11w if advertised by firmware and software crypto
@@ -336,13 +338,6 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	    !iwlwifi_mod_params.sw_crypto)
 		hw->flags |= IEEE80211_HW_MFP_CAPABLE;
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT &&
-	    !iwlwifi_mod_params.uapsd_disable) {
-		hw->flags |= IEEE80211_HW_SUPPORTS_UAPSD;
-		hw->uapsd_queues = IWL_MVM_UAPSD_QUEUES;
-		hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP;
-	}
-
 	if (mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_LMAC_SCAN ||
 	    mvm->fw->ucode_capa.capa[0] & IWL_UCODE_TLV_CAPA_UMAC_SCAN) {
 		hw->flags |= IEEE80211_SINGLE_HW_SCAN_ON_ALL_BANDS;
@@ -1147,6 +1142,10 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 		mvm->bf_allowed_vif = mvmvif;
 		vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER |
 				     IEEE80211_VIF_SUPPORTS_CQM_RSSI;
+		if (mvm->fw->ucode_capa.flags &
+					IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT &&
+		    !iwlwifi_mod_params.uapsd_disable)
+			vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD;
 	}
 
 	/*
diff --git a/drivers/net/wireless/ti/wl1251/main.c b/drivers/net/wireless/ti/wl1251/main.c
index 0b30a7b4d66..d4ba009ac9a 100644
--- a/drivers/net/wireless/ti/wl1251/main.c
+++ b/drivers/net/wireless/ti/wl1251/main.c
@@ -500,6 +500,7 @@ static int wl1251_op_add_interface(struct ieee80211_hw *hw,
 	int ret = 0;
 
 	vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER |
+			     IEEE80211_VIF_SUPPORTS_UAPSD |
 			     IEEE80211_VIF_SUPPORTS_CQM_RSSI;
 
 	wl1251_debug(DEBUG_MAC80211, "mac80211 add interface type %d mac %pM",
@@ -1480,9 +1481,7 @@ int wl1251_init_ieee80211(struct wl1251 *wl)
 	/* unit us */
 	/* FIXME: find a proper value */
 
-	wl->hw->flags = IEEE80211_HW_SIGNAL_DBM |
-		IEEE80211_HW_SUPPORTS_PS |
-		IEEE80211_HW_SUPPORTS_UAPSD;
+	wl->hw->flags = IEEE80211_HW_SIGNAL_DBM | IEEE80211_HW_SUPPORTS_PS;
 
 	wl->hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
 					 BIT(NL80211_IFTYPE_ADHOC);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 6ad3fcedab9..2a99456b6b8 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -2508,6 +2508,7 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	}
 
 	vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER |
+			     IEEE80211_VIF_SUPPORTS_UAPSD |
 			     IEEE80211_VIF_SUPPORTS_CQM_RSSI;
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 add interface type %d mac %pM",
@@ -5776,7 +5777,6 @@ static int wl1271_init_ieee80211(struct wl1271 *wl)
 	wl->hw->flags = IEEE80211_HW_SIGNAL_DBM |
 		IEEE80211_HW_SUPPORTS_PS |
 		IEEE80211_HW_SUPPORTS_DYNAMIC_PS |
-		IEEE80211_HW_SUPPORTS_UAPSD |
 		IEEE80211_HW_HAS_RATE_CONTROL |
 		IEEE80211_HW_CONNECTION_MONITOR |
 		IEEE80211_HW_REPORTS_TX_ACK_STATUS |
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index b24ef577aed..4913c00539f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1187,10 +1187,15 @@ struct ieee80211_channel_switch {
  *	monitoring on this virtual interface -- i.e. it can monitor
  *	connection quality related parameters, such as the RSSI level and
  *	provide notifications if configured trigger levels are reached.
+ * @IEEE80211_VIF_SUPPORTS_UAPSD: The device can do U-APSD for this
+ *	interface. This flag should be set during interface addition,
+ *	but may be set/cleared as late as authentication to an AP. It is
+ *	only valid for managed/station mode interfaces.
  */
 enum ieee80211_vif_flags {
 	IEEE80211_VIF_BEACON_FILTER		= BIT(0),
 	IEEE80211_VIF_SUPPORTS_CQM_RSSI		= BIT(1),
+	IEEE80211_VIF_SUPPORTS_UAPSD		= BIT(2),
 };
 
 /**
@@ -1589,11 +1594,6 @@ struct ieee80211_tx_control {
  * @IEEE80211_HW_MFP_CAPABLE:
  *	Hardware supports management frame protection (MFP, IEEE 802.11w).
  *
- * @IEEE80211_HW_SUPPORTS_UAPSD:
- *	Hardware supports Unscheduled Automatic Power Save Delivery
- *	(U-APSD) in managed mode. The mode is configured with
- *	conf_tx() operation.
- *
  * @IEEE80211_HW_REPORTS_TX_ACK_STATUS:
  *	Hardware can provide ack status reports of Tx frames to
  *	the stack.
@@ -1679,8 +1679,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_MFP_CAPABLE			= 1<<13,
 	IEEE80211_HW_WANT_MONITOR_VIF			= 1<<14,
 	IEEE80211_HW_NO_AUTO_VIF			= 1<<15,
-	/* free slot */
-	IEEE80211_HW_SUPPORTS_UAPSD			= 1<<17,
+	/* free slots */
 	IEEE80211_HW_REPORTS_TX_ACK_STATUS		= 1<<18,
 	IEEE80211_HW_CONNECTION_MONITOR			= 1<<19,
 	IEEE80211_HW_QUEUE_CONTROL			= 1<<20,
@@ -2032,7 +2031,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
  * enabled whenever user has enabled powersave.
  *
  * Driver informs U-APSD client support by enabling
- * %IEEE80211_HW_SUPPORTS_UAPSD flag. The mode is configured through the
+ * %IEEE80211_VIF_SUPPORTS_UAPSD flag. The mode is configured through the
  * uapsd parameter in conf_tx() operation. Hardware needs to send the QoS
  * Nullfunc frames and stay awake until the service period has ended. To
  * utilize U-APSD, dynamic powersave is disabled for voip AC and all frames
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 54a189f0393..eeb0bbd69d9 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -303,8 +303,6 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf,
 		sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_DYNAMIC_PS\n");
 	if (local->hw.flags & IEEE80211_HW_MFP_CAPABLE)
 		sf += scnprintf(buf + sf, mxln - sf, "MFP_CAPABLE\n");
-	if (local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)
-		sf += scnprintf(buf + sf, mxln - sf, "SUPPORTS_UAPSD\n");
 	if (local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS)
 		sf += scnprintf(buf + sf, mxln - sf,
 				"REPORTS_TX_ACK_STATUS\n");
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 6ab99da38db..d9ce33663c7 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -916,10 +916,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		}
 	}
 
-	WARN((local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)
-	     && (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK),
-	     "U-APSD not supported with HW_PS_NULLFUNC_STACK\n");
-
 	/*
 	 * Calculate scan IE length -- we need this to alloc
 	 * memory and to subtract from the driver limit. It
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 75a9bf50207..f495b800b92 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4667,8 +4667,13 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
 	rcu_read_unlock();
 
+	if (WARN((sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD) &&
+		 (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK),
+	     "U-APSD not supported with HW_PS_NULLFUNC_STACK\n"))
+		sdata->vif.driver_flags &= ~IEEE80211_VIF_SUPPORTS_UAPSD;
+
 	if (bss->wmm_used && bss->uapsd_supported &&
-	    (sdata->local->hw.flags & IEEE80211_HW_SUPPORTS_UAPSD)) {
+	    (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_UAPSD)) {
 		assoc_data->uapsd = true;
 		ifmgd->flags |= IEEE80211_STA_UAPSD_ENABLED;
 	} else {
-- 
cgit v1.2.3-70-g09d2


From e39f2d5956999c05c85814787a113ffadbcd4b26 Mon Sep 17 00:00:00 2001
From: Andrew Duggan <aduggan@synaptics.com>
Date: Fri, 12 Dec 2014 10:17:26 -0800
Subject: HID: rmi: Scan the report descriptor to determine if the device is
 suitable for the hid-rmi driver

On composite HID devices there may be multiple HID devices on separate
interfaces, but hid-rmi should only bind to the touchpad. The previous version
simply checked that the interface protocol was set to mouse. Unfortuately, it
is not always the case that the touchpad has the mouse interface protocol set.
This patch takes a different approach and scans the report descriptor looking
for the Generic Desktop Pointer usage and the Vendor Specific Top Level
Collection needed by the hid-rmi driver to interface with the device.

Signed-off-by: Andrew Duggan <aduggan@synaptics.com>
Reviewed-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c | 22 +++++++++++++++++-----
 include/linux/hid.h    |  4 +++-
 2 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index c3d0ac1a098..81665b4f225 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -698,6 +698,7 @@ static void hid_scan_feature_usage(struct hid_parser *parser, u32 usage)
 static void hid_scan_collection(struct hid_parser *parser, unsigned type)
 {
 	struct hid_device *hid = parser->device;
+	int i;
 
 	if (((parser->global.usage_page << 16) == HID_UP_SENSOR) &&
 	    type == HID_COLLECTION_PHYSICAL)
@@ -707,6 +708,14 @@ static void hid_scan_collection(struct hid_parser *parser, unsigned type)
 	    hid->product == USB_DEVICE_ID_MS_TYPE_COVER_3 &&
 	    hid->group == HID_GROUP_MULTITOUCH)
 		hid->group = HID_GROUP_GENERIC;
+
+	if ((parser->global.usage_page << 16) == HID_UP_GENDESK)
+		for (i = 0; i < parser->local.usage_index; i++)
+			if (parser->local.usage[i] == HID_GD_POINTER)
+				parser->scan_flags |= HID_SCAN_FLAG_GD_POINTER;
+
+	if ((parser->global.usage_page << 16) >= HID_UP_MSVENDOR)
+		parser->scan_flags |= HID_SCAN_FLAG_VENDOR_SPECIFIC;
 }
 
 static int hid_scan_main(struct hid_parser *parser, struct hid_item *item)
@@ -792,11 +801,14 @@ static int hid_scan_report(struct hid_device *hid)
 		hid->group = HID_GROUP_WACOM;
 		break;
 	case USB_VENDOR_ID_SYNAPTICS:
-		if ((hid->group == HID_GROUP_GENERIC) &&
-		    (hid->bus != BUS_USB || hid->type == HID_TYPE_USBMOUSE))
-			/* hid-rmi should only bind to the mouse interface of
-			 * composite USB devices */
-			hid->group = HID_GROUP_RMI;
+		if (hid->group == HID_GROUP_GENERIC)
+			if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC)
+			    && (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER))
+				/*
+				 * hid-rmi should take care of them,
+				 * not hid-generic
+				 */
+				hid->group = HID_GROUP_RMI;
 		break;
 	}
 
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 06c4607744f..efc7787a41a 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -574,7 +574,9 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data)
 #define HID_GLOBAL_STACK_SIZE 4
 #define HID_COLLECTION_STACK_SIZE 4
 
-#define HID_SCAN_FLAG_MT_WIN_8			0x00000001
+#define HID_SCAN_FLAG_MT_WIN_8			BIT(0)
+#define HID_SCAN_FLAG_VENDOR_SPECIFIC		BIT(1)
+#define HID_SCAN_FLAG_GD_POINTER		BIT(2)
 
 struct hid_parser {
 	struct hid_global     global;
-- 
cgit v1.2.3-70-g09d2


From ad30ca2c03cecfb1b0749874bdceead269542de6 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Mon, 15 Dec 2014 19:25:59 +0200
Subject: cfg80211: allow usermode to query wiphy specific regdom

If a wiphy-idx is specified, the kernel will return the wiphy specific
regdomain, if such exists. Otherwise return the global regdom.

When no wiphy-idx is specified, return the global regdomain as well as
all wiphy-specific regulatory domains in the system, via a new nested
list of attributes.

Add a new attribute for each wiphy-specific regdomain, for usermode to
identify it as such.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  10 ++-
 net/wireless/nl80211.c       | 173 ++++++++++++++++++++++++++++++++++---------
 net/wireless/reg.c           |   2 +-
 net/wireless/reg.h           |   1 +
 4 files changed, 151 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index b37bd5a1cb8..2d384d04122 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -252,7 +252,15 @@
  *	%NL80211_ATTR_IFINDEX.
  *
  * @NL80211_CMD_GET_REG: ask the wireless core to send us its currently set
- * 	regulatory domain.
+ *	regulatory domain. If %NL80211_ATTR_WIPHY is specified and the device
+ *	has a private regulatory domain, it will be returned. Otherwise, the
+ *	global regdomain will be returned.
+ *	A device will have a private regulatory domain if it uses the
+ *	regulatory_hint() API. Even when a private regdomain is used the channel
+ *	information will still be mended according to further hints from
+ *	the regulatory core to help with compliance. A dump version of this API
+ *	is now available which will returns the global regdomain as well as
+ *	all private regdomains of present wiphys (for those that have it).
  * @NL80211_CMD_SET_REG: Set current regulatory domain. CRDA sends this command
  *	after being queried by the kernel. CRDA replies by sending a regulatory
  *	domain structure which consists of %NL80211_ATTR_REG_ALPHA set to our
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index a17d6bc6b22..2d5dc428c5a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5327,42 +5327,20 @@ static int nl80211_update_mesh_config(struct sk_buff *skb,
 	return err;
 }
 
-static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
+static int nl80211_put_regdom(const struct ieee80211_regdomain *regdom,
+			      struct sk_buff *msg)
 {
-	const struct ieee80211_regdomain *regdom;
-	struct sk_buff *msg;
-	void *hdr = NULL;
 	struct nlattr *nl_reg_rules;
 	unsigned int i;
 
-	if (!cfg80211_regdomain)
-		return -EINVAL;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOBUFS;
-
-	hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
-			     NL80211_CMD_GET_REG);
-	if (!hdr)
-		goto put_failure;
-
-	if (reg_last_request_cell_base() &&
-	    nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE,
-			NL80211_USER_REG_HINT_CELL_BASE))
-		goto nla_put_failure;
-
-	rcu_read_lock();
-	regdom = rcu_dereference(cfg80211_regdomain);
-
 	if (nla_put_string(msg, NL80211_ATTR_REG_ALPHA2, regdom->alpha2) ||
 	    (regdom->dfs_region &&
 	     nla_put_u8(msg, NL80211_ATTR_DFS_REGION, regdom->dfs_region)))
-		goto nla_put_failure_rcu;
+		goto nla_put_failure;
 
 	nl_reg_rules = nla_nest_start(msg, NL80211_ATTR_REG_RULES);
 	if (!nl_reg_rules)
-		goto nla_put_failure_rcu;
+		goto nla_put_failure;
 
 	for (i = 0; i < regdom->n_reg_rules; i++) {
 		struct nlattr *nl_reg_rule;
@@ -5377,7 +5355,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
 
 		nl_reg_rule = nla_nest_start(msg, i);
 		if (!nl_reg_rule)
-			goto nla_put_failure_rcu;
+			goto nla_put_failure;
 
 		max_bandwidth_khz = freq_range->max_bandwidth_khz;
 		if (!max_bandwidth_khz)
@@ -5398,13 +5376,64 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info)
 				power_rule->max_eirp) ||
 		    nla_put_u32(msg, NL80211_ATTR_DFS_CAC_TIME,
 				reg_rule->dfs_cac_ms))
-			goto nla_put_failure_rcu;
+			goto nla_put_failure;
 
 		nla_nest_end(msg, nl_reg_rule);
 	}
-	rcu_read_unlock();
 
 	nla_nest_end(msg, nl_reg_rules);
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info)
+{
+	const struct ieee80211_regdomain *regdom = NULL;
+	struct cfg80211_registered_device *rdev;
+	struct wiphy *wiphy = NULL;
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOBUFS;
+
+	hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
+			     NL80211_CMD_GET_REG);
+	if (!hdr)
+		goto put_failure;
+
+	if (info->attrs[NL80211_ATTR_WIPHY]) {
+		rdev = cfg80211_get_dev_from_info(genl_info_net(info), info);
+		if (IS_ERR(rdev)) {
+			nlmsg_free(msg);
+			return PTR_ERR(rdev);
+		}
+
+		wiphy = &rdev->wiphy;
+		regdom = get_wiphy_regdom(wiphy);
+
+		if (regdom &&
+		    nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)))
+			goto nla_put_failure;
+	}
+
+	if (!wiphy && reg_last_request_cell_base() &&
+	    nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE,
+			NL80211_USER_REG_HINT_CELL_BASE))
+		goto nla_put_failure;
+
+	rcu_read_lock();
+
+	if (!regdom)
+		regdom = rcu_dereference(cfg80211_regdomain);
+
+	if (nl80211_put_regdom(regdom, msg))
+		goto nla_put_failure_rcu;
+
+	rcu_read_unlock();
 
 	genlmsg_end(msg, hdr);
 	return genlmsg_reply(msg, info);
@@ -5418,6 +5447,79 @@ put_failure:
 	return -EMSGSIZE;
 }
 
+static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb,
+			       u32 seq, int flags, struct wiphy *wiphy,
+			       const struct ieee80211_regdomain *regdom)
+{
+	void *hdr = nl80211hdr_put(msg, NETLINK_CB(cb->skb).portid, seq, flags,
+				   NL80211_CMD_GET_REG);
+
+	if (!hdr)
+		return -1;
+
+	genl_dump_check_consistent(cb, hdr, &nl80211_fam);
+
+	if (nl80211_put_regdom(regdom, msg))
+		goto nla_put_failure;
+
+	if (!wiphy && reg_last_request_cell_base() &&
+	    nla_put_u32(msg, NL80211_ATTR_USER_REG_HINT_TYPE,
+			NL80211_USER_REG_HINT_CELL_BASE))
+		goto nla_put_failure;
+
+	if (wiphy &&
+	    nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)))
+		goto nla_put_failure;
+
+	return genlmsg_end(msg, hdr);
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int nl80211_get_reg_dump(struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	const struct ieee80211_regdomain *regdom = NULL;
+	struct cfg80211_registered_device *rdev;
+	int err, reg_idx, start = cb->args[2];
+
+	rtnl_lock();
+
+	if (cfg80211_regdomain && start == 0) {
+		err = nl80211_send_regdom(skb, cb, cb->nlh->nlmsg_seq,
+					  NLM_F_MULTI, NULL,
+					  rtnl_dereference(cfg80211_regdomain));
+		if (err < 0)
+			goto out_err;
+	}
+
+	/* the global regdom is idx 0 */
+	reg_idx = 1;
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		regdom = get_wiphy_regdom(&rdev->wiphy);
+		if (!regdom)
+			continue;
+
+		if (++reg_idx <= start)
+			continue;
+
+		err = nl80211_send_regdom(skb, cb, cb->nlh->nlmsg_seq,
+					  NLM_F_MULTI, &rdev->wiphy, regdom);
+		if (err < 0) {
+			reg_idx--;
+			break;
+		}
+	}
+
+	cb->args[2] = reg_idx;
+	err = skb->len;
+out_err:
+	rtnl_unlock();
+	return err;
+}
+
 static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *tb[NL80211_REG_RULE_ATTR_MAX + 1];
@@ -10225,7 +10327,8 @@ static const struct genl_ops nl80211_ops[] = {
 	},
 	{
 		.cmd = NL80211_CMD_GET_REG,
-		.doit = nl80211_get_reg,
+		.doit = nl80211_get_reg_do,
+		.dumpit = nl80211_get_reg_dump,
 		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_RTNL,
 		/* can be retrieved by unprivileged users */
@@ -10983,9 +11086,13 @@ void nl80211_send_reg_change_event(struct regulatory_request *request)
 			goto nla_put_failure;
 	}
 
-	if (request->wiphy_idx != WIPHY_IDX_INVALID &&
-	    nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx))
-		goto nla_put_failure;
+	if (request->wiphy_idx != WIPHY_IDX_INVALID) {
+		struct wiphy *wiphy = wiphy_idx_to_wiphy(request->wiphy_idx);
+
+		if (wiphy &&
+		    nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx))
+			goto nla_put_failure;
+	}
 
 	genlmsg_end(msg, hdr);
 
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index d83480b6efd..2d9760084b7 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -142,7 +142,7 @@ static const struct ieee80211_regdomain *get_cfg80211_regdom(void)
 	return rtnl_dereference(cfg80211_regdomain);
 }
 
-static const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy)
+const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy)
 {
 	return rtnl_dereference(wiphy->regd);
 }
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index 5e48031ccb9..4b45d6e61d2 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -38,6 +38,7 @@ unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd,
 				   const struct ieee80211_reg_rule *rule);
 
 bool reg_last_request_cell_base(void);
+const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy);
 
 /**
  * regulatory_hint_found_beacon - hints a beacon was found on a channel
-- 
cgit v1.2.3-70-g09d2


From b0d7aa59592b4270531de5ce65dcf18338a2d98c Mon Sep 17 00:00:00 2001
From: Jonathan Doron <jond@wizery.com>
Date: Mon, 15 Dec 2014 19:26:00 +0200
Subject: cfg80211: allow wiphy specific regdomain management

Add a new regulatory flag that allows a driver to manage regdomain
changes/updates for its own wiphy.
A self-managed wiphys only employs regulatory information obtained from
the FW and driver and does not use other cfg80211 sources like
beacon-hints, country-code IEs and hints from other devices on the same
system. Conversely, a self-managed wiphy does not share its regulatory
hints with other devices in the system. If a system contains several
devices, one or more of which are self-managed, there might be
contradictory regulatory settings between them. Usage of flag is
generally discouraged. Only use it if the FW/driver is incompatible
with non-locally originated hints.

A new API lets the driver send a complete regdomain, to be applied on
its wiphy only.

After a wiphy-specific regdomain change takes place, usermode will get
a new type of change notification. The regulatory core also takes care
enforce regulatory restrictions, in case some interfaces are on
forbidden channels.

Signed-off-by: Jonathan Doron <jonathanx.doron@intel.com>
Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Reviewed-by: Luis R. Rodriguez <mcgrof@suse.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 14 +++++++
 include/net/regulatory.h     | 19 ++++++++++
 include/uapi/linux/nl80211.h |  6 +++
 net/wireless/core.c          |  8 ++++
 net/wireless/core.h          |  7 ++++
 net/wireless/nl80211.c       | 49 +++++++++++++++---------
 net/wireless/nl80211.h       | 16 +++++++-
 net/wireless/reg.c           | 88 ++++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 188 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 4ebb816241f..4bc1fc9971a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3807,6 +3807,20 @@ const u8 *cfg80211_find_vendor_ie(unsigned int oui, u8 oui_type,
  */
 int regulatory_hint(struct wiphy *wiphy, const char *alpha2);
 
+/**
+ * regulatory_set_wiphy_regd - set regdom info for self managed drivers
+ * @wiphy: the wireless device we want to process the regulatory domain on
+ * @rd: the regulatory domain informatoin to use for this wiphy
+ *
+ * Set the regulatory domain information for self-managed wiphys, only they
+ * may use this function. See %REGULATORY_WIPHY_SELF_MANAGED for more
+ * information.
+ *
+ * Return: 0 on success. -EINVAL, -EPERM
+ */
+int regulatory_set_wiphy_regd(struct wiphy *wiphy,
+			      struct ieee80211_regdomain *rd);
+
 /**
  * wiphy_apply_custom_regulatory - apply a custom driver regulatory domain
  * @wiphy: the wireless device we want to process the regulatory domain on
diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index b776d72d84b..ebc5a2ed863 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -147,6 +147,24 @@ struct regulatory_request {
  *	NL80211_IFTYPE_P2P_CLIENT, NL80211_IFTYPE_P2P_GO,
  *	NL80211_IFTYPE_P2P_DEVICE. The flag will be set by default if a device
  *	includes any modes unsupported for enforcement checking.
+ * @REGULATORY_WIPHY_SELF_MANAGED: for devices that employ wiphy-specific
+ *	regdom management. These devices will ignore all regdom changes not
+ *	originating from their own wiphy.
+ *	A self-managed wiphys only employs regulatory information obtained from
+ *	the FW and driver and does not use other cfg80211 sources like
+ *	beacon-hints, country-code IEs and hints from other devices on the same
+ *	system. Conversely, a self-managed wiphy does not share its regulatory
+ *	hints with other devices in the system. If a system contains several
+ *	devices, one or more of which are self-managed, there might be
+ *	contradictory regulatory settings between them. Usage of flag is
+ *	generally discouraged. Only use it if the FW/driver is incompatible
+ *	with non-locally originated hints.
+ *	This flag is incompatible with the flags: %REGULATORY_CUSTOM_REG,
+ *	%REGULATORY_STRICT_REG, %REGULATORY_COUNTRY_IE_FOLLOW_POWER,
+ *	%REGULATORY_COUNTRY_IE_IGNORE and %REGULATORY_DISABLE_BEACON_HINTS.
+ *	Mixing any of the above flags with this flag will result in a failure
+ *	to register the wiphy. This flag implies
+ *	%REGULATORY_DISABLE_BEACON_HINTS and %REGULATORY_COUNTRY_IE_IGNORE.
  */
 enum ieee80211_regulatory_flags {
 	REGULATORY_CUSTOM_REG			= BIT(0),
@@ -156,6 +174,7 @@ enum ieee80211_regulatory_flags {
 	REGULATORY_COUNTRY_IE_IGNORE		= BIT(4),
 	REGULATORY_ENABLE_RELAX_NO_IR           = BIT(5),
 	REGULATORY_IGNORE_STALE_KICKOFF         = BIT(6),
+	REGULATORY_WIPHY_SELF_MANAGED		= BIT(7),
 };
 
 struct ieee80211_freq_range {
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 2d384d04122..fb58e654f52 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -782,6 +782,10 @@
  *	peer given by %NL80211_ATTR_MAC. Both peers must be on the base channel
  *	when this command completes.
  *
+ * @NL80211_CMD_WIPHY_REG_CHANGE: Similar to %NL80211_CMD_REG_CHANGE, but used
+ *	as an event to indicate changes for devices with wiphy-specific regdom
+ *	management.
+ *
  * @NL80211_CMD_MAX: highest used command number
  * @__NL80211_CMD_AFTER_LAST: internal use
  */
@@ -966,6 +970,8 @@ enum nl80211_commands {
 	NL80211_CMD_TDLS_CHANNEL_SWITCH,
 	NL80211_CMD_TDLS_CANCEL_CHANNEL_SWITCH,
 
+	NL80211_CMD_WIPHY_REG_CHANGE,
+
 	/* add new commands above here */
 
 	/* used to define NL80211_CMD_MAX below */
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 4910758baab..b661fcce7e3 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -561,6 +561,14 @@ int wiphy_register(struct wiphy *wiphy)
 				       BIT(NL80211_IFTYPE_MONITOR)))
 		wiphy->regulatory_flags |= REGULATORY_IGNORE_STALE_KICKOFF;
 
+	if (WARN_ON((wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) &&
+		    (wiphy->regulatory_flags &
+					(REGULATORY_CUSTOM_REG |
+					 REGULATORY_STRICT_REG |
+					 REGULATORY_COUNTRY_IE_FOLLOW_POWER |
+					 REGULATORY_COUNTRY_IE_IGNORE))))
+		return -EINVAL;
+
 	if (WARN_ON(wiphy->coalesce &&
 		    (!wiphy->coalesce->n_rules ||
 		     !wiphy->coalesce->n_patterns) &&
diff --git a/net/wireless/core.h b/net/wireless/core.h
index faa5b1609aa..e87cae57a83 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -36,6 +36,13 @@ struct cfg80211_registered_device {
 	 * the country on the country IE changed. */
 	char country_ie_alpha2[2];
 
+	/*
+	 * the driver requests the regulatory core to set this regulatory
+	 * domain as the wiphy's. Only used for %REGULATORY_WIPHY_SELF_MANAGED
+	 * devices using the regulatory_set_wiphy_regd() API
+	 */
+	const struct ieee80211_regdomain *requested_regd;
+
 	/* If a Country IE has been received this tells us the environment
 	 * which its telling us its in. This defaults to ENVIRON_ANY */
 	enum environment_cap env;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 2d5dc428c5a..eebb7e42298 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -11042,25 +11042,9 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 				NL80211_MCGRP_SCAN, GFP_KERNEL);
 }
 
-/*
- * This can happen on global regulatory changes or device specific settings
- * based on custom world regulatory domains.
- */
-void nl80211_send_reg_change_event(struct regulatory_request *request)
+static bool nl80211_reg_change_event_fill(struct sk_buff *msg,
+					  struct regulatory_request *request)
 {
-	struct sk_buff *msg;
-	void *hdr;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return;
-
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_REG_CHANGE);
-	if (!hdr) {
-		nlmsg_free(msg);
-		return;
-	}
-
 	/* Userspace can always count this one always being set */
 	if (nla_put_u8(msg, NL80211_ATTR_REG_INITIATOR, request->initiator))
 		goto nla_put_failure;
@@ -11094,6 +11078,35 @@ void nl80211_send_reg_change_event(struct regulatory_request *request)
 			goto nla_put_failure;
 	}
 
+	return true;
+
+nla_put_failure:
+	return false;
+}
+
+/*
+ * This can happen on global regulatory changes or device specific settings
+ * based on custom regulatory domains.
+ */
+void nl80211_common_reg_change_event(enum nl80211_commands cmd_id,
+				     struct regulatory_request *request)
+{
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	hdr = nl80211hdr_put(msg, 0, 0, 0, cmd_id);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	if (nl80211_reg_change_event_fill(msg, request) == false)
+		goto nla_put_failure;
+
 	genlmsg_end(msg, hdr);
 
 	rcu_read_lock();
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 7ad70d6f0cc..84d4edf1d54 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -17,7 +17,21 @@ void nl80211_send_sched_scan(struct cfg80211_registered_device *rdev,
 			     struct net_device *netdev, u32 cmd);
 void nl80211_send_sched_scan_results(struct cfg80211_registered_device *rdev,
 				     struct net_device *netdev);
-void nl80211_send_reg_change_event(struct regulatory_request *request);
+void nl80211_common_reg_change_event(enum nl80211_commands cmd_id,
+				     struct regulatory_request *request);
+
+static inline void
+nl80211_send_reg_change_event(struct regulatory_request *request)
+{
+	nl80211_common_reg_change_event(NL80211_CMD_REG_CHANGE, request);
+}
+
+static inline void
+nl80211_send_wiphy_reg_change_event(struct regulatory_request *request)
+{
+	nl80211_common_reg_change_event(NL80211_CMD_WIPHY_REG_CHANGE, request);
+}
+
 void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  struct net_device *netdev,
 			  const u8 *buf, size_t len, gfp_t gfp);
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2d9760084b7..c040f8a0f1e 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1307,6 +1307,9 @@ static bool ignore_reg_update(struct wiphy *wiphy,
 {
 	struct regulatory_request *lr = get_last_request();
 
+	if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+		return true;
+
 	if (!lr) {
 		REG_DBG_PRINT("Ignoring regulatory request set by %s "
 			      "since last_request is not set\n",
@@ -2147,11 +2150,52 @@ static void reg_process_pending_beacon_hints(void)
 	spin_unlock_bh(&reg_pending_beacons_lock);
 }
 
+static void reg_process_self_managed_hints(void)
+{
+	struct cfg80211_registered_device *rdev;
+	struct wiphy *wiphy;
+	const struct ieee80211_regdomain *tmp;
+	const struct ieee80211_regdomain *regd;
+	enum ieee80211_band band;
+	struct regulatory_request request = {};
+
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		wiphy = &rdev->wiphy;
+
+		spin_lock(&reg_requests_lock);
+		regd = rdev->requested_regd;
+		rdev->requested_regd = NULL;
+		spin_unlock(&reg_requests_lock);
+
+		if (regd == NULL)
+			continue;
+
+		tmp = get_wiphy_regdom(wiphy);
+		rcu_assign_pointer(wiphy->regd, regd);
+		rcu_free_regdom(tmp);
+
+		for (band = 0; band < IEEE80211_NUM_BANDS; band++)
+			handle_band_custom(wiphy, wiphy->bands[band], regd);
+
+		reg_process_ht_flags(wiphy);
+
+		request.wiphy_idx = get_wiphy_idx(wiphy);
+		request.alpha2[0] = regd->alpha2[0];
+		request.alpha2[1] = regd->alpha2[1];
+		request.initiator = NL80211_REGDOM_SET_BY_DRIVER;
+
+		nl80211_send_wiphy_reg_change_event(&request);
+	}
+
+	reg_check_channels();
+}
+
 static void reg_todo(struct work_struct *work)
 {
 	rtnl_lock();
 	reg_process_pending_hints();
 	reg_process_pending_beacon_hints();
+	reg_process_self_managed_hints();
 	rtnl_unlock();
 }
 
@@ -2432,6 +2476,8 @@ static void restore_regulatory_settings(bool reset_user)
 	world_alpha2[1] = cfg80211_world_regdom->alpha2[1];
 
 	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		if (rdev->wiphy.regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+			continue;
 		if (rdev->wiphy.regulatory_flags & REGULATORY_CUSTOM_REG)
 			restore_custom_reg_settings(&rdev->wiphy);
 	}
@@ -2835,10 +2881,52 @@ int set_regdom(const struct ieee80211_regdomain *rd)
 	return 0;
 }
 
+int regulatory_set_wiphy_regd(struct wiphy *wiphy,
+			      struct ieee80211_regdomain *rd)
+{
+	const struct ieee80211_regdomain *regd;
+	const struct ieee80211_regdomain *prev_regd;
+	struct cfg80211_registered_device *rdev;
+
+	if (WARN_ON(!wiphy || !rd))
+		return -EINVAL;
+
+	if (WARN(!(wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED),
+		 "wiphy should have REGULATORY_WIPHY_SELF_MANAGED\n"))
+		return -EPERM;
+
+	if (WARN(!is_valid_rd(rd), "Invalid regulatory domain detected\n")) {
+		print_regdomain_info(rd);
+		return -EINVAL;
+	}
+
+	regd = reg_copy_regd(rd);
+	if (IS_ERR(regd))
+		return PTR_ERR(regd);
+
+	rdev = wiphy_to_rdev(wiphy);
+
+	spin_lock(&reg_requests_lock);
+	prev_regd = rdev->requested_regd;
+	rdev->requested_regd = regd;
+	spin_unlock(&reg_requests_lock);
+
+	kfree(prev_regd);
+
+	schedule_work(&reg_work);
+	return 0;
+}
+EXPORT_SYMBOL(regulatory_set_wiphy_regd);
+
 void wiphy_regulatory_register(struct wiphy *wiphy)
 {
 	struct regulatory_request *lr;
 
+	/* self-managed devices ignore external hints */
+	if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
+		wiphy->regulatory_flags |= REGULATORY_DISABLE_BEACON_HINTS |
+					   REGULATORY_COUNTRY_IE_IGNORE;
+
 	if (!reg_dev_ignore_cell_hint(wiphy))
 		reg_num_devs_support_basehint++;
 
-- 
cgit v1.2.3-70-g09d2


From 1bdd716cbccabc8127fbbaaa663c3090302ef78b Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Mon, 15 Dec 2014 19:26:01 +0200
Subject: cfg80211: return private regdom for self-managed devices

If a device has self-managed regulatory, insist on returning the wiphy
specific regdomain if a wiphy-idx is specified. The global regdomain is
meaningless for such devices.

Also add an attribute for self-managed devices, so usermode can
distinguish them as such.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Reviewed-by: Luis R. Rodriguez <mcgrof@suse.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 10 ++++++++++
 net/wireless/nl80211.c       | 24 ++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index fb58e654f52..b3ada0b3a27 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -261,6 +261,9 @@
  *	the regulatory core to help with compliance. A dump version of this API
  *	is now available which will returns the global regdomain as well as
  *	all private regdomains of present wiphys (for those that have it).
+ *	If a wiphy is self-managed (%NL80211_ATTR_WIPHY_SELF_MANAGED_REG), then
+ *	its private regdomain is the only valid one for it. The regulatory
+ *	core is not used to help with compliance in this case.
  * @NL80211_CMD_SET_REG: Set current regulatory domain. CRDA sends this command
  *	after being queried by the kernel. CRDA replies by sending a regulatory
  *	domain structure which consists of %NL80211_ATTR_REG_ALPHA set to our
@@ -1702,6 +1705,11 @@ enum nl80211_commands {
  *
  * @NL80211_ATTR_MAC_MASK: MAC address mask
  *
+ * @NL80211_ATTR_WIPHY_SELF_MANAGED_REG: flag attribute indicating this device
+ *	is self-managing its regulatory information and any regulatory domain
+ *	obtained from it is coming from the device's wiphy and not the global
+ *	cfg80211 regdomain.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2059,6 +2067,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_MAC_MASK,
 
+	NL80211_ATTR_WIPHY_SELF_MANAGED_REG,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index eebb7e42298..5b1907f4c18 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -396,6 +396,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 },
 	[NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 },
 	[NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN },
+	[NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG },
 };
 
 /* policy for the key attributes */
@@ -1701,6 +1702,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			       rdev->wiphy.max_num_csa_counters))
 			goto nla_put_failure;
 
+		if (rdev->wiphy.regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED &&
+		    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
+			goto nla_put_failure;
+
 		/* done */
 		state->split_start = 0;
 		break;
@@ -5406,6 +5411,8 @@ static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info)
 		goto put_failure;
 
 	if (info->attrs[NL80211_ATTR_WIPHY]) {
+		bool self_managed;
+
 		rdev = cfg80211_get_dev_from_info(genl_info_net(info), info);
 		if (IS_ERR(rdev)) {
 			nlmsg_free(msg);
@@ -5413,8 +5420,16 @@ static int nl80211_get_reg_do(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		wiphy = &rdev->wiphy;
+		self_managed = wiphy->regulatory_flags &
+			       REGULATORY_WIPHY_SELF_MANAGED;
 		regdom = get_wiphy_regdom(wiphy);
 
+		/* a self-managed-reg device must have a private regdom */
+		if (WARN_ON(!regdom && self_managed)) {
+			nlmsg_free(msg);
+			return -EINVAL;
+		}
+
 		if (regdom &&
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)))
 			goto nla_put_failure;
@@ -5471,6 +5486,10 @@ static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb,
 	    nla_put_u32(msg, NL80211_ATTR_WIPHY, get_wiphy_idx(wiphy)))
 		goto nla_put_failure;
 
+	if (wiphy && wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED &&
+	    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
+		goto nla_put_failure;
+
 	return genlmsg_end(msg, hdr);
 
 nla_put_failure:
@@ -11076,6 +11095,11 @@ static bool nl80211_reg_change_event_fill(struct sk_buff *msg,
 		if (wiphy &&
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY, request->wiphy_idx))
 			goto nla_put_failure;
+
+		if (wiphy &&
+		    wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED &&
+		    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
+			goto nla_put_failure;
 	}
 
 	return true;
-- 
cgit v1.2.3-70-g09d2


From 31a60ed1e95ab8afbadb65599bef12b195080a0c Mon Sep 17 00:00:00 2001
From: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Date: Mon, 15 Dec 2014 13:25:38 +0200
Subject: nl80211: Convert sched_scan_req pointer to RCU pointer

Because of possible races when accessing sched_scan_req pointer in
rdev, the sched_scan_req is converted to RCU pointer.

Signed-off-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  2 ++
 net/wireless/core.c    | 10 +++++++---
 net/wireless/core.h    |  2 +-
 net/wireless/nl80211.c | 19 +++++++++++--------
 net/wireless/scan.c    | 13 ++++++++-----
 5 files changed, 29 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 4bc1fc9971a..45d4d7292e5 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1516,6 +1516,7 @@ struct cfg80211_match_set {
  * @mac_addr_mask: MAC address mask used with randomisation, bits that
  *	are 0 in the mask should be randomised, bits that are 1 should
  *	be taken from the @mac_addr
+ * @rcu_head: RCU callback used to free the struct
  */
 struct cfg80211_sched_scan_request {
 	struct cfg80211_ssid *ssids;
@@ -1537,6 +1538,7 @@ struct cfg80211_sched_scan_request {
 	struct wiphy *wiphy;
 	struct net_device *dev;
 	unsigned long scan_start;
+	struct rcu_head rcu_head;
 
 	/* keep last */
 	struct ieee80211_channel *channels[0];
diff --git a/net/wireless/core.c b/net/wireless/core.c
index b661fcce7e3..0743449405c 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -867,6 +867,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 		      struct wireless_dev *wdev)
 {
 	struct net_device *dev = wdev->netdev;
+	struct cfg80211_sched_scan_request *sched_scan_req;
 
 	ASSERT_RTNL();
 	ASSERT_WDEV_LOCK(wdev);
@@ -877,7 +878,8 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_STATION:
-		if (rdev->sched_scan_req && dev == rdev->sched_scan_req->dev)
+		sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
+		if (sched_scan_req && dev == sched_scan_req->dev)
 			__cfg80211_stop_sched_scan(rdev, false);
 
 #ifdef CONFIG_CFG80211_WEXT
@@ -956,6 +958,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev;
+	struct cfg80211_sched_scan_request *sched_scan_req;
 
 	if (!wdev)
 		return NOTIFY_DONE;
@@ -1021,8 +1024,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 			___cfg80211_scan_done(rdev, false);
 		}
 
-		if (WARN_ON(rdev->sched_scan_req &&
-			    rdev->sched_scan_req->dev == wdev->netdev)) {
+		sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
+		if (WARN_ON(sched_scan_req &&
+			    sched_scan_req->dev == wdev->netdev)) {
 			__cfg80211_stop_sched_scan(rdev, false);
 		}
 
diff --git a/net/wireless/core.h b/net/wireless/core.h
index e87cae57a83..e82030c3231 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -70,7 +70,7 @@ struct cfg80211_registered_device {
 	u32 bss_generation;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
 	struct sk_buff *scan_msg;
-	struct cfg80211_sched_scan_request *sched_scan_req;
+	struct cfg80211_sched_scan_request __rcu *sched_scan_req;
 	unsigned long suspend_at;
 	struct work_struct scan_done_wk;
 	struct work_struct sched_scan_results_wk;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5b1907f4c18..bacdf22fa47 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6190,6 +6190,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	struct cfg80211_sched_scan_request *sched_scan_req;
 	int err;
 
 	if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) ||
@@ -6199,27 +6200,29 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	if (rdev->sched_scan_req)
 		return -EINPROGRESS;
 
-	rdev->sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy, wdev,
-							info->attrs);
-	err = PTR_ERR_OR_ZERO(rdev->sched_scan_req);
+	sched_scan_req = nl80211_parse_sched_scan(&rdev->wiphy, wdev,
+						  info->attrs);
+
+	err = PTR_ERR_OR_ZERO(sched_scan_req);
 	if (err)
 		goto out_err;
 
-	err = rdev_sched_scan_start(rdev, dev, rdev->sched_scan_req);
+	err = rdev_sched_scan_start(rdev, dev, sched_scan_req);
 	if (err)
 		goto out_free;
 
-	rdev->sched_scan_req->dev = dev;
-	rdev->sched_scan_req->wiphy = &rdev->wiphy;
+	sched_scan_req->dev = dev;
+	sched_scan_req->wiphy = &rdev->wiphy;
+
+	rcu_assign_pointer(rdev->sched_scan_req, sched_scan_req);
 
 	nl80211_send_sched_scan(rdev, dev,
 				NL80211_CMD_START_SCHED_SCAN);
 	return 0;
 
 out_free:
-	kfree(rdev->sched_scan_req);
+	kfree(sched_scan_req);
 out_err:
-	rdev->sched_scan_req = NULL;
 	return err;
 }
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index bda39f14981..c705c3e2b75 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -257,7 +257,7 @@ void __cfg80211_sched_scan_results(struct work_struct *wk)
 
 	rtnl_lock();
 
-	request = rdev->sched_scan_req;
+	request = rtnl_dereference(rdev->sched_scan_req);
 
 	/* we don't have sched_scan_req anymore if the scan is stopping */
 	if (request) {
@@ -279,7 +279,8 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
 {
 	trace_cfg80211_sched_scan_results(wiphy);
 	/* ignore if we're not scanning */
-	if (wiphy_to_rdev(wiphy)->sched_scan_req)
+
+	if (rcu_access_pointer(wiphy_to_rdev(wiphy)->sched_scan_req))
 		queue_work(cfg80211_wq,
 			   &wiphy_to_rdev(wiphy)->sched_scan_results_wk);
 }
@@ -308,6 +309,7 @@ EXPORT_SYMBOL(cfg80211_sched_scan_stopped);
 int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 			       bool driver_initiated)
 {
+	struct cfg80211_sched_scan_request *sched_scan_req;
 	struct net_device *dev;
 
 	ASSERT_RTNL();
@@ -315,7 +317,8 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 	if (!rdev->sched_scan_req)
 		return -ENOENT;
 
-	dev = rdev->sched_scan_req->dev;
+	sched_scan_req = rtnl_dereference(rdev->sched_scan_req);
+	dev = sched_scan_req->dev;
 
 	if (!driver_initiated) {
 		int err = rdev_sched_scan_stop(rdev, dev);
@@ -325,8 +328,8 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 
 	nl80211_send_sched_scan(rdev, dev, NL80211_CMD_SCHED_SCAN_STOPPED);
 
-	kfree(rdev->sched_scan_req);
-	rdev->sched_scan_req = NULL;
+	RCU_INIT_POINTER(rdev->sched_scan_req, NULL);
+	kfree_rcu(sched_scan_req, rcu_head);
 
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From 93a1e86ce10e4898f9ca9cd09d659a8a7780ee5e Mon Sep 17 00:00:00 2001
From: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Date: Mon, 15 Dec 2014 13:25:39 +0200
Subject: nl80211: Stop scheduled scan if netlink client disappears

An attribute NL80211_ATTR_SOCKET_OWNER can be set by the scan initiator.
If present, the attribute will cause the scan to be stopped if the client
dies.

Signed-off-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  3 +++
 include/uapi/linux/nl80211.h |  3 +++
 net/wireless/core.c          | 16 ++++++++++++++++
 net/wireless/core.h          |  2 ++
 net/wireless/nl80211.c       | 16 ++++++++++++++++
 5 files changed, 40 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 45d4d7292e5..bd672ea08c9 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1517,6 +1517,8 @@ struct cfg80211_match_set {
  *	are 0 in the mask should be randomised, bits that are 1 should
  *	be taken from the @mac_addr
  * @rcu_head: RCU callback used to free the struct
+ * @owner_nlportid: netlink portid of owner (if this should is a request
+ *	owned by a particular socket)
  */
 struct cfg80211_sched_scan_request {
 	struct cfg80211_ssid *ssids;
@@ -1539,6 +1541,7 @@ struct cfg80211_sched_scan_request {
 	struct net_device *dev;
 	unsigned long scan_start;
 	struct rcu_head rcu_head;
+	u32 owner_nlportid;
 
 	/* keep last */
 	struct ieee80211_channel *channels[0];
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index b3ada0b3a27..c0383e98354 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1672,6 +1672,9 @@ enum nl80211_commands {
  * @NL80211_ATTR_SOCKET_OWNER: Flag attribute, if set during interface
  *	creation then the new interface will be owned by the netlink socket
  *	that created it and will be destroyed when the socket is closed.
+ *	If set during scheduled scan start then the new scan req will be
+ *	owned by the netlink socket that created it and the scheduled scan will
+ *	be stopped when the socket is closed.
  *
  * @NL80211_ATTR_TDLS_INITIATOR: flag attribute indicating the current end is
  *	the TDLS link initiator.
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 0743449405c..456e4c38c27 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -321,6 +321,20 @@ static void cfg80211_destroy_iface_wk(struct work_struct *work)
 	rtnl_unlock();
 }
 
+static void cfg80211_sched_scan_stop_wk(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	rdev = container_of(work, struct cfg80211_registered_device,
+			   sched_scan_stop_wk);
+
+	rtnl_lock();
+
+	__cfg80211_stop_sched_scan(rdev, false);
+
+	rtnl_unlock();
+}
+
 /* exported functions */
 
 struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
@@ -407,6 +421,7 @@ use_default_name:
 	INIT_LIST_HEAD(&rdev->destroy_list);
 	spin_lock_init(&rdev->destroy_list_lock);
 	INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk);
+	INIT_WORK(&rdev->sched_scan_stop_wk, cfg80211_sched_scan_stop_wk);
 
 #ifdef CONFIG_CFG80211_DEFAULT_PS
 	rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -787,6 +802,7 @@ void wiphy_unregister(struct wiphy *wiphy)
 	flush_work(&rdev->event_work);
 	cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
 	flush_work(&rdev->destroy_work);
+	flush_work(&rdev->sched_scan_stop_wk);
 
 #ifdef CONFIG_PM
 	if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup)
diff --git a/net/wireless/core.h b/net/wireless/core.h
index e82030c3231..801cd49c5a0 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -91,6 +91,8 @@ struct cfg80211_registered_device {
 	struct list_head destroy_list;
 	struct work_struct destroy_work;
 
+	struct work_struct sched_scan_stop_wk;
+
 	/* must be last because of the way we do wiphy_priv(),
 	 * and it should at least be aligned to NETDEV_ALIGN */
 	struct wiphy wiphy __aligned(NETDEV_ALIGN);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index bacdf22fa47..702920134b3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6214,6 +6214,9 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
 	sched_scan_req->dev = dev;
 	sched_scan_req->wiphy = &rdev->wiphy;
 
+	if (info->attrs[NL80211_ATTR_SOCKET_OWNER])
+		sched_scan_req->owner_nlportid = info->snd_portid;
+
 	rcu_assign_pointer(rdev->sched_scan_req, sched_scan_req);
 
 	nl80211_send_sched_scan(rdev, dev,
@@ -12618,6 +12621,13 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 
 	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
 		bool schedule_destroy_work = false;
+		bool schedule_scan_stop = false;
+		struct cfg80211_sched_scan_request *sched_scan_req =
+			rcu_dereference(rdev->sched_scan_req);
+
+		if (sched_scan_req && notify->portid &&
+		    sched_scan_req->owner_nlportid == notify->portid)
+			schedule_scan_stop = true;
 
 		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) {
 			cfg80211_mlme_unregister_socket(wdev, notify->portid);
@@ -12648,6 +12658,12 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 				spin_unlock(&rdev->destroy_list_lock);
 				schedule_work(&rdev->destroy_work);
 			}
+		} else if (schedule_scan_stop) {
+			sched_scan_req->owner_nlportid = 0;
+
+			if (rdev->ops->sched_scan_stop &&
+			    rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+				schedule_work(&rdev->sched_scan_stop_wk);
 		}
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 79f241b41b5f581c6be66785ab8b9c8e3b1651c7 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Wed, 17 Dec 2014 18:00:44 +0200
Subject: nl80211: increase the max number of rules in regdomain

Some network cards (Intel) produce per-channel regdomains and rely on
cfg80211 to merge rules as needed. This hits the max rules limit and
fails.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index c0383e98354..18cb0aa0635 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2112,7 +2112,7 @@ enum nl80211_attrs {
 
 #define NL80211_MAX_SUPP_RATES			32
 #define NL80211_MAX_SUPP_HT_RATES		77
-#define NL80211_MAX_SUPP_REG_RULES		32
+#define NL80211_MAX_SUPP_REG_RULES		64
 #define NL80211_TKIP_DATA_OFFSET_ENCR_KEY	0
 #define NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY	16
 #define NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY	24
-- 
cgit v1.2.3-70-g09d2


From b40d6376ff470572e2fafb20ca06a68f2d7940cb Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 10 Dec 2014 15:33:11 +0100
Subject: nl802154: introduce cca mode enums

This patch adds enums for 802.15.4 specific CCA settings.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/nl802154.h | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'include')

diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 6dbd406ca41..86c1b2f15b5 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -119,4 +119,47 @@ enum nl802154_iftype {
 	NL802154_IFTYPE_MAX = NUM_NL802154_IFTYPES - 1
 };
 
+/**
+ * enum nl802154_cca_modes - cca modes
+ *
+ * @__NL802154_CCA_INVALID: cca mode number 0 is reserved
+ * @NL802154_CCA_ENERGY: Energy above threshold
+ * @NL802154_CCA_CARRIER: Carrier sense only
+ * @NL802154_CCA_ENERGY_CARRIER: Carrier sense with energy above threshold
+ * @NL802154_CCA_ALOHA: CCA shall always report an idle medium
+ * @NL802154_CCA_UWB_SHR: UWB preamble sense based on the SHR of a frame
+ * @NL802154_CCA_UWB_MULTIPEXED: UWB preamble sense based on the packet with
+ *	the multiplexed preamble
+ * @__NL802154_CCA_ATTR_AFTER_LAST: Internal
+ * @NL802154_CCA_ATTR_MAX: Maximum CCA attribute number
+ */
+enum nl802154_cca_modes {
+	__NL802154_CCA_INVALID,
+	NL802154_CCA_ENERGY,
+	NL802154_CCA_CARRIER,
+	NL802154_CCA_ENERGY_CARRIER,
+	NL802154_CCA_ALOHA,
+	NL802154_CCA_UWB_SHR,
+	NL802154_CCA_UWB_MULTIPEXED,
+
+	/* keep last */
+	__NL802154_CCA_ATTR_AFTER_LAST,
+	NL802154_CCA_ATTR_MAX = __NL802154_CCA_ATTR_AFTER_LAST - 1
+};
+
+/**
+ * enum nl802154_cca_opts - additional options for cca modes
+ *
+ * @NL802154_CCA_OPT_ENERGY_CARRIER_OR: NL802154_CCA_ENERGY_CARRIER with OR
+ * @NL802154_CCA_OPT_ENERGY_CARRIER_AND: NL802154_CCA_ENERGY_CARRIER with AND
+ */
+enum nl802154_cca_opts {
+	NL802154_CCA_OPT_ENERGY_CARRIER_AND,
+	NL802154_CCA_OPT_ENERGY_CARRIER_OR,
+
+	/* keep last */
+	__NL802154_CCA_OPT_ATTR_AFTER_LAST,
+	NL802154_CCA_OPT_ATTR_MAX = __NL802154_CCA_OPT_ATTR_AFTER_LAST - 1
+};
+
 #endif /* __NL802154_H */
-- 
cgit v1.2.3-70-g09d2


From 7fe9a3882bb37195c41ab125a0f2852398d2646a Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 10 Dec 2014 15:33:12 +0100
Subject: ieee802154: rework cca setting

The current cca setting handle is a driver specific call. We need to
introduce some 802.15.4 specific layer and mapping 802.15.4 cca modes to
driver specific ones inside the 802.15.4 driver. This patch will add
such 802.15.4 layer and mapping the cca settings to driver specific ones.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/net/ieee802154/at86rf230.c | 30 ++++++++++++++++++++++++++++--
 include/net/cfg802154.h            |  7 ++++++-
 include/net/ieee802154_netdev.h    |  4 +++-
 include/net/mac802154.h            |  5 ++++-
 net/ieee802154/nl-mac.c            |  4 ++--
 net/ieee802154/nl802154.c          |  2 +-
 net/ieee802154/sysfs.c             |  2 +-
 net/mac802154/driver-ops.h         |  5 +++--
 net/mac802154/mac_cmd.c            |  6 +++---
 9 files changed, 51 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 1c0135620c6..1ac46ba41fd 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -1146,11 +1146,37 @@ at86rf230_set_lbt(struct ieee802154_hw *hw, bool on)
 }
 
 static int
-at86rf230_set_cca_mode(struct ieee802154_hw *hw, u8 mode)
+at86rf230_set_cca_mode(struct ieee802154_hw *hw,
+		       const struct wpan_phy_cca *cca)
 {
 	struct at86rf230_local *lp = hw->priv;
+	u8 val;
 
-	return at86rf230_write_subreg(lp, SR_CCA_MODE, mode);
+	/* mapping 802.15.4 to driver spec */
+	switch (cca->mode) {
+	case NL802154_CCA_ENERGY:
+		val = 1;
+		break;
+	case NL802154_CCA_CARRIER:
+		val = 2;
+		break;
+	case NL802154_CCA_ENERGY_CARRIER:
+		switch (cca->opt) {
+		case NL802154_CCA_OPT_ENERGY_CARRIER_AND:
+			val = 3;
+			break;
+		case NL802154_CCA_OPT_ENERGY_CARRIER_OR:
+			val = 0;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return at86rf230_write_subreg(lp, SR_CCA_MODE, val);
 }
 
 static int
diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 7f713acfa10..6ee2618ac78 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -56,6 +56,11 @@ struct cfg802154_ops {
 				struct wpan_dev *wpan_dev, bool mode);
 };
 
+struct wpan_phy_cca {
+	enum nl802154_cca_modes mode;
+	enum nl802154_cca_opts opt;
+};
+
 struct wpan_phy {
 	struct mutex pib_lock;
 
@@ -76,7 +81,7 @@ struct wpan_phy {
 	u8 current_page;
 	u32 channels_supported[IEEE802154_MAX_PAGE + 1];
 	s8 transmit_power;
-	u8 cca_mode;
+	struct wpan_phy_cca cca;
 
 	__le64 perm_extended_addr;
 
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 83bb8a73d23..94a29705244 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -28,6 +28,8 @@
 #include <linux/skbuff.h>
 #include <linux/ieee802154.h>
 
+#include <net/cfg802154.h>
+
 struct ieee802154_sechdr {
 #if defined(__LITTLE_ENDIAN_BITFIELD)
 	u8 level:3,
@@ -337,7 +339,7 @@ struct ieee802154_mac_params {
 	s8 frame_retries;
 
 	bool lbt;
-	u8 cca_mode;
+	struct wpan_phy_cca cca;
 	s32 cca_ed_level;
 };
 
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index c823d910b46..85064781174 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -20,6 +20,8 @@
 #include <linux/ieee802154.h>
 #include <linux/skbuff.h>
 
+#include <net/cfg802154.h>
+
 /* General MAC frame format:
  *  2 bytes: Frame Control
  *  1 byte:  Sequence Number
@@ -212,7 +214,8 @@ struct ieee802154_ops {
 					    unsigned long changed);
 	int		(*set_txpower)(struct ieee802154_hw *hw, int db);
 	int		(*set_lbt)(struct ieee802154_hw *hw, bool on);
-	int		(*set_cca_mode)(struct ieee802154_hw *hw, u8 mode);
+	int		(*set_cca_mode)(struct ieee802154_hw *hw,
+					const struct wpan_phy_cca *cca);
 	int		(*set_cca_ed_level)(struct ieee802154_hw *hw,
 					    s32 level);
 	int		(*set_csma_params)(struct ieee802154_hw *hw,
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index cd919493c97..3c902e9516f 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -121,7 +121,7 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 			       params.transmit_power) ||
 		    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) ||
 		    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE,
-			       params.cca_mode) ||
+			       params.cca.mode) ||
 		    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL,
 				params.cca_ed_level) ||
 		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES,
@@ -516,7 +516,7 @@ int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
 		params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]);
 
 	if (info->attrs[IEEE802154_ATTR_CCA_MODE])
-		params.cca_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
+		params.cca.mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
 
 	if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL])
 		params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 88964774469..1efbe425002 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -291,7 +291,7 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev,
 
 	/* cca mode */
 	if (nla_put_u8(msg, NL802154_ATTR_CCA_MODE,
-		       rdev->wpan_phy.cca_mode))
+		       rdev->wpan_phy.cca.mode))
 		goto nla_put_failure;
 
 	if (nla_put_s8(msg, NL802154_ATTR_TX_POWER,
diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c
index 1613b9c65df..dff55c2d87f 100644
--- a/net/ieee802154/sysfs.c
+++ b/net/ieee802154/sysfs.c
@@ -68,7 +68,7 @@ static DEVICE_ATTR_RO(name)
 MASTER_SHOW(current_channel, "%d");
 MASTER_SHOW(current_page, "%d");
 MASTER_SHOW(transmit_power, "%d +- 1 dB");
-MASTER_SHOW(cca_mode, "%d");
+MASTER_SHOW_COMPLEX(cca_mode, "%d", phy->cca.mode);
 
 static ssize_t channels_supported_show(struct device *dev,
 				       struct device_attribute *attr,
diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h
index f21e864613d..98180a9fff4 100644
--- a/net/mac802154/driver-ops.h
+++ b/net/mac802154/driver-ops.h
@@ -70,7 +70,8 @@ static inline int drv_set_tx_power(struct ieee802154_local *local, s8 dbm)
 	return local->ops->set_txpower(&local->hw, dbm);
 }
 
-static inline int drv_set_cca_mode(struct ieee802154_local *local, u8 cca_mode)
+static inline int drv_set_cca_mode(struct ieee802154_local *local,
+				   const struct wpan_phy_cca *cca)
 {
 	might_sleep();
 
@@ -79,7 +80,7 @@ static inline int drv_set_cca_mode(struct ieee802154_local *local, u8 cca_mode)
 		return -EOPNOTSUPP;
 	}
 
-	return local->ops->set_cca_mode(&local->hw, cca_mode);
+	return local->ops->set_cca_mode(&local->hw, cca);
 }
 
 static inline int drv_set_lbt_mode(struct ieee802154_local *local, bool mode)
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index 6aacb181688..bdccb4ecd30 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -81,7 +81,7 @@ static int mac802154_set_mac_params(struct net_device *dev,
 
 	/* PHY */
 	wpan_dev->wpan_phy->transmit_power = params->transmit_power;
-	wpan_dev->wpan_phy->cca_mode = params->cca_mode;
+	wpan_dev->wpan_phy->cca = params->cca;
 	wpan_dev->wpan_phy->cca_ed_level = params->cca_ed_level;
 
 	/* MAC */
@@ -98,7 +98,7 @@ static int mac802154_set_mac_params(struct net_device *dev,
 	}
 
 	if (local->hw.flags & IEEE802154_HW_CCA_MODE) {
-		ret = drv_set_cca_mode(local, params->cca_mode);
+		ret = drv_set_cca_mode(local, &params->cca);
 		if (ret < 0)
 			return ret;
 	}
@@ -122,7 +122,7 @@ static void mac802154_get_mac_params(struct net_device *dev,
 
 	/* PHY */
 	params->transmit_power = wpan_dev->wpan_phy->transmit_power;
-	params->cca_mode = wpan_dev->wpan_phy->cca_mode;
+	params->cca = wpan_dev->wpan_phy->cca;
 	params->cca_ed_level = wpan_dev->wpan_phy->cca_ed_level;
 
 	/* MAC */
-- 
cgit v1.2.3-70-g09d2


From ba2a9506a76450568cbc0d51626d94cf8528c0c7 Mon Sep 17 00:00:00 2001
From: Alexander Aring <alex.aring@gmail.com>
Date: Wed, 10 Dec 2014 15:33:13 +0100
Subject: nl802154: introduce support for cca settings

This patch adds support for setting cca parameters via nl802154.

Signed-off-by: Alexander Aring <alex.aring@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/cfg802154.h   |  3 +++
 include/net/nl802154.h    |  2 +-
 net/ieee802154/nl802154.c | 46 +++++++++++++++++++++++++++++++++++++++++++---
 net/ieee802154/rdev-ops.h |  7 +++++++
 net/mac802154/cfg.c       | 21 +++++++++++++++++++++
 5 files changed, 75 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h
index 6ee2618ac78..eeda6765276 100644
--- a/include/net/cfg802154.h
+++ b/include/net/cfg802154.h
@@ -25,6 +25,7 @@
 #include <net/nl802154.h>
 
 struct wpan_phy;
+struct wpan_phy_cca;
 
 struct cfg802154_ops {
 	struct net_device * (*add_virtual_intf_deprecated)(struct wpan_phy *wpan_phy,
@@ -39,6 +40,8 @@ struct cfg802154_ops {
 	int	(*del_virtual_intf)(struct wpan_phy *wpan_phy,
 				    struct wpan_dev *wpan_dev);
 	int	(*set_channel)(struct wpan_phy *wpan_phy, u8 page, u8 channel);
+	int	(*set_cca_mode)(struct wpan_phy *wpan_phy,
+				const struct wpan_phy_cca *cca);
 	int	(*set_pan_id)(struct wpan_phy *wpan_phy,
 			      struct wpan_dev *wpan_dev, __le16 pan_id);
 	int	(*set_short_addr)(struct wpan_phy *wpan_phy,
diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 86c1b2f15b5..f8b5bc99795 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -82,7 +82,7 @@ enum nl802154_attrs {
 	NL802154_ATTR_TX_POWER,
 
 	NL802154_ATTR_CCA_MODE,
-	NL802154_ATTR_CCA_MODE3_AND,
+	NL802154_ATTR_CCA_OPT,
 	NL802154_ATTR_CCA_ED_LEVEL,
 
 	NL802154_ATTR_MAX_FRAME_RETRIES,
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 1efbe425002..a25b9bbd077 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -209,7 +209,8 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = {
 
 	[NL802154_ATTR_TX_POWER] = { .type = NLA_S8, },
 
-	[NL802154_ATTR_CCA_MODE] = { .type = NLA_U8, },
+	[NL802154_ATTR_CCA_MODE] = { .type = NLA_U32, },
+	[NL802154_ATTR_CCA_OPT] = { .type = NLA_U32, },
 
 	[NL802154_ATTR_SUPPORTED_CHANNEL] = { .type = NLA_U32, },
 
@@ -290,10 +291,16 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev,
 		goto nla_put_failure;
 
 	/* cca mode */
-	if (nla_put_u8(msg, NL802154_ATTR_CCA_MODE,
-		       rdev->wpan_phy.cca.mode))
+	if (nla_put_u32(msg, NL802154_ATTR_CCA_MODE,
+			rdev->wpan_phy.cca.mode))
 		goto nla_put_failure;
 
+	if (rdev->wpan_phy.cca.mode == NL802154_CCA_ENERGY_CARRIER) {
+		if (nla_put_u32(msg, NL802154_ATTR_CCA_OPT,
+				rdev->wpan_phy.cca.opt))
+			goto nla_put_failure;
+	}
+
 	if (nla_put_s8(msg, NL802154_ATTR_TX_POWER,
 		       rdev->wpan_phy.transmit_power))
 		goto nla_put_failure;
@@ -622,6 +629,31 @@ static int nl802154_set_channel(struct sk_buff *skb, struct genl_info *info)
 	return rdev_set_channel(rdev, page, channel);
 }
 
+static int nl802154_set_cca_mode(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg802154_registered_device *rdev = info->user_ptr[0];
+	struct wpan_phy_cca cca;
+
+	if (!info->attrs[NL802154_ATTR_CCA_MODE])
+		return -EINVAL;
+
+	cca.mode = nla_get_u32(info->attrs[NL802154_ATTR_CCA_MODE]);
+	/* checking 802.15.4 constraints */
+	if (cca.mode < NL802154_CCA_ENERGY || cca.mode > NL802154_CCA_ATTR_MAX)
+		return -EINVAL;
+
+	if (cca.mode == NL802154_CCA_ENERGY_CARRIER) {
+		if (!info->attrs[NL802154_ATTR_CCA_OPT])
+			return -EINVAL;
+
+		cca.opt = nla_get_u32(info->attrs[NL802154_ATTR_CCA_OPT]);
+		if (cca.opt > NL802154_CCA_OPT_ATTR_MAX)
+			return -EINVAL;
+	}
+
+	return rdev_set_cca_mode(rdev, &cca);
+}
+
 static int nl802154_set_pan_id(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg802154_registered_device *rdev = info->user_ptr[0];
@@ -894,6 +926,14 @@ static const struct genl_ops nl802154_ops[] = {
 		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
 				  NL802154_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL802154_CMD_SET_CCA_MODE,
+		.doit = nl802154_set_cca_mode,
+		.policy = nl802154_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = NL802154_FLAG_NEED_WPAN_PHY |
+				  NL802154_FLAG_NEED_RTNL,
+	},
 	{
 		.cmd = NL802154_CMD_SET_PAN_ID,
 		.doit = nl802154_set_pan_id,
diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h
index aff54fbd926..7c46732fad2 100644
--- a/net/ieee802154/rdev-ops.h
+++ b/net/ieee802154/rdev-ops.h
@@ -41,6 +41,13 @@ rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel)
 	return rdev->ops->set_channel(&rdev->wpan_phy, page, channel);
 }
 
+static inline int
+rdev_set_cca_mode(struct cfg802154_registered_device *rdev,
+		  const struct wpan_phy_cca *cca)
+{
+	return rdev->ops->set_cca_mode(&rdev->wpan_phy, cca);
+}
+
 static inline int
 rdev_set_pan_id(struct cfg802154_registered_device *rdev,
 		struct wpan_dev *wpan_dev, __le16 pan_id)
diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c
index c035708ada1..7d31da503dc 100644
--- a/net/mac802154/cfg.c
+++ b/net/mac802154/cfg.c
@@ -86,6 +86,26 @@ ieee802154_set_channel(struct wpan_phy *wpan_phy, u8 page, u8 channel)
 	return ret;
 }
 
+static int
+ieee802154_set_cca_mode(struct wpan_phy *wpan_phy,
+			const struct wpan_phy_cca *cca)
+{
+	struct ieee802154_local *local = wpan_phy_priv(wpan_phy);
+	int ret;
+
+	ASSERT_RTNL();
+
+	/* check if phy support this setting */
+	if (!(local->hw.flags & IEEE802154_HW_CCA_MODE))
+		return -EOPNOTSUPP;
+
+	ret = drv_set_cca_mode(local, cca);
+	if (!ret)
+		wpan_phy->cca = *cca;
+
+	return ret;
+}
+
 static int
 ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev,
 		      __le16 pan_id)
@@ -201,6 +221,7 @@ const struct cfg802154_ops mac802154_config_ops = {
 	.add_virtual_intf = ieee802154_add_iface,
 	.del_virtual_intf = ieee802154_del_iface,
 	.set_channel = ieee802154_set_channel,
+	.set_cca_mode = ieee802154_set_cca_mode,
 	.set_pan_id = ieee802154_set_pan_id,
 	.set_short_addr = ieee802154_set_short_addr,
 	.set_backoff_exponent = ieee802154_set_backoff_exponent,
-- 
cgit v1.2.3-70-g09d2


From cab9e3a0559c039b4e13b569fcf393618c661902 Mon Sep 17 00:00:00 2001
From: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Date: Fri, 19 Dec 2014 10:39:08 +0200
Subject: Bluetooth: 6lowpan: Add IPSP PSM value

The Internet Protocol Support Profile a.k.a BT 6LoWPAN specification
is ready so PSM value for it is now known.

Signed-off-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/l2cap.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index d1bb342d083..2239a375309 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -248,6 +248,7 @@ struct l2cap_conn_rsp {
 #define L2CAP_PSM_SDP		0x0001
 #define L2CAP_PSM_RFCOMM	0x0003
 #define L2CAP_PSM_3DSP		0x0021
+#define L2CAP_PSM_IPSP		0x0023 /* 6LoWPAN */
 
 /* channel identifier */
 #define L2CAP_CID_SIGNALING	0x0001
-- 
cgit v1.2.3-70-g09d2


From 1d2dc5b7b32393bb2d818e0de82a66b1a654d329 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 19 Dec 2014 13:40:19 +0200
Subject: Bluetooth: Split hci_update_page_scan into two functions

To keep the parameter list and its semantics clear it makes sense to
split the hci_update_page_scan function into two separate functions: one
taking a hci_dev and another taking a hci_request. The one taking a
hci_dev constructs its own hci_request and then calls the other
function.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  3 ++-
 net/bluetooth/hci_core.c         | 17 ++++++++++++-----
 net/bluetooth/hci_event.c        |  4 ++--
 net/bluetooth/mgmt.c             | 16 ++++++++--------
 4 files changed, 24 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3c7827005c2..664451a64d7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1306,7 +1306,8 @@ bool hci_req_pending(struct hci_dev *hdev);
 void hci_req_add_le_scan_disable(struct hci_request *req);
 void hci_req_add_le_passive_scan(struct hci_request *req);
 
-void hci_update_page_scan(struct hci_dev *hdev, struct hci_request *req);
+void hci_update_page_scan(struct hci_dev *hdev);
+void __hci_update_page_scan(struct hci_request *req);
 
 struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen,
 			       const void *param, u32 timeout);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 5dcacf9607e..3aa9015a885 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -5787,8 +5787,9 @@ static bool disconnected_whitelist_entries(struct hci_dev *hdev)
 	return false;
 }
 
-void hci_update_page_scan(struct hci_dev *hdev, struct hci_request *req)
+void __hci_update_page_scan(struct hci_request *req)
 {
+	struct hci_dev *hdev = req->hdev;
 	u8 scan;
 
 	if (!test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags))
@@ -5812,8 +5813,14 @@ void hci_update_page_scan(struct hci_dev *hdev, struct hci_request *req)
 	if (test_bit(HCI_DISCOVERABLE, &hdev->dev_flags))
 		scan |= SCAN_INQUIRY;
 
-	if (req)
-		hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
-	else
-		hci_send_cmd(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+	hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
+}
+
+void hci_update_page_scan(struct hci_dev *hdev)
+{
+	struct hci_request req;
+
+	hci_req_init(&req, hdev);
+	__hci_update_page_scan(&req);
+	hci_req_run(&req, NULL);
 }
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 39a5c8a0172..65f4ec8945a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2127,7 +2127,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			hci_send_cmd(hdev, HCI_OP_READ_REMOTE_FEATURES,
 				     sizeof(cp), &cp);
 
-			hci_update_page_scan(hdev, NULL);
+			hci_update_page_scan(hdev);
 		}
 
 		/* Set packet type for incoming connection */
@@ -2308,7 +2308,7 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		if (test_bit(HCI_CONN_FLUSH_KEY, &conn->flags))
 			hci_remove_link_key(hdev, &conn->dst);
 
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 	}
 
 	params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 693ce8bcd06..f86f3ec684b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1566,7 +1566,7 @@ static void set_discoverable_complete(struct hci_dev *hdev, u8 status)
 	 * entries.
 	 */
 	hci_req_init(&req, hdev);
-	hci_update_page_scan(hdev, &req);
+	__hci_update_page_scan(&req);
 	update_class(&req);
 	hci_req_run(&req, NULL);
 
@@ -1813,7 +1813,7 @@ static void set_connectable_complete(struct hci_dev *hdev, u8 status)
 
 	if (conn_changed || discov_changed) {
 		new_settings(hdev, cmd->sk);
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 		if (discov_changed)
 			mgmt_update_adv_data(hdev);
 		hci_update_background_scan(hdev);
@@ -1847,7 +1847,7 @@ static int set_connectable_update_settings(struct hci_dev *hdev,
 		return err;
 
 	if (changed) {
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 		hci_update_background_scan(hdev);
 		return new_settings(hdev, sk);
 	}
@@ -4697,7 +4697,7 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	hci_req_init(&req, hdev);
 
 	write_fast_connectable(&req, false);
-	hci_update_page_scan(hdev, &req);
+	__hci_update_page_scan(&req);
 
 	/* Since only the advertising data flags will change, there
 	 * is no need to update the scan response data.
@@ -5473,7 +5473,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 		if (err)
 			goto unlock;
 
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 
 		goto added;
 	}
@@ -5556,7 +5556,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 				goto unlock;
 			}
 
-			hci_update_page_scan(hdev, NULL);
+			hci_update_page_scan(hdev);
 
 			device_removed(sk, hdev, &cp->addr.bdaddr,
 				       cp->addr.type);
@@ -5607,7 +5607,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev,
 			kfree(b);
 		}
 
-		hci_update_page_scan(hdev, NULL);
+		hci_update_page_scan(hdev);
 
 		list_for_each_entry_safe(p, tmp, &hdev->le_conn_params, list) {
 			if (p->auto_connect == HCI_AUTO_CONN_DISABLED)
@@ -6139,7 +6139,7 @@ static int powered_update_hci(struct hci_dev *hdev)
 
 	if (lmp_bredr_capable(hdev)) {
 		write_fast_connectable(&req, false);
-		hci_update_page_scan(hdev, &req);
+		__hci_update_page_scan(&req);
 		update_class(&req);
 		update_name(&req);
 		update_eir(&req);
-- 
cgit v1.2.3-70-g09d2


From 0857dd3bed62d8f905f61a399d1ed76464b5270f Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 19 Dec 2014 13:40:20 +0200
Subject: Bluetooth: Split hci_request helpers to hci_request.[ch]

None of the hci_request related things in net/bluetooth/hci_core.h are
needed anywhere outside of the core bluetooth module. This patch creates
a new net/bluetooth/hci_request.c file with its corresponding h-file and
moves the functionality there from hci_core.c and hci_core.h.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  25 ---
 net/bluetooth/Makefile           |   2 +-
 net/bluetooth/hci_conn.c         |   1 +
 net/bluetooth/hci_core.c         | 370 +-----------------------------------
 net/bluetooth/hci_event.c        |   1 +
 net/bluetooth/hci_request.c      | 397 +++++++++++++++++++++++++++++++++++++++
 net/bluetooth/hci_request.h      |  51 +++++
 net/bluetooth/mgmt.c             |   1 +
 8 files changed, 453 insertions(+), 395 deletions(-)
 create mode 100644 net/bluetooth/hci_request.c
 create mode 100644 net/bluetooth/hci_request.h

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 664451a64d7..93066f70f8a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1284,31 +1284,8 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency,
 int hci_register_cb(struct hci_cb *hcb);
 int hci_unregister_cb(struct hci_cb *hcb);
 
-struct hci_request {
-	struct hci_dev		*hdev;
-	struct sk_buff_head	cmd_q;
-
-	/* If something goes wrong when building the HCI request, the error
-	 * value is stored in this field.
-	 */
-	int			err;
-};
-
-void hci_req_init(struct hci_request *req, struct hci_dev *hdev);
-int hci_req_run(struct hci_request *req, hci_req_complete_t complete);
-void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
-		 const void *param);
-void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
-		    const void *param, u8 event);
-void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status);
 bool hci_req_pending(struct hci_dev *hdev);
 
-void hci_req_add_le_scan_disable(struct hci_request *req);
-void hci_req_add_le_passive_scan(struct hci_request *req);
-
-void hci_update_page_scan(struct hci_dev *hdev);
-void __hci_update_page_scan(struct hci_request *req);
-
 struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen,
 			       const void *param, u32 timeout);
 struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
@@ -1418,8 +1395,6 @@ u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency,
 void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand,
 							__u8 ltk[16]);
 
-int hci_update_random_address(struct hci_request *req, bool require_privacy,
-			      u8 *own_addr_type);
 void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			       u8 *bdaddr_type);
 
diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile
index a5432a6a0ae..0a176fc9e29 100644
--- a/net/bluetooth/Makefile
+++ b/net/bluetooth/Makefile
@@ -13,6 +13,6 @@ bluetooth_6lowpan-y := 6lowpan.o
 
 bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \
 	hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o sco.o lib.o \
-	a2mp.o amp.o ecc.o
+	a2mp.o amp.o ecc.o hci_request.o
 
 subdir-ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index fe18825cc8a..4405fb352c7 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -30,6 +30,7 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/l2cap.h>
 
+#include "hci_request.h"
 #include "smp.h"
 #include "a2mp.h"
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 3aa9015a885..2cfaaa6acb0 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -37,6 +37,7 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
+#include "hci_request.h"
 #include "smp.h"
 
 static void hci_rx_work(struct work_struct *work);
@@ -3901,112 +3902,6 @@ static void le_scan_disable_work(struct work_struct *work)
 		BT_ERR("Disable LE scanning request failed: err %d", err);
 }
 
-static void set_random_addr(struct hci_request *req, bdaddr_t *rpa)
-{
-	struct hci_dev *hdev = req->hdev;
-
-	/* If we're advertising or initiating an LE connection we can't
-	 * go ahead and change the random address at this time. This is
-	 * because the eventual initiator address used for the
-	 * subsequently created connection will be undefined (some
-	 * controllers use the new address and others the one we had
-	 * when the operation started).
-	 *
-	 * In this kind of scenario skip the update and let the random
-	 * address be updated at the next cycle.
-	 */
-	if (test_bit(HCI_LE_ADV, &hdev->dev_flags) ||
-	    hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) {
-		BT_DBG("Deferring random address update");
-		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
-		return;
-	}
-
-	hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa);
-}
-
-int hci_update_random_address(struct hci_request *req, bool require_privacy,
-			      u8 *own_addr_type)
-{
-	struct hci_dev *hdev = req->hdev;
-	int err;
-
-	/* If privacy is enabled use a resolvable private address. If
-	 * current RPA has expired or there is something else than
-	 * the current RPA in use, then generate a new one.
-	 */
-	if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) {
-		int to;
-
-		*own_addr_type = ADDR_LE_DEV_RANDOM;
-
-		if (!test_and_clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags) &&
-		    !bacmp(&hdev->random_addr, &hdev->rpa))
-			return 0;
-
-		err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa);
-		if (err < 0) {
-			BT_ERR("%s failed to generate new RPA", hdev->name);
-			return err;
-		}
-
-		set_random_addr(req, &hdev->rpa);
-
-		to = msecs_to_jiffies(hdev->rpa_timeout * 1000);
-		queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, to);
-
-		return 0;
-	}
-
-	/* In case of required privacy without resolvable private address,
-	 * use an non-resolvable private address. This is useful for active
-	 * scanning and non-connectable advertising.
-	 */
-	if (require_privacy) {
-		bdaddr_t nrpa;
-
-		while (true) {
-			/* The non-resolvable private address is generated
-			 * from random six bytes with the two most significant
-			 * bits cleared.
-			 */
-			get_random_bytes(&nrpa, 6);
-			nrpa.b[5] &= 0x3f;
-
-			/* The non-resolvable private address shall not be
-			 * equal to the public address.
-			 */
-			if (bacmp(&hdev->bdaddr, &nrpa))
-				break;
-		}
-
-		*own_addr_type = ADDR_LE_DEV_RANDOM;
-		set_random_addr(req, &nrpa);
-		return 0;
-	}
-
-	/* If forcing static address is in use or there is no public
-	 * address use the static address as random address (but skip
-	 * the HCI command if the current random address is already the
-	 * static one.
-	 */
-	if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) ||
-	    !bacmp(&hdev->bdaddr, BDADDR_ANY)) {
-		*own_addr_type = ADDR_LE_DEV_RANDOM;
-		if (bacmp(&hdev->static_addr, &hdev->random_addr))
-			hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
-				    &hdev->static_addr);
-		return 0;
-	}
-
-	/* Neither privacy nor static address is being used so use a
-	 * public address.
-	 */
-	*own_addr_type = ADDR_LE_DEV_PUBLIC;
-
-	return 0;
-}
-
 /* Copy the Identity Address of the controller.
  *
  * If the controller has a public BD_ADDR, then by default use that one.
@@ -4539,76 +4434,11 @@ static void hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 }
 
-void hci_req_init(struct hci_request *req, struct hci_dev *hdev)
-{
-	skb_queue_head_init(&req->cmd_q);
-	req->hdev = hdev;
-	req->err = 0;
-}
-
-int hci_req_run(struct hci_request *req, hci_req_complete_t complete)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct sk_buff *skb;
-	unsigned long flags;
-
-	BT_DBG("length %u", skb_queue_len(&req->cmd_q));
-
-	/* If an error occurred during request building, remove all HCI
-	 * commands queued on the HCI request queue.
-	 */
-	if (req->err) {
-		skb_queue_purge(&req->cmd_q);
-		return req->err;
-	}
-
-	/* Do not allow empty requests */
-	if (skb_queue_empty(&req->cmd_q))
-		return -ENODATA;
-
-	skb = skb_peek_tail(&req->cmd_q);
-	bt_cb(skb)->req.complete = complete;
-
-	spin_lock_irqsave(&hdev->cmd_q.lock, flags);
-	skb_queue_splice_tail(&req->cmd_q, &hdev->cmd_q);
-	spin_unlock_irqrestore(&hdev->cmd_q.lock, flags);
-
-	queue_work(hdev->workqueue, &hdev->cmd_work);
-
-	return 0;
-}
-
 bool hci_req_pending(struct hci_dev *hdev)
 {
 	return (hdev->req_status == HCI_REQ_PEND);
 }
 
-static struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode,
-				       u32 plen, const void *param)
-{
-	int len = HCI_COMMAND_HDR_SIZE + plen;
-	struct hci_command_hdr *hdr;
-	struct sk_buff *skb;
-
-	skb = bt_skb_alloc(len, GFP_ATOMIC);
-	if (!skb)
-		return NULL;
-
-	hdr = (struct hci_command_hdr *) skb_put(skb, HCI_COMMAND_HDR_SIZE);
-	hdr->opcode = cpu_to_le16(opcode);
-	hdr->plen   = plen;
-
-	if (plen)
-		memcpy(skb_put(skb, plen), param, plen);
-
-	BT_DBG("skb len %d", skb->len);
-
-	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
-	bt_cb(skb)->opcode = opcode;
-
-	return skb;
-}
-
 /* Send HCI command */
 int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
 		 const void *param)
@@ -4634,43 +4464,6 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
 	return 0;
 }
 
-/* Queue a command to an asynchronous HCI request */
-void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
-		    const void *param, u8 event)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct sk_buff *skb;
-
-	BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen);
-
-	/* If an error occurred during request building, there is no point in
-	 * queueing the HCI command. We can simply return.
-	 */
-	if (req->err)
-		return;
-
-	skb = hci_prepare_cmd(hdev, opcode, plen, param);
-	if (!skb) {
-		BT_ERR("%s no memory for command (opcode 0x%4.4x)",
-		       hdev->name, opcode);
-		req->err = -ENOMEM;
-		return;
-	}
-
-	if (skb_queue_empty(&req->cmd_q))
-		bt_cb(skb)->req.start = true;
-
-	bt_cb(skb)->req.event = event;
-
-	skb_queue_tail(&req->cmd_q, skb);
-}
-
-void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
-		 const void *param)
-{
-	hci_req_add_ev(req, opcode, plen, param, 0);
-}
-
 /* Get data from the previously sent command */
 void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode)
 {
@@ -5519,167 +5312,6 @@ static void hci_cmd_work(struct work_struct *work)
 	}
 }
 
-void hci_req_add_le_scan_disable(struct hci_request *req)
-{
-	struct hci_cp_le_set_scan_enable cp;
-
-	memset(&cp, 0, sizeof(cp));
-	cp.enable = LE_SCAN_DISABLE;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
-}
-
-static void add_to_white_list(struct hci_request *req,
-			      struct hci_conn_params *params)
-{
-	struct hci_cp_le_add_to_white_list cp;
-
-	cp.bdaddr_type = params->addr_type;
-	bacpy(&cp.bdaddr, &params->addr);
-
-	hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp);
-}
-
-static u8 update_white_list(struct hci_request *req)
-{
-	struct hci_dev *hdev = req->hdev;
-	struct hci_conn_params *params;
-	struct bdaddr_list *b;
-	uint8_t white_list_entries = 0;
-
-	/* Go through the current white list programmed into the
-	 * controller one by one and check if that address is still
-	 * in the list of pending connections or list of devices to
-	 * report. If not present in either list, then queue the
-	 * command to remove it from the controller.
-	 */
-	list_for_each_entry(b, &hdev->le_white_list, list) {
-		struct hci_cp_le_del_from_white_list cp;
-
-		if (hci_pend_le_action_lookup(&hdev->pend_le_conns,
-					      &b->bdaddr, b->bdaddr_type) ||
-		    hci_pend_le_action_lookup(&hdev->pend_le_reports,
-					      &b->bdaddr, b->bdaddr_type)) {
-			white_list_entries++;
-			continue;
-		}
-
-		cp.bdaddr_type = b->bdaddr_type;
-		bacpy(&cp.bdaddr, &b->bdaddr);
-
-		hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST,
-			    sizeof(cp), &cp);
-	}
-
-	/* Since all no longer valid white list entries have been
-	 * removed, walk through the list of pending connections
-	 * and ensure that any new device gets programmed into
-	 * the controller.
-	 *
-	 * If the list of the devices is larger than the list of
-	 * available white list entries in the controller, then
-	 * just abort and return filer policy value to not use the
-	 * white list.
-	 */
-	list_for_each_entry(params, &hdev->pend_le_conns, action) {
-		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
-					   &params->addr, params->addr_type))
-			continue;
-
-		if (white_list_entries >= hdev->le_white_list_size) {
-			/* Select filter policy to accept all advertising */
-			return 0x00;
-		}
-
-		if (hci_find_irk_by_addr(hdev, &params->addr,
-					 params->addr_type)) {
-			/* White list can not be used with RPAs */
-			return 0x00;
-		}
-
-		white_list_entries++;
-		add_to_white_list(req, params);
-	}
-
-	/* After adding all new pending connections, walk through
-	 * the list of pending reports and also add these to the
-	 * white list if there is still space.
-	 */
-	list_for_each_entry(params, &hdev->pend_le_reports, action) {
-		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
-					   &params->addr, params->addr_type))
-			continue;
-
-		if (white_list_entries >= hdev->le_white_list_size) {
-			/* Select filter policy to accept all advertising */
-			return 0x00;
-		}
-
-		if (hci_find_irk_by_addr(hdev, &params->addr,
-					 params->addr_type)) {
-			/* White list can not be used with RPAs */
-			return 0x00;
-		}
-
-		white_list_entries++;
-		add_to_white_list(req, params);
-	}
-
-	/* Select filter policy to use white list */
-	return 0x01;
-}
-
-void hci_req_add_le_passive_scan(struct hci_request *req)
-{
-	struct hci_cp_le_set_scan_param param_cp;
-	struct hci_cp_le_set_scan_enable enable_cp;
-	struct hci_dev *hdev = req->hdev;
-	u8 own_addr_type;
-	u8 filter_policy;
-
-	/* Set require_privacy to false since no SCAN_REQ are send
-	 * during passive scanning. Not using an non-resolvable address
-	 * here is important so that peer devices using direct
-	 * advertising with our address will be correctly reported
-	 * by the controller.
-	 */
-	if (hci_update_random_address(req, false, &own_addr_type))
-		return;
-
-	/* Adding or removing entries from the white list must
-	 * happen before enabling scanning. The controller does
-	 * not allow white list modification while scanning.
-	 */
-	filter_policy = update_white_list(req);
-
-	/* When the controller is using random resolvable addresses and
-	 * with that having LE privacy enabled, then controllers with
-	 * Extended Scanner Filter Policies support can now enable support
-	 * for handling directed advertising.
-	 *
-	 * So instead of using filter polices 0x00 (no whitelist)
-	 * and 0x01 (whitelist enabled) use the new filter policies
-	 * 0x02 (no whitelist) and 0x03 (whitelist enabled).
-	 */
-	if (test_bit(HCI_PRIVACY, &hdev->dev_flags) &&
-	    (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY))
-		filter_policy |= 0x02;
-
-	memset(&param_cp, 0, sizeof(param_cp));
-	param_cp.type = LE_SCAN_PASSIVE;
-	param_cp.interval = cpu_to_le16(hdev->le_scan_interval);
-	param_cp.window = cpu_to_le16(hdev->le_scan_window);
-	param_cp.own_address_type = own_addr_type;
-	param_cp.filter_policy = filter_policy;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
-		    &param_cp);
-
-	memset(&enable_cp, 0, sizeof(enable_cp));
-	enable_cp.enable = LE_SCAN_ENABLE;
-	enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
-		    &enable_cp);
-}
-
 static void update_background_scan_complete(struct hci_dev *hdev, u8 status)
 {
 	if (status)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 65f4ec8945a..a412eb1e1f6 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -30,6 +30,7 @@
 #include <net/bluetooth/hci_core.h>
 #include <net/bluetooth/mgmt.h>
 
+#include "hci_request.h"
 #include "a2mp.h"
 #include "amp.h"
 #include "smp.h"
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
new file mode 100644
index 00000000000..eba83a2a655
--- /dev/null
+++ b/net/bluetooth/hci_request.c
@@ -0,0 +1,397 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+
+   Copyright (C) 2014 Intel Corporation
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 as
+   published by the Free Software Foundation;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "smp.h"
+#include "hci_request.h"
+
+void hci_req_init(struct hci_request *req, struct hci_dev *hdev)
+{
+	skb_queue_head_init(&req->cmd_q);
+	req->hdev = hdev;
+	req->err = 0;
+}
+
+int hci_req_run(struct hci_request *req, hci_req_complete_t complete)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	BT_DBG("length %u", skb_queue_len(&req->cmd_q));
+
+	/* If an error occurred during request building, remove all HCI
+	 * commands queued on the HCI request queue.
+	 */
+	if (req->err) {
+		skb_queue_purge(&req->cmd_q);
+		return req->err;
+	}
+
+	/* Do not allow empty requests */
+	if (skb_queue_empty(&req->cmd_q))
+		return -ENODATA;
+
+	skb = skb_peek_tail(&req->cmd_q);
+	bt_cb(skb)->req.complete = complete;
+
+	spin_lock_irqsave(&hdev->cmd_q.lock, flags);
+	skb_queue_splice_tail(&req->cmd_q, &hdev->cmd_q);
+	spin_unlock_irqrestore(&hdev->cmd_q.lock, flags);
+
+	queue_work(hdev->workqueue, &hdev->cmd_work);
+
+	return 0;
+}
+
+struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen,
+				const void *param)
+{
+	int len = HCI_COMMAND_HDR_SIZE + plen;
+	struct hci_command_hdr *hdr;
+	struct sk_buff *skb;
+
+	skb = bt_skb_alloc(len, GFP_ATOMIC);
+	if (!skb)
+		return NULL;
+
+	hdr = (struct hci_command_hdr *) skb_put(skb, HCI_COMMAND_HDR_SIZE);
+	hdr->opcode = cpu_to_le16(opcode);
+	hdr->plen   = plen;
+
+	if (plen)
+		memcpy(skb_put(skb, plen), param, plen);
+
+	BT_DBG("skb len %d", skb->len);
+
+	bt_cb(skb)->pkt_type = HCI_COMMAND_PKT;
+	bt_cb(skb)->opcode = opcode;
+
+	return skb;
+}
+
+/* Queue a command to an asynchronous HCI request */
+void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
+		    const void *param, u8 event)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct sk_buff *skb;
+
+	BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen);
+
+	/* If an error occurred during request building, there is no point in
+	 * queueing the HCI command. We can simply return.
+	 */
+	if (req->err)
+		return;
+
+	skb = hci_prepare_cmd(hdev, opcode, plen, param);
+	if (!skb) {
+		BT_ERR("%s no memory for command (opcode 0x%4.4x)",
+		       hdev->name, opcode);
+		req->err = -ENOMEM;
+		return;
+	}
+
+	if (skb_queue_empty(&req->cmd_q))
+		bt_cb(skb)->req.start = true;
+
+	bt_cb(skb)->req.event = event;
+
+	skb_queue_tail(&req->cmd_q, skb);
+}
+
+void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
+		 const void *param)
+{
+	hci_req_add_ev(req, opcode, plen, param, 0);
+}
+
+void hci_req_add_le_scan_disable(struct hci_request *req)
+{
+	struct hci_cp_le_set_scan_enable cp;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.enable = LE_SCAN_DISABLE;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+}
+
+static void add_to_white_list(struct hci_request *req,
+			      struct hci_conn_params *params)
+{
+	struct hci_cp_le_add_to_white_list cp;
+
+	cp.bdaddr_type = params->addr_type;
+	bacpy(&cp.bdaddr, &params->addr);
+
+	hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp);
+}
+
+static u8 update_white_list(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_conn_params *params;
+	struct bdaddr_list *b;
+	uint8_t white_list_entries = 0;
+
+	/* Go through the current white list programmed into the
+	 * controller one by one and check if that address is still
+	 * in the list of pending connections or list of devices to
+	 * report. If not present in either list, then queue the
+	 * command to remove it from the controller.
+	 */
+	list_for_each_entry(b, &hdev->le_white_list, list) {
+		struct hci_cp_le_del_from_white_list cp;
+
+		if (hci_pend_le_action_lookup(&hdev->pend_le_conns,
+					      &b->bdaddr, b->bdaddr_type) ||
+		    hci_pend_le_action_lookup(&hdev->pend_le_reports,
+					      &b->bdaddr, b->bdaddr_type)) {
+			white_list_entries++;
+			continue;
+		}
+
+		cp.bdaddr_type = b->bdaddr_type;
+		bacpy(&cp.bdaddr, &b->bdaddr);
+
+		hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST,
+			    sizeof(cp), &cp);
+	}
+
+	/* Since all no longer valid white list entries have been
+	 * removed, walk through the list of pending connections
+	 * and ensure that any new device gets programmed into
+	 * the controller.
+	 *
+	 * If the list of the devices is larger than the list of
+	 * available white list entries in the controller, then
+	 * just abort and return filer policy value to not use the
+	 * white list.
+	 */
+	list_for_each_entry(params, &hdev->pend_le_conns, action) {
+		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
+					   &params->addr, params->addr_type))
+			continue;
+
+		if (white_list_entries >= hdev->le_white_list_size) {
+			/* Select filter policy to accept all advertising */
+			return 0x00;
+		}
+
+		if (hci_find_irk_by_addr(hdev, &params->addr,
+					 params->addr_type)) {
+			/* White list can not be used with RPAs */
+			return 0x00;
+		}
+
+		white_list_entries++;
+		add_to_white_list(req, params);
+	}
+
+	/* After adding all new pending connections, walk through
+	 * the list of pending reports and also add these to the
+	 * white list if there is still space.
+	 */
+	list_for_each_entry(params, &hdev->pend_le_reports, action) {
+		if (hci_bdaddr_list_lookup(&hdev->le_white_list,
+					   &params->addr, params->addr_type))
+			continue;
+
+		if (white_list_entries >= hdev->le_white_list_size) {
+			/* Select filter policy to accept all advertising */
+			return 0x00;
+		}
+
+		if (hci_find_irk_by_addr(hdev, &params->addr,
+					 params->addr_type)) {
+			/* White list can not be used with RPAs */
+			return 0x00;
+		}
+
+		white_list_entries++;
+		add_to_white_list(req, params);
+	}
+
+	/* Select filter policy to use white list */
+	return 0x01;
+}
+
+void hci_req_add_le_passive_scan(struct hci_request *req)
+{
+	struct hci_cp_le_set_scan_param param_cp;
+	struct hci_cp_le_set_scan_enable enable_cp;
+	struct hci_dev *hdev = req->hdev;
+	u8 own_addr_type;
+	u8 filter_policy;
+
+	/* Set require_privacy to false since no SCAN_REQ are send
+	 * during passive scanning. Not using an non-resolvable address
+	 * here is important so that peer devices using direct
+	 * advertising with our address will be correctly reported
+	 * by the controller.
+	 */
+	if (hci_update_random_address(req, false, &own_addr_type))
+		return;
+
+	/* Adding or removing entries from the white list must
+	 * happen before enabling scanning. The controller does
+	 * not allow white list modification while scanning.
+	 */
+	filter_policy = update_white_list(req);
+
+	/* When the controller is using random resolvable addresses and
+	 * with that having LE privacy enabled, then controllers with
+	 * Extended Scanner Filter Policies support can now enable support
+	 * for handling directed advertising.
+	 *
+	 * So instead of using filter polices 0x00 (no whitelist)
+	 * and 0x01 (whitelist enabled) use the new filter policies
+	 * 0x02 (no whitelist) and 0x03 (whitelist enabled).
+	 */
+	if (test_bit(HCI_PRIVACY, &hdev->dev_flags) &&
+	    (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY))
+		filter_policy |= 0x02;
+
+	memset(&param_cp, 0, sizeof(param_cp));
+	param_cp.type = LE_SCAN_PASSIVE;
+	param_cp.interval = cpu_to_le16(hdev->le_scan_interval);
+	param_cp.window = cpu_to_le16(hdev->le_scan_window);
+	param_cp.own_address_type = own_addr_type;
+	param_cp.filter_policy = filter_policy;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
+		    &param_cp);
+
+	memset(&enable_cp, 0, sizeof(enable_cp));
+	enable_cp.enable = LE_SCAN_ENABLE;
+	enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
+		    &enable_cp);
+}
+
+static void set_random_addr(struct hci_request *req, bdaddr_t *rpa)
+{
+	struct hci_dev *hdev = req->hdev;
+
+	/* If we're advertising or initiating an LE connection we can't
+	 * go ahead and change the random address at this time. This is
+	 * because the eventual initiator address used for the
+	 * subsequently created connection will be undefined (some
+	 * controllers use the new address and others the one we had
+	 * when the operation started).
+	 *
+	 * In this kind of scenario skip the update and let the random
+	 * address be updated at the next cycle.
+	 */
+	if (test_bit(HCI_LE_ADV, &hdev->dev_flags) ||
+	    hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT)) {
+		BT_DBG("Deferring random address update");
+		set_bit(HCI_RPA_EXPIRED, &hdev->dev_flags);
+		return;
+	}
+
+	hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa);
+}
+
+int hci_update_random_address(struct hci_request *req, bool require_privacy,
+			      u8 *own_addr_type)
+{
+	struct hci_dev *hdev = req->hdev;
+	int err;
+
+	/* If privacy is enabled use a resolvable private address. If
+	 * current RPA has expired or there is something else than
+	 * the current RPA in use, then generate a new one.
+	 */
+	if (test_bit(HCI_PRIVACY, &hdev->dev_flags)) {
+		int to;
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+
+		if (!test_and_clear_bit(HCI_RPA_EXPIRED, &hdev->dev_flags) &&
+		    !bacmp(&hdev->random_addr, &hdev->rpa))
+			return 0;
+
+		err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa);
+		if (err < 0) {
+			BT_ERR("%s failed to generate new RPA", hdev->name);
+			return err;
+		}
+
+		set_random_addr(req, &hdev->rpa);
+
+		to = msecs_to_jiffies(hdev->rpa_timeout * 1000);
+		queue_delayed_work(hdev->workqueue, &hdev->rpa_expired, to);
+
+		return 0;
+	}
+
+	/* In case of required privacy without resolvable private address,
+	 * use an non-resolvable private address. This is useful for active
+	 * scanning and non-connectable advertising.
+	 */
+	if (require_privacy) {
+		bdaddr_t nrpa;
+
+		while (true) {
+			/* The non-resolvable private address is generated
+			 * from random six bytes with the two most significant
+			 * bits cleared.
+			 */
+			get_random_bytes(&nrpa, 6);
+			nrpa.b[5] &= 0x3f;
+
+			/* The non-resolvable private address shall not be
+			 * equal to the public address.
+			 */
+			if (bacmp(&hdev->bdaddr, &nrpa))
+				break;
+		}
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		set_random_addr(req, &nrpa);
+		return 0;
+	}
+
+	/* If forcing static address is in use or there is no public
+	 * address use the static address as random address (but skip
+	 * the HCI command if the current random address is already the
+	 * static one.
+	 */
+	if (test_bit(HCI_FORCE_STATIC_ADDR, &hdev->dbg_flags) ||
+	    !bacmp(&hdev->bdaddr, BDADDR_ANY)) {
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		if (bacmp(&hdev->static_addr, &hdev->random_addr))
+			hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6,
+				    &hdev->static_addr);
+		return 0;
+	}
+
+	/* Neither privacy nor static address is being used so use a
+	 * public address.
+	 */
+	*own_addr_type = ADDR_LE_DEV_PUBLIC;
+
+	return 0;
+}
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
new file mode 100644
index 00000000000..1793a46fea6
--- /dev/null
+++ b/net/bluetooth/hci_request.h
@@ -0,0 +1,51 @@
+/*
+   BlueZ - Bluetooth protocol stack for Linux
+   Copyright (C) 2014 Intel Corporation
+
+   This program is free software; you can redistribute it and/or modify
+   it under the terms of the GNU General Public License version 2 as
+   published by the Free Software Foundation;
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+   OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+   FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+   IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY
+   CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES
+   WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+   ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+   OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+   ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS,
+   COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS
+   SOFTWARE IS DISCLAIMED.
+*/
+
+struct hci_request {
+	struct hci_dev		*hdev;
+	struct sk_buff_head	cmd_q;
+
+	/* If something goes wrong when building the HCI request, the error
+	 * value is stored in this field.
+	 */
+	int			err;
+};
+
+void hci_req_init(struct hci_request *req, struct hci_dev *hdev);
+int hci_req_run(struct hci_request *req, hci_req_complete_t complete);
+void hci_req_add(struct hci_request *req, u16 opcode, u32 plen,
+		 const void *param);
+void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
+		    const void *param, u8 event);
+void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status);
+
+struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen,
+				const void *param);
+
+void hci_req_add_le_scan_disable(struct hci_request *req);
+void hci_req_add_le_passive_scan(struct hci_request *req);
+
+void hci_update_page_scan(struct hci_dev *hdev);
+void __hci_update_page_scan(struct hci_request *req);
+
+int hci_update_random_address(struct hci_request *req, bool require_privacy,
+			      u8 *own_addr_type);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f86f3ec684b..95473e96670 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -32,6 +32,7 @@
 #include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
+#include "hci_request.h"
 #include "smp.h"
 
 #define MGMT_VERSION	1
-- 
cgit v1.2.3-70-g09d2


From 2cf22218b00f46f93b39a9355b830e9e8e4fd077 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 19 Dec 2014 22:26:00 +0200
Subject: Bluetooth: Add hci_request support for hci_update_background_scan

Many places using hci_update_background_scan() try to synchronize
whatever they're doing with the help of hci_request callbacks. However,
since the hci_update_background_scan() function hasn't so far accepted a
hci_request pointer any commands triggered by it have been left out by
the synchronization. This patch modifies the API in a similar way as was
done for hci_update_page_scan, i.e. there's a variant that takes a
hci_request and another one that takes a hci_dev.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  2 -
 net/bluetooth/hci_core.c         | 89 -------------------------------------
 net/bluetooth/hci_request.c      | 96 ++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/hci_request.h      |  3 ++
 net/bluetooth/mgmt.c             | 12 ++---
 5 files changed, 105 insertions(+), 97 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 93066f70f8a..8eccdf02950 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -930,8 +930,6 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list,
 						  bdaddr_t *addr,
 						  u8 addr_type);
 
-void hci_update_background_scan(struct hci_dev *hdev);
-
 void hci_uuids_clear(struct hci_dev *hdev);
 
 void hci_link_keys_clear(struct hci_dev *hdev);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 2cfaaa6acb0..def6fba01b4 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -5312,95 +5312,6 @@ static void hci_cmd_work(struct work_struct *work)
 	}
 }
 
-static void update_background_scan_complete(struct hci_dev *hdev, u8 status)
-{
-	if (status)
-		BT_DBG("HCI request failed to update background scanning: "
-		       "status 0x%2.2x", status);
-}
-
-/* This function controls the background scanning based on hdev->pend_le_conns
- * list. If there are pending LE connection we start the background scanning,
- * otherwise we stop it.
- *
- * This function requires the caller holds hdev->lock.
- */
-void hci_update_background_scan(struct hci_dev *hdev)
-{
-	struct hci_request req;
-	struct hci_conn *conn;
-	int err;
-
-	if (!test_bit(HCI_UP, &hdev->flags) ||
-	    test_bit(HCI_INIT, &hdev->flags) ||
-	    test_bit(HCI_SETUP, &hdev->dev_flags) ||
-	    test_bit(HCI_CONFIG, &hdev->dev_flags) ||
-	    test_bit(HCI_AUTO_OFF, &hdev->dev_flags) ||
-	    test_bit(HCI_UNREGISTER, &hdev->dev_flags))
-		return;
-
-	/* No point in doing scanning if LE support hasn't been enabled */
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
-		return;
-
-	/* If discovery is active don't interfere with it */
-	if (hdev->discovery.state != DISCOVERY_STOPPED)
-		return;
-
-	/* Reset RSSI and UUID filters when starting background scanning
-	 * since these filters are meant for service discovery only.
-	 *
-	 * The Start Discovery and Start Service Discovery operations
-	 * ensure to set proper values for RSSI threshold and UUID
-	 * filter list. So it is safe to just reset them here.
-	 */
-	hci_discovery_filter_clear(hdev);
-
-	hci_req_init(&req, hdev);
-
-	if (list_empty(&hdev->pend_le_conns) &&
-	    list_empty(&hdev->pend_le_reports)) {
-		/* If there is no pending LE connections or devices
-		 * to be scanned for, we should stop the background
-		 * scanning.
-		 */
-
-		/* If controller is not scanning we are done. */
-		if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags))
-			return;
-
-		hci_req_add_le_scan_disable(&req);
-
-		BT_DBG("%s stopping background scanning", hdev->name);
-	} else {
-		/* If there is at least one pending LE connection, we should
-		 * keep the background scan running.
-		 */
-
-		/* If controller is connecting, we should not start scanning
-		 * since some controllers are not able to scan and connect at
-		 * the same time.
-		 */
-		conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
-		if (conn)
-			return;
-
-		/* If controller is currently scanning, we stop it to ensure we
-		 * don't miss any advertising (due to duplicates filter).
-		 */
-		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags))
-			hci_req_add_le_scan_disable(&req);
-
-		hci_req_add_le_passive_scan(&req);
-
-		BT_DBG("%s starting background scanning", hdev->name);
-	}
-
-	err = hci_req_run(&req, update_background_scan_complete);
-	if (err)
-		BT_ERR("Failed to run HCI request: err %d", err);
-}
-
 static bool disconnected_whitelist_entries(struct hci_dev *hdev)
 {
 	struct bdaddr_list *b;
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index eba83a2a655..e49f682f155 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -395,3 +395,99 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy,
 
 	return 0;
 }
+
+/* This function controls the background scanning based on hdev->pend_le_conns
+ * list. If there are pending LE connection we start the background scanning,
+ * otherwise we stop it.
+ *
+ * This function requires the caller holds hdev->lock.
+ */
+void __hci_update_background_scan(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_conn *conn;
+
+	if (!test_bit(HCI_UP, &hdev->flags) ||
+	    test_bit(HCI_INIT, &hdev->flags) ||
+	    test_bit(HCI_SETUP, &hdev->dev_flags) ||
+	    test_bit(HCI_CONFIG, &hdev->dev_flags) ||
+	    test_bit(HCI_AUTO_OFF, &hdev->dev_flags) ||
+	    test_bit(HCI_UNREGISTER, &hdev->dev_flags))
+		return;
+
+	/* No point in doing scanning if LE support hasn't been enabled */
+	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
+		return;
+
+	/* If discovery is active don't interfere with it */
+	if (hdev->discovery.state != DISCOVERY_STOPPED)
+		return;
+
+	/* Reset RSSI and UUID filters when starting background scanning
+	 * since these filters are meant for service discovery only.
+	 *
+	 * The Start Discovery and Start Service Discovery operations
+	 * ensure to set proper values for RSSI threshold and UUID
+	 * filter list. So it is safe to just reset them here.
+	 */
+	hci_discovery_filter_clear(hdev);
+
+	if (list_empty(&hdev->pend_le_conns) &&
+	    list_empty(&hdev->pend_le_reports)) {
+		/* If there is no pending LE connections or devices
+		 * to be scanned for, we should stop the background
+		 * scanning.
+		 */
+
+		/* If controller is not scanning we are done. */
+		if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+			return;
+
+		hci_req_add_le_scan_disable(req);
+
+		BT_DBG("%s stopping background scanning", hdev->name);
+	} else {
+		/* If there is at least one pending LE connection, we should
+		 * keep the background scan running.
+		 */
+
+		/* If controller is connecting, we should not start scanning
+		 * since some controllers are not able to scan and connect at
+		 * the same time.
+		 */
+		conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
+		if (conn)
+			return;
+
+		/* If controller is currently scanning, we stop it to ensure we
+		 * don't miss any advertising (due to duplicates filter).
+		 */
+		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+			hci_req_add_le_scan_disable(req);
+
+		hci_req_add_le_passive_scan(req);
+
+		BT_DBG("%s starting background scanning", hdev->name);
+	}
+}
+
+static void update_background_scan_complete(struct hci_dev *hdev, u8 status)
+{
+	if (status)
+		BT_DBG("HCI request failed to update background scanning: "
+		       "status 0x%2.2x", status);
+}
+
+void hci_update_background_scan(struct hci_dev *hdev)
+{
+	int err;
+	struct hci_request req;
+
+	hci_req_init(&req, hdev);
+
+	__hci_update_background_scan(&req);
+
+	err = hci_req_run(&req, update_background_scan_complete);
+	if (err && err != -ENODATA)
+		BT_ERR("Failed to run HCI request: err %d", err);
+}
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 1793a46fea6..adf074d3354 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -49,3 +49,6 @@ void __hci_update_page_scan(struct hci_request *req);
 
 int hci_update_random_address(struct hci_request *req, bool require_privacy,
 			      u8 *own_addr_type);
+
+void hci_update_background_scan(struct hci_dev *hdev);
+void __hci_update_background_scan(struct hci_request *req);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 95473e96670..3afe1e175eb 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2228,9 +2228,8 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status)
 		hci_req_init(&req, hdev);
 		update_adv_data(&req);
 		update_scan_rsp_data(&req);
+		__hci_update_background_scan(&req);
 		hci_req_run(&req, NULL);
-
-		hci_update_background_scan(hdev);
 	}
 
 unlock:
@@ -6038,8 +6037,9 @@ void mgmt_index_removed(struct hci_dev *hdev)
 }
 
 /* This function requires the caller holds hdev->lock */
-static void restart_le_actions(struct hci_dev *hdev)
+static void restart_le_actions(struct hci_request *req)
 {
+	struct hci_dev *hdev = req->hdev;
 	struct hci_conn_params *p;
 
 	list_for_each_entry(p, &hdev->le_conn_params, list) {
@@ -6061,7 +6061,7 @@ static void restart_le_actions(struct hci_dev *hdev)
 		}
 	}
 
-	hci_update_background_scan(hdev);
+	__hci_update_background_scan(req);
 }
 
 static void powered_complete(struct hci_dev *hdev, u8 status)
@@ -6072,8 +6072,6 @@ static void powered_complete(struct hci_dev *hdev, u8 status)
 
 	hci_dev_lock(hdev);
 
-	restart_le_actions(hdev);
-
 	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
 
 	new_settings(hdev, match.sk);
@@ -6131,6 +6129,8 @@ static int powered_update_hci(struct hci_dev *hdev)
 
 		if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
 			enable_advertising(&req);
+
+		restart_le_actions(&req);
 	}
 
 	link_sec = test_bit(HCI_LINK_SECURITY, &hdev->dev_flags);
-- 
cgit v1.2.3-70-g09d2


From 5a154e6f71dfd41c7b5cf96a13c83fca91e7df7f Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 19 Dec 2014 22:26:02 +0200
Subject: Bluetooth: Fix Add Device to wait for HCI before sending cmd_complete

This patch updates the Add Device mgmt command handler to use a
hci_request to wait for HCI command completion before notifying user
space of the mgmt command completion. To do this we need to add an extra
hci_request parameter to the hci_conn_params_set function. Since this
function has no other users besides mgmt.c it's moved there as a static
function.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |   2 -
 net/bluetooth/hci_core.c         |  58 -------------------
 net/bluetooth/mgmt.c             | 119 +++++++++++++++++++++++++++++++++++----
 3 files changed, 109 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 8eccdf02950..79724c87ab0 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -920,8 +920,6 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev,
 					       bdaddr_t *addr, u8 addr_type);
 struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev,
 					    bdaddr_t *addr, u8 addr_type);
-int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type,
-			u8 auto_connect);
 void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type);
 void hci_conn_params_clear_all(struct hci_dev *hdev);
 void hci_conn_params_clear_disabled(struct hci_dev *hdev);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index def6fba01b4..ee2096c7ec2 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3660,23 +3660,6 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev,
 	return NULL;
 }
 
-static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type)
-{
-	struct hci_conn *conn;
-
-	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, addr);
-	if (!conn)
-		return false;
-
-	if (conn->dst_type != type)
-		return false;
-
-	if (conn->state != BT_CONNECTED)
-		return false;
-
-	return true;
-}
-
 /* This function requires the caller holds hdev->lock */
 struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list,
 						  bdaddr_t *addr, u8 addr_type)
@@ -3732,47 +3715,6 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev,
 	return params;
 }
 
-/* This function requires the caller holds hdev->lock */
-int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type,
-			u8 auto_connect)
-{
-	struct hci_conn_params *params;
-
-	params = hci_conn_params_add(hdev, addr, addr_type);
-	if (!params)
-		return -EIO;
-
-	if (params->auto_connect == auto_connect)
-		return 0;
-
-	list_del_init(&params->action);
-
-	switch (auto_connect) {
-	case HCI_AUTO_CONN_DISABLED:
-	case HCI_AUTO_CONN_LINK_LOSS:
-		hci_update_background_scan(hdev);
-		break;
-	case HCI_AUTO_CONN_REPORT:
-		list_add(&params->action, &hdev->pend_le_reports);
-		hci_update_background_scan(hdev);
-		break;
-	case HCI_AUTO_CONN_DIRECT:
-	case HCI_AUTO_CONN_ALWAYS:
-		if (!is_connected(hdev, addr, addr_type)) {
-			list_add(&params->action, &hdev->pend_le_conns);
-			hci_update_background_scan(hdev);
-		}
-		break;
-	}
-
-	params->auto_connect = auto_connect;
-
-	BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type,
-	       auto_connect);
-
-	return 0;
-}
-
 static void hci_conn_params_free(struct hci_conn_params *params)
 {
 	if (params->conn) {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 6b925733c6f..ec7c0ec3d8d 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5425,6 +5425,65 @@ unlock:
 	return err;
 }
 
+static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type)
+{
+	struct hci_conn *conn;
+
+	conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, addr);
+	if (!conn)
+		return false;
+
+	if (conn->dst_type != type)
+		return false;
+
+	if (conn->state != BT_CONNECTED)
+		return false;
+
+	return true;
+}
+
+/* This function requires the caller holds hdev->lock */
+static int hci_conn_params_set(struct hci_request *req, bdaddr_t *addr,
+			       u8 addr_type, u8 auto_connect)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_conn_params *params;
+
+	params = hci_conn_params_add(hdev, addr, addr_type);
+	if (!params)
+		return -EIO;
+
+	if (params->auto_connect == auto_connect)
+		return 0;
+
+	list_del_init(&params->action);
+
+	switch (auto_connect) {
+	case HCI_AUTO_CONN_DISABLED:
+	case HCI_AUTO_CONN_LINK_LOSS:
+		__hci_update_background_scan(req);
+		break;
+	case HCI_AUTO_CONN_REPORT:
+		list_add(&params->action, &hdev->pend_le_reports);
+		__hci_update_background_scan(req);
+		break;
+	case HCI_AUTO_CONN_DIRECT:
+	case HCI_AUTO_CONN_ALWAYS:
+		if (!is_connected(hdev, addr, addr_type)) {
+			list_add(&params->action, &hdev->pend_le_conns);
+			__hci_update_background_scan(req);
+		}
+		break;
+	}
+
+	params->auto_connect = auto_connect;
+
+	BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type,
+	       auto_connect);
+
+	return 0;
+}
+
 static void device_added(struct sock *sk, struct hci_dev *hdev,
 			 bdaddr_t *bdaddr, u8 type, u8 action)
 {
@@ -5437,10 +5496,31 @@ static void device_added(struct sock *sk, struct hci_dev *hdev,
 	mgmt_event(MGMT_EV_DEVICE_ADDED, hdev, &ev, sizeof(ev), sk);
 }
 
+static void add_device_complete(struct hci_dev *hdev, u8 status)
+{
+	struct pending_cmd *cmd;
+
+	BT_DBG("status 0x%02x", status);
+
+	hci_dev_lock(hdev);
+
+	cmd = mgmt_pending_find(MGMT_OP_ADD_DEVICE, hdev);
+	if (!cmd)
+		goto unlock;
+
+	cmd->cmd_complete(cmd, mgmt_status(status));
+	mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static int add_device(struct sock *sk, struct hci_dev *hdev,
 		      void *data, u16 len)
 {
 	struct mgmt_cp_add_device *cp = data;
+	struct pending_cmd *cmd;
+	struct hci_request req;
 	u8 auto_conn, addr_type;
 	int err;
 
@@ -5457,14 +5537,24 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 				    MGMT_STATUS_INVALID_PARAMS,
 				    &cp->addr, sizeof(cp->addr));
 
+	hci_req_init(&req, hdev);
+
 	hci_dev_lock(hdev);
 
+	cmd = mgmt_pending_add(sk, MGMT_OP_ADD_DEVICE, hdev, data, len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	cmd->cmd_complete = addr_cmd_complete;
+
 	if (cp->addr.type == BDADDR_BREDR) {
 		/* Only incoming connections action is supported for now */
 		if (cp->action != 0x01) {
-			err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-					   MGMT_STATUS_INVALID_PARAMS,
-					   &cp->addr, sizeof(cp->addr));
+			err = 0;
+			cmd->cmd_complete(cmd, MGMT_STATUS_INVALID_PARAMS);
+			mgmt_pending_remove(cmd);
 			goto unlock;
 		}
 
@@ -5473,7 +5563,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 		if (err)
 			goto unlock;
 
-		hci_update_page_scan(hdev);
+		__hci_update_page_scan(&req);
 
 		goto added;
 	}
@@ -5493,19 +5583,28 @@ static int add_device(struct sock *sk, struct hci_dev *hdev,
 	/* If the connection parameters don't exist for this device,
 	 * they will be created and configured with defaults.
 	 */
-	if (hci_conn_params_set(hdev, &cp->addr.bdaddr, addr_type,
+	if (hci_conn_params_set(&req, &cp->addr.bdaddr, addr_type,
 				auto_conn) < 0) {
-		err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-				   MGMT_STATUS_FAILED,
-				   &cp->addr, sizeof(cp->addr));
+		err = 0;
+		cmd->cmd_complete(cmd, MGMT_STATUS_FAILED);
+		mgmt_pending_remove(cmd);
 		goto unlock;
 	}
 
 added:
 	device_added(sk, hdev, &cp->addr.bdaddr, cp->addr.type, cp->action);
 
-	err = cmd_complete(sk, hdev->id, MGMT_OP_ADD_DEVICE,
-			   MGMT_STATUS_SUCCESS, &cp->addr, sizeof(cp->addr));
+	err = hci_req_run(&req, add_device_complete);
+	if (err < 0) {
+		/* ENODATA means no HCI commands were needed (e.g. if
+		 * the adapter is powered off).
+		 */
+		if (err == -ENODATA) {
+			cmd->cmd_complete(cmd, MGMT_STATUS_SUCCESS);
+			err = 0;
+		}
+		mgmt_pending_remove(cmd);
+	}
 
 unlock:
 	hci_dev_unlock(hdev);
-- 
cgit v1.2.3-70-g09d2


From 94a3bd02a6b79b98236d9805a1f95a2857e7696a Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 20 Dec 2014 16:28:38 +0100
Subject: Bluetooth: Add structures for LE Data Length Extension feature

This patch adds the structures for HCI commands and events of the
LE Data Length Extension feature from Bluetooth 4.2 specification.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 40129b3838b..f39926ee06f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -343,6 +343,7 @@ enum {
 #define HCI_LE_ENCRYPTION		0x01
 #define HCI_LE_CONN_PARAM_REQ_PROC	0x02
 #define HCI_LE_PING			0x10
+#define HCI_LE_DATA_LEN_EXT		0x20
 #define HCI_LE_EXT_SCAN_POLICY		0x80
 
 /* Connection modes */
@@ -1371,6 +1372,39 @@ struct hci_cp_le_conn_param_req_neg_reply {
 	__u8	reason;
 } __packed;
 
+#define HCI_OP_LE_SET_DATA_LEN		0x2022
+struct hci_cp_le_set_data_len {
+	__le16	handle;
+	__le16	tx_len;
+	__le16	tx_time;
+} __packed;
+struct hci_rp_le_set_data_len {
+	__u8	status;
+	__le16	handle;
+} __packed;
+
+#define HCI_OP_LE_READ_DEF_DATA_LEN	0x2023
+struct hci_rp_le_read_def_data_len {
+	__u8	status;
+	__le16	tx_len;
+	__le16	tx_time;
+} __packed;
+
+#define HCI_OP_LE_WRITE_DEF_DATA_LEN	0x2024
+struct hci_cp_le_write_def_data_len {
+	__le16	tx_len;
+	__le16	tx_time;
+} __packed;
+
+#define HCI_OP_LE_READ_MAX_DATA_LEN	0x202f
+struct hci_rp_le_read_max_data_len {
+	__u8	status;
+	__le16	tx_len;
+	__le16	tx_time;
+	__le16	rx_len;
+	__le16	rx_time;
+} __packed;
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
@@ -1796,6 +1830,15 @@ struct hci_ev_le_remote_conn_param_req {
 	__le16 timeout;
 } __packed;
 
+#define HCI_EV_LE_DATA_LEN_CHANGE	0x07
+struct hci_ev_le_data_len_change {
+	__le16	handle;
+	__le16	tx_len;
+	__le16	tx_time;
+	__le16	rx_len;
+	__le16	rx_time;
+} __packed;
+
 #define HCI_EV_LE_DIRECT_ADV_REPORT	0x0B
 struct hci_ev_le_direct_adv_info {
 	__u8	 evt_type;
-- 
cgit v1.2.3-70-g09d2


From a8e1bfaa55cf8ac4e419a09bdda5bb45bcd8f985 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 20 Dec 2014 16:28:40 +0100
Subject: Bluetooth: Store default and maximum LE data length settings

When the controller supports the LE Data Length Extension feature, the
default and maximum data length are read and now stored.

For backwards compatibility all values are initialized to the data
length values from Bluetooth 4.1 and earlier specifications.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  6 ++++
 net/bluetooth/hci_core.c         |  6 ++++
 net/bluetooth/hci_event.c        | 61 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 73 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 79724c87ab0..f20f6bd668b 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -220,6 +220,12 @@ struct hci_dev {
 	__u16		le_conn_max_interval;
 	__u16		le_conn_latency;
 	__u16		le_supv_timeout;
+	__u16		le_def_tx_len;
+	__u16		le_def_tx_time;
+	__u16		le_max_tx_len;
+	__u16		le_max_tx_time;
+	__u16		le_max_rx_len;
+	__u16		le_max_rx_time;
 	__u16		discov_interleaved_timeout;
 	__u16		conn_info_min_age;
 	__u16		conn_info_max_age;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 01e35ef6d20..47f0311d100 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2896,6 +2896,12 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->le_conn_max_interval = 0x0038;
 	hdev->le_conn_latency = 0x0000;
 	hdev->le_supv_timeout = 0x002a;
+	hdev->le_def_tx_len = 0x001b;
+	hdev->le_def_tx_time = 0x0148;
+	hdev->le_max_tx_len = 0x001b;
+	hdev->le_max_tx_time = 0x0148;
+	hdev->le_max_rx_len = 0x001b;
+	hdev->le_max_rx_time = 0x0148;
 
 	hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT;
 	hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a412eb1e1f6..a3055e90a5b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1280,6 +1280,55 @@ static void hci_cc_le_read_supported_states(struct hci_dev *hdev,
 	memcpy(hdev->le_states, rp->le_states, 8);
 }
 
+static void hci_cc_le_read_def_data_len(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_le_read_def_data_len *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hdev->le_def_tx_len = le16_to_cpu(rp->tx_len);
+	hdev->le_def_tx_time = le16_to_cpu(rp->tx_time);
+}
+
+static void hci_cc_le_write_def_data_len(struct hci_dev *hdev,
+					 struct sk_buff *skb)
+{
+	struct hci_cp_le_write_def_data_len *sent;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_WRITE_DEF_DATA_LEN);
+	if (!sent)
+		return;
+
+	hdev->le_def_tx_len = le16_to_cpu(sent->tx_len);
+	hdev->le_def_tx_time = le16_to_cpu(sent->tx_time);
+}
+
+static void hci_cc_le_read_max_data_len(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_le_read_max_data_len *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hdev->le_max_tx_len = le16_to_cpu(rp->tx_len);
+	hdev->le_max_tx_time = le16_to_cpu(rp->tx_time);
+	hdev->le_max_rx_len = le16_to_cpu(rp->rx_len);
+	hdev->le_max_rx_time = le16_to_cpu(rp->rx_time);
+}
+
 static void hci_cc_write_le_host_supported(struct hci_dev *hdev,
 					   struct sk_buff *skb)
 {
@@ -2847,6 +2896,18 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_le_read_supported_states(hdev, skb);
 		break;
 
+	case HCI_OP_LE_READ_DEF_DATA_LEN:
+		hci_cc_le_read_def_data_len(hdev, skb);
+		break;
+
+	case HCI_OP_LE_WRITE_DEF_DATA_LEN:
+		hci_cc_le_write_def_data_len(hdev, skb);
+		break;
+
+	case HCI_OP_LE_READ_MAX_DATA_LEN:
+		hci_cc_le_read_max_data_len(hdev, skb);
+		break;
+
 	case HCI_OP_WRITE_LE_HOST_SUPPORTED:
 		hci_cc_write_le_host_supported(hdev, skb);
 		break;
-- 
cgit v1.2.3-70-g09d2


From 23b9ceb74f8e46bddd61a1e2afd9317221be74b7 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 20 Dec 2014 17:13:41 +0100
Subject: Bluetooth: Create debugfs directory for each connection handle

For every internal representation of a Bluetooth connection which is
identified by hci_conn, create a debugfs directory with the handle
number as directory name.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_conn.c         |  3 +++
 net/bluetooth/hci_debugfs.c      | 12 ++++++++++++
 net/bluetooth/hci_debugfs.h      |  1 +
 net/bluetooth/hci_event.c        |  5 +++++
 5 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f20f6bd668b..3e7e5110f29 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -440,6 +440,7 @@ struct hci_conn {
 	struct delayed_work le_conn_timeout;
 
 	struct device	dev;
+	struct dentry	*debugfs;
 
 	struct hci_dev	*hdev;
 	void		*l2cap_data;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 4405fb352c7..75240aaca10 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -25,6 +25,7 @@
 /* Bluetooth HCI connection handling. */
 
 #include <linux/export.h>
+#include <linux/debugfs.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -547,6 +548,8 @@ int hci_conn_del(struct hci_conn *conn)
 
 	hci_conn_del_sysfs(conn);
 
+	debugfs_remove_recursive(conn->debugfs);
+
 	if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags))
 		hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type);
 
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index a7a0db03b0b..ee33ce88d3d 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -1062,3 +1062,15 @@ void hci_debugfs_create_le(struct hci_dev *hdev)
 	debugfs_create_u16("discov_interleaved_timeout", 0644, hdev->debugfs,
 			   &hdev->discov_interleaved_timeout);
 }
+
+void hci_debugfs_create_conn(struct hci_conn *conn)
+{
+	struct hci_dev *hdev = conn->hdev;
+	char name[6];
+
+	if (IS_ERR_OR_NULL(hdev->debugfs))
+		return;
+
+	snprintf(name, sizeof(name), "%u", conn->handle);
+	conn->debugfs = debugfs_create_dir(name, hdev->debugfs);
+}
diff --git a/net/bluetooth/hci_debugfs.h b/net/bluetooth/hci_debugfs.h
index f191100b50c..fb68efe083c 100644
--- a/net/bluetooth/hci_debugfs.h
+++ b/net/bluetooth/hci_debugfs.h
@@ -23,3 +23,4 @@
 void hci_debugfs_create_common(struct hci_dev *hdev);
 void hci_debugfs_create_bredr(struct hci_dev *hdev);
 void hci_debugfs_create_le(struct hci_dev *hdev);
+void hci_debugfs_create_conn(struct hci_conn *conn);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a3055e90a5b..eed44c643c0 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -31,6 +31,7 @@
 #include <net/bluetooth/mgmt.h>
 
 #include "hci_request.h"
+#include "hci_debugfs.h"
 #include "a2mp.h"
 #include "amp.h"
 #include "smp.h"
@@ -2162,6 +2163,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		} else
 			conn->state = BT_CONNECTED;
 
+		hci_debugfs_create_conn(conn);
 		hci_conn_add_sysfs(conn);
 
 		if (test_bit(HCI_AUTH, &hdev->flags))
@@ -3638,6 +3640,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev,
 		conn->handle = __le16_to_cpu(ev->handle);
 		conn->state  = BT_CONNECTED;
 
+		hci_debugfs_create_conn(conn);
 		hci_conn_add_sysfs(conn);
 		break;
 
@@ -4178,6 +4181,7 @@ static void hci_phy_link_complete_evt(struct hci_dev *hdev,
 	hcon->disc_timeout = HCI_DISCONN_TIMEOUT;
 	hci_conn_drop(hcon);
 
+	hci_debugfs_create_conn(hcon);
 	hci_conn_add_sysfs(hcon);
 
 	amp_physical_cfm(bredr_hcon, hcon);
@@ -4384,6 +4388,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	conn->le_conn_latency = le16_to_cpu(ev->latency);
 	conn->le_supv_timeout = le16_to_cpu(ev->supervision_timeout);
 
+	hci_debugfs_create_conn(conn);
 	hci_conn_add_sysfs(conn);
 
 	hci_proto_connect_cfm(conn, ev->status);
-- 
cgit v1.2.3-70-g09d2


From 72e4a6bd02204eed0464d6139439d7e89b94266e Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sat, 20 Dec 2014 18:00:41 +0100
Subject: Bluetooth: Remove duplicate constant for RFCOMM PSM

The RFCOMM_PSM constant is actually a duplicate. So remove it and
use the L2CAP_PSM_RFCOMM constant instead.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/rfcomm.h | 2 --
 net/bluetooth/rfcomm/core.c    | 4 ++--
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 578b83127af..4190af53a46 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -24,8 +24,6 @@
 #ifndef __RFCOMM_H
 #define __RFCOMM_H
 
-#define RFCOMM_PSM 3
-
 #define RFCOMM_CONN_TIMEOUT (HZ * 30)
 #define RFCOMM_DISC_TIMEOUT (HZ * 20)
 #define RFCOMM_AUTH_TIMEOUT (HZ * 25)
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 73f8c75abe6..4fea24275b1 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -771,7 +771,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src,
 
 	bacpy(&addr.l2_bdaddr, dst);
 	addr.l2_family = AF_BLUETOOTH;
-	addr.l2_psm    = cpu_to_le16(RFCOMM_PSM);
+	addr.l2_psm    = cpu_to_le16(L2CAP_PSM_RFCOMM);
 	addr.l2_cid    = 0;
 	addr.l2_bdaddr_type = BDADDR_BREDR;
 	*err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK);
@@ -2038,7 +2038,7 @@ static int rfcomm_add_listener(bdaddr_t *ba)
 	/* Bind socket */
 	bacpy(&addr.l2_bdaddr, ba);
 	addr.l2_family = AF_BLUETOOTH;
-	addr.l2_psm    = cpu_to_le16(RFCOMM_PSM);
+	addr.l2_psm    = cpu_to_le16(L2CAP_PSM_RFCOMM);
 	addr.l2_cid    = 0;
 	addr.l2_bdaddr_type = BDADDR_BREDR;
 	err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr));
-- 
cgit v1.2.3-70-g09d2


From d64cb71bede87dbca60d586a7bb4cef87fbe2731 Mon Sep 17 00:00:00 2001
From: Jaewon Kim <jaewon02.kim@samsung.com>
Date: Wed, 17 Dec 2014 10:31:08 -0800
Subject: Input: add regulator haptic driver

This change adds support for haptic driver controlled by voltage of a
regulator. Userspace can control the device via Force Feedback interface
from input framework.

Signed-off-by: Jaewon Kim <jaewon02.kim@samsung.com>
Signed-off-by: Hyunhee Kim <hyunhee.kim@samsung.com>
Acked-by: Kyungmin Park <kyungmin.park@samsung.com>
Tested-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/regulator-haptic.txt |  21 ++
 drivers/input/misc/Kconfig                         |  12 +
 drivers/input/misc/Makefile                        |   1 +
 drivers/input/misc/regulator-haptic.c              | 279 +++++++++++++++++++++
 include/linux/platform_data/regulator-haptic.h     |  29 +++
 5 files changed, 342 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/input/regulator-haptic.txt
 create mode 100644 drivers/input/misc/regulator-haptic.c
 create mode 100644 include/linux/platform_data/regulator-haptic.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/input/regulator-haptic.txt b/Documentation/devicetree/bindings/input/regulator-haptic.txt
new file mode 100644
index 00000000000..3ed1c7eb2f9
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/regulator-haptic.txt
@@ -0,0 +1,21 @@
+* Regulator Haptic Device Tree Bindings
+
+Required Properties:
+ - compatible : Should be "regulator-haptic"
+ - haptic-supply : Power supply to the haptic motor.
+	[*] refer Documentation/devicetree/bindings/regulator/regulator.txt
+
+ - max-microvolt : The maximum voltage value supplied to the haptic motor.
+		[The unit of the voltage is a micro]
+
+ - min-microvolt : The minimum voltage value supplied to the haptic motor.
+		[The unit of the voltage is a micro]
+
+Example:
+
+	haptics {
+		compatible = "regulator-haptic";
+		haptic-supply = <&motor_regulator>;
+		max-microvolt = <2700000>;
+		min-microvolt = <1100000>;
+	};
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 23297ab6163..1da0a20c42e 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -394,6 +394,18 @@ config INPUT_CM109
 	  To compile this driver as a module, choose M here: the module will be
 	  called cm109.
 
+config INPUT_REGULATOR_HAPTIC
+	tristate "Regulator haptics support"
+	depends on REGULATOR
+	select INPUT_FF_MEMLESS
+	help
+	  This option enables device driver support for the haptic controlled
+	  by a regulator. This driver supports ff-memless interface
+	  from input framework.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called regulator-haptic.
+
 config INPUT_RETU_PWRBUTTON
 	tristate "Retu Power button Driver"
 	depends on MFD_RETU
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index 19c760361f8..1f135af4af0 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -53,6 +53,7 @@ obj-$(CONFIG_INPUT_PMIC8XXX_PWRKEY)	+= pmic8xxx-pwrkey.o
 obj-$(CONFIG_INPUT_POWERMATE)		+= powermate.o
 obj-$(CONFIG_INPUT_PWM_BEEPER)		+= pwm-beeper.o
 obj-$(CONFIG_INPUT_RB532_BUTTON)	+= rb532_button.o
+obj-$(CONFIG_INPUT_REGULATOR_HAPTIC)	+= regulator-haptic.o
 obj-$(CONFIG_INPUT_RETU_PWRBUTTON)	+= retu-pwrbutton.o
 obj-$(CONFIG_INPUT_GPIO_ROTARY_ENCODER)	+= rotary_encoder.o
 obj-$(CONFIG_INPUT_SGI_BTNS)		+= sgi_btns.o
diff --git a/drivers/input/misc/regulator-haptic.c b/drivers/input/misc/regulator-haptic.c
new file mode 100644
index 00000000000..942622189be
--- /dev/null
+++ b/drivers/input/misc/regulator-haptic.c
@@ -0,0 +1,279 @@
+/*
+ * Regulator haptic driver
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Jaewon Kim <jaewon02.kim@samsung.com>
+ * Author: Hyunhee Kim <hyunhee.kim@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_data/regulator-haptic.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+#define MAX_MAGNITUDE_SHIFT	16
+
+struct regulator_haptic {
+	struct device *dev;
+	struct input_dev *input_dev;
+	struct regulator *regulator;
+
+	struct work_struct work;
+	struct mutex mutex;
+
+	bool active;
+	bool suspended;
+
+	unsigned int max_volt;
+	unsigned int min_volt;
+	unsigned int magnitude;
+};
+
+static int regulator_haptic_toggle(struct regulator_haptic *haptic, bool on)
+{
+	int error;
+
+	if (haptic->active != on) {
+
+		error = on ? regulator_enable(haptic->regulator) :
+			     regulator_disable(haptic->regulator);
+		if (error) {
+			dev_err(haptic->dev,
+				"failed to switch regulator %s: %d\n",
+				on ? "on" : "off", error);
+			return error;
+		}
+
+		haptic->active = on;
+	}
+
+	return 0;
+}
+
+static int regulator_haptic_set_voltage(struct regulator_haptic *haptic,
+					 unsigned int magnitude)
+{
+	u64 volt_mag_multi;
+	unsigned int intensity;
+	int error;
+
+	volt_mag_multi = (u64)(haptic->max_volt - haptic->min_volt) * magnitude;
+	intensity = (unsigned int)(volt_mag_multi >> MAX_MAGNITUDE_SHIFT);
+
+	error = regulator_set_voltage(haptic->regulator,
+				      intensity + haptic->min_volt,
+				      haptic->max_volt);
+	if (error) {
+		dev_err(haptic->dev, "cannot set regulator voltage to %d: %d\n",
+			intensity + haptic->min_volt, error);
+		return error;
+	}
+
+	return 0;
+}
+
+static void regulator_haptic_work(struct work_struct *work)
+{
+	struct regulator_haptic *haptic = container_of(work,
+					struct regulator_haptic, work);
+	unsigned int magnitude;
+	int error;
+
+	mutex_lock(&haptic->mutex);
+
+	if (haptic->suspended)
+		goto out;
+
+	magnitude = ACCESS_ONCE(haptic->magnitude);
+
+	error = regulator_haptic_set_voltage(haptic, magnitude);
+	if (error)
+		goto out;
+
+	regulator_haptic_toggle(haptic, magnitude != 0);
+
+out:
+	mutex_unlock(&haptic->mutex);
+}
+
+static int regulator_haptic_play_effect(struct input_dev *input, void *data,
+					struct ff_effect *effect)
+{
+	struct regulator_haptic *haptic = input_get_drvdata(input);
+
+	haptic->magnitude = effect->u.rumble.strong_magnitude;
+	if (!haptic->magnitude)
+		haptic->magnitude = effect->u.rumble.weak_magnitude;
+
+	schedule_work(&haptic->work);
+
+	return 0;
+}
+
+static void regulator_haptic_close(struct input_dev *input)
+{
+	struct regulator_haptic *haptic = input_get_drvdata(input);
+
+	cancel_work_sync(&haptic->work);
+	regulator_haptic_set_voltage(haptic, 0);
+	regulator_haptic_toggle(haptic, false);
+}
+
+static int __maybe_unused
+regulator_haptic_parse_dt(struct device *dev, struct regulator_haptic *haptic)
+{
+	struct device_node *node;
+	int error;
+
+	node = dev->of_node;
+	if(!node) {
+		dev_err(dev, "Missing dveice tree data\n");
+		return -EINVAL;
+	}
+
+	error = of_property_read_u32(node, "max-microvolt", &haptic->max_volt);
+	if (error) {
+		dev_err(dev, "cannot parse max-microvolt\n");
+		return error;
+	}
+
+	error = of_property_read_u32(node, "min-microvolt", &haptic->min_volt);
+	if (error) {
+		dev_err(dev, "cannot parse min-microvolt\n");
+		return error;
+	}
+
+	return 0;
+}
+
+static int regulator_haptic_probe(struct platform_device *pdev)
+{
+	const struct regulator_haptic_data *pdata = dev_get_platdata(&pdev->dev);
+	struct regulator_haptic *haptic;
+	struct input_dev *input_dev;
+	int error;
+
+	haptic = devm_kzalloc(&pdev->dev, sizeof(*haptic), GFP_KERNEL);
+	if (!haptic)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, haptic);
+	haptic->dev = &pdev->dev;
+	mutex_init(&haptic->mutex);
+	INIT_WORK(&haptic->work, regulator_haptic_work);
+
+	if (pdata) {
+		haptic->max_volt = pdata->max_volt;
+		haptic->min_volt = pdata->min_volt;
+	} else if (IS_ENABLED(CONFIG_OF)) {
+		error = regulator_haptic_parse_dt(&pdev->dev, haptic);
+		if (error)
+			return error;
+	} else {
+		dev_err(&pdev->dev, "Missing platform data\n");
+		return -EINVAL;
+	}
+
+	haptic->regulator = devm_regulator_get_exclusive(&pdev->dev, "haptic");
+	if (IS_ERR(haptic->regulator)) {
+		dev_err(&pdev->dev, "failed to get regulator\n");
+		return PTR_ERR(haptic->regulator);
+	}
+
+	input_dev = devm_input_allocate_device(&pdev->dev);
+	if (!input_dev)
+		return	-ENOMEM;
+
+	haptic->input_dev = input_dev;
+	haptic->input_dev->name = "regulator-haptic";
+	haptic->input_dev->dev.parent = &pdev->dev;
+	haptic->input_dev->close = regulator_haptic_close;
+	input_set_drvdata(haptic->input_dev, haptic);
+	input_set_capability(haptic->input_dev, EV_FF, FF_RUMBLE);
+
+	error = input_ff_create_memless(input_dev, NULL,
+					regulator_haptic_play_effect);
+	if (error) {
+		dev_err(&pdev->dev, "failed to create force-feedback\n");
+		return error;
+	}
+
+	error = input_register_device(haptic->input_dev);
+	if (error) {
+		dev_err(&pdev->dev, "failed to register input device\n");
+		return error;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused regulator_haptic_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct regulator_haptic *haptic = platform_get_drvdata(pdev);
+	int error;
+
+	error = mutex_lock_interruptible(&haptic->mutex);
+	if (error)
+		return error;
+
+	regulator_haptic_set_voltage(haptic, 0);
+	regulator_haptic_toggle(haptic, false);
+
+	haptic->suspended = true;
+
+	mutex_unlock(&haptic->mutex);
+
+	return 0;
+}
+
+static int __maybe_unused regulator_haptic_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct regulator_haptic *haptic = platform_get_drvdata(pdev);
+	unsigned int magnitude;
+
+	mutex_lock(&haptic->mutex);
+
+	haptic->suspended = false;
+
+	magnitude = ACCESS_ONCE(haptic->magnitude);
+	if (magnitude) {
+		regulator_haptic_set_voltage(haptic, magnitude);
+		regulator_haptic_toggle(haptic, true);
+	}
+
+	mutex_unlock(&haptic->mutex);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(regulator_haptic_pm_ops,
+		regulator_haptic_suspend, regulator_haptic_resume);
+
+static struct of_device_id regulator_haptic_dt_match[] = {
+	{ .compatible = "regulator-haptic" },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver regulator_haptic_driver = {
+	.probe		= regulator_haptic_probe,
+	.driver		= {
+		.name		= "regulator-haptic",
+		.of_match_table = regulator_haptic_dt_match,
+		.pm		= &regulator_haptic_pm_ops,
+	},
+};
+module_platform_driver(regulator_haptic_driver);
+
+MODULE_AUTHOR("Jaewon Kim <jaewon02.kim@samsung.com>");
+MODULE_AUTHOR("Hyunhee Kim <hyunhee.kim@samsung.com>");
+MODULE_DESCRIPTION("Regulator haptic driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/platform_data/regulator-haptic.h b/include/linux/platform_data/regulator-haptic.h
new file mode 100644
index 00000000000..5658e58e073
--- /dev/null
+++ b/include/linux/platform_data/regulator-haptic.h
@@ -0,0 +1,29 @@
+/*
+ * Regulator Haptic Platform Data
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Jaewon Kim <jaewon02.kim@samsung.com>
+ * Author: Hyunhee Kim <hyunhee.kim@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _REGULATOR_HAPTIC_H
+#define _REGULATOR_HAPTIC_H
+
+/*
+ * struct regulator_haptic_data - Platform device data
+ *
+ * @max_volt: maximum voltage value supplied to the haptic motor.
+ *		<The unit of the voltage is a micro>
+ * @min_volt: minimum voltage value supplied to the haptic motor.
+ *		<The unit of the voltage is a micro>
+ */
+struct regulator_haptic_data {
+	unsigned int max_volt;
+	unsigned int min_volt;
+};
+
+#endif /* _REGULATOR_HAPTIC_H */
-- 
cgit v1.2.3-70-g09d2


From 86d7500326ea71ea72aeaf0da78671eef28be2af Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 21 Dec 2014 11:05:44 +0100
Subject: ASoC: dapm: Simplify fully route card handling

For legacy reasons the ASoC framework assumes that a CODEC INPUT or OUTPUT
widget that is not explicitly connected to a external source or sink is
potentially connected to a source or a sink and hence the framework treats
the widget itself as source (for INPUT) or sink (for OUTPUT). For this
reason a INPUT or OUTPUT widget that is really not connected needs to be
explicitly marked as so.

Setting the card's fully_routed flag will cause the ASoC core, once that all
widgets and routes have been registered, to go through the list of all
widgets and mark all INPUT and OUTPUT that are not externally connected as
non-connected. This essentially negates the default behaviour of treating
INPUT or OUTPUT widgets without external routes as sources or sinks.

This patch takes a different approach while getting the same result. Instead
of first marking INPUT and OUTPUT widgets as sinks/sources and then later
marking them as non-connected, just never mark them as a sink or a source if
the fully_routed flag is set on a card.

This requires a lot less code and also results in a slightly faster card
initialization since there is no need to iterate over all widgets and check
whether the INPUT and OUTPUT widgets are connected or not.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |   1 -
 sound/soc/soc-core.c     |   3 --
 sound/soc/soc-dapm.c     | 104 ++++++++---------------------------------------
 3 files changed, 16 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 89823cfe6f0..ecffeccb553 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -431,7 +431,6 @@ int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm,
 					   const char *pin);
 int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm,
 				const char *pin);
-void snd_soc_dapm_auto_nc_pins(struct snd_soc_card *card);
 unsigned int dapm_kcontrol_get_value(const struct snd_kcontrol *kcontrol);
 
 /* Mostly internal - should not normally be used */
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 985052b3fbe..89aa6717f26 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1626,9 +1626,6 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 		}
 	}
 
-	if (card->fully_routed)
-		snd_soc_dapm_auto_nc_pins(card);
-
 	snd_soc_dapm_new_widgets(card);
 
 	ret = snd_card_register(card->snd_card);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index b8eba93b5fa..ea496842ee8 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2279,6 +2279,9 @@ static void dapm_update_widget_flags(struct snd_soc_dapm_widget *w)
 
 	switch (w->id) {
 	case snd_soc_dapm_input:
+		/* On a fully routed card a input is never a source */
+		if (w->dapm->card->fully_routed)
+			break;
 		w->is_source = 1;
 		list_for_each_entry(p, &w->sources, list_sink) {
 			if (p->source->id == snd_soc_dapm_micbias ||
@@ -2291,6 +2294,9 @@ static void dapm_update_widget_flags(struct snd_soc_dapm_widget *w)
 		}
 		break;
 	case snd_soc_dapm_output:
+		/* On a fully routed card a output is never a sink */
+		if (w->dapm->card->fully_routed)
+			break;
 		w->is_sink = 1;
 		list_for_each_entry(p, &w->sinks, list_source) {
 			if (p->sink->id == snd_soc_dapm_spk ||
@@ -3085,16 +3091,24 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 
 	switch (w->id) {
 	case snd_soc_dapm_mic:
-	case snd_soc_dapm_input:
 		w->is_source = 1;
 		w->power_check = dapm_generic_check_power;
 		break;
+	case snd_soc_dapm_input:
+		if (!dapm->card->fully_routed)
+			w->is_source = 1;
+		w->power_check = dapm_generic_check_power;
+		break;
 	case snd_soc_dapm_spk:
 	case snd_soc_dapm_hp:
-	case snd_soc_dapm_output:
 		w->is_sink = 1;
 		w->power_check = dapm_generic_check_power;
 		break;
+	case snd_soc_dapm_output:
+		if (!dapm->card->fully_routed)
+			w->is_sink = 1;
+		w->power_check = dapm_generic_check_power;
+		break;
 	case snd_soc_dapm_vmid:
 	case snd_soc_dapm_siggen:
 		w->is_source = 1;
@@ -3808,92 +3822,6 @@ int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm,
 }
 EXPORT_SYMBOL_GPL(snd_soc_dapm_ignore_suspend);
 
-/**
- * dapm_is_external_path() - Checks if a path is a external path
- * @card: The card the path belongs to
- * @path: The path to check
- *
- * Returns true if the path is either between two different DAPM contexts or
- * between two external pins of the same DAPM context. Otherwise returns
- * false.
- */
-static bool dapm_is_external_path(struct snd_soc_card *card,
-	struct snd_soc_dapm_path *path)
-{
-	dev_dbg(card->dev,
-		"... Path %s(id:%d dapm:%p) - %s(id:%d dapm:%p)\n",
-		path->source->name, path->source->id, path->source->dapm,
-		path->sink->name, path->sink->id, path->sink->dapm);
-
-	/* Connection between two different DAPM contexts */
-	if (path->source->dapm != path->sink->dapm)
-		return true;
-
-	/* Loopback connection from external pin to external pin */
-	if (path->sink->id == snd_soc_dapm_input) {
-		switch (path->source->id) {
-		case snd_soc_dapm_output:
-		case snd_soc_dapm_micbias:
-			return true;
-		default:
-			break;
-		}
-	}
-
-	return false;
-}
-
-static bool snd_soc_dapm_widget_in_card_paths(struct snd_soc_card *card,
-					      struct snd_soc_dapm_widget *w)
-{
-	struct snd_soc_dapm_path *p;
-
-	list_for_each_entry(p, &w->sources, list_sink) {
-		if (dapm_is_external_path(card, p))
-			return true;
-	}
-
-	list_for_each_entry(p, &w->sinks, list_source) {
-		if (dapm_is_external_path(card, p))
-			return true;
-	}
-
-	return false;
-}
-
-/**
- * snd_soc_dapm_auto_nc_pins - call snd_soc_dapm_nc_pin for unused pins
- * @card: The card whose pins should be processed
- *
- * Automatically call snd_soc_dapm_nc_pin() for any external pins in the card
- * which are unused. Pins are used if they are connected externally to a
- * component, whether that be to some other device, or a loop-back connection to
- * the component itself.
- */
-void snd_soc_dapm_auto_nc_pins(struct snd_soc_card *card)
-{
-	struct snd_soc_dapm_widget *w;
-
-	dev_dbg(card->dev, "ASoC: Auto NC: DAPMs: card:%p\n", &card->dapm);
-
-	list_for_each_entry(w, &card->widgets, list) {
-		switch (w->id) {
-		case snd_soc_dapm_input:
-		case snd_soc_dapm_output:
-			dev_dbg(card->dev, "ASoC: Auto NC: Checking widget %s\n",
-				w->name);
-			if (!snd_soc_dapm_widget_in_card_paths(card, w)) {
-				dev_dbg(card->dev,
-					"... Not in map; disabling\n");
-				snd_soc_dapm_nc_pin(w->dapm, w->name);
-			}
-			break;
-		default:
-			break;
-		}
-	}
-}
-
 /**
  * snd_soc_dapm_free - free dapm resources
  * @dapm: DAPM context
-- 
cgit v1.2.3-70-g09d2


From c5f4546593e9911800f0926c1090959b58bc5c93 Mon Sep 17 00:00:00 2001
From: Seth Jennings <sjenning@redhat.com>
Date: Tue, 16 Dec 2014 11:58:18 -0600
Subject: livepatch: kernel: add TAINT_LIVEPATCH

This adds a new taint flag to indicate when the kernel or a kernel
module has been live patched.  This will provide a clean indication in
bug reports that live patching was used.

Additionally, if the crash occurs in a live patched function, the live
patch module will appear beside the patched function in the backtrace.

Signed-off-by: Seth Jennings <sjenning@redhat.com>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 Documentation/oops-tracing.txt  | 2 ++
 Documentation/sysctl/kernel.txt | 1 +
 include/linux/kernel.h          | 1 +
 kernel/panic.c                  | 2 ++
 4 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/Documentation/oops-tracing.txt b/Documentation/oops-tracing.txt
index beefb9f8290..f3ac05cc23e 100644
--- a/Documentation/oops-tracing.txt
+++ b/Documentation/oops-tracing.txt
@@ -270,6 +270,8 @@ characters, each representing a particular tainted value.
 
  15: 'L' if a soft lockup has previously occurred on the system.
 
+ 16: 'K' if the kernel has been live patched.
+
 The primary reason for the 'Tainted: ' string is to tell kernel
 debuggers if this is a clean kernel or if anything unusual has
 occurred.  Tainting is permanent: even if an offending module is
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 75511efefc6..83ab25660fc 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -843,6 +843,7 @@ can be ORed together:
 8192 - An unsigned module has been loaded in a kernel supporting module
        signature.
 16384 - A soft lockup has previously occurred on the system.
+32768 - The kernel has been live patched.
 
 ==============================================================
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5449d2f4a1e..d03e3deee09 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -471,6 +471,7 @@ extern enum system_states {
 #define TAINT_OOT_MODULE		12
 #define TAINT_UNSIGNED_MODULE		13
 #define TAINT_SOFTLOCKUP		14
+#define TAINT_LIVEPATCH			15
 
 extern const char hex_asc[];
 #define hex_asc_lo(x)	hex_asc[((x) & 0x0f)]
diff --git a/kernel/panic.c b/kernel/panic.c
index 4d8d6f906de..8136ad76e5f 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -226,6 +226,7 @@ static const struct tnt tnts[] = {
 	{ TAINT_OOT_MODULE,		'O', ' ' },
 	{ TAINT_UNSIGNED_MODULE,	'E', ' ' },
 	{ TAINT_SOFTLOCKUP,		'L', ' ' },
+	{ TAINT_LIVEPATCH,		'K', ' ' },
 };
 
 /**
@@ -246,6 +247,7 @@ static const struct tnt tnts[] = {
  *  'O' - Out-of-tree module has been loaded.
  *  'E' - Unsigned module has been loaded.
  *  'L' - A soft lockup has previously occurred.
+ *  'K' - Kernel has been live patched.
  *
  *	The string is overwritten by the next call to print_tainted().
  */
-- 
cgit v1.2.3-70-g09d2


From b700e7f03df5d92f85fa5247fe1f557528d3363d Mon Sep 17 00:00:00 2001
From: Seth Jennings <sjenning@redhat.com>
Date: Tue, 16 Dec 2014 11:58:19 -0600
Subject: livepatch: kernel: add support for live patching

This commit introduces code for the live patching core.  It implements
an ftrace-based mechanism and kernel interface for doing live patching
of kernel and kernel module functions.

It represents the greatest common functionality set between kpatch and
kgraft and can accept patches built using either method.

This first version does not implement any consistency mechanism that
ensures that old and new code do not run together.  In practice, ~90% of
CVEs are safe to apply in this way, since they simply add a conditional
check.  However, any function change that can not execute safely with
the old version of the function can _not_ be safely applied in this
version.

[ jkosina@suse.cz: due to the number of contributions that got folded into
  this original patch from Seth Jennings, add SUSE's copyright as well, as
  discussed via e-mail ]

Signed-off-by: Seth Jennings <sjenning@redhat.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Miroslav Benes <mbenes@suse.cz>
Signed-off-by: Petr Mladek <pmladek@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 Documentation/ABI/testing/sysfs-kernel-livepatch |  44 ++
 MAINTAINERS                                      |  13 +
 arch/x86/Kconfig                                 |   3 +
 arch/x86/include/asm/livepatch.h                 |  37 +
 arch/x86/kernel/Makefile                         |   1 +
 arch/x86/kernel/livepatch.c                      |  90 +++
 include/linux/livepatch.h                        | 133 ++++
 kernel/Makefile                                  |   1 +
 kernel/livepatch/Kconfig                         |  18 +
 kernel/livepatch/Makefile                        |   3 +
 kernel/livepatch/core.c                          | 930 +++++++++++++++++++++++
 11 files changed, 1273 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-kernel-livepatch
 create mode 100644 arch/x86/include/asm/livepatch.h
 create mode 100644 arch/x86/kernel/livepatch.c
 create mode 100644 include/linux/livepatch.h
 create mode 100644 kernel/livepatch/Kconfig
 create mode 100644 kernel/livepatch/Makefile
 create mode 100644 kernel/livepatch/core.c

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-kernel-livepatch b/Documentation/ABI/testing/sysfs-kernel-livepatch
new file mode 100644
index 00000000000..5bf42a840b2
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-livepatch
@@ -0,0 +1,44 @@
+What:		/sys/kernel/livepatch
+Date:		Nov 2014
+KernelVersion:	3.19.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		Interface for kernel live patching
+
+		The /sys/kernel/livepatch directory contains subdirectories for
+		each loaded live patch module.
+
+What:		/sys/kernel/livepatch/<patch>
+Date:		Nov 2014
+KernelVersion:	3.19.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		The patch directory contains subdirectories for each kernel
+		object (vmlinux or a module) in which it patched functions.
+
+What:		/sys/kernel/livepatch/<patch>/enabled
+Date:		Nov 2014
+KernelVersion:	3.19.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		A writable attribute that indicates whether the patched
+		code is currently applied.  Writing 0 will disable the patch
+		while writing 1 will re-enable the patch.
+
+What:		/sys/kernel/livepatch/<patch>/<object>
+Date:		Nov 2014
+KernelVersion:	3.19.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		The object directory contains subdirectories for each function
+		that is patched within the object.
+
+What:		/sys/kernel/livepatch/<patch>/<object>/<function>
+Date:		Nov 2014
+KernelVersion:	3.19.0
+Contact:	live-patching@vger.kernel.org
+Description:
+		The function directory contains attributes regarding the
+		properties and state of the patched function.
+
+		There are currently no such attributes.
diff --git a/MAINTAINERS b/MAINTAINERS
index ddb9ac8d32b..df6a0784b46 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5784,6 +5784,19 @@ F:	Documentation/misc-devices/lis3lv02d
 F:	drivers/misc/lis3lv02d/
 F:	drivers/platform/x86/hp_accel.c
 
+LIVE PATCHING
+M:	Josh Poimboeuf <jpoimboe@redhat.com>
+M:	Seth Jennings <sjenning@redhat.com>
+M:	Jiri Kosina <jkosina@suse.cz>
+M:	Vojtech Pavlik <vojtech@suse.cz>
+S:	Maintained
+F:	kernel/livepatch/
+F:	include/linux/livepatch.h
+F:	arch/x86/include/asm/livepatch.h
+F:	arch/x86/kernel/livepatch.c
+F:	Documentation/ABI/testing/sysfs-kernel-livepatch
+L:	live-patching@vger.kernel.org
+
 LLC (802.2)
 M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 S:	Maintained
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba397bde794..460b31b7993 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -17,6 +17,7 @@ config X86_64
 	depends on 64BIT
 	select X86_DEV_DMA_OPS
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_HAVE_LIVE_PATCHING
 
 ### Arch settings
 config X86
@@ -2008,6 +2009,8 @@ config CMDLINE_OVERRIDE
 	  This is used to work around broken boot loaders.  This should
 	  be set to 'N' under normal conditions.
 
+source "kernel/livepatch/Kconfig"
+
 endmenu
 
 config ARCH_ENABLE_MEMORY_HOTPLUG
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
new file mode 100644
index 00000000000..d529db1b1ed
--- /dev/null
+++ b/arch/x86/include/asm/livepatch.h
@@ -0,0 +1,37 @@
+/*
+ * livepatch.h - x86-specific Kernel Live Patching Core
+ *
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ * Copyright (C) 2014 SUSE
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ASM_X86_LIVEPATCH_H
+#define _ASM_X86_LIVEPATCH_H
+
+#include <linux/module.h>
+
+#ifdef CONFIG_LIVE_PATCHING
+#ifndef CC_USING_FENTRY
+#error Your compiler must support -mfentry for live patching to work
+#endif
+extern int klp_write_module_reloc(struct module *mod, unsigned long type,
+				  unsigned long loc, unsigned long value);
+
+#else
+#error Live patching support is disabled; check CONFIG_LIVE_PATCHING
+#endif
+
+#endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 5d4502c8b98..316b34e74c1 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
+obj-$(CONFIG_LIVE_PATCHING)	+= livepatch.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c
new file mode 100644
index 00000000000..ff3c3101d00
--- /dev/null
+++ b/arch/x86/kernel/livepatch.c
@@ -0,0 +1,90 @@
+/*
+ * livepatch.c - x86-specific Kernel Live Patching Core
+ *
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ * Copyright (C) 2014 SUSE
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/page_types.h>
+#include <asm/elf.h>
+#include <asm/livepatch.h>
+
+/**
+ * klp_write_module_reloc() - write a relocation in a module
+ * @mod:	module in which the section to be modified is found
+ * @type:	ELF relocation type (see asm/elf.h)
+ * @loc:	address that the relocation should be written to
+ * @value:	relocation value (sym address + addend)
+ *
+ * This function writes a relocation to the specified location for
+ * a particular module.
+ */
+int klp_write_module_reloc(struct module *mod, unsigned long type,
+			   unsigned long loc, unsigned long value)
+{
+	int ret, numpages, size = 4;
+	bool readonly;
+	unsigned long val;
+	unsigned long core = (unsigned long)mod->module_core;
+	unsigned long core_ro_size = mod->core_ro_size;
+	unsigned long core_size = mod->core_size;
+
+	switch (type) {
+	case R_X86_64_NONE:
+		return 0;
+	case R_X86_64_64:
+		val = value;
+		size = 8;
+		break;
+	case R_X86_64_32:
+		val = (u32)value;
+		break;
+	case R_X86_64_32S:
+		val = (s32)value;
+		break;
+	case R_X86_64_PC32:
+		val = (u32)(value - loc);
+		break;
+	default:
+		/* unsupported relocation type */
+		return -EINVAL;
+	}
+
+	if (loc < core || loc >= core + core_size)
+		/* loc does not point to any symbol inside the module */
+		return -EINVAL;
+
+	if (loc < core + core_ro_size)
+		readonly = true;
+	else
+		readonly = false;
+
+	/* determine if the relocation spans a page boundary */
+	numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2;
+
+	if (readonly)
+		set_memory_rw(loc & PAGE_MASK, numpages);
+
+	ret = probe_kernel_write((void *)loc, &val, size);
+
+	if (readonly)
+		set_memory_ro(loc & PAGE_MASK, numpages);
+
+	return ret;
+}
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
new file mode 100644
index 00000000000..950bc615842
--- /dev/null
+++ b/include/linux/livepatch.h
@@ -0,0 +1,133 @@
+/*
+ * livepatch.h - Kernel Live Patching Core
+ *
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ * Copyright (C) 2014 SUSE
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _LINUX_LIVEPATCH_H_
+#define _LINUX_LIVEPATCH_H_
+
+#include <linux/module.h>
+#include <linux/ftrace.h>
+
+#if IS_ENABLED(CONFIG_LIVE_PATCHING)
+
+#include <asm/livepatch.h>
+
+enum klp_state {
+	KLP_DISABLED,
+	KLP_ENABLED
+};
+
+/**
+ * struct klp_func - function structure for live patching
+ * @old_name:	name of the function to be patched
+ * @new_func:	pointer to the patched function code
+ * @old_addr:	a hint conveying at what address the old function
+ *		can be found (optional, vmlinux patches only)
+ * @kobj:	kobject for sysfs resources
+ * @fops:	ftrace operations structure
+ * @state:	tracks function-level patch application state
+ */
+struct klp_func {
+	/* external */
+	const char *old_name;
+	void *new_func;
+	/*
+	 * The old_addr field is optional and can be used to resolve
+	 * duplicate symbol names in the vmlinux object.  If this
+	 * information is not present, the symbol is located by name
+	 * with kallsyms. If the name is not unique and old_addr is
+	 * not provided, the patch application fails as there is no
+	 * way to resolve the ambiguity.
+	 */
+	unsigned long old_addr;
+
+	/* internal */
+	struct kobject kobj;
+	struct ftrace_ops *fops;
+	enum klp_state state;
+};
+
+/**
+ * struct klp_reloc - relocation structure for live patching
+ * @loc:	address where the relocation will be written
+ * @val:	address of the referenced symbol (optional,
+ *		vmlinux	patches only)
+ * @type:	ELF relocation type
+ * @name:	name of the referenced symbol (for lookup/verification)
+ * @addend:	offset from the referenced symbol
+ * @external:	symbol is either exported or within the live patch module itself
+ */
+struct klp_reloc {
+	unsigned long loc;
+	unsigned long val;
+	unsigned long type;
+	const char *name;
+	int addend;
+	int external;
+};
+
+/**
+ * struct klp_object - kernel object structure for live patching
+ * @name:	module name (or NULL for vmlinux)
+ * @relocs:	relocation entries to be applied at load time
+ * @funcs:	function entries for functions to be patched in the object
+ * @kobj:	kobject for sysfs resources
+ * @mod:	kernel module associated with the patched object
+ * 		(NULL for vmlinux)
+ * @state:	tracks object-level patch application state
+ */
+struct klp_object {
+	/* external */
+	const char *name;
+	struct klp_reloc *relocs;
+	struct klp_func *funcs;
+
+	/* internal */
+	struct kobject *kobj;
+	struct module *mod;
+	enum klp_state state;
+};
+
+/**
+ * struct klp_patch - patch structure for live patching
+ * @mod:	reference to the live patch module
+ * @objs:	object entries for kernel objects to be patched
+ * @list:	list node for global list of registered patches
+ * @kobj:	kobject for sysfs resources
+ * @state:	tracks patch-level application state
+ */
+struct klp_patch {
+	/* external */
+	struct module *mod;
+	struct klp_object *objs;
+
+	/* internal */
+	struct list_head list;
+	struct kobject kobj;
+	enum klp_state state;
+};
+
+extern int klp_register_patch(struct klp_patch *);
+extern int klp_unregister_patch(struct klp_patch *);
+extern int klp_enable_patch(struct klp_patch *);
+extern int klp_disable_patch(struct klp_patch *);
+
+#endif /* CONFIG_LIVE_PATCHING */
+
+#endif /* _LINUX_LIVEPATCH_H_ */
diff --git a/kernel/Makefile b/kernel/Makefile
index a59481a3fa6..616994f0a76 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -26,6 +26,7 @@ obj-y += power/
 obj-y += printk/
 obj-y += irq/
 obj-y += rcu/
+obj-y += livepatch/
 
 obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
 obj-$(CONFIG_FREEZER) += freezer.o
diff --git a/kernel/livepatch/Kconfig b/kernel/livepatch/Kconfig
new file mode 100644
index 00000000000..96da00fbc12
--- /dev/null
+++ b/kernel/livepatch/Kconfig
@@ -0,0 +1,18 @@
+config ARCH_HAVE_LIVE_PATCHING
+	boolean
+	help
+	  Arch supports kernel live patching
+
+config LIVE_PATCHING
+	boolean "Kernel Live Patching"
+	depends on DYNAMIC_FTRACE_WITH_REGS
+	depends on MODULES
+	depends on SYSFS
+	depends on KALLSYMS_ALL
+	depends on ARCH_HAVE_LIVE_PATCHING
+	help
+	  Say Y here if you want to support kernel live patching.
+	  This option has no runtime impact until a kernel "patch"
+	  module uses the interface provided by this option to register
+	  a patch, causing calls to patched functions to be redirected
+	  to new function code contained in the patch module.
diff --git a/kernel/livepatch/Makefile b/kernel/livepatch/Makefile
new file mode 100644
index 00000000000..7c1f0086142
--- /dev/null
+++ b/kernel/livepatch/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_LIVE_PATCHING) += livepatch.o
+
+livepatch-objs := core.o
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
new file mode 100644
index 00000000000..f99fe189d59
--- /dev/null
+++ b/kernel/livepatch/core.c
@@ -0,0 +1,930 @@
+/*
+ * core.c - Kernel Live Patching Core
+ *
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ * Copyright (C) 2014 SUSE
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/ftrace.h>
+#include <linux/list.h>
+#include <linux/kallsyms.h>
+#include <linux/livepatch.h>
+
+/*
+ * The klp_mutex protects the klp_patches list and state transitions of any
+ * structure reachable from the patches list.  References to any structure must
+ * be obtained under mutex protection.
+ */
+
+static DEFINE_MUTEX(klp_mutex);
+static LIST_HEAD(klp_patches);
+
+static struct kobject *klp_root_kobj;
+
+static bool klp_is_module(struct klp_object *obj)
+{
+	return obj->name;
+}
+
+static bool klp_is_object_loaded(struct klp_object *obj)
+{
+	return !obj->name || obj->mod;
+}
+
+/* sets obj->mod if object is not vmlinux and module is found */
+static void klp_find_object_module(struct klp_object *obj)
+{
+	if (!klp_is_module(obj))
+		return;
+
+	mutex_lock(&module_mutex);
+	/*
+	 * We don't need to take a reference on the module here because we have
+	 * the klp_mutex, which is also taken by the module notifier.  This
+	 * prevents any module from unloading until we release the klp_mutex.
+	 */
+	obj->mod = find_module(obj->name);
+	mutex_unlock(&module_mutex);
+}
+
+/* klp_mutex must be held by caller */
+static bool klp_is_patch_registered(struct klp_patch *patch)
+{
+	struct klp_patch *mypatch;
+
+	list_for_each_entry(mypatch, &klp_patches, list)
+		if (mypatch == patch)
+			return true;
+
+	return false;
+}
+
+static bool klp_initialized(void)
+{
+	return klp_root_kobj;
+}
+
+struct klp_find_arg {
+	const char *objname;
+	const char *name;
+	unsigned long addr;
+	/*
+	 * If count == 0, the symbol was not found. If count == 1, a unique
+	 * match was found and addr is set.  If count > 1, there is
+	 * unresolvable ambiguity among "count" number of symbols with the same
+	 * name in the same object.
+	 */
+	unsigned long count;
+};
+
+static int klp_find_callback(void *data, const char *name,
+			     struct module *mod, unsigned long addr)
+{
+	struct klp_find_arg *args = data;
+
+	if ((mod && !args->objname) || (!mod && args->objname))
+		return 0;
+
+	if (strcmp(args->name, name))
+		return 0;
+
+	if (args->objname && strcmp(args->objname, mod->name))
+		return 0;
+
+	/*
+	 * args->addr might be overwritten if another match is found
+	 * but klp_find_object_symbol() handles this and only returns the
+	 * addr if count == 1.
+	 */
+	args->addr = addr;
+	args->count++;
+
+	return 0;
+}
+
+static int klp_find_object_symbol(const char *objname, const char *name,
+				  unsigned long *addr)
+{
+	struct klp_find_arg args = {
+		.objname = objname,
+		.name = name,
+		.addr = 0,
+		.count = 0
+	};
+
+	kallsyms_on_each_symbol(klp_find_callback, &args);
+
+	if (args.count == 0)
+		pr_err("symbol '%s' not found in symbol table\n", name);
+	else if (args.count > 1)
+		pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n",
+		       args.count, name, objname);
+	else {
+		*addr = args.addr;
+		return 0;
+	}
+
+	*addr = 0;
+	return -EINVAL;
+}
+
+struct klp_verify_args {
+	const char *name;
+	const unsigned long addr;
+};
+
+static int klp_verify_callback(void *data, const char *name,
+			       struct module *mod, unsigned long addr)
+{
+	struct klp_verify_args *args = data;
+
+	if (!mod &&
+	    !strcmp(args->name, name) &&
+	    args->addr == addr)
+		return 1;
+
+	return 0;
+}
+
+static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr)
+{
+	struct klp_verify_args args = {
+		.name = name,
+		.addr = addr,
+	};
+
+	if (kallsyms_on_each_symbol(klp_verify_callback, &args))
+		return 0;
+
+	pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?",
+		name, addr);
+	return -EINVAL;
+}
+
+static int klp_find_verify_func_addr(struct klp_object *obj,
+				     struct klp_func *func)
+{
+	int ret;
+
+#if defined(CONFIG_RANDOMIZE_BASE)
+	/* KASLR is enabled, disregard old_addr from user */
+	func->old_addr = 0;
+#endif
+
+	if (!func->old_addr || klp_is_module(obj))
+		ret = klp_find_object_symbol(obj->name, func->old_name,
+					     &func->old_addr);
+	else
+		ret = klp_verify_vmlinux_symbol(func->old_name,
+						func->old_addr);
+
+	return ret;
+}
+
+/*
+ * external symbols are located outside the parent object (where the parent
+ * object is either vmlinux or the kmod being patched).
+ */
+static int klp_find_external_symbol(struct module *pmod, const char *name,
+				    unsigned long *addr)
+{
+	const struct kernel_symbol *sym;
+
+	/* first, check if it's an exported symbol */
+	preempt_disable();
+	sym = find_symbol(name, NULL, NULL, true, true);
+	preempt_enable();
+	if (sym) {
+		*addr = sym->value;
+		return 0;
+	}
+
+	/* otherwise check if it's in another .o within the patch module */
+	return klp_find_object_symbol(pmod->name, name, addr);
+}
+
+static int klp_write_object_relocations(struct module *pmod,
+					struct klp_object *obj)
+{
+	int ret;
+	struct klp_reloc *reloc;
+
+	if (WARN_ON(!klp_is_object_loaded(obj)))
+		return -EINVAL;
+
+	if (WARN_ON(!obj->relocs))
+		return -EINVAL;
+
+	for (reloc = obj->relocs; reloc->name; reloc++) {
+		if (!klp_is_module(obj)) {
+			ret = klp_verify_vmlinux_symbol(reloc->name,
+							reloc->val);
+			if (ret)
+				return ret;
+		} else {
+			/* module, reloc->val needs to be discovered */
+			if (reloc->external)
+				ret = klp_find_external_symbol(pmod,
+							       reloc->name,
+							       &reloc->val);
+			else
+				ret = klp_find_object_symbol(obj->mod->name,
+							     reloc->name,
+							     &reloc->val);
+			if (ret)
+				return ret;
+		}
+		ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc,
+					     reloc->val + reloc->addend);
+		if (ret) {
+			pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n",
+			       reloc->name, reloc->val, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void notrace klp_ftrace_handler(unsigned long ip,
+				       unsigned long parent_ip,
+				       struct ftrace_ops *ops,
+				       struct pt_regs *regs)
+{
+	struct klp_func *func = ops->private;
+
+	regs->ip = (unsigned long)func->new_func;
+}
+
+static int klp_disable_func(struct klp_func *func)
+{
+	int ret;
+
+	if (WARN_ON(func->state != KLP_ENABLED))
+		return -EINVAL;
+
+	if (WARN_ON(!func->old_addr))
+		return -EINVAL;
+
+	ret = unregister_ftrace_function(func->fops);
+	if (ret) {
+		pr_err("failed to unregister ftrace handler for function '%s' (%d)\n",
+		       func->old_name, ret);
+		return ret;
+	}
+
+	ret = ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0);
+	if (ret)
+		pr_warn("function unregister succeeded but failed to clear the filter\n");
+
+	func->state = KLP_DISABLED;
+
+	return 0;
+}
+
+static int klp_enable_func(struct klp_func *func)
+{
+	int ret;
+
+	if (WARN_ON(!func->old_addr))
+		return -EINVAL;
+
+	if (WARN_ON(func->state != KLP_DISABLED))
+		return -EINVAL;
+
+	ret = ftrace_set_filter_ip(func->fops, func->old_addr, 0, 0);
+	if (ret) {
+		pr_err("failed to set ftrace filter for function '%s' (%d)\n",
+		       func->old_name, ret);
+		return ret;
+	}
+
+	ret = register_ftrace_function(func->fops);
+	if (ret) {
+		pr_err("failed to register ftrace handler for function '%s' (%d)\n",
+		       func->old_name, ret);
+		ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0);
+	} else {
+		func->state = KLP_ENABLED;
+	}
+
+	return ret;
+}
+
+static int klp_disable_object(struct klp_object *obj)
+{
+	struct klp_func *func;
+	int ret;
+
+	for (func = obj->funcs; func->old_name; func++) {
+		if (func->state != KLP_ENABLED)
+			continue;
+
+		ret = klp_disable_func(func);
+		if (ret)
+			return ret;
+	}
+
+	obj->state = KLP_DISABLED;
+
+	return 0;
+}
+
+static int klp_enable_object(struct klp_object *obj)
+{
+	struct klp_func *func;
+	int ret;
+
+	if (WARN_ON(obj->state != KLP_DISABLED))
+		return -EINVAL;
+
+	if (WARN_ON(!klp_is_object_loaded(obj)))
+		return -EINVAL;
+
+	for (func = obj->funcs; func->old_name; func++) {
+		ret = klp_enable_func(func);
+		if (ret)
+			goto unregister;
+	}
+	obj->state = KLP_ENABLED;
+
+	return 0;
+
+unregister:
+	WARN_ON(klp_disable_object(obj));
+	return ret;
+}
+
+static int __klp_disable_patch(struct klp_patch *patch)
+{
+	struct klp_object *obj;
+	int ret;
+
+	pr_notice("disabling patch '%s'\n", patch->mod->name);
+
+	for (obj = patch->objs; obj->funcs; obj++) {
+		if (obj->state != KLP_ENABLED)
+			continue;
+
+		ret = klp_disable_object(obj);
+		if (ret)
+			return ret;
+	}
+
+	patch->state = KLP_DISABLED;
+
+	return 0;
+}
+
+/**
+ * klp_disable_patch() - disables a registered patch
+ * @patch:	The registered, enabled patch to be disabled
+ *
+ * Unregisters the patched functions from ftrace.
+ *
+ * Return: 0 on success, otherwise error
+ */
+int klp_disable_patch(struct klp_patch *patch)
+{
+	int ret;
+
+	mutex_lock(&klp_mutex);
+
+	if (!klp_is_patch_registered(patch)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (patch->state == KLP_DISABLED) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = __klp_disable_patch(patch);
+
+err:
+	mutex_unlock(&klp_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(klp_disable_patch);
+
+static int __klp_enable_patch(struct klp_patch *patch)
+{
+	struct klp_object *obj;
+	int ret;
+
+	if (WARN_ON(patch->state != KLP_DISABLED))
+		return -EINVAL;
+
+	pr_notice_once("tainting kernel with TAINT_LIVEPATCH\n");
+	add_taint(TAINT_LIVEPATCH, LOCKDEP_STILL_OK);
+
+	pr_notice("enabling patch '%s'\n", patch->mod->name);
+
+	for (obj = patch->objs; obj->funcs; obj++) {
+		klp_find_object_module(obj);
+
+		if (!klp_is_object_loaded(obj))
+			continue;
+
+		ret = klp_enable_object(obj);
+		if (ret)
+			goto unregister;
+	}
+
+	patch->state = KLP_ENABLED;
+
+	return 0;
+
+unregister:
+	WARN_ON(__klp_disable_patch(patch));
+	return ret;
+}
+
+/**
+ * klp_enable_patch() - enables a registered patch
+ * @patch:	The registered, disabled patch to be enabled
+ *
+ * Performs the needed symbol lookups and code relocations,
+ * then registers the patched functions with ftrace.
+ *
+ * Return: 0 on success, otherwise error
+ */
+int klp_enable_patch(struct klp_patch *patch)
+{
+	int ret;
+
+	mutex_lock(&klp_mutex);
+
+	if (!klp_is_patch_registered(patch)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	ret = __klp_enable_patch(patch);
+
+err:
+	mutex_unlock(&klp_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(klp_enable_patch);
+
+/*
+ * Sysfs Interface
+ *
+ * /sys/kernel/livepatch
+ * /sys/kernel/livepatch/<patch>
+ * /sys/kernel/livepatch/<patch>/enabled
+ * /sys/kernel/livepatch/<patch>/<object>
+ * /sys/kernel/livepatch/<patch>/<object>/<func>
+ */
+
+static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct klp_patch *patch;
+	int ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return -EINVAL;
+
+	if (val != KLP_DISABLED && val != KLP_ENABLED)
+		return -EINVAL;
+
+	patch = container_of(kobj, struct klp_patch, kobj);
+
+	mutex_lock(&klp_mutex);
+
+	if (val == patch->state) {
+		/* already in requested state */
+		ret = -EINVAL;
+		goto err;
+	}
+
+	if (val == KLP_ENABLED) {
+		ret = __klp_enable_patch(patch);
+		if (ret)
+			goto err;
+	} else {
+		ret = __klp_disable_patch(patch);
+		if (ret)
+			goto err;
+	}
+
+	mutex_unlock(&klp_mutex);
+
+	return count;
+
+err:
+	mutex_unlock(&klp_mutex);
+	return ret;
+}
+
+static ssize_t enabled_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	struct klp_patch *patch;
+
+	patch = container_of(kobj, struct klp_patch, kobj);
+	return snprintf(buf, PAGE_SIZE-1, "%d\n", patch->state);
+}
+
+static struct kobj_attribute enabled_kobj_attr = __ATTR_RW(enabled);
+static struct attribute *klp_patch_attrs[] = {
+	&enabled_kobj_attr.attr,
+	NULL
+};
+
+static void klp_kobj_release_patch(struct kobject *kobj)
+{
+	/*
+	 * Once we have a consistency model we'll need to module_put() the
+	 * patch module here.  See klp_register_patch() for more details.
+	 */
+}
+
+static struct kobj_type klp_ktype_patch = {
+	.release = klp_kobj_release_patch,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.default_attrs = klp_patch_attrs,
+};
+
+static void klp_kobj_release_func(struct kobject *kobj)
+{
+	struct klp_func *func;
+
+	func = container_of(kobj, struct klp_func, kobj);
+	kfree(func->fops);
+}
+
+static struct kobj_type klp_ktype_func = {
+	.release = klp_kobj_release_func,
+	.sysfs_ops = &kobj_sysfs_ops,
+};
+
+/*
+ * Free all functions' kobjects in the array up to some limit. When limit is
+ * NULL, all kobjects are freed.
+ */
+static void klp_free_funcs_limited(struct klp_object *obj,
+				   struct klp_func *limit)
+{
+	struct klp_func *func;
+
+	for (func = obj->funcs; func->old_name && func != limit; func++)
+		kobject_put(&func->kobj);
+}
+
+/* Clean up when a patched object is unloaded */
+static void klp_free_object_loaded(struct klp_object *obj)
+{
+	struct klp_func *func;
+
+	obj->mod = NULL;
+
+	for (func = obj->funcs; func->old_name; func++)
+		func->old_addr = 0;
+}
+
+/*
+ * Free all objects' kobjects in the array up to some limit. When limit is
+ * NULL, all kobjects are freed.
+ */
+static void klp_free_objects_limited(struct klp_patch *patch,
+				     struct klp_object *limit)
+{
+	struct klp_object *obj;
+
+	for (obj = patch->objs; obj->funcs && obj != limit; obj++) {
+		klp_free_funcs_limited(obj, NULL);
+		kobject_put(obj->kobj);
+	}
+}
+
+static void klp_free_patch(struct klp_patch *patch)
+{
+	klp_free_objects_limited(patch, NULL);
+	if (!list_empty(&patch->list))
+		list_del(&patch->list);
+	kobject_put(&patch->kobj);
+}
+
+static int klp_init_func(struct klp_object *obj, struct klp_func *func)
+{
+	struct ftrace_ops *ops;
+	int ret;
+
+	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+	if (!ops)
+		return -ENOMEM;
+
+	ops->private = func;
+	ops->func = klp_ftrace_handler;
+	ops->flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_DYNAMIC;
+	func->fops = ops;
+	func->state = KLP_DISABLED;
+
+	ret = kobject_init_and_add(&func->kobj, &klp_ktype_func,
+				   obj->kobj, func->old_name);
+	if (ret) {
+		kfree(func->fops);
+		return ret;
+	}
+
+	return 0;
+}
+
+/* parts of the initialization that is done only when the object is loaded */
+static int klp_init_object_loaded(struct klp_patch *patch,
+				  struct klp_object *obj)
+{
+	struct klp_func *func;
+	int ret;
+
+	if (obj->relocs) {
+		ret = klp_write_object_relocations(patch->mod, obj);
+		if (ret)
+			return ret;
+	}
+
+	for (func = obj->funcs; func->old_name; func++) {
+		ret = klp_find_verify_func_addr(obj, func);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int klp_init_object(struct klp_patch *patch, struct klp_object *obj)
+{
+	struct klp_func *func;
+	int ret;
+	const char *name;
+
+	if (!obj->funcs)
+		return -EINVAL;
+
+	obj->state = KLP_DISABLED;
+
+	klp_find_object_module(obj);
+
+	name = klp_is_module(obj) ? obj->name : "vmlinux";
+	obj->kobj = kobject_create_and_add(name, &patch->kobj);
+	if (!obj->kobj)
+		return -ENOMEM;
+
+	for (func = obj->funcs; func->old_name; func++) {
+		ret = klp_init_func(obj, func);
+		if (ret)
+			goto free;
+	}
+
+	if (klp_is_object_loaded(obj)) {
+		ret = klp_init_object_loaded(patch, obj);
+		if (ret)
+			goto free;
+	}
+
+	return 0;
+
+free:
+	klp_free_funcs_limited(obj, func);
+	kobject_put(obj->kobj);
+	return ret;
+}
+
+static int klp_init_patch(struct klp_patch *patch)
+{
+	struct klp_object *obj;
+	int ret;
+
+	if (!patch->objs)
+		return -EINVAL;
+
+	mutex_lock(&klp_mutex);
+
+	patch->state = KLP_DISABLED;
+
+	ret = kobject_init_and_add(&patch->kobj, &klp_ktype_patch,
+				   klp_root_kobj, patch->mod->name);
+	if (ret)
+		goto unlock;
+
+	for (obj = patch->objs; obj->funcs; obj++) {
+		ret = klp_init_object(patch, obj);
+		if (ret)
+			goto free;
+	}
+
+	list_add(&patch->list, &klp_patches);
+
+	mutex_unlock(&klp_mutex);
+
+	return 0;
+
+free:
+	klp_free_objects_limited(patch, obj);
+	kobject_put(&patch->kobj);
+unlock:
+	mutex_unlock(&klp_mutex);
+	return ret;
+}
+
+/**
+ * klp_unregister_patch() - unregisters a patch
+ * @patch:	Disabled patch to be unregistered
+ *
+ * Frees the data structures and removes the sysfs interface.
+ *
+ * Return: 0 on success, otherwise error
+ */
+int klp_unregister_patch(struct klp_patch *patch)
+{
+	int ret = 0;
+
+	mutex_lock(&klp_mutex);
+
+	if (!klp_is_patch_registered(patch)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (patch->state == KLP_ENABLED) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	klp_free_patch(patch);
+
+out:
+	mutex_unlock(&klp_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(klp_unregister_patch);
+
+/**
+ * klp_register_patch() - registers a patch
+ * @patch:	Patch to be registered
+ *
+ * Initializes the data structure associated with the patch and
+ * creates the sysfs interface.
+ *
+ * Return: 0 on success, otherwise error
+ */
+int klp_register_patch(struct klp_patch *patch)
+{
+	int ret;
+
+	if (!klp_initialized())
+		return -ENODEV;
+
+	if (!patch || !patch->mod)
+		return -EINVAL;
+
+	/*
+	 * A reference is taken on the patch module to prevent it from being
+	 * unloaded.  Right now, we don't allow patch modules to unload since
+	 * there is currently no method to determine if a thread is still
+	 * running in the patched code contained in the patch module once
+	 * the ftrace registration is successful.
+	 */
+	if (!try_module_get(patch->mod))
+		return -ENODEV;
+
+	ret = klp_init_patch(patch);
+	if (ret)
+		module_put(patch->mod);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(klp_register_patch);
+
+static void klp_module_notify_coming(struct klp_patch *patch,
+				     struct klp_object *obj)
+{
+	struct module *pmod = patch->mod;
+	struct module *mod = obj->mod;
+	int ret;
+
+	ret = klp_init_object_loaded(patch, obj);
+	if (ret)
+		goto err;
+
+	if (patch->state == KLP_DISABLED)
+		return;
+
+	pr_notice("applying patch '%s' to loading module '%s'\n",
+		  pmod->name, mod->name);
+
+	ret = klp_enable_object(obj);
+	if (!ret)
+		return;
+
+err:
+	pr_warn("failed to apply patch '%s' to module '%s' (%d)\n",
+		pmod->name, mod->name, ret);
+}
+
+static void klp_module_notify_going(struct klp_patch *patch,
+				    struct klp_object *obj)
+{
+	struct module *pmod = patch->mod;
+	struct module *mod = obj->mod;
+	int ret;
+
+	if (patch->state == KLP_DISABLED)
+		goto disabled;
+
+	pr_notice("reverting patch '%s' on unloading module '%s'\n",
+		  pmod->name, mod->name);
+
+	ret = klp_disable_object(obj);
+	if (ret)
+		pr_warn("failed to revert patch '%s' on module '%s' (%d)\n",
+			pmod->name, mod->name, ret);
+
+disabled:
+	klp_free_object_loaded(obj);
+}
+
+static int klp_module_notify(struct notifier_block *nb, unsigned long action,
+			     void *data)
+{
+	struct module *mod = data;
+	struct klp_patch *patch;
+	struct klp_object *obj;
+
+	if (action != MODULE_STATE_COMING && action != MODULE_STATE_GOING)
+		return 0;
+
+	mutex_lock(&klp_mutex);
+
+	list_for_each_entry(patch, &klp_patches, list) {
+		for (obj = patch->objs; obj->funcs; obj++) {
+			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
+				continue;
+
+			if (action == MODULE_STATE_COMING) {
+				obj->mod = mod;
+				klp_module_notify_coming(patch, obj);
+			} else /* MODULE_STATE_GOING */
+				klp_module_notify_going(patch, obj);
+
+			break;
+		}
+	}
+
+	mutex_unlock(&klp_mutex);
+
+	return 0;
+}
+
+static struct notifier_block klp_module_nb = {
+	.notifier_call = klp_module_notify,
+	.priority = INT_MIN+1, /* called late but before ftrace notifier */
+};
+
+static int klp_init(void)
+{
+	int ret;
+
+	ret = register_module_notifier(&klp_module_nb);
+	if (ret)
+		return ret;
+
+	klp_root_kobj = kobject_create_and_add("livepatch", kernel_kobj);
+	if (!klp_root_kobj) {
+		ret = -ENOMEM;
+		goto unregister;
+	}
+
+	return 0;
+
+unregister:
+	unregister_module_notifier(&klp_module_nb);
+	return ret;
+}
+
+module_init(klp_init);
-- 
cgit v1.2.3-70-g09d2


From 2c658e212ce7e40ace56d9441c8c5634d4d420e3 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 18 Dec 2014 16:12:08 +0200
Subject: spi: Remove FSF mailing addresses

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-au1550.c        | 4 ----
 drivers/spi/spi-bcm2835.c       | 4 ----
 drivers/spi/spi-bcm63xx.c       | 4 ----
 drivers/spi/spi-bitbang.c       | 4 ----
 drivers/spi/spi-butterfly.c     | 4 ----
 drivers/spi/spi-coldfire-qspi.c | 5 -----
 drivers/spi/spi-davinci.c       | 4 ----
 drivers/spi/spi-gpio.c          | 4 ----
 drivers/spi/spi-lm70llp.c       | 4 ----
 drivers/spi/spi-omap-100k.c     | 5 -----
 drivers/spi/spi-omap-uwire.c    | 4 ----
 drivers/spi/spi-omap2-mcspi.c   | 5 -----
 drivers/spi/spi-pxa2xx-pxadma.c | 4 ----
 drivers/spi/spi-pxa2xx.c        | 4 ----
 drivers/spi/spi-rspi.c          | 5 -----
 drivers/spi/spi-s3c64xx.c       | 4 ----
 drivers/spi/spi-sc18is602.c     | 4 ----
 drivers/spi/spi-sh-hspi.c       | 5 -----
 drivers/spi/spi-sh.c            | 5 -----
 drivers/spi/spi-topcliff-pch.c  | 4 ----
 drivers/spi/spi.c               | 4 ----
 drivers/spi/spidev.c            | 4 ----
 include/linux/spi/at86rf230.h   | 4 ----
 include/linux/spi/l4f00242t03.h | 4 ----
 include/linux/spi/lms283gf05.h  | 4 ----
 include/linux/spi/mxs-spi.h     | 4 ----
 include/linux/spi/pxa2xx_spi.h  | 4 ----
 include/linux/spi/rspi.h        | 5 -----
 include/linux/spi/sh_hspi.h     | 4 ----
 include/linux/spi/spi.h         | 4 ----
 include/linux/spi/tle62x0.h     | 4 ----
 include/linux/spi/tsc2005.h     | 5 -----
 32 files changed, 136 deletions(-)

(limited to 'include')

diff --git a/drivers/spi/spi-au1550.c b/drivers/spi/spi-au1550.c
index 326f4797368..f45e085c01a 100644
--- a/drivers/spi/spi-au1550.c
+++ b/drivers/spi/spi-au1550.c
@@ -15,10 +15,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/init.h>
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 98aab457b24..419a782ab6d 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -17,10 +17,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  */
 
 #include <linux/clk.h>
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index c20530982e2..e73e2b052c9 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -13,10 +13,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the
- * Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index dc7d2c2d643..5ef6638d5e8 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -10,10 +10,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/spinlock.h>
diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c
index ee4f91ccd8f..9a95862986c 100644
--- a/drivers/spi/spi-butterfly.c
+++ b/drivers/spi/spi-butterfly.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index 41b5dc4445f..688956ff509 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -12,11 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA
- *
 */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index b3707badb1e..5e991065f5b 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/interrupt.h>
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index aee4e758956..2b76492fe5c 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c
index 41c5765be74..ba72347cb99 100644
--- a/drivers/spi/spi-lm70llp.c
+++ b/drivers/spi/spi-lm70llp.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
diff --git a/drivers/spi/spi-omap-100k.c b/drivers/spi/spi-omap-100k.c
index 79399ae9c84..d890d309dff 100644
--- a/drivers/spi/spi-omap-100k.c
+++ b/drivers/spi/spi-omap-100k.c
@@ -16,11 +16,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c
index daf1ada5cd1..3c0844457c0 100644
--- a/drivers/spi/spi-omap-uwire.c
+++ b/drivers/spi/spi-omap-uwire.c
@@ -28,10 +28,6 @@
  * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
  * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 3bc3cbabbbc..4df8942058d 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -14,11 +14,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-pxa2xx-pxadma.c b/drivers/spi/spi-pxa2xx-pxadma.c
index e8a26f25d5c..e51fcf9fd39 100644
--- a/drivers/spi/spi-pxa2xx-pxadma.c
+++ b/drivers/spi/spi-pxa2xx-pxadma.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 05c623cfb07..7a9a605d9bd 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 2071f788c6f..46ce47076e6 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -15,11 +15,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #include <linux/module.h>
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 37b19836f5c..9231c34b5a5 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c
index 237f2e7a717..5a56acf8a43 100644
--- a/drivers/spi/spi-sc18is602.c
+++ b/drivers/spi/spi-sc18is602.c
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c
index fc29233d065..20e800e7044 100644
--- a/drivers/spi/spi-sh-hspi.c
+++ b/drivers/spi/spi-sh-hspi.c
@@ -16,11 +16,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #include <linux/clk.h>
diff --git a/drivers/spi/spi-sh.c b/drivers/spi/spi-sh.c
index 1cfc906dd17..502501187c9 100644
--- a/drivers/spi/spi-sh.c
+++ b/drivers/spi/spi-sh.c
@@ -14,11 +14,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #include <linux/module.h>
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index be692ad5044..93dfcee0f98 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307, USA.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 66a70e9bc74..c76cc756863 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -13,10 +13,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 6941e04afb8..6f97e5af282 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -14,10 +14,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #include <linux/init.h>
diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h
index b2b1afbb320..cd519a11c2c 100644
--- a/include/linux/spi/at86rf230.h
+++ b/include/linux/spi/at86rf230.h
@@ -12,10 +12,6 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
  * Written by:
  * Dmitry Eremin-Solenikov <dmitry.baryshkov@siemens.com>
  */
diff --git a/include/linux/spi/l4f00242t03.h b/include/linux/spi/l4f00242t03.h
index bc8677c8eba..e69e9b51b21 100644
--- a/include/linux/spi/l4f00242t03.h
+++ b/include/linux/spi/l4f00242t03.h
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 
 #ifndef _INCLUDE_LINUX_SPI_L4F00242T03_H_
diff --git a/include/linux/spi/lms283gf05.h b/include/linux/spi/lms283gf05.h
index 555d254e660..fdd1d1d51da 100644
--- a/include/linux/spi/lms283gf05.h
+++ b/include/linux/spi/lms283gf05.h
@@ -11,10 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 
 #ifndef _INCLUDE_LINUX_SPI_LMS283GF05_H_
diff --git a/include/linux/spi/mxs-spi.h b/include/linux/spi/mxs-spi.h
index 4835486f58e..381d368b91b 100644
--- a/include/linux/spi/mxs-spi.h
+++ b/include/linux/spi/mxs-spi.h
@@ -15,10 +15,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef __LINUX_SPI_MXS_SPI_H__
diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h
index d5a31655017..5eb56e35cf0 100644
--- a/include/linux/spi/pxa2xx_spi.h
+++ b/include/linux/spi/pxa2xx_spi.h
@@ -10,10 +10,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #ifndef __linux_pxa2xx_spi_h
 #define __linux_pxa2xx_spi_h
diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h
index e546b2ceb62..a693188cc08 100644
--- a/include/linux/spi/rspi.h
+++ b/include/linux/spi/rspi.h
@@ -11,11 +11,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- *
  */
 
 #ifndef __LINUX_SPI_RENESAS_SPI_H__
diff --git a/include/linux/spi/sh_hspi.h b/include/linux/spi/sh_hspi.h
index a1121f872ac..aa0d440ab4f 100644
--- a/include/linux/spi/sh_hspi.h
+++ b/include/linux/spi/sh_hspi.h
@@ -9,10 +9,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #ifndef SH_HSPI_H
 #define SH_HSPI_H
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index a6ef2a8e6de..6e2664a1711 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -10,10 +10,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
 #ifndef __LINUX_SPI_H
diff --git a/include/linux/spi/tle62x0.h b/include/linux/spi/tle62x0.h
index 60b59187e59..414c6fddfcf 100644
--- a/include/linux/spi/tle62x0.h
+++ b/include/linux/spi/tle62x0.h
@@ -12,10 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
 
 struct tle62x0_pdata {
diff --git a/include/linux/spi/tsc2005.h b/include/linux/spi/tsc2005.h
index 8f721e465e0..563b3b1799a 100644
--- a/include/linux/spi/tsc2005.h
+++ b/include/linux/spi/tsc2005.h
@@ -12,11 +12,6 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
  */
 
 #ifndef _LINUX_SPI_TSC2005_H
-- 
cgit v1.2.3-70-g09d2


From 556d2f055bf6d79ce81587dfe774d4dd10da473f Mon Sep 17 00:00:00 2001
From: Yalin Wang <Yalin.Wang@sonymobile.com>
Date: Mon, 3 Nov 2014 03:01:03 +0100
Subject: ARM: 8187/1: add CONFIG_HAVE_ARCH_BITREVERSE to support rbit
 instruction

this change add CONFIG_HAVE_ARCH_BITREVERSE config option,
so that we can use some architecture's bitrev hardware instruction
to do bitrev operation.

Introduce __constant_bitrev* macro for constant bitrev operation.

Change __bitrev16() __bitrev32() to be inline function,
don't need export symbol for these tiny functions.

Signed-off-by: Yalin Wang <yalin.wang@sonymobile.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 include/linux/bitrev.h | 77 +++++++++++++++++++++++++++++++++++++++++++++++---
 lib/Kconfig            |  9 ++++++
 lib/bitrev.c           | 17 ++---------
 3 files changed, 84 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h
index 7ffe03f4693..fb790b8449c 100644
--- a/include/linux/bitrev.h
+++ b/include/linux/bitrev.h
@@ -3,14 +3,83 @@
 
 #include <linux/types.h>
 
-extern u8 const byte_rev_table[256];
+#ifdef CONFIG_HAVE_ARCH_BITREVERSE
+#include <asm/bitrev.h>
+
+#define __bitrev32 __arch_bitrev32
+#define __bitrev16 __arch_bitrev16
+#define __bitrev8 __arch_bitrev8
 
-static inline u8 bitrev8(u8 byte)
+#else
+extern u8 const byte_rev_table[256];
+static inline u8 __bitrev8(u8 byte)
 {
 	return byte_rev_table[byte];
 }
 
-extern u16 bitrev16(u16 in);
-extern u32 bitrev32(u32 in);
+static inline u16 __bitrev16(u16 x)
+{
+	return (__bitrev8(x & 0xff) << 8) | __bitrev8(x >> 8);
+}
+
+static inline u32 __bitrev32(u32 x)
+{
+	return (__bitrev16(x & 0xffff) << 16) | __bitrev16(x >> 16);
+}
+
+#endif /* CONFIG_HAVE_ARCH_BITREVERSE */
+
+#define __constant_bitrev32(x)	\
+({					\
+	u32 __x = x;			\
+	__x = (__x >> 16) | (__x << 16);	\
+	__x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8);	\
+	__x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4);	\
+	__x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2);	\
+	__x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1);	\
+	__x;								\
+})
+
+#define __constant_bitrev16(x)	\
+({					\
+	u16 __x = x;			\
+	__x = (__x >> 8) | (__x << 8);	\
+	__x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4);	\
+	__x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2);	\
+	__x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1);	\
+	__x;								\
+})
+
+#define __constant_bitrev8(x)	\
+({					\
+	u8 __x = x;			\
+	__x = (__x >> 4) | (__x << 4);	\
+	__x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2);	\
+	__x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1);	\
+	__x;								\
+})
+
+#define bitrev32(x) \
+({			\
+	u32 __x = x;	\
+	__builtin_constant_p(__x) ?	\
+	__constant_bitrev32(__x) :			\
+	__bitrev32(__x);				\
+})
+
+#define bitrev16(x) \
+({			\
+	u16 __x = x;	\
+	__builtin_constant_p(__x) ?	\
+	__constant_bitrev16(__x) :			\
+	__bitrev16(__x);				\
+ })
 
+#define bitrev8(x) \
+({			\
+	u8 __x = x;	\
+	__builtin_constant_p(__x) ?	\
+	__constant_bitrev8(__x) :			\
+	__bitrev8(__x)	;			\
+ })
 #endif /* _LINUX_BITREV_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index 54cf309a92a..cd177caf387 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -13,6 +13,15 @@ config RAID6_PQ
 config BITREVERSE
 	tristate
 
+config HAVE_ARCH_BITREVERSE
+	boolean
+	default n
+	depends on BITREVERSE
+	help
+	  This option provides an config for the architecture which have instruction
+	  can do bitreverse operation, we use the hardware instruction if the architecture
+	  have this capability.
+
 config RATIONAL
 	boolean
 
diff --git a/lib/bitrev.c b/lib/bitrev.c
index 3956203456d..40ffda94cc5 100644
--- a/lib/bitrev.c
+++ b/lib/bitrev.c
@@ -1,3 +1,4 @@
+#ifndef CONFIG_HAVE_ARCH_BITREVERSE
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/bitrev.h>
@@ -42,18 +43,4 @@ const u8 byte_rev_table[256] = {
 };
 EXPORT_SYMBOL_GPL(byte_rev_table);
 
-u16 bitrev16(u16 x)
-{
-	return (bitrev8(x & 0xff) << 8) | bitrev8(x >> 8);
-}
-EXPORT_SYMBOL(bitrev16);
-
-/**
- * bitrev32 - reverse the order of bits in a u32 value
- * @x: value to be bit-reversed
- */
-u32 bitrev32(u32 x)
-{
-	return (bitrev16(x & 0xffff) << 16) | bitrev16(x >> 16);
-}
-EXPORT_SYMBOL(bitrev32);
+#endif /* CONFIG_HAVE_ARCH_BITREVERSE */
-- 
cgit v1.2.3-70-g09d2


From 215cedec379b69427c457104f0c36b389edc471c Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 1 Dec 2014 10:10:42 -0300
Subject: [media] media: remove emacs editor variables

1) This is not allowed by the kernel coding style
2) Just configure your editor correctly
3) It's really ugly

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 Documentation/DocBook/media/v4l/vidioc-dv-timings-cap.xml  |  8 --------
 Documentation/DocBook/media/v4l/vidioc-enum-dv-timings.xml |  8 --------
 drivers/media/common/btcx-risc.c                           |  6 ------
 drivers/media/common/btcx-risc.h                           |  6 ------
 drivers/media/dvb-frontends/au8522.h                       |  5 -----
 drivers/media/dvb-frontends/lg2160.c                       |  6 ------
 drivers/media/dvb-frontends/lgdt3305.c                     |  6 ------
 drivers/media/dvb-frontends/lgdt330x.c                     |  6 ------
 drivers/media/dvb-frontends/lgdt330x.h                     |  6 ------
 drivers/media/dvb-frontends/lgdt330x_priv.h                |  6 ------
 drivers/media/dvb-frontends/nxt200x.h                      |  6 ------
 drivers/media/dvb-frontends/or51132.c                      |  6 ------
 drivers/media/dvb-frontends/or51132.h                      |  6 ------
 drivers/media/dvb-frontends/s5h1409.c                      |  6 ------
 drivers/media/dvb-frontends/s5h1409.h                      |  5 -----
 drivers/media/dvb-frontends/s5h1411.c                      |  5 -----
 drivers/media/dvb-frontends/s5h1411.h                      |  5 -----
 drivers/media/i2c/msp3400-driver.c                         |  8 --------
 drivers/media/pci/bt8xx/bt878.c                            |  6 ------
 drivers/media/pci/bt8xx/bttv-cards.c                       |  7 -------
 drivers/media/pci/bt8xx/bttv-driver.c                      |  6 ------
 drivers/media/pci/bt8xx/bttv-gpio.c                        |  6 ------
 drivers/media/pci/bt8xx/bttv-if.c                          |  6 ------
 drivers/media/pci/bt8xx/bttv-risc.c                        |  6 ------
 drivers/media/pci/bt8xx/bttv-vbi.c                         |  7 -------
 drivers/media/pci/bt8xx/bttv.h                             |  5 -----
 drivers/media/pci/bt8xx/bttvp.h                            |  6 ------
 drivers/media/pci/cx88/cx88-core.c                         |  7 -------
 drivers/media/pci/cx88/cx88-mpeg.c                         |  7 -------
 drivers/media/pci/cx88/cx88-tvaudio.c                      |  7 -------
 drivers/media/tuners/mt20xx.c                              |  8 --------
 drivers/media/tuners/mt2131.c                              |  5 -----
 drivers/media/tuners/mt2131.h                              |  5 -----
 drivers/media/tuners/mt2131_priv.h                         |  5 -----
 drivers/media/tuners/mxl5007t.c                            |  8 --------
 drivers/media/tuners/mxl5007t.h                            |  9 ---------
 drivers/media/tuners/tda18271-fe.c                         |  8 --------
 drivers/media/tuners/tda18271-maps.c                       |  8 --------
 drivers/media/tuners/tda18271-priv.h                       |  8 --------
 drivers/media/tuners/tda827x.c                             |  8 --------
 drivers/media/tuners/tda8290.c                             |  8 --------
 drivers/media/tuners/tda9887.c                             |  8 --------
 drivers/media/tuners/tuner-simple.c                        |  8 --------
 drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c              |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h              |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c               |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h               |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c                |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h                |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c                |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h                |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h                |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c              |  8 --------
 drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h              |  9 ---------
 drivers/media/usb/dvb-usb-v2/mxl111sf.c                    |  6 ------
 drivers/media/usb/dvb-usb-v2/mxl111sf.h                    |  6 ------
 drivers/media/usb/dvb-usb/m920x.c                          |  5 -----
 drivers/media/usb/pvrusb2/pvrusb2-audio.c                  | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-audio.h                  | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-context.c                | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-context.h                |  9 ---------
 drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.c               | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.h               | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-ctrl.c                   | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-ctrl.h                   | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c            | 12 ------------
 drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.h            | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-debug.h                  | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-debugifc.c               | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-debugifc.h               | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-devattr.c                | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-devattr.h                | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-eeprom.c                 | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-eeprom.h                 | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-encoder.c                | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-encoder.h                | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-fx2-cmd.h                | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h           | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-hdw.h                    | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c               | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-i2c-core.h               | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-io.c                     | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-io.h                     | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-ioread.c                 | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-ioread.h                 | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-main.c                   | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-std.c                    | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-std.h                    | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-sysfs.c                  | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-sysfs.h                  | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-util.h                   | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-v4l2.c                   | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-v4l2.h                   | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c              | 11 -----------
 drivers/media/usb/pvrusb2/pvrusb2-video-v4l.h              | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2-wm8775.c                 | 12 ------------
 drivers/media/usb/pvrusb2/pvrusb2-wm8775.h                 | 10 ----------
 drivers/media/usb/pvrusb2/pvrusb2.h                        | 10 ----------
 drivers/media/usb/usbvision/usbvision-core.c               |  8 --------
 drivers/media/usb/usbvision/usbvision-i2c.c                |  8 --------
 drivers/media/usb/usbvision/usbvision-video.c              |  8 --------
 drivers/media/usb/usbvision/usbvision.h                    |  8 --------
 drivers/media/v4l2-core/v4l2-dev.c                         |  7 -------
 include/media/videobuf-dvb.h                               |  6 ------
 104 files changed, 840 deletions(-)

(limited to 'include')

diff --git a/Documentation/DocBook/media/v4l/vidioc-dv-timings-cap.xml b/Documentation/DocBook/media/v4l/vidioc-dv-timings-cap.xml
index 28a8c1e1c70..a2017bfcaed 100644
--- a/Documentation/DocBook/media/v4l/vidioc-dv-timings-cap.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-dv-timings-cap.xml
@@ -212,11 +212,3 @@ standards set in the <structfield>standards</structfield> field.
     &return-value;
   </refsect1>
 </refentry>
-
-<!--
-Local Variables:
-mode: sgml
-sgml-parent-document: "v4l2.sgml"
-indent-tabs-mode: nil
-End:
--->
diff --git a/Documentation/DocBook/media/v4l/vidioc-enum-dv-timings.xml b/Documentation/DocBook/media/v4l/vidioc-enum-dv-timings.xml
index b9fdfeacdbc..6e3cadd4e1f 100644
--- a/Documentation/DocBook/media/v4l/vidioc-enum-dv-timings.xml
+++ b/Documentation/DocBook/media/v4l/vidioc-enum-dv-timings.xml
@@ -131,11 +131,3 @@ is out of bounds or the <structfield>pad</structfield> number is invalid.</para>
     </variablelist>
   </refsect1>
 </refentry>
-
-<!--
-Local Variables:
-mode: sgml
-sgml-parent-document: "v4l2.sgml"
-indent-tabs-mode: nil
-End:
--->
diff --git a/drivers/media/common/btcx-risc.c b/drivers/media/common/btcx-risc.c
index ac1b2687a20..e67338aa8c8 100644
--- a/drivers/media/common/btcx-risc.c
+++ b/drivers/media/common/btcx-risc.c
@@ -252,9 +252,3 @@ EXPORT_SYMBOL(btcx_screen_clips);
 EXPORT_SYMBOL(btcx_align);
 EXPORT_SYMBOL(btcx_sort_clips);
 EXPORT_SYMBOL(btcx_calc_skips);
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/common/btcx-risc.h b/drivers/media/common/btcx-risc.h
index f8bc6e8e7b5..03583ef9050 100644
--- a/drivers/media/common/btcx-risc.h
+++ b/drivers/media/common/btcx-risc.h
@@ -26,9 +26,3 @@ void btcx_sort_clips(struct v4l2_clip *clips, unsigned int nclips);
 void btcx_calc_skips(int line, int width, int *maxy,
 		     struct btcx_skiplist *skips, unsigned int *nskips,
 		     const struct v4l2_clip *clips, unsigned int nclips);
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/au8522.h b/drivers/media/dvb-frontends/au8522.h
index 83fe9a61561..61225195885 100644
--- a/drivers/media/dvb-frontends/au8522.h
+++ b/drivers/media/dvb-frontends/au8522.h
@@ -91,8 +91,3 @@ enum au8522_audio_input {
 };
 
 #endif /* __AU8522_H__ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/dvb-frontends/lg2160.c b/drivers/media/dvb-frontends/lg2160.c
index 5fd14f840ab..99efeba3c31 100644
--- a/drivers/media/dvb-frontends/lg2160.c
+++ b/drivers/media/dvb-frontends/lg2160.c
@@ -1456,9 +1456,3 @@ MODULE_DESCRIPTION("LG Electronics LG216x ATSC/MH Demodulator Driver");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.3");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/lgdt3305.c b/drivers/media/dvb-frontends/lgdt3305.c
index 92c891a571a..60df376e65c 100644
--- a/drivers/media/dvb-frontends/lgdt3305.c
+++ b/drivers/media/dvb-frontends/lgdt3305.c
@@ -1215,9 +1215,3 @@ MODULE_DESCRIPTION("LG Electronics LGDT3304/5 ATSC/QAM-B Demodulator Driver");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.2");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c
index e046622df0e..2e1a61893fc 100644
--- a/drivers/media/dvb-frontends/lgdt330x.c
+++ b/drivers/media/dvb-frontends/lgdt330x.c
@@ -823,9 +823,3 @@ MODULE_AUTHOR("Wilson Michaels");
 MODULE_LICENSE("GPL");
 
 EXPORT_SYMBOL(lgdt330x_attach);
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/lgdt330x.h b/drivers/media/dvb-frontends/lgdt330x.h
index ca0eab562e1..8bb332219fc 100644
--- a/drivers/media/dvb-frontends/lgdt330x.h
+++ b/drivers/media/dvb-frontends/lgdt330x.h
@@ -65,9 +65,3 @@ static inline struct dvb_frontend* lgdt330x_attach(const struct lgdt330x_config*
 #endif // CONFIG_DVB_LGDT330X
 
 #endif /* LGDT330X_H */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/lgdt330x_priv.h b/drivers/media/dvb-frontends/lgdt330x_priv.h
index 38c76695abf..1922f09a02d 100644
--- a/drivers/media/dvb-frontends/lgdt330x_priv.h
+++ b/drivers/media/dvb-frontends/lgdt330x_priv.h
@@ -69,9 +69,3 @@ enum I2C_REG {
 };
 
 #endif /* _LGDT330X_PRIV_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/nxt200x.h b/drivers/media/dvb-frontends/nxt200x.h
index b518d545609..e38d01fb6c2 100644
--- a/drivers/media/dvb-frontends/nxt200x.h
+++ b/drivers/media/dvb-frontends/nxt200x.h
@@ -55,9 +55,3 @@ static inline struct dvb_frontend* nxt200x_attach(const struct nxt200x_config* c
 #endif // CONFIG_DVB_NXT200X
 
 #endif /* NXT200X_H */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c
index 5ef921823c1..cbbd259eacf 100644
--- a/drivers/media/dvb-frontends/or51132.c
+++ b/drivers/media/dvb-frontends/or51132.c
@@ -623,9 +623,3 @@ MODULE_AUTHOR("Trent Piepho");
 MODULE_LICENSE("GPL");
 
 EXPORT_SYMBOL(or51132_attach);
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/or51132.h b/drivers/media/dvb-frontends/or51132.h
index 938958386cb..cdb5be3c65d 100644
--- a/drivers/media/dvb-frontends/or51132.h
+++ b/drivers/media/dvb-frontends/or51132.h
@@ -47,9 +47,3 @@ static inline struct dvb_frontend* or51132_attach(const struct or51132_config* c
 #endif // CONFIG_DVB_OR51132
 
 #endif // OR51132_H
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/dvb-frontends/s5h1409.c b/drivers/media/dvb-frontends/s5h1409.c
index f71b06221e1..5ff474a7ff2 100644
--- a/drivers/media/dvb-frontends/s5h1409.c
+++ b/drivers/media/dvb-frontends/s5h1409.c
@@ -1021,9 +1021,3 @@ static struct dvb_frontend_ops s5h1409_ops = {
 MODULE_DESCRIPTION("Samsung S5H1409 QAM-B/ATSC Demodulator driver");
 MODULE_AUTHOR("Steven Toth");
 MODULE_LICENSE("GPL");
-
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/dvb-frontends/s5h1409.h b/drivers/media/dvb-frontends/s5h1409.h
index 63b1e0a34e4..9e143f5c810 100644
--- a/drivers/media/dvb-frontends/s5h1409.h
+++ b/drivers/media/dvb-frontends/s5h1409.h
@@ -81,8 +81,3 @@ static inline struct dvb_frontend *s5h1409_attach(
 #endif /* CONFIG_DVB_S5H1409 */
 
 #endif /* __S5H1409_H__ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c
index 6cc4b7a9dd6..64f35fed7ae 100644
--- a/drivers/media/dvb-frontends/s5h1411.c
+++ b/drivers/media/dvb-frontends/s5h1411.c
@@ -944,8 +944,3 @@ MODULE_PARM_DESC(debug, "Enable verbose debug messages");
 MODULE_DESCRIPTION("Samsung S5H1411 QAM-B/ATSC Demodulator driver");
 MODULE_AUTHOR("Steven Toth");
 MODULE_LICENSE("GPL");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/dvb-frontends/s5h1411.h b/drivers/media/dvb-frontends/s5h1411.h
index e4f56871f98..1d7deb61567 100644
--- a/drivers/media/dvb-frontends/s5h1411.h
+++ b/drivers/media/dvb-frontends/s5h1411.h
@@ -83,8 +83,3 @@ static inline struct dvb_frontend *s5h1411_attach(
 #endif /* CONFIG_DVB_S5H1411 */
 
 #endif /* __S5H1411_H__ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/i2c/msp3400-driver.c b/drivers/media/i2c/msp3400-driver.c
index 4d9c6bc3426..dcc68ec7173 100644
--- a/drivers/media/i2c/msp3400-driver.c
+++ b/drivers/media/i2c/msp3400-driver.c
@@ -904,11 +904,3 @@ static struct i2c_driver msp_driver = {
 };
 
 module_i2c_driver(msp_driver);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bt878.c b/drivers/media/pci/bt8xx/bt878.c
index 11765835d7b..0939d399b77 100644
--- a/drivers/media/pci/bt8xx/bt878.c
+++ b/drivers/media/pci/bt8xx/bt878.c
@@ -590,9 +590,3 @@ module_init(bt878_init_module);
 module_exit(bt878_cleanup_module);
 
 MODULE_LICENSE("GPL");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttv-cards.c b/drivers/media/pci/bt8xx/bttv-cards.c
index 41055606b96..c5186778fc8 100644
--- a/drivers/media/pci/bt8xx/bttv-cards.c
+++ b/drivers/media/pci/bt8xx/bttv-cards.c
@@ -5048,10 +5048,3 @@ int bttv_handle_chipset(struct bttv *btv)
 		pci_write_config_byte(btv->c.pci, PCI_LATENCY_TIMER, latency);
 	return 0;
 }
-
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index 4a8176c09fc..665e46dafe6 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -4429,9 +4429,3 @@ static void __exit bttv_cleanup_module(void)
 
 module_init(bttv_init_module);
 module_exit(bttv_cleanup_module);
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttv-gpio.c b/drivers/media/pci/bt8xx/bttv-gpio.c
index 3f364b7062b..25b9916906d 100644
--- a/drivers/media/pci/bt8xx/bttv-gpio.c
+++ b/drivers/media/pci/bt8xx/bttv-gpio.c
@@ -181,9 +181,3 @@ void bttv_gpio_bits(struct bttv_core *core, u32 mask, u32 bits)
 	btwrite(data,BT848_GPIO_DATA);
 	spin_unlock_irqrestore(&btv->gpio_lock,flags);
 }
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttv-if.c b/drivers/media/pci/bt8xx/bttv-if.c
index a6a540dc9e4..538652e16a5 100644
--- a/drivers/media/pci/bt8xx/bttv-if.c
+++ b/drivers/media/pci/bt8xx/bttv-if.c
@@ -113,9 +113,3 @@ int bttv_write_gpio(unsigned int card, unsigned long mask, unsigned long data)
 		bttv_gpio_tracking(btv,"extern write");
 	return 0;
 }
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttv-risc.c b/drivers/media/pci/bt8xx/bttv-risc.c
index 4d3f05a19af..3859dde98be 100644
--- a/drivers/media/pci/bt8xx/bttv-risc.c
+++ b/drivers/media/pci/bt8xx/bttv-risc.c
@@ -901,9 +901,3 @@ bttv_overlay_risc(struct bttv *btv,
 	buf->vb.field = ov->field;
 	return 0;
 }
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttv-vbi.c b/drivers/media/pci/bt8xx/bttv-vbi.c
index b433267d9aa..e77129c92fa 100644
--- a/drivers/media/pci/bt8xx/bttv-vbi.c
+++ b/drivers/media/pci/bt8xx/bttv-vbi.c
@@ -450,10 +450,3 @@ void bttv_vbi_fmt_reset(struct bttv_vbi_fmt *f, unsigned int norm)
 	/* See bttv_vbi_fmt_set(). */
 	f->end                  = tvnorm->vbistart[0] * 2 + 2;
 }
-
-/* ----------------------------------------------------------------------- */
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttv.h b/drivers/media/pci/bt8xx/bttv.h
index f0812624466..91301c3cad1 100644
--- a/drivers/media/pci/bt8xx/bttv.h
+++ b/drivers/media/pci/bt8xx/bttv.h
@@ -378,8 +378,3 @@ extern void bttv_input_fini(struct bttv *dev);
 extern void bttv_input_irq(struct bttv *dev);
 
 #endif /* _BTTV_H_ */
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/bt8xx/bttvp.h b/drivers/media/pci/bt8xx/bttvp.h
index 9fe19488b30..e6e2c60f9e3 100644
--- a/drivers/media/pci/bt8xx/bttvp.h
+++ b/drivers/media/pci/bt8xx/bttvp.h
@@ -531,9 +531,3 @@ static inline unsigned int bttv_muxsel(const struct bttv *btv,
 #define btaor(dat,mask,adr) btwrite((dat) | ((mask) & btread(adr)), adr)
 
 #endif /* _BTTVP_H_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/pci/cx88/cx88-core.c b/drivers/media/pci/cx88/cx88-core.c
index dee177ed5fe..c38d5a12e27 100644
--- a/drivers/media/pci/cx88/cx88-core.c
+++ b/drivers/media/pci/cx88/cx88-core.c
@@ -1091,10 +1091,3 @@ EXPORT_SYMBOL(cx88_core_put);
 
 EXPORT_SYMBOL(cx88_ir_start);
 EXPORT_SYMBOL(cx88_ir_stop);
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- * kate: eol "unix"; indent-width 3; remove-trailing-space on; replace-trailing-space-save on; tab-width 8; replace-tabs off; space-indent off; mixed-indent off
- */
diff --git a/drivers/media/pci/cx88/cx88-mpeg.c b/drivers/media/pci/cx88/cx88-mpeg.c
index 1c1f69e6b0b..a369b0840ac 100644
--- a/drivers/media/pci/cx88/cx88-mpeg.c
+++ b/drivers/media/pci/cx88/cx88-mpeg.c
@@ -833,10 +833,3 @@ EXPORT_SYMBOL(cx8802_start_dma);
 EXPORT_SYMBOL(cx8802_register_driver);
 EXPORT_SYMBOL(cx8802_unregister_driver);
 EXPORT_SYMBOL(cx8802_get_driver);
-/* ----------------------------------------------------------- */
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- * kate: eol "unix"; indent-width 3; remove-trailing-space on; replace-trailing-space-save on; tab-width 8; replace-tabs off; space-indent off; mixed-indent off
- */
diff --git a/drivers/media/pci/cx88/cx88-tvaudio.c b/drivers/media/pci/cx88/cx88-tvaudio.c
index 424fd97495d..6bbce6ad629 100644
--- a/drivers/media/pci/cx88/cx88-tvaudio.c
+++ b/drivers/media/pci/cx88/cx88-tvaudio.c
@@ -1050,10 +1050,3 @@ EXPORT_SYMBOL(cx88_newstation);
 EXPORT_SYMBOL(cx88_set_stereo);
 EXPORT_SYMBOL(cx88_get_stereo);
 EXPORT_SYMBOL(cx88_audio_thread);
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- * kate: eol "unix"; indent-width 3; remove-trailing-space on; replace-trailing-space-save on; tab-width 8; replace-tabs off; space-indent off; mixed-indent off
- */
diff --git a/drivers/media/tuners/mt20xx.c b/drivers/media/tuners/mt20xx.c
index 0e74e97e0d1..9e031040c13 100644
--- a/drivers/media/tuners/mt20xx.c
+++ b/drivers/media/tuners/mt20xx.c
@@ -660,11 +660,3 @@ EXPORT_SYMBOL_GPL(microtune_attach);
 MODULE_DESCRIPTION("Microtune tuner driver");
 MODULE_AUTHOR("Ralph Metzler, Gerd Knorr, Gunther Mayer");
 MODULE_LICENSE("GPL");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/mt2131.c b/drivers/media/tuners/mt2131.c
index f83b0c1ea6c..6e2cdd2b617 100644
--- a/drivers/media/tuners/mt2131.c
+++ b/drivers/media/tuners/mt2131.c
@@ -294,8 +294,3 @@ EXPORT_SYMBOL(mt2131_attach);
 MODULE_AUTHOR("Steven Toth");
 MODULE_DESCRIPTION("Microtune MT2131 silicon tuner driver");
 MODULE_LICENSE("GPL");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/tuners/mt2131.h b/drivers/media/tuners/mt2131.h
index 09ceaf68e47..837c854b9c6 100644
--- a/drivers/media/tuners/mt2131.h
+++ b/drivers/media/tuners/mt2131.h
@@ -47,8 +47,3 @@ static inline struct dvb_frontend* mt2131_attach(struct dvb_frontend *fe,
 #endif /* CONFIG_MEDIA_TUNER_MT2131 */
 
 #endif /* __MT2131_H__ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/tuners/mt2131_priv.h b/drivers/media/tuners/mt2131_priv.h
index 62aeedf5c55..91283b599cb 100644
--- a/drivers/media/tuners/mt2131_priv.h
+++ b/drivers/media/tuners/mt2131_priv.h
@@ -41,8 +41,3 @@ struct mt2131_priv {
 };
 
 #endif /* __MT2131_PRIV_H__ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/tuners/mxl5007t.c b/drivers/media/tuners/mxl5007t.c
index 1810ad66888..f4ae04c3328 100644
--- a/drivers/media/tuners/mxl5007t.c
+++ b/drivers/media/tuners/mxl5007t.c
@@ -938,11 +938,3 @@ MODULE_DESCRIPTION("MaxLinear MxL5007T Silicon IC tuner driver");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.2");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/mxl5007t.h b/drivers/media/tuners/mxl5007t.h
index 37b0942e238..ae7037d681c 100644
--- a/drivers/media/tuners/mxl5007t.h
+++ b/drivers/media/tuners/mxl5007t.h
@@ -93,12 +93,3 @@ static inline struct dvb_frontend *mxl5007t_attach(struct dvb_frontend *fe,
 #endif
 
 #endif /* __MXL5007T_H__ */
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
-
diff --git a/drivers/media/tuners/tda18271-fe.c b/drivers/media/tuners/tda18271-fe.c
index 4995b890c16..f8620741bb5 100644
--- a/drivers/media/tuners/tda18271-fe.c
+++ b/drivers/media/tuners/tda18271-fe.c
@@ -1355,11 +1355,3 @@ MODULE_DESCRIPTION("NXP TDA18271HD analog / digital tuner driver");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.4");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/tda18271-maps.c b/drivers/media/tuners/tda18271-maps.c
index b62e925f643..1e89dd93c4b 100644
--- a/drivers/media/tuners/tda18271-maps.c
+++ b/drivers/media/tuners/tda18271-maps.c
@@ -1305,11 +1305,3 @@ int tda18271_assign_map_layout(struct dvb_frontend *fe)
 
 	return ret;
 }
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/tda18271-priv.h b/drivers/media/tuners/tda18271-priv.h
index b36a7b75477..cc80f544af3 100644
--- a/drivers/media/tuners/tda18271-priv.h
+++ b/drivers/media/tuners/tda18271-priv.h
@@ -226,11 +226,3 @@ extern int tda18271_calc_ir_measure(struct dvb_frontend *fe, u32 *freq);
 extern int tda18271_calc_rf_cal(struct dvb_frontend *fe, u32 *freq);
 
 #endif /* __TDA18271_PRIV_H__ */
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/tda827x.c b/drivers/media/tuners/tda827x.c
index 73453a255cd..edcb4a723aa 100644
--- a/drivers/media/tuners/tda827x.c
+++ b/drivers/media/tuners/tda827x.c
@@ -907,11 +907,3 @@ MODULE_DESCRIPTION("DVB TDA827x driver");
 MODULE_AUTHOR("Hartmut Hackmann <hartmut.hackmann@t-online.de>");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/tda8290.c b/drivers/media/tuners/tda8290.c
index ab4106c17b4..998e82bba9c 100644
--- a/drivers/media/tuners/tda8290.c
+++ b/drivers/media/tuners/tda8290.c
@@ -881,11 +881,3 @@ EXPORT_SYMBOL_GPL(tda829x_probe);
 MODULE_DESCRIPTION("Philips/NXP TDA8290/TDA8295 analog IF demodulator driver");
 MODULE_AUTHOR("Gerd Knorr, Hartmut Hackmann, Michael Krufky");
 MODULE_LICENSE("GPL");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/tda9887.c b/drivers/media/tuners/tda9887.c
index 9823248d743..56be6c29399 100644
--- a/drivers/media/tuners/tda9887.c
+++ b/drivers/media/tuners/tda9887.c
@@ -707,11 +707,3 @@ struct dvb_frontend *tda9887_attach(struct dvb_frontend *fe,
 EXPORT_SYMBOL_GPL(tda9887_attach);
 
 MODULE_LICENSE("GPL");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/tuners/tuner-simple.c b/drivers/media/tuners/tuner-simple.c
index ca274c2d8c7..8e9ce144da9 100644
--- a/drivers/media/tuners/tuner-simple.c
+++ b/drivers/media/tuners/tuner-simple.c
@@ -1148,11 +1148,3 @@ EXPORT_SYMBOL_GPL(simple_tuner_attach);
 MODULE_DESCRIPTION("Simple 4-control-bytes style tuner driver");
 MODULE_AUTHOR("Ralph Metzler, Gerd Knorr, Gunther Mayer");
 MODULE_LICENSE("GPL");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
index 0a98d04c53e..ecefa5c477f 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
@@ -604,9 +604,3 @@ MODULE_DESCRIPTION("MaxLinear MxL111SF DVB-T demodulator driver");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.1");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
index 2d4530f5be5..0bd83e52669 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h
@@ -47,9 +47,3 @@ struct dvb_frontend *mxl111sf_demod_attach(struct mxl111sf_state *mxl_state,
 #endif /* CONFIG_DVB_USB_MXL111SF */
 
 #endif /* __MXL111SF_DEMOD_H__ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c
index a619410adde..2180c13a6dc 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.c
@@ -755,9 +755,3 @@ int mxl111sf_gpio_mode_switch(struct mxl111sf_state *state, unsigned int mode)
 	}
 	return 0;
 }
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h
index b85a5772d77..16fa4d4daf8 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-gpio.h
@@ -48,9 +48,3 @@ int mxl111sf_config_pin_mux_modes(struct mxl111sf_state *state,
 				  enum mxl111sf_mux_config pin_mux_config);
 
 #endif /* _DVB_USB_MXL111SF_GPIO_H_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c
index a101d06eb14..283495c84ba 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.c
@@ -842,9 +842,3 @@ int mxl111sf_i2c_xfer(struct i2c_adapter *adap,
 
 	return i == num ? num : -EREMOTEIO;
 }
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h
index 465762145ad..c486fe02f01 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-i2c.h
@@ -27,9 +27,3 @@ int mxl111sf_i2c_xfer(struct i2c_adapter *adap,
 		      struct i2c_msg msg[], int num);
 
 #endif /* _DVB_USB_MXL111SF_I2C_H_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c
index f6b348024be..5b0191178f9 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.c
@@ -335,9 +335,3 @@ int mxl111sf_idac_config(struct mxl111sf_state *state,
 
 	return ret;
 }
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h
index 0643738de7d..25aa4a1ea75 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-phy.h
@@ -45,9 +45,3 @@ int mxl111sf_idac_config(struct mxl111sf_state *state,
 			 u8 current_value, u8 hysteresis_value);
 
 #endif /* _DVB_USB_MXL111SF_PHY_H_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h
index 89bf115e927..1f4bfbcdbab 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-reg.h
@@ -171,9 +171,3 @@
 #define V6_DIG_RF_PWR_MSB_REG  0x47
 
 #endif /* _DVB_USB_MXL111SF_REG_H_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
index a8d2c705367..444579be0b7 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
@@ -515,11 +515,3 @@ MODULE_DESCRIPTION("MaxLinear MxL111SF CMOS tuner driver");
 MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.1");
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
index 2046db22519..e6caab21a19 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h
@@ -77,12 +77,3 @@ struct dvb_frontend *mxl111sf_tuner_attach(struct dvb_frontend *fe,
 #endif
 
 #endif /* __MXL111SF_TUNER_H__ */
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
-
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.c b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
index c3447eaf110..bec12b0e076 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c
@@ -1425,9 +1425,3 @@ MODULE_AUTHOR("Michael Krufky <mkrufky@linuxtv.org>");
 MODULE_DESCRIPTION("Driver for MaxLinear MxL111SF");
 MODULE_VERSION("1.0");
 MODULE_LICENSE("GPL");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf.h b/drivers/media/usb/dvb-usb-v2/mxl111sf.h
index 8516c011b7c..ee70df1f1e9 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.h
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.h
@@ -152,9 +152,3 @@ extern int dvb_usb_mxl111sf_debug;
 })
 
 #endif /* _DVB_USB_MXL111SF_H_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/dvb-usb/m920x.c b/drivers/media/usb/dvb-usb/m920x.c
index abf8ab2e02e..eafc5c82467 100644
--- a/drivers/media/usb/dvb-usb/m920x.c
+++ b/drivers/media/usb/dvb-usb/m920x.c
@@ -1269,8 +1269,3 @@ MODULE_AUTHOR("Aapo Tahkola <aet@rasterburn.org>");
 MODULE_DESCRIPTION("DVB Driver for ULI M920x");
 MODULE_VERSION("0.1");
 MODULE_LICENSE("GPL");
-
-/*
- * Local variables:
- * c-basic-offset: 8
- */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-audio.c b/drivers/media/usb/pvrusb2/pvrusb2-audio.c
index cc06d5e4adc..45276c62848 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-audio.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-audio.c
@@ -84,13 +84,3 @@ void pvr2_msp3400_subdev_update(struct pvr2_hdw *hdw, struct v4l2_subdev *sd)
 			MSP_OUTPUT(MSP_SC_IN_DSP_SCART1), 0);
 	}
 }
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-audio.h b/drivers/media/usb/pvrusb2/pvrusb2-audio.h
index e3e63d75089..27cefb5cb17 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-audio.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-audio.h
@@ -25,13 +25,3 @@
 #include "pvrusb2-hdw-internal.h"
 void pvr2_msp3400_subdev_update(struct pvr2_hdw *, struct v4l2_subdev *);
 #endif /* __PVRUSB2_AUDIO_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-context.c b/drivers/media/usb/pvrusb2/pvrusb2-context.c
index c8761c71c9d..924fc4c6019 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-context.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-context.c
@@ -418,14 +418,3 @@ struct pvr2_ioread *pvr2_channel_create_mpeg_stream(
 	pvr2_ioread_set_sync_key(cp,stream_sync_key,sizeof(stream_sync_key));
 	return cp;
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-context.h b/drivers/media/usb/pvrusb2/pvrusb2-context.h
index d657e53bbfa..1c1d442d9ea 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-context.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-context.h
@@ -83,12 +83,3 @@ int pvr2_context_global_init(void);
 void pvr2_context_global_done(void);
 
 #endif /* __PVRUSB2_CONTEXT_H */
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.c b/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.c
index 88320900dbd..f82f0f0f2c0 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.c
@@ -82,14 +82,3 @@ void pvr2_cs53l32a_subdev_update(struct pvr2_hdw *hdw, struct v4l2_subdev *sd)
 		sd->ops->audio->s_routing(sd, input, 0, 0);
 	}
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.h b/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.h
index 53ba548b72a..86c17bee56f 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-cs53l32a.h
@@ -36,13 +36,3 @@
 void pvr2_cs53l32a_subdev_update(struct pvr2_hdw *, struct v4l2_subdev *);
 
 #endif /* __PVRUSB2_AUDIO_CS53L32A_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-ctrl.c b/drivers/media/usb/pvrusb2/pvrusb2-ctrl.c
index 7d5a7139a45..958db170a04 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-ctrl.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-ctrl.c
@@ -596,14 +596,3 @@ int pvr2_ctrl_value_to_sym(struct pvr2_ctrl *cptr,
 	} while(0); LOCK_GIVE(cptr->hdw->big_lock);
 	return ret;
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-ctrl.h b/drivers/media/usb/pvrusb2/pvrusb2-ctrl.h
index 794ff90121c..c175571868a 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-ctrl.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-ctrl.h
@@ -110,13 +110,3 @@ int pvr2_ctrl_value_to_sym_internal(struct pvr2_ctrl *,
 			   unsigned int *len);
 
 #endif /* __PVRUSB2_CTRL_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c b/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c
index c514d0b9ffd..1a81aa70509 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.c
@@ -152,15 +152,3 @@ void pvr2_cx25840_subdev_update(struct pvr2_hdw *hdw, struct v4l2_subdev *sd)
 		sd->ops->audio->s_routing(sd, (u32)aud_input, 0, 0);
 	}
 }
-
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.h b/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.h
index e35c2322a08..2eed7b7ee25 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-cx2584x-v4l.h
@@ -40,13 +40,3 @@ void pvr2_cx25840_subdev_update(struct pvr2_hdw *, struct v4l2_subdev *sd);
 
 
 #endif /* __PVRUSB2_CX2584X_V4L_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-debug.h b/drivers/media/usb/pvrusb2/pvrusb2-debug.h
index be79249f862..4ef2ebcd97a 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-debug.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-debug.h
@@ -57,13 +57,3 @@ extern int pvrusb2_debug;
 
 
 #endif /* __PVRUSB2_HDW_INTERNAL_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-debugifc.c b/drivers/media/usb/pvrusb2/pvrusb2-debugifc.c
index 4279ebb811a..e4022bcb155 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-debugifc.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-debugifc.c
@@ -322,14 +322,3 @@ int pvr2_debugifc_docmd(struct pvr2_hdw *hdw,const char *buf,
 
 	return 0;
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-debugifc.h b/drivers/media/usb/pvrusb2/pvrusb2-debugifc.h
index 2f8d46761cd..a8dfc55f136 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-debugifc.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-debugifc.h
@@ -40,13 +40,3 @@ int pvr2_debugifc_docmd(struct pvr2_hdw *,
 			const char *buf_ptr,unsigned int buf_size);
 
 #endif /* __PVRUSB2_DEBUGIFC_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-devattr.c b/drivers/media/usb/pvrusb2/pvrusb2-devattr.c
index adc501d3c28..06c4c3dabcd 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-devattr.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-devattr.c
@@ -564,13 +564,3 @@ MODULE_FIRMWARE(PVR2_FIRMWARE_29xxx);
 MODULE_FIRMWARE(PVR2_FIRMWARE_24xxx);
 MODULE_FIRMWARE(PVR2_FIRMWARE_73xxx);
 MODULE_FIRMWARE(PVR2_FIRMWARE_75xxx);
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-devattr.h b/drivers/media/usb/pvrusb2/pvrusb2-devattr.h
index 273c8d4b385..5aeefb6a991 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-devattr.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-devattr.h
@@ -187,13 +187,3 @@ struct pvr2_device_desc {
 extern struct usb_device_id pvr2_device_table[];
 
 #endif /* __PVRUSB2_HDW_INTERNAL_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c
index 9515f3a68f8..e1907cd0c3b 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.c
@@ -152,13 +152,3 @@ int pvr2_eeprom_analyze(struct pvr2_hdw *hdw)
 
 	return 0;
 }
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.h b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.h
index cca3216f94c..f1e33c807f4 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-eeprom.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-eeprom.h
@@ -27,13 +27,3 @@ struct pvr2_hdw;
 int pvr2_eeprom_analyze(struct pvr2_hdw *);
 
 #endif /* __PVRUSB2_EEPROM_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-encoder.c b/drivers/media/usb/pvrusb2/pvrusb2-encoder.c
index f7702aeeda3..593b3e9b6bf 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-encoder.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-encoder.c
@@ -538,14 +538,3 @@ int pvr2_encoder_stop(struct pvr2_hdw *hdw)
 
 	return status;
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-encoder.h b/drivers/media/usb/pvrusb2/pvrusb2-encoder.h
index 232fefbcd1a..a2bfb48f1ec 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-encoder.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-encoder.h
@@ -30,13 +30,3 @@ int pvr2_encoder_start(struct pvr2_hdw *);
 int pvr2_encoder_stop(struct pvr2_hdw *);
 
 #endif /* __PVRUSB2_ENCODER_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-fx2-cmd.h b/drivers/media/usb/pvrusb2/pvrusb2-fx2-cmd.h
index 614755ea2ea..06a15a68bcf 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-fx2-cmd.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-fx2-cmd.h
@@ -60,13 +60,3 @@
 #define FX2CMD_ONAIR_DTV_POWER_OFF     0xa3u
 
 #endif /* _PVRUSB2_FX2_CMD_H_ */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h b/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h
index 036952f2a3c..1f9c02801ce 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw-internal.h
@@ -394,13 +394,3 @@ unsigned long pvr2_hdw_get_cur_freq(struct pvr2_hdw *);
 void pvr2_hdw_status_poll(struct pvr2_hdw *);
 
 #endif /* __PVRUSB2_HDW_INTERNAL_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.h b/drivers/media/usb/pvrusb2/pvrusb2-hdw.h
index 41847076f51..fc503795766 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.h
@@ -343,13 +343,3 @@ void pvr2_hdw_trigger_module_log(struct pvr2_hdw *hdw);
 int pvr2_upload_firmware2(struct pvr2_hdw *hdw);
 
 #endif /* __PVRUSB2_HDW_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
index b5e929f1bf8..4baa9d632a4 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
@@ -686,13 +686,3 @@ void pvr2_i2c_core_done(struct pvr2_hdw *hdw)
 		hdw->i2c_linked = 0;
 	}
 }
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.h b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.h
index 6a75769200b..a10a3e8e934 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.h
@@ -27,14 +27,3 @@ void pvr2_i2c_core_done(struct pvr2_hdw *);
 
 
 #endif /* __PVRUSB2_I2C_ADAPTER_H */
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-io.c b/drivers/media/usb/pvrusb2/pvrusb2-io.c
index 1e354747de3..0c08f22bdfc 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-io.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-io.c
@@ -682,14 +682,3 @@ int pvr2_buffer_get_id(struct pvr2_buffer *bp)
 {
 	return bp->id;
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-io.h b/drivers/media/usb/pvrusb2/pvrusb2-io.h
index afb7e87c039..0c47c6a95ab 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-io.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-io.h
@@ -90,13 +90,3 @@ int pvr2_buffer_get_id(struct pvr2_buffer *);
 int pvr2_buffer_queue(struct pvr2_buffer *);
 
 #endif /* __PVRUSB2_IO_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-ioread.c b/drivers/media/usb/pvrusb2/pvrusb2-ioread.c
index bba6115c9ae..cd995b54732 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-ioread.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-ioread.c
@@ -499,14 +499,3 @@ int pvr2_ioread_read(struct pvr2_ioread *cp,void __user *buf,unsigned int cnt)
 		   cp,req_cnt,ret);
 	return ret;
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-ioread.h b/drivers/media/usb/pvrusb2/pvrusb2-ioread.h
index 100e0780e1a..0b1f0fbc343 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-ioread.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-ioread.h
@@ -36,13 +36,3 @@ int pvr2_ioread_read(struct pvr2_ioread *,void __user *buf,unsigned int cnt);
 int pvr2_ioread_avail(struct pvr2_ioread *);
 
 #endif /* __PVRUSB2_IOREAD_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-main.c b/drivers/media/usb/pvrusb2/pvrusb2-main.c
index c1d9bb61cd7..86be902a004 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-main.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-main.c
@@ -169,14 +169,3 @@ MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 MODULE_VERSION("0.9.1");
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-std.c b/drivers/media/usb/pvrusb2/pvrusb2-std.c
index 453627b0783..9a596a3a4c2 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-std.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-std.c
@@ -398,14 +398,3 @@ v4l2_std_id pvr2_std_get_usable(void)
 {
 	return CSTD_ALL;
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-std.h b/drivers/media/usb/pvrusb2/pvrusb2-std.h
index a35c53d0b32..ed4ec047442 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-std.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-std.h
@@ -47,13 +47,3 @@ struct v4l2_standard *pvr2_std_create_enum(unsigned int *countptr,
 v4l2_std_id pvr2_std_get_usable(void);
 
 #endif /* __PVRUSB2_STD_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c
index 6ef1335b285..06fe63ced58 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.c
@@ -848,14 +848,3 @@ static ssize_t debugcmd_store(struct device *class_dev,
 	return count;
 }
 #endif /* CONFIG_VIDEO_PVRUSB2_DEBUGIFC */
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h
index 6d875bfe799..6f0579e1e07 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-sysfs.h
@@ -34,13 +34,3 @@ struct pvr2_sysfs *pvr2_sysfs_create(struct pvr2_context *,
 				     struct pvr2_sysfs_class *);
 
 #endif /* __PVRUSB2_SYSFS_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-util.h b/drivers/media/usb/pvrusb2/pvrusb2-util.h
index 92b75544ee2..5465bf9cd73 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-util.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-util.h
@@ -50,13 +50,3 @@
 
 
 #endif /* __PVRUSB2_UTIL_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
index 1b158f1167e..422d79e71e9 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.c
@@ -1360,13 +1360,3 @@ struct pvr2_v4l2 *pvr2_v4l2_create(struct pvr2_context *mnp)
 	pvr2_v4l2_destroy_no_lock(vp);
 	return NULL;
 }
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.h b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.h
index 34c011a7b10..e455c951584 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-v4l2.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-v4l2.h
@@ -27,13 +27,3 @@ struct pvr2_v4l2;
 struct pvr2_v4l2 *pvr2_v4l2_create(struct pvr2_context *);
 
 #endif /* __PVRUSB2_V4L2_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 75 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c b/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c
index 2e205c99eb9..139b3974053 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.c
@@ -101,14 +101,3 @@ void pvr2_saa7115_subdev_update(struct pvr2_hdw *hdw, struct v4l2_subdev *sd)
 		sd->ops->video->s_routing(sd, input, 0, 0);
 	}
 }
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.h b/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.h
index 3b0bd5db602..dacf3ec7f9e 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-video-v4l.h
@@ -36,13 +36,3 @@
 void pvr2_saa7115_subdev_update(struct pvr2_hdw *, struct v4l2_subdev *);
 
 #endif /* __PVRUSB2_VIDEO_V4L_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-wm8775.c b/drivers/media/usb/pvrusb2/pvrusb2-wm8775.c
index 3ac8d751a5c..f1df94a2436 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-wm8775.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-wm8775.c
@@ -56,15 +56,3 @@ void pvr2_wm8775_subdev_update(struct pvr2_hdw *hdw, struct v4l2_subdev *sd)
 		sd->ops->audio->s_routing(sd, input, 0, 0);
 	}
 }
-
-
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-wm8775.h b/drivers/media/usb/pvrusb2/pvrusb2-wm8775.h
index 0577bc7246f..a4ee12e28d5 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-wm8775.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-wm8775.h
@@ -40,13 +40,3 @@ void pvr2_wm8775_subdev_update(struct pvr2_hdw *, struct v4l2_subdev *sd);
 
 
 #endif /* __PVRUSB2_WM8775_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/pvrusb2/pvrusb2.h b/drivers/media/usb/pvrusb2/pvrusb2.h
index 240de9b3566..95f98a87abb 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2.h
@@ -30,13 +30,3 @@
 #define PVR_NUM 20
 
 #endif /* __PVRUSB2_H */
-
-/*
-  Stuff for Emacs to see, in order to encourage consistent editing style:
-  *** Local Variables: ***
-  *** mode: c ***
-  *** fill-column: 70 ***
-  *** tab-width: 8 ***
-  *** c-basic-offset: 8 ***
-  *** End: ***
-  */
diff --git a/drivers/media/usb/usbvision/usbvision-core.c b/drivers/media/usb/usbvision/usbvision-core.c
index 302aa07c458..2144b7b31be 100644
--- a/drivers/media/usb/usbvision/usbvision-core.c
+++ b/drivers/media/usb/usbvision/usbvision-core.c
@@ -2502,11 +2502,3 @@ int usbvision_muxsel(struct usb_usbvision *usbvision, int channel)
 	usbvision_set_audio(usbvision, audio[channel]);
 	return 0;
 }
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/usbvision/usbvision-i2c.c b/drivers/media/usb/usbvision/usbvision-i2c.c
index ba262a32bd3..26dbcb1146a 100644
--- a/drivers/media/usb/usbvision/usbvision-i2c.c
+++ b/drivers/media/usb/usbvision/usbvision-i2c.c
@@ -445,11 +445,3 @@ static struct i2c_adapter i2c_adap_template = {
 	.owner = THIS_MODULE,
 	.name              = "usbvision",
 };
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c
index 693d5f40913..cd2fbf11e3b 100644
--- a/drivers/media/usb/usbvision/usbvision-video.c
+++ b/drivers/media/usb/usbvision/usbvision-video.c
@@ -1716,11 +1716,3 @@ static void __exit usbvision_exit(void)
 
 module_init(usbvision_init);
 module_exit(usbvision_exit);
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/usb/usbvision/usbvision.h b/drivers/media/usb/usbvision/usbvision.h
index a0c73cf1517..77aeb1ed9a8 100644
--- a/drivers/media/usb/usbvision/usbvision.h
+++ b/drivers/media/usb/usbvision/usbvision.h
@@ -517,11 +517,3 @@ int usbvision_power_off(struct usb_usbvision *usbvision);
 int usbvision_power_on(struct usb_usbvision *usbvision);
 
 #endif									/* __LINUX_USBVISION_H */
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 9aa530a8bea..a13cc6123dd 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -1033,10 +1033,3 @@ MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@infradead.org>");
 MODULE_DESCRIPTION("Device registrar for Video4Linux drivers v2");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_CHARDEV_MAJOR(VIDEO_MAJOR);
-
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index d63965a1faa..c3bfa473c3a 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -56,9 +56,3 @@ struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_fro
 int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_frontend *p);
 
 #endif			/* _VIDEOBUF_DVB_H_ */
-
-/*
- * Local variables:
- * c-basic-offset: 8
- * End:
- */
-- 
cgit v1.2.3-70-g09d2


From 05b9cc3eeffcb2b0d6720930fc144058d4ace1aa Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 4 Dec 2014 06:54:53 -0300
Subject: [media] v4l2-subdev: drop get/set_crop pad ops

Drop the duplicate get/set_crop pad ops and only use get/set_selection.
It makes no sense to have two duplicate ops in the internal subdev API.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/v4l2-core/v4l2-subdev.c | 8 --------
 include/media/v4l2-subdev.h           | 4 ----
 2 files changed, 12 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 543631c3557..19a034e79be 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -283,10 +283,6 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 		if (rval)
 			return rval;
 
-		rval = v4l2_subdev_call(sd, pad, get_crop, subdev_fh, crop);
-		if (rval != -ENOIOCTLCMD)
-			return rval;
-
 		memset(&sel, 0, sizeof(sel));
 		sel.which = crop->which;
 		sel.pad = crop->pad;
@@ -308,10 +304,6 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 		if (rval)
 			return rval;
 
-		rval = v4l2_subdev_call(sd, pad, set_crop, subdev_fh, crop);
-		if (rval != -ENOIOCTLCMD)
-			return rval;
-
 		memset(&sel, 0, sizeof(sel));
 		sel.which = crop->which;
 		sel.pad = crop->pad;
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 5860292d42e..b052184512e 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -503,10 +503,6 @@ struct v4l2_subdev_pad_ops {
 		       struct v4l2_subdev_format *format);
 	int (*set_fmt)(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
 		       struct v4l2_subdev_format *format);
-	int (*set_crop)(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
-		       struct v4l2_subdev_crop *crop);
-	int (*get_crop)(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
-		       struct v4l2_subdev_crop *crop);
 	int (*get_selection)(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
 			     struct v4l2_subdev_selection *sel);
 	int (*set_selection)(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh,
-- 
cgit v1.2.3-70-g09d2


From cb03893e3e55924c87943435ab6c7b38e507466c Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 4 Dec 2014 06:54:54 -0300
Subject: [media] v4l2-subdev: drop unused op enum_mbus_fmt

Weird, this op isn't used at all. Seems to be orphaned code.
Remove it.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/v4l2-subdev.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index b052184512e..5beeb8744fd 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -342,8 +342,6 @@ struct v4l2_subdev_video_ops {
 			struct v4l2_dv_timings *timings);
 	int (*enum_mbus_fmt)(struct v4l2_subdev *sd, unsigned int index,
 			     u32 *code);
-	int (*enum_mbus_fsizes)(struct v4l2_subdev *sd,
-			     struct v4l2_frmsizeenum *fsize);
 	int (*g_mbus_fmt)(struct v4l2_subdev *sd,
 			  struct v4l2_mbus_framefmt *fmt);
 	int (*try_mbus_fmt)(struct v4l2_subdev *sd,
-- 
cgit v1.2.3-70-g09d2


From c4827bb859cbe8afad9287c9dd4e7162119d3d59 Mon Sep 17 00:00:00 2001
From: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Date: Thu, 18 Dec 2014 15:04:21 +0200
Subject: spi: pxa2xx: Add definition for Intel Quark DDS_RATE register

Intel Quark DDS_RATE register is defined only in register access macro. Add
a definition for it to common SSP register definitions for preparing to
cleanup those macros.

Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/pxa2xx_ssp.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 77aed9ea1d2..dab545bb66b 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -37,6 +37,7 @@
 #define SSDR		(0x10)  /* SSP Data Write/Data Read Register */
 
 #define SSTO		(0x28)  /* SSP Time Out Register */
+#define DDS_RATE	(0x28)  /* SSP DDS Clock Rate Register (Intel Quark) */
 #define SSPSP		(0x2C)  /* SSP Programmable Serial Protocol */
 #define SSTSA		(0x30)  /* SSP Tx Timeslot Active */
 #define SSRSA		(0x34)  /* SSP Rx Timeslot Active */
-- 
cgit v1.2.3-70-g09d2


From 32d17597d3e299ffe8b07e3afc12f8074e7ae483 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Wed, 9 Apr 2014 08:13:18 -0300
Subject: [media] v4l: vsp1: Remove support for platform data

Now that all platforms instantiate the VSP1 through DT, platform data
support isn't needed anymore.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Acked-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/platform/Kconfig         |  2 +-
 drivers/media/platform/vsp1/vsp1.h     | 14 +++++-
 drivers/media/platform/vsp1/vsp1_drv.c | 81 ++++++++++++----------------------
 drivers/media/platform/vsp1/vsp1_wpf.c |  2 +-
 include/linux/platform_data/vsp1.h     | 27 ------------
 5 files changed, 43 insertions(+), 83 deletions(-)
 delete mode 100644 include/linux/platform_data/vsp1.h

(limited to 'include')

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 765bffb49a7..480a174832a 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -223,7 +223,7 @@ config VIDEO_SH_VEU
 config VIDEO_RENESAS_VSP1
 	tristate "Renesas VSP1 Video Processing Engine"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && HAS_DMA
-	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on (ARCH_SHMOBILE && OF) || COMPILE_TEST
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  This is a V4L2 driver for the Renesas VSP1 video processing engine.
diff --git a/drivers/media/platform/vsp1/vsp1.h b/drivers/media/platform/vsp1/vsp1.h
index 12467191dff..989e96f7e36 100644
--- a/drivers/media/platform/vsp1/vsp1.h
+++ b/drivers/media/platform/vsp1/vsp1.h
@@ -16,7 +16,6 @@
 #include <linux/io.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
-#include <linux/platform_data/vsp1.h>
 
 #include <media/media-device.h>
 #include <media/v4l2-device.h>
@@ -40,9 +39,20 @@ struct vsp1_uds;
 #define VSP1_MAX_UDS		3
 #define VSP1_MAX_WPF		4
 
+#define VSP1_HAS_LIF		(1 << 0)
+#define VSP1_HAS_LUT		(1 << 1)
+#define VSP1_HAS_SRU		(1 << 2)
+
+struct vsp1_platform_data {
+	unsigned int features;
+	unsigned int rpf_count;
+	unsigned int uds_count;
+	unsigned int wpf_count;
+};
+
 struct vsp1_device {
 	struct device *dev;
-	struct vsp1_platform_data *pdata;
+	struct vsp1_platform_data pdata;
 
 	void __iomem *mmio;
 	struct clk *clock;
diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c
index 5eb16e87d53..913485a90e9 100644
--- a/drivers/media/platform/vsp1/vsp1_drv.c
+++ b/drivers/media/platform/vsp1/vsp1_drv.c
@@ -40,7 +40,7 @@ static irqreturn_t vsp1_irq_handler(int irq, void *data)
 	irqreturn_t ret = IRQ_NONE;
 	unsigned int i;
 
-	for (i = 0; i < vsp1->pdata->wpf_count; ++i) {
+	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
 		struct vsp1_rwpf *wpf = vsp1->wpf[i];
 		struct vsp1_pipeline *pipe;
 		u32 status;
@@ -181,7 +181,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 
 	list_add_tail(&vsp1->hst->entity.list_dev, &vsp1->entities);
 
-	if (vsp1->pdata->features & VSP1_HAS_LIF) {
+	if (vsp1->pdata.features & VSP1_HAS_LIF) {
 		vsp1->lif = vsp1_lif_create(vsp1);
 		if (IS_ERR(vsp1->lif)) {
 			ret = PTR_ERR(vsp1->lif);
@@ -191,7 +191,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->lif->entity.list_dev, &vsp1->entities);
 	}
 
-	if (vsp1->pdata->features & VSP1_HAS_LUT) {
+	if (vsp1->pdata.features & VSP1_HAS_LUT) {
 		vsp1->lut = vsp1_lut_create(vsp1);
 		if (IS_ERR(vsp1->lut)) {
 			ret = PTR_ERR(vsp1->lut);
@@ -201,7 +201,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->lut->entity.list_dev, &vsp1->entities);
 	}
 
-	for (i = 0; i < vsp1->pdata->rpf_count; ++i) {
+	for (i = 0; i < vsp1->pdata.rpf_count; ++i) {
 		struct vsp1_rwpf *rpf;
 
 		rpf = vsp1_rpf_create(vsp1, i);
@@ -214,7 +214,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&rpf->entity.list_dev, &vsp1->entities);
 	}
 
-	if (vsp1->pdata->features & VSP1_HAS_SRU) {
+	if (vsp1->pdata.features & VSP1_HAS_SRU) {
 		vsp1->sru = vsp1_sru_create(vsp1);
 		if (IS_ERR(vsp1->sru)) {
 			ret = PTR_ERR(vsp1->sru);
@@ -224,7 +224,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->sru->entity.list_dev, &vsp1->entities);
 	}
 
-	for (i = 0; i < vsp1->pdata->uds_count; ++i) {
+	for (i = 0; i < vsp1->pdata.uds_count; ++i) {
 		struct vsp1_uds *uds;
 
 		uds = vsp1_uds_create(vsp1, i);
@@ -237,7 +237,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&uds->entity.list_dev, &vsp1->entities);
 	}
 
-	for (i = 0; i < vsp1->pdata->wpf_count; ++i) {
+	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
 		struct vsp1_rwpf *wpf;
 
 		wpf = vsp1_wpf_create(vsp1, i);
@@ -261,7 +261,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 			goto done;
 	}
 
-	if (vsp1->pdata->features & VSP1_HAS_LIF) {
+	if (vsp1->pdata.features & VSP1_HAS_LIF) {
 		ret = media_entity_create_link(
 			&vsp1->wpf[0]->entity.subdev.entity, RWPF_PAD_SOURCE,
 			&vsp1->lif->entity.subdev.entity, LIF_PAD_SINK, 0);
@@ -294,7 +294,7 @@ static int vsp1_device_init(struct vsp1_device *vsp1)
 	/* Reset any channel that might be running. */
 	status = vsp1_read(vsp1, VI6_STATUS);
 
-	for (i = 0; i < vsp1->pdata->wpf_count; ++i) {
+	for (i = 0; i < vsp1->pdata.wpf_count; ++i) {
 		unsigned int timeout;
 
 		if (!(status & VI6_STATUS_SYS_ACT(i)))
@@ -318,10 +318,10 @@ static int vsp1_device_init(struct vsp1_device *vsp1)
 	vsp1_write(vsp1, VI6_CLK_DCSWT, (8 << VI6_CLK_DCSWT_CSTPW_SHIFT) |
 		   (8 << VI6_CLK_DCSWT_CSTRW_SHIFT));
 
-	for (i = 0; i < vsp1->pdata->rpf_count; ++i)
+	for (i = 0; i < vsp1->pdata.rpf_count; ++i)
 		vsp1_write(vsp1, VI6_DPR_RPF_ROUTE(i), VI6_DPR_NODE_UNUSED);
 
-	for (i = 0; i < vsp1->pdata->uds_count; ++i)
+	for (i = 0; i < vsp1->pdata.uds_count; ++i)
 		vsp1_write(vsp1, VI6_DPR_UDS_ROUTE(i), VI6_DPR_NODE_UNUSED);
 
 	vsp1_write(vsp1, VI6_DPR_SRU_ROUTE, VI6_DPR_NODE_UNUSED);
@@ -428,28 +428,36 @@ static const struct dev_pm_ops vsp1_pm_ops = {
  * Platform Driver
  */
 
-static int vsp1_validate_platform_data(struct platform_device *pdev,
-				       struct vsp1_platform_data *pdata)
+static int vsp1_parse_dt(struct vsp1_device *vsp1)
 {
-	if (pdata == NULL) {
-		dev_err(&pdev->dev, "missing platform data\n");
-		return -EINVAL;
-	}
+	struct device_node *np = vsp1->dev->of_node;
+	struct vsp1_platform_data *pdata = &vsp1->pdata;
+
+	if (of_property_read_bool(np, "renesas,has-lif"))
+		pdata->features |= VSP1_HAS_LIF;
+	if (of_property_read_bool(np, "renesas,has-lut"))
+		pdata->features |= VSP1_HAS_LUT;
+	if (of_property_read_bool(np, "renesas,has-sru"))
+		pdata->features |= VSP1_HAS_SRU;
+
+	of_property_read_u32(np, "renesas,#rpf", &pdata->rpf_count);
+	of_property_read_u32(np, "renesas,#uds", &pdata->uds_count);
+	of_property_read_u32(np, "renesas,#wpf", &pdata->wpf_count);
 
 	if (pdata->rpf_count <= 0 || pdata->rpf_count > VSP1_MAX_RPF) {
-		dev_err(&pdev->dev, "invalid number of RPF (%u)\n",
+		dev_err(vsp1->dev, "invalid number of RPF (%u)\n",
 			pdata->rpf_count);
 		return -EINVAL;
 	}
 
 	if (pdata->uds_count <= 0 || pdata->uds_count > VSP1_MAX_UDS) {
-		dev_err(&pdev->dev, "invalid number of UDS (%u)\n",
+		dev_err(vsp1->dev, "invalid number of UDS (%u)\n",
 			pdata->uds_count);
 		return -EINVAL;
 	}
 
 	if (pdata->wpf_count <= 0 || pdata->wpf_count > VSP1_MAX_WPF) {
-		dev_err(&pdev->dev, "invalid number of WPF (%u)\n",
+		dev_err(vsp1->dev, "invalid number of WPF (%u)\n",
 			pdata->wpf_count);
 		return -EINVAL;
 	}
@@ -457,33 +465,6 @@ static int vsp1_validate_platform_data(struct platform_device *pdev,
 	return 0;
 }
 
-static struct vsp1_platform_data *
-vsp1_get_platform_data(struct platform_device *pdev)
-{
-	struct device_node *np = pdev->dev.of_node;
-	struct vsp1_platform_data *pdata;
-
-	if (!IS_ENABLED(CONFIG_OF) || np == NULL)
-		return pdev->dev.platform_data;
-
-	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-	if (pdata == NULL)
-		return NULL;
-
-	if (of_property_read_bool(np, "renesas,has-lif"))
-		pdata->features |= VSP1_HAS_LIF;
-	if (of_property_read_bool(np, "renesas,has-lut"))
-		pdata->features |= VSP1_HAS_LUT;
-	if (of_property_read_bool(np, "renesas,has-sru"))
-		pdata->features |= VSP1_HAS_SRU;
-
-	of_property_read_u32(np, "renesas,#rpf", &pdata->rpf_count);
-	of_property_read_u32(np, "renesas,#uds", &pdata->uds_count);
-	of_property_read_u32(np, "renesas,#wpf", &pdata->wpf_count);
-
-	return pdata;
-}
-
 static int vsp1_probe(struct platform_device *pdev)
 {
 	struct vsp1_device *vsp1;
@@ -499,11 +480,7 @@ static int vsp1_probe(struct platform_device *pdev)
 	mutex_init(&vsp1->lock);
 	INIT_LIST_HEAD(&vsp1->entities);
 
-	vsp1->pdata = vsp1_get_platform_data(pdev);
-	if (vsp1->pdata == NULL)
-		return -ENODEV;
-
-	ret = vsp1_validate_platform_data(pdev, vsp1->pdata);
+	ret = vsp1_parse_dt(vsp1);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/media/platform/vsp1/vsp1_wpf.c b/drivers/media/platform/vsp1/vsp1_wpf.c
index 6e057762c93..b1089d05583 100644
--- a/drivers/media/platform/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/vsp1/vsp1_wpf.c
@@ -280,7 +280,7 @@ struct vsp1_rwpf *vsp1_wpf_create(struct vsp1_device *vsp1, unsigned int index)
 	 * except for the WPF0 source link if a LIF is present.
 	 */
 	flags = MEDIA_LNK_FL_ENABLED;
-	if (!(vsp1->pdata->features & VSP1_HAS_LIF) || index != 0)
+	if (!(vsp1->pdata.features & VSP1_HAS_LIF) || index != 0)
 		flags |= MEDIA_LNK_FL_IMMUTABLE;
 
 	ret = media_entity_create_link(&wpf->entity.subdev.entity,
diff --git a/include/linux/platform_data/vsp1.h b/include/linux/platform_data/vsp1.h
deleted file mode 100644
index 63170e2614b..00000000000
--- a/include/linux/platform_data/vsp1.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * vsp1.h  --  R-Car VSP1 Platform Data
- *
- * Copyright (C) 2013 Renesas Corporation
- *
- * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-#ifndef __PLATFORM_VSP1_H__
-#define __PLATFORM_VSP1_H__
-
-#define VSP1_HAS_LIF		(1 << 0)
-#define VSP1_HAS_LUT		(1 << 1)
-#define VSP1_HAS_SRU		(1 << 2)
-
-struct vsp1_platform_data {
-	unsigned int features;
-	unsigned int rpf_count;
-	unsigned int uds_count;
-	unsigned int wpf_count;
-};
-
-#endif /* __PLATFORM_VSP1_H__ */
-- 
cgit v1.2.3-70-g09d2


From 17028cdb74bf8bb593aebe5550bc90325fa9af88 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 1 Dec 2014 10:10:44 -0300
Subject: [media] v4l2 core: improve debug flag handling

The old debug field is renamed to dev_debug to ensure that existing drivers
(including out-of-tree drivers) that try to use the old name will no longer
compile. A comment has also been added that makes it explicit that drivers
shouldn't use this field.

Additional bits have been added to the debug flag to be more fine-grained
when debugging, especially when dealing with streaming ioctls and read,
write and poll. You want to enable those explicitly to prevent flooding
the log when streaming unless you actually want to do that.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/v4l2-core/v4l2-dev.c   | 28 +++++++++++++++-------------
 drivers/media/v4l2-core/v4l2-ioctl.c | 10 +++++++---
 include/media/v4l2-dev.h             |  3 ++-
 include/media/v4l2-ioctl.h           | 15 ++++++++++++---
 4 files changed, 36 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index a13cc6123dd..86bb93fd7db 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -47,15 +47,15 @@ static ssize_t index_show(struct device *cd,
 }
 static DEVICE_ATTR_RO(index);
 
-static ssize_t debug_show(struct device *cd,
+static ssize_t dev_debug_show(struct device *cd,
 			  struct device_attribute *attr, char *buf)
 {
 	struct video_device *vdev = to_video_device(cd);
 
-	return sprintf(buf, "%i\n", vdev->debug);
+	return sprintf(buf, "%i\n", vdev->dev_debug);
 }
 
-static ssize_t debug_store(struct device *cd, struct device_attribute *attr,
+static ssize_t dev_debug_store(struct device *cd, struct device_attribute *attr,
 			  const char *buf, size_t len)
 {
 	struct video_device *vdev = to_video_device(cd);
@@ -66,10 +66,10 @@ static ssize_t debug_store(struct device *cd, struct device_attribute *attr,
 	if (res)
 		return res;
 
-	vdev->debug = value;
+	vdev->dev_debug = value;
 	return len;
 }
-static DEVICE_ATTR_RW(debug);
+static DEVICE_ATTR_RW(dev_debug);
 
 static ssize_t name_show(struct device *cd,
 			 struct device_attribute *attr, char *buf)
@@ -82,7 +82,7 @@ static DEVICE_ATTR_RO(name);
 
 static struct attribute *video_device_attrs[] = {
 	&dev_attr_name.attr,
-	&dev_attr_debug.attr,
+	&dev_attr_dev_debug.attr,
 	&dev_attr_index.attr,
 	NULL,
 };
@@ -304,7 +304,8 @@ static ssize_t v4l2_read(struct file *filp, char __user *buf,
 		return -EINVAL;
 	if (video_is_registered(vdev))
 		ret = vdev->fops->read(filp, buf, sz, off);
-	if (vdev->debug)
+	if ((vdev->dev_debug & V4L2_DEV_DEBUG_FOP) &&
+	    (vdev->dev_debug & V4L2_DEV_DEBUG_STREAMING))
 		printk(KERN_DEBUG "%s: read: %zd (%d)\n",
 			video_device_node_name(vdev), sz, ret);
 	return ret;
@@ -320,7 +321,8 @@ static ssize_t v4l2_write(struct file *filp, const char __user *buf,
 		return -EINVAL;
 	if (video_is_registered(vdev))
 		ret = vdev->fops->write(filp, buf, sz, off);
-	if (vdev->debug)
+	if ((vdev->dev_debug & V4L2_DEV_DEBUG_FOP) &&
+	    (vdev->dev_debug & V4L2_DEV_DEBUG_STREAMING))
 		printk(KERN_DEBUG "%s: write: %zd (%d)\n",
 			video_device_node_name(vdev), sz, ret);
 	return ret;
@@ -335,7 +337,7 @@ static unsigned int v4l2_poll(struct file *filp, struct poll_table_struct *poll)
 		return DEFAULT_POLLMASK;
 	if (video_is_registered(vdev))
 		res = vdev->fops->poll(filp, poll);
-	if (vdev->debug > 2)
+	if (vdev->dev_debug & V4L2_DEV_DEBUG_POLL)
 		printk(KERN_DEBUG "%s: poll: %08x\n",
 			video_device_node_name(vdev), res);
 	return res;
@@ -404,7 +406,7 @@ static unsigned long v4l2_get_unmapped_area(struct file *filp,
 	if (!video_is_registered(vdev))
 		return -ENODEV;
 	ret = vdev->fops->get_unmapped_area(filp, addr, len, pgoff, flags);
-	if (vdev->debug)
+	if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP)
 		printk(KERN_DEBUG "%s: get_unmapped_area (%d)\n",
 			video_device_node_name(vdev), ret);
 	return ret;
@@ -420,7 +422,7 @@ static int v4l2_mmap(struct file *filp, struct vm_area_struct *vm)
 		return -ENODEV;
 	if (video_is_registered(vdev))
 		ret = vdev->fops->mmap(filp, vm);
-	if (vdev->debug)
+	if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP)
 		printk(KERN_DEBUG "%s: mmap (%d)\n",
 			video_device_node_name(vdev), ret);
 	return ret;
@@ -450,7 +452,7 @@ static int v4l2_open(struct inode *inode, struct file *filp)
 			ret = -ENODEV;
 	}
 
-	if (vdev->debug)
+	if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP)
 		printk(KERN_DEBUG "%s: open (%d)\n",
 			video_device_node_name(vdev), ret);
 	/* decrease the refcount in case of an error */
@@ -467,7 +469,7 @@ static int v4l2_release(struct inode *inode, struct file *filp)
 
 	if (vdev->fops->release)
 		ret = vdev->fops->release(filp);
-	if (vdev->debug)
+	if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP)
 		printk(KERN_DEBUG "%s: release\n",
 			video_device_node_name(vdev));
 
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index faac2f4e0f3..b08407225db 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -2339,7 +2339,7 @@ static long __video_do_ioctl(struct file *file,
 	const struct v4l2_ioctl_info *info;
 	void *fh = file->private_data;
 	struct v4l2_fh *vfh = NULL;
-	int debug = vfd->debug;
+	int dev_debug = vfd->dev_debug;
 	long ret = -ENOTTY;
 
 	if (ops == NULL) {
@@ -2388,11 +2388,15 @@ static long __video_do_ioctl(struct file *file,
 	}
 
 done:
-	if (debug) {
+	if (dev_debug & (V4L2_DEV_DEBUG_IOCTL | V4L2_DEV_DEBUG_IOCTL_ARG)) {
+		if (!(dev_debug & V4L2_DEV_DEBUG_STREAMING) &&
+		    (cmd == VIDIOC_QBUF || cmd == VIDIOC_DQBUF))
+			return ret;
+
 		v4l_printk_ioctl(video_device_node_name(vfd), cmd);
 		if (ret < 0)
 			pr_cont(": error %ld", ret);
-		if (debug == V4L2_DEBUG_IOCTL)
+		if (!(dev_debug & V4L2_DEV_DEBUG_IOCTL_ARG))
 			pr_cont("\n");
 		else if (_IOC_DIR(cmd) == _IOC_NONE)
 			info->debug(arg, write_only);
diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h
index eb76cfd4718..3e4fddfc840 100644
--- a/include/media/v4l2-dev.h
+++ b/include/media/v4l2-dev.h
@@ -124,7 +124,8 @@ struct video_device
 	spinlock_t		fh_lock; /* Lock for all v4l2_fhs */
 	struct list_head	fh_list; /* List of struct v4l2_fh */
 
-	int debug;			/* Activates debug level*/
+	/* Internal device debug flags, not for use by drivers */
+	int dev_debug;
 
 	/* Video standard vars */
 	v4l2_std_id tvnorms;		/* Supported tv norms */
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index 53605f0f990..8537983b9b2 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -291,9 +291,18 @@ struct v4l2_ioctl_ops {
 
 /* v4l debugging and diagnostics */
 
-/* Debug bitmask flags to be used on V4L2 */
-#define V4L2_DEBUG_IOCTL     0x01
-#define V4L2_DEBUG_IOCTL_ARG 0x02
+/* Device debug flags to be used with the video device debug attribute */
+
+/* Just log the ioctl name + error code */
+#define V4L2_DEV_DEBUG_IOCTL		0x01
+/* Log the ioctl name arguments + error code */
+#define V4L2_DEV_DEBUG_IOCTL_ARG	0x02
+/* Log the file operations open, release, mmap and get_unmapped_area */
+#define V4L2_DEV_DEBUG_FOP		0x04
+/* Log the read and write file operations and the VIDIOC_(D)QBUF ioctls */
+#define V4L2_DEV_DEBUG_STREAMING	0x08
+/* Log poll() */
+#define V4L2_DEV_DEBUG_POLL		0x10
 
 /*  Video standard functions  */
 extern const char *v4l2_norm_to_name(v4l2_std_id id);
-- 
cgit v1.2.3-70-g09d2


From cbb77bc281d697764dbb035157b643a8cbc9df30 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@iki.fi>
Date: Sun, 7 Dec 2014 20:17:49 -0300
Subject: [media] DocBook: v4l: Rearrange raw bayer format definitions, remove
 bad comment

Rearrange 12-bit raw bayer format definitions after 10-bit ones. Also remove
the comment related to 16-bit bayer formats, it was simply wrong.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/uapi/linux/videodev2.h | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index d279c1b75cf..f0b94b8fcdf 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -463,10 +463,6 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_SGBRG10 v4l2_fourcc('G', 'B', '1', '0') /* 10  GBGB.. RGRG.. */
 #define V4L2_PIX_FMT_SGRBG10 v4l2_fourcc('B', 'A', '1', '0') /* 10  GRGR.. BGBG.. */
 #define V4L2_PIX_FMT_SRGGB10 v4l2_fourcc('R', 'G', '1', '0') /* 10  RGRG.. GBGB.. */
-#define V4L2_PIX_FMT_SBGGR12 v4l2_fourcc('B', 'G', '1', '2') /* 12  BGBG.. GRGR.. */
-#define V4L2_PIX_FMT_SGBRG12 v4l2_fourcc('G', 'B', '1', '2') /* 12  GBGB.. RGRG.. */
-#define V4L2_PIX_FMT_SGRBG12 v4l2_fourcc('B', 'A', '1', '2') /* 12  GRGR.. BGBG.. */
-#define V4L2_PIX_FMT_SRGGB12 v4l2_fourcc('R', 'G', '1', '2') /* 12  RGRG.. GBGB.. */
 	/* 10bit raw bayer a-law compressed to 8 bits */
 #define V4L2_PIX_FMT_SBGGR10ALAW8 v4l2_fourcc('a', 'B', 'A', '8')
 #define V4L2_PIX_FMT_SGBRG10ALAW8 v4l2_fourcc('a', 'G', 'A', '8')
@@ -477,10 +473,10 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_SGBRG10DPCM8 v4l2_fourcc('b', 'G', 'A', '8')
 #define V4L2_PIX_FMT_SGRBG10DPCM8 v4l2_fourcc('B', 'D', '1', '0')
 #define V4L2_PIX_FMT_SRGGB10DPCM8 v4l2_fourcc('b', 'R', 'A', '8')
-	/*
-	 * 10bit raw bayer, expanded to 16 bits
-	 * xxxxrrrrrrrrrrxxxxgggggggggg xxxxggggggggggxxxxbbbbbbbbbb...
-	 */
+#define V4L2_PIX_FMT_SBGGR12 v4l2_fourcc('B', 'G', '1', '2') /* 12  BGBG.. GRGR.. */
+#define V4L2_PIX_FMT_SGBRG12 v4l2_fourcc('G', 'B', '1', '2') /* 12  GBGB.. RGRG.. */
+#define V4L2_PIX_FMT_SGRBG12 v4l2_fourcc('B', 'A', '1', '2') /* 12  GRGR.. BGBG.. */
+#define V4L2_PIX_FMT_SRGGB12 v4l2_fourcc('R', 'G', '1', '2') /* 12  RGRG.. GBGB.. */
 #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16  BGBG.. GRGR.. */
 
 /* compressed formats */
-- 
cgit v1.2.3-70-g09d2


From 4353e36ee84d936859eb6d65ecd9d3076edd11bc Mon Sep 17 00:00:00 2001
From: Aviv Greenberg <aviv.d.greenberg@intel.com>
Date: Wed, 3 Dec 2014 08:14:09 -0300
Subject: [media] v4l: Add packed Bayer raw10 pixel formats

These formats are just like 10-bit raw bayer formats that exist already, but
the pixels are not padded to byte boundaries. Instead, the eight high order
bits of four consecutive pixels are stored in four bytes, followed by a byte
of two low order bits of each of the four pixels.

Signed-off-by: Aviv Greenberg <aviv.d.greenberg@intel.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 .../DocBook/media/v4l/pixfmt-srggb10p.xml          | 99 ++++++++++++++++++++++
 Documentation/DocBook/media/v4l/pixfmt.xml         |  1 +
 include/uapi/linux/videodev2.h                     |  5 ++
 3 files changed, 105 insertions(+)
 create mode 100644 Documentation/DocBook/media/v4l/pixfmt-srggb10p.xml

(limited to 'include')

diff --git a/Documentation/DocBook/media/v4l/pixfmt-srggb10p.xml b/Documentation/DocBook/media/v4l/pixfmt-srggb10p.xml
new file mode 100644
index 00000000000..30aa63581fe
--- /dev/null
+++ b/Documentation/DocBook/media/v4l/pixfmt-srggb10p.xml
@@ -0,0 +1,99 @@
+    <refentry id="pixfmt-srggb10p">
+      <refmeta>
+	<refentrytitle>V4L2_PIX_FMT_SRGGB10P ('pRAA'),
+	 V4L2_PIX_FMT_SGRBG10P ('pgAA'),
+	 V4L2_PIX_FMT_SGBRG10P ('pGAA'),
+	 V4L2_PIX_FMT_SBGGR10P ('pBAA'),
+	 </refentrytitle>
+	&manvol;
+      </refmeta>
+      <refnamediv>
+	<refname id="V4L2-PIX-FMT-SRGGB10P"><constant>V4L2_PIX_FMT_SRGGB10P</constant></refname>
+	<refname id="V4L2-PIX-FMT-SGRBG10P"><constant>V4L2_PIX_FMT_SGRBG10P</constant></refname>
+	<refname id="V4L2-PIX-FMT-SGBRG10P"><constant>V4L2_PIX_FMT_SGBRG10P</constant></refname>
+	<refname id="V4L2-PIX-FMT-SBGGR10P"><constant>V4L2_PIX_FMT_SBGGR10P</constant></refname>
+	<refpurpose>10-bit packed Bayer formats</refpurpose>
+      </refnamediv>
+      <refsect1>
+	<title>Description</title>
+
+	<para>These four pixel formats are packed raw sRGB /
+	Bayer formats with 10 bits per colour. Every four consecutive
+	colour components are packed into 5 bytes. Each of the first 4
+	bytes contain the 8 high order bits of the pixels, and the
+	fifth byte contains the two least significants bits of each
+	pixel, in the same order.</para>
+
+	<para>Each n-pixel row contains n/2 green samples and n/2 blue
+	or red samples, with alternating green-red and green-blue
+	rows. They are conventionally described as GRGR... BGBG...,
+	RGRG... GBGB..., etc. Below is an example of one of these
+	formats:</para>
+
+    <example>
+      <title><constant>V4L2_PIX_FMT_SBGGR10P</constant> 4 &times; 4
+      pixel image</title>
+
+      <formalpara>
+	<title>Byte Order.</title>
+	<para>Each cell is one byte.
+	  <informaltable frame="topbot" colsep="1" rowsep="1">
+	    <tgroup cols="5" align="center" border="1">
+	      <colspec align="left" colwidth="2*" />
+	      <tbody valign="top">
+		<row>
+		  <entry>start&nbsp;+&nbsp;0:</entry>
+		  <entry>B<subscript>00high</subscript></entry>
+		  <entry>G<subscript>01high</subscript></entry>
+		  <entry>B<subscript>02high</subscript></entry>
+		  <entry>G<subscript>03high</subscript></entry>
+		  <entry>B<subscript>00low</subscript>(bits 7--6)
+			 G<subscript>01low</subscript>(bits 5--4)
+			 B<subscript>02low</subscript>(bits 3--2)
+			 G<subscript>03low</subscript>(bits 1--0)
+		  </entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;5:</entry>
+		  <entry>G<subscript>10high</subscript></entry>
+		  <entry>R<subscript>11high</subscript></entry>
+		  <entry>G<subscript>12high</subscript></entry>
+		  <entry>R<subscript>13high</subscript></entry>
+		  <entry>G<subscript>10low</subscript>(bits 7--6)
+			 R<subscript>11low</subscript>(bits 5--4)
+			 G<subscript>12low</subscript>(bits 3--2)
+			 R<subscript>13low</subscript>(bits 1--0)
+		  </entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;10:</entry>
+		  <entry>B<subscript>20high</subscript></entry>
+		  <entry>G<subscript>21high</subscript></entry>
+		  <entry>B<subscript>22high</subscript></entry>
+		  <entry>G<subscript>23high</subscript></entry>
+		  <entry>B<subscript>20low</subscript>(bits 7--6)
+			 G<subscript>21low</subscript>(bits 5--4)
+			 B<subscript>22low</subscript>(bits 3--2)
+			 G<subscript>23low</subscript>(bits 1--0)
+		  </entry>
+		</row>
+		<row>
+		  <entry>start&nbsp;+&nbsp;15:</entry>
+		  <entry>G<subscript>30high</subscript></entry>
+		  <entry>R<subscript>31high</subscript></entry>
+		  <entry>G<subscript>32high</subscript></entry>
+		  <entry>R<subscript>33high</subscript></entry>
+		  <entry>G<subscript>30low</subscript>(bits 7--6)
+			 R<subscript>31low</subscript>(bits 5--4)
+			 G<subscript>32low</subscript>(bits 3--2)
+			 R<subscript>33low</subscript>(bits 1--0)
+		  </entry>
+		</row>
+	      </tbody>
+	    </tgroup>
+	  </informaltable>
+	</para>
+      </formalpara>
+    </example>
+  </refsect1>
+</refentry>
diff --git a/Documentation/DocBook/media/v4l/pixfmt.xml b/Documentation/DocBook/media/v4l/pixfmt.xml
index d5eca4b8f74..5e0352c5032 100644
--- a/Documentation/DocBook/media/v4l/pixfmt.xml
+++ b/Documentation/DocBook/media/v4l/pixfmt.xml
@@ -1405,6 +1405,7 @@ access the palette, this must be done with ioctls of the Linux framebuffer API.<
     &sub-srggb8;
     &sub-sbggr16;
     &sub-srggb10;
+    &sub-srggb10p;
     &sub-srggb10alaw8;
     &sub-srggb10dpcm8;
     &sub-srggb12;
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index f0b94b8fcdf..fbdc3602ee2 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -463,6 +463,11 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_SGBRG10 v4l2_fourcc('G', 'B', '1', '0') /* 10  GBGB.. RGRG.. */
 #define V4L2_PIX_FMT_SGRBG10 v4l2_fourcc('B', 'A', '1', '0') /* 10  GRGR.. BGBG.. */
 #define V4L2_PIX_FMT_SRGGB10 v4l2_fourcc('R', 'G', '1', '0') /* 10  RGRG.. GBGB.. */
+	/* 10bit raw bayer packed, 5 bytes for every 4 pixels */
+#define V4L2_PIX_FMT_SBGGR10P v4l2_fourcc('p', 'B', 'A', 'A')
+#define V4L2_PIX_FMT_SGBRG10P v4l2_fourcc('p', 'G', 'A', 'A')
+#define V4L2_PIX_FMT_SGRBG10P v4l2_fourcc('p', 'g', 'A', 'A')
+#define V4L2_PIX_FMT_SRGGB10P v4l2_fourcc('p', 'R', 'A', 'A')
 	/* 10bit raw bayer a-law compressed to 8 bits */
 #define V4L2_PIX_FMT_SBGGR10ALAW8 v4l2_fourcc('a', 'B', 'A', '8')
 #define V4L2_PIX_FMT_SGBRG10ALAW8 v4l2_fourcc('a', 'G', 'A', '8')
-- 
cgit v1.2.3-70-g09d2


From ec176a6f142bb403b8a9b977a6919b556e80ea99 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@iki.fi>
Date: Sat, 30 Nov 2013 16:35:48 -0300
Subject: [media] smiapp: Use types better suitable for DT

Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/media/smiapp.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/media/smiapp.h b/include/media/smiapp.h
index 0b8f124a630..268a3cdbf6c 100644
--- a/include/media/smiapp.h
+++ b/include/media/smiapp.h
@@ -65,19 +65,19 @@ struct smiapp_platform_data {
 	unsigned short i2c_addr_dfl;	/* Default i2c addr */
 	unsigned short i2c_addr_alt;	/* Alternate i2c addr */
 
-	unsigned int nvm_size;			/* bytes */
-	unsigned int ext_clk;			/* sensor external clk */
+	uint32_t nvm_size;		/* bytes */
+	uint32_t ext_clk;		/* sensor external clk */
 
 	unsigned int lanes;		/* Number of CSI-2 lanes */
-	u8 csi_signalling_mode;		/* SMIAPP_CSI_SIGNALLING_MODE_* */
-	const s64 *op_sys_clock;
+	uint32_t csi_signalling_mode;	/* SMIAPP_CSI_SIGNALLING_MODE_* */
+	uint64_t *op_sys_clock;
 
 	enum smiapp_module_board_orient module_board_orient;
 
 	struct smiapp_flash_strobe_parms *strobe_setup;
 
 	int (*set_xclk)(struct v4l2_subdev *sd, int hz);
-	int xshutdown;			/* gpio or SMIAPP_NO_XSHUTDOWN */
+	int32_t xshutdown;		/* gpio or SMIAPP_NO_XSHUTDOWN */
 };
 
 #endif /* __SMIAPP_H_  */
-- 
cgit v1.2.3-70-g09d2


From 417d2e507edcb5cf15eb344f86bd3dd28737f24e Mon Sep 17 00:00:00 2001
From: Benoit Parrot <bparrot@ti.com>
Date: Tue, 9 Dec 2014 16:43:44 -0300
Subject: [media] media: platform: add VPFE capture driver support for AM437X

This patch adds Video Processing Front End (VPFE) driver for
AM437X family of devices
Driver supports the following:
- V4L2 API using MMAP buffer access based on videobuf2 api
- Asynchronous sensor/decoder sub device registration
- DT support

Signed-off-by: Benoit Parrot <bparrot@ti.com>
Signed-off-by: Darren Etheridge <detheridge@ti.com>
Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
[hans.verkuil@cisco.com: swapped two lines to fix vpfe_release() & add pinctrl include]
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>

Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 .../devicetree/bindings/media/ti-am437x-vpfe.txt   |   61 +
 MAINTAINERS                                        |    9 +
 drivers/media/platform/Kconfig                     |    1 +
 drivers/media/platform/Makefile                    |    2 +
 drivers/media/platform/am437x/Kconfig              |   11 +
 drivers/media/platform/am437x/Makefile             |    3 +
 drivers/media/platform/am437x/am437x-vpfe.c        | 2778 ++++++++++++++++++++
 drivers/media/platform/am437x/am437x-vpfe.h        |  283 ++
 drivers/media/platform/am437x/am437x-vpfe_regs.h   |  140 +
 include/uapi/linux/Kbuild                          |    1 +
 include/uapi/linux/am437x-vpfe.h                   |  122 +
 11 files changed, 3411 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/media/ti-am437x-vpfe.txt
 create mode 100644 drivers/media/platform/am437x/Kconfig
 create mode 100644 drivers/media/platform/am437x/Makefile
 create mode 100644 drivers/media/platform/am437x/am437x-vpfe.c
 create mode 100644 drivers/media/platform/am437x/am437x-vpfe.h
 create mode 100644 drivers/media/platform/am437x/am437x-vpfe_regs.h
 create mode 100644 include/uapi/linux/am437x-vpfe.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/media/ti-am437x-vpfe.txt b/Documentation/devicetree/bindings/media/ti-am437x-vpfe.txt
new file mode 100644
index 00000000000..3932e766553
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/ti-am437x-vpfe.txt
@@ -0,0 +1,61 @@
+Texas Instruments AM437x CAMERA (VPFE)
+--------------------------------------
+
+The Video Processing Front End (VPFE) is a key component for image capture
+applications. The capture module provides the system interface and the
+processing capability to connect RAW image-sensor modules and video decoders
+to the AM437x device.
+
+Required properties:
+- compatible: must be "ti,am437x-vpfe"
+- reg: physical base address and length of the registers set for the device;
+- interrupts: should contain IRQ line for the VPFE;
+- ti,am437x-vpfe-interface: can be one of the following,
+	0 - Raw Bayer Interface.
+	1 - 8 Bit BT656 Interface.
+	2 - 10 Bit BT656 Interface.
+	3 - YCbCr 8 Bit Interface.
+	4 - YCbCr 16 Bit Interface.
+
+VPFE supports a single port node with parallel bus. It should contain one
+'port' child node with child 'endpoint' node. Please refer to the bindings
+defined in Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+Example:
+	vpfe: vpfe@f0034000 {
+		compatible = "ti,am437x-vpfe";
+		reg = <0x48328000 0x2000>;
+		interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>;
+
+		pinctrl-names = "default", "sleep";
+		pinctrl-0 = <&vpfe_pins_default>;
+		pinctrl-1 = <&vpfe_pins_sleep>;
+
+		port {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			vpfe0_ep: endpoint {
+				remote-endpoint = <&ov2659_1>;
+				ti,am437x-vpfe-interface = <0>;
+				bus-width = <8>;
+				hsync-active = <0>;
+				vsync-active = <0>;
+			};
+		};
+	};
+
+	i2c1: i2c@4802a000 {
+
+		ov2659@30 {
+			compatible = "ti,ov2659";
+			reg = <0x30>;
+
+			port {
+				ov2659_1: endpoint {
+					remote-endpoint = <&vpfe0_ep>;
+					bus-width = <8>;
+					mclk-frequency = <12000000>;
+				};
+			};
+	};
diff --git a/MAINTAINERS b/MAINTAINERS
index dc2d91252d8..4318f348dbd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8745,6 +8745,15 @@ S:	Maintained
 F:	drivers/media/platform/davinci/
 F:	include/media/davinci/
 
+TI AM437X VPFE DRIVER
+M:	Lad, Prabhakar <prabhakar.csengg@gmail.com>
+L:	linux-media@vger.kernel.org
+W:	http://linuxtv.org/
+Q:	http://patchwork.linuxtv.org/project/linux-media/list/
+T:	git git://linuxtv.org/mhadli/v4l-dvb-davinci_devices.git
+S:	Maintained
+F:	drivers/media/platform/am437x/
+
 SIS 190 ETHERNET DRIVER
 M:	Francois Romieu <romieu@fr.zoreil.com>
 L:	netdev@vger.kernel.org
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 480a174832a..71e8873ceb9 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -118,6 +118,7 @@ config VIDEO_S3C_CAMIF
 source "drivers/media/platform/soc_camera/Kconfig"
 source "drivers/media/platform/exynos4-is/Kconfig"
 source "drivers/media/platform/s5p-tv/Kconfig"
+source "drivers/media/platform/am437x/Kconfig"
 
 endif # V4L_PLATFORM_DRIVERS
 
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index a49936b8ce8..3ec15474208 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -46,4 +46,6 @@ obj-$(CONFIG_VIDEO_RENESAS_VSP1)	+= vsp1/
 
 obj-y	+= omap/
 
+obj-$(CONFIG_VIDEO_AM437X_VPFE)		+= am437x/
+
 ccflags-y += -I$(srctree)/drivers/media/i2c
diff --git a/drivers/media/platform/am437x/Kconfig b/drivers/media/platform/am437x/Kconfig
new file mode 100644
index 00000000000..7b023a76e32
--- /dev/null
+++ b/drivers/media/platform/am437x/Kconfig
@@ -0,0 +1,11 @@
+config VIDEO_AM437X_VPFE
+	tristate "TI AM437x VPFE video capture driver"
+	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	depends on SOC_AM43XX || COMPILE_TEST
+	select VIDEOBUF2_DMA_CONTIG
+	help
+	   Support for AM437x Video Processing Front End based Video
+	   Capture Driver.
+
+	   To compile this driver as a module, choose M here. The module
+	   will be called am437x-vpfe.
diff --git a/drivers/media/platform/am437x/Makefile b/drivers/media/platform/am437x/Makefile
new file mode 100644
index 00000000000..d11fff16f26
--- /dev/null
+++ b/drivers/media/platform/am437x/Makefile
@@ -0,0 +1,3 @@
+# Makefile for AM437x VPFE driver
+
+obj-$(CONFIG_VIDEO_AM437X_VPFE) += am437x-vpfe.o
diff --git a/drivers/media/platform/am437x/am437x-vpfe.c b/drivers/media/platform/am437x/am437x-vpfe.c
new file mode 100644
index 00000000000..e01ac22d624
--- /dev/null
+++ b/drivers/media/platform/am437x/am437x-vpfe.c
@@ -0,0 +1,2778 @@
+/*
+ * TI VPFE capture Driver
+ *
+ * Copyright (C) 2013 - 2014 Texas Instruments, Inc.
+ *
+ * Benoit Parrot <bparrot@ti.com>
+ * Lad, Prabhakar <prabhakar.csengg@gmail.com>
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-of.h>
+
+#include "am437x-vpfe.h"
+
+#define VPFE_MODULE_NAME	"vpfe"
+#define VPFE_VERSION		"0.1.0"
+
+static int debug;
+module_param(debug, int, 0644);
+MODULE_PARM_DESC(debug, "Debug level 0-8");
+
+#define vpfe_dbg(level, dev, fmt, arg...)	\
+		v4l2_dbg(level, debug, &dev->v4l2_dev, fmt, ##arg)
+#define vpfe_info(dev, fmt, arg...)	\
+		v4l2_info(&dev->v4l2_dev, fmt, ##arg)
+#define vpfe_err(dev, fmt, arg...)	\
+		v4l2_err(&dev->v4l2_dev, fmt, ##arg)
+
+/* standard information */
+struct vpfe_standard {
+	v4l2_std_id std_id;
+	unsigned int width;
+	unsigned int height;
+	struct v4l2_fract pixelaspect;
+	int frame_format;
+};
+
+const struct vpfe_standard vpfe_standards[] = {
+	{V4L2_STD_525_60, 720, 480, {11, 10}, 1},
+	{V4L2_STD_625_50, 720, 576, {54, 59}, 1},
+};
+
+struct bus_format {
+	unsigned int width;
+	unsigned int bpp;
+};
+
+/*
+ * struct vpfe_fmt - VPFE media bus format information
+ * @name: V4L2 format description
+ * @code: V4L2 media bus format code
+ * @shifted: V4L2 media bus format code for the same pixel layout but
+ *	shifted to be 8 bits per pixel. =0 if format is not shiftable.
+ * @pixelformat: V4L2 pixel format FCC identifier
+ * @width: Bits per pixel (when transferred over a bus)
+ * @bpp: Bytes per pixel (when stored in memory)
+ * @supported: Indicates format supported by subdev
+ */
+struct vpfe_fmt {
+	const char *name;
+	u32 fourcc;
+	u32 code;
+	struct bus_format l;
+	struct bus_format s;
+	bool supported;
+	u32 index;
+};
+
+static struct vpfe_fmt formats[] = {
+	{
+		.name		= "YUV 4:2:2 packed, YCbYCr",
+		.fourcc		= V4L2_PIX_FMT_YUYV,
+		.code		= MEDIA_BUS_FMT_YUYV8_2X8,
+		.l.width	= 10,
+		.l.bpp		= 4,
+		.s.width	= 8,
+		.s.bpp		= 2,
+		.supported	= false,
+	}, {
+		.name		= "YUV 4:2:2 packed, CbYCrY",
+		.fourcc		= V4L2_PIX_FMT_UYVY,
+		.code		= MEDIA_BUS_FMT_UYVY8_2X8,
+		.l.width	= 10,
+		.l.bpp		= 4,
+		.s.width	= 8,
+		.s.bpp		= 2,
+		.supported	= false,
+	}, {
+		.name		= "YUV 4:2:2 packed, YCrYCb",
+		.fourcc		= V4L2_PIX_FMT_YVYU,
+		.code		= MEDIA_BUS_FMT_YVYU8_2X8,
+		.l.width	= 10,
+		.l.bpp		= 4,
+		.s.width	= 8,
+		.s.bpp		= 2,
+		.supported	= false,
+	}, {
+		.name		= "YUV 4:2:2 packed, CrYCbY",
+		.fourcc		= V4L2_PIX_FMT_VYUY,
+		.code		= MEDIA_BUS_FMT_VYUY8_2X8,
+		.l.width	= 10,
+		.l.bpp		= 4,
+		.s.width	= 8,
+		.s.bpp		= 2,
+		.supported	= false,
+	}, {
+		.name		= "RAW8 BGGR",
+		.fourcc		= V4L2_PIX_FMT_SBGGR8,
+		.code		= MEDIA_BUS_FMT_SBGGR8_1X8,
+		.l.width	= 10,
+		.l.bpp		= 2,
+		.s.width	= 8,
+		.s.bpp		= 1,
+		.supported	= false,
+	}, {
+		.name		= "RAW8 GBRG",
+		.fourcc		= V4L2_PIX_FMT_SGBRG8,
+		.code		= MEDIA_BUS_FMT_SGBRG8_1X8,
+		.l.width	= 10,
+		.l.bpp		= 2,
+		.s.width	= 8,
+		.s.bpp		= 1,
+		.supported	= false,
+	}, {
+		.name		= "RAW8 GRBG",
+		.fourcc		= V4L2_PIX_FMT_SGRBG8,
+		.code		= MEDIA_BUS_FMT_SGRBG8_1X8,
+		.l.width	= 10,
+		.l.bpp		= 2,
+		.s.width	= 8,
+		.s.bpp		= 1,
+		.supported	= false,
+	}, {
+		.name		= "RAW8 RGGB",
+		.fourcc		= V4L2_PIX_FMT_SRGGB8,
+		.code		= MEDIA_BUS_FMT_SRGGB8_1X8,
+		.l.width	= 10,
+		.l.bpp		= 2,
+		.s.width	= 8,
+		.s.bpp		= 1,
+		.supported	= false,
+	}, {
+		.name		= "RGB565 (LE)",
+		.fourcc		= V4L2_PIX_FMT_RGB565,
+		.code		= MEDIA_BUS_FMT_RGB565_2X8_LE,
+		.l.width	= 10,
+		.l.bpp		= 4,
+		.s.width	= 8,
+		.s.bpp		= 2,
+		.supported	= false,
+	}, {
+		.name		= "RGB565 (BE)",
+		.fourcc		= V4L2_PIX_FMT_RGB565X,
+		.code		= MEDIA_BUS_FMT_RGB565_2X8_BE,
+		.l.width	= 10,
+		.l.bpp		= 4,
+		.s.width	= 8,
+		.s.bpp		= 2,
+		.supported	= false,
+	},
+};
+
+static int
+__vpfe_get_format(struct vpfe_device *vpfe,
+		  struct v4l2_format *format, unsigned int *bpp);
+
+static struct vpfe_fmt *find_format_by_code(unsigned int code)
+{
+	struct vpfe_fmt *fmt;
+	unsigned int k;
+
+	for (k = 0; k < ARRAY_SIZE(formats); k++) {
+		fmt = &formats[k];
+		if (fmt->code == code)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+static struct vpfe_fmt *find_format_by_pix(unsigned int pixelformat)
+{
+	struct vpfe_fmt *fmt;
+	unsigned int k;
+
+	for (k = 0; k < ARRAY_SIZE(formats); k++) {
+		fmt = &formats[k];
+		if (fmt->fourcc == pixelformat)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+static void
+mbus_to_pix(struct vpfe_device *vpfe,
+	    const struct v4l2_mbus_framefmt *mbus,
+	    struct v4l2_pix_format *pix, unsigned int *bpp)
+{
+	struct vpfe_subdev_info *sdinfo = vpfe->current_subdev;
+	unsigned int bus_width = sdinfo->vpfe_param.bus_width;
+	struct vpfe_fmt *fmt;
+
+	fmt = find_format_by_code(mbus->code);
+	if (WARN_ON(fmt == NULL)) {
+		pr_err("Invalid mbus code set\n");
+		*bpp = 1;
+		return;
+	}
+
+	memset(pix, 0, sizeof(*pix));
+	v4l2_fill_pix_format(pix, mbus);
+	pix->pixelformat = fmt->fourcc;
+	*bpp = (bus_width == 10) ?  fmt->l.bpp : fmt->s.bpp;
+
+	/* pitch should be 32 bytes aligned */
+	pix->bytesperline = ALIGN(pix->width * *bpp, 32);
+	pix->sizeimage = pix->bytesperline * pix->height;
+}
+
+static void pix_to_mbus(struct vpfe_device *vpfe,
+			struct v4l2_pix_format *pix_fmt,
+			struct v4l2_mbus_framefmt *mbus_fmt)
+{
+	struct vpfe_fmt *fmt;
+
+	fmt = find_format_by_pix(pix_fmt->pixelformat);
+	if (!fmt) {
+		/* default to first entry */
+		vpfe_dbg(3, vpfe, "Invalid pixel code: %x, default used instead\n",
+			pix_fmt->pixelformat);
+		fmt = &formats[0];
+	}
+
+	memset(mbus_fmt, 0, sizeof(*mbus_fmt));
+	v4l2_fill_mbus_format(mbus_fmt, pix_fmt, fmt->code);
+}
+
+/*  Print Four-character-code (FOURCC) */
+static char *print_fourcc(u32 fmt)
+{
+	static char code[5];
+
+	code[0] = (unsigned char)(fmt & 0xff);
+	code[1] = (unsigned char)((fmt >> 8) & 0xff);
+	code[2] = (unsigned char)((fmt >> 16) & 0xff);
+	code[3] = (unsigned char)((fmt >> 24) & 0xff);
+	code[4] = '\0';
+
+	return code;
+}
+
+static int
+cmp_v4l2_format(const struct v4l2_format *lhs, const struct v4l2_format *rhs)
+{
+	return lhs->type == rhs->type &&
+		lhs->fmt.pix.width == rhs->fmt.pix.width &&
+		lhs->fmt.pix.height == rhs->fmt.pix.height &&
+		lhs->fmt.pix.pixelformat == rhs->fmt.pix.pixelformat &&
+		lhs->fmt.pix.field == rhs->fmt.pix.field &&
+		lhs->fmt.pix.colorspace == rhs->fmt.pix.colorspace &&
+		lhs->fmt.pix.ycbcr_enc == rhs->fmt.pix.ycbcr_enc &&
+		lhs->fmt.pix.quantization == rhs->fmt.pix.quantization;
+}
+
+static inline u32 vpfe_reg_read(struct vpfe_ccdc *ccdc, u32 offset)
+{
+	return ioread32(ccdc->ccdc_cfg.base_addr + offset);
+}
+
+static inline void vpfe_reg_write(struct vpfe_ccdc *ccdc, u32 val, u32 offset)
+{
+	iowrite32(val, ccdc->ccdc_cfg.base_addr + offset);
+}
+
+static inline struct vpfe_device *to_vpfe(struct vpfe_ccdc *ccdc)
+{
+	return container_of(ccdc, struct vpfe_device, ccdc);
+}
+
+static inline struct vpfe_cap_buffer *to_vpfe_buffer(struct vb2_buffer *vb)
+{
+	return container_of(vb, struct vpfe_cap_buffer, vb);
+}
+
+static inline void vpfe_pcr_enable(struct vpfe_ccdc *ccdc, int flag)
+{
+	vpfe_reg_write(ccdc, !!flag, VPFE_PCR);
+}
+
+static void vpfe_config_enable(struct vpfe_ccdc *ccdc, int flag)
+{
+	unsigned int cfg;
+
+	if (!flag) {
+		cfg = vpfe_reg_read(ccdc, VPFE_CONFIG);
+		cfg &= ~(VPFE_CONFIG_EN_ENABLE << VPFE_CONFIG_EN_SHIFT);
+	} else {
+		cfg = VPFE_CONFIG_EN_ENABLE << VPFE_CONFIG_EN_SHIFT;
+	}
+
+	vpfe_reg_write(ccdc, cfg, VPFE_CONFIG);
+}
+
+static void vpfe_ccdc_setwin(struct vpfe_ccdc *ccdc,
+			     struct v4l2_rect *image_win,
+			     enum ccdc_frmfmt frm_fmt,
+			     int bpp)
+{
+	int horz_start, horz_nr_pixels;
+	int vert_start, vert_nr_lines;
+	int val, mid_img;
+
+	/*
+	 * ppc - per pixel count. indicates how many pixels per cell
+	 * output to SDRAM. example, for ycbcr, it is one y and one c, so 2.
+	 * raw capture this is 1
+	 */
+	horz_start = image_win->left * bpp;
+	horz_nr_pixels = (image_win->width * bpp) - 1;
+	vpfe_reg_write(ccdc, (horz_start << VPFE_HORZ_INFO_SPH_SHIFT) |
+				horz_nr_pixels, VPFE_HORZ_INFO);
+
+	vert_start = image_win->top;
+
+	if (frm_fmt == CCDC_FRMFMT_INTERLACED) {
+		vert_nr_lines = (image_win->height >> 1) - 1;
+		vert_start >>= 1;
+		/* Since first line doesn't have any data */
+		vert_start += 1;
+		/* configure VDINT0 */
+		val = (vert_start << VPFE_VDINT_VDINT0_SHIFT);
+	} else {
+		/* Since first line doesn't have any data */
+		vert_start += 1;
+		vert_nr_lines = image_win->height - 1;
+		/*
+		 * configure VDINT0 and VDINT1. VDINT1 will be at half
+		 * of image height
+		 */
+		mid_img = vert_start + (image_win->height / 2);
+		val = (vert_start << VPFE_VDINT_VDINT0_SHIFT) |
+				(mid_img & VPFE_VDINT_VDINT1_MASK);
+	}
+
+	vpfe_reg_write(ccdc, val, VPFE_VDINT);
+
+	vpfe_reg_write(ccdc, (vert_start << VPFE_VERT_START_SLV0_SHIFT) |
+				vert_start, VPFE_VERT_START);
+	vpfe_reg_write(ccdc, vert_nr_lines, VPFE_VERT_LINES);
+}
+
+static void vpfe_reg_dump(struct vpfe_ccdc *ccdc)
+{
+	struct vpfe_device *vpfe = to_vpfe(ccdc);
+
+	vpfe_dbg(3, vpfe, "ALAW: 0x%x\n", vpfe_reg_read(ccdc, VPFE_ALAW));
+	vpfe_dbg(3, vpfe, "CLAMP: 0x%x\n", vpfe_reg_read(ccdc, VPFE_CLAMP));
+	vpfe_dbg(3, vpfe, "DCSUB: 0x%x\n", vpfe_reg_read(ccdc, VPFE_DCSUB));
+	vpfe_dbg(3, vpfe, "BLKCMP: 0x%x\n", vpfe_reg_read(ccdc, VPFE_BLKCMP));
+	vpfe_dbg(3, vpfe, "COLPTN: 0x%x\n", vpfe_reg_read(ccdc, VPFE_COLPTN));
+	vpfe_dbg(3, vpfe, "SDOFST: 0x%x\n", vpfe_reg_read(ccdc, VPFE_SDOFST));
+	vpfe_dbg(3, vpfe, "SYN_MODE: 0x%x\n",
+		 vpfe_reg_read(ccdc, VPFE_SYNMODE));
+	vpfe_dbg(3, vpfe, "HSIZE_OFF: 0x%x\n",
+		 vpfe_reg_read(ccdc, VPFE_HSIZE_OFF));
+	vpfe_dbg(3, vpfe, "HORZ_INFO: 0x%x\n",
+		 vpfe_reg_read(ccdc, VPFE_HORZ_INFO));
+	vpfe_dbg(3, vpfe, "VERT_START: 0x%x\n",
+		 vpfe_reg_read(ccdc, VPFE_VERT_START));
+	vpfe_dbg(3, vpfe, "VERT_LINES: 0x%x\n",
+		 vpfe_reg_read(ccdc, VPFE_VERT_LINES));
+}
+
+static int
+vpfe_ccdc_validate_param(struct vpfe_ccdc *ccdc,
+			 struct vpfe_ccdc_config_params_raw *ccdcparam)
+{
+	struct vpfe_device *vpfe = to_vpfe(ccdc);
+	u8 max_gamma, max_data;
+
+	if (!ccdcparam->alaw.enable)
+		return 0;
+
+	max_gamma = ccdc_gamma_width_max_bit(ccdcparam->alaw.gamma_wd);
+	max_data = ccdc_data_size_max_bit(ccdcparam->data_sz);
+
+	if (ccdcparam->alaw.gamma_wd > VPFE_CCDC_GAMMA_BITS_09_0 ||
+	    ccdcparam->alaw.gamma_wd < VPFE_CCDC_GAMMA_BITS_15_6 ||
+	    max_gamma > max_data) {
+		vpfe_dbg(1, vpfe, "Invalid data line select\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+vpfe_ccdc_update_raw_params(struct vpfe_ccdc *ccdc,
+			    struct vpfe_ccdc_config_params_raw *raw_params)
+{
+	struct vpfe_ccdc_config_params_raw *config_params =
+				&ccdc->ccdc_cfg.bayer.config_params;
+
+	config_params = raw_params;
+}
+
+/*
+ * vpfe_ccdc_restore_defaults()
+ * This function will write defaults to all CCDC registers
+ */
+static void vpfe_ccdc_restore_defaults(struct vpfe_ccdc *ccdc)
+{
+	int i;
+
+	/* Disable CCDC */
+	vpfe_pcr_enable(ccdc, 0);
+
+	/* set all registers to default value */
+	for (i = 4; i <= 0x94; i += 4)
+		vpfe_reg_write(ccdc, 0,  i);
+
+	vpfe_reg_write(ccdc, VPFE_NO_CULLING, VPFE_CULLING);
+	vpfe_reg_write(ccdc, VPFE_CCDC_GAMMA_BITS_11_2, VPFE_ALAW);
+}
+
+static int vpfe_ccdc_close(struct vpfe_ccdc *ccdc, struct device *dev)
+{
+	int dma_cntl, i, pcr;
+
+	/* If the CCDC module is still busy wait for it to be done */
+	for (i = 0; i < 10; i++) {
+		usleep_range(5000, 6000);
+		pcr = vpfe_reg_read(ccdc, VPFE_PCR);
+		if (!pcr)
+			break;
+
+		/* make sure it it is disabled */
+		vpfe_pcr_enable(ccdc, 0);
+	}
+
+	/* Disable CCDC by resetting all register to default POR values */
+	vpfe_ccdc_restore_defaults(ccdc);
+
+	/* if DMA_CNTL overflow bit is set. Clear it
+	 *  It appears to take a while for this to become quiescent ~20ms
+	 */
+	for (i = 0; i < 10; i++) {
+		dma_cntl = vpfe_reg_read(ccdc, VPFE_DMA_CNTL);
+		if (!(dma_cntl & VPFE_DMA_CNTL_OVERFLOW))
+			break;
+
+		/* Clear the overflow bit */
+		vpfe_reg_write(ccdc, dma_cntl, VPFE_DMA_CNTL);
+		usleep_range(5000, 6000);
+	}
+
+	/* Disabled the module at the CONFIG level */
+	vpfe_config_enable(ccdc, 0);
+
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int vpfe_ccdc_set_params(struct vpfe_ccdc *ccdc, void __user *params)
+{
+	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
+	struct vpfe_ccdc_config_params_raw raw_params;
+	int x;
+
+	if (ccdc->ccdc_cfg.if_type != VPFE_RAW_BAYER)
+		return -EINVAL;
+
+	x = copy_from_user(&raw_params, params, sizeof(raw_params));
+	if (x) {
+		vpfe_dbg(1, vpfe,
+			"vpfe_ccdc_set_params: error in copying ccdc params, %d\n",
+			x);
+		return -EFAULT;
+	}
+
+	if (!vpfe_ccdc_validate_param(ccdc, &raw_params)) {
+		vpfe_ccdc_update_raw_params(ccdc, &raw_params);
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
+/*
+ * vpfe_ccdc_config_ycbcr()
+ * This function will configure CCDC for YCbCr video capture
+ */
+static void vpfe_ccdc_config_ycbcr(struct vpfe_ccdc *ccdc)
+{
+	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
+	struct ccdc_params_ycbcr *params = &ccdc->ccdc_cfg.ycbcr;
+	u32 syn_mode;
+
+	vpfe_dbg(3, vpfe, "vpfe_ccdc_config_ycbcr:\n");
+	/*
+	 * first restore the CCDC registers to default values
+	 * This is important since we assume default values to be set in
+	 * a lot of registers that we didn't touch
+	 */
+	vpfe_ccdc_restore_defaults(ccdc);
+
+	/*
+	 * configure pixel format, frame format, configure video frame
+	 * format, enable output to SDRAM, enable internal timing generator
+	 * and 8bit pack mode
+	 */
+	syn_mode = (((params->pix_fmt & VPFE_SYN_MODE_INPMOD_MASK) <<
+		    VPFE_SYN_MODE_INPMOD_SHIFT) |
+		    ((params->frm_fmt & VPFE_SYN_FLDMODE_MASK) <<
+		    VPFE_SYN_FLDMODE_SHIFT) | VPFE_VDHDEN_ENABLE |
+		    VPFE_WEN_ENABLE | VPFE_DATA_PACK_ENABLE);
+
+	/* setup BT.656 sync mode */
+	if (params->bt656_enable) {
+		vpfe_reg_write(ccdc, VPFE_REC656IF_BT656_EN, VPFE_REC656IF);
+
+		/*
+		 * configure the FID, VD, HD pin polarity,
+		 * fld,hd pol positive, vd negative, 8-bit data
+		 */
+		syn_mode |= VPFE_SYN_MODE_VD_POL_NEGATIVE;
+		if (ccdc->ccdc_cfg.if_type == VPFE_BT656_10BIT)
+			syn_mode |= VPFE_SYN_MODE_10BITS;
+		else
+			syn_mode |= VPFE_SYN_MODE_8BITS;
+	} else {
+		/* y/c external sync mode */
+		syn_mode |= (((params->fid_pol & VPFE_FID_POL_MASK) <<
+			     VPFE_FID_POL_SHIFT) |
+			     ((params->hd_pol & VPFE_HD_POL_MASK) <<
+			     VPFE_HD_POL_SHIFT) |
+			     ((params->vd_pol & VPFE_VD_POL_MASK) <<
+			     VPFE_VD_POL_SHIFT));
+	}
+	vpfe_reg_write(ccdc, syn_mode, VPFE_SYNMODE);
+
+	/* configure video window */
+	vpfe_ccdc_setwin(ccdc, &params->win,
+			 params->frm_fmt, params->bytesperpixel);
+
+	/*
+	 * configure the order of y cb cr in SDRAM, and disable latch
+	 * internal register on vsync
+	 */
+	if (ccdc->ccdc_cfg.if_type == VPFE_BT656_10BIT)
+		vpfe_reg_write(ccdc,
+			       (params->pix_order << VPFE_CCDCFG_Y8POS_SHIFT) |
+			       VPFE_LATCH_ON_VSYNC_DISABLE |
+			       VPFE_CCDCFG_BW656_10BIT, VPFE_CCDCFG);
+	else
+		vpfe_reg_write(ccdc,
+			       (params->pix_order << VPFE_CCDCFG_Y8POS_SHIFT) |
+			       VPFE_LATCH_ON_VSYNC_DISABLE, VPFE_CCDCFG);
+
+	/*
+	 * configure the horizontal line offset. This should be a
+	 * on 32 byte boundary. So clear LSB 5 bits
+	 */
+	vpfe_reg_write(ccdc, params->bytesperline, VPFE_HSIZE_OFF);
+
+	/* configure the memory line offset */
+	if (params->buf_type == CCDC_BUFTYPE_FLD_INTERLEAVED)
+		/* two fields are interleaved in memory */
+		vpfe_reg_write(ccdc, VPFE_SDOFST_FIELD_INTERLEAVED,
+			       VPFE_SDOFST);
+}
+
+static void
+vpfe_ccdc_config_black_clamp(struct vpfe_ccdc *ccdc,
+			     struct vpfe_ccdc_black_clamp *bclamp)
+{
+	u32 val;
+
+	if (!bclamp->enable) {
+		/* configure DCSub */
+		val = (bclamp->dc_sub) & VPFE_BLK_DC_SUB_MASK;
+		vpfe_reg_write(ccdc, val, VPFE_DCSUB);
+		vpfe_reg_write(ccdc, VPFE_CLAMP_DEFAULT_VAL, VPFE_CLAMP);
+		return;
+	}
+	/*
+	 * Configure gain,  Start pixel, No of line to be avg,
+	 * No of pixel/line to be avg, & Enable the Black clamping
+	 */
+	val = ((bclamp->sgain & VPFE_BLK_SGAIN_MASK) |
+	       ((bclamp->start_pixel & VPFE_BLK_ST_PXL_MASK) <<
+		VPFE_BLK_ST_PXL_SHIFT) |
+	       ((bclamp->sample_ln & VPFE_BLK_SAMPLE_LINE_MASK) <<
+		VPFE_BLK_SAMPLE_LINE_SHIFT) |
+	       ((bclamp->sample_pixel & VPFE_BLK_SAMPLE_LN_MASK) <<
+		VPFE_BLK_SAMPLE_LN_SHIFT) | VPFE_BLK_CLAMP_ENABLE);
+	vpfe_reg_write(ccdc, val, VPFE_CLAMP);
+	/* If Black clamping is enable then make dcsub 0 */
+	vpfe_reg_write(ccdc, VPFE_DCSUB_DEFAULT_VAL, VPFE_DCSUB);
+}
+
+static void
+vpfe_ccdc_config_black_compense(struct vpfe_ccdc *ccdc,
+				struct vpfe_ccdc_black_compensation *bcomp)
+{
+	u32 val;
+
+	val = ((bcomp->b & VPFE_BLK_COMP_MASK) |
+	      ((bcomp->gb & VPFE_BLK_COMP_MASK) <<
+	       VPFE_BLK_COMP_GB_COMP_SHIFT) |
+	      ((bcomp->gr & VPFE_BLK_COMP_MASK) <<
+	       VPFE_BLK_COMP_GR_COMP_SHIFT) |
+	      ((bcomp->r & VPFE_BLK_COMP_MASK) <<
+	       VPFE_BLK_COMP_R_COMP_SHIFT));
+	vpfe_reg_write(ccdc, val, VPFE_BLKCMP);
+}
+
+/*
+ * vpfe_ccdc_config_raw()
+ * This function will configure CCDC for Raw capture mode
+ */
+static void vpfe_ccdc_config_raw(struct vpfe_ccdc *ccdc)
+{
+	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
+	struct vpfe_ccdc_config_params_raw *config_params =
+				&ccdc->ccdc_cfg.bayer.config_params;
+	struct ccdc_params_raw *params = &ccdc->ccdc_cfg.bayer;
+	unsigned int syn_mode;
+	unsigned int val;
+
+	vpfe_dbg(3, vpfe, "vpfe_ccdc_config_raw:\n");
+
+	/* Reset CCDC */
+	vpfe_ccdc_restore_defaults(ccdc);
+
+	/* Disable latching function registers on VSYNC  */
+	vpfe_reg_write(ccdc, VPFE_LATCH_ON_VSYNC_DISABLE, VPFE_CCDCFG);
+
+	/*
+	 * Configure the vertical sync polarity(SYN_MODE.VDPOL),
+	 * horizontal sync polarity (SYN_MODE.HDPOL), frame id polarity
+	 * (SYN_MODE.FLDPOL), frame format(progressive or interlace),
+	 * data size(SYNMODE.DATSIZ), &pixel format (Input mode), output
+	 * SDRAM, enable internal timing generator
+	 */
+	syn_mode = (((params->vd_pol & VPFE_VD_POL_MASK) << VPFE_VD_POL_SHIFT) |
+		   ((params->hd_pol & VPFE_HD_POL_MASK) << VPFE_HD_POL_SHIFT) |
+		   ((params->fid_pol & VPFE_FID_POL_MASK) <<
+		   VPFE_FID_POL_SHIFT) | ((params->frm_fmt &
+		   VPFE_FRM_FMT_MASK) << VPFE_FRM_FMT_SHIFT) |
+		   ((config_params->data_sz & VPFE_DATA_SZ_MASK) <<
+		   VPFE_DATA_SZ_SHIFT) | ((params->pix_fmt &
+		   VPFE_PIX_FMT_MASK) << VPFE_PIX_FMT_SHIFT) |
+		   VPFE_WEN_ENABLE | VPFE_VDHDEN_ENABLE);
+
+	/* Enable and configure aLaw register if needed */
+	if (config_params->alaw.enable) {
+		val = ((config_params->alaw.gamma_wd &
+		      VPFE_ALAW_GAMMA_WD_MASK) | VPFE_ALAW_ENABLE);
+		vpfe_reg_write(ccdc, val, VPFE_ALAW);
+		vpfe_dbg(3, vpfe, "\nWriting 0x%x to ALAW...\n", val);
+	}
+
+	/* Configure video window */
+	vpfe_ccdc_setwin(ccdc, &params->win, params->frm_fmt,
+			 params->bytesperpixel);
+
+	/* Configure Black Clamp */
+	vpfe_ccdc_config_black_clamp(ccdc, &config_params->blk_clamp);
+
+	/* Configure Black level compensation */
+	vpfe_ccdc_config_black_compense(ccdc, &config_params->blk_comp);
+
+	/* If data size is 8 bit then pack the data */
+	if ((config_params->data_sz == VPFE_CCDC_DATA_8BITS) ||
+	    config_params->alaw.enable)
+		syn_mode |= VPFE_DATA_PACK_ENABLE;
+
+	/*
+	 * Configure Horizontal offset register. If pack 8 is enabled then
+	 * 1 pixel will take 1 byte
+	 */
+	vpfe_reg_write(ccdc, params->bytesperline, VPFE_HSIZE_OFF);
+
+	vpfe_dbg(3, vpfe, "Writing %d (%x) to HSIZE_OFF\n",
+		params->bytesperline, params->bytesperline);
+
+	/* Set value for SDOFST */
+	if (params->frm_fmt == CCDC_FRMFMT_INTERLACED) {
+		if (params->image_invert_enable) {
+			/* For interlace inverse mode */
+			vpfe_reg_write(ccdc, VPFE_INTERLACED_IMAGE_INVERT,
+				   VPFE_SDOFST);
+		} else {
+			/* For interlace non inverse mode */
+			vpfe_reg_write(ccdc, VPFE_INTERLACED_NO_IMAGE_INVERT,
+				   VPFE_SDOFST);
+		}
+	} else if (params->frm_fmt == CCDC_FRMFMT_PROGRESSIVE) {
+		vpfe_reg_write(ccdc, VPFE_PROGRESSIVE_NO_IMAGE_INVERT,
+			   VPFE_SDOFST);
+	}
+
+	vpfe_reg_write(ccdc, syn_mode, VPFE_SYNMODE);
+
+	vpfe_reg_dump(ccdc);
+}
+
+static inline int
+vpfe_ccdc_set_buftype(struct vpfe_ccdc *ccdc,
+		      enum ccdc_buftype buf_type)
+{
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER)
+		ccdc->ccdc_cfg.bayer.buf_type = buf_type;
+	else
+		ccdc->ccdc_cfg.ycbcr.buf_type = buf_type;
+
+	return 0;
+}
+
+static inline enum ccdc_buftype vpfe_ccdc_get_buftype(struct vpfe_ccdc *ccdc)
+{
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER)
+		return ccdc->ccdc_cfg.bayer.buf_type;
+
+	return ccdc->ccdc_cfg.ycbcr.buf_type;
+}
+
+static int vpfe_ccdc_set_pixel_format(struct vpfe_ccdc *ccdc, u32 pixfmt)
+{
+	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
+
+	vpfe_dbg(1, vpfe, "vpfe_ccdc_set_pixel_format: if_type: %d, pixfmt:%s\n",
+		 ccdc->ccdc_cfg.if_type, print_fourcc(pixfmt));
+
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER) {
+		ccdc->ccdc_cfg.bayer.pix_fmt = CCDC_PIXFMT_RAW;
+		/*
+		 * Need to clear it in case it was left on
+		 * after the last capture.
+		 */
+		ccdc->ccdc_cfg.bayer.config_params.alaw.enable = 0;
+
+		switch (pixfmt) {
+		case V4L2_PIX_FMT_SBGGR8:
+			ccdc->ccdc_cfg.bayer.config_params.alaw.enable = 1;
+			break;
+
+		case V4L2_PIX_FMT_YUYV:
+		case V4L2_PIX_FMT_UYVY:
+		case V4L2_PIX_FMT_YUV420:
+		case V4L2_PIX_FMT_NV12:
+		case V4L2_PIX_FMT_RGB565X:
+			break;
+
+		case V4L2_PIX_FMT_SBGGR16:
+		default:
+			return -EINVAL;
+		}
+	} else {
+		switch (pixfmt) {
+		case V4L2_PIX_FMT_YUYV:
+			ccdc->ccdc_cfg.ycbcr.pix_order = CCDC_PIXORDER_YCBYCR;
+			break;
+
+		case V4L2_PIX_FMT_UYVY:
+			ccdc->ccdc_cfg.ycbcr.pix_order = CCDC_PIXORDER_CBYCRY;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static u32 vpfe_ccdc_get_pixel_format(struct vpfe_ccdc *ccdc)
+{
+	u32 pixfmt;
+
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER) {
+		pixfmt = V4L2_PIX_FMT_YUYV;
+	} else {
+		if (ccdc->ccdc_cfg.ycbcr.pix_order == CCDC_PIXORDER_YCBYCR)
+			pixfmt = V4L2_PIX_FMT_YUYV;
+		else
+			pixfmt = V4L2_PIX_FMT_UYVY;
+	}
+
+	return pixfmt;
+}
+
+static int
+vpfe_ccdc_set_image_window(struct vpfe_ccdc *ccdc,
+			   struct v4l2_rect *win, unsigned int bpp)
+{
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER) {
+		ccdc->ccdc_cfg.bayer.win = *win;
+		ccdc->ccdc_cfg.bayer.bytesperpixel = bpp;
+		ccdc->ccdc_cfg.bayer.bytesperline = ALIGN(win->width * bpp, 32);
+	} else {
+		ccdc->ccdc_cfg.ycbcr.win = *win;
+		ccdc->ccdc_cfg.ycbcr.bytesperpixel = bpp;
+		ccdc->ccdc_cfg.ycbcr.bytesperline = ALIGN(win->width * bpp, 32);
+	}
+
+	return 0;
+}
+
+static inline void
+vpfe_ccdc_get_image_window(struct vpfe_ccdc *ccdc,
+			   struct v4l2_rect *win)
+{
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER)
+		*win = ccdc->ccdc_cfg.bayer.win;
+	else
+		*win = ccdc->ccdc_cfg.ycbcr.win;
+}
+
+static inline unsigned int vpfe_ccdc_get_line_length(struct vpfe_ccdc *ccdc)
+{
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER)
+		return ccdc->ccdc_cfg.bayer.bytesperline;
+
+	return ccdc->ccdc_cfg.ycbcr.bytesperline;
+}
+
+static inline int
+vpfe_ccdc_set_frame_format(struct vpfe_ccdc *ccdc,
+			   enum ccdc_frmfmt frm_fmt)
+{
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER)
+		ccdc->ccdc_cfg.bayer.frm_fmt = frm_fmt;
+	else
+		ccdc->ccdc_cfg.ycbcr.frm_fmt = frm_fmt;
+
+	return 0;
+}
+
+static inline enum ccdc_frmfmt
+vpfe_ccdc_get_frame_format(struct vpfe_ccdc *ccdc)
+{
+	if (ccdc->ccdc_cfg.if_type == VPFE_RAW_BAYER)
+		return ccdc->ccdc_cfg.bayer.frm_fmt;
+
+	return ccdc->ccdc_cfg.ycbcr.frm_fmt;
+}
+
+static inline int vpfe_ccdc_getfid(struct vpfe_ccdc *ccdc)
+{
+	return (vpfe_reg_read(ccdc, VPFE_SYNMODE) >> 15) & 1;
+}
+
+static inline void vpfe_set_sdr_addr(struct vpfe_ccdc *ccdc, unsigned long addr)
+{
+	vpfe_reg_write(ccdc, addr & 0xffffffe0, VPFE_SDR_ADDR);
+}
+
+static int vpfe_ccdc_set_hw_if_params(struct vpfe_ccdc *ccdc,
+				      struct vpfe_hw_if_param *params)
+{
+	struct vpfe_device *vpfe = container_of(ccdc, struct vpfe_device, ccdc);
+
+	ccdc->ccdc_cfg.if_type = params->if_type;
+
+	switch (params->if_type) {
+	case VPFE_BT656:
+	case VPFE_YCBCR_SYNC_16:
+	case VPFE_YCBCR_SYNC_8:
+	case VPFE_BT656_10BIT:
+		ccdc->ccdc_cfg.ycbcr.vd_pol = params->vdpol;
+		ccdc->ccdc_cfg.ycbcr.hd_pol = params->hdpol;
+		break;
+
+	case VPFE_RAW_BAYER:
+		ccdc->ccdc_cfg.bayer.vd_pol = params->vdpol;
+		ccdc->ccdc_cfg.bayer.hd_pol = params->hdpol;
+		if (params->bus_width == 10)
+			ccdc->ccdc_cfg.bayer.config_params.data_sz =
+				VPFE_CCDC_DATA_10BITS;
+		else
+			ccdc->ccdc_cfg.bayer.config_params.data_sz =
+				VPFE_CCDC_DATA_8BITS;
+		vpfe_dbg(1, vpfe, "params.bus_width: %d\n",
+			params->bus_width);
+		vpfe_dbg(1, vpfe, "config_params.data_sz: %d\n",
+			ccdc->ccdc_cfg.bayer.config_params.data_sz);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void vpfe_clear_intr(struct vpfe_ccdc *ccdc, int vdint)
+{
+	unsigned int vpfe_int_status;
+
+	vpfe_int_status = vpfe_reg_read(ccdc, VPFE_IRQ_STS);
+
+	switch (vdint) {
+	/* VD0 interrupt */
+	case VPFE_VDINT0:
+		vpfe_int_status &= ~VPFE_VDINT0;
+		vpfe_int_status |= VPFE_VDINT0;
+		break;
+
+	/* VD1 interrupt */
+	case VPFE_VDINT1:
+		vpfe_int_status &= ~VPFE_VDINT1;
+		vpfe_int_status |= VPFE_VDINT1;
+		break;
+
+	/* VD2 interrupt */
+	case VPFE_VDINT2:
+		vpfe_int_status &= ~VPFE_VDINT2;
+		vpfe_int_status |= VPFE_VDINT2;
+		break;
+
+	/* Clear all interrupts */
+	default:
+		vpfe_int_status &= ~(VPFE_VDINT0 |
+				VPFE_VDINT1 |
+				VPFE_VDINT2);
+		vpfe_int_status |= (VPFE_VDINT0 |
+				VPFE_VDINT1 |
+				VPFE_VDINT2);
+		break;
+	}
+	/* Clear specific VDINT from the status register */
+	vpfe_reg_write(ccdc, vpfe_int_status, VPFE_IRQ_STS);
+
+	vpfe_int_status = vpfe_reg_read(ccdc, VPFE_IRQ_STS);
+
+	/* Acknowledge that we are done with all interrupts */
+	vpfe_reg_write(ccdc, 1, VPFE_IRQ_EOI);
+}
+
+static void vpfe_ccdc_config_defaults(struct vpfe_ccdc *ccdc)
+{
+	ccdc->ccdc_cfg.if_type = VPFE_RAW_BAYER;
+
+	ccdc->ccdc_cfg.ycbcr.pix_fmt = CCDC_PIXFMT_YCBCR_8BIT;
+	ccdc->ccdc_cfg.ycbcr.frm_fmt = CCDC_FRMFMT_INTERLACED;
+	ccdc->ccdc_cfg.ycbcr.fid_pol = VPFE_PINPOL_POSITIVE;
+	ccdc->ccdc_cfg.ycbcr.vd_pol = VPFE_PINPOL_POSITIVE;
+	ccdc->ccdc_cfg.ycbcr.hd_pol = VPFE_PINPOL_POSITIVE;
+	ccdc->ccdc_cfg.ycbcr.pix_order = CCDC_PIXORDER_CBYCRY;
+	ccdc->ccdc_cfg.ycbcr.buf_type = CCDC_BUFTYPE_FLD_INTERLEAVED;
+
+	ccdc->ccdc_cfg.ycbcr.win.left = 0;
+	ccdc->ccdc_cfg.ycbcr.win.top = 0;
+	ccdc->ccdc_cfg.ycbcr.win.width = 720;
+	ccdc->ccdc_cfg.ycbcr.win.height = 576;
+	ccdc->ccdc_cfg.ycbcr.bt656_enable = 1;
+
+	ccdc->ccdc_cfg.bayer.pix_fmt = CCDC_PIXFMT_RAW;
+	ccdc->ccdc_cfg.bayer.frm_fmt = CCDC_FRMFMT_PROGRESSIVE;
+	ccdc->ccdc_cfg.bayer.fid_pol = VPFE_PINPOL_POSITIVE;
+	ccdc->ccdc_cfg.bayer.vd_pol = VPFE_PINPOL_POSITIVE;
+	ccdc->ccdc_cfg.bayer.hd_pol = VPFE_PINPOL_POSITIVE;
+
+	ccdc->ccdc_cfg.bayer.win.left = 0;
+	ccdc->ccdc_cfg.bayer.win.top = 0;
+	ccdc->ccdc_cfg.bayer.win.width = 800;
+	ccdc->ccdc_cfg.bayer.win.height = 600;
+	ccdc->ccdc_cfg.bayer.config_params.data_sz = VPFE_CCDC_DATA_8BITS;
+	ccdc->ccdc_cfg.bayer.config_params.alaw.gamma_wd =
+						VPFE_CCDC_GAMMA_BITS_09_0;
+}
+
+/*
+ * vpfe_get_ccdc_image_format - Get image parameters based on CCDC settings
+ */
+static int vpfe_get_ccdc_image_format(struct vpfe_device *vpfe,
+				      struct v4l2_format *f)
+{
+	struct v4l2_rect image_win;
+	enum ccdc_buftype buf_type;
+	enum ccdc_frmfmt frm_fmt;
+
+	memset(f, 0, sizeof(*f));
+	f->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	vpfe_ccdc_get_image_window(&vpfe->ccdc, &image_win);
+	f->fmt.pix.width = image_win.width;
+	f->fmt.pix.height = image_win.height;
+	f->fmt.pix.bytesperline = vpfe_ccdc_get_line_length(&vpfe->ccdc);
+	f->fmt.pix.sizeimage = f->fmt.pix.bytesperline *
+				f->fmt.pix.height;
+	buf_type = vpfe_ccdc_get_buftype(&vpfe->ccdc);
+	f->fmt.pix.pixelformat = vpfe_ccdc_get_pixel_format(&vpfe->ccdc);
+	frm_fmt = vpfe_ccdc_get_frame_format(&vpfe->ccdc);
+
+	if (frm_fmt == CCDC_FRMFMT_PROGRESSIVE) {
+		f->fmt.pix.field = V4L2_FIELD_NONE;
+	} else if (frm_fmt == CCDC_FRMFMT_INTERLACED) {
+		if (buf_type == CCDC_BUFTYPE_FLD_INTERLEAVED) {
+			f->fmt.pix.field = V4L2_FIELD_INTERLACED;
+		 } else if (buf_type == CCDC_BUFTYPE_FLD_SEPARATED) {
+			f->fmt.pix.field = V4L2_FIELD_SEQ_TB;
+		} else {
+			vpfe_err(vpfe, "Invalid buf_type\n");
+			return -EINVAL;
+		}
+	} else {
+		vpfe_err(vpfe, "Invalid frm_fmt\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int vpfe_config_ccdc_image_format(struct vpfe_device *vpfe)
+{
+	enum ccdc_frmfmt frm_fmt = CCDC_FRMFMT_INTERLACED;
+	int ret;
+
+	vpfe_dbg(2, vpfe, "vpfe_config_ccdc_image_format\n");
+
+	vpfe_dbg(1, vpfe, "pixelformat: %s\n",
+		print_fourcc(vpfe->fmt.fmt.pix.pixelformat));
+
+	if (vpfe_ccdc_set_pixel_format(&vpfe->ccdc,
+			vpfe->fmt.fmt.pix.pixelformat) < 0) {
+		vpfe_err(vpfe, "couldn't set pix format in ccdc\n");
+		return -EINVAL;
+	}
+
+	/* configure the image window */
+	vpfe_ccdc_set_image_window(&vpfe->ccdc, &vpfe->crop, vpfe->bpp);
+
+	switch (vpfe->fmt.fmt.pix.field) {
+	case V4L2_FIELD_INTERLACED:
+		/* do nothing, since it is default */
+		ret = vpfe_ccdc_set_buftype(
+				&vpfe->ccdc,
+				CCDC_BUFTYPE_FLD_INTERLEAVED);
+		break;
+
+	case V4L2_FIELD_NONE:
+		frm_fmt = CCDC_FRMFMT_PROGRESSIVE;
+		/* buffer type only applicable for interlaced scan */
+		break;
+
+	case V4L2_FIELD_SEQ_TB:
+		ret = vpfe_ccdc_set_buftype(
+				&vpfe->ccdc,
+				CCDC_BUFTYPE_FLD_SEPARATED);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	return vpfe_ccdc_set_frame_format(&vpfe->ccdc, frm_fmt);
+}
+
+/*
+ * vpfe_config_image_format()
+ * For a given standard, this functions sets up the default
+ * pix format & crop values in the vpfe device and ccdc.  It first
+ * starts with defaults based values from the standard table.
+ * It then checks if sub device support g_mbus_fmt and then override the
+ * values based on that.Sets crop values to match with scan resolution
+ * starting at 0,0. It calls vpfe_config_ccdc_image_format() set the
+ * values in ccdc
+ */
+static int vpfe_config_image_format(struct vpfe_device *vpfe,
+				    v4l2_std_id std_id)
+{
+	struct v4l2_pix_format *pix = &vpfe->fmt.fmt.pix;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(vpfe_standards); i++) {
+		if (vpfe_standards[i].std_id & std_id) {
+			vpfe->std_info.active_pixels =
+					vpfe_standards[i].width;
+			vpfe->std_info.active_lines =
+					vpfe_standards[i].height;
+			vpfe->std_info.frame_format =
+					vpfe_standards[i].frame_format;
+			vpfe->std_index = i;
+
+			break;
+		}
+	}
+
+	if (i ==  ARRAY_SIZE(vpfe_standards)) {
+		vpfe_err(vpfe, "standard not supported\n");
+		return -EINVAL;
+	}
+
+	vpfe->crop.top = vpfe->crop.left = 0;
+	vpfe->crop.width = vpfe->std_info.active_pixels;
+	vpfe->crop.height = vpfe->std_info.active_lines;
+	pix->width = vpfe->crop.width;
+	pix->height = vpfe->crop.height;
+	pix->pixelformat = V4L2_PIX_FMT_YUYV;
+
+	/* first field and frame format based on standard frame format */
+	if (vpfe->std_info.frame_format)
+		pix->field = V4L2_FIELD_INTERLACED;
+	else
+		pix->field = V4L2_FIELD_NONE;
+
+	ret = __vpfe_get_format(vpfe, &vpfe->fmt, &vpfe->bpp);
+	if (ret)
+		return ret;
+
+	/* Update the crop window based on found values */
+	vpfe->crop.width = pix->width;
+	vpfe->crop.height = pix->height;
+
+	return vpfe_config_ccdc_image_format(vpfe);
+}
+
+static int vpfe_initialize_device(struct vpfe_device *vpfe)
+{
+	struct vpfe_subdev_info *sdinfo;
+	int ret;
+
+	sdinfo = &vpfe->cfg->sub_devs[0];
+	sdinfo->sd = vpfe->sd[0];
+	vpfe->current_input = 0;
+	vpfe->std_index = 0;
+	/* Configure the default format information */
+	ret = vpfe_config_image_format(vpfe,
+				       vpfe_standards[vpfe->std_index].std_id);
+	if (ret)
+		return ret;
+
+	pm_runtime_get_sync(vpfe->pdev);
+
+	vpfe_config_enable(&vpfe->ccdc, 1);
+
+	vpfe_ccdc_restore_defaults(&vpfe->ccdc);
+
+	/* Clear all VPFE interrupts */
+	vpfe_clear_intr(&vpfe->ccdc, -1);
+
+	return ret;
+}
+
+/*
+ * vpfe_release : This function is based on the vb2_fop_release
+ * helper function.
+ * It has been augmented to handle module power management,
+ * by disabling/enabling h/w module fcntl clock when necessary.
+ */
+static int vpfe_release(struct file *file)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	int ret;
+
+	mutex_lock(&vpfe->lock);
+
+	if (v4l2_fh_is_singular_file(file))
+		vpfe_ccdc_close(&vpfe->ccdc, vpfe->pdev);
+	ret = _vb2_fop_release(file, NULL);
+
+	mutex_unlock(&vpfe->lock);
+
+	return ret;
+}
+
+/*
+ * vpfe_open : This function is based on the v4l2_fh_open helper function.
+ * It has been augmented to handle module power management,
+ * by disabling/enabling h/w module fcntl clock when necessary.
+ */
+static int vpfe_open(struct file *file)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	int ret;
+
+	mutex_lock(&vpfe->lock);
+
+	ret = v4l2_fh_open(file);
+	if (ret) {
+		vpfe_err(vpfe, "v4l2_fh_open failed\n");
+		goto unlock;
+	}
+
+	if (!v4l2_fh_is_singular_file(file))
+		goto unlock;
+
+	if (vpfe_initialize_device(vpfe)) {
+		v4l2_fh_release(file);
+		ret = -ENODEV;
+	}
+
+unlock:
+	mutex_unlock(&vpfe->lock);
+	return ret;
+}
+
+/**
+ * vpfe_schedule_next_buffer: set next buffer address for capture
+ * @vpfe : ptr to vpfe device
+ *
+ * This function will get next buffer from the dma queue and
+ * set the buffer address in the vpfe register for capture.
+ * the buffer is marked active
+ *
+ * Assumes caller is holding vpfe->dma_queue_lock already
+ */
+static inline void vpfe_schedule_next_buffer(struct vpfe_device *vpfe)
+{
+	vpfe->next_frm = list_entry(vpfe->dma_queue.next,
+				    struct vpfe_cap_buffer, list);
+	list_del(&vpfe->next_frm->list);
+
+	vpfe_set_sdr_addr(&vpfe->ccdc,
+		       vb2_dma_contig_plane_dma_addr(&vpfe->next_frm->vb, 0));
+}
+
+static inline void vpfe_schedule_bottom_field(struct vpfe_device *vpfe)
+{
+	unsigned long addr;
+
+	addr = vb2_dma_contig_plane_dma_addr(&vpfe->next_frm->vb, 0) +
+					vpfe->field_off;
+
+	vpfe_set_sdr_addr(&vpfe->ccdc, addr);
+}
+
+/*
+ * vpfe_process_buffer_complete: process a completed buffer
+ * @vpfe : ptr to vpfe device
+ *
+ * This function time stamp the buffer and mark it as DONE. It also
+ * wake up any process waiting on the QUEUE and set the next buffer
+ * as current
+ */
+static inline void vpfe_process_buffer_complete(struct vpfe_device *vpfe)
+{
+	v4l2_get_timestamp(&vpfe->cur_frm->vb.v4l2_buf.timestamp);
+	vpfe->cur_frm->vb.v4l2_buf.field = vpfe->fmt.fmt.pix.field;
+	vpfe->cur_frm->vb.v4l2_buf.sequence = vpfe->sequence++;
+	vb2_buffer_done(&vpfe->cur_frm->vb, VB2_BUF_STATE_DONE);
+	vpfe->cur_frm = vpfe->next_frm;
+}
+
+/*
+ * vpfe_isr : ISR handler for vpfe capture (VINT0)
+ * @irq: irq number
+ * @dev_id: dev_id ptr
+ *
+ * It changes status of the captured buffer, takes next buffer from the queue
+ * and sets its address in VPFE registers
+ */
+static irqreturn_t vpfe_isr(int irq, void *dev)
+{
+	struct vpfe_device *vpfe = (struct vpfe_device *)dev;
+	enum v4l2_field field;
+	int intr_status;
+	int fid;
+
+	intr_status = vpfe_reg_read(&vpfe->ccdc, VPFE_IRQ_STS);
+
+	if (intr_status & VPFE_VDINT0) {
+		field = vpfe->fmt.fmt.pix.field;
+
+		if (field == V4L2_FIELD_NONE) {
+			/* handle progressive frame capture */
+			if (vpfe->cur_frm != vpfe->next_frm)
+				vpfe_process_buffer_complete(vpfe);
+			goto next_intr;
+		}
+
+		/* interlaced or TB capture check which field
+		   we are in hardware */
+		fid = vpfe_ccdc_getfid(&vpfe->ccdc);
+
+		/* switch the software maintained field id */
+		vpfe->field ^= 1;
+		if (fid == vpfe->field) {
+			/* we are in-sync here,continue */
+			if (fid == 0) {
+				/*
+				 * One frame is just being captured. If the
+				 * next frame is available, release the
+				 * current frame and move on
+				 */
+				if (vpfe->cur_frm != vpfe->next_frm)
+					vpfe_process_buffer_complete(vpfe);
+				/*
+				 * based on whether the two fields are stored
+				 * interleave or separately in memory,
+				 * reconfigure the CCDC memory address
+				 */
+				if (field == V4L2_FIELD_SEQ_TB)
+					vpfe_schedule_bottom_field(vpfe);
+
+				goto next_intr;
+			}
+			/*
+			 * if one field is just being captured configure
+			 * the next frame get the next frame from the empty
+			 * queue if no frame is available hold on to the
+			 * current buffer
+			 */
+			spin_lock(&vpfe->dma_queue_lock);
+			if (!list_empty(&vpfe->dma_queue) &&
+			    vpfe->cur_frm == vpfe->next_frm)
+				vpfe_schedule_next_buffer(vpfe);
+			spin_unlock(&vpfe->dma_queue_lock);
+		} else if (fid == 0) {
+			/*
+			 * out of sync. Recover from any hardware out-of-sync.
+			 * May loose one frame
+			 */
+			vpfe->field = fid;
+		}
+	}
+
+next_intr:
+	if (intr_status & VPFE_VDINT1) {
+		spin_lock(&vpfe->dma_queue_lock);
+		if (vpfe->fmt.fmt.pix.field == V4L2_FIELD_NONE &&
+		    !list_empty(&vpfe->dma_queue) &&
+		    vpfe->cur_frm == vpfe->next_frm)
+			vpfe_schedule_next_buffer(vpfe);
+		spin_unlock(&vpfe->dma_queue_lock);
+	}
+
+	vpfe_clear_intr(&vpfe->ccdc, intr_status);
+
+	return IRQ_HANDLED;
+}
+
+static inline void vpfe_detach_irq(struct vpfe_device *vpfe)
+{
+	unsigned int intr = VPFE_VDINT0;
+	enum ccdc_frmfmt frame_format;
+
+	frame_format = vpfe_ccdc_get_frame_format(&vpfe->ccdc);
+	if (frame_format == CCDC_FRMFMT_PROGRESSIVE)
+		intr |= VPFE_VDINT1;
+
+	vpfe_reg_write(&vpfe->ccdc, intr, VPFE_IRQ_EN_CLR);
+}
+
+static inline void vpfe_attach_irq(struct vpfe_device *vpfe)
+{
+	unsigned int intr = VPFE_VDINT0;
+	enum ccdc_frmfmt frame_format;
+
+	frame_format = vpfe_ccdc_get_frame_format(&vpfe->ccdc);
+	if (frame_format == CCDC_FRMFMT_PROGRESSIVE)
+		intr |= VPFE_VDINT1;
+
+	vpfe_reg_write(&vpfe->ccdc, intr, VPFE_IRQ_EN_SET);
+}
+
+static int vpfe_querycap(struct file *file, void  *priv,
+			 struct v4l2_capability *cap)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+
+	vpfe_dbg(2, vpfe, "vpfe_querycap\n");
+
+	strlcpy(cap->driver, VPFE_MODULE_NAME, sizeof(cap->driver));
+	strlcpy(cap->card, "TI AM437x VPFE", sizeof(cap->card));
+	snprintf(cap->bus_info, sizeof(cap->bus_info),
+			"platform:%s", vpfe->v4l2_dev.name);
+	cap->device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING |
+			    V4L2_CAP_READWRITE;
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+
+	return 0;
+}
+
+/* get the format set at output pad of the adjacent subdev */
+static int __vpfe_get_format(struct vpfe_device *vpfe,
+			     struct v4l2_format *format, unsigned int *bpp)
+{
+	struct v4l2_mbus_framefmt mbus_fmt;
+	struct vpfe_subdev_info *sdinfo;
+	struct v4l2_subdev_format fmt;
+	int ret;
+
+	sdinfo = vpfe->current_subdev;
+	if (!sdinfo->sd)
+		return -EINVAL;
+
+	fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	fmt.pad = 0;
+
+	ret = v4l2_subdev_call(sdinfo->sd, pad, get_fmt, NULL, &fmt);
+	if (ret && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		return ret;
+
+	if (!ret) {
+		v4l2_fill_pix_format(&format->fmt.pix, &fmt.format);
+		mbus_to_pix(vpfe, &fmt.format, &format->fmt.pix, bpp);
+	} else {
+		ret = v4l2_device_call_until_err(&vpfe->v4l2_dev,
+						 sdinfo->grp_id,
+						 video, g_mbus_fmt,
+						 &mbus_fmt);
+		if (ret && ret != -ENOIOCTLCMD && ret != -ENODEV)
+			return ret;
+		v4l2_fill_pix_format(&format->fmt.pix, &mbus_fmt);
+		mbus_to_pix(vpfe, &mbus_fmt, &format->fmt.pix, bpp);
+	}
+
+	format->type = vpfe->fmt.type;
+
+	vpfe_dbg(1, vpfe,
+		 "%s size %dx%d (%s) bytesperline = %d, size = %d, bpp = %d\n",
+		 __func__, format->fmt.pix.width, format->fmt.pix.height,
+		 print_fourcc(format->fmt.pix.pixelformat),
+		 format->fmt.pix.bytesperline, format->fmt.pix.sizeimage, *bpp);
+
+	return 0;
+}
+
+/* set the format at output pad of the adjacent subdev */
+static int __vpfe_set_format(struct vpfe_device *vpfe,
+			     struct v4l2_format *format, unsigned int *bpp)
+{
+	struct v4l2_mbus_framefmt mbus_fmt;
+	struct vpfe_subdev_info *sdinfo;
+	struct v4l2_subdev_format fmt;
+	int ret;
+
+	vpfe_dbg(2, vpfe, "__vpfe_set_format\n");
+
+	sdinfo = vpfe->current_subdev;
+	if (!sdinfo->sd)
+		return -EINVAL;
+
+	fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	fmt.pad = 0;
+
+	pix_to_mbus(vpfe, &format->fmt.pix, &fmt.format);
+
+	ret = v4l2_subdev_call(sdinfo->sd, pad, set_fmt, NULL, &fmt);
+	if (ret && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		return ret;
+
+	if (!ret) {
+		v4l2_fill_pix_format(&format->fmt.pix, &fmt.format);
+		mbus_to_pix(vpfe, &fmt.format, &format->fmt.pix, bpp);
+	} else {
+		ret = v4l2_device_call_until_err(&vpfe->v4l2_dev,
+						 sdinfo->grp_id,
+						 video, s_mbus_fmt,
+						 &mbus_fmt);
+		if (ret && ret != -ENOIOCTLCMD && ret != -ENODEV)
+			return ret;
+
+		v4l2_fill_pix_format(&format->fmt.pix, &mbus_fmt);
+		mbus_to_pix(vpfe, &mbus_fmt, &format->fmt.pix, bpp);
+	}
+
+	format->type = vpfe->fmt.type;
+
+	vpfe_dbg(1, vpfe,
+		 "%s size %dx%d (%s) bytesperline = %d, size = %d, bpp = %d\n",
+		 __func__,  format->fmt.pix.width, format->fmt.pix.height,
+		 print_fourcc(format->fmt.pix.pixelformat),
+		 format->fmt.pix.bytesperline, format->fmt.pix.sizeimage, *bpp);
+
+	return 0;
+}
+
+static int vpfe_g_fmt(struct file *file, void *priv,
+		      struct v4l2_format *fmt)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+
+	vpfe_dbg(2, vpfe, "vpfe_g_fmt\n");
+
+	*fmt = vpfe->fmt;
+
+	return 0;
+}
+
+static int vpfe_enum_fmt(struct file *file, void  *priv,
+			 struct v4l2_fmtdesc *f)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct vpfe_subdev_info *sdinfo;
+	struct vpfe_fmt *fmt = NULL;
+	unsigned int k;
+
+	vpfe_dbg(2, vpfe, "vpfe_enum_format index:%d\n",
+		f->index);
+
+	sdinfo = vpfe->current_subdev;
+	if (!sdinfo->sd)
+		return -EINVAL;
+
+	if (f->index > ARRAY_SIZE(formats))
+		return -EINVAL;
+
+	for (k = 0; k < ARRAY_SIZE(formats); k++) {
+		if (formats[k].index == f->index) {
+			fmt = &formats[k];
+			break;
+		}
+	}
+	if (!fmt)
+		return -EINVAL;
+
+	strncpy(f->description, fmt->name, sizeof(f->description) - 1);
+	f->pixelformat = fmt->fourcc;
+	f->type = vpfe->fmt.type;
+
+	vpfe_dbg(1, vpfe, "vpfe_enum_format: mbus index: %d code: %x pixelformat: %s [%s]\n",
+		f->index, fmt->code, print_fourcc(fmt->fourcc), fmt->name);
+
+	return 0;
+}
+
+static int vpfe_try_fmt(struct file *file, void *priv,
+			struct v4l2_format *fmt)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	unsigned int bpp;
+
+	vpfe_dbg(2, vpfe, "vpfe_try_fmt\n");
+
+	return __vpfe_get_format(vpfe, fmt, &bpp);
+}
+
+static int vpfe_s_fmt(struct file *file, void *priv,
+		      struct v4l2_format *fmt)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct v4l2_format format;
+	unsigned int bpp;
+	int ret;
+
+	vpfe_dbg(2, vpfe, "vpfe_s_fmt\n");
+
+	/* If streaming is started, return error */
+	if (vb2_is_busy(&vpfe->buffer_queue)) {
+		vpfe_err(vpfe, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+
+	ret = vpfe_try_fmt(file, priv, fmt);
+	if (ret)
+		return ret;
+
+
+	if (!cmp_v4l2_format(fmt, &format)) {
+		/* Sensor format is different from the requested format
+		 * so we need to change it
+		 */
+		ret = __vpfe_set_format(vpfe, fmt, &bpp);
+		if (ret)
+			return ret;
+	} else /* Just make sure all of the fields are consistent */
+		*fmt = format;
+
+	/* First detach any IRQ if currently attached */
+	vpfe_detach_irq(vpfe);
+	vpfe->fmt = *fmt;
+	vpfe->bpp = bpp;
+
+	/* Update the crop window based on found values */
+	vpfe->crop.width = fmt->fmt.pix.width;
+	vpfe->crop.height = fmt->fmt.pix.height;
+
+	/* set image capture parameters in the ccdc */
+	return vpfe_config_ccdc_image_format(vpfe);
+}
+
+static int vpfe_enum_size(struct file *file, void  *priv,
+			  struct v4l2_frmsizeenum *fsize)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct v4l2_subdev_frame_size_enum fse;
+	struct vpfe_subdev_info *sdinfo;
+	struct v4l2_mbus_framefmt mbus;
+	struct v4l2_pix_format pix;
+	struct vpfe_fmt *fmt;
+	int ret;
+
+	vpfe_dbg(2, vpfe, "vpfe_enum_size\n");
+
+	/* check for valid format */
+	fmt = find_format_by_pix(fsize->pixel_format);
+	if (!fmt) {
+		vpfe_dbg(3, vpfe, "Invalid pixel code: %x, default used instead\n",
+			fsize->pixel_format);
+		return -EINVAL;
+	}
+
+	memset(fsize->reserved, 0x0, sizeof(fsize->reserved));
+
+	sdinfo = vpfe->current_subdev;
+	if (!sdinfo->sd)
+		return -EINVAL;
+
+	memset(&pix, 0x0, sizeof(pix));
+	/* Construct pix from parameter and use default for the rest */
+	pix.pixelformat = fsize->pixel_format;
+	pix.width = 640;
+	pix.height = 480;
+	pix.colorspace = V4L2_COLORSPACE_SRGB;
+	pix.field = V4L2_FIELD_NONE;
+	pix_to_mbus(vpfe, &pix, &mbus);
+
+	memset(&fse, 0x0, sizeof(fse));
+	fse.index = fsize->index;
+	fse.pad = 0;
+	fse.code = mbus.code;
+	ret = v4l2_subdev_call(sdinfo->sd, pad, enum_frame_size, NULL, &fse);
+	if (ret)
+		return -EINVAL;
+
+	vpfe_dbg(1, vpfe, "vpfe_enum_size: index: %d code: %x W:[%d,%d] H:[%d,%d]\n",
+		fse.index, fse.code, fse.min_width, fse.max_width,
+		fse.min_height, fse.max_height);
+
+	fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE;
+	fsize->discrete.width = fse.max_width;
+	fsize->discrete.height = fse.max_height;
+
+	vpfe_dbg(1, vpfe, "vpfe_enum_size: index: %d pixformat: %s size: %dx%d\n",
+		fsize->index, print_fourcc(fsize->pixel_format),
+		fsize->discrete.width, fsize->discrete.height);
+
+	return 0;
+}
+
+/*
+ * vpfe_get_subdev_input_index - Get subdev index and subdev input index for a
+ * given app input index
+ */
+static int
+vpfe_get_subdev_input_index(struct vpfe_device *vpfe,
+			    int *subdev_index,
+			    int *subdev_input_index,
+			    int app_input_index)
+{
+	struct vpfe_config *cfg = vpfe->cfg;
+	struct vpfe_subdev_info *sdinfo;
+	int i, j = 0;
+
+	for (i = 0; i < ARRAY_SIZE(vpfe->cfg->asd); i++) {
+		sdinfo = &cfg->sub_devs[i];
+		if (app_input_index < (j + 1)) {
+			*subdev_index = i;
+			*subdev_input_index = app_input_index - j;
+			return 0;
+		}
+		j++;
+	}
+	return -EINVAL;
+}
+
+/*
+ * vpfe_get_app_input - Get app input index for a given subdev input index
+ * driver stores the input index of the current sub device and translate it
+ * when application request the current input
+ */
+static int vpfe_get_app_input_index(struct vpfe_device *vpfe,
+				    int *app_input_index)
+{
+	struct vpfe_config *cfg = vpfe->cfg;
+	struct vpfe_subdev_info *sdinfo;
+	int i, j = 0;
+
+	for (i = 0; i < ARRAY_SIZE(vpfe->cfg->asd); i++) {
+		sdinfo = &cfg->sub_devs[i];
+		if (!strcmp(sdinfo->name, vpfe->current_subdev->name)) {
+			if (vpfe->current_input >= 1)
+				return -1;
+			*app_input_index = j + vpfe->current_input;
+			return 0;
+		}
+		j++;
+	}
+	return -EINVAL;
+}
+
+static int vpfe_enum_input(struct file *file, void *priv,
+			   struct v4l2_input *inp)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct vpfe_subdev_info *sdinfo;
+	int subdev, index;
+
+	vpfe_dbg(2, vpfe, "vpfe_enum_input\n");
+
+	if (vpfe_get_subdev_input_index(vpfe, &subdev, &index,
+					inp->index) < 0) {
+		vpfe_dbg(1, vpfe,
+			"input information not found for the subdev\n");
+		return -EINVAL;
+	}
+	sdinfo = &vpfe->cfg->sub_devs[subdev];
+	*inp = sdinfo->inputs[index];
+
+	return 0;
+}
+
+static int vpfe_g_input(struct file *file, void *priv, unsigned int *index)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+
+	vpfe_dbg(2, vpfe, "vpfe_g_input\n");
+
+	return vpfe_get_app_input_index(vpfe, index);
+}
+
+/* Assumes caller is holding vpfe_dev->lock */
+static int vpfe_set_input(struct vpfe_device *vpfe, unsigned int index)
+{
+	int subdev_index = 0, inp_index = 0;
+	struct vpfe_subdev_info *sdinfo;
+	struct vpfe_route *route;
+	u32 input, output;
+	int ret;
+
+	vpfe_dbg(2, vpfe, "vpfe_set_input: index: %d\n", index);
+
+	/* If streaming is started, return error */
+	if (vb2_is_busy(&vpfe->buffer_queue)) {
+		vpfe_err(vpfe, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+	ret = vpfe_get_subdev_input_index(vpfe,
+					  &subdev_index,
+					  &inp_index,
+					  index);
+	if (ret < 0) {
+		vpfe_err(vpfe, "invalid input index: %d\n", index);
+		goto get_out;
+	}
+
+	sdinfo = &vpfe->cfg->sub_devs[subdev_index];
+	sdinfo->sd = vpfe->sd[subdev_index];
+	route = &sdinfo->routes[inp_index];
+	if (route && sdinfo->can_route) {
+		input = route->input;
+		output = route->output;
+		if (sdinfo->sd) {
+			ret = v4l2_subdev_call(sdinfo->sd, video,
+					s_routing, input, output, 0);
+			if (ret) {
+				vpfe_err(vpfe, "s_routing failed\n");
+				ret = -EINVAL;
+				goto get_out;
+			}
+		}
+
+	}
+
+	vpfe->current_subdev = sdinfo;
+	if (sdinfo->sd)
+		vpfe->v4l2_dev.ctrl_handler = sdinfo->sd->ctrl_handler;
+	vpfe->current_input = index;
+	vpfe->std_index = 0;
+
+	/* set the bus/interface parameter for the sub device in ccdc */
+	ret = vpfe_ccdc_set_hw_if_params(&vpfe->ccdc, &sdinfo->vpfe_param);
+	if (ret)
+		return ret;
+
+	/* set the default image parameters in the device */
+	return vpfe_config_image_format(vpfe,
+					vpfe_standards[vpfe->std_index].std_id);
+
+get_out:
+	return ret;
+}
+
+static int vpfe_s_input(struct file *file, void *priv, unsigned int index)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+
+	vpfe_dbg(2, vpfe,
+		"vpfe_s_input: index: %d\n", index);
+
+	return vpfe_set_input(vpfe, index);
+}
+
+static int vpfe_querystd(struct file *file, void *priv, v4l2_std_id *std_id)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct vpfe_subdev_info *sdinfo;
+
+	vpfe_dbg(2, vpfe, "vpfe_querystd\n");
+
+	sdinfo = vpfe->current_subdev;
+	if (!(sdinfo->inputs[0].capabilities & V4L2_IN_CAP_STD))
+		return -ENODATA;
+
+	/* Call querystd function of decoder device */
+	return v4l2_device_call_until_err(&vpfe->v4l2_dev, sdinfo->grp_id,
+					 video, querystd, std_id);
+}
+
+static int vpfe_s_std(struct file *file, void *priv, v4l2_std_id std_id)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct vpfe_subdev_info *sdinfo;
+	int ret;
+
+	vpfe_dbg(2, vpfe, "vpfe_s_std\n");
+
+	sdinfo = vpfe->current_subdev;
+	if (!(sdinfo->inputs[0].capabilities & V4L2_IN_CAP_STD))
+		return -ENODATA;
+
+	/* If streaming is started, return error */
+	if (vb2_is_busy(&vpfe->buffer_queue)) {
+		vpfe_err(vpfe, "%s device busy\n", __func__);
+		ret = -EBUSY;
+		return ret;
+	}
+
+	ret = v4l2_device_call_until_err(&vpfe->v4l2_dev, sdinfo->grp_id,
+					 video, s_std, std_id);
+	if (ret < 0) {
+		vpfe_err(vpfe, "Failed to set standard\n");
+		return ret;
+	}
+	ret = vpfe_config_image_format(vpfe, std_id);
+
+	return ret;
+}
+
+static int vpfe_g_std(struct file *file, void *priv, v4l2_std_id *std_id)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct vpfe_subdev_info *sdinfo;
+
+	vpfe_dbg(2, vpfe, "vpfe_g_std\n");
+
+	sdinfo = vpfe->current_subdev;
+	if (sdinfo->inputs[0].capabilities != V4L2_IN_CAP_STD)
+		return -ENODATA;
+
+	*std_id = vpfe_standards[vpfe->std_index].std_id;
+
+	return 0;
+}
+
+/*
+ * vpfe_calculate_offsets : This function calculates buffers offset
+ * for top and bottom field
+ */
+static void vpfe_calculate_offsets(struct vpfe_device *vpfe)
+{
+	struct v4l2_rect image_win;
+
+	vpfe_dbg(2, vpfe, "vpfe_calculate_offsets\n");
+
+	vpfe_ccdc_get_image_window(&vpfe->ccdc, &image_win);
+	vpfe->field_off = image_win.height * image_win.width;
+}
+
+/*
+ * vpfe_queue_setup - Callback function for buffer setup.
+ * @vq: vb2_queue ptr
+ * @fmt: v4l2 format
+ * @nbuffers: ptr to number of buffers requested by application
+ * @nplanes:: contains number of distinct video planes needed to hold a frame
+ * @sizes[]: contains the size (in bytes) of each plane.
+ * @alloc_ctxs: ptr to allocation context
+ *
+ * This callback function is called when reqbuf() is called to adjust
+ * the buffer count and buffer size
+ */
+static int vpfe_queue_setup(struct vb2_queue *vq,
+			    const struct v4l2_format *fmt,
+			    unsigned int *nbuffers, unsigned int *nplanes,
+			    unsigned int sizes[], void *alloc_ctxs[])
+{
+	struct vpfe_device *vpfe = vb2_get_drv_priv(vq);
+
+	if (fmt && fmt->fmt.pix.sizeimage < vpfe->fmt.fmt.pix.sizeimage)
+		return -EINVAL;
+
+	if (vq->num_buffers + *nbuffers < 3)
+		*nbuffers = 3 - vq->num_buffers;
+
+	*nplanes = 1;
+	sizes[0] = fmt ? fmt->fmt.pix.sizeimage : vpfe->fmt.fmt.pix.sizeimage;
+	alloc_ctxs[0] = vpfe->alloc_ctx;
+
+	vpfe_dbg(1, vpfe,
+		"nbuffers=%d, size=%u\n", *nbuffers, sizes[0]);
+
+	/* Calculate field offset */
+	vpfe_calculate_offsets(vpfe);
+
+	return 0;
+}
+
+/*
+ * vpfe_buffer_prepare :  callback function for buffer prepare
+ * @vb: ptr to vb2_buffer
+ *
+ * This is the callback function for buffer prepare when vb2_qbuf()
+ * function is called. The buffer is prepared and user space virtual address
+ * or user address is converted into  physical address
+ */
+static int vpfe_buffer_prepare(struct vb2_buffer *vb)
+{
+	struct vpfe_device *vpfe = vb2_get_drv_priv(vb->vb2_queue);
+
+	vb2_set_plane_payload(vb, 0, vpfe->fmt.fmt.pix.sizeimage);
+
+	if (vb2_get_plane_payload(vb, 0) > vb2_plane_size(vb, 0))
+		return -EINVAL;
+
+	vb->v4l2_buf.field = vpfe->fmt.fmt.pix.field;
+
+	return 0;
+}
+
+/*
+ * vpfe_buffer_queue : Callback function to add buffer to DMA queue
+ * @vb: ptr to vb2_buffer
+ */
+static void vpfe_buffer_queue(struct vb2_buffer *vb)
+{
+	struct vpfe_device *vpfe = vb2_get_drv_priv(vb->vb2_queue);
+	struct vpfe_cap_buffer *buf = to_vpfe_buffer(vb);
+	unsigned long flags = 0;
+
+	/* add the buffer to the DMA queue */
+	spin_lock_irqsave(&vpfe->dma_queue_lock, flags);
+	list_add_tail(&buf->list, &vpfe->dma_queue);
+	spin_unlock_irqrestore(&vpfe->dma_queue_lock, flags);
+}
+
+/*
+ * vpfe_start_streaming : Starts the DMA engine for streaming
+ * @vb: ptr to vb2_buffer
+ * @count: number of buffers
+ */
+static int vpfe_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct vpfe_device *vpfe = vb2_get_drv_priv(vq);
+	struct vpfe_cap_buffer *buf, *tmp;
+	struct vpfe_subdev_info *sdinfo;
+	unsigned long flags;
+	unsigned long addr;
+	int ret;
+
+	spin_lock_irqsave(&vpfe->dma_queue_lock, flags);
+
+	vpfe->field = 0;
+	vpfe->sequence = 0;
+
+	sdinfo = vpfe->current_subdev;
+
+	vpfe_attach_irq(vpfe);
+
+	if (vpfe->ccdc.ccdc_cfg.if_type == VPFE_RAW_BAYER)
+		vpfe_ccdc_config_raw(&vpfe->ccdc);
+	else
+		vpfe_ccdc_config_ycbcr(&vpfe->ccdc);
+
+	/* Get the next frame from the buffer queue */
+	vpfe->next_frm = list_entry(vpfe->dma_queue.next,
+				    struct vpfe_cap_buffer, list);
+	vpfe->cur_frm = vpfe->next_frm;
+	/* Remove buffer from the buffer queue */
+	list_del(&vpfe->cur_frm->list);
+	spin_unlock_irqrestore(&vpfe->dma_queue_lock, flags);
+
+	addr = vb2_dma_contig_plane_dma_addr(&vpfe->cur_frm->vb, 0);
+
+	vpfe_set_sdr_addr(&vpfe->ccdc, (unsigned long)(addr));
+
+	vpfe_pcr_enable(&vpfe->ccdc, 1);
+
+	ret = v4l2_subdev_call(sdinfo->sd, video, s_stream, 1);
+	if (ret < 0) {
+		vpfe_err(vpfe, "Error in attaching interrupt handle\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	list_for_each_entry_safe(buf, tmp, &vpfe->dma_queue, list) {
+		list_del(&buf->list);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
+	}
+	spin_unlock_irqrestore(&vpfe->dma_queue_lock, flags);
+
+	return ret;
+}
+
+/*
+ * vpfe_stop_streaming : Stop the DMA engine
+ * @vq: ptr to vb2_queue
+ *
+ * This callback stops the DMA engine and any remaining buffers
+ * in the DMA queue are released.
+ */
+static void vpfe_stop_streaming(struct vb2_queue *vq)
+{
+	struct vpfe_device *vpfe = vb2_get_drv_priv(vq);
+	struct vpfe_subdev_info *sdinfo;
+	unsigned long flags;
+	int ret;
+
+	vpfe_pcr_enable(&vpfe->ccdc, 0);
+
+	vpfe_detach_irq(vpfe);
+
+	sdinfo = vpfe->current_subdev;
+	ret = v4l2_subdev_call(sdinfo->sd, video, s_stream, 0);
+	if (ret && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		vpfe_dbg(1, vpfe, "stream off failed in subdev\n");
+
+	/* release all active buffers */
+	spin_lock_irqsave(&vpfe->dma_queue_lock, flags);
+	if (vpfe->cur_frm == vpfe->next_frm) {
+		vb2_buffer_done(&vpfe->cur_frm->vb, VB2_BUF_STATE_ERROR);
+	} else {
+		if (vpfe->cur_frm != NULL)
+			vb2_buffer_done(&vpfe->cur_frm->vb,
+					VB2_BUF_STATE_ERROR);
+		if (vpfe->next_frm != NULL)
+			vb2_buffer_done(&vpfe->next_frm->vb,
+					VB2_BUF_STATE_ERROR);
+	}
+
+	while (!list_empty(&vpfe->dma_queue)) {
+		vpfe->next_frm = list_entry(vpfe->dma_queue.next,
+						struct vpfe_cap_buffer, list);
+		list_del(&vpfe->next_frm->list);
+		vb2_buffer_done(&vpfe->next_frm->vb, VB2_BUF_STATE_ERROR);
+	}
+	spin_unlock_irqrestore(&vpfe->dma_queue_lock, flags);
+}
+
+static int vpfe_cropcap(struct file *file, void *priv,
+			struct v4l2_cropcap *crop)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+
+	vpfe_dbg(2, vpfe, "vpfe_cropcap\n");
+
+	if (vpfe->std_index >= ARRAY_SIZE(vpfe_standards))
+		return -EINVAL;
+
+	memset(crop, 0, sizeof(struct v4l2_cropcap));
+
+	crop->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	crop->defrect.width = vpfe_standards[vpfe->std_index].width;
+	crop->bounds.width = crop->defrect.width;
+	crop->defrect.height = vpfe_standards[vpfe->std_index].height;
+	crop->bounds.height = crop->defrect.height;
+	crop->pixelaspect = vpfe_standards[vpfe->std_index].pixelaspect;
+
+	return 0;
+}
+
+static int
+vpfe_g_selection(struct file *file, void *fh, struct v4l2_selection *s)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+
+	switch (s->target) {
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+		s->r.left = s->r.top = 0;
+		s->r.width = vpfe->crop.width;
+		s->r.height = vpfe->crop.height;
+		break;
+
+	case V4L2_SEL_TGT_CROP:
+		s->r = vpfe->crop;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int enclosed_rectangle(struct v4l2_rect *a, struct v4l2_rect *b)
+{
+	if (a->left < b->left || a->top < b->top)
+		return 0;
+
+	if (a->left + a->width > b->left + b->width)
+		return 0;
+
+	if (a->top + a->height > b->top + b->height)
+		return 0;
+
+	return 1;
+}
+
+static int
+vpfe_s_selection(struct file *file, void *fh, struct v4l2_selection *s)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	struct v4l2_rect cr = vpfe->crop;
+	struct v4l2_rect r = s->r;
+
+	/* If streaming is started, return error */
+	if (vb2_is_busy(&vpfe->buffer_queue)) {
+		vpfe_err(vpfe, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+
+	if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE ||
+			s->target != V4L2_SEL_TGT_CROP)
+		return -EINVAL;
+
+	v4l_bound_align_image(&r.width, 0, cr.width, 0,
+			      &r.height, 0, cr.height, 0, 0);
+
+	r.left = clamp_t(unsigned int, r.left, 0, cr.width - r.width);
+	r.top  = clamp_t(unsigned int, r.top, 0, cr.height - r.height);
+
+	if (s->flags & V4L2_SEL_FLAG_LE && !enclosed_rectangle(&r, &s->r))
+		return -ERANGE;
+
+	if (s->flags & V4L2_SEL_FLAG_GE && !enclosed_rectangle(&s->r, &r))
+		return -ERANGE;
+
+	s->r = vpfe->crop = r;
+
+	vpfe_ccdc_set_image_window(&vpfe->ccdc, &r, vpfe->bpp);
+	vpfe->fmt.fmt.pix.width = r.width;
+	vpfe->fmt.fmt.pix.height = r.height;
+	vpfe->fmt.fmt.pix.bytesperline = vpfe_ccdc_get_line_length(&vpfe->ccdc);
+	vpfe->fmt.fmt.pix.sizeimage = vpfe->fmt.fmt.pix.bytesperline *
+						vpfe->fmt.fmt.pix.height;
+
+	vpfe_dbg(1, vpfe, "cropped (%d,%d)/%dx%d of %dx%d\n",
+		 r.left, r.top, r.width, r.height, cr.width, cr.height);
+
+	return 0;
+}
+
+static long vpfe_ioctl_default(struct file *file, void *priv,
+			       bool valid_prio, unsigned int cmd, void *param)
+{
+	struct vpfe_device *vpfe = video_drvdata(file);
+	int ret;
+
+	vpfe_dbg(2, vpfe, "vpfe_ioctl_default\n");
+
+	if (!valid_prio) {
+		vpfe_err(vpfe, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+
+	/* If streaming is started, return error */
+	if (vb2_is_busy(&vpfe->buffer_queue)) {
+		vpfe_err(vpfe, "%s device busy\n", __func__);
+		return -EBUSY;
+	}
+
+	switch (cmd) {
+	case VIDIOC_AM437X_CCDC_CFG:
+		ret = vpfe_ccdc_set_params(&vpfe->ccdc, param);
+		if (ret) {
+			vpfe_dbg(2, vpfe,
+				"Error setting parameters in CCDC\n");
+			return ret;
+		}
+		ret = vpfe_get_ccdc_image_format(vpfe,
+						 &vpfe->fmt);
+		if (ret < 0) {
+			vpfe_dbg(2, vpfe,
+				"Invalid image format at CCDC\n");
+			return ret;
+		}
+		break;
+
+	default:
+		ret = -ENOTTY;
+		break;
+	}
+
+	return ret;
+}
+
+static const struct vb2_ops vpfe_video_qops = {
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+	.queue_setup		= vpfe_queue_setup,
+	.buf_prepare		= vpfe_buffer_prepare,
+	.buf_queue		= vpfe_buffer_queue,
+	.start_streaming	= vpfe_start_streaming,
+	.stop_streaming		= vpfe_stop_streaming,
+};
+
+/* vpfe capture driver file operations */
+static const struct v4l2_file_operations vpfe_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vpfe_open,
+	.release	= vpfe_release,
+	.read		= vb2_fop_read,
+	.poll		= vb2_fop_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= vb2_fop_mmap,
+};
+
+/* vpfe capture ioctl operations */
+static const struct v4l2_ioctl_ops vpfe_ioctl_ops = {
+	.vidioc_querycap		= vpfe_querycap,
+	.vidioc_enum_fmt_vid_cap	= vpfe_enum_fmt,
+	.vidioc_g_fmt_vid_cap		= vpfe_g_fmt,
+	.vidioc_s_fmt_vid_cap		= vpfe_s_fmt,
+	.vidioc_try_fmt_vid_cap		= vpfe_try_fmt,
+
+	.vidioc_enum_framesizes		= vpfe_enum_size,
+
+	.vidioc_enum_input		= vpfe_enum_input,
+	.vidioc_g_input			= vpfe_g_input,
+	.vidioc_s_input			= vpfe_s_input,
+
+	.vidioc_querystd		= vpfe_querystd,
+	.vidioc_s_std			= vpfe_s_std,
+	.vidioc_g_std			= vpfe_g_std,
+
+	.vidioc_reqbufs			= vb2_ioctl_reqbufs,
+	.vidioc_create_bufs		= vb2_ioctl_create_bufs,
+	.vidioc_prepare_buf		= vb2_ioctl_prepare_buf,
+	.vidioc_querybuf		= vb2_ioctl_querybuf,
+	.vidioc_qbuf			= vb2_ioctl_qbuf,
+	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
+	.vidioc_expbuf			= vb2_ioctl_expbuf,
+	.vidioc_streamon		= vb2_ioctl_streamon,
+	.vidioc_streamoff		= vb2_ioctl_streamoff,
+
+	.vidioc_log_status		= v4l2_ctrl_log_status,
+	.vidioc_subscribe_event		= v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
+
+	.vidioc_cropcap			= vpfe_cropcap,
+	.vidioc_g_selection		= vpfe_g_selection,
+	.vidioc_s_selection		= vpfe_s_selection,
+
+	.vidioc_default			= vpfe_ioctl_default,
+};
+
+static int
+vpfe_async_bound(struct v4l2_async_notifier *notifier,
+		 struct v4l2_subdev *subdev,
+		 struct v4l2_async_subdev *asd)
+{
+	struct vpfe_device *vpfe = container_of(notifier->v4l2_dev,
+					       struct vpfe_device, v4l2_dev);
+	struct v4l2_subdev_mbus_code_enum mbus_code;
+	struct vpfe_subdev_info *sdinfo;
+	bool found = false;
+	int i, j;
+
+	vpfe_dbg(1, vpfe, "vpfe_async_bound\n");
+
+	for (i = 0; i < ARRAY_SIZE(vpfe->cfg->asd); i++) {
+		sdinfo = &vpfe->cfg->sub_devs[i];
+
+		if (!strcmp(sdinfo->name, subdev->name)) {
+			vpfe->sd[i] = subdev;
+			vpfe_info(vpfe,
+				 "v4l2 sub device %s registered\n",
+				 subdev->name);
+			vpfe->sd[i]->grp_id =
+					sdinfo->grp_id;
+			/* update tvnorms from the sub devices */
+			for (j = 0; j < 1; j++)
+				vpfe->video_dev->tvnorms |=
+					sdinfo->inputs[j].std;
+
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		vpfe_info(vpfe, "sub device (%s) not matched\n", subdev->name);
+		return -EINVAL;
+	}
+
+	/* setup the supported formats & indexes */
+	for (j = 0, i = 0; ; ++j) {
+		struct vpfe_fmt *fmt;
+		int ret;
+
+		memset(&mbus_code, 0, sizeof(mbus_code));
+		mbus_code.index = j;
+		ret = v4l2_subdev_call(subdev, pad, enum_mbus_code,
+			       NULL, &mbus_code);
+		if (ret)
+			break;
+
+		fmt = find_format_by_code(mbus_code.code);
+		if (!fmt)
+			continue;
+
+		fmt->supported = true;
+		fmt->index = i++;
+	}
+
+	return 0;
+}
+
+static int vpfe_probe_complete(struct vpfe_device *vpfe)
+{
+	struct video_device *vdev;
+	struct vb2_queue *q;
+	int err;
+
+	spin_lock_init(&vpfe->dma_queue_lock);
+	mutex_init(&vpfe->lock);
+
+	vpfe->fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+
+	/* set first sub device as current one */
+	vpfe->current_subdev = &vpfe->cfg->sub_devs[0];
+	vpfe->v4l2_dev.ctrl_handler = vpfe->sd[0]->ctrl_handler;
+
+	err = vpfe_set_input(vpfe, 0);
+	if (err)
+		goto probe_out;
+
+	/* Initialize videobuf2 queue as per the buffer type */
+	vpfe->alloc_ctx = vb2_dma_contig_init_ctx(vpfe->pdev);
+	if (IS_ERR(vpfe->alloc_ctx)) {
+		vpfe_err(vpfe, "Failed to get the context\n");
+		err = PTR_ERR(vpfe->alloc_ctx);
+		goto probe_out;
+	}
+
+	q = &vpfe->buffer_queue;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_READ;
+	q->drv_priv = vpfe;
+	q->ops = &vpfe_video_qops;
+	q->mem_ops = &vb2_dma_contig_memops;
+	q->buf_struct_size = sizeof(struct vpfe_cap_buffer);
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &vpfe->lock;
+	q->min_buffers_needed = 1;
+
+	err = vb2_queue_init(q);
+	if (err) {
+		vpfe_err(vpfe, "vb2_queue_init() failed\n");
+		vb2_dma_contig_cleanup_ctx(vpfe->alloc_ctx);
+		goto probe_out;
+	}
+
+	INIT_LIST_HEAD(&vpfe->dma_queue);
+
+	vdev = vpfe->video_dev;
+	strlcpy(vdev->name, VPFE_MODULE_NAME, sizeof(vdev->name));
+	vdev->release = video_device_release;
+	vdev->fops = &vpfe_fops;
+	vdev->ioctl_ops = &vpfe_ioctl_ops;
+	vdev->v4l2_dev = &vpfe->v4l2_dev;
+	vdev->vfl_dir = VFL_DIR_RX;
+	vdev->queue = q;
+	vdev->lock = &vpfe->lock;
+	video_set_drvdata(vdev, vpfe);
+	err = video_register_device(vpfe->video_dev, VFL_TYPE_GRABBER, -1);
+	if (err) {
+		vpfe_err(vpfe,
+			"Unable to register video device.\n");
+		goto probe_out;
+	}
+
+	return 0;
+
+probe_out:
+	v4l2_device_unregister(&vpfe->v4l2_dev);
+	return err;
+}
+
+static int vpfe_async_complete(struct v4l2_async_notifier *notifier)
+{
+	struct vpfe_device *vpfe = container_of(notifier->v4l2_dev,
+					struct vpfe_device, v4l2_dev);
+
+	return vpfe_probe_complete(vpfe);
+}
+
+static struct vpfe_config *
+vpfe_get_pdata(struct platform_device *pdev)
+{
+	struct device_node *endpoint = NULL, *rem = NULL;
+	struct v4l2_of_endpoint bus_cfg;
+	struct vpfe_subdev_info *sdinfo;
+	struct vpfe_config *pdata;
+	unsigned int flags;
+	unsigned int i;
+	int err;
+
+	dev_dbg(&pdev->dev, "vpfe_get_pdata\n");
+
+	if (!IS_ENABLED(CONFIG_OF) || !pdev->dev.of_node)
+		return pdev->dev.platform_data;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	for (i = 0; ; i++) {
+		endpoint = of_graph_get_next_endpoint(pdev->dev.of_node,
+						      endpoint);
+		if (!endpoint)
+			break;
+
+		sdinfo = &pdata->sub_devs[i];
+		sdinfo->grp_id = 0;
+
+		/* we only support camera */
+		sdinfo->inputs[0].index = i;
+		strcpy(sdinfo->inputs[0].name, "Camera");
+		sdinfo->inputs[0].type = V4L2_INPUT_TYPE_CAMERA;
+		sdinfo->inputs[0].std = V4L2_STD_ALL;
+		sdinfo->inputs[0].capabilities = V4L2_IN_CAP_STD;
+
+		sdinfo->can_route = 0;
+		sdinfo->routes = NULL;
+
+		of_property_read_u32(endpoint, "ti,am437x-vpfe-interface",
+				     &sdinfo->vpfe_param.if_type);
+		if (sdinfo->vpfe_param.if_type < 0 ||
+			sdinfo->vpfe_param.if_type > 4) {
+			sdinfo->vpfe_param.if_type = VPFE_RAW_BAYER;
+		}
+
+		err = v4l2_of_parse_endpoint(endpoint, &bus_cfg);
+		if (err) {
+			dev_err(&pdev->dev, "Could not parse the endpoint\n");
+			goto done;
+		}
+
+		sdinfo->vpfe_param.bus_width = bus_cfg.bus.parallel.bus_width;
+
+		if (sdinfo->vpfe_param.bus_width < 8 ||
+			sdinfo->vpfe_param.bus_width > 16) {
+			dev_err(&pdev->dev, "Invalid bus width.\n");
+			goto done;
+		}
+
+		flags = bus_cfg.bus.parallel.flags;
+
+		if (flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH)
+			sdinfo->vpfe_param.hdpol = 1;
+
+		if (flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH)
+			sdinfo->vpfe_param.vdpol = 1;
+
+		rem = of_graph_get_remote_port_parent(endpoint);
+		if (!rem) {
+			dev_err(&pdev->dev, "Remote device at %s not found\n",
+				endpoint->full_name);
+			goto done;
+		}
+
+		strncpy(sdinfo->name, rem->name, sizeof(sdinfo->name));
+
+		pdata->asd[i] = devm_kzalloc(&pdev->dev,
+					     sizeof(struct v4l2_async_subdev),
+					     GFP_KERNEL);
+		pdata->asd[i]->match_type = V4L2_ASYNC_MATCH_OF;
+		pdata->asd[i]->match.of.node = rem;
+		of_node_put(endpoint);
+		of_node_put(rem);
+	}
+
+	of_node_put(endpoint);
+	return pdata;
+
+done:
+	of_node_put(endpoint);
+	of_node_put(rem);
+	return NULL;
+}
+
+/*
+ * vpfe_probe : This function creates device entries by register
+ * itself to the V4L2 driver and initializes fields of each
+ * device objects
+ */
+static int vpfe_probe(struct platform_device *pdev)
+{
+	struct vpfe_config *vpfe_cfg = vpfe_get_pdata(pdev);
+	struct vpfe_device *vpfe;
+	struct vpfe_ccdc *ccdc;
+	struct resource	*res;
+	int ret;
+
+	if (!vpfe_cfg) {
+		dev_err(&pdev->dev, "No platform data\n");
+		return -EINVAL;
+	}
+
+	vpfe = devm_kzalloc(&pdev->dev, sizeof(*vpfe), GFP_KERNEL);
+	if (!vpfe)
+		return -ENOMEM;
+
+	vpfe->pdev = &pdev->dev;
+	vpfe->cfg = vpfe_cfg;
+	ccdc = &vpfe->ccdc;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ccdc->ccdc_cfg.base_addr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ccdc->ccdc_cfg.base_addr))
+		return PTR_ERR(ccdc->ccdc_cfg.base_addr);
+
+	vpfe->irq = platform_get_irq(pdev, 0);
+	if (vpfe->irq <= 0) {
+		dev_err(&pdev->dev, "No IRQ resource\n");
+		return -ENODEV;
+	}
+
+	ret = devm_request_irq(vpfe->pdev, vpfe->irq, vpfe_isr, 0,
+			       "vpfe_capture0", vpfe);
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to request interrupt\n");
+		return -EINVAL;
+	}
+
+	vpfe->video_dev = video_device_alloc();
+	if (!vpfe->video_dev) {
+		dev_err(&pdev->dev, "Unable to allocate video device\n");
+		return -ENOMEM;
+	}
+
+	ret = v4l2_device_register(&pdev->dev, &vpfe->v4l2_dev);
+	if (ret) {
+		vpfe_err(vpfe,
+			"Unable to register v4l2 device.\n");
+		goto probe_out_video_release;
+	}
+
+	/* set the driver data in platform device */
+	platform_set_drvdata(pdev, vpfe);
+	/* Enabling module functional clock */
+	pm_runtime_enable(&pdev->dev);
+
+	/* for now just enable it here instead of waiting for the open */
+	pm_runtime_get_sync(&pdev->dev);
+
+	vpfe_ccdc_config_defaults(ccdc);
+
+	pm_runtime_put_sync(&pdev->dev);
+
+	vpfe->sd = devm_kzalloc(&pdev->dev, sizeof(struct v4l2_subdev *) *
+				ARRAY_SIZE(vpfe->cfg->asd), GFP_KERNEL);
+	if (!vpfe->sd) {
+		ret = -ENOMEM;
+		goto probe_out_v4l2_unregister;
+	}
+
+	vpfe->notifier.subdevs = vpfe->cfg->asd;
+	vpfe->notifier.num_subdevs = ARRAY_SIZE(vpfe->cfg->asd);
+	vpfe->notifier.bound = vpfe_async_bound;
+	vpfe->notifier.complete = vpfe_async_complete;
+	ret = v4l2_async_notifier_register(&vpfe->v4l2_dev,
+						&vpfe->notifier);
+	if (ret) {
+		vpfe_err(vpfe, "Error registering async notifier\n");
+		ret = -EINVAL;
+		goto probe_out_v4l2_unregister;
+	}
+
+	return 0;
+
+probe_out_v4l2_unregister:
+	v4l2_device_unregister(&vpfe->v4l2_dev);
+probe_out_video_release:
+	if (!video_is_registered(vpfe->video_dev))
+		video_device_release(vpfe->video_dev);
+	return ret;
+}
+
+/*
+ * vpfe_remove : It un-register device from V4L2 driver
+ */
+static int vpfe_remove(struct platform_device *pdev)
+{
+	struct vpfe_device *vpfe = platform_get_drvdata(pdev);
+
+	vpfe_dbg(2, vpfe, "vpfe_remove\n");
+
+	pm_runtime_disable(&pdev->dev);
+
+	v4l2_async_notifier_unregister(&vpfe->notifier);
+	v4l2_device_unregister(&vpfe->v4l2_dev);
+	video_unregister_device(vpfe->video_dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+
+static void vpfe_save_context(struct vpfe_ccdc *ccdc)
+{
+	ccdc->ccdc_ctx[VPFE_PCR >> 2] = vpfe_reg_read(ccdc, VPFE_PCR);
+	ccdc->ccdc_ctx[VPFE_SYNMODE >> 2] = vpfe_reg_read(ccdc, VPFE_SYNMODE);
+	ccdc->ccdc_ctx[VPFE_SDOFST >> 2] = vpfe_reg_read(ccdc, VPFE_SDOFST);
+	ccdc->ccdc_ctx[VPFE_SDR_ADDR >> 2] = vpfe_reg_read(ccdc, VPFE_SDR_ADDR);
+	ccdc->ccdc_ctx[VPFE_CLAMP >> 2] = vpfe_reg_read(ccdc, VPFE_CLAMP);
+	ccdc->ccdc_ctx[VPFE_DCSUB >> 2] = vpfe_reg_read(ccdc, VPFE_DCSUB);
+	ccdc->ccdc_ctx[VPFE_COLPTN >> 2] = vpfe_reg_read(ccdc, VPFE_COLPTN);
+	ccdc->ccdc_ctx[VPFE_BLKCMP >> 2] = vpfe_reg_read(ccdc, VPFE_BLKCMP);
+	ccdc->ccdc_ctx[VPFE_VDINT >> 2] = vpfe_reg_read(ccdc, VPFE_VDINT);
+	ccdc->ccdc_ctx[VPFE_ALAW >> 2] = vpfe_reg_read(ccdc, VPFE_ALAW);
+	ccdc->ccdc_ctx[VPFE_REC656IF >> 2] = vpfe_reg_read(ccdc, VPFE_REC656IF);
+	ccdc->ccdc_ctx[VPFE_CCDCFG >> 2] = vpfe_reg_read(ccdc, VPFE_CCDCFG);
+	ccdc->ccdc_ctx[VPFE_CULLING >> 2] = vpfe_reg_read(ccdc, VPFE_CULLING);
+	ccdc->ccdc_ctx[VPFE_HD_VD_WID >> 2] = vpfe_reg_read(ccdc,
+							    VPFE_HD_VD_WID);
+	ccdc->ccdc_ctx[VPFE_PIX_LINES >> 2] = vpfe_reg_read(ccdc,
+							    VPFE_PIX_LINES);
+	ccdc->ccdc_ctx[VPFE_HORZ_INFO >> 2] = vpfe_reg_read(ccdc,
+							    VPFE_HORZ_INFO);
+	ccdc->ccdc_ctx[VPFE_VERT_START >> 2] = vpfe_reg_read(ccdc,
+							     VPFE_VERT_START);
+	ccdc->ccdc_ctx[VPFE_VERT_LINES >> 2] = vpfe_reg_read(ccdc,
+							     VPFE_VERT_LINES);
+	ccdc->ccdc_ctx[VPFE_HSIZE_OFF >> 2] = vpfe_reg_read(ccdc,
+							    VPFE_HSIZE_OFF);
+}
+
+static int vpfe_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct vpfe_device *vpfe = platform_get_drvdata(pdev);
+	struct vpfe_ccdc *ccdc = &vpfe->ccdc;
+
+	/* if streaming has not started we don't care */
+	if (!vb2_start_streaming_called(&vpfe->buffer_queue))
+		return 0;
+
+	pm_runtime_get_sync(dev);
+	vpfe_config_enable(ccdc, 1);
+
+	/* Save VPFE context */
+	vpfe_save_context(ccdc);
+
+	/* Disable CCDC */
+	vpfe_pcr_enable(ccdc, 0);
+	vpfe_config_enable(ccdc, 0);
+
+	/* Disable both master and slave clock */
+	pm_runtime_put_sync(dev);
+
+	/* Select sleep pin state */
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+static void vpfe_restore_context(struct vpfe_ccdc *ccdc)
+{
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_SYNMODE >> 2], VPFE_SYNMODE);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_CULLING >> 2], VPFE_CULLING);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_SDOFST >> 2], VPFE_SDOFST);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_SDR_ADDR >> 2], VPFE_SDR_ADDR);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_CLAMP >> 2], VPFE_CLAMP);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_DCSUB >> 2], VPFE_DCSUB);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_COLPTN >> 2], VPFE_COLPTN);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_BLKCMP >> 2], VPFE_BLKCMP);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_VDINT >> 2], VPFE_VDINT);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_ALAW >> 2], VPFE_ALAW);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_REC656IF >> 2], VPFE_REC656IF);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_CCDCFG >> 2], VPFE_CCDCFG);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_PCR >> 2], VPFE_PCR);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_HD_VD_WID >> 2],
+						VPFE_HD_VD_WID);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_PIX_LINES >> 2],
+						VPFE_PIX_LINES);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_HORZ_INFO >> 2],
+						VPFE_HORZ_INFO);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_VERT_START >> 2],
+						VPFE_VERT_START);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_VERT_LINES >> 2],
+						VPFE_VERT_LINES);
+	vpfe_reg_write(ccdc, ccdc->ccdc_ctx[VPFE_HSIZE_OFF >> 2],
+						VPFE_HSIZE_OFF);
+}
+
+static int vpfe_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct vpfe_device *vpfe = platform_get_drvdata(pdev);
+	struct vpfe_ccdc *ccdc = &vpfe->ccdc;
+
+	/* if streaming has not started we don't care */
+	if (!vb2_start_streaming_called(&vpfe->buffer_queue))
+		return 0;
+
+	/* Enable both master and slave clock */
+	pm_runtime_get_sync(dev);
+	vpfe_config_enable(ccdc, 1);
+
+	/* Restore VPFE context */
+	vpfe_restore_context(ccdc);
+
+	vpfe_config_enable(ccdc, 0);
+	pm_runtime_put_sync(dev);
+
+	/* Select default pin state */
+	pinctrl_pm_select_default_state(dev);
+
+	return 0;
+}
+
+#endif
+
+static SIMPLE_DEV_PM_OPS(vpfe_pm_ops, vpfe_suspend, vpfe_resume);
+
+static const struct of_device_id vpfe_of_match[] = {
+	{ .compatible = "ti,am437x-vpfe", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, vpfe_of_match);
+
+static struct platform_driver vpfe_driver = {
+	.probe		= vpfe_probe,
+	.remove		= vpfe_remove,
+	.driver = {
+		.name	= VPFE_MODULE_NAME,
+		.owner	= THIS_MODULE,
+		.pm	= &vpfe_pm_ops,
+		.of_match_table = of_match_ptr(vpfe_of_match),
+	},
+};
+
+module_platform_driver(vpfe_driver);
+
+MODULE_AUTHOR("Texas Instruments");
+MODULE_DESCRIPTION("TI AM437x VPFE driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(VPFE_VERSION);
diff --git a/drivers/media/platform/am437x/am437x-vpfe.h b/drivers/media/platform/am437x/am437x-vpfe.h
new file mode 100644
index 00000000000..0f557352313
--- /dev/null
+++ b/drivers/media/platform/am437x/am437x-vpfe.h
@@ -0,0 +1,283 @@
+/*
+ * Copyright (C) 2013 - 2014 Texas Instruments, Inc.
+ *
+ * Benoit Parrot <bparrot@ti.com>
+ * Lad, Prabhakar <prabhakar.csengg@gmail.com>
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef AM437X_VPFE_H
+#define AM437X_VPFE_H
+
+#include <linux/am437x-vpfe.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/i2c.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "am437x-vpfe_regs.h"
+
+enum vpfe_pin_pol {
+	VPFE_PINPOL_POSITIVE = 0,
+	VPFE_PINPOL_NEGATIVE,
+};
+
+enum vpfe_hw_if_type {
+	/* Raw Bayer */
+	VPFE_RAW_BAYER = 0,
+	/* BT656 - 8 bit */
+	VPFE_BT656,
+	/* BT656 - 10 bit */
+	VPFE_BT656_10BIT,
+	/* YCbCr - 8 bit with external sync */
+	VPFE_YCBCR_SYNC_8,
+	/* YCbCr - 16 bit with external sync */
+	VPFE_YCBCR_SYNC_16,
+};
+
+/* interface description */
+struct vpfe_hw_if_param {
+	enum vpfe_hw_if_type if_type;
+	enum vpfe_pin_pol hdpol;
+	enum vpfe_pin_pol vdpol;
+	unsigned int bus_width;
+};
+
+#define VPFE_MAX_SUBDEV		1
+#define VPFE_MAX_INPUTS		1
+
+struct vpfe_pixel_format {
+	struct v4l2_fmtdesc fmtdesc;
+	/* bytes per pixel */
+	int bpp;
+};
+
+struct vpfe_std_info {
+	int active_pixels;
+	int active_lines;
+	/* current frame format */
+	int frame_format;
+};
+
+struct vpfe_route {
+	u32 input;
+	u32 output;
+};
+
+struct vpfe_subdev_info {
+	 char name[32];
+	/* Sub device group id */
+	int grp_id;
+	/* inputs available at the sub device */
+	struct v4l2_input inputs[VPFE_MAX_INPUTS];
+	/* Sub dev routing information for each input */
+	struct vpfe_route *routes;
+	/* check if sub dev supports routing */
+	int can_route;
+	/* ccdc bus/interface configuration */
+	struct vpfe_hw_if_param vpfe_param;
+	struct v4l2_subdev *sd;
+};
+
+struct vpfe_config {
+	/* information about each subdev */
+	struct vpfe_subdev_info sub_devs[VPFE_MAX_SUBDEV];
+	/* Flat array, arranged in groups */
+	struct v4l2_async_subdev *asd[VPFE_MAX_SUBDEV];
+};
+
+struct vpfe_cap_buffer {
+	struct vb2_buffer vb;
+	struct list_head list;
+};
+
+enum ccdc_pixfmt {
+	CCDC_PIXFMT_RAW = 0,
+	CCDC_PIXFMT_YCBCR_16BIT,
+	CCDC_PIXFMT_YCBCR_8BIT,
+};
+
+enum ccdc_frmfmt {
+	CCDC_FRMFMT_PROGRESSIVE = 0,
+	CCDC_FRMFMT_INTERLACED,
+};
+
+/* PIXEL ORDER IN MEMORY from LSB to MSB */
+/* only applicable for 8-bit input mode  */
+enum ccdc_pixorder {
+	CCDC_PIXORDER_YCBYCR,
+	CCDC_PIXORDER_CBYCRY,
+};
+
+enum ccdc_buftype {
+	CCDC_BUFTYPE_FLD_INTERLEAVED,
+	CCDC_BUFTYPE_FLD_SEPARATED
+};
+
+
+/* returns the highest bit used for the gamma */
+static inline u8 ccdc_gamma_width_max_bit(enum vpfe_ccdc_gamma_width width)
+{
+	return 15 - width;
+}
+
+/* returns the highest bit used for this data size */
+static inline u8 ccdc_data_size_max_bit(enum vpfe_ccdc_data_size sz)
+{
+	return sz == VPFE_CCDC_DATA_8BITS ? 7 : 15 - sz;
+}
+
+/* Structure for CCDC configuration parameters for raw capture mode */
+struct ccdc_params_raw {
+	/* pixel format */
+	enum ccdc_pixfmt pix_fmt;
+	/* progressive or interlaced frame */
+	enum ccdc_frmfmt frm_fmt;
+	struct v4l2_rect win;
+	/* Current Format Bytes Per Pixels */
+	unsigned int bytesperpixel;
+	/* Current Format Bytes per Lines
+	 * (Aligned to 32 bytes) used for HORZ_INFO
+	 */
+	unsigned int bytesperline;
+	/* field id polarity */
+	enum vpfe_pin_pol fid_pol;
+	/* vertical sync polarity */
+	enum vpfe_pin_pol vd_pol;
+	/* horizontal sync polarity */
+	enum vpfe_pin_pol hd_pol;
+	/* interleaved or separated fields */
+	enum ccdc_buftype buf_type;
+	/*
+	 * enable to store the image in inverse
+	 * order in memory(bottom to top)
+	 */
+	unsigned char image_invert_enable;
+	/* configurable parameters */
+	struct vpfe_ccdc_config_params_raw config_params;
+};
+
+struct ccdc_params_ycbcr {
+	/* pixel format */
+	enum ccdc_pixfmt pix_fmt;
+	/* progressive or interlaced frame */
+	enum ccdc_frmfmt frm_fmt;
+	struct v4l2_rect win;
+	/* Current Format Bytes Per Pixels */
+	unsigned int bytesperpixel;
+	/* Current Format Bytes per Lines
+	 * (Aligned to 32 bytes) used for HORZ_INFO
+	 */
+	unsigned int bytesperline;
+	/* field id polarity */
+	enum vpfe_pin_pol fid_pol;
+	/* vertical sync polarity */
+	enum vpfe_pin_pol vd_pol;
+	/* horizontal sync polarity */
+	enum vpfe_pin_pol hd_pol;
+	/* enable BT.656 embedded sync mode */
+	int bt656_enable;
+	/* cb:y:cr:y or y:cb:y:cr in memory */
+	enum ccdc_pixorder pix_order;
+	/* interleaved or separated fields  */
+	enum ccdc_buftype buf_type;
+};
+
+/*
+ * CCDC operational configuration
+ */
+struct ccdc_config {
+	/* CCDC interface type */
+	enum vpfe_hw_if_type if_type;
+	/* Raw Bayer configuration */
+	struct ccdc_params_raw bayer;
+	/* YCbCr configuration */
+	struct ccdc_params_ycbcr ycbcr;
+	/* ccdc base address */
+	void __iomem *base_addr;
+};
+
+struct vpfe_ccdc {
+	struct ccdc_config ccdc_cfg;
+	u32 ccdc_ctx[VPFE_REG_END / sizeof(u32)];
+};
+
+struct vpfe_device {
+	/* V4l2 specific parameters */
+	/* Identifies video device for this channel */
+	struct video_device *video_dev;
+	/* sub devices */
+	struct v4l2_subdev **sd;
+	/* vpfe cfg */
+	struct vpfe_config *cfg;
+	/* V4l2 device */
+	struct v4l2_device v4l2_dev;
+	/* parent device */
+	struct device *pdev;
+	/* subdevice async Notifier */
+	struct v4l2_async_notifier notifier;
+	/* Indicates id of the field which is being displayed */
+	unsigned field;
+	unsigned sequence;
+	/* current interface type */
+	struct vpfe_hw_if_param vpfe_if_params;
+	/* ptr to currently selected sub device */
+	struct vpfe_subdev_info *current_subdev;
+	/* current input at the sub device */
+	int current_input;
+	/* Keeps track of the information about the standard */
+	struct vpfe_std_info std_info;
+	/* std index into std table */
+	int std_index;
+	/* IRQs used when CCDC output to SDRAM */
+	unsigned int irq;
+	/* Pointer pointing to current v4l2_buffer */
+	struct vpfe_cap_buffer *cur_frm;
+	/* Pointer pointing to next v4l2_buffer */
+	struct vpfe_cap_buffer *next_frm;
+	/* Used to store pixel format */
+	struct v4l2_format fmt;
+	/* Used to store current bytes per pixel based on current format */
+	unsigned int bpp;
+	/*
+	 * used when IMP is chained to store the crop window which
+	 * is different from the image window
+	 */
+	struct v4l2_rect crop;
+	/* Buffer queue used in video-buf */
+	struct vb2_queue buffer_queue;
+	/* Allocator-specific contexts for each plane */
+	struct vb2_alloc_ctx *alloc_ctx;
+	/* Queue of filled frames */
+	struct list_head dma_queue;
+	/* IRQ lock for DMA queue */
+	spinlock_t dma_queue_lock;
+	/* lock used to access this structure */
+	struct mutex lock;
+	/*
+	 * offset where second field starts from the starting of the
+	 * buffer for field separated YCbCr formats
+	 */
+	u32 field_off;
+	struct vpfe_ccdc ccdc;
+};
+
+#endif	/* AM437X_VPFE_H */
diff --git a/drivers/media/platform/am437x/am437x-vpfe_regs.h b/drivers/media/platform/am437x/am437x-vpfe_regs.h
new file mode 100644
index 00000000000..4a0ed29723e
--- /dev/null
+++ b/drivers/media/platform/am437x/am437x-vpfe_regs.h
@@ -0,0 +1,140 @@
+/*
+ * TI AM437x Image Sensor Interface Registers
+ *
+ * Copyright (C) 2013 - 2014 Texas Instruments, Inc.
+ *
+ * Benoit Parrot <bparrot@ti.com>
+ * Lad, Prabhakar <prabhakar.csengg@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef AM437X_VPFE_REGS_H
+#define AM437X_VPFE_REGS_H
+
+/* VPFE module register offset */
+#define VPFE_REVISION				0x0
+#define VPFE_PCR				0x4
+#define VPFE_SYNMODE				0x8
+#define VPFE_HD_VD_WID				0xc
+#define VPFE_PIX_LINES				0x10
+#define VPFE_HORZ_INFO				0x14
+#define VPFE_VERT_START				0x18
+#define VPFE_VERT_LINES				0x1c
+#define VPFE_CULLING				0x20
+#define VPFE_HSIZE_OFF				0x24
+#define VPFE_SDOFST				0x28
+#define VPFE_SDR_ADDR				0x2c
+#define VPFE_CLAMP				0x30
+#define VPFE_DCSUB				0x34
+#define VPFE_COLPTN				0x38
+#define VPFE_BLKCMP				0x3c
+#define VPFE_VDINT				0x48
+#define VPFE_ALAW				0x4c
+#define VPFE_REC656IF				0x50
+#define VPFE_CCDCFG				0x54
+#define VPFE_DMA_CNTL				0x98
+#define VPFE_SYSCONFIG				0x104
+#define VPFE_CONFIG				0x108
+#define VPFE_IRQ_EOI				0x110
+#define VPFE_IRQ_STS_RAW			0x114
+#define VPFE_IRQ_STS				0x118
+#define VPFE_IRQ_EN_SET				0x11c
+#define VPFE_IRQ_EN_CLR				0x120
+#define VPFE_REG_END				0x124
+
+/* Define bit fields within selected registers */
+#define VPFE_FID_POL_MASK			1
+#define VPFE_FID_POL_SHIFT			4
+#define VPFE_HD_POL_MASK			1
+#define VPFE_HD_POL_SHIFT			3
+#define VPFE_VD_POL_MASK			1
+#define VPFE_VD_POL_SHIFT			2
+#define VPFE_HSIZE_OFF_MASK			0xffffffe0
+#define VPFE_32BYTE_ALIGN_VAL			31
+#define VPFE_FRM_FMT_MASK			0x1
+#define VPFE_FRM_FMT_SHIFT			7
+#define VPFE_DATA_SZ_MASK			7
+#define VPFE_DATA_SZ_SHIFT			8
+#define VPFE_PIX_FMT_MASK			3
+#define VPFE_PIX_FMT_SHIFT			12
+#define VPFE_VP2SDR_DISABLE			0xfffbffff
+#define VPFE_WEN_ENABLE				(1 << 17)
+#define VPFE_SDR2RSZ_DISABLE			0xfff7ffff
+#define VPFE_VDHDEN_ENABLE			(1 << 16)
+#define VPFE_LPF_ENABLE				(1 << 14)
+#define VPFE_ALAW_ENABLE			(1 << 3)
+#define VPFE_ALAW_GAMMA_WD_MASK			7
+#define VPFE_BLK_CLAMP_ENABLE			(1 << 31)
+#define VPFE_BLK_SGAIN_MASK			0x1f
+#define VPFE_BLK_ST_PXL_MASK			0x7fff
+#define VPFE_BLK_ST_PXL_SHIFT			10
+#define VPFE_BLK_SAMPLE_LN_MASK			7
+#define VPFE_BLK_SAMPLE_LN_SHIFT		28
+#define VPFE_BLK_SAMPLE_LINE_MASK		7
+#define VPFE_BLK_SAMPLE_LINE_SHIFT		25
+#define VPFE_BLK_DC_SUB_MASK			0x03fff
+#define VPFE_BLK_COMP_MASK			0xff
+#define VPFE_BLK_COMP_GB_COMP_SHIFT		8
+#define VPFE_BLK_COMP_GR_COMP_SHIFT		16
+#define VPFE_BLK_COMP_R_COMP_SHIFT		24
+#define VPFE_LATCH_ON_VSYNC_DISABLE		(1 << 15)
+#define VPFE_DATA_PACK_ENABLE			(1 << 11)
+#define VPFE_HORZ_INFO_SPH_SHIFT		16
+#define VPFE_VERT_START_SLV0_SHIFT		16
+#define VPFE_VDINT_VDINT0_SHIFT			16
+#define VPFE_VDINT_VDINT1_MASK			0xffff
+#define VPFE_PPC_RAW				1
+#define VPFE_DCSUB_DEFAULT_VAL			0
+#define VPFE_CLAMP_DEFAULT_VAL			0
+#define VPFE_COLPTN_VAL				0xbb11bb11
+#define VPFE_TWO_BYTES_PER_PIXEL		2
+#define VPFE_INTERLACED_IMAGE_INVERT		0x4b6d
+#define VPFE_INTERLACED_NO_IMAGE_INVERT		0x0249
+#define VPFE_PROGRESSIVE_IMAGE_INVERT		0x4000
+#define VPFE_PROGRESSIVE_NO_IMAGE_INVERT	0
+#define VPFE_INTERLACED_HEIGHT_SHIFT		1
+#define VPFE_SYN_MODE_INPMOD_SHIFT		12
+#define VPFE_SYN_MODE_INPMOD_MASK		3
+#define VPFE_SYN_MODE_8BITS			(7 << 8)
+#define VPFE_SYN_MODE_10BITS			(6 << 8)
+#define VPFE_SYN_MODE_11BITS			(5 << 8)
+#define VPFE_SYN_MODE_12BITS			(4 << 8)
+#define VPFE_SYN_MODE_13BITS			(3 << 8)
+#define VPFE_SYN_MODE_14BITS			(2 << 8)
+#define VPFE_SYN_MODE_15BITS			(1 << 8)
+#define VPFE_SYN_MODE_16BITS			(0 << 8)
+#define VPFE_SYN_FLDMODE_MASK			1
+#define VPFE_SYN_FLDMODE_SHIFT			7
+#define VPFE_REC656IF_BT656_EN			3
+#define VPFE_SYN_MODE_VD_POL_NEGATIVE		(1 << 2)
+#define VPFE_CCDCFG_Y8POS_SHIFT			11
+#define VPFE_CCDCFG_BW656_10BIT			(1 << 5)
+#define VPFE_SDOFST_FIELD_INTERLEAVED		0x249
+#define VPFE_NO_CULLING				0xffff00ff
+#define VPFE_VDINT0				(1 << 0)
+#define VPFE_VDINT1				(1 << 1)
+#define VPFE_VDINT2				(1 << 2)
+#define VPFE_DMA_CNTL_OVERFLOW			(1 << 31)
+
+#define VPFE_CONFIG_PCLK_INV_SHIFT		0
+#define VPFE_CONFIG_PCLK_INV_MASK		1
+#define VPFE_CONFIG_PCLK_INV_NOT_INV		0
+#define VPFE_CONFIG_PCLK_INV_INV		1
+#define VPFE_CONFIG_EN_SHIFT			1
+#define VPFE_CONFIG_EN_MASK			2
+#define VPFE_CONFIG_EN_DISABLE			0
+#define VPFE_CONFIG_EN_ENABLE			1
+#define VPFE_CONFIG_ST_SHIFT			2
+#define VPFE_CONFIG_ST_MASK			4
+#define VPFE_CONFIG_ST_OCP_ACTIVE		0
+#define VPFE_CONFIG_ST_OCP_STANDBY		1
+
+#endif		/* AM437X_VPFE_REGS_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 00b100023c4..9312d580654 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -35,6 +35,7 @@ header-y += adfs_fs.h
 header-y += affs_hardblocks.h
 header-y += agpgart.h
 header-y += aio_abi.h
+header-y += am437x-vpfe.h
 header-y += apm_bios.h
 header-y += arcfb.h
 header-y += atalk.h
diff --git a/include/uapi/linux/am437x-vpfe.h b/include/uapi/linux/am437x-vpfe.h
new file mode 100644
index 00000000000..9b03033f9cd
--- /dev/null
+++ b/include/uapi/linux/am437x-vpfe.h
@@ -0,0 +1,122 @@
+/*
+ * Copyright (C) 2013 - 2014 Texas Instruments, Inc.
+ *
+ * Benoit Parrot <bparrot@ti.com>
+ * Lad, Prabhakar <prabhakar.csengg@gmail.com>
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef AM437X_VPFE_USER_H
+#define AM437X_VPFE_USER_H
+
+enum vpfe_ccdc_data_size {
+	VPFE_CCDC_DATA_16BITS = 0,
+	VPFE_CCDC_DATA_15BITS,
+	VPFE_CCDC_DATA_14BITS,
+	VPFE_CCDC_DATA_13BITS,
+	VPFE_CCDC_DATA_12BITS,
+	VPFE_CCDC_DATA_11BITS,
+	VPFE_CCDC_DATA_10BITS,
+	VPFE_CCDC_DATA_8BITS,
+};
+
+/* enum for No of pixel per line to be avg. in Black Clamping*/
+enum vpfe_ccdc_sample_length {
+	VPFE_CCDC_SAMPLE_1PIXELS = 0,
+	VPFE_CCDC_SAMPLE_2PIXELS,
+	VPFE_CCDC_SAMPLE_4PIXELS,
+	VPFE_CCDC_SAMPLE_8PIXELS,
+	VPFE_CCDC_SAMPLE_16PIXELS,
+};
+
+/* enum for No of lines in Black Clamping */
+enum vpfe_ccdc_sample_line {
+	VPFE_CCDC_SAMPLE_1LINES = 0,
+	VPFE_CCDC_SAMPLE_2LINES,
+	VPFE_CCDC_SAMPLE_4LINES,
+	VPFE_CCDC_SAMPLE_8LINES,
+	VPFE_CCDC_SAMPLE_16LINES,
+};
+
+/* enum for Alaw gamma width */
+enum vpfe_ccdc_gamma_width {
+	VPFE_CCDC_GAMMA_BITS_15_6 = 0,	/* use bits 15-6 for gamma */
+	VPFE_CCDC_GAMMA_BITS_14_5,
+	VPFE_CCDC_GAMMA_BITS_13_4,
+	VPFE_CCDC_GAMMA_BITS_12_3,
+	VPFE_CCDC_GAMMA_BITS_11_2,
+	VPFE_CCDC_GAMMA_BITS_10_1,
+	VPFE_CCDC_GAMMA_BITS_09_0,	/* use bits 9-0 for gamma */
+};
+
+/* structure for ALaw */
+struct vpfe_ccdc_a_law {
+	/* Enable/disable A-Law */
+	unsigned char enable;
+	/* Gamma Width Input */
+	enum vpfe_ccdc_gamma_width gamma_wd;
+};
+
+/* structure for Black Clamping */
+struct vpfe_ccdc_black_clamp {
+	unsigned char enable;
+	/* only if bClampEnable is TRUE */
+	enum vpfe_ccdc_sample_length sample_pixel;
+	/* only if bClampEnable is TRUE */
+	enum vpfe_ccdc_sample_line sample_ln;
+	/* only if bClampEnable is TRUE */
+	unsigned short start_pixel;
+	/* only if bClampEnable is TRUE */
+	unsigned short sgain;
+	/* only if bClampEnable is FALSE */
+	unsigned short dc_sub;
+};
+
+/* structure for Black Level Compensation */
+struct vpfe_ccdc_black_compensation {
+	/* Constant value to subtract from Red component */
+	char r;
+	/* Constant value to subtract from Gr component */
+	char gr;
+	/* Constant value to subtract from Blue component */
+	char b;
+	/* Constant value to subtract from Gb component */
+	char gb;
+};
+
+/* Structure for CCDC configuration parameters for raw capture mode passed
+ * by application
+ */
+struct vpfe_ccdc_config_params_raw {
+	/* data size value from 8 to 16 bits */
+	enum vpfe_ccdc_data_size data_sz;
+	/* Structure for Optional A-Law */
+	struct vpfe_ccdc_a_law alaw;
+	/* Structure for Optical Black Clamp */
+	struct vpfe_ccdc_black_clamp blk_clamp;
+	/* Structure for Black Compensation */
+	struct vpfe_ccdc_black_compensation blk_comp;
+};
+
+/*
+ *  Private IOCTL
+ * VIDIOC_AM437X_CCDC_CFG - Set CCDC configuration for raw capture
+ * This is an experimental ioctl that will change in future kernels. So use
+ * this ioctl with care !
+ **/
+#define VIDIOC_AM437X_CCDC_CFG \
+	_IOW('V', BASE_VIDIOC_PRIVATE + 1, void *)
+
+#endif		/* AM437X_VPFE_USER_H */
-- 
cgit v1.2.3-70-g09d2


From 3110628d89f80fbafa085fd62e75afcb39fb764c Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Fri, 19 Dec 2014 17:15:53 +0900
Subject: spi: sh-msiof: Configure MSIOF sync signal timing in device tree

The MSIOF controller has DTDL and SYNCDL in SITMDR1 register. So,
this patch adds new properties like the following commit:
  d0fb47a5237d8b9576113568bacfd27892308b62
  (spi: fsl-espi: Configure FSL eSPI CSBEF and CSAFT)

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/spi/sh-msiof.txt | 16 ++++++++
 drivers/spi/spi-sh-msiof.c                         | 47 ++++++++++++++++++++++
 include/linux/spi/sh_msiof.h                       |  2 +
 3 files changed, 65 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index d11c3721e7c..4c388bb2f0a 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -30,6 +30,22 @@ Optional properties:
 			 specifiers, one for transmission, and one for
 			 reception.
 - dma-names            : Must contain a list of two DMA names, "tx" and "rx".
+- renesas,dtdl         : delay sync signal (setup) in transmit mode.
+			 Must contain one of the following values:
+			 0   (no bit delay)
+			 50  (0.5-clock-cycle delay)
+			 100 (1-clock-cycle delay)
+			 150 (1.5-clock-cycle delay)
+			 200 (2-clock-cycle delay)
+
+- renesas,syncdl       : delay sync signal (hold) in transmit mode.
+			 Must contain one of the following values:
+			 0   (no bit delay)
+			 50  (0.5-clock-cycle delay)
+			 100 (1-clock-cycle delay)
+			 150 (1.5-clock-cycle delay)
+			 200 (2-clock-cycle delay)
+			 300 (3-clock-cycle delay)
 
 Optional properties, deprecated for soctype-specific bindings:
 - renesas,tx-fifo-size : Overrides the default tx fifo size given in words
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 239be7cbe5a..2a87cb939f5 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -82,6 +82,8 @@ struct sh_msiof_spi_priv {
 #define MDR1_SYNCMD_LR	 0x30000000 /*   L/R mode */
 #define MDR1_SYNCAC_SHIFT	 25 /* Sync Polarity (1 = Active-low) */
 #define MDR1_BITLSB_SHIFT	 24 /* MSB/LSB First (1 = LSB first) */
+#define MDR1_DTDL_SHIFT		 20 /* Data Pin Bit Delay for MSIOF_SYNC */
+#define MDR1_SYNCDL_SHIFT	 16 /* Frame Sync Signal Timing Delay */
 #define MDR1_FLD_MASK	 0x000000c0 /* Frame Sync Signal Interval (0-3) */
 #define MDR1_FLD_SHIFT		  2
 #define MDR1_XXSTP	 0x00000001 /* Transmission/Reception Stop on FIFO */
@@ -279,6 +281,48 @@ static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
 		sh_msiof_write(p, RSCR, sh_msiof_spi_clk_table[k].scr);
 }
 
+static u32 sh_msiof_get_delay_bit(u32 dtdl_or_syncdl)
+{
+	/*
+	 * DTDL/SYNCDL bit	: p->info->dtdl or p->info->syncdl
+	 * b'000		: 0
+	 * b'001		: 100
+	 * b'010		: 200
+	 * b'011 (SYNCDL only)	: 300
+	 * b'101		: 50
+	 * b'110		: 150
+	 */
+	if (dtdl_or_syncdl % 100)
+		return dtdl_or_syncdl / 100 + 5;
+	else
+		return dtdl_or_syncdl / 100;
+}
+
+static u32 sh_msiof_spi_get_dtdl_and_syncdl(struct sh_msiof_spi_priv *p)
+{
+	u32 val;
+
+	if (!p->info)
+		return 0;
+
+	/* check if DTDL and SYNCDL is allowed value */
+	if (p->info->dtdl > 200 || p->info->syncdl > 300) {
+		dev_warn(&p->pdev->dev, "DTDL or SYNCDL is too large\n");
+		return 0;
+	}
+
+	/* check if the sum of DTDL and SYNCDL becomes an integer value  */
+	if ((p->info->dtdl + p->info->syncdl) % 100) {
+		dev_warn(&p->pdev->dev, "the sum of DTDL/SYNCDL is not good\n");
+		return 0;
+	}
+
+	val = sh_msiof_get_delay_bit(p->info->dtdl) << MDR1_DTDL_SHIFT;
+	val |= sh_msiof_get_delay_bit(p->info->syncdl) << MDR1_SYNCDL_SHIFT;
+
+	return val;
+}
+
 static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p,
 				      u32 cpol, u32 cpha,
 				      u32 tx_hi_z, u32 lsb_first, u32 cs_high)
@@ -296,6 +340,7 @@ static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p,
 	tmp = MDR1_SYNCMD_SPI | 1 << MDR1_FLD_SHIFT | MDR1_XXSTP;
 	tmp |= !cs_high << MDR1_SYNCAC_SHIFT;
 	tmp |= lsb_first << MDR1_BITLSB_SHIFT;
+	tmp |= sh_msiof_spi_get_dtdl_and_syncdl(p);
 	sh_msiof_write(p, TMDR1, tmp | MDR1_TRMD | TMDR1_PCON);
 	if (p->chipdata->master_flags & SPI_MASTER_MUST_TX) {
 		/* These bits are reserved if RX needs TX */
@@ -952,6 +997,8 @@ static struct sh_msiof_spi_info *sh_msiof_spi_parse_dt(struct device *dev)
 					&info->tx_fifo_override);
 	of_property_read_u32(np, "renesas,rx-fifo-size",
 					&info->rx_fifo_override);
+	of_property_read_u32(np, "renesas,dtdl", &info->dtdl);
+	of_property_read_u32(np, "renesas,syncdl", &info->syncdl);
 
 	info->num_chipselect = num_cs;
 
diff --git a/include/linux/spi/sh_msiof.h b/include/linux/spi/sh_msiof.h
index 88a14d81c49..b087a85f5f7 100644
--- a/include/linux/spi/sh_msiof.h
+++ b/include/linux/spi/sh_msiof.h
@@ -7,6 +7,8 @@ struct sh_msiof_spi_info {
 	u16 num_chipselect;
 	unsigned int dma_tx_id;
 	unsigned int dma_rx_id;
+	u32 dtdl;
+	u32 syncdl;
 };
 
 #endif /* __SPI_SH_MSIOF_H__ */
-- 
cgit v1.2.3-70-g09d2


From 0425e2420c0ab1b5da24f6d9fce39241ad85fc46 Mon Sep 17 00:00:00 2001
From: Flora Fu <flora.fu@mediatek.com>
Date: Fri, 5 Dec 2014 12:07:54 +0800
Subject: regulator: mt6397: Add support for MT6397 regulator

Add MT6397 regulator driver.

Signed-off-by: Flora Fu <flora.fu@mediatek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig                  |   9 +
 drivers/regulator/Makefile                 |   1 +
 drivers/regulator/mt6397-regulator.c       | 332 +++++++++++++++++++++++++++++
 include/linux/regulator/mt6397-regulator.h |  49 +++++
 4 files changed, 391 insertions(+)
 create mode 100644 drivers/regulator/mt6397-regulator.c
 create mode 100644 include/linux/regulator/mt6397-regulator.h

(limited to 'include')

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index c3a60b57a86..f622d0613d2 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -433,6 +433,15 @@ config REGULATOR_MC13892
 	  Say y here to support the regulators found on the Freescale MC13892
 	  PMIC.
 
+config REGULATOR_MT6397
+	tristate "MediaTek MT6397 PMIC"
+	depends on MFD_MT6397
+	help
+	  Say y here to select this option to enable the power regulator of
+	  MediaTek MT6397 PMIC.
+	  This driver supports the control of different power rails of device
+	  through regulator interface.
+
 config REGULATOR_PALMAS
 	tristate "TI Palmas PMIC Regulators"
 	depends on MFD_PALMAS
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 1f28ebfc6f3..1a0fbc397de 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -58,6 +58,7 @@ obj-$(CONFIG_REGULATOR_MAX77802) += max77802.o
 obj-$(CONFIG_REGULATOR_MC13783) += mc13783-regulator.o
 obj-$(CONFIG_REGULATOR_MC13892) += mc13892-regulator.o
 obj-$(CONFIG_REGULATOR_MC13XXX_CORE) +=  mc13xxx-regulator-core.o
+obj-$(CONFIG_REGULATOR_MT6397)	+= mt6397-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o
 obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o
 obj-$(CONFIG_REGULATOR_PFUZE100) += pfuze100-regulator.o
diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c
new file mode 100644
index 00000000000..a5b2f476267
--- /dev/null
+++ b/drivers/regulator/mt6397-regulator.c
@@ -0,0 +1,332 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Flora Fu <flora.fu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/mt6397/core.h>
+#include <linux/mfd/mt6397/registers.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/mt6397-regulator.h>
+#include <linux/regulator/of_regulator.h>
+
+/*
+ * MT6397 regulators' information
+ *
+ * @desc: standard fields of regulator description.
+ * @qi: Mask for query enable signal status of regulators
+ * @vselon_reg: Register sections for hardware control mode of bucks
+ * @vselctrl_reg: Register for controlling the buck control mode.
+ * @vselctrl_mask: Mask for query buck's voltage control mode.
+ */
+struct mt6397_regulator_info {
+	struct regulator_desc desc;
+	u32 qi;
+	u32 vselon_reg;
+	u32 vselctrl_reg;
+	u32 vselctrl_mask;
+};
+
+#define MT6397_BUCK(match, vreg, min, max, step, volt_ranges, enreg,	\
+		vosel, vosel_mask, voselon, vosel_ctrl)			\
+[MT6397_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6397_volt_range_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6397_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = (max - min)/step + 1,			\
+		.linear_ranges = volt_ranges,				\
+		.n_linear_ranges = ARRAY_SIZE(volt_ranges),		\
+		.vsel_reg = vosel,					\
+		.vsel_mask = vosel_mask,				\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(0),					\
+	},								\
+	.qi = BIT(13),							\
+	.vselon_reg = voselon,						\
+	.vselctrl_reg = vosel_ctrl,					\
+	.vselctrl_mask = BIT(1),					\
+}
+
+#define MT6397_LDO(match, vreg, ldo_volt_table, enreg, enbit, vosel,	\
+		vosel_mask)						\
+[MT6397_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6397_volt_table_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6397_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = ARRAY_SIZE(ldo_volt_table),		\
+		.volt_table = ldo_volt_table,				\
+		.vsel_reg = vosel,					\
+		.vsel_mask = vosel_mask,				\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(enbit),				\
+	},								\
+	.qi = BIT(15),							\
+}
+
+#define MT6397_REG_FIXED(match, vreg, enreg, enbit, volt)		\
+[MT6397_ID_##vreg] = {							\
+	.desc = {							\
+		.name = #vreg,						\
+		.of_match = of_match_ptr(match),			\
+		.ops = &mt6397_volt_fixed_ops,				\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = MT6397_ID_##vreg,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = 1,					\
+		.enable_reg = enreg,					\
+		.enable_mask = BIT(enbit),				\
+		.min_uV = volt,						\
+	},								\
+	.qi = BIT(15),							\
+}
+
+static const struct regulator_linear_range buck_volt_range1[] = {
+	REGULATOR_LINEAR_RANGE(700000, 0, 0x7f, 6250),
+};
+
+static const struct regulator_linear_range buck_volt_range2[] = {
+	REGULATOR_LINEAR_RANGE(800000, 0, 0x7f, 6250),
+};
+
+static const struct regulator_linear_range buck_volt_range3[] = {
+	REGULATOR_LINEAR_RANGE(1500000, 0, 0x1f, 20000),
+};
+
+static const u32 ldo_volt_table1[] = {
+	1500000, 1800000, 2500000, 2800000,
+};
+
+static const u32 ldo_volt_table2[] = {
+	1800000, 3300000,
+};
+
+static const u32 ldo_volt_table3[] = {
+	3000000, 3300000,
+};
+
+static const u32 ldo_volt_table4[] = {
+	1220000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static const u32 ldo_volt_table5[] = {
+	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static const u32 ldo_volt_table5_v2[] = {
+	1200000, 1000000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static const u32 ldo_volt_table6[] = {
+	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 2000000,
+};
+
+static const u32 ldo_volt_table7[] = {
+	1300000, 1500000, 1800000, 2000000, 2500000, 2800000, 3000000, 3300000,
+};
+
+static int mt6397_get_status(struct regulator_dev *rdev)
+{
+	int ret;
+	u32 regval;
+	struct mt6397_regulator_info *info = rdev_get_drvdata(rdev);
+
+	ret = regmap_read(rdev->regmap, info->desc.enable_reg, &regval);
+	if (ret != 0) {
+		dev_err(&rdev->dev, "Failed to get enable reg: %d\n", ret);
+		return ret;
+	}
+
+	return (regval & info->qi) ? REGULATOR_STATUS_ON : REGULATOR_STATUS_OFF;
+}
+
+static struct regulator_ops mt6397_volt_range_ops = {
+	.list_voltage = regulator_list_voltage_linear_range,
+	.map_voltage = regulator_map_voltage_linear_range,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6397_get_status,
+};
+
+static struct regulator_ops mt6397_volt_table_ops = {
+	.list_voltage = regulator_list_voltage_table,
+	.map_voltage = regulator_map_voltage_iterate,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6397_get_status,
+};
+
+static struct regulator_ops mt6397_volt_fixed_ops = {
+	.list_voltage = regulator_list_voltage_linear,
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.get_status = mt6397_get_status,
+};
+
+/* The array is indexed by id(MT6397_ID_XXX) */
+static struct mt6397_regulator_info mt6397_regulators[] = {
+	MT6397_BUCK("buck_vpca15", VPCA15, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VCA15_CON7, MT6397_VCA15_CON9, 0x7f,
+		MT6397_VCA15_CON10, MT6397_VCA15_CON5),
+	MT6397_BUCK("buck_vpca7", VPCA7, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VPCA7_CON7, MT6397_VPCA7_CON9, 0x7f,
+		MT6397_VPCA7_CON10, MT6397_VPCA7_CON5),
+	MT6397_BUCK("buck_vsramca15", VSRAMCA15, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VSRMCA15_CON7, MT6397_VSRMCA15_CON9,
+		0x7f, MT6397_VSRMCA15_CON10, MT6397_VSRMCA15_CON5),
+	MT6397_BUCK("buck_vsramca7", VSRAMCA7, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VSRMCA7_CON7, MT6397_VSRMCA7_CON9,
+		0x7f, MT6397_VSRMCA7_CON10, MT6397_VSRMCA7_CON5),
+	MT6397_BUCK("buck_vcore", VCORE, 700000, 1493750, 6250,
+		buck_volt_range1, MT6397_VCORE_CON7, MT6397_VCORE_CON9, 0x7f,
+		MT6397_VCORE_CON10, MT6397_VCORE_CON5),
+	MT6397_BUCK("buck_vgpu", VGPU, 700000, 1493750, 6250, buck_volt_range1,
+		MT6397_VGPU_CON7, MT6397_VGPU_CON9, 0x7f,
+		MT6397_VGPU_CON10, MT6397_VGPU_CON5),
+	MT6397_BUCK("buck_vdrm", VDRM, 800000, 1593750, 6250, buck_volt_range2,
+		MT6397_VDRM_CON7, MT6397_VDRM_CON9, 0x7f,
+		MT6397_VDRM_CON10, MT6397_VDRM_CON5),
+	MT6397_BUCK("buck_vio18", VIO18, 1500000, 2120000, 20000,
+		buck_volt_range3, MT6397_VIO18_CON7, MT6397_VIO18_CON9, 0x1f,
+		MT6397_VIO18_CON10, MT6397_VIO18_CON5),
+	MT6397_REG_FIXED("ldo_vtcxo", VTCXO, MT6397_ANALDO_CON0, 10, 2800000),
+	MT6397_REG_FIXED("ldo_va28", VA28, MT6397_ANALDO_CON1, 14, 2800000),
+	MT6397_LDO("ldo_vcama", VCAMA, ldo_volt_table1,
+		MT6397_ANALDO_CON2, 15, MT6397_ANALDO_CON6, 0xC0),
+	MT6397_REG_FIXED("ldo_vio28", VIO28, MT6397_DIGLDO_CON0, 14, 2800000),
+	MT6397_REG_FIXED("ldo_vusb", VUSB, MT6397_DIGLDO_CON1, 14, 3300000),
+	MT6397_LDO("ldo_vmc", VMC, ldo_volt_table2,
+		MT6397_DIGLDO_CON2, 12, MT6397_DIGLDO_CON29, 0x10),
+	MT6397_LDO("ldo_vmch", VMCH, ldo_volt_table3,
+		MT6397_DIGLDO_CON3, 14, MT6397_DIGLDO_CON17, 0x80),
+	MT6397_LDO("ldo_vemc3v3", VEMC3V3, ldo_volt_table3,
+		MT6397_DIGLDO_CON4, 14, MT6397_DIGLDO_CON18, 0x10),
+	MT6397_LDO("ldo_vgp1", VGP1, ldo_volt_table4,
+		MT6397_DIGLDO_CON5, 15, MT6397_DIGLDO_CON19, 0xE0),
+	MT6397_LDO("ldo_vgp2", VGP2, ldo_volt_table5,
+		MT6397_DIGLDO_CON6, 15, MT6397_DIGLDO_CON20, 0xE0),
+	MT6397_LDO("ldo_vgp3", VGP3, ldo_volt_table5,
+		MT6397_DIGLDO_CON7, 15, MT6397_DIGLDO_CON21, 0xE0),
+	MT6397_LDO("ldo_vgp4", VGP4, ldo_volt_table5,
+		MT6397_DIGLDO_CON8, 15, MT6397_DIGLDO_CON22, 0xE0),
+	MT6397_LDO("ldo_vgp5", VGP5, ldo_volt_table6,
+		MT6397_DIGLDO_CON9, 15, MT6397_DIGLDO_CON23, 0xE0),
+	MT6397_LDO("ldo_vgp6", VGP6, ldo_volt_table5,
+		MT6397_DIGLDO_CON10, 15, MT6397_DIGLDO_CON33, 0xE0),
+	MT6397_LDO("ldo_vibr", VIBR, ldo_volt_table7,
+		MT6397_DIGLDO_CON24, 15, MT6397_DIGLDO_CON25, 0xE00),
+};
+
+static int mt6397_set_buck_vosel_reg(struct platform_device *pdev)
+{
+	struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent);
+	int i;
+	u32 regval;
+
+	for (i = 0; i < MT6397_MAX_REGULATOR; i++) {
+		if (mt6397_regulators[i].vselctrl_reg) {
+			if (regmap_read(mt6397->regmap,
+				mt6397_regulators[i].vselctrl_reg,
+				&regval) < 0) {
+				dev_err(&pdev->dev,
+					"Failed to read buck ctrl\n");
+				return -EIO;
+			}
+
+			if (regval & mt6397_regulators[i].vselctrl_mask) {
+				mt6397_regulators[i].desc.vsel_reg =
+				mt6397_regulators[i].vselon_reg;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int mt6397_regulator_probe(struct platform_device *pdev)
+{
+	struct mt6397_chip *mt6397 = dev_get_drvdata(pdev->dev.parent);
+	struct regulator_config config = {};
+	struct regulator_dev *rdev;
+	int i;
+	u32 reg_value, version;
+
+	/* Query buck controller to select activated voltage register part */
+	if (mt6397_set_buck_vosel_reg(pdev))
+		return -EIO;
+
+	/* Read PMIC chip revision to update constraints and voltage table */
+	if (regmap_read(mt6397->regmap, MT6397_CID, &reg_value) < 0) {
+		dev_err(&pdev->dev, "Failed to read Chip ID\n");
+		return -EIO;
+	}
+	dev_info(&pdev->dev, "Chip ID = 0x%x\n", reg_value);
+
+	version = (reg_value & 0xFF);
+	switch (version) {
+	case MT6397_REGULATOR_ID91:
+		mt6397_regulators[MT6397_ID_VGP2].desc.volt_table =
+		ldo_volt_table5_v2;
+		break;
+	default:
+		break;
+	}
+
+	for (i = 0; i < MT6397_MAX_REGULATOR; i++) {
+		config.dev = &pdev->dev;
+		config.driver_data = &mt6397_regulators[i];
+		config.regmap = mt6397->regmap;
+		rdev = devm_regulator_register(&pdev->dev,
+				&mt6397_regulators[i].desc, &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to register %s\n",
+				mt6397_regulators[i].desc.name);
+			return PTR_ERR(rdev);
+		}
+	}
+
+	return 0;
+}
+
+static struct platform_driver mt6397_regulator_driver = {
+	.driver = {
+		.name = "mt6397-regulator",
+	},
+	.probe = mt6397_regulator_probe,
+};
+
+module_platform_driver(mt6397_regulator_driver);
+
+MODULE_AUTHOR("Flora Fu <flora.fu@mediatek.com>");
+MODULE_DESCRIPTION("Regulator Driver for MediaTek MT6397 PMIC");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mt6397-regulator");
diff --git a/include/linux/regulator/mt6397-regulator.h b/include/linux/regulator/mt6397-regulator.h
new file mode 100644
index 00000000000..30cc5963e26
--- /dev/null
+++ b/include/linux/regulator/mt6397-regulator.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright (c) 2014 MediaTek Inc.
+ * Author: Flora Fu <flora.fu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_REGULATOR_MT6397_H
+#define __LINUX_REGULATOR_MT6397_H
+
+enum {
+	MT6397_ID_VPCA15 = 0,
+	MT6397_ID_VPCA7,
+	MT6397_ID_VSRAMCA15,
+	MT6397_ID_VSRAMCA7,
+	MT6397_ID_VCORE,
+	MT6397_ID_VGPU,
+	MT6397_ID_VDRM,
+	MT6397_ID_VIO18 = 7,
+	MT6397_ID_VTCXO,
+	MT6397_ID_VA28,
+	MT6397_ID_VCAMA,
+	MT6397_ID_VIO28,
+	MT6397_ID_VUSB,
+	MT6397_ID_VMC,
+	MT6397_ID_VMCH,
+	MT6397_ID_VEMC3V3,
+	MT6397_ID_VGP1,
+	MT6397_ID_VGP2,
+	MT6397_ID_VGP3,
+	MT6397_ID_VGP4,
+	MT6397_ID_VGP5,
+	MT6397_ID_VGP6,
+	MT6397_ID_VIBR,
+	MT6397_ID_RG_MAX,
+};
+
+#define MT6397_MAX_REGULATOR	MT6397_ID_RG_MAX
+#define MT6397_REGULATOR_ID97	0x97
+#define MT6397_REGULATOR_ID91	0x91
+
+#endif /* __LINUX_REGULATOR_MT6397_H */
-- 
cgit v1.2.3-70-g09d2


From 0628ee7c81a8ced9b10f9ee300707f7f79fdecf1 Mon Sep 17 00:00:00 2001
From: Nicholas Krause <xerofoify@gmail.com>
Date: Sun, 21 Dec 2014 22:36:37 -0500
Subject: libata: s/ata_id_removeable()/ata_id_removable()/

Changes the spelling typos of removeable to removable where
ata_id_removeable is defined in ata.h and called in libata-scsi.c
respectively.

Signed-off-by: Nicholas Krause <xerofoify@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/libata-scsi.c | 4 ++--
 include/linux/ata.h       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index e364e86e84d..7659d646830 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1995,8 +1995,8 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
 
 	VPRINTK("ENTER\n");
 
-	/* set scsi removeable (RMB) bit per ata bit */
-	if (ata_id_removeable(args->id))
+	/* set scsi removable (RMB) bit per ata bit */
+	if (ata_id_removable(args->id))
 		hdr[1] |= (1 << 7);
 
 	if (args->dev->class == ATA_DEV_ZAC) {
diff --git a/include/linux/ata.h b/include/linux/ata.h
index f2f4d8da97c..1648026e06b 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -503,7 +503,7 @@ struct ata_bmdma_prd {
 #define ata_id_has_dma(id)	((id)[ATA_ID_CAPABILITY] & (1 << 8))
 #define ata_id_has_ncq(id)	((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8))
 #define ata_id_queue_depth(id)	(((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1)
-#define ata_id_removeable(id)	((id)[ATA_ID_CONFIG] & (1 << 7))
+#define ata_id_removable(id)	((id)[ATA_ID_CONFIG] & (1 << 7))
 #define ata_id_has_atapi_AN(id)	\
 	((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \
 	  ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \
-- 
cgit v1.2.3-70-g09d2


From 711ffa78f4b23e25a6c91cb80be436a48b5e725d Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 26 Dec 2014 04:42:31 +0100
Subject: Bluetooth: Introduce HCI_QUIRK_BROKEN_LOCAL_COMMANDS constant

Some controllers advertise support for Bluetooth 1.2 specification,
but they do not support the HCI Read Local Supported Commands command.

If that is the case, then the driver can quirk the behavior and force
the core to skip this command. This will allow removing vendor specific
checks out of the core.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index f39926ee06f..1849a437f6e 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -102,6 +102,16 @@ enum {
 	 */
 	HCI_QUIRK_FIXUP_BUFFER_SIZE,
 
+	/* When this quirk is set, then the HCI Read Local Supported
+	 * Commands command is not supported. In general Bluetooth 1.2
+	 * and later controllers should support this command. However
+	 * some controllers indicate Bluetooth 1.2 support, but do
+	 * not support this command.
+	 *
+	 * This quirk must be set before hci_register_dev is called.
+	 */
+	HCI_QUIRK_BROKEN_LOCAL_COMMANDS,
+
 	/* When this quirk is set, then no stored link key handling
 	 * is performed. This is mainly due to the fact that the
 	 * HCI Delete Stored Link Key command is advertised, but
-- 
cgit v1.2.3-70-g09d2


From 26c0d8a415e5c4a01faf24165ec9dea821f6a908 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:38 +0100
Subject: ALSA: pcm_params: Remove unused add/sub functions

Those two functions are not used anywhere and also their name is a bit to
generic to be in a global header, so remove them.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm_params.h | 14 --------------
 1 file changed, 14 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index 6b1c78f05fa..15760f5f98e 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -325,20 +325,6 @@ static inline int snd_interval_eq(const struct snd_interval *i1, const struct sn
 		i1->max == i2->max && i1->openmax == i2->openmax;
 }
 
-static inline unsigned int add(unsigned int a, unsigned int b)
-{
-	if (a >= UINT_MAX - b)
-		return UINT_MAX;
-	return a + b;
-}
-
-static inline unsigned int sub(unsigned int a, unsigned int b)
-{
-	if (a > b)
-		return a - b;
-	return 0;
-}
-
 #define params_access(p) ((__force snd_pcm_access_t)\
 		snd_mask_min(hw_param_mask_c((p), SNDRV_PCM_HW_PARAM_ACCESS)))
 #define params_format(p) ((__force snd_pcm_format_t)\
-- 
cgit v1.2.3-70-g09d2


From b3a8c862cd33b97c920122248ed9931af546de54 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:39 +0100
Subject: ALSA: pcm: Remove unused SNDRV_PCM_IOCTL1_{FALSE,TRUE} defines

Both SNDRV_PCM_IOCTL1_FALSE and SNDRV_PCM_IOCTL1_TRUE are unused and have in
fact never been used (at least as far as the git history goes).

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index b429b73e875..3652c9439af 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -94,9 +94,6 @@ struct snd_pcm_ops {
 #define SNDRV_PCM_DEVICES	8
 #endif
 
-#define SNDRV_PCM_IOCTL1_FALSE		((void *)0)
-#define SNDRV_PCM_IOCTL1_TRUE		((void *)1)
-
 #define SNDRV_PCM_IOCTL1_RESET		0
 #define SNDRV_PCM_IOCTL1_INFO		1
 #define SNDRV_PCM_IOCTL1_CHANNEL_INFO	2
-- 
cgit v1.2.3-70-g09d2


From 744c2ad2f98965473880ef85cac2f8a8ca95959f Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:41 +0100
Subject: ALSA: pcm: Convert params_* mask helpers to static inline functions

Use static inline functions instead of macros for the remaining params_*()
helpers that have not been converted yet. This is slightly cleaner and
offers better type safety.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm_params.h | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index 15760f5f98e..bf51f2285c4 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -325,12 +325,24 @@ static inline int snd_interval_eq(const struct snd_interval *i1, const struct sn
 		i1->max == i2->max && i1->openmax == i2->openmax;
 }
 
-#define params_access(p) ((__force snd_pcm_access_t)\
-		snd_mask_min(hw_param_mask_c((p), SNDRV_PCM_HW_PARAM_ACCESS)))
-#define params_format(p) ((__force snd_pcm_format_t)\
-		snd_mask_min(hw_param_mask_c((p), SNDRV_PCM_HW_PARAM_FORMAT)))
-#define params_subformat(p) \
-	snd_mask_min(hw_param_mask_c((p), SNDRV_PCM_HW_PARAM_SUBFORMAT))
+static inline snd_pcm_access_t params_access(const struct snd_pcm_hw_params *p)
+{
+	return (__force snd_pcm_access_t)snd_mask_min(hw_param_mask_c(p,
+		SNDRV_PCM_HW_PARAM_ACCESS));
+}
+
+static inline snd_pcm_format_t params_format(const struct snd_pcm_hw_params *p)
+{
+	return (__force snd_pcm_format_t)snd_mask_min(hw_param_mask_c(p,
+		SNDRV_PCM_HW_PARAM_FORMAT));
+}
+
+static inline snd_pcm_subformat_t
+params_subformat(const struct snd_pcm_hw_params *p)
+{
+	return (__force snd_pcm_subformat_t)snd_mask_min(hw_param_mask_c(p,
+		SNDRV_PCM_HW_PARAM_SUBFORMAT));
+}
 
 static inline unsigned int
 params_period_bytes(const struct snd_pcm_hw_params *p)
-- 
cgit v1.2.3-70-g09d2


From 89827ca9dd6173da7dcc035653bea67fa6ac0cbf Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:42 +0100
Subject: ALSA: pcm: Add kernel doc for params_*() functions

Add kernel doc for the remaining undocumented params_*() functions.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm_params.h | 37 +++++++++++++++++++++++++++++++++----
 1 file changed, 33 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index bf51f2285c4..2e2169e4985 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -325,18 +325,30 @@ static inline int snd_interval_eq(const struct snd_interval *i1, const struct sn
 		i1->max == i2->max && i1->openmax == i2->openmax;
 }
 
+/**
+ * params_access - get the access type from the hw params
+ * @p: hw params
+ */
 static inline snd_pcm_access_t params_access(const struct snd_pcm_hw_params *p)
 {
 	return (__force snd_pcm_access_t)snd_mask_min(hw_param_mask_c(p,
 		SNDRV_PCM_HW_PARAM_ACCESS));
 }
 
+/**
+ * params_format - get the sample format from the hw params
+ * @p: hw params
+ */
 static inline snd_pcm_format_t params_format(const struct snd_pcm_hw_params *p)
 {
 	return (__force snd_pcm_format_t)snd_mask_min(hw_param_mask_c(p,
 		SNDRV_PCM_HW_PARAM_FORMAT));
 }
 
+/**
+ * params_subformat - get the sample subformat from the hw params
+ * @p: hw params
+ */
 static inline snd_pcm_subformat_t
 params_subformat(const struct snd_pcm_hw_params *p)
 {
@@ -344,6 +356,10 @@ params_subformat(const struct snd_pcm_hw_params *p)
 		SNDRV_PCM_HW_PARAM_SUBFORMAT));
 }
 
+/**
+ * params_period_bytes - get the period size (in bytes) from the hw params
+ * @p: hw params
+ */
 static inline unsigned int
 params_period_bytes(const struct snd_pcm_hw_params *p)
 {
@@ -352,14 +368,27 @@ params_period_bytes(const struct snd_pcm_hw_params *p)
 		params_channels(p)) / 8;
 }
 
-static inline int
-params_width(const struct snd_pcm_hw_params *p)
+/**
+ * params_width - get the number of bits of the sample format from the hw params
+ * @p: hw params
+ *
+ * This function returns the number of bits per sample that the selected sample
+ * format of the hw params has.
+ */
+static inline int params_width(const struct snd_pcm_hw_params *p)
 {
 	return snd_pcm_format_width(params_format(p));
 }
 
-static inline int
-params_physical_width(const struct snd_pcm_hw_params *p)
+/*
+ * params_physical_width - get the storage size of the sample format from the hw params
+ * @p: hw params
+ *
+ * This functions returns the number of bits per sample that the selected sample
+ * format of the hw params takes up in memory. This will be equal or larger than
+ * params_width().
+ */
+static inline int params_physical_width(const struct snd_pcm_hw_params *p)
 {
 	return snd_pcm_format_physical_width(params_format(p));
 }
-- 
cgit v1.2.3-70-g09d2


From cd9978f1d3dbb9596a7ab9c652cb0d9b355489b5 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:43 +0100
Subject: ALSA: pcm: Simplify params_period_bytes()

The hw_params struct has a parameter that contains the period size in bytes.
This can be used instead of deriving the value from other parameters. This
is similar to e.g. params_buffer_bytes()

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm_params.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index 2e2169e4985..042049bab0b 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -363,9 +363,7 @@ params_subformat(const struct snd_pcm_hw_params *p)
 static inline unsigned int
 params_period_bytes(const struct snd_pcm_hw_params *p)
 {
-	return (params_period_size(p) *
-		snd_pcm_format_physical_width(params_format(p)) *
-		params_channels(p)) / 8;
+	return hw_param_interval_c(p, SNDRV_PCM_HW_PARAM_PERIOD_BYTES)->min;
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 599ee3291ae88700749e2910a11d1c0f0532355e Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:44 +0100
Subject: ALSA: pcm: Use __ffs() instead of ffs() in snd_mask_min()

The difference between __ffs and ffs is that ffs will return a one based
index whereas __ffs will return a zero based index. Furthermore ffs will
check if the passed value is zero and return zero in that case, whereas
__ffs behavior is undefined if the passed parameter is 0.

Since we already check if the mask is 0 before calling ffs and also subtract
1 from the result __ffs is the better choice.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm_params.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index 042049bab0b..c99e20b0c4c 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -92,7 +92,7 @@ static inline unsigned int snd_mask_min(const struct snd_mask *mask)
 	int i;
 	for (i = 0; i < SNDRV_MASK_SIZE; i++) {
 		if (mask->bits[i])
-			return ffs(mask->bits[i]) - 1 + (i << 5);
+			return __ffs(mask->bits[i]) + (i << 5);
 	}
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From 757b037650c9ecca79a46ab744820b1b3c1bb49d Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Mon, 29 Dec 2014 19:41:46 +0100
Subject: ALSA: pcm: Replace custom ld2 function with __fls

__fls has the same semantics as ld2, so there is no need to re-implement it.
Furthermore a lot of architectures have custom implementations of __fls that
are able to use special hardware instructions to compute the result. This
makes the code slightly shorter and faster.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm_params.h | 27 +--------------------------
 1 file changed, 1 insertion(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index c99e20b0c4c..3c45f3924ba 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -38,31 +38,6 @@ int snd_pcm_hw_param_value(const struct snd_pcm_hw_params *params,
 #define MASK_OFS(i)	((i) >> 5)
 #define MASK_BIT(i)	(1U << ((i) & 31))
 
-static inline unsigned int ld2(u_int32_t v)
-{
-        unsigned r = 0;
-
-        if (v >= 0x10000) {
-                v >>= 16;
-                r += 16;
-        }
-        if (v >= 0x100) {
-                v >>= 8;
-                r += 8;
-        }
-        if (v >= 0x10) {
-                v >>= 4;
-                r += 4;
-        }
-        if (v >= 4) {
-                v >>= 2;
-                r += 2;
-        }
-        if (v >= 2)
-                r++;
-        return r;
-}
-
 static inline size_t snd_mask_sizeof(void)
 {
 	return sizeof(struct snd_mask);
@@ -102,7 +77,7 @@ static inline unsigned int snd_mask_max(const struct snd_mask *mask)
 	int i;
 	for (i = SNDRV_MASK_SIZE - 1; i >= 0; i--) {
 		if (mask->bits[i])
-			return ld2(mask->bits[i]) + (i << 5);
+			return __fls(mask->bits[i]) + (i << 5);
 	}
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From 74d23cc704d19732e70ef1579a669f7d5f09dd9a Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Sun, 21 Dec 2014 19:46:56 +0100
Subject: time: move the timecounter/cyclecounter code into its own file.

The timecounter code has almost nothing to do with the clocksource
code. Let it live in its own file. This will help isolate the
timecounter users from the clocksource users in the source tree.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe.h        |   2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x.h |   2 +-
 drivers/net/ethernet/freescale/fec.h        |   1 +
 drivers/net/ethernet/intel/e1000e/e1000.h   |   2 +-
 drivers/net/ethernet/intel/igb/igb.h        |   2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe.h    |   2 +-
 drivers/net/ethernet/ti/cpts.h              |   1 +
 include/clocksource/arm_arch_timer.h        |   2 +-
 include/linux/clocksource.h                 | 102 -----------------------
 include/linux/mlx4/device.h                 |   2 +-
 include/linux/timecounter.h                 | 122 ++++++++++++++++++++++++++++
 include/linux/types.h                       |   3 +
 kernel/time/Makefile                        |   2 +-
 kernel/time/clocksource.c                   |  76 -----------------
 kernel/time/timecounter.c                   |  95 ++++++++++++++++++++++
 sound/pci/hda/hda_priv.h                    |   2 +-
 16 files changed, 231 insertions(+), 187 deletions(-)
 create mode 100644 include/linux/timecounter.h
 create mode 100644 kernel/time/timecounter.c

(limited to 'include')

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index f9ec762ac3f..2af6affc35a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -124,7 +124,7 @@
 #include <linux/if_vlan.h>
 #include <linux/bitops.h>
 #include <linux/ptp_clock_kernel.h>
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
 #include <net/dcbnl.h>
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index c3a6072134f..792ba72fb5c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -22,7 +22,7 @@
 
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 
 /* compilation time flags */
 
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 469691ad4a1..df8bbddaeb3 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -16,6 +16,7 @@
 #include <linux/clocksource.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
+#include <linux/timecounter.h>
 
 #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
     defined(CONFIG_M520x) || defined(CONFIG_M532x) || \
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 7785240a0da..9416e5a7e0c 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -34,7 +34,7 @@
 #include <linux/pci-aspm.h>
 #include <linux/crc32.h>
 #include <linux/if_vlan.h>
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/ptp_classify.h>
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 82d891e183b..ee22da39147 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -29,7 +29,7 @@
 #include "e1000_mac.h"
 #include "e1000_82575.h"
 
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index b6137be4392..38fc64cf5dc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -38,7 +38,7 @@
 #include <linux/if_vlan.h>
 #include <linux/jiffies.h>
 
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index 1a581ef7eee..69a46b92c7d 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -27,6 +27,7 @@
 #include <linux/list.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/skbuff.h>
+#include <linux/timecounter.h>
 
 struct cpsw_cpts {
 	u32 idver;                /* Identification and version */
diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 6d26b40cbf5..9916d0e4eff 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -16,7 +16,7 @@
 #ifndef __CLKSOURCE_ARM_ARCH_TIMER_H
 #define __CLKSOURCE_ARM_ARCH_TIMER_H
 
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 #include <linux/types.h>
 
 #define ARCH_TIMER_CTRL_ENABLE		(1 << 0)
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index abcafaa20b8..9c78d15d33e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -18,8 +18,6 @@
 #include <asm/div64.h>
 #include <asm/io.h>
 
-/* clocksource cycle base type */
-typedef u64 cycle_t;
 struct clocksource;
 struct module;
 
@@ -27,106 +25,6 @@ struct module;
 #include <asm/clocksource.h>
 #endif
 
-/**
- * struct cyclecounter - hardware abstraction for a free running counter
- *	Provides completely state-free accessors to the underlying hardware.
- *	Depending on which hardware it reads, the cycle counter may wrap
- *	around quickly. Locking rules (if necessary) have to be defined
- *	by the implementor and user of specific instances of this API.
- *
- * @read:		returns the current cycle value
- * @mask:		bitmask for two's complement
- *			subtraction of non 64 bit counters,
- *			see CLOCKSOURCE_MASK() helper macro
- * @mult:		cycle to nanosecond multiplier
- * @shift:		cycle to nanosecond divisor (power of two)
- */
-struct cyclecounter {
-	cycle_t (*read)(const struct cyclecounter *cc);
-	cycle_t mask;
-	u32 mult;
-	u32 shift;
-};
-
-/**
- * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds
- *	Contains the state needed by timecounter_read() to detect
- *	cycle counter wrap around. Initialize with
- *	timecounter_init(). Also used to convert cycle counts into the
- *	corresponding nanosecond counts with timecounter_cyc2time(). Users
- *	of this code are responsible for initializing the underlying
- *	cycle counter hardware, locking issues and reading the time
- *	more often than the cycle counter wraps around. The nanosecond
- *	counter will only wrap around after ~585 years.
- *
- * @cc:			the cycle counter used by this instance
- * @cycle_last:		most recent cycle counter value seen by
- *			timecounter_read()
- * @nsec:		continuously increasing count
- */
-struct timecounter {
-	const struct cyclecounter *cc;
-	cycle_t cycle_last;
-	u64 nsec;
-};
-
-/**
- * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
- * @cc:		Pointer to cycle counter.
- * @cycles:	Cycles
- *
- * XXX - This could use some mult_lxl_ll() asm optimization. Same code
- * as in cyc2ns, but with unsigned result.
- */
-static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
-				      cycle_t cycles)
-{
-	u64 ret = (u64)cycles;
-	ret = (ret * cc->mult) >> cc->shift;
-	return ret;
-}
-
-/**
- * timecounter_init - initialize a time counter
- * @tc:			Pointer to time counter which is to be initialized/reset
- * @cc:			A cycle counter, ready to be used.
- * @start_tstamp:	Arbitrary initial time stamp.
- *
- * After this call the current cycle register (roughly) corresponds to
- * the initial time stamp. Every call to timecounter_read() increments
- * the time stamp counter by the number of elapsed nanoseconds.
- */
-extern void timecounter_init(struct timecounter *tc,
-			     const struct cyclecounter *cc,
-			     u64 start_tstamp);
-
-/**
- * timecounter_read - return nanoseconds elapsed since timecounter_init()
- *                    plus the initial time stamp
- * @tc:          Pointer to time counter.
- *
- * In other words, keeps track of time since the same epoch as
- * the function which generated the initial time stamp.
- */
-extern u64 timecounter_read(struct timecounter *tc);
-
-/**
- * timecounter_cyc2time - convert a cycle counter to same
- *                        time base as values returned by
- *                        timecounter_read()
- * @tc:		Pointer to time counter.
- * @cycle_tstamp:	a value returned by tc->cc->read()
- *
- * Cycle counts that are converted correctly as long as they
- * fall into the interval [-1/2 max cycle count, +1/2 max cycle count],
- * with "max cycle count" == cs->mask+1.
- *
- * This allows conversion of cycle counter values which were generated
- * in the past.
- */
-extern u64 timecounter_cyc2time(struct timecounter *tc,
-				cycle_t cycle_tstamp);
-
 /**
  * struct clocksource - hardware abstraction for a free running counter
  *	Provides mostly state-free accessors to the underlying hardware.
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 25c791e295f..f1e41b33462 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -42,7 +42,7 @@
 
 #include <linux/atomic.h>
 
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 
 #define MAX_MSIX_P_PORT		17
 #define MAX_MSIX		64
diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h
new file mode 100644
index 00000000000..146f07a6651
--- /dev/null
+++ b/include/linux/timecounter.h
@@ -0,0 +1,122 @@
+/*
+ * linux/include/linux/timecounter.h
+ *
+ * based on code that migrated away from
+ * linux/include/linux/clocksource.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef _LINUX_TIMECOUNTER_H
+#define _LINUX_TIMECOUNTER_H
+
+#include <linux/types.h>
+
+/**
+ * struct cyclecounter - hardware abstraction for a free running counter
+ *	Provides completely state-free accessors to the underlying hardware.
+ *	Depending on which hardware it reads, the cycle counter may wrap
+ *	around quickly. Locking rules (if necessary) have to be defined
+ *	by the implementor and user of specific instances of this API.
+ *
+ * @read:		returns the current cycle value
+ * @mask:		bitmask for two's complement
+ *			subtraction of non 64 bit counters,
+ *			see CLOCKSOURCE_MASK() helper macro
+ * @mult:		cycle to nanosecond multiplier
+ * @shift:		cycle to nanosecond divisor (power of two)
+ */
+struct cyclecounter {
+	cycle_t (*read)(const struct cyclecounter *cc);
+	cycle_t mask;
+	u32 mult;
+	u32 shift;
+};
+
+/**
+ * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds
+ *	Contains the state needed by timecounter_read() to detect
+ *	cycle counter wrap around. Initialize with
+ *	timecounter_init(). Also used to convert cycle counts into the
+ *	corresponding nanosecond counts with timecounter_cyc2time(). Users
+ *	of this code are responsible for initializing the underlying
+ *	cycle counter hardware, locking issues and reading the time
+ *	more often than the cycle counter wraps around. The nanosecond
+ *	counter will only wrap around after ~585 years.
+ *
+ * @cc:			the cycle counter used by this instance
+ * @cycle_last:		most recent cycle counter value seen by
+ *			timecounter_read()
+ * @nsec:		continuously increasing count
+ */
+struct timecounter {
+	const struct cyclecounter *cc;
+	cycle_t cycle_last;
+	u64 nsec;
+};
+
+/**
+ * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
+ * @cc:		Pointer to cycle counter.
+ * @cycles:	Cycles
+ *
+ * XXX - This could use some mult_lxl_ll() asm optimization. Same code
+ * as in cyc2ns, but with unsigned result.
+ */
+static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
+				      cycle_t cycles)
+{
+	u64 ret = (u64)cycles;
+	ret = (ret * cc->mult) >> cc->shift;
+	return ret;
+}
+
+/**
+ * timecounter_init - initialize a time counter
+ * @tc:			Pointer to time counter which is to be initialized/reset
+ * @cc:			A cycle counter, ready to be used.
+ * @start_tstamp:	Arbitrary initial time stamp.
+ *
+ * After this call the current cycle register (roughly) corresponds to
+ * the initial time stamp. Every call to timecounter_read() increments
+ * the time stamp counter by the number of elapsed nanoseconds.
+ */
+extern void timecounter_init(struct timecounter *tc,
+			     const struct cyclecounter *cc,
+			     u64 start_tstamp);
+
+/**
+ * timecounter_read - return nanoseconds elapsed since timecounter_init()
+ *                    plus the initial time stamp
+ * @tc:          Pointer to time counter.
+ *
+ * In other words, keeps track of time since the same epoch as
+ * the function which generated the initial time stamp.
+ */
+extern u64 timecounter_read(struct timecounter *tc);
+
+/**
+ * timecounter_cyc2time - convert a cycle counter to same
+ *                        time base as values returned by
+ *                        timecounter_read()
+ * @tc:		Pointer to time counter.
+ * @cycle_tstamp:	a value returned by tc->cc->read()
+ *
+ * Cycle counts that are converted correctly as long as they
+ * fall into the interval [-1/2 max cycle count, +1/2 max cycle count],
+ * with "max cycle count" == cs->mask+1.
+ *
+ * This allows conversion of cycle counter values which were generated
+ * in the past.
+ */
+extern u64 timecounter_cyc2time(struct timecounter *tc,
+				cycle_t cycle_tstamp);
+
+#endif
diff --git a/include/linux/types.h b/include/linux/types.h
index a0bb7048687..62323825cff 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -213,5 +213,8 @@ struct callback_head {
 };
 #define rcu_head callback_head
 
+/* clocksource cycle base type */
+typedef u64 cycle_t;
+
 #endif /*  __ASSEMBLY__ */
 #endif /* _LINUX_TYPES_H */
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index f622cf28628..c09c07817d7 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -1,6 +1,6 @@
 obj-y += time.o timer.o hrtimer.o itimer.o posix-timers.o posix-cpu-timers.o
 obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
-obj-y += timeconv.o posix-clock.o alarmtimer.o
+obj-y += timeconv.o timecounter.o posix-clock.o alarmtimer.o
 
 obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD)		+= clockevents.o
 obj-$(CONFIG_GENERIC_CLOCKEVENTS)		+= tick-common.o
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index b79f39bda7e..4892352f0e4 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -34,82 +34,6 @@
 #include "tick-internal.h"
 #include "timekeeping_internal.h"
 
-void timecounter_init(struct timecounter *tc,
-		      const struct cyclecounter *cc,
-		      u64 start_tstamp)
-{
-	tc->cc = cc;
-	tc->cycle_last = cc->read(cc);
-	tc->nsec = start_tstamp;
-}
-EXPORT_SYMBOL_GPL(timecounter_init);
-
-/**
- * timecounter_read_delta - get nanoseconds since last call of this function
- * @tc:         Pointer to time counter
- *
- * When the underlying cycle counter runs over, this will be handled
- * correctly as long as it does not run over more than once between
- * calls.
- *
- * The first call to this function for a new time counter initializes
- * the time tracking and returns an undefined result.
- */
-static u64 timecounter_read_delta(struct timecounter *tc)
-{
-	cycle_t cycle_now, cycle_delta;
-	u64 ns_offset;
-
-	/* read cycle counter: */
-	cycle_now = tc->cc->read(tc->cc);
-
-	/* calculate the delta since the last timecounter_read_delta(): */
-	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
-
-	/* convert to nanoseconds: */
-	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
-
-	/* update time stamp of timecounter_read_delta() call: */
-	tc->cycle_last = cycle_now;
-
-	return ns_offset;
-}
-
-u64 timecounter_read(struct timecounter *tc)
-{
-	u64 nsec;
-
-	/* increment time by nanoseconds since last call */
-	nsec = timecounter_read_delta(tc);
-	nsec += tc->nsec;
-	tc->nsec = nsec;
-
-	return nsec;
-}
-EXPORT_SYMBOL_GPL(timecounter_read);
-
-u64 timecounter_cyc2time(struct timecounter *tc,
-			 cycle_t cycle_tstamp)
-{
-	u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
-	u64 nsec;
-
-	/*
-	 * Instead of always treating cycle_tstamp as more recent
-	 * than tc->cycle_last, detect when it is too far in the
-	 * future and treat it as old time stamp instead.
-	 */
-	if (cycle_delta > tc->cc->mask / 2) {
-		cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
-		nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
-	} else {
-		nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
-	}
-
-	return nsec;
-}
-EXPORT_SYMBOL_GPL(timecounter_cyc2time);
-
 /**
  * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks
  * @mult:	pointer to mult variable
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
new file mode 100644
index 00000000000..59a1ec3a57c
--- /dev/null
+++ b/kernel/time/timecounter.c
@@ -0,0 +1,95 @@
+/*
+ * linux/kernel/time/timecounter.c
+ *
+ * based on code that migrated away from
+ * linux/kernel/time/clocksource.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/export.h>
+#include <linux/timecounter.h>
+
+void timecounter_init(struct timecounter *tc,
+		      const struct cyclecounter *cc,
+		      u64 start_tstamp)
+{
+	tc->cc = cc;
+	tc->cycle_last = cc->read(cc);
+	tc->nsec = start_tstamp;
+}
+EXPORT_SYMBOL_GPL(timecounter_init);
+
+/**
+ * timecounter_read_delta - get nanoseconds since last call of this function
+ * @tc:         Pointer to time counter
+ *
+ * When the underlying cycle counter runs over, this will be handled
+ * correctly as long as it does not run over more than once between
+ * calls.
+ *
+ * The first call to this function for a new time counter initializes
+ * the time tracking and returns an undefined result.
+ */
+static u64 timecounter_read_delta(struct timecounter *tc)
+{
+	cycle_t cycle_now, cycle_delta;
+	u64 ns_offset;
+
+	/* read cycle counter: */
+	cycle_now = tc->cc->read(tc->cc);
+
+	/* calculate the delta since the last timecounter_read_delta(): */
+	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
+
+	/* convert to nanoseconds: */
+	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
+
+	/* update time stamp of timecounter_read_delta() call: */
+	tc->cycle_last = cycle_now;
+
+	return ns_offset;
+}
+
+u64 timecounter_read(struct timecounter *tc)
+{
+	u64 nsec;
+
+	/* increment time by nanoseconds since last call */
+	nsec = timecounter_read_delta(tc);
+	nsec += tc->nsec;
+	tc->nsec = nsec;
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_read);
+
+u64 timecounter_cyc2time(struct timecounter *tc,
+			 cycle_t cycle_tstamp)
+{
+	u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
+	u64 nsec;
+
+	/*
+	 * Instead of always treating cycle_tstamp as more recent
+	 * than tc->cycle_last, detect when it is too far in the
+	 * future and treat it as old time stamp instead.
+	 */
+	if (cycle_delta > tc->cc->mask / 2) {
+		cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
+		nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
+	} else {
+		nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
+	}
+
+	return nsec;
+}
+EXPORT_SYMBOL_GPL(timecounter_cyc2time);
diff --git a/sound/pci/hda/hda_priv.h b/sound/pci/hda/hda_priv.h
index 166e3e84b96..daf45829975 100644
--- a/sound/pci/hda/hda_priv.h
+++ b/sound/pci/hda/hda_priv.h
@@ -15,7 +15,7 @@
 #ifndef __SOUND_HDA_PRIV_H
 #define __SOUND_HDA_PRIV_H
 
-#include <linux/clocksource.h>
+#include <linux/timecounter.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 
-- 
cgit v1.2.3-70-g09d2


From 796c1efd6fa0ed696d550b68f4410ab1a1749d01 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Sun, 21 Dec 2014 19:46:57 +0100
Subject: timecounter: provide a helper function to shift the time.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some PTP Hardware Clock drivers use a struct timecounter to represent
their clock. To adjust the time by a given offset, these drivers all
perform a two step read/write of their timecounter. However, it is
better and simpler just to adjust the offset in one step. This patch
introduces a little routine to help drivers implement the adjtime
method.

Suggested-by: Janusz Użycki <j.uzycki@elproma.com.pl>
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/timecounter.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h
index 146f07a6651..af3dfa4e90f 100644
--- a/include/linux/timecounter.h
+++ b/include/linux/timecounter.h
@@ -78,6 +78,15 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
 	return ret;
 }
 
+/**
+ * timecounter_adjtime - Shifts the time of the clock.
+ * @delta:	Desired change in nanoseconds.
+ */
+static inline void timecounter_adjtime(struct timecounter *tc, s64 delta)
+{
+	tc->nsec += delta;
+}
+
 /**
  * timecounter_init - initialize a time counter
  * @tc:			Pointer to time counter which is to be initialized/reset
-- 
cgit v1.2.3-70-g09d2


From 2eebdde6528a722fbf8e2cffcf7aa52cbb4c2de0 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Sun, 21 Dec 2014 19:47:06 +0100
Subject: timecounter: keep track of accumulated fractional nanoseconds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current timecounter implementation will drop a variable amount
of resolution, depending on the magnitude of the time delta. In
other words, reading the clock too often or too close to a time
stamp conversion will introduce errors into the time values. This
patch fixes the issue by introducing a fractional nanosecond field
that accumulates the low order bits.

Reported-by: Janusz Użycki <j.uzycki@elproma.com.pl>
Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_clock.c |  4 ++--
 include/linux/timecounter.h                   | 19 ++++++++++------
 kernel/time/timecounter.c                     | 31 +++++++++++++++++++++------
 virt/kvm/arm/arch_timer.c                     |  3 ++-
 4 files changed, 40 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index df35d0e1b89..e9cce4f72b2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -240,7 +240,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 {
 	struct mlx4_dev *dev = mdev->dev;
 	unsigned long flags;
-	u64 ns;
+	u64 ns, zero = 0;
 
 	rwlock_init(&mdev->clock_lock);
 
@@ -265,7 +265,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev)
 	/* Calculate period in seconds to call the overflow watchdog - to make
 	 * sure counter is checked at least once every wrap around.
 	 */
-	ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask);
+	ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask, zero, &zero);
 	do_div(ns, NSEC_PER_SEC / 2 / HZ);
 	mdev->overflow_period = ns;
 
diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h
index af3dfa4e90f..74f45496e6d 100644
--- a/include/linux/timecounter.h
+++ b/include/linux/timecounter.h
@@ -55,27 +55,32 @@ struct cyclecounter {
  * @cycle_last:		most recent cycle counter value seen by
  *			timecounter_read()
  * @nsec:		continuously increasing count
+ * @mask:		bit mask for maintaining the 'frac' field
+ * @frac:		accumulated fractional nanoseconds
  */
 struct timecounter {
 	const struct cyclecounter *cc;
 	cycle_t cycle_last;
 	u64 nsec;
+	u64 mask;
+	u64 frac;
 };
 
 /**
  * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds
  * @cc:		Pointer to cycle counter.
  * @cycles:	Cycles
- *
- * XXX - This could use some mult_lxl_ll() asm optimization. Same code
- * as in cyc2ns, but with unsigned result.
+ * @mask:	bit mask for maintaining the 'frac' field
+ * @frac:	pointer to storage for the fractional nanoseconds.
  */
 static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
-				      cycle_t cycles)
+				      cycle_t cycles, u64 mask, u64 *frac)
 {
-	u64 ret = (u64)cycles;
-	ret = (ret * cc->mult) >> cc->shift;
-	return ret;
+	u64 ns = (u64) cycles;
+
+	ns = (ns * cc->mult) + *frac;
+	*frac = ns & mask;
+	return ns >> cc->shift;
 }
 
 /**
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
index 59a1ec3a57c..4687b3104ba 100644
--- a/kernel/time/timecounter.c
+++ b/kernel/time/timecounter.c
@@ -25,6 +25,8 @@ void timecounter_init(struct timecounter *tc,
 	tc->cc = cc;
 	tc->cycle_last = cc->read(cc);
 	tc->nsec = start_tstamp;
+	tc->mask = (1ULL << cc->shift) - 1;
+	tc->frac = 0;
 }
 EXPORT_SYMBOL_GPL(timecounter_init);
 
@@ -51,7 +53,8 @@ static u64 timecounter_read_delta(struct timecounter *tc)
 	cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask;
 
 	/* convert to nanoseconds: */
-	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta);
+	ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta,
+					tc->mask, &tc->frac);
 
 	/* update time stamp of timecounter_read_delta() call: */
 	tc->cycle_last = cycle_now;
@@ -72,22 +75,36 @@ u64 timecounter_read(struct timecounter *tc)
 }
 EXPORT_SYMBOL_GPL(timecounter_read);
 
+/*
+ * This is like cyclecounter_cyc2ns(), but it is used for computing a
+ * time previous to the time stored in the cycle counter.
+ */
+static u64 cc_cyc2ns_backwards(const struct cyclecounter *cc,
+			       cycle_t cycles, u64 mask, u64 frac)
+{
+	u64 ns = (u64) cycles;
+
+	ns = ((ns * cc->mult) - frac) >> cc->shift;
+
+	return ns;
+}
+
 u64 timecounter_cyc2time(struct timecounter *tc,
 			 cycle_t cycle_tstamp)
 {
-	u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
-	u64 nsec;
+	u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
+	u64 nsec = tc->nsec, frac = tc->frac;
 
 	/*
 	 * Instead of always treating cycle_tstamp as more recent
 	 * than tc->cycle_last, detect when it is too far in the
 	 * future and treat it as old time stamp instead.
 	 */
-	if (cycle_delta > tc->cc->mask / 2) {
-		cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
-		nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta);
+	if (delta > tc->cc->mask / 2) {
+		delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask;
+		nsec -= cc_cyc2ns_backwards(tc->cc, delta, tc->mask, frac);
 	} else {
-		nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec;
+		nsec += cyclecounter_cyc2ns(tc->cc, delta, tc->mask, &frac);
 	}
 
 	return nsec;
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 1c0772b340d..6e54f354212 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -152,7 +152,8 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 		return;
 	}
 
-	ns = cyclecounter_cyc2ns(timecounter->cc, cval - now);
+	ns = cyclecounter_cyc2ns(timecounter->cc, cval - now, timecounter->mask,
+				 &timecounter->frac);
 	timer_arm(timer, ns);
 }
 
-- 
cgit v1.2.3-70-g09d2


From dd450777990baae668c1143064f2f234dbab1b9b Mon Sep 17 00:00:00 2001
From: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
Date: Wed, 24 Dec 2014 01:14:14 +0300
Subject: arm: sa1100: move irda header to linux/platform_data

In the end asm/mach/irda.h header is not used by anybody except sa1100.
Move the header to the platform data includes dir and rename it to
irda-sa11x0.h.

Signed-off-by: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/include/asm/mach/irda.h          | 20 --------------------
 arch/arm/mach-sa1100/assabet.c            |  2 +-
 arch/arm/mach-sa1100/collie.c             |  2 +-
 arch/arm/mach-sa1100/h3100.c              |  2 +-
 arch/arm/mach-sa1100/h3600.c              |  2 +-
 drivers/net/irda/sa1100_ir.c              |  2 +-
 include/linux/platform_data/irda-sa11x0.h | 20 ++++++++++++++++++++
 7 files changed, 25 insertions(+), 25 deletions(-)
 delete mode 100644 arch/arm/include/asm/mach/irda.h
 create mode 100644 include/linux/platform_data/irda-sa11x0.h

(limited to 'include')

diff --git a/arch/arm/include/asm/mach/irda.h b/arch/arm/include/asm/mach/irda.h
deleted file mode 100644
index 38f77b5e56c..00000000000
--- a/arch/arm/include/asm/mach/irda.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *  arch/arm/include/asm/mach/irda.h
- *
- *  Copyright (C) 2004 Russell King.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARM_MACH_IRDA_H
-#define __ASM_ARM_MACH_IRDA_H
-
-struct irda_platform_data {
-	int (*startup)(struct device *);
-	void (*shutdown)(struct device *);
-	int (*set_power)(struct device *, unsigned int state);
-	void (*set_speed)(struct device *, unsigned int speed);
-};
-
-#endif
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index 7dd894ece9a..d28ecb9ef17 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -37,7 +37,7 @@
 
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
-#include <asm/mach/irda.h>
+#include <linux/platform_data/irda-sa11x0.h>
 #include <asm/mach/map.h>
 #include <mach/assabet.h>
 #include <linux/platform_data/mfd-mcp-sa11x0.h>
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index b90c7d82839..7fcbe3d119c 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -43,7 +43,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
-#include <asm/mach/irda.h>
+#include <linux/platform_data/irda-sa11x0.h>
 
 #include <asm/hardware/scoop.h>
 #include <asm/mach/sharpsl_param.h>
diff --git a/arch/arm/mach-sa1100/h3100.c b/arch/arm/mach-sa1100/h3100.c
index 3c43219bc88..c6b412054a3 100644
--- a/arch/arm/mach-sa1100/h3100.c
+++ b/arch/arm/mach-sa1100/h3100.c
@@ -18,7 +18,7 @@
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/mach/irda.h>
+#include <linux/platform_data/irda-sa11x0.h>
 
 #include <mach/h3xxx.h>
 #include <mach/irqs.h>
diff --git a/arch/arm/mach-sa1100/h3600.c b/arch/arm/mach-sa1100/h3600.c
index 5be54c214c7..118338efd79 100644
--- a/arch/arm/mach-sa1100/h3600.c
+++ b/arch/arm/mach-sa1100/h3600.c
@@ -18,7 +18,7 @@
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
-#include <asm/mach/irda.h>
+#include <linux/platform_data/irda-sa11x0.h>
 
 #include <mach/h3xxx.h>
 #include <mach/irqs.h>
diff --git a/drivers/net/irda/sa1100_ir.c b/drivers/net/irda/sa1100_ir.c
index 7b17fa2114e..b6e44ff4e37 100644
--- a/drivers/net/irda/sa1100_ir.c
+++ b/drivers/net/irda/sa1100_ir.c
@@ -38,7 +38,7 @@
 #include <net/irda/irda_device.h>
 
 #include <mach/hardware.h>
-#include <asm/mach/irda.h>
+#include <linux/platform_data/irda-sa11x0.h>
 
 static int power_level = 3;
 static int tx_lpm;
diff --git a/include/linux/platform_data/irda-sa11x0.h b/include/linux/platform_data/irda-sa11x0.h
new file mode 100644
index 00000000000..38f77b5e56c
--- /dev/null
+++ b/include/linux/platform_data/irda-sa11x0.h
@@ -0,0 +1,20 @@
+/*
+ *  arch/arm/include/asm/mach/irda.h
+ *
+ *  Copyright (C) 2004 Russell King.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __ASM_ARM_MACH_IRDA_H
+#define __ASM_ARM_MACH_IRDA_H
+
+struct irda_platform_data {
+	int (*startup)(struct device *);
+	void (*shutdown)(struct device *);
+	int (*set_power)(struct device *, unsigned int state);
+	void (*set_speed)(struct device *, unsigned int speed);
+};
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From 48d882978eb0a15547093b4542a82b5c22548041 Mon Sep 17 00:00:00 2001
From: Libin Yang <libin.yang@intel.com>
Date: Wed, 31 Dec 2014 22:09:54 +0800
Subject: ALSA: pcm: add SNDRV_PCM_TRIGGER_DRAIN trigger

Add SNDRV_PCM_TRIGGER_DRAIN trigger for pcm drain.

Some audio devices require notification of drain events
in order to properly drain and shutdown an audio stream.

Signed-off-by: Libin Yang <libin.yang@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h         |  1 +
 include/uapi/sound/asound.h |  1 +
 sound/core/pcm_native.c     | 10 +++++++++-
 3 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 3652c9439af..bf32cea2202 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -106,6 +106,7 @@ struct snd_pcm_ops {
 #define SNDRV_PCM_TRIGGER_PAUSE_RELEASE	4
 #define SNDRV_PCM_TRIGGER_SUSPEND	5
 #define SNDRV_PCM_TRIGGER_RESUME	6
+#define SNDRV_PCM_TRIGGER_DRAIN		7
 
 #define SNDRV_PCM_POS_XRUN		((snd_pcm_uframes_t)-1)
 
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 1f23cd63595..0e88e7a0f0e 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -268,6 +268,7 @@ typedef int __bitwise snd_pcm_subformat_t;
 #define SNDRV_PCM_INFO_SYNC_START	0x00400000	/* pcm support some kind of sync go */
 #define SNDRV_PCM_INFO_NO_PERIOD_WAKEUP	0x00800000	/* period wakeup can be disabled */
 #define SNDRV_PCM_INFO_HAS_WALL_CLOCK   0x01000000      /* has audio wall clock for audio/system time sync */
+#define SNDRV_PCM_INFO_DRAIN_TRIGGER	0x40000000		/* internal kernel flag - trigger in drain */
 #define SNDRV_PCM_INFO_FIFO_IN_FRAMES	0x80000000	/* internal kernel flag - FIFO size is in frames */
 
 typedef int __bitwise snd_pcm_state_t;
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 095d9572ad2..ff3abc3b4ff 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -420,7 +420,8 @@ int snd_pcm_hw_refine(struct snd_pcm_substream *substream,
 
 	hw = &substream->runtime->hw;
 	if (!params->info) {
-		params->info = hw->info & ~SNDRV_PCM_INFO_FIFO_IN_FRAMES;
+		params->info = hw->info & ~(SNDRV_PCM_INFO_FIFO_IN_FRAMES |
+					    SNDRV_PCM_INFO_DRAIN_TRIGGER);
 		if (!hw_support_mmap(substream))
 			params->info &= ~(SNDRV_PCM_INFO_MMAP |
 					  SNDRV_PCM_INFO_MMAP_VALID);
@@ -1566,6 +1567,13 @@ static int snd_pcm_do_drain_init(struct snd_pcm_substream *substream, int state)
 			snd_pcm_post_stop(substream, new_state);
 		}
 	}
+
+	if (runtime->status->state == SNDRV_PCM_STATE_DRAINING &&
+	    runtime->trigger_master == substream &&
+	    (runtime->hw.info & SNDRV_PCM_INFO_DRAIN_TRIGGER))
+		return substream->ops->trigger(substream,
+					       SNDRV_PCM_TRIGGER_DRAIN);
+
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From de40ed31b3c577cefd7b54972365a272ecbe9dd6 Mon Sep 17 00:00:00 2001
From: Nimrod Andy <B38611@freescale.com>
Date: Wed, 24 Dec 2014 17:30:39 +0800
Subject: net: fec: add Wake-on-LAN support

Support for Wake-on-LAN using Magic Packet. ENET IP supports sleep mode
in low power status, when system enter suspend status, Magic packet can
wake up system even if all SOC clocks are gate. The patch doing below things:
- flagging the device as a wakeup source for the system, as well as
  its Wake-on-LAN interrupt
- prepare the hardware for entering WoL mode
- add standard ethtool WOL interface
- enable the ENET interrupt to wake us

Tested on i.MX6q/dl sabresd, sabreauto boards, i.MX6SX arm2 boards.

Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/fsl-fec.txt |   2 +
 drivers/net/ethernet/freescale/fec.h              |   2 +
 drivers/net/ethernet/freescale/fec_main.c         | 104 +++++++++++++++++++---
 include/linux/fec.h                               |   1 +
 4 files changed, 99 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt
index 0c8775c4579..a9eb611bee6 100644
--- a/Documentation/devicetree/bindings/net/fsl-fec.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fec.txt
@@ -22,6 +22,8 @@ Optional properties:
 - fsl,num-rx-queues : The property is valid for enet-avb IP, which supports
   hw multi queues. Should specify the rx queue number, otherwise set rx queue
   number to 1.
+- fsl,magic-packet : If present, indicates that the hardware supports waking
+  up via magic packet.
 
 Optional subnodes:
 - mdio : specifies the mdio bus in the FEC, used as a container for phy nodes
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index df8bbddaeb3..d77a96fdf1d 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -357,6 +357,7 @@ struct bufdesc_ex {
 #define FEC_ENET_RXB    ((uint)0x01000000)      /* A buffer was received */
 #define FEC_ENET_MII    ((uint)0x00800000)      /* MII interrupt */
 #define FEC_ENET_EBERR  ((uint)0x00400000)      /* SDMA bus error */
+#define FEC_ENET_WAKEUP	((uint)0x00020000)	/* Wakeup request */
 #define FEC_ENET_TXF	(FEC_ENET_TXF_0 | FEC_ENET_TXF_1 | FEC_ENET_TXF_2)
 #define FEC_ENET_RXF	(FEC_ENET_RXF_0 | FEC_ENET_RXF_1 | FEC_ENET_RXF_2)
 #define FEC_ENET_TS_AVAIL       ((uint)0x00010000)
@@ -512,6 +513,7 @@ struct fec_enet_private {
 	int	irq[FEC_IRQ_NUM];
 	bool	bufdesc_ex;
 	int	pause_flag;
+	int	wol_flag;
 	u32	quirks;
 
 	struct	napi_struct napi;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 5ebdf8dc8a3..49cd358c30f 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -187,6 +187,9 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #define FEC_MMFR_RA(v)		((v & 0x1f) << 18)
 #define FEC_MMFR_TA		(2 << 16)
 #define FEC_MMFR_DATA(v)	(v & 0xffff)
+/* FEC ECR bits definition */
+#define FEC_ECR_MAGICEN		(1 << 2)
+#define FEC_ECR_SLEEP		(1 << 3)
 
 #define FEC_MII_TIMEOUT		30000 /* us */
 
@@ -195,6 +198,9 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 
 #define FEC_PAUSE_FLAG_AUTONEG	0x1
 #define FEC_PAUSE_FLAG_ENABLE	0x2
+#define FEC_WOL_HAS_MAGIC_PACKET	(0x1 << 0)
+#define FEC_WOL_FLAG_ENABLE		(0x1 << 1)
+#define FEC_WOL_FLAG_SLEEP_ON		(0x1 << 2)
 
 #define COPYBREAK_DEFAULT	256
 
@@ -1089,7 +1095,9 @@ static void
 fec_stop(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
 	u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8);
+	u32 val;
 
 	/* We cannot expect a graceful transmit stop without link !!! */
 	if (fep->link) {
@@ -1103,17 +1111,28 @@ fec_stop(struct net_device *ndev)
 	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
 	 * instead of reset MAC itself.
 	 */
-	if (fep->quirks & FEC_QUIRK_HAS_AVB) {
-		writel(0, fep->hwp + FEC_ECNTRL);
+	if (!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
+		if (fep->quirks & FEC_QUIRK_HAS_AVB) {
+			writel(0, fep->hwp + FEC_ECNTRL);
+		} else {
+			writel(1, fep->hwp + FEC_ECNTRL);
+			udelay(10);
+		}
+		writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 	} else {
-		writel(1, fep->hwp + FEC_ECNTRL);
-		udelay(10);
+		writel(FEC_DEFAULT_IMASK | FEC_ENET_WAKEUP, fep->hwp + FEC_IMASK);
+		val = readl(fep->hwp + FEC_ECNTRL);
+		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
+		writel(val, fep->hwp + FEC_ECNTRL);
+
+		if (pdata && pdata->sleep_mode_enable)
+			pdata->sleep_mode_enable(true);
 	}
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
-	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 
 	/* We have to keep ENET enabled to have MII interrupt stay working */
-	if (fep->quirks & FEC_QUIRK_ENET_MAC) {
+	if (fep->quirks & FEC_QUIRK_ENET_MAC &&
+		!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
 		writel(2, fep->hwp + FEC_ECNTRL);
 		writel(rmii_mode, fep->hwp + FEC_R_CNTRL);
 	}
@@ -2427,6 +2446,44 @@ static int fec_enet_set_tunable(struct net_device *netdev,
 	return ret;
 }
 
+static void
+fec_enet_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	if (fep->wol_flag & FEC_WOL_HAS_MAGIC_PACKET) {
+		wol->supported = WAKE_MAGIC;
+		wol->wolopts = fep->wol_flag & FEC_WOL_FLAG_ENABLE ? WAKE_MAGIC : 0;
+	} else {
+		wol->supported = wol->wolopts = 0;
+	}
+}
+
+static int
+fec_enet_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	if (!(fep->wol_flag & FEC_WOL_HAS_MAGIC_PACKET))
+		return -EINVAL;
+
+	if (wol->wolopts & ~WAKE_MAGIC)
+		return -EINVAL;
+
+	device_set_wakeup_enable(&ndev->dev, wol->wolopts & WAKE_MAGIC);
+	if (device_may_wakeup(&ndev->dev)) {
+		fep->wol_flag |= FEC_WOL_FLAG_ENABLE;
+		if (fep->irq[0] > 0)
+			enable_irq_wake(fep->irq[0]);
+	} else {
+		fep->wol_flag &= (~FEC_WOL_FLAG_ENABLE);
+		if (fep->irq[0] > 0)
+			disable_irq_wake(fep->irq[0]);
+	}
+
+	return 0;
+}
+
 static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_settings		= fec_enet_get_settings,
 	.set_settings		= fec_enet_set_settings,
@@ -2445,6 +2502,8 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_ts_info		= fec_enet_get_ts_info,
 	.get_tunable		= fec_enet_get_tunable,
 	.set_tunable		= fec_enet_set_tunable,
+	.get_wol		= fec_enet_get_wol,
+	.set_wol		= fec_enet_set_wol,
 };
 
 static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
@@ -2705,6 +2764,9 @@ fec_enet_open(struct net_device *ndev)
 	phy_start(fep->phy_dev);
 	netif_tx_start_all_queues(ndev);
 
+	device_set_wakeup_enable(&ndev->dev, fep->wol_flag &
+				 FEC_WOL_FLAG_ENABLE);
+
 	return 0;
 
 err_enet_mii_probe:
@@ -3153,6 +3215,9 @@ fec_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, ndev);
 
+	if (of_get_property(np, "fsl,magic-packet", NULL))
+		fep->wol_flag |= FEC_WOL_HAS_MAGIC_PACKET;
+
 	phy_node = of_parse_phandle(np, "phy-handle", 0);
 	if (!phy_node && of_phy_is_fixed_link(np)) {
 		ret = of_phy_register_fixed_link(np);
@@ -3247,6 +3312,8 @@ fec_probe(struct platform_device *pdev)
 				       0, pdev->name, ndev);
 		if (ret)
 			goto failed_irq;
+
+		fep->irq[i] = irq;
 	}
 
 	init_completion(&fep->mdio_done);
@@ -3263,6 +3330,9 @@ fec_probe(struct platform_device *pdev)
 	if (ret)
 		goto failed_register;
 
+	device_init_wakeup(&ndev->dev, fep->wol_flag &
+			   FEC_WOL_HAS_MAGIC_PACKET);
+
 	if (fep->bufdesc_ex && fep->ptp_clock)
 		netdev_info(ndev, "registered PHC device %d\n", fep->dev_id);
 
@@ -3316,6 +3386,8 @@ static int __maybe_unused fec_suspend(struct device *dev)
 
 	rtnl_lock();
 	if (netif_running(ndev)) {
+		if (fep->wol_flag & FEC_WOL_FLAG_ENABLE)
+			fep->wol_flag |= FEC_WOL_FLAG_SLEEP_ON;
 		phy_stop(fep->phy_dev);
 		napi_disable(&fep->napi);
 		netif_tx_lock_bh(ndev);
@@ -3323,11 +3395,12 @@ static int __maybe_unused fec_suspend(struct device *dev)
 		netif_tx_unlock_bh(ndev);
 		fec_stop(ndev);
 		fec_enet_clk_enable(ndev, false);
-		pinctrl_pm_select_sleep_state(&fep->pdev->dev);
+		if (!(fep->wol_flag & FEC_WOL_FLAG_ENABLE))
+			pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	}
 	rtnl_unlock();
 
-	if (fep->reg_phy)
+	if (fep->reg_phy && !(fep->wol_flag & FEC_WOL_FLAG_ENABLE))
 		regulator_disable(fep->reg_phy);
 
 	/* SOC supply clock to phy, when clock is disabled, phy link down
@@ -3343,9 +3416,11 @@ static int __maybe_unused fec_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
 	int ret;
+	int val;
 
-	if (fep->reg_phy) {
+	if (fep->reg_phy && !(fep->wol_flag & FEC_WOL_FLAG_ENABLE)) {
 		ret = regulator_enable(fep->reg_phy);
 		if (ret)
 			return ret;
@@ -3353,12 +3428,21 @@ static int __maybe_unused fec_resume(struct device *dev)
 
 	rtnl_lock();
 	if (netif_running(ndev)) {
-		pinctrl_pm_select_default_state(&fep->pdev->dev);
 		ret = fec_enet_clk_enable(ndev, true);
 		if (ret) {
 			rtnl_unlock();
 			goto failed_clk;
 		}
+		if (fep->wol_flag & FEC_WOL_FLAG_ENABLE) {
+			if (pdata && pdata->sleep_mode_enable)
+				pdata->sleep_mode_enable(false);
+			val = readl(fep->hwp + FEC_ECNTRL);
+			val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
+			writel(val, fep->hwp + FEC_ECNTRL);
+			fep->wol_flag &= ~FEC_WOL_FLAG_SLEEP_ON;
+		} else {
+			pinctrl_pm_select_default_state(&fep->pdev->dev);
+		}
 		fec_restart(ndev);
 		netif_tx_lock_bh(ndev);
 		netif_device_attach(ndev);
diff --git a/include/linux/fec.h b/include/linux/fec.h
index bcff455d1d5..1454a503622 100644
--- a/include/linux/fec.h
+++ b/include/linux/fec.h
@@ -19,6 +19,7 @@
 struct fec_platform_data {
 	phy_interface_t phy;
 	unsigned char mac[ETH_ALEN];
+	void (*sleep_mode_enable)(int enabled);
 };
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 33f72e6f0c67f673fd0c63a8182dbd9ffb8cf50b Mon Sep 17 00:00:00 2001
From: Bill Hong <bhong@brocade.com>
Date: Sat, 27 Dec 2014 10:12:39 -0800
Subject: l2tp : multicast notification to the registered listeners

Previously l2tp module did not provide any means for the user space to
get notified when tunnels/sessions are added/modified/deleted.
This change contains the following
- create a multicast group for the listeners to register.
- notify the registered listeners when the tunnels/sessions are
  created/modified/deleted.

Signed-off-by: Bill Hong <bhong@brocade.com>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Sven-Thorsten Dietrich <sven@brocade.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/l2tp.h |   1 +
 net/l2tp/l2tp_netlink.c   | 101 +++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 92 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 21caa2631c2..347ef22a964 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -178,5 +178,6 @@ enum l2tp_seqmode {
  */
 #define L2TP_GENL_NAME		"l2tp"
 #define L2TP_GENL_VERSION	0x1
+#define L2TP_GENL_MCGROUP       "l2tp"
 
 #endif /* _UAPI_LINUX_L2TP_H_ */
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 0ac907adb2f..6b16598f31d 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -40,6 +40,18 @@ static struct genl_family l2tp_nl_family = {
 	.netnsok	= true,
 };
 
+static const struct genl_multicast_group l2tp_multicast_group[] = {
+	{
+		.name = L2TP_GENL_MCGROUP,
+	},
+};
+
+static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq,
+			       int flags, struct l2tp_tunnel *tunnel, u8 cmd);
+static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq,
+				int flags, struct l2tp_session *session,
+				u8 cmd);
+
 /* Accessed under genl lock */
 static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
 
@@ -97,6 +109,52 @@ out:
 	return ret;
 }
 
+static int l2tp_tunnel_notify(struct genl_family *family,
+			      struct genl_info *info,
+			      struct l2tp_tunnel *tunnel,
+			      u8 cmd)
+{
+	struct sk_buff *msg;
+	int ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
+				  NLM_F_ACK, tunnel, cmd);
+
+	if (ret >= 0)
+		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+
+	nlmsg_free(msg);
+
+	return ret;
+}
+
+static int l2tp_session_notify(struct genl_family *family,
+			       struct genl_info *info,
+			       struct l2tp_session *session,
+			       u8 cmd)
+{
+	struct sk_buff *msg;
+	int ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
+				   NLM_F_ACK, session, cmd);
+
+	if (ret >= 0)
+		return genlmsg_multicast_allns(family, msg, 0,	0, GFP_ATOMIC);
+
+	nlmsg_free(msg);
+
+	return ret;
+}
+
 static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info)
 {
 	u32 tunnel_id;
@@ -188,6 +246,9 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 		break;
 	}
 
+	if (ret >= 0)
+		ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
+					 tunnel, L2TP_CMD_TUNNEL_CREATE);
 out:
 	return ret;
 }
@@ -211,6 +272,9 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info
 		goto out;
 	}
 
+	l2tp_tunnel_notify(&l2tp_nl_family, info,
+			   tunnel, L2TP_CMD_TUNNEL_DELETE);
+
 	(void) l2tp_tunnel_delete(tunnel);
 
 out:
@@ -239,12 +303,15 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info
 	if (info->attrs[L2TP_ATTR_DEBUG])
 		tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
 
+	ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
+				 tunnel, L2TP_CMD_TUNNEL_MODIFY);
+
 out:
 	return ret;
 }
 
 static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int flags,
-			       struct l2tp_tunnel *tunnel)
+			       struct l2tp_tunnel *tunnel, u8 cmd)
 {
 	void *hdr;
 	struct nlattr *nest;
@@ -254,8 +321,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	struct ipv6_pinfo *np = NULL;
 #endif
 
-	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags,
-			  L2TP_CMD_TUNNEL_GET);
+	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, cmd);
 	if (!hdr)
 		return -EMSGSIZE;
 
@@ -359,7 +425,7 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq,
-				  NLM_F_ACK, tunnel);
+				  NLM_F_ACK, tunnel, L2TP_CMD_TUNNEL_GET);
 	if (ret < 0)
 		goto err_out;
 
@@ -385,7 +451,7 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
 					cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					tunnel) <= 0)
+					tunnel, L2TP_CMD_TUNNEL_GET) <= 0)
 			goto out;
 
 		ti++;
@@ -539,6 +605,13 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 		ret = (*l2tp_nl_cmd_ops[cfg.pw_type]->session_create)(net, tunnel_id,
 			session_id, peer_session_id, &cfg);
 
+	if (ret >= 0) {
+		session = l2tp_session_find(net, tunnel, session_id);
+		if (session)
+			ret = l2tp_session_notify(&l2tp_nl_family, info, session,
+						  L2TP_CMD_SESSION_CREATE);
+	}
+
 out:
 	return ret;
 }
@@ -555,6 +628,9 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
 		goto out;
 	}
 
+	l2tp_session_notify(&l2tp_nl_family, info,
+			    session, L2TP_CMD_SESSION_DELETE);
+
 	pw_type = session->pwtype;
 	if (pw_type < __L2TP_PWTYPE_MAX)
 		if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
@@ -601,12 +677,15 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_MRU])
 		session->mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]);
 
+	ret = l2tp_session_notify(&l2tp_nl_family, info,
+				  session, L2TP_CMD_SESSION_MODIFY);
+
 out:
 	return ret;
 }
 
 static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int flags,
-				struct l2tp_session *session)
+				struct l2tp_session *session, u8 cmd)
 {
 	void *hdr;
 	struct nlattr *nest;
@@ -615,7 +694,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 
 	sk = tunnel->sock;
 
-	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, L2TP_CMD_SESSION_GET);
+	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, cmd);
 	if (!hdr)
 		return -EMSGSIZE;
 
@@ -699,7 +778,7 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
-				   0, session);
+				   0, session, L2TP_CMD_SESSION_GET);
 	if (ret < 0)
 		goto err_out;
 
@@ -737,7 +816,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session) <= 0)
+					 session, L2TP_CMD_SESSION_GET) <= 0)
 			break;
 
 		si++;
@@ -896,7 +975,9 @@ EXPORT_SYMBOL_GPL(l2tp_nl_unregister_ops);
 static int l2tp_nl_init(void)
 {
 	pr_info("L2TP netlink interface\n");
-	return genl_register_family_with_ops(&l2tp_nl_family, l2tp_nl_ops);
+	return genl_register_family_with_ops_groups(&l2tp_nl_family,
+						    l2tp_nl_ops,
+						    l2tp_multicast_group);
 }
 
 static void l2tp_nl_cleanup(void)
-- 
cgit v1.2.3-70-g09d2


From 345e9b54268ae065520a7252c182d22ef4591718 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@redhat.com>
Date: Wed, 31 Dec 2014 10:56:24 -0800
Subject: fib_trie: Push rcu_read_lock/unlock to callers

This change is to start cleaning up some of the rcu_read_lock/unlock
handling.  I realized while reviewing the code there are several spots that
I don't believe are being handled correctly or are masking warnings by
locally calling rcu_read_lock/unlock instead of calling them at the correct
level.

A common example is a call to fib_get_table followed by fib_table_lookup.
The rcu_read_lock/unlock ought to wrap both but there are several spots where
they were not wrapped.

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h    |  50 ++++++++++--------
 net/ipv4/fib_frontend.c |  27 +++++-----
 net/ipv4/fib_rules.c    |  22 ++++----
 net/ipv4/fib_trie.c     | 137 +++++++++++++++++++++---------------------------
 4 files changed, 114 insertions(+), 122 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 09a819ee215..5bd120e4bc0 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -222,16 +222,19 @@ static inline struct fib_table *fib_new_table(struct net *net, u32 id)
 static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
 			     struct fib_result *res)
 {
-	struct fib_table *table;
+	int err = -ENETUNREACH;
+
+	rcu_read_lock();
+
+	if (!fib_table_lookup(fib_get_table(net, RT_TABLE_LOCAL), flp, res,
+			      FIB_LOOKUP_NOREF) ||
+	    !fib_table_lookup(fib_get_table(net, RT_TABLE_MAIN), flp, res,
+			      FIB_LOOKUP_NOREF))
+		err = 0;
 
-	table = fib_get_table(net, RT_TABLE_LOCAL);
-	if (!fib_table_lookup(table, flp, res, FIB_LOOKUP_NOREF))
-		return 0;
+	rcu_read_unlock();
 
-	table = fib_get_table(net, RT_TABLE_MAIN);
-	if (!fib_table_lookup(table, flp, res, FIB_LOOKUP_NOREF))
-		return 0;
-	return -ENETUNREACH;
+	return err;
 }
 
 #else /* CONFIG_IP_MULTIPLE_TABLES */
@@ -247,20 +250,25 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,
 			     struct fib_result *res)
 {
 	if (!net->ipv4.fib_has_custom_rules) {
+		int err = -ENETUNREACH;
+
+		rcu_read_lock();
+
 		res->tclassid = 0;
-		if (net->ipv4.fib_local &&
-		    !fib_table_lookup(net->ipv4.fib_local, flp, res,
-				      FIB_LOOKUP_NOREF))
-			return 0;
-		if (net->ipv4.fib_main &&
-		    !fib_table_lookup(net->ipv4.fib_main, flp, res,
-				      FIB_LOOKUP_NOREF))
-			return 0;
-		if (net->ipv4.fib_default &&
-		    !fib_table_lookup(net->ipv4.fib_default, flp, res,
-				      FIB_LOOKUP_NOREF))
-			return 0;
-		return -ENETUNREACH;
+		if ((net->ipv4.fib_local &&
+		     !fib_table_lookup(net->ipv4.fib_local, flp, res,
+				       FIB_LOOKUP_NOREF)) ||
+		    (net->ipv4.fib_main &&
+		     !fib_table_lookup(net->ipv4.fib_main, flp, res,
+				       FIB_LOOKUP_NOREF)) ||
+		    (net->ipv4.fib_default &&
+		     !fib_table_lookup(net->ipv4.fib_default, flp, res,
+				       FIB_LOOKUP_NOREF)))
+			err = 0;
+
+		rcu_read_unlock();
+
+		return err;
 	}
 	return __fib_lookup(net, flp, res);
 }
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 66890209208..57be71dd6a9 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -109,6 +109,7 @@ struct fib_table *fib_new_table(struct net *net, u32 id)
 	return tb;
 }
 
+/* caller must hold either rtnl or rcu read lock */
 struct fib_table *fib_get_table(struct net *net, u32 id)
 {
 	struct fib_table *tb;
@@ -119,15 +120,11 @@ struct fib_table *fib_get_table(struct net *net, u32 id)
 		id = RT_TABLE_MAIN;
 	h = id & (FIB_TABLE_HASHSZ - 1);
 
-	rcu_read_lock();
 	head = &net->ipv4.fib_table_hash[h];
 	hlist_for_each_entry_rcu(tb, head, tb_hlist) {
-		if (tb->tb_id == id) {
-			rcu_read_unlock();
+		if (tb->tb_id == id)
 			return tb;
-		}
 	}
-	rcu_read_unlock();
 	return NULL;
 }
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
@@ -167,16 +164,18 @@ static inline unsigned int __inet_dev_addr_type(struct net *net,
 	if (ipv4_is_multicast(addr))
 		return RTN_MULTICAST;
 
+	rcu_read_lock();
+
 	local_table = fib_get_table(net, RT_TABLE_LOCAL);
 	if (local_table) {
 		ret = RTN_UNICAST;
-		rcu_read_lock();
 		if (!fib_table_lookup(local_table, &fl4, &res, FIB_LOOKUP_NOREF)) {
 			if (!dev || dev == res.fi->fib_dev)
 				ret = res.type;
 		}
-		rcu_read_unlock();
 	}
+
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -919,7 +918,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
 #undef BRD1_OK
 }
 
-static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
+static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
 {
 
 	struct fib_result       res;
@@ -929,6 +928,11 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
 		.flowi4_tos = frn->fl_tos,
 		.flowi4_scope = frn->fl_scope,
 	};
+	struct fib_table *tb;
+
+	rcu_read_lock();
+
+	tb = fib_get_table(net, frn->tb_id_in);
 
 	frn->err = -ENOENT;
 	if (tb) {
@@ -945,6 +949,8 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb)
 		}
 		local_bh_enable();
 	}
+
+	rcu_read_unlock();
 }
 
 static void nl_fib_input(struct sk_buff *skb)
@@ -952,7 +958,6 @@ static void nl_fib_input(struct sk_buff *skb)
 	struct net *net;
 	struct fib_result_nl *frn;
 	struct nlmsghdr *nlh;
-	struct fib_table *tb;
 	u32 portid;
 
 	net = sock_net(skb->sk);
@@ -967,9 +972,7 @@ static void nl_fib_input(struct sk_buff *skb)
 	nlh = nlmsg_hdr(skb);
 
 	frn = (struct fib_result_nl *) nlmsg_data(nlh);
-	tb = fib_get_table(net, frn->tb_id_in);
-
-	nl_fib_lookup(frn, tb);
+	nl_fib_lookup(net, frn);
 
 	portid = NETLINK_CB(skb).portid;      /* netlink portid */
 	NETLINK_CB(skb).portid = 0;        /* from kernel */
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 8f7bd56955b..d3db718be51 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -81,27 +81,25 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp,
 		break;
 
 	case FR_ACT_UNREACHABLE:
-		err = -ENETUNREACH;
-		goto errout;
+		return -ENETUNREACH;
 
 	case FR_ACT_PROHIBIT:
-		err = -EACCES;
-		goto errout;
+		return -EACCES;
 
 	case FR_ACT_BLACKHOLE:
 	default:
-		err = -EINVAL;
-		goto errout;
+		return -EINVAL;
 	}
 
+	rcu_read_lock();
+
 	tbl = fib_get_table(rule->fr_net, rule->table);
-	if (!tbl)
-		goto errout;
+	if (tbl)
+		err = fib_table_lookup(tbl, &flp->u.ip4,
+				       (struct fib_result *)arg->result,
+				       arg->flags);
 
-	err = fib_table_lookup(tbl, &flp->u.ip4, (struct fib_result *) arg->result, arg->flags);
-	if (err > 0)
-		err = -EAGAIN;
-errout:
+	rcu_read_unlock();
 	return err;
 }
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 28a3065470b..987b06d1eff 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1181,72 +1181,6 @@ err:
 	return err;
 }
 
-/* should be called with rcu_read_lock */
-static int check_leaf(struct fib_table *tb, struct trie *t, struct tnode *l,
-		      t_key key,  const struct flowi4 *flp,
-		      struct fib_result *res, int fib_flags)
-{
-	struct leaf_info *li;
-	struct hlist_head *hhead = &l->list;
-
-	hlist_for_each_entry_rcu(li, hhead, hlist) {
-		struct fib_alias *fa;
-
-		if (l->key != (key & li->mask_plen))
-			continue;
-
-		list_for_each_entry_rcu(fa, &li->falh, fa_list) {
-			struct fib_info *fi = fa->fa_info;
-			int nhsel, err;
-
-			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
-				continue;
-			if (fi->fib_dead)
-				continue;
-			if (fa->fa_info->fib_scope < flp->flowi4_scope)
-				continue;
-			fib_alias_accessed(fa);
-			err = fib_props[fa->fa_type].error;
-			if (unlikely(err < 0)) {
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-				this_cpu_inc(t->stats->semantic_match_passed);
-#endif
-				return err;
-			}
-			if (fi->fib_flags & RTNH_F_DEAD)
-				continue;
-			for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
-				const struct fib_nh *nh = &fi->fib_nh[nhsel];
-
-				if (nh->nh_flags & RTNH_F_DEAD)
-					continue;
-				if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif)
-					continue;
-
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-				this_cpu_inc(t->stats->semantic_match_passed);
-#endif
-				res->prefixlen = li->plen;
-				res->nh_sel = nhsel;
-				res->type = fa->fa_type;
-				res->scope = fi->fib_scope;
-				res->fi = fi;
-				res->table = tb;
-				res->fa_head = &li->falh;
-				if (!(fib_flags & FIB_LOOKUP_NOREF))
-					atomic_inc(&fi->fib_clntref);
-				return 0;
-			}
-		}
-
-#ifdef CONFIG_IP_FIB_TRIE_STATS
-		this_cpu_inc(t->stats->semantic_match_miss);
-#endif
-	}
-
-	return 1;
-}
-
 static inline t_key prefix_mismatch(t_key key, struct tnode *n)
 {
 	t_key prefix = n->key;
@@ -1254,6 +1188,7 @@ static inline t_key prefix_mismatch(t_key key, struct tnode *n)
 	return (key ^ prefix) & (prefix | -prefix);
 }
 
+/* should be called with rcu_read_lock */
 int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 		     struct fib_result *res, int fib_flags)
 {
@@ -1263,14 +1198,12 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 #endif
 	const t_key key = ntohl(flp->daddr);
 	struct tnode *n, *pn;
+	struct leaf_info *li;
 	t_key cindex;
-	int ret = 1;
-
-	rcu_read_lock();
 
 	n = rcu_dereference(t->trie);
 	if (!n)
-		goto failed;
+		return -EAGAIN;
 
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 	this_cpu_inc(stats->gets);
@@ -1350,7 +1283,7 @@ backtrace:
 
 				pn = node_parent_rcu(pn);
 				if (unlikely(!pn))
-					goto failed;
+					return -EAGAIN;
 #ifdef CONFIG_IP_FIB_TRIE_STATS
 				this_cpu_inc(stats->backtrack);
 #endif
@@ -1368,12 +1301,62 @@ backtrace:
 
 found:
 	/* Step 3: Process the leaf, if that fails fall back to backtracing */
-	ret = check_leaf(tb, t, n, key, flp, res, fib_flags);
-	if (unlikely(ret > 0))
-		goto backtrace;
-failed:
-	rcu_read_unlock();
-	return ret;
+	hlist_for_each_entry_rcu(li, &n->list, hlist) {
+		struct fib_alias *fa;
+
+		if ((key ^ n->key) & li->mask_plen)
+			continue;
+
+		list_for_each_entry_rcu(fa, &li->falh, fa_list) {
+			struct fib_info *fi = fa->fa_info;
+			int nhsel, err;
+
+			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+				continue;
+			if (fi->fib_dead)
+				continue;
+			if (fa->fa_info->fib_scope < flp->flowi4_scope)
+				continue;
+			fib_alias_accessed(fa);
+			err = fib_props[fa->fa_type].error;
+			if (unlikely(err < 0)) {
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+				this_cpu_inc(stats->semantic_match_passed);
+#endif
+				return err;
+			}
+			if (fi->fib_flags & RTNH_F_DEAD)
+				continue;
+			for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
+				const struct fib_nh *nh = &fi->fib_nh[nhsel];
+
+				if (nh->nh_flags & RTNH_F_DEAD)
+					continue;
+				if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif)
+					continue;
+
+				if (!(fib_flags & FIB_LOOKUP_NOREF))
+					atomic_inc(&fi->fib_clntref);
+
+				res->prefixlen = li->plen;
+				res->nh_sel = nhsel;
+				res->type = fa->fa_type;
+				res->scope = fi->fib_scope;
+				res->fi = fi;
+				res->table = tb;
+				res->fa_head = &li->falh;
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+				this_cpu_inc(stats->semantic_match_passed);
+#endif
+				return err;
+			}
+		}
+
+#ifdef CONFIG_IP_FIB_TRIE_STATS
+		this_cpu_inc(stats->semantic_match_miss);
+#endif
+	}
+	goto backtrace;
 }
 EXPORT_SYMBOL_GPL(fib_table_lookup);
 
-- 
cgit v1.2.3-70-g09d2


From 3cf8e53a48f67ccdbc527860e852eef135971d98 Mon Sep 17 00:00:00 2001
From: Roger Chen <roger.chen@rock-chips.com>
Date: Mon, 29 Dec 2014 17:43:55 +0800
Subject: GMAC: define clock ID used for GMAC

changes since v2:
1. remove SCLK_MAC_PLL

Signed-off-by: Roger Chen <roger.chen@rock-chips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/dt-bindings/clock/rk3288-cru.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
index f60ce72a2b2..1c34c24efe0 100644
--- a/include/dt-bindings/clock/rk3288-cru.h
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -81,6 +81,9 @@
 #define SCLK_SDIO1_SAMPLE	120
 #define SCLK_EMMC_SAMPLE	121
 
+#define SCLK_MAC		151
+#define SCLK_MACREF_OUT		152
+
 #define DCLK_VOP0		190
 #define DCLK_VOP1		191
 
-- 
cgit v1.2.3-70-g09d2


From 7f605418837add961466dc66f7370332d44c1a92 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 2 Jan 2015 12:24:36 +0100
Subject: ALSA: ad1816a: Remove always NULL parameters

snd_ad1816a_pcm() and snd_ad1816a_timer() take a pointer to a pointer of a
PCM/timer where if this parameter is provided the newly allocated object is
stored. All callers pass NULL though, so remove the parameter. This makes
the code a bit cleaner and shorter.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/ad1816a.h         | 5 ++---
 sound/isa/ad1816a/ad1816a.c     | 5 ++---
 sound/isa/ad1816a/ad1816a_lib.c | 9 ++-------
 3 files changed, 6 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/sound/ad1816a.h b/include/sound/ad1816a.h
index abdf609c591..f2d3a6d0721 100644
--- a/include/sound/ad1816a.h
+++ b/include/sound/ad1816a.h
@@ -170,10 +170,9 @@ extern int snd_ad1816a_create(struct snd_card *card, unsigned long port,
 			      int irq, int dma1, int dma2,
 			      struct snd_ad1816a *chip);
 
-extern int snd_ad1816a_pcm(struct snd_ad1816a *chip, int device, struct snd_pcm **rpcm);
+extern int snd_ad1816a_pcm(struct snd_ad1816a *chip, int device);
 extern int snd_ad1816a_mixer(struct snd_ad1816a *chip);
-extern int snd_ad1816a_timer(struct snd_ad1816a *chip, int device,
-			     struct snd_timer **rtimer);
+extern int snd_ad1816a_timer(struct snd_ad1816a *chip, int device);
 #ifdef CONFIG_PM
 extern void snd_ad1816a_suspend(struct snd_ad1816a *chip);
 extern void snd_ad1816a_resume(struct snd_ad1816a *chip);
diff --git a/sound/isa/ad1816a/ad1816a.c b/sound/isa/ad1816a/ad1816a.c
index f481a41e027..769226515f0 100644
--- a/sound/isa/ad1816a/ad1816a.c
+++ b/sound/isa/ad1816a/ad1816a.c
@@ -142,7 +142,6 @@ static int snd_card_ad1816a_probe(int dev, struct pnp_card_link *pcard,
 	struct snd_card *card;
 	struct snd_ad1816a *chip;
 	struct snd_opl3 *opl3;
-	struct snd_timer *timer;
 
 	error = snd_card_new(&pcard->card->dev,
 			     index[dev], id[dev], THIS_MODULE,
@@ -172,7 +171,7 @@ static int snd_card_ad1816a_probe(int dev, struct pnp_card_link *pcard,
 	sprintf(card->longname, "%s, SS at 0x%lx, irq %d, dma %d&%d",
 		card->shortname, chip->port, irq[dev], dma1[dev], dma2[dev]);
 
-	if ((error = snd_ad1816a_pcm(chip, 0, NULL)) < 0) {
+	if ((error = snd_ad1816a_pcm(chip, 0)) < 0) {
 		snd_card_free(card);
 		return error;
 	}
@@ -182,7 +181,7 @@ static int snd_card_ad1816a_probe(int dev, struct pnp_card_link *pcard,
 		return error;
 	}
 
-	error = snd_ad1816a_timer(chip, 0, &timer);
+	error = snd_ad1816a_timer(chip, 0);
 	if (error < 0) {
 		snd_card_free(card);
 		return error;
diff --git a/sound/isa/ad1816a/ad1816a_lib.c b/sound/isa/ad1816a/ad1816a_lib.c
index 01a07986f4a..5f99102cc0c 100644
--- a/sound/isa/ad1816a/ad1816a_lib.c
+++ b/sound/isa/ad1816a/ad1816a_lib.c
@@ -675,7 +675,7 @@ static struct snd_pcm_ops snd_ad1816a_capture_ops = {
 	.pointer =	snd_ad1816a_capture_pointer,
 };
 
-int snd_ad1816a_pcm(struct snd_ad1816a *chip, int device, struct snd_pcm **rpcm)
+int snd_ad1816a_pcm(struct snd_ad1816a *chip, int device)
 {
 	int error;
 	struct snd_pcm *pcm;
@@ -697,13 +697,10 @@ int snd_ad1816a_pcm(struct snd_ad1816a *chip, int device, struct snd_pcm **rpcm)
 					      64*1024, chip->dma1 > 3 || chip->dma2 > 3 ? 128*1024 : 64*1024);
 
 	chip->pcm = pcm;
-	if (rpcm)
-		*rpcm = pcm;
 	return 0;
 }
 
-int snd_ad1816a_timer(struct snd_ad1816a *chip, int device,
-		      struct snd_timer **rtimer)
+int snd_ad1816a_timer(struct snd_ad1816a *chip, int device)
 {
 	struct snd_timer *timer;
 	struct snd_timer_id tid;
@@ -720,8 +717,6 @@ int snd_ad1816a_timer(struct snd_ad1816a *chip, int device,
 	timer->private_data = chip;
 	chip->timer = timer;
 	timer->hw = snd_ad1816a_timer_table;
-	if (rtimer)
-		*rtimer = timer;
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 4b8ab88518726197c8659bc9aca96c6af01dab57 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 2 Jan 2015 12:24:37 +0100
Subject: ALSA: es1688: Remove almost always NULL parameter

snd_es1688_pcm() takes a pointer to a pointer of a PCM where if this
parameter is provided the newly allocated PCM is stored. This PCM is also
available from the pcm field of the snd_es1688 struct that got passed to the
same function. This patch updates all callers which passed a pointer to use
that field instead and then removes the parameter from the function. This
makes the code a bit shorter and cleaner.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/es1688.h        | 3 +--
 sound/isa/es1688/es1688.c     | 7 +++----
 sound/isa/es1688/es1688_lib.c | 6 +-----
 sound/isa/gus/gusextreme.c    | 2 +-
 4 files changed, 6 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/sound/es1688.h b/include/sound/es1688.h
index 1d636a2d889..b34f23a5bb7 100644
--- a/include/sound/es1688.h
+++ b/include/sound/es1688.h
@@ -115,8 +115,7 @@ int snd_es1688_create(struct snd_card *card,
 		      int mpu_irq,
 		      int dma8,
 		      unsigned short hardware);
-int snd_es1688_pcm(struct snd_card *card, struct snd_es1688 *chip, int device,
-		   struct snd_pcm **rpcm);
+int snd_es1688_pcm(struct snd_card *card, struct snd_es1688 *chip, int device);
 int snd_es1688_mixer(struct snd_card *card, struct snd_es1688 *chip);
 int snd_es1688_reset(struct snd_es1688 *chip);
 
diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c
index 76001fe0579..1901c2bb6c3 100644
--- a/sound/isa/es1688/es1688.c
+++ b/sound/isa/es1688/es1688.c
@@ -138,10 +138,9 @@ static int snd_es1688_probe(struct snd_card *card, unsigned int n)
 {
 	struct snd_es1688 *chip = card->private_data;
 	struct snd_opl3 *opl3;
-	struct snd_pcm *pcm;
 	int error;
 
-	error = snd_es1688_pcm(card, chip, 0, &pcm);
+	error = snd_es1688_pcm(card, chip, 0);
 	if (error < 0)
 		return error;
 
@@ -150,9 +149,9 @@ static int snd_es1688_probe(struct snd_card *card, unsigned int n)
 		return error;
 
 	strlcpy(card->driver, "ES1688", sizeof(card->driver));
-	strlcpy(card->shortname, pcm->name, sizeof(card->shortname));
+	strlcpy(card->shortname, chip->pcm->name, sizeof(card->shortname));
 	snprintf(card->longname, sizeof(card->longname),
-		"%s at 0x%lx, irq %i, dma %i", pcm->name, chip->port,
+		"%s at 0x%lx, irq %i, dma %i", chip->pcm->name, chip->port,
 		 chip->irq, chip->dma8);
 
 	if (fm_port[n] == SNDRV_AUTO_PORT)
diff --git a/sound/isa/es1688/es1688_lib.c b/sound/isa/es1688/es1688_lib.c
index b5450143407..52aac846717 100644
--- a/sound/isa/es1688/es1688_lib.c
+++ b/sound/isa/es1688/es1688_lib.c
@@ -728,8 +728,7 @@ static struct snd_pcm_ops snd_es1688_capture_ops = {
 	.pointer =		snd_es1688_capture_pointer,
 };
 
-int snd_es1688_pcm(struct snd_card *card, struct snd_es1688 *chip,
-		   int device, struct snd_pcm **rpcm)
+int snd_es1688_pcm(struct snd_card *card, struct snd_es1688 *chip, int device)
 {
 	struct snd_pcm *pcm;
 	int err;
@@ -749,9 +748,6 @@ int snd_es1688_pcm(struct snd_card *card, struct snd_es1688 *chip,
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
 					      snd_dma_isa_data(),
 					      64*1024, 64*1024);
-
-	if (rpcm)
-		*rpcm = pcm;
 	return 0;
 }
 
diff --git a/sound/isa/gus/gusextreme.c b/sound/isa/gus/gusextreme.c
index 28a16936a39..acc655284a9 100644
--- a/sound/isa/gus/gusextreme.c
+++ b/sound/isa/gus/gusextreme.c
@@ -284,7 +284,7 @@ static int snd_gusextreme_probe(struct device *dev, unsigned int n)
 	}
 	gus->codec_flag = 1;
 
-	error = snd_es1688_pcm(card, es1688, 0, NULL);
+	error = snd_es1688_pcm(card, es1688, 0);
 	if (error < 0)
 		goto out;
 
-- 
cgit v1.2.3-70-g09d2


From db5abb3c499e553a8afedee1417d6a6308dda7bd Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 2 Jan 2015 12:24:39 +0100
Subject: ALSA: gus: Remove always NULL parameters

snd_gf1_pcm_new() and snd_gf1_rawmidi_new() take a pointer to a pointer of a
PCM/MIDI where if this parameter is provided the newly allocated object is
stored. All callers pass NULL though, so remove the parameter. This makes
the code a bit cleaner and shorter.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/gus.h        | 4 ++--
 sound/isa/gus/gus_pcm.c    | 6 +-----
 sound/isa/gus/gus_uart.c   | 6 +-----
 sound/isa/gus/gusclassic.c | 4 ++--
 sound/isa/gus/gusextreme.c | 2 +-
 sound/isa/gus/gusmax.c     | 4 ++--
 sound/isa/gus/interwave.c  | 4 ++--
 7 files changed, 11 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/sound/gus.h b/include/sound/gus.h
index 42905d811da..06bbdc25917 100644
--- a/include/sound/gus.h
+++ b/include/sound/gus.h
@@ -591,7 +591,7 @@ int snd_gf1_new_mixer(struct snd_gus_card * gus);
 
 /* gus_pcm.c */
 
-int snd_gf1_pcm_new(struct snd_gus_card * gus, int pcm_dev, int control_index, struct snd_pcm ** rpcm);
+int snd_gf1_pcm_new(struct snd_gus_card *gus, int pcm_dev, int control_index);
 
 #ifdef CONFIG_SND_DEBUG
 extern void snd_gf1_print_voice_registers(struct snd_gus_card * gus);
@@ -620,7 +620,7 @@ void snd_gus_irq_profile_init(struct snd_gus_card *gus);
 
 /* gus_uart.c */
 
-int snd_gf1_rawmidi_new(struct snd_gus_card * gus, int device, struct snd_rawmidi **rrawmidi);
+int snd_gf1_rawmidi_new(struct snd_gus_card *gus, int device);
 
 /* gus_dram.c */
 int snd_gus_dram_write(struct snd_gus_card *gus, char __user *ptr,
diff --git a/sound/isa/gus/gus_pcm.c b/sound/isa/gus/gus_pcm.c
index 2dcf45bf729..25f6788ccef 100644
--- a/sound/isa/gus/gus_pcm.c
+++ b/sound/isa/gus/gus_pcm.c
@@ -849,7 +849,7 @@ static struct snd_pcm_ops snd_gf1_pcm_capture_ops = {
 	.pointer =	snd_gf1_pcm_capture_pointer,
 };
 
-int snd_gf1_pcm_new(struct snd_gus_card * gus, int pcm_dev, int control_index, struct snd_pcm ** rpcm)
+int snd_gf1_pcm_new(struct snd_gus_card *gus, int pcm_dev, int control_index)
 {
 	struct snd_card *card;
 	struct snd_kcontrol *kctl;
@@ -857,8 +857,6 @@ int snd_gf1_pcm_new(struct snd_gus_card * gus, int pcm_dev, int control_index, s
 	struct snd_pcm_substream *substream;
 	int capture, err;
 
-	if (rpcm)
-		*rpcm = NULL;
 	card = gus->card;
 	capture = !gus->interwave && !gus->ess_flag && !gus->ace_flag ? 1 : 0;
 	err = snd_pcm_new(card,
@@ -903,8 +901,6 @@ int snd_gf1_pcm_new(struct snd_gus_card * gus, int pcm_dev, int control_index, s
 		return err;
 	kctl->id.index = control_index;
 
-	if (rpcm)
-		*rpcm = pcm;
 	return 0;
 }
 
diff --git a/sound/isa/gus/gus_uart.c b/sound/isa/gus/gus_uart.c
index 21cc42e4c4b..3992912743f 100644
--- a/sound/isa/gus/gus_uart.c
+++ b/sound/isa/gus/gus_uart.c
@@ -241,13 +241,11 @@ static struct snd_rawmidi_ops snd_gf1_uart_input =
 	.trigger =	snd_gf1_uart_input_trigger,
 };
 
-int snd_gf1_rawmidi_new(struct snd_gus_card * gus, int device, struct snd_rawmidi ** rrawmidi)
+int snd_gf1_rawmidi_new(struct snd_gus_card *gus, int device)
 {
 	struct snd_rawmidi *rmidi;
 	int err;
 
-	if (rrawmidi)
-		*rrawmidi = NULL;
 	if ((err = snd_rawmidi_new(gus->card, "GF1", device, 1, 1, &rmidi)) < 0)
 		return err;
 	strcpy(rmidi->name, gus->interwave ? "AMD InterWave" : "GF1");
@@ -256,7 +254,5 @@ int snd_gf1_rawmidi_new(struct snd_gus_card * gus, int device, struct snd_rawmid
 	rmidi->info_flags |= SNDRV_RAWMIDI_INFO_OUTPUT | SNDRV_RAWMIDI_INFO_INPUT | SNDRV_RAWMIDI_INFO_DUPLEX;
 	rmidi->private_data = gus;
 	gus->midi_uart = rmidi;
-	if (rrawmidi)
-		*rrawmidi = rmidi;
 	return err;
 }
diff --git a/sound/isa/gus/gusclassic.c b/sound/isa/gus/gusclassic.c
index 7ce29ffa1af..f0019715d82 100644
--- a/sound/isa/gus/gusclassic.c
+++ b/sound/isa/gus/gusclassic.c
@@ -181,12 +181,12 @@ static int snd_gusclassic_probe(struct device *dev, unsigned int n)
 	if (error < 0)
 		goto out;
 
-	error = snd_gf1_pcm_new(gus, 0, 0, NULL);
+	error = snd_gf1_pcm_new(gus, 0, 0);
 	if (error < 0)
 		goto out;
 
 	if (!gus->ace_flag) {
-		error = snd_gf1_rawmidi_new(gus, 0, NULL);
+		error = snd_gf1_rawmidi_new(gus, 0);
 		if (error < 0)
 			goto out;
 	}
diff --git a/sound/isa/gus/gusextreme.c b/sound/isa/gus/gusextreme.c
index acc655284a9..693d95f4680 100644
--- a/sound/isa/gus/gusextreme.c
+++ b/sound/isa/gus/gusextreme.c
@@ -295,7 +295,7 @@ static int snd_gusextreme_probe(struct device *dev, unsigned int n)
 	snd_component_add(card, "ES1688");
 
 	if (pcm_channels[n] > 0) {
-		error = snd_gf1_pcm_new(gus, 1, 1, NULL);
+		error = snd_gf1_pcm_new(gus, 1, 1);
 		if (error < 0)
 			goto out;
 	}
diff --git a/sound/isa/gus/gusmax.c b/sound/isa/gus/gusmax.c
index 39df36ca3ac..b2b3734a8e7 100644
--- a/sound/isa/gus/gusmax.c
+++ b/sound/isa/gus/gusmax.c
@@ -322,14 +322,14 @@ static int snd_gusmax_probe(struct device *pdev, unsigned int dev)
 		goto _err;
 
 	if (pcm_channels[dev] > 0) {
-		if ((err = snd_gf1_pcm_new(gus, 1, 1, NULL)) < 0)
+		if ((err = snd_gf1_pcm_new(gus, 1, 1)) < 0)
 			goto _err;
 	}
 	err = snd_gusmax_mixer(wss);
 	if (err < 0)
 		goto _err;
 
-	err = snd_gf1_rawmidi_new(gus, 0, NULL);
+	err = snd_gf1_rawmidi_new(gus, 0);
 	if (err < 0)
 		goto _err;
 
diff --git a/sound/isa/gus/interwave.c b/sound/isa/gus/interwave.c
index ad55e5cb8e9..8ea54a7f78d 100644
--- a/sound/isa/gus/interwave.c
+++ b/sound/isa/gus/interwave.c
@@ -711,7 +711,7 @@ static int snd_interwave_probe(struct snd_card *card, int dev)
 		return err;
 
 	if (pcm_channels[dev] > 0) {
-		err = snd_gf1_pcm_new(gus, 1, 1, NULL);
+		err = snd_gf1_pcm_new(gus, 1, 1);
 		if (err < 0)
 			return err;
 	}
@@ -740,7 +740,7 @@ static int snd_interwave_probe(struct snd_card *card, int dev)
 #endif
 
 	gus->uart_enable = midi[dev];
-	if ((err = snd_gf1_rawmidi_new(gus, 0, NULL)) < 0)
+	if ((err = snd_gf1_rawmidi_new(gus, 0)) < 0)
 		return err;
 
 #ifndef SNDRV_STB
-- 
cgit v1.2.3-70-g09d2


From 8c77629996cbabee1d5b6d9b0d1e97cbca197ba1 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 2 Jan 2015 12:24:41 +0100
Subject: ALSA: sb8: Remove always NULL parameters

snd_sb8dsp_pcm() and snd_sb8dsp_midi() take a pointer to a pointer of a
PCM/MIDI where if this parameter is provided the newly allocated object is
stored. All callers pass NULL though, so remove the parameter. This makes
the code a bit cleaner and shorter.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/sb.h      | 4 ++--
 sound/isa/sb/jazz16.c   | 2 +-
 sound/isa/sb/sb8.c      | 4 ++--
 sound/isa/sb/sb8_main.c | 6 +-----
 sound/isa/sb/sb8_midi.c | 6 +-----
 5 files changed, 7 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/sound/sb.h b/include/sound/sb.h
index ba396032964..13438ff3e5a 100644
--- a/include/sound/sb.h
+++ b/include/sound/sb.h
@@ -308,7 +308,7 @@ void snd_sbmixer_resume(struct snd_sb *chip);
 #endif
 
 /* sb8_init.c */
-int snd_sb8dsp_pcm(struct snd_sb *chip, int device, struct snd_pcm ** rpcm);
+int snd_sb8dsp_pcm(struct snd_sb *chip, int device);
 /* sb8.c */
 irqreturn_t snd_sb8dsp_interrupt(struct snd_sb *chip);
 int snd_sb8_playback_open(struct snd_pcm_substream *substream);
@@ -317,7 +317,7 @@ int snd_sb8_playback_close(struct snd_pcm_substream *substream);
 int snd_sb8_capture_close(struct snd_pcm_substream *substream);
 /* midi8.c */
 irqreturn_t snd_sb8dsp_midi_interrupt(struct snd_sb *chip);
-int snd_sb8dsp_midi(struct snd_sb *chip, int device, struct snd_rawmidi ** rrawmidi);
+int snd_sb8dsp_midi(struct snd_sb *chip, int device);
 
 /* sb16_init.c */
 int snd_sb16dsp_pcm(struct snd_sb *chip, int device, struct snd_pcm ** rpcm);
diff --git a/sound/isa/sb/jazz16.c b/sound/isa/sb/jazz16.c
index 90d2eba549e..6b4884d052a 100644
--- a/sound/isa/sb/jazz16.c
+++ b/sound/isa/sb/jazz16.c
@@ -297,7 +297,7 @@ static int snd_jazz16_probe(struct device *devptr, unsigned int dev)
 		"Media Vision Jazz16 at 0x%lx, irq %d, dma8 %d, dma16 %d",
 		port[dev], xirq, xdma8, xdma16);
 
-	err = snd_sb8dsp_pcm(chip, 0, NULL);
+	err = snd_sb8dsp_pcm(chip, 0);
 	if (err < 0)
 		goto err_free;
 	err = snd_sbmixer_new(chip);
diff --git a/sound/isa/sb/sb8.c b/sound/isa/sb/sb8.c
index 6c32b3aa34a..b8e2391c33f 100644
--- a/sound/isa/sb/sb8.c
+++ b/sound/isa/sb/sb8.c
@@ -157,7 +157,7 @@ static int snd_sb8_probe(struct device *pdev, unsigned int dev)
 		goto _err;
 	}
 
-	if ((err = snd_sb8dsp_pcm(chip, 0, NULL)) < 0)
+	if ((err = snd_sb8dsp_pcm(chip, 0)) < 0)
 		goto _err;
 
 	if ((err = snd_sbmixer_new(chip)) < 0)
@@ -182,7 +182,7 @@ static int snd_sb8_probe(struct device *pdev, unsigned int dev)
 			goto _err;
 	}
 
-	if ((err = snd_sb8dsp_midi(chip, 0, NULL)) < 0)
+	if ((err = snd_sb8dsp_midi(chip, 0)) < 0)
 		goto _err;
 
 	strcpy(card->driver, chip->hardware == SB_HW_PRO ? "SB Pro" : "SB8");
diff --git a/sound/isa/sb/sb8_main.c b/sound/isa/sb/sb8_main.c
index 24d4121ab0e..d4d8b0e604e 100644
--- a/sound/isa/sb/sb8_main.c
+++ b/sound/isa/sb/sb8_main.c
@@ -594,15 +594,13 @@ static struct snd_pcm_ops snd_sb8_capture_ops = {
 	.pointer =		snd_sb8_capture_pointer,
 };
 
-int snd_sb8dsp_pcm(struct snd_sb *chip, int device, struct snd_pcm ** rpcm)
+int snd_sb8dsp_pcm(struct snd_sb *chip, int device)
 {
 	struct snd_card *card = chip->card;
 	struct snd_pcm *pcm;
 	int err;
 	size_t max_prealloc = 64 * 1024;
 
-	if (rpcm)
-		*rpcm = NULL;
 	if ((err = snd_pcm_new(card, "SB8 DSP", device, 1, 1, &pcm)) < 0)
 		return err;
 	sprintf(pcm->name, "DSP v%i.%i", chip->version >> 8, chip->version & 0xff);
@@ -618,8 +616,6 @@ int snd_sb8dsp_pcm(struct snd_sb *chip, int device, struct snd_pcm ** rpcm)
 					      snd_dma_isa_data(),
 					      64*1024, max_prealloc);
 
-	if (rpcm)
-		*rpcm = pcm;
 	return 0;
 }
 
diff --git a/sound/isa/sb/sb8_midi.c b/sound/isa/sb/sb8_midi.c
index 988a8b73475..ffc71f0267d 100644
--- a/sound/isa/sb/sb8_midi.c
+++ b/sound/isa/sb/sb8_midi.c
@@ -263,13 +263,11 @@ static struct snd_rawmidi_ops snd_sb8dsp_midi_input =
 	.trigger =	snd_sb8dsp_midi_input_trigger,
 };
 
-int snd_sb8dsp_midi(struct snd_sb *chip, int device, struct snd_rawmidi ** rrawmidi)
+int snd_sb8dsp_midi(struct snd_sb *chip, int device)
 {
 	struct snd_rawmidi *rmidi;
 	int err;
 
-	if (rrawmidi)
-		*rrawmidi = NULL;
 	if ((err = snd_rawmidi_new(chip->card, "SB8 MIDI", device, 1, 1, &rmidi)) < 0)
 		return err;
 	strcpy(rmidi->name, "SB8 MIDI");
@@ -280,7 +278,5 @@ int snd_sb8dsp_midi(struct snd_sb *chip, int device, struct snd_rawmidi ** rrawm
 		rmidi->info_flags |= SNDRV_RAWMIDI_INFO_DUPLEX;
 	rmidi->private_data = chip;
 	chip->rmidi = rmidi;
-	if (rrawmidi)
-		*rrawmidi = rmidi;
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From 92533f188862fbefe357ada4e4af67b8e730e680 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 2 Jan 2015 12:24:42 +0100
Subject: ASoC: sb16: Simplify snd_sb16dsp_pcm()

All callers of snd_sb16dsp_pcm() always pass the pcm field of the first
parameter as the last parameter. Simplify the function by moving this inside
the function itself. This makes the code a bit shorter and cleaner.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/sb.h       | 2 +-
 sound/isa/als100.c       | 2 +-
 sound/isa/sb/sb16.c      | 2 +-
 sound/isa/sb/sb16_main.c | 8 ++------
 sound/pci/cs5530.c       | 2 +-
 5 files changed, 6 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/sound/sb.h b/include/sound/sb.h
index 13438ff3e5a..33e2d11deed 100644
--- a/include/sound/sb.h
+++ b/include/sound/sb.h
@@ -320,7 +320,7 @@ irqreturn_t snd_sb8dsp_midi_interrupt(struct snd_sb *chip);
 int snd_sb8dsp_midi(struct snd_sb *chip, int device);
 
 /* sb16_init.c */
-int snd_sb16dsp_pcm(struct snd_sb *chip, int device, struct snd_pcm ** rpcm);
+int snd_sb16dsp_pcm(struct snd_sb *chip, int device);
 const struct snd_pcm_ops *snd_sb16dsp_get_pcm_ops(int direction);
 int snd_sb16dsp_configure(struct snd_sb *chip);
 /* sb16.c */
diff --git a/sound/isa/als100.c b/sound/isa/als100.c
index 32d01525211..bc9ea306ee0 100644
--- a/sound/isa/als100.c
+++ b/sound/isa/als100.c
@@ -233,7 +233,7 @@ static int snd_card_als100_probe(int dev,
 			irq[dev], dma8[dev], dma16[dev]);
 	}
 
-	if ((error = snd_sb16dsp_pcm(chip, 0, &chip->pcm)) < 0) {
+	if ((error = snd_sb16dsp_pcm(chip, 0)) < 0) {
 		snd_card_free(card);
 		return error;
 	}
diff --git a/sound/isa/sb/sb16.c b/sound/isa/sb/sb16.c
index 3f694543a7e..4a7d7c89808 100644
--- a/sound/isa/sb/sb16.c
+++ b/sound/isa/sb/sb16.c
@@ -374,7 +374,7 @@ static int snd_sb16_probe(struct snd_card *card, int dev)
 	if (! is_isapnp_selected(dev) && (err = snd_sb16dsp_configure(chip)) < 0)
 		return err;
 
-	if ((err = snd_sb16dsp_pcm(chip, 0, &chip->pcm)) < 0)
+	if ((err = snd_sb16dsp_pcm(chip, 0)) < 0)
 		return err;
 
 	strcpy(card->driver,
diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index 72b10f4f3e7..63d11b7b9fe 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -860,19 +860,18 @@ static struct snd_pcm_ops snd_sb16_capture_ops = {
 	.pointer =	snd_sb16_capture_pointer,
 };
 
-int snd_sb16dsp_pcm(struct snd_sb * chip, int device, struct snd_pcm ** rpcm)
+int snd_sb16dsp_pcm(struct snd_sb *chip, int device)
 {
 	struct snd_card *card = chip->card;
 	struct snd_pcm *pcm;
 	int err;
 
-	if (rpcm)
-		*rpcm = NULL;
 	if ((err = snd_pcm_new(card, "SB16 DSP", device, 1, 1, &pcm)) < 0)
 		return err;
 	sprintf(pcm->name, "DSP v%i.%i", chip->version >> 8, chip->version & 0xff);
 	pcm->info_flags = SNDRV_PCM_INFO_JOINT_DUPLEX;
 	pcm->private_data = chip;
+	chip->pcm = pcm;
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &snd_sb16_playback_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_sb16_capture_ops);
@@ -885,9 +884,6 @@ int snd_sb16dsp_pcm(struct snd_sb * chip, int device, struct snd_pcm ** rpcm)
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV,
 					      snd_dma_isa_data(),
 					      64*1024, 128*1024);
-
-	if (rpcm)
-		*rpcm = pcm;
 	return 0;
 }
 
diff --git a/sound/pci/cs5530.c b/sound/pci/cs5530.c
index b1025507a46..0a8cf94c485 100644
--- a/sound/pci/cs5530.c
+++ b/sound/pci/cs5530.c
@@ -223,7 +223,7 @@ static int snd_cs5530_create(struct snd_card *card,
 		return err;
 	}
 
-	err = snd_sb16dsp_pcm(chip->sb, 0, &chip->sb->pcm);
+	err = snd_sb16dsp_pcm(chip->sb, 0);
 	if (err < 0) {
 		dev_err(card->dev, "Could not create PCM\n");
 		snd_cs5530_free(chip);
-- 
cgit v1.2.3-70-g09d2


From fa60c065694a81e534c61809ab7dd419366e9335 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 2 Jan 2015 12:24:43 +0100
Subject: ALSA: wss: Remove (almost) always NULL parameters

Most callers of snd_wss_pcm(), snd_wss_timer() and snd_cs4236_pcm() pass
NULL as the last parameter, some callers pass a pointer but never use it
after the function has been called and only a few callers pass a pointer and
actually use it. The later is only the case for snd_wss_pcm() for
snd_cs4236_pcm() and it is possible to get the same PCM object by accessing
the pcm field of the snd_wss struct that was passed as the first parameter.

This function removes the last parameters from the functions mentioned above
and updates the callers which used it to use chip->pcm instead. This allows
us to slightly simplify the functions since they don't have to check and set
the last parameter anymore which makes the code slightly shorter and
cleaner.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/wss.h                |  6 +++---
 sound/isa/ad1848/ad1848.c          |  7 +++----
 sound/isa/azt2320.c                |  4 ++--
 sound/isa/cmi8328.c                |  4 ++--
 sound/isa/cs423x/cs4231.c          |  9 ++++-----
 sound/isa/cs423x/cs4236.c          | 13 ++++++-------
 sound/isa/cs423x/cs4236_lib.c      |  9 +++------
 sound/isa/galaxy/galaxy.c          |  4 ++--
 sound/isa/gus/gusmax.c             |  4 ++--
 sound/isa/gus/interwave.c          | 10 +++++-----
 sound/isa/opl3sa2.c                |  4 ++--
 sound/isa/opti9xx/miro.c           | 12 +++++-------
 sound/isa/opti9xx/opti92x-ad1848.c | 13 +++++--------
 sound/isa/sc6000.c                 |  2 +-
 sound/isa/sscape.c                 |  5 ++---
 sound/isa/wavefront/wavefront.c    |  4 ++--
 sound/isa/wss/wss_lib.c            |  8 ++------
 17 files changed, 51 insertions(+), 67 deletions(-)

(limited to 'include')

diff --git a/include/sound/wss.h b/include/sound/wss.h
index 0c7f034f1e8..1823e3a964e 100644
--- a/include/sound/wss.h
+++ b/include/sound/wss.h
@@ -154,8 +154,8 @@ int snd_wss_create(struct snd_card *card,
 		      unsigned short hardware,
 		      unsigned short hwshare,
 		      struct snd_wss **rchip);
-int snd_wss_pcm(struct snd_wss *chip, int device, struct snd_pcm **rpcm);
-int snd_wss_timer(struct snd_wss *chip, int device, struct snd_timer **rtimer);
+int snd_wss_pcm(struct snd_wss *chip, int device);
+int snd_wss_timer(struct snd_wss *chip, int device);
 int snd_wss_mixer(struct snd_wss *chip);
 
 const struct snd_pcm_ops *snd_wss_get_pcm_ops(int direction);
@@ -167,7 +167,7 @@ int snd_cs4236_create(struct snd_card *card,
 		      unsigned short hardware,
 		      unsigned short hwshare,
 		      struct snd_wss **rchip);
-int snd_cs4236_pcm(struct snd_wss *chip, int device, struct snd_pcm **rpcm);
+int snd_cs4236_pcm(struct snd_wss *chip, int device);
 int snd_cs4236_mixer(struct snd_wss *chip);
 
 /*
diff --git a/sound/isa/ad1848/ad1848.c b/sound/isa/ad1848/ad1848.c
index 093f22a464d..f159da4ec89 100644
--- a/sound/isa/ad1848/ad1848.c
+++ b/sound/isa/ad1848/ad1848.c
@@ -88,7 +88,6 @@ static int snd_ad1848_probe(struct device *dev, unsigned int n)
 {
 	struct snd_card *card;
 	struct snd_wss *chip;
-	struct snd_pcm *pcm;
 	int error;
 
 	error = snd_card_new(dev, index[n], id[n], THIS_MODULE, 0, &card);
@@ -103,7 +102,7 @@ static int snd_ad1848_probe(struct device *dev, unsigned int n)
 
 	card->private_data = chip;
 
-	error = snd_wss_pcm(chip, 0, &pcm);
+	error = snd_wss_pcm(chip, 0);
 	if (error < 0)
 		goto out;
 
@@ -112,10 +111,10 @@ static int snd_ad1848_probe(struct device *dev, unsigned int n)
 		goto out;
 
 	strcpy(card->driver, "AD1848");
-	strcpy(card->shortname, pcm->name);
+	strcpy(card->shortname, chip->pcm->name);
 
 	sprintf(card->longname, "%s at 0x%lx, irq %d, dma %d",
-		pcm->name, chip->port, irq[n], dma1[n]);
+		chip->pcm->name, chip->port, irq[n], dma1[n]);
 	if (thinkpad[n])
 		strcat(card->longname, " [Thinkpad]");
 
diff --git a/sound/isa/azt2320.c b/sound/isa/azt2320.c
index 0ea75fc6207..b8e768e5ce8 100644
--- a/sound/isa/azt2320.c
+++ b/sound/isa/azt2320.c
@@ -215,7 +215,7 @@ static int snd_card_azt2320_probe(int dev,
 	sprintf(card->longname, "%s, WSS at 0x%lx, irq %i, dma %i&%i",
 		card->shortname, chip->port, irq[dev], dma1[dev], dma2[dev]);
 
-	error = snd_wss_pcm(chip, 0, NULL);
+	error = snd_wss_pcm(chip, 0);
 	if (error < 0) {
 		snd_card_free(card);
 		return error;
@@ -225,7 +225,7 @@ static int snd_card_azt2320_probe(int dev,
 		snd_card_free(card);
 		return error;
 	}
-	error = snd_wss_timer(chip, 0, NULL);
+	error = snd_wss_timer(chip, 0);
 	if (error < 0) {
 		snd_card_free(card);
 		return error;
diff --git a/sound/isa/cmi8328.c b/sound/isa/cmi8328.c
index 4778852a120..2c89d95da67 100644
--- a/sound/isa/cmi8328.c
+++ b/sound/isa/cmi8328.c
@@ -307,7 +307,7 @@ static int snd_cmi8328_probe(struct device *pdev, unsigned int ndev)
 	if (err < 0)
 		goto error;
 
-	err = snd_wss_pcm(cmi->wss, 0, NULL);
+	err = snd_wss_pcm(cmi->wss, 0);
 	if (err < 0)
 		goto error;
 
@@ -318,7 +318,7 @@ static int snd_cmi8328_probe(struct device *pdev, unsigned int ndev)
 	if (err < 0)
 		goto error;
 
-	if (snd_wss_timer(cmi->wss, 0, NULL) < 0)
+	if (snd_wss_timer(cmi->wss, 0) < 0)
 		snd_printk(KERN_WARNING "error initializing WSS timer\n");
 
 	if (mpuport[ndev] == SNDRV_AUTO_PORT) {
diff --git a/sound/isa/cs423x/cs4231.c b/sound/isa/cs423x/cs4231.c
index 7dba07a4343..282cd75d223 100644
--- a/sound/isa/cs423x/cs4231.c
+++ b/sound/isa/cs423x/cs4231.c
@@ -92,7 +92,6 @@ static int snd_cs4231_probe(struct device *dev, unsigned int n)
 {
 	struct snd_card *card;
 	struct snd_wss *chip;
-	struct snd_pcm *pcm;
 	int error;
 
 	error = snd_card_new(dev, index[n], id[n], THIS_MODULE, 0, &card);
@@ -106,15 +105,15 @@ static int snd_cs4231_probe(struct device *dev, unsigned int n)
 
 	card->private_data = chip;
 
-	error = snd_wss_pcm(chip, 0, &pcm);
+	error = snd_wss_pcm(chip, 0);
 	if (error < 0)
 		goto out;
 
 	strcpy(card->driver, "CS4231");
-	strcpy(card->shortname, pcm->name);
+	strcpy(card->shortname, chip->pcm->name);
 
 	sprintf(card->longname, "%s at 0x%lx, irq %d, dma %d",
-		pcm->name, chip->port, irq[n], dma1[n]);
+		chip->pcm->name, chip->port, irq[n], dma1[n]);
 	if (dma2[n] >= 0)
 		sprintf(card->longname + strlen(card->longname), "&%d", dma2[n]);
 
@@ -122,7 +121,7 @@ static int snd_cs4231_probe(struct device *dev, unsigned int n)
 	if (error < 0)
 		goto out;
 
-	error = snd_wss_timer(chip, 0, NULL);
+	error = snd_wss_timer(chip, 0);
 	if (error < 0)
 		goto out;
 
diff --git a/sound/isa/cs423x/cs4236.c b/sound/isa/cs423x/cs4236.c
index 750f51c904f..9d7582c90a9 100644
--- a/sound/isa/cs423x/cs4236.c
+++ b/sound/isa/cs423x/cs4236.c
@@ -382,7 +382,6 @@ static int snd_cs423x_card_new(struct device *pdev, int dev,
 static int snd_cs423x_probe(struct snd_card *card, int dev)
 {
 	struct snd_card_cs4236 *acard;
-	struct snd_pcm *pcm;
 	struct snd_wss *chip;
 	struct snd_opl3 *opl3;
 	int err;
@@ -404,7 +403,7 @@ static int snd_cs423x_probe(struct snd_card *card, int dev)
 	acard->chip = chip;
 	if (chip->hardware & WSS_HW_CS4236B_MASK) {
 
-		err = snd_cs4236_pcm(chip, 0, &pcm);
+		err = snd_cs4236_pcm(chip, 0);
 		if (err < 0)
 			return err;
 
@@ -412,7 +411,7 @@ static int snd_cs423x_probe(struct snd_card *card, int dev)
 		if (err < 0)
 			return err;
 	} else {
-		err = snd_wss_pcm(chip, 0, &pcm);
+		err = snd_wss_pcm(chip, 0);
 		if (err < 0)
 			return err;
 
@@ -420,17 +419,17 @@ static int snd_cs423x_probe(struct snd_card *card, int dev)
 		if (err < 0)
 			return err;
 	}
-	strcpy(card->driver, pcm->name);
-	strcpy(card->shortname, pcm->name);
+	strcpy(card->driver, chip->pcm->name);
+	strcpy(card->shortname, chip->pcm->name);
 	sprintf(card->longname, "%s at 0x%lx, irq %i, dma %i",
-		pcm->name,
+		chip->pcm->name,
 		chip->port,
 		irq[dev],
 		dma1[dev]);
 	if (dma2[dev] >= 0)
 		sprintf(card->longname + strlen(card->longname), "&%d", dma2[dev]);
 
-	err = snd_wss_timer(chip, 0, NULL);
+	err = snd_wss_timer(chip, 0);
 	if (err < 0)
 		return err;
 
diff --git a/sound/isa/cs423x/cs4236_lib.c b/sound/isa/cs423x/cs4236_lib.c
index c5adca30063..add7ffc072c 100644
--- a/sound/isa/cs423x/cs4236_lib.c
+++ b/sound/isa/cs423x/cs4236_lib.c
@@ -376,17 +376,14 @@ int snd_cs4236_create(struct snd_card *card,
 	return 0;
 }
 
-int snd_cs4236_pcm(struct snd_wss *chip, int device, struct snd_pcm **rpcm)
+int snd_cs4236_pcm(struct snd_wss *chip, int device)
 {
-	struct snd_pcm *pcm;
 	int err;
 	
-	err = snd_wss_pcm(chip, device, &pcm);
+	err = snd_wss_pcm(chip, device);
 	if (err < 0)
 		return err;
-	pcm->info_flags &= ~SNDRV_PCM_INFO_JOINT_DUPLEX;
-	if (rpcm)
-		*rpcm = pcm;
+	chip->pcm->info_flags &= ~SNDRV_PCM_INFO_JOINT_DUPLEX;
 	return 0;
 }
 
diff --git a/sound/isa/galaxy/galaxy.c b/sound/isa/galaxy/galaxy.c
index 1eb2b1ec0fd..32278847884 100644
--- a/sound/isa/galaxy/galaxy.c
+++ b/sound/isa/galaxy/galaxy.c
@@ -569,7 +569,7 @@ static int snd_galaxy_probe(struct device *dev, unsigned int n)
 	if (err < 0)
 		goto error;
 
-	err = snd_wss_pcm(chip, 0, NULL);
+	err = snd_wss_pcm(chip, 0);
 	if (err < 0)
 		goto error;
 
@@ -577,7 +577,7 @@ static int snd_galaxy_probe(struct device *dev, unsigned int n)
 	if (err < 0)
 		goto error;
 
-	err = snd_wss_timer(chip, 0, NULL);
+	err = snd_wss_timer(chip, 0);
 	if (err < 0)
 		goto error;
 
diff --git a/sound/isa/gus/gusmax.c b/sound/isa/gus/gusmax.c
index b2b3734a8e7..8216e8d8f01 100644
--- a/sound/isa/gus/gusmax.c
+++ b/sound/isa/gus/gusmax.c
@@ -309,7 +309,7 @@ static int snd_gusmax_probe(struct device *pdev, unsigned int dev)
 	if (err < 0)
 		goto _err;
 
-	err = snd_wss_pcm(wss, 0, NULL);
+	err = snd_wss_pcm(wss, 0);
 	if (err < 0)
 		goto _err;
 
@@ -317,7 +317,7 @@ static int snd_gusmax_probe(struct device *pdev, unsigned int dev)
 	if (err < 0)
 		goto _err;
 
-	err = snd_wss_timer(wss, 2, NULL);
+	err = snd_wss_timer(wss, 2);
 	if (err < 0)
 		goto _err;
 
diff --git a/sound/isa/gus/interwave.c b/sound/isa/gus/interwave.c
index 8ea54a7f78d..70d0040484c 100644
--- a/sound/isa/gus/interwave.c
+++ b/sound/isa/gus/interwave.c
@@ -647,7 +647,6 @@ static int snd_interwave_probe(struct snd_card *card, int dev)
 #ifdef SNDRV_STB
 	struct snd_i2c_bus *i2c_bus;
 #endif
-	struct snd_pcm *pcm;
 	char *str;
 	int err;
 
@@ -695,14 +694,15 @@ static int snd_interwave_probe(struct snd_card *card, int dev)
 	if (err < 0)
 		return err;
 
-	err = snd_wss_pcm(wss, 0, &pcm);
+	err = snd_wss_pcm(wss, 0);
 	if (err < 0)
 		return err;
 
-	sprintf(pcm->name + strlen(pcm->name), " rev %c", gus->revision + 'A');
-	strcat(pcm->name, " (codec)");
+	sprintf(wss->pcm->name + strlen(wss->pcm->name), " rev %c",
+		gus->revision + 'A');
+	strcat(wss->pcm->name, " (codec)");
 
-	err = snd_wss_timer(wss, 2, NULL);
+	err = snd_wss_timer(wss, 2);
 	if (err < 0)
 		return err;
 
diff --git a/sound/isa/opl3sa2.c b/sound/isa/opl3sa2.c
index a219bc37816..d7aff527da8 100644
--- a/sound/isa/opl3sa2.c
+++ b/sound/isa/opl3sa2.c
@@ -684,7 +684,7 @@ static int snd_opl3sa2_probe(struct snd_card *card, int dev)
 		return err;
 	}
 	chip->wss = wss;
-	err = snd_wss_pcm(wss, 0, NULL);
+	err = snd_wss_pcm(wss, 0);
 	if (err < 0)
 		return err;
 	err = snd_wss_mixer(wss);
@@ -693,7 +693,7 @@ static int snd_opl3sa2_probe(struct snd_card *card, int dev)
 	err = snd_opl3sa2_mixer(card);
 	if (err < 0)
 		return err;
-	err = snd_wss_timer(wss, 0, NULL);
+	err = snd_wss_timer(wss, 0);
 	if (err < 0)
 		return err;
 	if (fm_port[dev] >= 0x340 && fm_port[dev] < 0x400) {
diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c
index c2ca681ac51..546452888ae 100644
--- a/sound/isa/opti9xx/miro.c
+++ b/sound/isa/opti9xx/miro.c
@@ -1270,8 +1270,6 @@ static int snd_miro_probe(struct snd_card *card)
 	int error;
 	struct snd_miro *miro = card->private_data;
 	struct snd_wss *codec;
-	struct snd_timer *timer;
-	struct snd_pcm *pcm;
 	struct snd_rawmidi *rmidi;
 
 	if (!miro->res_mc_base) {
@@ -1310,7 +1308,7 @@ static int snd_miro_probe(struct snd_card *card)
 	if (error < 0)
 		return error;
 
-	error = snd_wss_pcm(codec, 0, &pcm);
+	error = snd_wss_pcm(codec, 0);
 	if (error < 0)
 		return error;
 
@@ -1318,11 +1316,11 @@ static int snd_miro_probe(struct snd_card *card)
 	if (error < 0)
 		return error;
 
-	error = snd_wss_timer(codec, 0, &timer);
+	error = snd_wss_timer(codec, 0);
 	if (error < 0)
 		return error;
 
-	miro->pcm = pcm;
+	miro->pcm = codec->pcm;
 
 	error = snd_miro_mixer(card, miro);
 	if (error < 0)
@@ -1356,8 +1354,8 @@ static int snd_miro_probe(struct snd_card *card)
 
 	strcpy(card->driver, "miro");
 	sprintf(card->longname, "%s: OPTi%s, %s at 0x%lx, irq %d, dma %d&%d",
-		card->shortname, miro->name, pcm->name, miro->wss_base + 4,
-		miro->irq, miro->dma1, miro->dma2);
+		card->shortname, miro->name, codec->pcm->name,
+		miro->wss_base + 4, miro->irq, miro->dma1, miro->dma2);
 
 	if (mpu_port <= 0 || mpu_port == SNDRV_AUTO_PORT)
 		rmidi = NULL;
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index c9b58284860..840831f1dd4 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -820,10 +820,6 @@ static int snd_opti9xx_probe(struct snd_card *card)
 	int xdma2;
 	struct snd_opti9xx *chip = card->private_data;
 	struct snd_wss *codec;
-#ifdef CS4231
-	struct snd_timer *timer;
-#endif
-	struct snd_pcm *pcm;
 	struct snd_rawmidi *rmidi;
 	struct snd_hwdep *synth;
 
@@ -855,7 +851,7 @@ static int snd_opti9xx_probe(struct snd_card *card)
 	if (error < 0)
 		return error;
 	chip->codec = codec;
-	error = snd_wss_pcm(codec, 0, &pcm);
+	error = snd_wss_pcm(codec, 0);
 	if (error < 0)
 		return error;
 	error = snd_wss_mixer(codec);
@@ -867,7 +863,7 @@ static int snd_opti9xx_probe(struct snd_card *card)
 		return error;
 #endif
 #ifdef CS4231
-	error = snd_wss_timer(codec, 0, &timer);
+	error = snd_wss_timer(codec, 0);
 	if (error < 0)
 		return error;
 #endif
@@ -884,11 +880,12 @@ static int snd_opti9xx_probe(struct snd_card *card)
 	sprintf(card->shortname, "OPTi %s", card->driver);
 #if defined(CS4231) || defined(OPTi93X)
 	sprintf(card->longname, "%s, %s at 0x%lx, irq %d, dma %d&%d",
-		card->shortname, pcm->name,
+		card->shortname, codec->pcm->name,
 		chip->wss_base + 4, irq, dma1, xdma2);
 #else
 	sprintf(card->longname, "%s, %s at 0x%lx, irq %d, dma %d",
-		card->shortname, pcm->name, chip->wss_base + 4, irq, dma1);
+		card->shortname, codec->pcm->name, chip->wss_base + 4, irq,
+		dma1);
 #endif	/* CS4231 || OPTi93X */
 
 	if (mpu_port <= 0 || mpu_port == SNDRV_AUTO_PORT)
diff --git a/sound/isa/sc6000.c b/sound/isa/sc6000.c
index 15a152eaa2e..51cfa7615f7 100644
--- a/sound/isa/sc6000.c
+++ b/sound/isa/sc6000.c
@@ -625,7 +625,7 @@ static int snd_sc6000_probe(struct device *devptr, unsigned int dev)
 	if (err < 0)
 		goto err_unmap2;
 
-	err = snd_wss_pcm(chip, 0, NULL);
+	err = snd_wss_pcm(chip, 0);
 	if (err < 0) {
 		snd_printk(KERN_ERR PFX
 			   "error creating new WSS PCM device\n");
diff --git a/sound/isa/sscape.c b/sound/isa/sscape.c
index 44405df7d4b..018ab140c2b 100644
--- a/sound/isa/sscape.c
+++ b/sound/isa/sscape.c
@@ -877,7 +877,6 @@ static int create_ad1845(struct snd_card *card, unsigned port,
 			     codec_type, WSS_HWSHARE_DMA1, &chip);
 	if (!err) {
 		unsigned long flags;
-		struct snd_pcm *pcm;
 
 		if (sscape->type != SSCAPE_VIVO) {
 			/*
@@ -893,7 +892,7 @@ static int create_ad1845(struct snd_card *card, unsigned port,
 
 		}
 
-		err = snd_wss_pcm(chip, 0, &pcm);
+		err = snd_wss_pcm(chip, 0);
 		if (err < 0) {
 			snd_printk(KERN_ERR "sscape: No PCM device "
 					    "for AD1845 chip\n");
@@ -907,7 +906,7 @@ static int create_ad1845(struct snd_card *card, unsigned port,
 			goto _error;
 		}
 		if (chip->hardware != WSS_HW_AD1848) {
-			err = snd_wss_timer(chip, 0, NULL);
+			err = snd_wss_timer(chip, 0);
 			if (err < 0) {
 				snd_printk(KERN_ERR "sscape: No timer device "
 						    "for AD1845 chip\n");
diff --git a/sound/isa/wavefront/wavefront.c b/sound/isa/wavefront/wavefront.c
index bfbf38cf984..a0987a57c8a 100644
--- a/sound/isa/wavefront/wavefront.c
+++ b/sound/isa/wavefront/wavefront.c
@@ -380,11 +380,11 @@ snd_wavefront_probe (struct snd_card *card, int dev)
 		return err;
 	}
 
-	err = snd_wss_pcm(chip, 0, NULL);
+	err = snd_wss_pcm(chip, 0);
 	if (err < 0)
 		return err;
 
-	err = snd_wss_timer(chip, 0, NULL);
+	err = snd_wss_timer(chip, 0);
 	if (err < 0)
 		return err;
 
diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c
index 347bb1bda11..6530d32901b 100644
--- a/sound/isa/wss/wss_lib.c
+++ b/sound/isa/wss/wss_lib.c
@@ -1923,7 +1923,7 @@ static struct snd_pcm_ops snd_wss_capture_ops = {
 	.pointer =	snd_wss_capture_pointer,
 };
 
-int snd_wss_pcm(struct snd_wss *chip, int device, struct snd_pcm **rpcm)
+int snd_wss_pcm(struct snd_wss *chip, int device)
 {
 	struct snd_pcm *pcm;
 	int err;
@@ -1949,8 +1949,6 @@ int snd_wss_pcm(struct snd_wss *chip, int device, struct snd_pcm **rpcm)
 					      64*1024, chip->dma1 > 3 || chip->dma2 > 3 ? 128*1024 : 64*1024);
 
 	chip->pcm = pcm;
-	if (rpcm)
-		*rpcm = pcm;
 	return 0;
 }
 EXPORT_SYMBOL(snd_wss_pcm);
@@ -1961,7 +1959,7 @@ static void snd_wss_timer_free(struct snd_timer *timer)
 	chip->timer = NULL;
 }
 
-int snd_wss_timer(struct snd_wss *chip, int device, struct snd_timer **rtimer)
+int snd_wss_timer(struct snd_wss *chip, int device)
 {
 	struct snd_timer *timer;
 	struct snd_timer_id tid;
@@ -1980,8 +1978,6 @@ int snd_wss_timer(struct snd_wss *chip, int device, struct snd_timer **rtimer)
 	timer->private_free = snd_wss_timer_free;
 	timer->hw = snd_wss_timer_table;
 	chip->timer = timer;
-	if (rtimer)
-		*rtimer = timer;
 	return 0;
 }
 EXPORT_SYMBOL(snd_wss_timer);
-- 
cgit v1.2.3-70-g09d2


From bb814c396af777c31ed168ce57f620967dd133f1 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 2 Jan 2015 12:24:49 +0100
Subject: ALSA: emu10k1: Remove always NULL parameters

The various PCM and hwdep allocation functions in this driver take a pointer
to a pointer of a PCM/hwdep where if this parameter is provided the newly
allocated object is stored. All callers pass NULL though, so remove the
parameter.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/emu10k1.h      | 14 +++++++-------
 sound/pci/emu10k1/emu10k1.c  | 12 ++++++------
 sound/pci/emu10k1/emu10k1x.c | 19 +++++--------------
 sound/pci/emu10k1/emufx.c    |  7 +------
 sound/pci/emu10k1/emupcm.c   | 33 ++++-----------------------------
 sound/pci/emu10k1/p16v.c     |  7 +------
 6 files changed, 24 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index c46908c1bb3..7f6ab6cd565 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -1809,17 +1809,17 @@ int snd_emu10k1_create(struct snd_card *card,
 		       uint subsystem,
 		       struct snd_emu10k1 ** remu);
 
-int snd_emu10k1_pcm(struct snd_emu10k1 * emu, int device, struct snd_pcm ** rpcm);
-int snd_emu10k1_pcm_mic(struct snd_emu10k1 * emu, int device, struct snd_pcm ** rpcm);
-int snd_emu10k1_pcm_efx(struct snd_emu10k1 * emu, int device, struct snd_pcm ** rpcm);
-int snd_p16v_pcm(struct snd_emu10k1 * emu, int device, struct snd_pcm ** rpcm);
+int snd_emu10k1_pcm(struct snd_emu10k1 *emu, int device);
+int snd_emu10k1_pcm_mic(struct snd_emu10k1 *emu, int device);
+int snd_emu10k1_pcm_efx(struct snd_emu10k1 *emu, int device);
+int snd_p16v_pcm(struct snd_emu10k1 *emu, int device);
 int snd_p16v_free(struct snd_emu10k1 * emu);
 int snd_p16v_mixer(struct snd_emu10k1 * emu);
-int snd_emu10k1_pcm_multi(struct snd_emu10k1 * emu, int device, struct snd_pcm ** rpcm);
-int snd_emu10k1_fx8010_pcm(struct snd_emu10k1 * emu, int device, struct snd_pcm ** rpcm);
+int snd_emu10k1_pcm_multi(struct snd_emu10k1 *emu, int device);
+int snd_emu10k1_fx8010_pcm(struct snd_emu10k1 *emu, int device);
 int snd_emu10k1_mixer(struct snd_emu10k1 * emu, int pcm_device, int multi_device);
 int snd_emu10k1_timer(struct snd_emu10k1 * emu, int device);
-int snd_emu10k1_fx8010_new(struct snd_emu10k1 *emu, int device, struct snd_hwdep ** rhwdep);
+int snd_emu10k1_fx8010_new(struct snd_emu10k1 *emu, int device);
 
 irqreturn_t snd_emu10k1_interrupt(int irq, void *dev_id);
 
diff --git a/sound/pci/emu10k1/emu10k1.c b/sound/pci/emu10k1/emu10k1.c
index 4c171636efc..a3c00a66826 100644
--- a/sound/pci/emu10k1/emu10k1.c
+++ b/sound/pci/emu10k1/emu10k1.c
@@ -132,11 +132,11 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci,
 		goto error;
 	card->private_data = emu;
 	emu->delay_pcm_irq = delay_pcm_irq[dev] & 0x1f;
-	if ((err = snd_emu10k1_pcm(emu, 0, NULL)) < 0)
+	if ((err = snd_emu10k1_pcm(emu, 0)) < 0)
 		goto error;
-	if ((err = snd_emu10k1_pcm_mic(emu, 1, NULL)) < 0)
+	if ((err = snd_emu10k1_pcm_mic(emu, 1)) < 0)
 		goto error;
-	if ((err = snd_emu10k1_pcm_efx(emu, 2, NULL)) < 0)
+	if ((err = snd_emu10k1_pcm_efx(emu, 2)) < 0)
 		goto error;
 	/* This stores the periods table. */
 	if (emu->card_capabilities->ca0151_chip) { /* P16V */	
@@ -151,10 +151,10 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci,
 	if ((err = snd_emu10k1_timer(emu, 0)) < 0)
 		goto error;
 
-	if ((err = snd_emu10k1_pcm_multi(emu, 3, NULL)) < 0)
+	if ((err = snd_emu10k1_pcm_multi(emu, 3)) < 0)
 		goto error;
 	if (emu->card_capabilities->ca0151_chip) { /* P16V */
-		if ((err = snd_p16v_pcm(emu, 4, NULL)) < 0)
+		if ((err = snd_p16v_pcm(emu, 4)) < 0)
 			goto error;
 	}
 	if (emu->audigy) {
@@ -164,7 +164,7 @@ static int snd_card_emu10k1_probe(struct pci_dev *pci,
 		if ((err = snd_emu10k1_midi(emu)) < 0)
 			goto error;
 	}
-	if ((err = snd_emu10k1_fx8010_new(emu, 0, NULL)) < 0)
+	if ((err = snd_emu10k1_fx8010_new(emu, 0)) < 0)
 		goto error;
 #ifdef ENABLE_SYNTH
 	if (snd_seq_device_new(card, 1, SNDRV_SEQ_DEV_ID_EMU10K1_SYNTH,
diff --git a/sound/pci/emu10k1/emu10k1x.c b/sound/pci/emu10k1/emu10k1x.c
index 15933f92f63..6d1b98d1432 100644
--- a/sound/pci/emu10k1/emu10k1x.c
+++ b/sound/pci/emu10k1/emu10k1x.c
@@ -847,15 +847,13 @@ static const struct snd_pcm_chmap_elem clfe_map[] = {
 	{ }
 };
 
-static int snd_emu10k1x_pcm(struct emu10k1x *emu, int device, struct snd_pcm **rpcm)
+static int snd_emu10k1x_pcm(struct emu10k1x *emu, int device)
 {
 	struct snd_pcm *pcm;
 	const struct snd_pcm_chmap_elem *map = NULL;
 	int err;
 	int capture = 0;
   
-	if (rpcm)
-		*rpcm = NULL;
 	if (device == 0)
 		capture = 1;
 	
@@ -896,15 +894,8 @@ static int snd_emu10k1x_pcm(struct emu10k1x *emu, int device, struct snd_pcm **r
 					      snd_dma_pci_data(emu->pci), 
 					      32*1024, 32*1024);
   
-	err = snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK, map, 2,
+	return snd_pcm_add_chmap_ctls(pcm, SNDRV_PCM_STREAM_PLAYBACK, map, 2,
 				     1 << 2, NULL);
-	if (err < 0)
-		return err;
-
-	if (rpcm)
-		*rpcm = pcm;
-  
-	return 0;
 }
 
 static int snd_emu10k1x_create(struct snd_card *card,
@@ -1583,15 +1574,15 @@ static int snd_emu10k1x_probe(struct pci_dev *pci,
 		return err;
 	}
 
-	if ((err = snd_emu10k1x_pcm(chip, 0, NULL)) < 0) {
+	if ((err = snd_emu10k1x_pcm(chip, 0)) < 0) {
 		snd_card_free(card);
 		return err;
 	}
-	if ((err = snd_emu10k1x_pcm(chip, 1, NULL)) < 0) {
+	if ((err = snd_emu10k1x_pcm(chip, 1)) < 0) {
 		snd_card_free(card);
 		return err;
 	}
-	if ((err = snd_emu10k1x_pcm(chip, 2, NULL)) < 0) {
+	if ((err = snd_emu10k1x_pcm(chip, 2)) < 0) {
 		snd_card_free(card);
 		return err;
 	}
diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c
index eb5c0aba41c..56fc47bd6db 100644
--- a/sound/pci/emu10k1/emufx.c
+++ b/sound/pci/emu10k1/emufx.c
@@ -2641,14 +2641,11 @@ static int snd_emu10k1_fx8010_release(struct snd_hwdep * hw, struct file *file)
 	return 0;
 }
 
-int snd_emu10k1_fx8010_new(struct snd_emu10k1 *emu, int device,
-			   struct snd_hwdep **rhwdep)
+int snd_emu10k1_fx8010_new(struct snd_emu10k1 *emu, int device)
 {
 	struct snd_hwdep *hw;
 	int err;
 	
-	if (rhwdep)
-		*rhwdep = NULL;
 	if ((err = snd_hwdep_new(emu->card, "FX8010", device, &hw)) < 0)
 		return err;
 	strcpy(hw->name, "EMU10K1 (FX8010)");
@@ -2657,8 +2654,6 @@ int snd_emu10k1_fx8010_new(struct snd_emu10k1 *emu, int device,
 	hw->ops.ioctl = snd_emu10k1_fx8010_ioctl;
 	hw->ops.release = snd_emu10k1_fx8010_release;
 	hw->private_data = emu;
-	if (rhwdep)
-		*rhwdep = hw;
 	return 0;
 }
 
diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index f82481bd254..0dc07385af0 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -1400,15 +1400,12 @@ static struct snd_pcm_ops snd_emu10k1_efx_playback_ops = {
 	.page =			snd_pcm_sgbuf_ops_page,
 };
 
-int snd_emu10k1_pcm(struct snd_emu10k1 *emu, int device, struct snd_pcm **rpcm)
+int snd_emu10k1_pcm(struct snd_emu10k1 *emu, int device)
 {
 	struct snd_pcm *pcm;
 	struct snd_pcm_substream *substream;
 	int err;
 
-	if (rpcm)
-		*rpcm = NULL;
-
 	if ((err = snd_pcm_new(emu->card, "emu10k1", device, 32, 1, &pcm)) < 0)
 		return err;
 
@@ -1429,22 +1426,15 @@ int snd_emu10k1_pcm(struct snd_emu10k1 *emu, int device, struct snd_pcm **rpcm)
 	for (substream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream; substream; substream = substream->next)
 		snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(emu->pci), 64*1024, 64*1024);
 
-	if (rpcm)
-		*rpcm = pcm;
-
 	return 0;
 }
 
-int snd_emu10k1_pcm_multi(struct snd_emu10k1 *emu, int device,
-			  struct snd_pcm **rpcm)
+int snd_emu10k1_pcm_multi(struct snd_emu10k1 *emu, int device)
 {
 	struct snd_pcm *pcm;
 	struct snd_pcm_substream *substream;
 	int err;
 
-	if (rpcm)
-		*rpcm = NULL;
-
 	if ((err = snd_pcm_new(emu->card, "emu10k1", device, 1, 0, &pcm)) < 0)
 		return err;
 
@@ -1461,9 +1451,6 @@ int snd_emu10k1_pcm_multi(struct snd_emu10k1 *emu, int device,
 		if ((err = snd_pcm_lib_preallocate_pages(substream, SNDRV_DMA_TYPE_DEV_SG, snd_dma_pci_data(emu->pci), 64*1024, 64*1024)) < 0)
 			return err;
 
-	if (rpcm)
-		*rpcm = pcm;
-
 	return 0;
 }
 
@@ -1479,15 +1466,11 @@ static struct snd_pcm_ops snd_emu10k1_capture_mic_ops = {
 	.pointer =		snd_emu10k1_capture_pointer,
 };
 
-int snd_emu10k1_pcm_mic(struct snd_emu10k1 *emu, int device,
-			struct snd_pcm **rpcm)
+int snd_emu10k1_pcm_mic(struct snd_emu10k1 *emu, int device)
 {
 	struct snd_pcm *pcm;
 	int err;
 
-	if (rpcm)
-		*rpcm = NULL;
-
 	if ((err = snd_pcm_new(emu->card, "emu10k1 mic", device, 0, 1, &pcm)) < 0)
 		return err;
 
@@ -1501,8 +1484,6 @@ int snd_emu10k1_pcm_mic(struct snd_emu10k1 *emu, int device,
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(emu->pci), 64*1024, 64*1024);
 
-	if (rpcm)
-		*rpcm = pcm;
 	return 0;
 }
 
@@ -1822,16 +1803,12 @@ static struct snd_pcm_ops snd_emu10k1_fx8010_playback_ops = {
 	.ack =			snd_emu10k1_fx8010_playback_transfer,
 };
 
-int snd_emu10k1_pcm_efx(struct snd_emu10k1 *emu, int device,
-			struct snd_pcm **rpcm)
+int snd_emu10k1_pcm_efx(struct snd_emu10k1 *emu, int device)
 {
 	struct snd_pcm *pcm;
 	struct snd_kcontrol *kctl;
 	int err;
 
-	if (rpcm)
-		*rpcm = NULL;
-
 	if ((err = snd_pcm_new(emu->card, "emu10k1 efx", device, 8, 1, &pcm)) < 0)
 		return err;
 
@@ -1843,8 +1820,6 @@ int snd_emu10k1_pcm_efx(struct snd_emu10k1 *emu, int device,
 	pcm->info_flags = 0;
 	strcpy(pcm->name, "Multichannel Capture/PT Playback");
 	emu->pcm_efx = pcm;
-	if (rpcm)
-		*rpcm = pcm;
 
 	/* EFX capture - record the "FXBUS2" channels, by default we connect the EXTINs 
 	 * to these
diff --git a/sound/pci/emu10k1/p16v.c b/sound/pci/emu10k1/p16v.c
index 7ef3898a780..b672755815e 100644
--- a/sound/pci/emu10k1/p16v.c
+++ b/sound/pci/emu10k1/p16v.c
@@ -640,7 +640,7 @@ int snd_p16v_free(struct snd_emu10k1 *chip)
 	return 0;
 }
 
-int snd_p16v_pcm(struct snd_emu10k1 *emu, int device, struct snd_pcm **rpcm)
+int snd_p16v_pcm(struct snd_emu10k1 *emu, int device)
 {
 	struct snd_pcm *pcm;
 	struct snd_pcm_substream *substream;
@@ -649,8 +649,6 @@ int snd_p16v_pcm(struct snd_emu10k1 *emu, int device, struct snd_pcm **rpcm)
   
 	/* dev_dbg(emu->card->dev, "snd_p16v_pcm called. device=%d\n", device); */
 	emu->p16v_device_offset = device;
-	if (rpcm)
-		*rpcm = NULL;
 
 	if ((err = snd_pcm_new(emu->card, "p16v", device, 1, capture, &pcm)) < 0)
 		return err;
@@ -694,9 +692,6 @@ int snd_p16v_pcm(struct snd_emu10k1 *emu, int device, struct snd_pcm **rpcm)
 		*/
 	}
   
-	if (rpcm)
-		*rpcm = pcm;
-  
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 9b174d88c257150562b0101fcc6cb6c3cb74275c Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Tue, 30 Dec 2014 19:10:15 -0800
Subject: net: Add Transparent Ethernet Bridging GRO support.

Currently the only tunnel protocol that supports GRO with encapsulated
Ethernet is VXLAN. This pulls out the Ethernet code into a proper layer
so that it can be used by other tunnel protocols such as GRE and Geneve.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c         | 53 +++-----------------------
 include/linux/etherdevice.h |  4 ++
 net/ethernet/eth.c          | 92 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 102 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 7fbd89fbe10..2ab0922af0b 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -549,10 +549,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff
 {
 	struct sk_buff *p, **pp = NULL;
 	struct vxlanhdr *vh, *vh2;
-	struct ethhdr *eh, *eh2;
-	unsigned int hlen, off_vx, off_eth;
-	const struct packet_offload *ptype;
-	__be16 type;
+	unsigned int hlen, off_vx;
 	int flush = 1;
 
 	off_vx = skb_gro_offset(skb);
@@ -563,17 +560,6 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff
 		if (unlikely(!vh))
 			goto out;
 	}
-	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
-	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
-
-	off_eth = skb_gro_offset(skb);
-	hlen = off_eth + sizeof(*eh);
-	eh   = skb_gro_header_fast(skb, off_eth);
-	if (skb_gro_header_hard(skb, hlen)) {
-		eh = skb_gro_header_slow(skb, hlen, off_eth);
-		if (unlikely(!eh))
-			goto out;
-	}
 
 	flush = 0;
 
@@ -582,28 +568,16 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff
 			continue;
 
 		vh2 = (struct vxlanhdr *)(p->data + off_vx);
-		eh2 = (struct ethhdr   *)(p->data + off_eth);
-		if (vh->vx_vni != vh2->vx_vni || compare_ether_header(eh, eh2)) {
+		if (vh->vx_vni != vh2->vx_vni) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
 	}
 
-	type = eh->h_proto;
-
-	rcu_read_lock();
-	ptype = gro_find_receive_by_type(type);
-	if (ptype == NULL) {
-		flush = 1;
-		goto out_unlock;
-	}
-
-	skb_gro_pull(skb, sizeof(*eh)); /* pull inner eth header */
-	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
-	pp = ptype->callbacks.gro_receive(head, skb);
+	skb_gro_pull(skb, sizeof(struct vxlanhdr));
+	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
+	pp = eth_gro_receive(head, skb);
 
-out_unlock:
-	rcu_read_unlock();
 out:
 	NAPI_GRO_CB(skb)->flush |= flush;
 
@@ -612,24 +586,9 @@ out:
 
 static int vxlan_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	struct ethhdr *eh;
-	struct packet_offload *ptype;
-	__be16 type;
-	int vxlan_len  = sizeof(struct vxlanhdr) + sizeof(struct ethhdr);
-	int err = -ENOSYS;
-
 	udp_tunnel_gro_complete(skb, nhoff);
 
-	eh = (struct ethhdr *)(skb->data + nhoff + sizeof(struct vxlanhdr));
-	type = eh->h_proto;
-
-	rcu_read_lock();
-	ptype = gro_find_complete_by_type(type);
-	if (ptype != NULL)
-		err = ptype->callbacks.gro_complete(skb, nhoff + vxlan_len);
-
-	rcu_read_unlock();
-	return err;
+	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
 /* Notify netdevs that UDP port started listening */
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 41c891d05f0..1d869d185a0 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -52,6 +52,10 @@ struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
 #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1)
 #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count)
 
+struct sk_buff **eth_gro_receive(struct sk_buff **head,
+				 struct sk_buff *skb);
+int eth_gro_complete(struct sk_buff *skb, int nhoff);
+
 /* Reserved Ethernet Addresses per IEEE 802.1Q */
 static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
 { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 33a140e1583..238f38d2164 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -424,3 +424,95 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
 	return scnprintf(buf, PAGE_SIZE, "%*phC\n", len, addr);
 }
 EXPORT_SYMBOL(sysfs_format_mac);
+
+struct sk_buff **eth_gro_receive(struct sk_buff **head,
+				 struct sk_buff *skb)
+{
+	struct sk_buff *p, **pp = NULL;
+	struct ethhdr *eh, *eh2;
+	unsigned int hlen, off_eth;
+	const struct packet_offload *ptype;
+	__be16 type;
+	int flush = 1;
+
+	off_eth = skb_gro_offset(skb);
+	hlen = off_eth + sizeof(*eh);
+	eh = skb_gro_header_fast(skb, off_eth);
+	if (skb_gro_header_hard(skb, hlen)) {
+		eh = skb_gro_header_slow(skb, hlen, off_eth);
+		if (unlikely(!eh))
+			goto out;
+	}
+
+	flush = 0;
+
+	for (p = *head; p; p = p->next) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		eh2 = (struct ethhdr *)(p->data + off_eth);
+		if (compare_ether_header(eh, eh2)) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+	}
+
+	type = eh->h_proto;
+
+	rcu_read_lock();
+	ptype = gro_find_receive_by_type(type);
+	if (ptype == NULL) {
+		flush = 1;
+		goto out_unlock;
+	}
+
+	skb_gro_pull(skb, sizeof(*eh));
+	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
+	pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	NAPI_GRO_CB(skb)->flush |= flush;
+
+	return pp;
+}
+EXPORT_SYMBOL(eth_gro_receive);
+
+int eth_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct ethhdr *eh = (struct ethhdr *)(skb->data + nhoff);
+	__be16 type = eh->h_proto;
+	struct packet_offload *ptype;
+	int err = -ENOSYS;
+
+	if (skb->encapsulation)
+		skb_set_inner_mac_header(skb, nhoff);
+
+	rcu_read_lock();
+	ptype = gro_find_complete_by_type(type);
+	if (ptype != NULL)
+		err = ptype->callbacks.gro_complete(skb, nhoff +
+						    sizeof(struct ethhdr));
+
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(eth_gro_complete);
+
+static struct packet_offload eth_packet_offload __read_mostly = {
+	.type = cpu_to_be16(ETH_P_TEB),
+	.callbacks = {
+		.gro_receive = eth_gro_receive,
+		.gro_complete = eth_gro_complete,
+	},
+};
+
+static int __init eth_offload_init(void)
+{
+	dev_add_offload(&eth_packet_offload);
+
+	return 0;
+}
+
+fs_initcall(eth_offload_init);
-- 
cgit v1.2.3-70-g09d2


From 300acfdec916be696373864226267b11302d3b84 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 31 Dec 2014 14:43:16 -0800
Subject: Bluetooth: Introduce force_bredr_smp debugfs option for testing

Testing cross-transport pairing that starts on BR/EDR is only valid when
using a controller with BR/EDR Secure Connections. Devices will indicate
this by providing BR/EDR SMP fixed channel over L2CAP. To allow testing
of this feature on Bluetooth 4.0 controller or controllers without the
BR/EDR Secure Connections features, introduce a force_bredr_smp debugfs
option that allows faking the required AES connection.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h |  1 +
 net/bluetooth/l2cap_core.c  |  2 +-
 net/bluetooth/smp.c         | 78 ++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 76 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 1849a437f6e..fddb93f168b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -174,6 +174,7 @@ enum {
 	HCI_DUT_MODE,
 	HCI_FORCE_SC,
 	HCI_FORCE_LESC,
+	HCI_FORCE_BREDR_SMP,
 	HCI_FORCE_STATIC_ADDR,
 };
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index d04dc009573..11029b21287 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -6968,7 +6968,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon)
 
 	if (test_bit(HCI_LE_ENABLED, &hcon->hdev->dev_flags) &&
 	    (bredr_sc_enabled(hcon->hdev) ||
-	     test_bit(HCI_FORCE_LESC, &hcon->hdev->dbg_flags)))
+	     test_bit(HCI_FORCE_BREDR_SMP, &hcon->hdev->dbg_flags)))
 		conn->local_fixed_chan |= L2CAP_FC_SMP_BREDR;
 
 	mutex_init(&conn->ident_lock);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 358264c0e78..73643a6ca3c 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -20,6 +20,7 @@
    SOFTWARE IS DISCLAIMED.
 */
 
+#include <linux/debugfs.h>
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
 #include <crypto/b128ops.h>
@@ -1675,7 +1676,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (conn->hcon->type == ACL_LINK) {
 		/* We must have a BR/EDR SC link */
 		if (!test_bit(HCI_CONN_AES_CCM, &conn->hcon->flags) &&
-		    !test_bit(HCI_FORCE_LESC, &hdev->dbg_flags))
+		    !test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags))
 			return SMP_CROSS_TRANSP_NOT_ALLOWED;
 
 		set_bit(SMP_FLAG_SC, &smp->flags);
@@ -2738,7 +2739,7 @@ static void bredr_pairing(struct l2cap_chan *chan)
 
 	/* BR/EDR must use Secure Connections for SMP */
 	if (!test_bit(HCI_CONN_AES_CCM, &hcon->flags) &&
-	    !test_bit(HCI_FORCE_LESC, &hdev->dbg_flags))
+	    !test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags))
 		return;
 
 	/* If our LE support is not enabled don't do anything */
@@ -2976,6 +2977,66 @@ static void smp_del_chan(struct l2cap_chan *chan)
 	l2cap_chan_put(chan);
 }
 
+static ssize_t force_bredr_smp_read(struct file *file,
+				    char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
+
+	buf[0] = test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags) ? 'Y': 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t force_bredr_smp_write(struct file *file,
+				     const char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[32];
+	size_t buf_size = min(count, (sizeof(buf)-1));
+	bool enable;
+
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	if (strtobool(buf, &enable))
+		return -EINVAL;
+
+	if (enable == test_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags))
+		return -EALREADY;
+
+	if (enable) {
+		struct l2cap_chan *chan;
+
+		chan = smp_add_cid(hdev, L2CAP_CID_SMP_BREDR);
+		if (IS_ERR(chan))
+			return PTR_ERR(chan);
+
+		hdev->smp_bredr_data = chan;
+	} else {
+		struct l2cap_chan *chan;
+
+		chan = hdev->smp_bredr_data;
+		hdev->smp_bredr_data = NULL;
+		smp_del_chan(chan);
+	}
+
+	change_bit(HCI_FORCE_BREDR_SMP, &hdev->dbg_flags);
+
+	return count;
+}
+
+static const struct file_operations force_bredr_smp_fops = {
+	.open		= simple_open,
+	.read		= force_bredr_smp_read,
+	.write		= force_bredr_smp_write,
+	.llseek		= default_llseek,
+};
+
 int smp_register(struct hci_dev *hdev)
 {
 	struct l2cap_chan *chan;
@@ -2988,9 +3049,18 @@ int smp_register(struct hci_dev *hdev)
 
 	hdev->smp_data = chan;
 
-	if (!lmp_sc_capable(hdev) &&
-	    !test_bit(HCI_FORCE_LESC, &hdev->dbg_flags))
+	/* If the controller does not support BR/EDR Secure Connections
+	 * feature, then the BR/EDR SMP channel shall not be present.
+	 *
+	 * To test this with Bluetooth 4.0 controllers, create a debugfs
+	 * switch that allows forcing BR/EDR SMP support and accepting
+	 * cross-transport pairing on non-AES encrypted connections.
+	 */
+	if (!lmp_sc_capable(hdev)) {
+		debugfs_create_file("force_bredr_smp", 0644, hdev->debugfs,
+				    hdev, &force_bredr_smp_fops);
 		return 0;
+	}
 
 	chan = smp_add_cid(hdev, L2CAP_CID_SMP_BREDR);
 	if (IS_ERR(chan)) {
-- 
cgit v1.2.3-70-g09d2


From 91389af67c3a8d8f9eca5f51deda58fae4d9326e Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 31 Dec 2014 14:43:17 -0800
Subject: Bluetooth: Remove broken force_lesc_support debugfs option

The force_lesc_support debugfs option never really worked. It has a race
condition between creating the debugfs entry and registering the L2CAP
fixed channel for BR/EDR SMP support.

Also this has been replaced with a working force_bredr_smp debugfs
switch that developers can use now.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h |  1 -
 net/bluetooth/hci_debugfs.c | 49 ---------------------------------------------
 2 files changed, 50 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index fddb93f168b..884ba004237 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -173,7 +173,6 @@ enum {
 enum {
 	HCI_DUT_MODE,
 	HCI_FORCE_SC,
-	HCI_FORCE_LESC,
 	HCI_FORCE_BREDR_SMP,
 	HCI_FORCE_STATIC_ADDR,
 };
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index ee33ce88d3d..dc8f994a957 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -421,50 +421,6 @@ static const struct file_operations force_sc_support_fops = {
 	.llseek		= default_llseek,
 };
 
-static ssize_t force_lesc_support_read(struct file *file,
-				       char __user *user_buf,
-				       size_t count, loff_t *ppos)
-{
-	struct hci_dev *hdev = file->private_data;
-	char buf[3];
-
-	buf[0] = test_bit(HCI_FORCE_LESC, &hdev->dbg_flags) ? 'Y': 'N';
-	buf[1] = '\n';
-	buf[2] = '\0';
-	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
-
-static ssize_t force_lesc_support_write(struct file *file,
-					const char __user *user_buf,
-					size_t count, loff_t *ppos)
-{
-	struct hci_dev *hdev = file->private_data;
-	char buf[32];
-	size_t buf_size = min(count, (sizeof(buf)-1));
-	bool enable;
-
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
-	if (strtobool(buf, &enable))
-		return -EINVAL;
-
-	if (enable == test_bit(HCI_FORCE_LESC, &hdev->dbg_flags))
-		return -EALREADY;
-
-	change_bit(HCI_FORCE_LESC, &hdev->dbg_flags);
-
-	return count;
-}
-
-static const struct file_operations force_lesc_support_fops = {
-	.open		= simple_open,
-	.read		= force_lesc_support_read,
-	.write		= force_lesc_support_write,
-	.llseek		= default_llseek,
-};
-
 static int idle_timeout_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
@@ -568,11 +524,6 @@ void hci_debugfs_create_bredr(struct hci_dev *hdev)
 
 		debugfs_create_file("force_sc_support", 0644, hdev->debugfs,
 				    hdev, &force_sc_support_fops);
-
-		if (lmp_le_capable(hdev))
-			debugfs_create_file("force_lesc_support", 0644,
-					    hdev->debugfs, hdev,
-					    &force_lesc_support_fops);
 	}
 
 	if (lmp_sniff_capable(hdev)) {
-- 
cgit v1.2.3-70-g09d2


From 05b3c3e7905d00a1fe2e9184fdd9b5eac427c736 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 31 Dec 2014 14:43:18 -0800
Subject: Bluetooth: Remove no longer needed force_sc_support debugfs option

The force_sc_support debugfs option was introduced to easily work with
pre-production Bluetooth 4.1 silicon. This option is no longer needed
since controllers supporting BR/EDR Secure Connections feature are now
available.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h      |  1 -
 include/net/bluetooth/hci_core.h |  3 +--
 net/bluetooth/hci_debugfs.c      | 49 ----------------------------------------
 net/bluetooth/mgmt.c             | 11 ++++-----
 4 files changed, 5 insertions(+), 59 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 884ba004237..aee16bf5d34 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -172,7 +172,6 @@ enum {
  */
 enum {
 	HCI_DUT_MODE,
-	HCI_FORCE_SC,
 	HCI_FORCE_BREDR_SMP,
 	HCI_FORCE_STATIC_ADDR,
 };
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 3e7e5110f29..89f4e3c8a09 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1017,8 +1017,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 
 #define hdev_is_powered(hdev) (test_bit(HCI_UP, &hdev->flags) && \
 				!test_bit(HCI_AUTO_OFF, &hdev->dev_flags))
-#define bredr_sc_enabled(dev) ((lmp_sc_capable(dev) || \
-				test_bit(HCI_FORCE_SC, &(dev)->dbg_flags)) && \
+#define bredr_sc_enabled(dev) (lmp_sc_capable(dev) && \
 			       test_bit(HCI_SC_ENABLED, &(dev)->dev_flags))
 
 /* ----- HCI protocols ----- */
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index dc8f994a957..d72ebc2b11f 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -375,52 +375,6 @@ static const struct file_operations sc_only_mode_fops = {
 	.llseek		= default_llseek,
 };
 
-static ssize_t force_sc_support_read(struct file *file, char __user *user_buf,
-				     size_t count, loff_t *ppos)
-{
-	struct hci_dev *hdev = file->private_data;
-	char buf[3];
-
-	buf[0] = test_bit(HCI_FORCE_SC, &hdev->dbg_flags) ? 'Y': 'N';
-	buf[1] = '\n';
-	buf[2] = '\0';
-	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
-
-static ssize_t force_sc_support_write(struct file *file,
-				      const char __user *user_buf,
-				      size_t count, loff_t *ppos)
-{
-	struct hci_dev *hdev = file->private_data;
-	char buf[32];
-	size_t buf_size = min(count, (sizeof(buf)-1));
-	bool enable;
-
-	if (test_bit(HCI_UP, &hdev->flags))
-		return -EBUSY;
-
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
-	if (strtobool(buf, &enable))
-		return -EINVAL;
-
-	if (enable == test_bit(HCI_FORCE_SC, &hdev->dbg_flags))
-		return -EALREADY;
-
-	change_bit(HCI_FORCE_SC, &hdev->dbg_flags);
-
-	return count;
-}
-
-static const struct file_operations force_sc_support_fops = {
-	.open		= simple_open,
-	.read		= force_sc_support_read,
-	.write		= force_sc_support_write,
-	.llseek		= default_llseek,
-};
-
 static int idle_timeout_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
@@ -521,9 +475,6 @@ void hci_debugfs_create_bredr(struct hci_dev *hdev)
 				    hdev, &auto_accept_delay_fops);
 		debugfs_create_file("sc_only_mode", 0444, hdev->debugfs,
 				    hdev, &sc_only_mode_fops);
-
-		debugfs_create_file("force_sc_support", 0644, hdev->debugfs,
-				    hdev, &force_sc_support_fops);
 	}
 
 	if (lmp_sniff_capable(hdev)) {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3d2f7ad1e65..6b3f5537e44 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -570,8 +570,7 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 			settings |= MGMT_SETTING_HS;
 		}
 
-		if (lmp_sc_capable(hdev) ||
-		    test_bit(HCI_FORCE_SC, &hdev->dbg_flags))
+		if (lmp_sc_capable(hdev))
 			settings |= MGMT_SETTING_SECURE_CONN;
 	}
 
@@ -4727,8 +4726,8 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev,
 
 	BT_DBG("request for %s", hdev->name);
 
-	if (!test_bit(HCI_LE_ENABLED, &hdev->dev_flags) &&
-	    !lmp_sc_capable(hdev) && !test_bit(HCI_FORCE_SC, &hdev->dbg_flags))
+	if (!lmp_sc_capable(hdev) &&
+	    !test_bit(HCI_LE_ENABLED, &hdev->dev_flags))
 		return cmd_status(sk, hdev->id, MGMT_OP_SET_SECURE_CONN,
 				  MGMT_STATUS_NOT_SUPPORTED);
 
@@ -4738,9 +4737,7 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev,
 
 	hci_dev_lock(hdev);
 
-	if (!hdev_is_powered(hdev) ||
-	    (!lmp_sc_capable(hdev) &&
-	     !test_bit(HCI_FORCE_SC, &hdev->dbg_flags)) ||
+	if (!hdev_is_powered(hdev) || !lmp_sc_capable(hdev) ||
 	    !test_bit(HCI_BREDR_ENABLED, &hdev->dev_flags)) {
 		bool changed;
 
-- 
cgit v1.2.3-70-g09d2


From 1891172aa5c32f08ad9931b794edd71e91a4a527 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Fri, 2 Jan 2015 20:22:03 +0100
Subject: timecounter: provide a macro to initialize the cyclecounter mask
 field.

There is no need for users of the timecounter/cyclecounter code to include
clocksource.h just for a single macro.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/timecounter.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h
index 74f45496e6d..4382035a75b 100644
--- a/include/linux/timecounter.h
+++ b/include/linux/timecounter.h
@@ -19,6 +19,9 @@
 
 #include <linux/types.h>
 
+/* simplify initialization of mask field */
+#define CYCLECOUNTER_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
+
 /**
  * struct cyclecounter - hardware abstraction for a free running counter
  *	Provides completely state-free accessors to the underlying hardware.
@@ -29,7 +32,7 @@
  * @read:		returns the current cycle value
  * @mask:		bitmask for two's complement
  *			subtraction of non 64 bit counters,
- *			see CLOCKSOURCE_MASK() helper macro
+ *			see CYCLECOUNTER_MASK() helper macro
  * @mult:		cycle to nanosecond multiplier
  * @shift:		cycle to nanosecond divisor (power of two)
  */
-- 
cgit v1.2.3-70-g09d2


From 8d24c0b43125ec26cc80e04588477a9a2afc025c Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 2 Jan 2015 23:00:14 +0100
Subject: rhashtable: Do hashing inside of rhashtable_lookup_compare()

Hash the key inside of rhashtable_lookup_compare() like
rhashtable_lookup() does. This allows to simplify the hashing
functions and keep them private.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  5 +--
 lib/rhashtable.c           | 91 +++++++++++++++-------------------------------
 net/netfilter/nft_hash.c   | 46 ++++++++++++++---------
 net/netlink/af_netlink.c   |  5 +--
 4 files changed, 61 insertions(+), 86 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index b93fd89b2e5..1b51221c6bb 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -96,9 +96,6 @@ static inline int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
 
 int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params);
 
-u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len);
-u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr);
-
 void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node);
 bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node);
 void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
@@ -111,7 +108,7 @@ int rhashtable_expand(struct rhashtable *ht);
 int rhashtable_shrink(struct rhashtable *ht);
 
 void *rhashtable_lookup(const struct rhashtable *ht, const void *key);
-void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+void *rhashtable_lookup_compare(const struct rhashtable *ht, const void *key,
 				bool (*compare)(void *, void *), void *arg);
 
 void rhashtable_destroy(const struct rhashtable *ht);
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 6c3c723e902..1ee0eb636ca 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -42,69 +42,39 @@ static void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he)
 	return (void *) he - ht->p.head_offset;
 }
 
-static u32 __hashfn(const struct rhashtable *ht, const void *key,
-		      u32 len, u32 hsize)
+static u32 rht_bucket_index(const struct bucket_table *tbl, u32 hash)
 {
-	u32 h;
-
-	h = ht->p.hashfn(key, len, ht->p.hash_rnd);
-
-	return h & (hsize - 1);
-}
-
-/**
- * rhashtable_hashfn - compute hash for key of given length
- * @ht:		hash table to compute for
- * @key:	pointer to key
- * @len:	length of key
- *
- * Computes the hash value using the hash function provided in the 'hashfn'
- * of struct rhashtable_params. The returned value is guaranteed to be
- * smaller than the number of buckets in the hash table.
- */
-u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len)
-{
-	struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
-
-	return __hashfn(ht, key, len, tbl->size);
+	return hash & (tbl->size - 1);
 }
-EXPORT_SYMBOL_GPL(rhashtable_hashfn);
 
-static u32 obj_hashfn(const struct rhashtable *ht, const void *ptr, u32 hsize)
+static u32 obj_raw_hashfn(const struct rhashtable *ht, const void *ptr)
 {
-	if (unlikely(!ht->p.key_len)) {
-		u32 h;
-
-		h = ht->p.obj_hashfn(ptr, ht->p.hash_rnd);
+	u32 hash;
 
-		return h & (hsize - 1);
-	}
+	if (unlikely(!ht->p.key_len))
+		hash = ht->p.obj_hashfn(ptr, ht->p.hash_rnd);
+	else
+		hash = ht->p.hashfn(ptr + ht->p.key_offset, ht->p.key_len,
+				    ht->p.hash_rnd);
 
-	return __hashfn(ht, ptr + ht->p.key_offset, ht->p.key_len, hsize);
+	return hash;
 }
 
-/**
- * rhashtable_obj_hashfn - compute hash for hashed object
- * @ht:		hash table to compute for
- * @ptr:	pointer to hashed object
- *
- * Computes the hash value using the hash function `hashfn` respectively
- * 'obj_hashfn' depending on whether the hash table is set up to work with
- * a fixed length key. The returned value is guaranteed to be smaller than
- * the number of buckets in the hash table.
- */
-u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr)
+static u32 key_hashfn(const struct rhashtable *ht, const void *key, u32 len)
 {
 	struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
+	u32 hash;
+
+	hash = ht->p.hashfn(key, len, ht->p.hash_rnd);
 
-	return obj_hashfn(ht, ptr, tbl->size);
+	return rht_bucket_index(tbl, hash);
 }
-EXPORT_SYMBOL_GPL(rhashtable_obj_hashfn);
 
 static u32 head_hashfn(const struct rhashtable *ht,
-		       const struct rhash_head *he, u32 hsize)
+		       const struct bucket_table *tbl,
+		       const struct rhash_head *he)
 {
-	return obj_hashfn(ht, rht_obj(ht, he), hsize);
+	return rht_bucket_index(tbl, obj_raw_hashfn(ht, rht_obj(ht, he)));
 }
 
 static struct bucket_table *bucket_table_alloc(size_t nbuckets)
@@ -170,9 +140,9 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 	 * reaches a node that doesn't hash to the same bucket as the
 	 * previous node p. Call the previous node p;
 	 */
-	h = head_hashfn(ht, p, new_tbl->size);
+	h = head_hashfn(ht, new_tbl, p);
 	rht_for_each(he, p->next, ht) {
-		if (head_hashfn(ht, he, new_tbl->size) != h)
+		if (head_hashfn(ht, new_tbl, he) != h)
 			break;
 		p = he;
 	}
@@ -184,7 +154,7 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 	next = NULL;
 	if (he) {
 		rht_for_each(he, he->next, ht) {
-			if (head_hashfn(ht, he, new_tbl->size) == h) {
+			if (head_hashfn(ht, new_tbl, he) == h) {
 				next = he;
 				break;
 			}
@@ -237,9 +207,9 @@ int rhashtable_expand(struct rhashtable *ht)
 	 * single imprecise chain.
 	 */
 	for (i = 0; i < new_tbl->size; i++) {
-		h = i & (old_tbl->size - 1);
+		h = rht_bucket_index(old_tbl, i);
 		rht_for_each(he, old_tbl->buckets[h], ht) {
-			if (head_hashfn(ht, he, new_tbl->size) == i) {
+			if (head_hashfn(ht, new_tbl, he) == i) {
 				RCU_INIT_POINTER(new_tbl->buckets[i], he);
 				break;
 			}
@@ -353,7 +323,7 @@ void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 
 	ASSERT_RHT_MUTEX(ht);
 
-	hash = head_hashfn(ht, obj, tbl->size);
+	hash = head_hashfn(ht, tbl, obj);
 	RCU_INIT_POINTER(obj->next, tbl->buckets[hash]);
 	rcu_assign_pointer(tbl->buckets[hash], obj);
 	ht->nelems++;
@@ -413,7 +383,7 @@ bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj)
 
 	ASSERT_RHT_MUTEX(ht);
 
-	h = head_hashfn(ht, obj, tbl->size);
+	h = head_hashfn(ht, tbl, obj);
 
 	pprev = &tbl->buckets[h];
 	rht_for_each(he, tbl->buckets[h], ht) {
@@ -452,7 +422,7 @@ void *rhashtable_lookup(const struct rhashtable *ht, const void *key)
 
 	BUG_ON(!ht->p.key_len);
 
-	h = __hashfn(ht, key, ht->p.key_len, tbl->size);
+	h = key_hashfn(ht, key, ht->p.key_len);
 	rht_for_each_rcu(he, tbl->buckets[h], ht) {
 		if (memcmp(rht_obj(ht, he) + ht->p.key_offset, key,
 			   ht->p.key_len))
@@ -467,7 +437,7 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup);
 /**
  * rhashtable_lookup_compare - search hash table with compare function
  * @ht:		hash table
- * @hash:	hash value of desired entry
+ * @key:	the pointer to the key
  * @compare:	compare function, must return true on match
  * @arg:	argument passed on to compare function
  *
@@ -479,15 +449,14 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup);
  *
  * Returns the first entry on which the compare function returned true.
  */
-void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash,
+void *rhashtable_lookup_compare(const struct rhashtable *ht, const void *key,
 				bool (*compare)(void *, void *), void *arg)
 {
 	const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
 	struct rhash_head *he;
+	u32 hash;
 
-	if (unlikely(hash >= tbl->size))
-		return NULL;
-
+	hash = key_hashfn(ht, key, ht->p.key_len);
 	rht_for_each_rcu(he, tbl->buckets[hash], ht) {
 		if (!compare(rht_obj(ht, he), arg))
 			continue;
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 1e316ce4cb5..614ee099ba3 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -94,28 +94,40 @@ static void nft_hash_remove(const struct nft_set *set,
 	kfree(he);
 }
 
+struct nft_compare_arg {
+	const struct nft_set *set;
+	struct nft_set_elem *elem;
+};
+
+static bool nft_hash_compare(void *ptr, void *arg)
+{
+	struct nft_hash_elem *he = ptr;
+	struct nft_compare_arg *x = arg;
+
+	if (!nft_data_cmp(&he->key, &x->elem->key, x->set->klen)) {
+		x->elem->cookie = &he->node;
+		x->elem->flags = 0;
+		if (x->set->flags & NFT_SET_MAP)
+			nft_data_copy(&x->elem->data, he->data);
+
+		return true;
+	}
+
+	return false;
+}
+
 static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
 {
 	const struct rhashtable *priv = nft_set_priv(set);
-	const struct bucket_table *tbl = rht_dereference_rcu(priv->tbl, priv);
-	struct rhash_head __rcu * const *pprev;
-	struct nft_hash_elem *he;
-	u32 h;
-
-	h = rhashtable_hashfn(priv, &elem->key, set->klen);
-	pprev = &tbl->buckets[h];
-	rht_for_each_entry_rcu(he, tbl->buckets[h], node) {
-		if (nft_data_cmp(&he->key, &elem->key, set->klen)) {
-			pprev = &he->node.next;
-			continue;
-		}
+	struct nft_compare_arg arg = {
+		.set = set,
+		.elem = elem,
+	};
 
-		elem->cookie = (void *)pprev;
-		elem->flags = 0;
-		if (set->flags & NFT_SET_MAP)
-			nft_data_copy(&elem->data, he->data);
+	if (rhashtable_lookup_compare(priv, &elem->key,
+				      &nft_hash_compare, &arg))
 		return 0;
-	}
+
 	return -ENOENT;
 }
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 84ea76ca3f1..a5d7ed62756 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1002,11 +1002,8 @@ static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid,
 		.net = net,
 		.portid = portid,
 	};
-	u32 hash;
 
-	hash = rhashtable_hashfn(&table->hash, &portid, sizeof(portid));
-
-	return rhashtable_lookup_compare(&table->hash, hash,
+	return rhashtable_lookup_compare(&table->hash, &portid,
 					 &netlink_compare, &arg);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 88d6ed15acff1cb44b1d1f3c0a393b7f7744957a Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 2 Jan 2015 23:00:16 +0100
Subject: rhashtable: Convert bucket iterators to take table and index

This patch is in preparation to introduce per bucket spinlocks. It
extends all iterator macros to take the bucket table and bucket
index. It also introduces a new rht_dereference_bucket() to
handle protected accesses to buckets.

It introduces a barrier() to the RCU iterators to the prevent
the compiler from caching the first element.

The lockdep verifier is introduced as stub which always succeeds
and properly implement in the next patch when the locks are
introduced.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 173 ++++++++++++++++++++++++++++++---------------
 lib/rhashtable.c           |  30 +++++---
 net/netfilter/nft_hash.c   |  12 ++--
 net/netlink/af_netlink.c   |  12 ++--
 net/netlink/diag.c         |   4 +-
 5 files changed, 152 insertions(+), 79 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 1b51221c6bb..b54e24a0880 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -87,11 +87,18 @@ struct rhashtable {
 
 #ifdef CONFIG_PROVE_LOCKING
 int lockdep_rht_mutex_is_held(const struct rhashtable *ht);
+int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash);
 #else
 static inline int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
 {
 	return 1;
 }
+
+static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl,
+					     u32 hash)
+{
+	return 1;
+}
 #endif /* CONFIG_PROVE_LOCKING */
 
 int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params);
@@ -119,92 +126,144 @@ void rhashtable_destroy(const struct rhashtable *ht);
 #define rht_dereference_rcu(p, ht) \
 	rcu_dereference_check(p, lockdep_rht_mutex_is_held(ht))
 
-#define rht_entry(ptr, type, member) container_of(ptr, type, member)
-#define rht_entry_safe(ptr, type, member) \
-({ \
-	typeof(ptr) __ptr = (ptr); \
-	   __ptr ? rht_entry(__ptr, type, member) : NULL; \
-})
+#define rht_dereference_bucket(p, tbl, hash) \
+	rcu_dereference_protected(p, lockdep_rht_bucket_is_held(tbl, hash))
 
-#define rht_next_entry_safe(pos, ht, member) \
-({ \
-	pos ? rht_entry_safe(rht_dereference((pos)->member.next, ht), \
-			     typeof(*(pos)), member) : NULL; \
-})
+#define rht_dereference_bucket_rcu(p, tbl, hash) \
+	rcu_dereference_check(p, lockdep_rht_bucket_is_held(tbl, hash))
+
+#define rht_entry(tpos, pos, member) \
+	({ tpos = container_of(pos, typeof(*tpos), member); 1; })
 
 /**
- * rht_for_each - iterate over hash chain
- * @pos:	&struct rhash_head to use as a loop cursor.
- * @head:	head of the hash chain (struct rhash_head *)
- * @ht:		pointer to your struct rhashtable
+ * rht_for_each_continue - continue iterating over hash chain
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @head:	the previous &struct rhash_head to continue from
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
  */
-#define rht_for_each(pos, head, ht) \
-	for (pos = rht_dereference(head, ht); \
+#define rht_for_each_continue(pos, head, tbl, hash) \
+	for (pos = rht_dereference_bucket(head, tbl, hash); \
 	     pos; \
-	     pos = rht_dereference((pos)->next, ht))
+	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
+
+/**
+ * rht_for_each - iterate over hash chain
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
+ */
+#define rht_for_each(pos, tbl, hash) \
+	rht_for_each_continue(pos, (tbl)->buckets[hash], tbl, hash)
+
+/**
+ * rht_for_each_entry_continue - continue iterating over hash chain
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @head:	the previous &struct rhash_head to continue from
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
+ * @member:	name of the &struct rhash_head within the hashable struct.
+ */
+#define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member)	\
+	for (pos = rht_dereference_bucket(head, tbl, hash);		\
+	     pos && rht_entry(tpos, pos, member);			\
+	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
 
 /**
  * rht_for_each_entry - iterate over hash chain of given type
- * @pos:	type * to use as a loop cursor.
- * @head:	head of the hash chain (struct rhash_head *)
- * @ht:		pointer to your struct rhashtable
- * @member:	name of the rhash_head within the hashable struct.
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
+ * @member:	name of the &struct rhash_head within the hashable struct.
  */
-#define rht_for_each_entry(pos, head, ht, member) \
-	for (pos = rht_entry_safe(rht_dereference(head, ht), \
-				   typeof(*(pos)), member); \
-	     pos; \
-	     pos = rht_next_entry_safe(pos, ht, member))
+#define rht_for_each_entry(tpos, pos, tbl, hash, member)		\
+	rht_for_each_entry_continue(tpos, pos, (tbl)->buckets[hash],	\
+				    tbl, hash, member)
 
 /**
  * rht_for_each_entry_safe - safely iterate over hash chain of given type
- * @pos:	type * to use as a loop cursor.
- * @n:		type * to use for temporary next object storage
- * @head:	head of the hash chain (struct rhash_head *)
- * @ht:		pointer to your struct rhashtable
- * @member:	name of the rhash_head within the hashable struct.
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @next:	the &struct rhash_head to use as next in loop cursor.
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
+ * @member:	name of the &struct rhash_head within the hashable struct.
  *
  * This hash chain list-traversal primitive allows for the looped code to
  * remove the loop cursor from the list.
  */
-#define rht_for_each_entry_safe(pos, n, head, ht, member)		\
-	for (pos = rht_entry_safe(rht_dereference(head, ht), \
-				  typeof(*(pos)), member), \
-	     n = rht_next_entry_safe(pos, ht, member); \
-	     pos; \
-	     pos = n, \
-	     n = rht_next_entry_safe(pos, ht, member))
+#define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member)	    \
+	for (pos = rht_dereference_bucket((tbl)->buckets[hash], tbl, hash), \
+	     next = pos ? rht_dereference_bucket(pos->next, tbl, hash)      \
+			: NULL;						    \
+	     pos && rht_entry(tpos, pos, member);			    \
+	     pos = next)
+
+/**
+ * rht_for_each_rcu_continue - continue iterating over rcu hash chain
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @head:	the previous &struct rhash_head to continue from
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
+ *
+ * This hash chain list-traversal primitive may safely run concurrently with
+ * the _rcu mutation primitives such as rhashtable_insert() as long as the
+ * traversal is guarded by rcu_read_lock().
+ */
+#define rht_for_each_rcu_continue(pos, head, tbl, hash)			\
+	for (({barrier(); }),						\
+	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		\
+	     pos;							\
+	     pos = rcu_dereference_raw(pos->next))
 
 /**
  * rht_for_each_rcu - iterate over rcu hash chain
- * @pos:	&struct rhash_head to use as a loop cursor.
- * @head:	head of the hash chain (struct rhash_head *)
- * @ht:		pointer to your struct rhashtable
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
  *
  * This hash chain list-traversal primitive may safely run concurrently with
- * the _rcu fkht mutation primitives such as rht_insert() as long as the
+ * the _rcu mutation primitives such as rhashtable_insert() as long as the
  * traversal is guarded by rcu_read_lock().
  */
-#define rht_for_each_rcu(pos, head, ht) \
-	for (pos = rht_dereference_rcu(head, ht); \
-	     pos; \
-	     pos = rht_dereference_rcu((pos)->next, ht))
+#define rht_for_each_rcu(pos, tbl, hash)				\
+	rht_for_each_rcu_continue(pos, (tbl)->buckets[hash], tbl, hash)
+
+/**
+ * rht_for_each_entry_rcu_continue - continue iterating over rcu hash chain
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @head:	the previous &struct rhash_head to continue from
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
+ * @member:	name of the &struct rhash_head within the hashable struct.
+ *
+ * This hash chain list-traversal primitive may safely run concurrently with
+ * the _rcu mutation primitives such as rhashtable_insert() as long as the
+ * traversal is guarded by rcu_read_lock().
+ */
+#define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \
+	for (({barrier(); }),						    \
+	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		    \
+	     pos && rht_entry(tpos, pos, member);			    \
+	     pos = rht_dereference_bucket_rcu(pos->next, tbl, hash))
 
 /**
  * rht_for_each_entry_rcu - iterate over rcu hash chain of given type
- * @pos:	type * to use as a loop cursor.
- * @head:	head of the hash chain (struct rhash_head *)
- * @member:	name of the rhash_head within the hashable struct.
+ * @tpos:	the type * to use as a loop cursor.
+ * @pos:	the &struct rhash_head to use as a loop cursor.
+ * @tbl:	the &struct bucket_table
+ * @hash:	the hash value / bucket index
+ * @member:	name of the &struct rhash_head within the hashable struct.
  *
  * This hash chain list-traversal primitive may safely run concurrently with
- * the _rcu fkht mutation primitives such as rht_insert() as long as the
+ * the _rcu mutation primitives such as rhashtable_insert() as long as the
  * traversal is guarded by rcu_read_lock().
  */
-#define rht_for_each_entry_rcu(pos, head, member) \
-	for (pos = rht_entry_safe(rcu_dereference_raw(head), \
-				  typeof(*(pos)), member); \
-	     pos; \
-	     pos = rht_entry_safe(rcu_dereference_raw((pos)->member.next), \
-				  typeof(*(pos)), member))
+#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member)		\
+	rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\
+					tbl, hash, member)
 
 #endif /* _LINUX_RHASHTABLE_H */
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index b658245826a..ce450d095fd 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -35,6 +35,12 @@ int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
 	return ht->p.mutex_is_held(ht->p.parent);
 }
 EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
+
+int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
+{
+	return 1;
+}
+EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
 #endif
 
 static void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he)
@@ -141,7 +147,7 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 	 * previous node p. Call the previous node p;
 	 */
 	h = head_hashfn(ht, new_tbl, p);
-	rht_for_each(he, p->next, ht) {
+	rht_for_each_continue(he, p->next, old_tbl, n) {
 		if (head_hashfn(ht, new_tbl, he) != h)
 			break;
 		p = he;
@@ -153,7 +159,7 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 	 */
 	next = NULL;
 	if (he) {
-		rht_for_each(he, he->next, ht) {
+		rht_for_each_continue(he, he->next, old_tbl, n) {
 			if (head_hashfn(ht, new_tbl, he) == h) {
 				next = he;
 				break;
@@ -208,7 +214,7 @@ int rhashtable_expand(struct rhashtable *ht)
 	 */
 	for (i = 0; i < new_tbl->size; i++) {
 		h = rht_bucket_index(old_tbl, i);
-		rht_for_each(he, old_tbl->buckets[h], ht) {
+		rht_for_each(he, old_tbl, h) {
 			if (head_hashfn(ht, new_tbl, he) == i) {
 				RCU_INIT_POINTER(new_tbl->buckets[i], he);
 				break;
@@ -286,7 +292,7 @@ int rhashtable_shrink(struct rhashtable *ht)
 		 * to the new bucket.
 		 */
 		for (pprev = &ntbl->buckets[i]; *pprev != NULL;
-		     pprev = &rht_dereference(*pprev, ht)->next)
+		     pprev = &rht_dereference_bucket(*pprev, ntbl, i)->next)
 			;
 		RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]);
 	}
@@ -386,7 +392,7 @@ bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj)
 	h = head_hashfn(ht, tbl, obj);
 
 	pprev = &tbl->buckets[h];
-	rht_for_each(he, tbl->buckets[h], ht) {
+	rht_for_each(he, tbl, h) {
 		if (he != obj) {
 			pprev = &he->next;
 			continue;
@@ -423,7 +429,7 @@ void *rhashtable_lookup(const struct rhashtable *ht, const void *key)
 	BUG_ON(!ht->p.key_len);
 
 	h = key_hashfn(ht, key, ht->p.key_len);
-	rht_for_each_rcu(he, tbl->buckets[h], ht) {
+	rht_for_each_rcu(he, tbl, h) {
 		if (memcmp(rht_obj(ht, he) + ht->p.key_offset, key,
 			   ht->p.key_len))
 			continue;
@@ -457,7 +463,7 @@ void *rhashtable_lookup_compare(const struct rhashtable *ht, const void *key,
 	u32 hash;
 
 	hash = key_hashfn(ht, key, ht->p.key_len);
-	rht_for_each_rcu(he, tbl->buckets[hash], ht) {
+	rht_for_each_rcu(he, tbl, hash) {
 		if (!compare(rht_obj(ht, he), arg))
 			continue;
 		return rht_obj(ht, he);
@@ -625,6 +631,7 @@ static int __init test_rht_lookup(struct rhashtable *ht)
 static void test_bucket_stats(struct rhashtable *ht, bool quiet)
 {
 	unsigned int cnt, rcu_cnt, i, total = 0;
+	struct rhash_head *pos;
 	struct test_obj *obj;
 	struct bucket_table *tbl;
 
@@ -635,14 +642,14 @@ static void test_bucket_stats(struct rhashtable *ht, bool quiet)
 		if (!quiet)
 			pr_info(" [%#4x/%zu]", i, tbl->size);
 
-		rht_for_each_entry_rcu(obj, tbl->buckets[i], node) {
+		rht_for_each_entry_rcu(obj, pos, tbl, i, node) {
 			cnt++;
 			total++;
 			if (!quiet)
 				pr_cont(" [%p],", obj);
 		}
 
-		rht_for_each_entry_rcu(obj, tbl->buckets[i], node)
+		rht_for_each_entry_rcu(obj, pos, tbl, i, node)
 			rcu_cnt++;
 
 		if (rcu_cnt != cnt)
@@ -664,7 +671,8 @@ static void test_bucket_stats(struct rhashtable *ht, bool quiet)
 static int __init test_rhashtable(struct rhashtable *ht)
 {
 	struct bucket_table *tbl;
-	struct test_obj *obj, *next;
+	struct test_obj *obj;
+	struct rhash_head *pos, *next;
 	int err;
 	unsigned int i;
 
@@ -733,7 +741,7 @@ static int __init test_rhashtable(struct rhashtable *ht)
 error:
 	tbl = rht_dereference_rcu(ht->tbl, ht);
 	for (i = 0; i < tbl->size; i++)
-		rht_for_each_entry_safe(obj, next, tbl->buckets[i], ht, node)
+		rht_for_each_entry_safe(obj, pos, next, tbl, i, node)
 			kfree(obj);
 
 	return err;
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 614ee099ba3..d93f1f4c22a 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -142,7 +142,9 @@ static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 
 	tbl = rht_dereference_rcu(priv->tbl, priv);
 	for (i = 0; i < tbl->size; i++) {
-		rht_for_each_entry_rcu(he, tbl->buckets[i], node) {
+		struct rhash_head *pos;
+
+		rht_for_each_entry_rcu(he, pos, tbl, i, node) {
 			if (iter->count < iter->skip)
 				goto cont;
 
@@ -197,15 +199,13 @@ static void nft_hash_destroy(const struct nft_set *set)
 {
 	const struct rhashtable *priv = nft_set_priv(set);
 	const struct bucket_table *tbl = priv->tbl;
-	struct nft_hash_elem *he, *next;
+	struct nft_hash_elem *he;
+	struct rhash_head *pos, *next;
 	unsigned int i;
 
 	for (i = 0; i < tbl->size; i++) {
-		for (he = rht_entry(tbl->buckets[i], struct nft_hash_elem, node);
-		     he != NULL; he = next) {
-			next = rht_entry(he->node.next, struct nft_hash_elem, node);
+		rht_for_each_entry_safe(he, pos, next, tbl, i, node)
 			nft_hash_elem_destroy(set, he);
-		}
 	}
 	rhashtable_destroy(priv);
 }
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index a5d7ed62756..57449b6089c 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2898,7 +2898,9 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos)
 		const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
 
 		for (j = 0; j < tbl->size; j++) {
-			rht_for_each_entry_rcu(nlk, tbl->buckets[j], node) {
+			struct rhash_head *node;
+
+			rht_for_each_entry_rcu(nlk, node, tbl, j, node) {
 				s = (struct sock *)nlk;
 
 				if (sock_net(s) != seq_file_net(seq))
@@ -2926,6 +2928,8 @@ static void *netlink_seq_start(struct seq_file *seq, loff_t *pos)
 static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct rhashtable *ht;
+	const struct bucket_table *tbl;
+	struct rhash_head *node;
 	struct netlink_sock *nlk;
 	struct nl_seq_iter *iter;
 	struct net *net;
@@ -2942,17 +2946,17 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 	i = iter->link;
 	ht = &nl_table[i].hash;
-	rht_for_each_entry(nlk, nlk->node.next, ht, node)
+	tbl = rht_dereference_rcu(ht->tbl, ht);
+	rht_for_each_entry_rcu_continue(nlk, node, nlk->node.next, tbl, iter->hash_idx, node)
 		if (net_eq(sock_net((struct sock *)nlk), net))
 			return nlk;
 
 	j = iter->hash_idx + 1;
 
 	do {
-		const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
 
 		for (; j < tbl->size; j++) {
-			rht_for_each_entry(nlk, tbl->buckets[j], ht, node) {
+			rht_for_each_entry_rcu(nlk, node, tbl, j, node) {
 				if (net_eq(sock_net((struct sock *)nlk), net)) {
 					iter->link = i;
 					iter->hash_idx = j;
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index de8c74a3c06..fcca36d81a6 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -113,7 +113,9 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	req = nlmsg_data(cb->nlh);
 
 	for (i = 0; i < htbl->size; i++) {
-		rht_for_each_entry(nlsk, htbl->buckets[i], ht, node) {
+		struct rhash_head *pos;
+
+		rht_for_each_entry(nlsk, pos, htbl, i, node) {
 			sk = (struct sock *)nlsk;
 
 			if (!net_eq(sock_net(sk), net))
-- 
cgit v1.2.3-70-g09d2


From 897362e446436d245972e72c6bc5b33bd7a5c659 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 2 Jan 2015 23:00:18 +0100
Subject: nft_hash: Remove rhashtable_remove_pprev()

The removal function of nft_hash currently stores a reference to the
previous element during lookup which is used to optimize removal later
on. This was possible because a lock is held throughout calling
rhashtable_lookup() and rhashtable_remove().

With the introdution of deferred table resizing in parallel to lookups
and insertions, the nftables lock will no longer synchronize all
table mutations and the stored pprev may become invalid.

Removing this optimization makes removal slightly more expensive on
average but allows taking the resize cost out of the insert and
remove path.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Cc: netfilter-devel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  2 --
 lib/rhashtable.c           | 34 +++++++---------------------------
 net/netfilter/nft_hash.c   | 11 +++--------
 3 files changed, 10 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index b54e24a0880..f624d4b5045 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -105,8 +105,6 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params);
 
 void rhashtable_insert(struct rhashtable *ht, struct rhash_head *node);
 bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *node);
-void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
-			     struct rhash_head __rcu **pprev);
 
 bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size);
 bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size);
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 0bd29c17891..e6b85c4a582 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -344,32 +344,6 @@ void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 }
 EXPORT_SYMBOL_GPL(rhashtable_insert);
 
-/**
- * rhashtable_remove_pprev - remove object from hash table given previous element
- * @ht:		hash table
- * @obj:	pointer to hash head inside object
- * @pprev:	pointer to previous element
- *
- * Identical to rhashtable_remove() but caller is alreayd aware of the element
- * in front of the element to be deleted. This is in particular useful for
- * deletion when combined with walking or lookup.
- */
-void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj,
-			     struct rhash_head __rcu **pprev)
-{
-	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
-
-	ASSERT_RHT_MUTEX(ht);
-
-	RCU_INIT_POINTER(*pprev, obj->next);
-	ht->nelems--;
-
-	if (ht->p.shrink_decision &&
-	    ht->p.shrink_decision(ht, tbl->size))
-		rhashtable_shrink(ht);
-}
-EXPORT_SYMBOL_GPL(rhashtable_remove_pprev);
-
 /**
  * rhashtable_remove - remove object from hash table
  * @ht:		hash table
@@ -403,7 +377,13 @@ bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj)
 			continue;
 		}
 
-		rhashtable_remove_pprev(ht, he, pprev);
+		RCU_INIT_POINTER(*pprev, he->next);
+		ht->nelems--;
+
+		if (ht->p.shrink_decision &&
+		    ht->p.shrink_decision(ht, tbl->size))
+			rhashtable_shrink(ht);
+
 		return true;
 	}
 
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index d93f1f4c22a..7f903cf9a1b 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -83,15 +83,10 @@ static void nft_hash_remove(const struct nft_set *set,
 			    const struct nft_set_elem *elem)
 {
 	struct rhashtable *priv = nft_set_priv(set);
-	struct rhash_head *he, __rcu **pprev;
-
-	pprev = elem->cookie;
-	he = rht_dereference((*pprev), priv);
-
-	rhashtable_remove_pprev(priv, he, pprev);
 
+	rhashtable_remove(priv, elem->cookie);
 	synchronize_rcu();
-	kfree(he);
+	kfree(elem->cookie);
 }
 
 struct nft_compare_arg {
@@ -105,7 +100,7 @@ static bool nft_hash_compare(void *ptr, void *arg)
 	struct nft_compare_arg *x = arg;
 
 	if (!nft_data_cmp(&he->key, &x->elem->key, x->set->klen)) {
-		x->elem->cookie = &he->node;
+		x->elem->cookie = he;
 		x->elem->flags = 0;
 		if (x->set->flags & NFT_SET_MAP)
 			nft_data_copy(&x->elem->data, he->data);
-- 
cgit v1.2.3-70-g09d2


From 113948d841e8d78039e5dbbb5248f5b73e99eafa Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 2 Jan 2015 23:00:19 +0100
Subject: spinlock: Add spin_lock_bh_nested()

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/spinlock.h         | 8 ++++++++
 include/linux/spinlock_api_smp.h | 2 ++
 include/linux/spinlock_api_up.h  | 1 +
 kernel/locking/spinlock.c        | 8 ++++++++
 4 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 262ba4ef9a8..3e18379dfa6 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -190,6 +190,8 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define raw_spin_lock_nested(lock, subclass) \
 	_raw_spin_lock_nested(lock, subclass)
+# define raw_spin_lock_bh_nested(lock, subclass) \
+	_raw_spin_lock_bh_nested(lock, subclass)
 
 # define raw_spin_lock_nest_lock(lock, nest_lock)			\
 	 do {								\
@@ -205,6 +207,7 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 # define raw_spin_lock_nested(lock, subclass)		\
 	_raw_spin_lock(((void)(subclass), (lock)))
 # define raw_spin_lock_nest_lock(lock, nest_lock)	_raw_spin_lock(lock)
+# define raw_spin_lock_bh_nested(lock, subclass)	_raw_spin_lock_bh(lock)
 #endif
 
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
@@ -324,6 +327,11 @@ do {								\
 	raw_spin_lock_nested(spinlock_check(lock), subclass);	\
 } while (0)
 
+#define spin_lock_bh_nested(lock, subclass)			\
+do {								\
+	raw_spin_lock_bh_nested(spinlock_check(lock), subclass);\
+} while (0)
+
 #define spin_lock_nest_lock(lock, nest_lock)				\
 do {									\
 	raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock);	\
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 42dfab89e74..5344268e6e6 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -22,6 +22,8 @@ int in_lock_functions(unsigned long addr);
 void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)		__acquires(lock);
 void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
 								__acquires(lock);
+void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass)
+								__acquires(lock);
 void __lockfunc
 _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map)
 								__acquires(lock);
diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h
index d0d188861ad..d3afef9d8db 100644
--- a/include/linux/spinlock_api_up.h
+++ b/include/linux/spinlock_api_up.h
@@ -57,6 +57,7 @@
 
 #define _raw_spin_lock(lock)			__LOCK(lock)
 #define _raw_spin_lock_nested(lock, subclass)	__LOCK(lock)
+#define _raw_spin_lock_bh_nested(lock, subclass) __LOCK(lock)
 #define _raw_read_lock(lock)			__LOCK(lock)
 #define _raw_write_lock(lock)			__LOCK(lock)
 #define _raw_spin_lock_bh(lock)			__LOCK_BH(lock)
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 4b082b5cac9..db3ccb1dd61 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -363,6 +363,14 @@ void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
 }
 EXPORT_SYMBOL(_raw_spin_lock_nested);
 
+void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass)
+{
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
+}
+EXPORT_SYMBOL(_raw_spin_lock_bh_nested);
+
 unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock,
 						   int subclass)
 {
-- 
cgit v1.2.3-70-g09d2


From 97defe1ecf868b8127f8e62395499d6a06e4c4b1 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 2 Jan 2015 23:00:20 +0100
Subject: rhashtable: Per bucket locks & deferred expansion/shrinking

Introduces an array of spinlocks to protect bucket mutations. The number
of spinlocks per CPU is configurable and selected based on the hash of
the bucket. This allows for parallel insertions and removals of entries
which do not share a lock.

The patch also defers expansion and shrinking to a worker queue which
allows insertion and removal from atomic context. Insertions and
deletions may occur in parallel to it and are only held up briefly
while the particular bucket is linked or unzipped.

Mutations of the bucket table pointer is protected by a new mutex, read
access is RCU protected.

In the event of an expansion or shrinking, the new bucket table allocated
is exposed as a so called future table as soon as the resize process
starts.  Lookups, deletions, and insertions will briefly use both tables.
The future table becomes the main table after an RCU grace period and
initial linking of the old to the new table was performed. Optimization
of the chains to make use of the new number of buckets follows only the
new table is in use.

The side effect of this is that during that RCU grace period, a bucket
traversal using any rht_for_each() variant on the main table will not see
any insertions performed during the RCU grace period which would at that
point land in the future table. The lookup will see them as it searches
both tables if needed.

Having multiple insertions and removals occur in parallel requires nelems
to become an atomic counter.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  37 ++--
 lib/rhashtable.c           | 458 ++++++++++++++++++++++++++++++++++-----------
 net/netfilter/nft_hash.c   |  27 ++-
 net/netlink/af_netlink.c   |  15 +-
 4 files changed, 384 insertions(+), 153 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index f624d4b5045..a1688f0a619 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -19,6 +19,7 @@
 #define _LINUX_RHASHTABLE_H
 
 #include <linux/rculist.h>
+#include <linux/workqueue.h>
 
 struct rhash_head {
 	struct rhash_head __rcu		*next;
@@ -26,8 +27,17 @@ struct rhash_head {
 
 #define INIT_HASH_HEAD(ptr) ((ptr)->next = NULL)
 
+/**
+ * struct bucket_table - Table of hash buckets
+ * @size: Number of hash buckets
+ * @locks_mask: Mask to apply before accessing locks[]
+ * @locks: Array of spinlocks protecting individual buckets
+ * @buckets: size * hash buckets
+ */
 struct bucket_table {
 	size_t				size;
+	unsigned int			locks_mask;
+	spinlock_t			*locks;
 	struct rhash_head __rcu		*buckets[];
 };
 
@@ -45,11 +55,11 @@ struct rhashtable;
  * @hash_rnd: Seed to use while hashing
  * @max_shift: Maximum number of shifts while expanding
  * @min_shift: Minimum number of shifts while shrinking
+ * @locks_mul: Number of bucket locks to allocate per cpu (default: 128)
  * @hashfn: Function to hash key
  * @obj_hashfn: Function to hash object
  * @grow_decision: If defined, may return true if table should expand
  * @shrink_decision: If defined, may return true if table should shrink
- * @mutex_is_held: Must return true if protecting mutex is held
  */
 struct rhashtable_params {
 	size_t			nelem_hint;
@@ -59,37 +69,42 @@ struct rhashtable_params {
 	u32			hash_rnd;
 	size_t			max_shift;
 	size_t			min_shift;
+	size_t			locks_mul;
 	rht_hashfn_t		hashfn;
 	rht_obj_hashfn_t	obj_hashfn;
 	bool			(*grow_decision)(const struct rhashtable *ht,
 						 size_t new_size);
 	bool			(*shrink_decision)(const struct rhashtable *ht,
 						   size_t new_size);
-#ifdef CONFIG_PROVE_LOCKING
-	int			(*mutex_is_held)(void *parent);
-	void			*parent;
-#endif
 };
 
 /**
  * struct rhashtable - Hash table handle
  * @tbl: Bucket table
+ * @future_tbl: Table under construction during expansion/shrinking
  * @nelems: Number of elements in table
  * @shift: Current size (1 << shift)
  * @p: Configuration parameters
+ * @run_work: Deferred worker to expand/shrink asynchronously
+ * @mutex: Mutex to protect current/future table swapping
+ * @being_destroyed: True if table is set up for destruction
  */
 struct rhashtable {
 	struct bucket_table __rcu	*tbl;
-	size_t				nelems;
+	struct bucket_table __rcu       *future_tbl;
+	atomic_t			nelems;
 	size_t				shift;
 	struct rhashtable_params	p;
+	struct delayed_work             run_work;
+	struct mutex                    mutex;
+	bool                            being_destroyed;
 };
 
 #ifdef CONFIG_PROVE_LOCKING
-int lockdep_rht_mutex_is_held(const struct rhashtable *ht);
+int lockdep_rht_mutex_is_held(struct rhashtable *ht);
 int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash);
 #else
-static inline int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
+static inline int lockdep_rht_mutex_is_held(struct rhashtable *ht)
 {
 	return 1;
 }
@@ -112,11 +127,11 @@ bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size);
 int rhashtable_expand(struct rhashtable *ht);
 int rhashtable_shrink(struct rhashtable *ht);
 
-void *rhashtable_lookup(const struct rhashtable *ht, const void *key);
-void *rhashtable_lookup_compare(const struct rhashtable *ht, const void *key,
+void *rhashtable_lookup(struct rhashtable *ht, const void *key);
+void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key,
 				bool (*compare)(void *, void *), void *arg);
 
-void rhashtable_destroy(const struct rhashtable *ht);
+void rhashtable_destroy(struct rhashtable *ht);
 
 #define rht_dereference(p, ht) \
 	rcu_dereference_protected(p, lockdep_rht_mutex_is_held(ht))
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index e6b85c4a582..312e3437c7b 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -26,19 +26,42 @@
 
 #define HASH_DEFAULT_SIZE	64UL
 #define HASH_MIN_SIZE		4UL
+#define BUCKET_LOCKS_PER_CPU   128UL
+
+enum {
+	RHT_LOCK_NORMAL,
+	RHT_LOCK_NESTED,
+	RHT_LOCK_NESTED2,
+};
+
+/* The bucket lock is selected based on the hash and protects mutations
+ * on a group of hash buckets.
+ *
+ * IMPORTANT: When holding the bucket lock of both the old and new table
+ * during expansions and shrinking, the old bucket lock must always be
+ * acquired first.
+ */
+static spinlock_t *bucket_lock(const struct bucket_table *tbl, u32 hash)
+{
+	return &tbl->locks[hash & tbl->locks_mask];
+}
 
 #define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT))
+#define ASSERT_BUCKET_LOCK(TBL, HASH) \
+	BUG_ON(!lockdep_rht_bucket_is_held(TBL, HASH))
 
 #ifdef CONFIG_PROVE_LOCKING
-int lockdep_rht_mutex_is_held(const struct rhashtable *ht)
+int lockdep_rht_mutex_is_held(struct rhashtable *ht)
 {
-	return ht->p.mutex_is_held(ht->p.parent);
+	return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1;
 }
 EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held);
 
 int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash)
 {
-	return 1;
+	spinlock_t *lock = bucket_lock(tbl, hash);
+
+	return (debug_locks) ? lockdep_is_held(lock) : 1;
 }
 EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held);
 #endif
@@ -66,7 +89,7 @@ static u32 obj_raw_hashfn(const struct rhashtable *ht, const void *ptr)
 	return hash;
 }
 
-static u32 key_hashfn(const struct rhashtable *ht, const void *key, u32 len)
+static u32 key_hashfn(struct rhashtable *ht, const void *key, u32 len)
 {
 	struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
 	u32 hash;
@@ -95,7 +118,49 @@ static struct rhash_head __rcu **bucket_tail(struct bucket_table *tbl, u32 n)
 	return pprev;
 }
 
-static struct bucket_table *bucket_table_alloc(size_t nbuckets)
+static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl)
+{
+	unsigned int i, size;
+#if defined(CONFIG_PROVE_LOCKING)
+	unsigned int nr_pcpus = 2;
+#else
+	unsigned int nr_pcpus = num_possible_cpus();
+#endif
+
+	nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL);
+	size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul);
+
+	/* Never allocate more than one lock per bucket */
+	size = min_t(unsigned int, size, tbl->size);
+
+	if (sizeof(spinlock_t) != 0) {
+#ifdef CONFIG_NUMA
+		if (size * sizeof(spinlock_t) > PAGE_SIZE)
+			tbl->locks = vmalloc(size * sizeof(spinlock_t));
+		else
+#endif
+		tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
+					   GFP_KERNEL);
+		if (!tbl->locks)
+			return -ENOMEM;
+		for (i = 0; i < size; i++)
+			spin_lock_init(&tbl->locks[i]);
+	}
+	tbl->locks_mask = size - 1;
+
+	return 0;
+}
+
+static void bucket_table_free(const struct bucket_table *tbl)
+{
+	if (tbl)
+		kvfree(tbl->locks);
+
+	kvfree(tbl);
+}
+
+static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
+					       size_t nbuckets)
 {
 	struct bucket_table *tbl;
 	size_t size;
@@ -110,12 +175,12 @@ static struct bucket_table *bucket_table_alloc(size_t nbuckets)
 
 	tbl->size = nbuckets;
 
-	return tbl;
-}
+	if (alloc_bucket_locks(ht, tbl) < 0) {
+		bucket_table_free(tbl);
+		return NULL;
+	}
 
-static void bucket_table_free(const struct bucket_table *tbl)
-{
-	kvfree(tbl);
+	return tbl;
 }
 
 /**
@@ -126,7 +191,7 @@ static void bucket_table_free(const struct bucket_table *tbl)
 bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size)
 {
 	/* Expand table when exceeding 75% load */
-	return ht->nelems > (new_size / 4 * 3);
+	return atomic_read(&ht->nelems) > (new_size / 4 * 3);
 }
 EXPORT_SYMBOL_GPL(rht_grow_above_75);
 
@@ -138,41 +203,59 @@ EXPORT_SYMBOL_GPL(rht_grow_above_75);
 bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size)
 {
 	/* Shrink table beneath 30% load */
-	return ht->nelems < (new_size * 3 / 10);
+	return atomic_read(&ht->nelems) < (new_size * 3 / 10);
 }
 EXPORT_SYMBOL_GPL(rht_shrink_below_30);
 
 static void hashtable_chain_unzip(const struct rhashtable *ht,
 				  const struct bucket_table *new_tbl,
-				  struct bucket_table *old_tbl, size_t n)
+				  struct bucket_table *old_tbl,
+				  size_t old_hash)
 {
 	struct rhash_head *he, *p, *next;
-	unsigned int h;
+	spinlock_t *new_bucket_lock, *new_bucket_lock2 = NULL;
+	unsigned int new_hash, new_hash2;
+
+	ASSERT_BUCKET_LOCK(old_tbl, old_hash);
 
 	/* Old bucket empty, no work needed. */
-	p = rht_dereference(old_tbl->buckets[n], ht);
+	p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl,
+				   old_hash);
 	if (!p)
 		return;
 
+	new_hash = new_hash2 = head_hashfn(ht, new_tbl, p);
+	new_bucket_lock = bucket_lock(new_tbl, new_hash);
+
 	/* Advance the old bucket pointer one or more times until it
 	 * reaches a node that doesn't hash to the same bucket as the
 	 * previous node p. Call the previous node p;
 	 */
-	h = head_hashfn(ht, new_tbl, p);
-	rht_for_each_continue(he, p->next, old_tbl, n) {
-		if (head_hashfn(ht, new_tbl, he) != h)
+	rht_for_each_continue(he, p->next, old_tbl, old_hash) {
+		new_hash2 = head_hashfn(ht, new_tbl, he);
+		if (new_hash != new_hash2)
 			break;
 		p = he;
 	}
-	RCU_INIT_POINTER(old_tbl->buckets[n], p->next);
+	rcu_assign_pointer(old_tbl->buckets[old_hash], p->next);
+
+	spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
+
+	/* If we have encountered an entry that maps to a different bucket in
+	 * the new table, lock down that bucket as well as we might cut off
+	 * the end of the chain.
+	 */
+	new_bucket_lock2 = bucket_lock(new_tbl, new_hash);
+	if (new_bucket_lock != new_bucket_lock2)
+		spin_lock_bh_nested(new_bucket_lock2, RHT_LOCK_NESTED2);
 
 	/* Find the subsequent node which does hash to the same
 	 * bucket as node P, or NULL if no such node exists.
 	 */
 	next = NULL;
 	if (he) {
-		rht_for_each_continue(he, he->next, old_tbl, n) {
-			if (head_hashfn(ht, new_tbl, he) == h) {
+		rht_for_each_continue(he, he->next, old_tbl, old_hash) {
+			if (head_hashfn(ht, new_tbl, he) == new_hash) {
 				next = he;
 				break;
 			}
@@ -182,7 +265,23 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 	/* Set p's next pointer to that subsequent node pointer,
 	 * bypassing the nodes which do not hash to p's bucket
 	 */
-	RCU_INIT_POINTER(p->next, next);
+	rcu_assign_pointer(p->next, next);
+
+	if (new_bucket_lock != new_bucket_lock2)
+		spin_unlock_bh(new_bucket_lock2);
+	spin_unlock_bh(new_bucket_lock);
+}
+
+static void link_old_to_new(struct bucket_table *new_tbl,
+			    unsigned int new_hash, struct rhash_head *entry)
+{
+	spinlock_t *new_bucket_lock;
+
+	new_bucket_lock = bucket_lock(new_tbl, new_hash);
+
+	spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
+	rcu_assign_pointer(*bucket_tail(new_tbl, new_hash), entry);
+	spin_unlock_bh(new_bucket_lock);
 }
 
 /**
@@ -195,43 +294,59 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
  * This function may only be called in a context where it is safe to call
  * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
  *
- * The caller must ensure that no concurrent table mutations take place.
- * It is however valid to have concurrent lookups if they are RCU protected.
+ * The caller must ensure that no concurrent resizing occurs by holding
+ * ht->mutex.
+ *
+ * It is valid to have concurrent insertions and deletions protected by per
+ * bucket locks or concurrent RCU protected lookups and traversals.
  */
 int rhashtable_expand(struct rhashtable *ht)
 {
 	struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
 	struct rhash_head *he;
-	unsigned int i, h;
-	bool complete;
+	spinlock_t *old_bucket_lock;
+	unsigned int new_hash, old_hash;
+	bool complete = false;
 
 	ASSERT_RHT_MUTEX(ht);
 
 	if (ht->p.max_shift && ht->shift >= ht->p.max_shift)
 		return 0;
 
-	new_tbl = bucket_table_alloc(old_tbl->size * 2);
+	new_tbl = bucket_table_alloc(ht, old_tbl->size * 2);
 	if (new_tbl == NULL)
 		return -ENOMEM;
 
 	ht->shift++;
 
-	/* For each new bucket, search the corresponding old bucket
-	 * for the first entry that hashes to the new bucket, and
-	 * link the new bucket to that entry. Since all the entries
-	 * which will end up in the new bucket appear in the same
-	 * old bucket, this constructs an entirely valid new hash
-	 * table, but with multiple buckets "zipped" together into a
-	 * single imprecise chain.
+	/* Make insertions go into the new, empty table right away. Deletions
+	 * and lookups will be attempted in both tables until we synchronize.
+	 * The synchronize_rcu() guarantees for the new table to be picked up
+	 * so no new additions go into the old table while we relink.
+	 */
+	rcu_assign_pointer(ht->future_tbl, new_tbl);
+	synchronize_rcu();
+
+	/* For each new bucket, search the corresponding old bucket for the
+	 * first entry that hashes to the new bucket, and link the end of
+	 * newly formed bucket chain (containing entries added to future
+	 * table) to that entry. Since all the entries which will end up in
+	 * the new bucket appear in the same old bucket, this constructs an
+	 * entirely valid new hash table, but with multiple buckets
+	 * "zipped" together into a single imprecise chain.
 	 */
-	for (i = 0; i < new_tbl->size; i++) {
-		h = rht_bucket_index(old_tbl, i);
-		rht_for_each(he, old_tbl, h) {
-			if (head_hashfn(ht, new_tbl, he) == i) {
-				RCU_INIT_POINTER(new_tbl->buckets[i], he);
+	for (new_hash = 0; new_hash < new_tbl->size; new_hash++) {
+		old_hash = rht_bucket_index(old_tbl, new_hash);
+		old_bucket_lock = bucket_lock(old_tbl, old_hash);
+
+		spin_lock_bh(old_bucket_lock);
+		rht_for_each(he, old_tbl, old_hash) {
+			if (head_hashfn(ht, new_tbl, he) == new_hash) {
+				link_old_to_new(new_tbl, new_hash, he);
 				break;
 			}
 		}
+		spin_unlock_bh(old_bucket_lock);
 	}
 
 	/* Publish the new table pointer. Lookups may now traverse
@@ -241,7 +356,7 @@ int rhashtable_expand(struct rhashtable *ht)
 	rcu_assign_pointer(ht->tbl, new_tbl);
 
 	/* Unzip interleaved hash chains */
-	do {
+	while (!complete && !ht->being_destroyed) {
 		/* Wait for readers. All new readers will see the new
 		 * table, and thus no references to the old table will
 		 * remain.
@@ -253,12 +368,17 @@ int rhashtable_expand(struct rhashtable *ht)
 		 * table): ...
 		 */
 		complete = true;
-		for (i = 0; i < old_tbl->size; i++) {
-			hashtable_chain_unzip(ht, new_tbl, old_tbl, i);
-			if (old_tbl->buckets[i] != NULL)
+		for (old_hash = 0; old_hash < old_tbl->size; old_hash++) {
+			old_bucket_lock = bucket_lock(old_tbl, old_hash);
+			spin_lock_bh(old_bucket_lock);
+
+			hashtable_chain_unzip(ht, new_tbl, old_tbl, old_hash);
+			if (old_tbl->buckets[old_hash] != NULL)
 				complete = false;
+
+			spin_unlock_bh(old_bucket_lock);
 		}
-	} while (!complete);
+	}
 
 	bucket_table_free(old_tbl);
 	return 0;
@@ -272,38 +392,65 @@ EXPORT_SYMBOL_GPL(rhashtable_expand);
  * This function may only be called in a context where it is safe to call
  * synchronize_rcu(), e.g. not within a rcu_read_lock() section.
  *
+ * The caller must ensure that no concurrent resizing occurs by holding
+ * ht->mutex.
+ *
  * The caller must ensure that no concurrent table mutations take place.
  * It is however valid to have concurrent lookups if they are RCU protected.
+ *
+ * It is valid to have concurrent insertions and deletions protected by per
+ * bucket locks or concurrent RCU protected lookups and traversals.
  */
 int rhashtable_shrink(struct rhashtable *ht)
 {
-	struct bucket_table *ntbl, *tbl = rht_dereference(ht->tbl, ht);
-	unsigned int i;
+	struct bucket_table *new_tbl, *tbl = rht_dereference(ht->tbl, ht);
+	spinlock_t *new_bucket_lock, *old_bucket_lock1, *old_bucket_lock2;
+	unsigned int new_hash;
 
 	ASSERT_RHT_MUTEX(ht);
 
 	if (ht->shift <= ht->p.min_shift)
 		return 0;
 
-	ntbl = bucket_table_alloc(tbl->size / 2);
-	if (ntbl == NULL)
+	new_tbl = bucket_table_alloc(ht, tbl->size / 2);
+	if (new_tbl == NULL)
 		return -ENOMEM;
 
-	ht->shift--;
+	rcu_assign_pointer(ht->future_tbl, new_tbl);
+	synchronize_rcu();
 
-	/* Link each bucket in the new table to the first bucket
-	 * in the old table that contains entries which will hash
-	 * to the new bucket.
+	/* Link the first entry in the old bucket to the end of the
+	 * bucket in the new table. As entries are concurrently being
+	 * added to the new table, lock down the new bucket. As we
+	 * always divide the size in half when shrinking, each bucket
+	 * in the new table maps to exactly two buckets in the old
+	 * table.
+	 *
+	 * As removals can occur concurrently on the old table, we need
+	 * to lock down both matching buckets in the old table.
 	 */
-	for (i = 0; i < ntbl->size; i++) {
-		ntbl->buckets[i] = tbl->buckets[i];
-		RCU_INIT_POINTER(*bucket_tail(ntbl, i),
-				 tbl->buckets[i + ntbl->size]);
-
+	for (new_hash = 0; new_hash < new_tbl->size; new_hash++) {
+		old_bucket_lock1 = bucket_lock(tbl, new_hash);
+		old_bucket_lock2 = bucket_lock(tbl, new_hash + new_tbl->size);
+		new_bucket_lock = bucket_lock(new_tbl, new_hash);
+
+		spin_lock_bh(old_bucket_lock1);
+		spin_lock_bh_nested(old_bucket_lock2, RHT_LOCK_NESTED);
+		spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED2);
+
+		rcu_assign_pointer(*bucket_tail(new_tbl, new_hash),
+				   tbl->buckets[new_hash]);
+		rcu_assign_pointer(*bucket_tail(new_tbl, new_hash),
+				   tbl->buckets[new_hash + new_tbl->size]);
+
+		spin_unlock_bh(new_bucket_lock);
+		spin_unlock_bh(old_bucket_lock2);
+		spin_unlock_bh(old_bucket_lock1);
 	}
 
 	/* Publish the new, valid hash table */
-	rcu_assign_pointer(ht->tbl, ntbl);
+	rcu_assign_pointer(ht->tbl, new_tbl);
+	ht->shift--;
 
 	/* Wait for readers. No new readers will have references to the
 	 * old hash table.
@@ -316,31 +463,63 @@ int rhashtable_shrink(struct rhashtable *ht)
 }
 EXPORT_SYMBOL_GPL(rhashtable_shrink);
 
+static void rht_deferred_worker(struct work_struct *work)
+{
+	struct rhashtable *ht;
+	struct bucket_table *tbl;
+
+	ht = container_of(work, struct rhashtable, run_work.work);
+	mutex_lock(&ht->mutex);
+	tbl = rht_dereference(ht->tbl, ht);
+
+	if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size))
+		rhashtable_expand(ht);
+	else if (ht->p.shrink_decision && ht->p.shrink_decision(ht, tbl->size))
+		rhashtable_shrink(ht);
+
+	mutex_unlock(&ht->mutex);
+}
+
 /**
  * rhashtable_insert - insert object into hash hash table
  * @ht:		hash table
  * @obj:	pointer to hash head inside object
  *
- * Will automatically grow the table via rhashtable_expand() if the the
- * grow_decision function specified at rhashtable_init() returns true.
+ * Will take a per bucket spinlock to protect against mutual mutations
+ * on the same bucket. Multiple insertions may occur in parallel unless
+ * they map to the same bucket lock.
  *
- * The caller must ensure that no concurrent table mutations occur. It is
- * however valid to have concurrent lookups if they are RCU protected.
+ * It is safe to call this function from atomic context.
+ *
+ * Will trigger an automatic deferred table resizing if the size grows
+ * beyond the watermark indicated by grow_decision() which can be passed
+ * to rhashtable_init().
  */
 void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 {
-	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
-	u32 hash;
+	struct bucket_table *tbl;
+	spinlock_t *lock;
+	unsigned hash;
 
-	ASSERT_RHT_MUTEX(ht);
+	rcu_read_lock();
 
+	tbl = rht_dereference_rcu(ht->future_tbl, ht);
 	hash = head_hashfn(ht, tbl, obj);
+	lock = bucket_lock(tbl, hash);
+
+	spin_lock_bh(lock);
 	RCU_INIT_POINTER(obj->next, tbl->buckets[hash]);
 	rcu_assign_pointer(tbl->buckets[hash], obj);
-	ht->nelems++;
+	spin_unlock_bh(lock);
 
-	if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size))
-		rhashtable_expand(ht);
+	atomic_inc(&ht->nelems);
+
+	/* Only grow the table if no resizing is currently in progress. */
+	if (ht->tbl != ht->future_tbl &&
+	    ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size))
+		schedule_delayed_work(&ht->run_work, 0);
+
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(rhashtable_insert);
 
@@ -361,32 +540,56 @@ EXPORT_SYMBOL_GPL(rhashtable_insert);
  */
 bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj)
 {
-	struct bucket_table *tbl = rht_dereference(ht->tbl, ht);
+	struct bucket_table *tbl;
 	struct rhash_head __rcu **pprev;
 	struct rhash_head *he;
-	u32 h;
+	spinlock_t *lock;
+	unsigned int hash;
 
-	ASSERT_RHT_MUTEX(ht);
+	rcu_read_lock();
+	tbl = rht_dereference_rcu(ht->tbl, ht);
+	hash = head_hashfn(ht, tbl, obj);
 
-	h = head_hashfn(ht, tbl, obj);
+	lock = bucket_lock(tbl, hash);
+	spin_lock_bh(lock);
 
-	pprev = &tbl->buckets[h];
-	rht_for_each(he, tbl, h) {
+restart:
+	pprev = &tbl->buckets[hash];
+	rht_for_each(he, tbl, hash) {
 		if (he != obj) {
 			pprev = &he->next;
 			continue;
 		}
 
-		RCU_INIT_POINTER(*pprev, he->next);
-		ht->nelems--;
+		rcu_assign_pointer(*pprev, obj->next);
+		atomic_dec(&ht->nelems);
 
-		if (ht->p.shrink_decision &&
+		spin_unlock_bh(lock);
+
+		if (ht->tbl != ht->future_tbl &&
+		    ht->p.shrink_decision &&
 		    ht->p.shrink_decision(ht, tbl->size))
-			rhashtable_shrink(ht);
+			schedule_delayed_work(&ht->run_work, 0);
+
+		rcu_read_unlock();
 
 		return true;
 	}
 
+	if (tbl != rht_dereference_rcu(ht->tbl, ht)) {
+		spin_unlock_bh(lock);
+
+		tbl = rht_dereference_rcu(ht->tbl, ht);
+		hash = head_hashfn(ht, tbl, obj);
+
+		lock = bucket_lock(tbl, hash);
+		spin_lock_bh(lock);
+		goto restart;
+	}
+
+	spin_unlock_bh(lock);
+	rcu_read_unlock();
+
 	return false;
 }
 EXPORT_SYMBOL_GPL(rhashtable_remove);
@@ -402,25 +605,35 @@ EXPORT_SYMBOL_GPL(rhashtable_remove);
  * This lookup function may only be used for fixed key hash table (key_len
  * paramter set). It will BUG() if used inappropriately.
  *
- * Lookups may occur in parallel with hash mutations as long as the lookup is
- * guarded by rcu_read_lock(). The caller must take care of this.
+ * Lookups may occur in parallel with hashtable mutations and resizing.
  */
-void *rhashtable_lookup(const struct rhashtable *ht, const void *key)
+void *rhashtable_lookup(struct rhashtable *ht, const void *key)
 {
-	const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
+	const struct bucket_table *tbl, *old_tbl;
 	struct rhash_head *he;
-	u32 h;
+	u32 hash;
 
 	BUG_ON(!ht->p.key_len);
 
-	h = key_hashfn(ht, key, ht->p.key_len);
-	rht_for_each_rcu(he, tbl, h) {
+	rcu_read_lock();
+	old_tbl = rht_dereference_rcu(ht->tbl, ht);
+	tbl = rht_dereference_rcu(ht->future_tbl, ht);
+	hash = key_hashfn(ht, key, ht->p.key_len);
+restart:
+	rht_for_each_rcu(he, tbl, rht_bucket_index(tbl, hash)) {
 		if (memcmp(rht_obj(ht, he) + ht->p.key_offset, key,
 			   ht->p.key_len))
 			continue;
+		rcu_read_unlock();
 		return rht_obj(ht, he);
 	}
 
+	if (unlikely(tbl != old_tbl)) {
+		tbl = old_tbl;
+		goto restart;
+	}
+
+	rcu_read_unlock();
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(rhashtable_lookup);
@@ -435,25 +648,36 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup);
  * Traverses the bucket chain behind the provided hash value and calls the
  * specified compare function for each entry.
  *
- * Lookups may occur in parallel with hash mutations as long as the lookup is
- * guarded by rcu_read_lock(). The caller must take care of this.
+ * Lookups may occur in parallel with hashtable mutations and resizing.
  *
  * Returns the first entry on which the compare function returned true.
  */
-void *rhashtable_lookup_compare(const struct rhashtable *ht, const void *key,
+void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key,
 				bool (*compare)(void *, void *), void *arg)
 {
-	const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht);
+	const struct bucket_table *tbl, *old_tbl;
 	struct rhash_head *he;
 	u32 hash;
 
+	rcu_read_lock();
+
+	old_tbl = rht_dereference_rcu(ht->tbl, ht);
+	tbl = rht_dereference_rcu(ht->future_tbl, ht);
 	hash = key_hashfn(ht, key, ht->p.key_len);
-	rht_for_each_rcu(he, tbl, hash) {
+restart:
+	rht_for_each_rcu(he, tbl, rht_bucket_index(tbl, hash)) {
 		if (!compare(rht_obj(ht, he), arg))
 			continue;
+		rcu_read_unlock();
 		return rht_obj(ht, he);
 	}
 
+	if (unlikely(tbl != old_tbl)) {
+		tbl = old_tbl;
+		goto restart;
+	}
+	rcu_read_unlock();
+
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(rhashtable_lookup_compare);
@@ -485,9 +709,6 @@ static size_t rounded_hashtable_size(struct rhashtable_params *params)
  *	.key_offset = offsetof(struct test_obj, key),
  *	.key_len = sizeof(int),
  *	.hashfn = jhash,
- * #ifdef CONFIG_PROVE_LOCKING
- *	.mutex_is_held = &my_mutex_is_held,
- * #endif
  * };
  *
  * Configuration Example 2: Variable length keys
@@ -507,9 +728,6 @@ static size_t rounded_hashtable_size(struct rhashtable_params *params)
  *	.head_offset = offsetof(struct test_obj, node),
  *	.hashfn = jhash,
  *	.obj_hashfn = my_hash_fn,
- * #ifdef CONFIG_PROVE_LOCKING
- *	.mutex_is_held = &my_mutex_is_held,
- * #endif
  * };
  */
 int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
@@ -529,18 +747,29 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
 	if (params->nelem_hint)
 		size = rounded_hashtable_size(params);
 
-	tbl = bucket_table_alloc(size);
+	memset(ht, 0, sizeof(*ht));
+	mutex_init(&ht->mutex);
+	memcpy(&ht->p, params, sizeof(*params));
+
+	if (params->locks_mul)
+		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
+	else
+		ht->p.locks_mul = BUCKET_LOCKS_PER_CPU;
+
+	tbl = bucket_table_alloc(ht, size);
 	if (tbl == NULL)
 		return -ENOMEM;
 
-	memset(ht, 0, sizeof(*ht));
 	ht->shift = ilog2(tbl->size);
-	memcpy(&ht->p, params, sizeof(*params));
 	RCU_INIT_POINTER(ht->tbl, tbl);
+	RCU_INIT_POINTER(ht->future_tbl, tbl);
 
 	if (!ht->p.hash_rnd)
 		get_random_bytes(&ht->p.hash_rnd, sizeof(ht->p.hash_rnd));
 
+	if (ht->p.grow_decision || ht->p.shrink_decision)
+		INIT_DEFERRABLE_WORK(&ht->run_work, rht_deferred_worker);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(rhashtable_init);
@@ -553,9 +782,16 @@ EXPORT_SYMBOL_GPL(rhashtable_init);
  * has to make sure that no resizing may happen by unpublishing the hashtable
  * and waiting for the quiescent cycle before releasing the bucket array.
  */
-void rhashtable_destroy(const struct rhashtable *ht)
+void rhashtable_destroy(struct rhashtable *ht)
 {
-	bucket_table_free(ht->tbl);
+	ht->being_destroyed = true;
+
+	mutex_lock(&ht->mutex);
+
+	cancel_delayed_work(&ht->run_work);
+	bucket_table_free(rht_dereference(ht->tbl, ht));
+
+	mutex_unlock(&ht->mutex);
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
 
@@ -570,13 +806,6 @@ EXPORT_SYMBOL_GPL(rhashtable_destroy);
 #define TEST_PTR	((void *) 0xdeadbeef)
 #define TEST_NEXPANDS	4
 
-#ifdef CONFIG_PROVE_LOCKING
-static int test_mutex_is_held(void *parent)
-{
-	return 1;
-}
-#endif
-
 struct test_obj {
 	void			*ptr;
 	int			value;
@@ -646,10 +875,10 @@ static void test_bucket_stats(struct rhashtable *ht, bool quiet)
 				i, tbl->buckets[i], cnt);
 	}
 
-	pr_info("  Traversal complete: counted=%u, nelems=%zu, entries=%d\n",
-		total, ht->nelems, TEST_ENTRIES);
+	pr_info("  Traversal complete: counted=%u, nelems=%u, entries=%d\n",
+		total, atomic_read(&ht->nelems), TEST_ENTRIES);
 
-	if (total != ht->nelems || total != TEST_ENTRIES)
+	if (total != atomic_read(&ht->nelems) || total != TEST_ENTRIES)
 		pr_warn("Test failed: Total count mismatch ^^^");
 }
 
@@ -688,7 +917,9 @@ static int __init test_rhashtable(struct rhashtable *ht)
 
 	for (i = 0; i < TEST_NEXPANDS; i++) {
 		pr_info("  Table expansion iteration %u...\n", i);
+		mutex_lock(&ht->mutex);
 		rhashtable_expand(ht);
+		mutex_unlock(&ht->mutex);
 
 		rcu_read_lock();
 		pr_info("  Verifying lookups...\n");
@@ -698,7 +929,9 @@ static int __init test_rhashtable(struct rhashtable *ht)
 
 	for (i = 0; i < TEST_NEXPANDS; i++) {
 		pr_info("  Table shrinkage iteration %u...\n", i);
+		mutex_lock(&ht->mutex);
 		rhashtable_shrink(ht);
+		mutex_unlock(&ht->mutex);
 
 		rcu_read_lock();
 		pr_info("  Verifying lookups...\n");
@@ -741,9 +974,6 @@ static int __init test_rht_init(void)
 		.key_offset = offsetof(struct test_obj, value),
 		.key_len = sizeof(int),
 		.hashfn = jhash,
-#ifdef CONFIG_PROVE_LOCKING
-		.mutex_is_held = &test_mutex_is_held,
-#endif
 		.grow_decision = rht_grow_above_75,
 		.shrink_decision = rht_shrink_below_30,
 	};
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 7f903cf9a1b..75887d7d2c6 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -33,7 +33,7 @@ static bool nft_hash_lookup(const struct nft_set *set,
 			    const struct nft_data *key,
 			    struct nft_data *data)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
+	struct rhashtable *priv = nft_set_priv(set);
 	const struct nft_hash_elem *he;
 
 	he = rhashtable_lookup(priv, key);
@@ -113,7 +113,7 @@ static bool nft_hash_compare(void *ptr, void *arg)
 
 static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
+	struct rhashtable *priv = nft_set_priv(set);
 	struct nft_compare_arg arg = {
 		.set = set,
 		.elem = elem,
@@ -129,7 +129,7 @@ static int nft_hash_get(const struct nft_set *set, struct nft_set_elem *elem)
 static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
 			  struct nft_set_iter *iter)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
+	struct rhashtable *priv = nft_set_priv(set);
 	const struct bucket_table *tbl;
 	const struct nft_hash_elem *he;
 	struct nft_set_elem elem;
@@ -162,13 +162,6 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 	return sizeof(struct rhashtable);
 }
 
-#ifdef CONFIG_PROVE_LOCKING
-static int lockdep_nfnl_lock_is_held(void *parent)
-{
-	return lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES);
-}
-#endif
-
 static int nft_hash_init(const struct nft_set *set,
 			 const struct nft_set_desc *desc,
 			 const struct nlattr * const tb[])
@@ -182,9 +175,6 @@ static int nft_hash_init(const struct nft_set *set,
 		.hashfn = jhash,
 		.grow_decision = rht_grow_above_75,
 		.shrink_decision = rht_shrink_below_30,
-#ifdef CONFIG_PROVE_LOCKING
-		.mutex_is_held = lockdep_nfnl_lock_is_held,
-#endif
 	};
 
 	return rhashtable_init(priv, &params);
@@ -192,16 +182,23 @@ static int nft_hash_init(const struct nft_set *set,
 
 static void nft_hash_destroy(const struct nft_set *set)
 {
-	const struct rhashtable *priv = nft_set_priv(set);
-	const struct bucket_table *tbl = priv->tbl;
+	struct rhashtable *priv = nft_set_priv(set);
+	const struct bucket_table *tbl;
 	struct nft_hash_elem *he;
 	struct rhash_head *pos, *next;
 	unsigned int i;
 
+	/* Stop an eventual async resizing */
+	priv->being_destroyed = true;
+	mutex_lock(&priv->mutex);
+
+	tbl = rht_dereference(priv->tbl, priv);
 	for (i = 0; i < tbl->size; i++) {
 		rht_for_each_entry_safe(he, pos, next, tbl, i, node)
 			nft_hash_elem_destroy(set, he);
 	}
+	mutex_unlock(&priv->mutex);
+
 	rhashtable_destroy(priv);
 }
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 57449b6089c..738c3bfaa56 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -114,15 +114,6 @@ static atomic_t nl_table_users = ATOMIC_INIT(0);
 DEFINE_MUTEX(nl_sk_hash_lock);
 EXPORT_SYMBOL_GPL(nl_sk_hash_lock);
 
-#ifdef CONFIG_PROVE_LOCKING
-static int lockdep_nl_sk_hash_is_held(void *parent)
-{
-	if (debug_locks)
-		return lockdep_is_held(&nl_sk_hash_lock) || lockdep_is_held(&nl_table_lock);
-	return 1;
-}
-#endif
-
 static ATOMIC_NOTIFIER_HEAD(netlink_chain);
 
 static DEFINE_SPINLOCK(netlink_tap_lock);
@@ -1063,7 +1054,8 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 portid)
 		goto err;
 
 	err = -ENOMEM;
-	if (BITS_PER_LONG > 32 && unlikely(table->hash.nelems >= UINT_MAX))
+	if (BITS_PER_LONG > 32 &&
+	    unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX))
 		goto err;
 
 	nlk_sk(sk)->portid = portid;
@@ -3122,9 +3114,6 @@ static int __init netlink_proto_init(void)
 		.max_shift = 16, /* 64K */
 		.grow_decision = rht_grow_above_75,
 		.shrink_decision = rht_shrink_below_30,
-#ifdef CONFIG_PROVE_LOCKING
-		.mutex_is_held = lockdep_nl_sk_hash_is_held,
-#endif
 	};
 
 	if (err != 0)
-- 
cgit v1.2.3-70-g09d2


From f89bd6f87a53ce5a7d60662429591ebac2745c10 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Fri, 2 Jan 2015 23:00:21 +0100
Subject: rhashtable: Supports for nulls marker

In order to allow for wider usage of rhashtable, use a special nulls
marker to terminate each chain. The reason for not using the existing
nulls_list is that the prev pointer usage would not be valid as entries
can be linked in two different buckets at the same time.

The 4 nulls base bits can be set through the rhashtable_params structure
like this:

struct rhashtable_params params = {
        [...]
        .nulls_base = (1U << RHT_BASE_SHIFT),
};

This reduces the hash length from 32 bits to 27 bits.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/list_nulls.h |  3 ++-
 include/linux/rhashtable.h | 57 ++++++++++++++++++++++++++++++++++++++--------
 lib/rhashtable.c           | 37 ++++++++++++++++++++++++------
 3 files changed, 79 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index 5d10ae364b5..e8c300e0643 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -21,8 +21,9 @@ struct hlist_nulls_head {
 struct hlist_nulls_node {
 	struct hlist_nulls_node *next, **pprev;
 };
+#define NULLS_MARKER(value) (1UL | (((long)value) << 1))
 #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \
-	((ptr)->first = (struct hlist_nulls_node *) (1UL | (((long)nulls) << 1)))
+	((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls))
 
 #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member)
 /**
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index a1688f0a619..de7cac753b0 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -18,15 +18,32 @@
 #ifndef _LINUX_RHASHTABLE_H
 #define _LINUX_RHASHTABLE_H
 
-#include <linux/rculist.h>
+#include <linux/list_nulls.h>
 #include <linux/workqueue.h>
 
+/*
+ * The end of the chain is marked with a special nulls marks which has
+ * the following format:
+ *
+ * +-------+-----------------------------------------------------+-+
+ * | Base  |                      Hash                           |1|
+ * +-------+-----------------------------------------------------+-+
+ *
+ * Base (4 bits) : Reserved to distinguish between multiple tables.
+ *                 Specified via &struct rhashtable_params.nulls_base.
+ * Hash (27 bits): Full hash (unmasked) of first element added to bucket
+ * 1 (1 bit)     : Nulls marker (always set)
+ *
+ * The remaining bits of the next pointer remain unused for now.
+ */
+#define RHT_BASE_BITS		4
+#define RHT_HASH_BITS		27
+#define RHT_BASE_SHIFT		RHT_HASH_BITS
+
 struct rhash_head {
 	struct rhash_head __rcu		*next;
 };
 
-#define INIT_HASH_HEAD(ptr) ((ptr)->next = NULL)
-
 /**
  * struct bucket_table - Table of hash buckets
  * @size: Number of hash buckets
@@ -55,6 +72,7 @@ struct rhashtable;
  * @hash_rnd: Seed to use while hashing
  * @max_shift: Maximum number of shifts while expanding
  * @min_shift: Minimum number of shifts while shrinking
+ * @nulls_base: Base value to generate nulls marker
  * @locks_mul: Number of bucket locks to allocate per cpu (default: 128)
  * @hashfn: Function to hash key
  * @obj_hashfn: Function to hash object
@@ -69,6 +87,7 @@ struct rhashtable_params {
 	u32			hash_rnd;
 	size_t			max_shift;
 	size_t			min_shift;
+	u32			nulls_base;
 	size_t			locks_mul;
 	rht_hashfn_t		hashfn;
 	rht_obj_hashfn_t	obj_hashfn;
@@ -100,6 +119,24 @@ struct rhashtable {
 	bool                            being_destroyed;
 };
 
+static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash)
+{
+	return NULLS_MARKER(ht->p.nulls_base + hash);
+}
+
+#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \
+	((ptr) = (typeof(ptr)) rht_marker(ht, hash))
+
+static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
+{
+	return ((unsigned long) ptr & 1);
+}
+
+static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr)
+{
+	return ((unsigned long) ptr) >> 1;
+}
+
 #ifdef CONFIG_PROVE_LOCKING
 int lockdep_rht_mutex_is_held(struct rhashtable *ht);
 int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash);
@@ -157,7 +194,7 @@ void rhashtable_destroy(struct rhashtable *ht);
  */
 #define rht_for_each_continue(pos, head, tbl, hash) \
 	for (pos = rht_dereference_bucket(head, tbl, hash); \
-	     pos; \
+	     !rht_is_a_nulls(pos); \
 	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
 
 /**
@@ -180,7 +217,7 @@ void rhashtable_destroy(struct rhashtable *ht);
  */
 #define rht_for_each_entry_continue(tpos, pos, head, tbl, hash, member)	\
 	for (pos = rht_dereference_bucket(head, tbl, hash);		\
-	     pos && rht_entry(tpos, pos, member);			\
+	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	\
 	     pos = rht_dereference_bucket((pos)->next, tbl, hash))
 
 /**
@@ -209,9 +246,9 @@ void rhashtable_destroy(struct rhashtable *ht);
  */
 #define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member)	    \
 	for (pos = rht_dereference_bucket((tbl)->buckets[hash], tbl, hash), \
-	     next = pos ? rht_dereference_bucket(pos->next, tbl, hash)      \
-			: NULL;						    \
-	     pos && rht_entry(tpos, pos, member);			    \
+	     next = !rht_is_a_nulls(pos) ?				    \
+		       rht_dereference_bucket(pos->next, tbl, hash) : NULL; \
+	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	    \
 	     pos = next)
 
 /**
@@ -228,7 +265,7 @@ void rhashtable_destroy(struct rhashtable *ht);
 #define rht_for_each_rcu_continue(pos, head, tbl, hash)			\
 	for (({barrier(); }),						\
 	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		\
-	     pos;							\
+	     !rht_is_a_nulls(pos);					\
 	     pos = rcu_dereference_raw(pos->next))
 
 /**
@@ -260,7 +297,7 @@ void rhashtable_destroy(struct rhashtable *ht);
 #define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \
 	for (({barrier(); }),						    \
 	     pos = rht_dereference_bucket_rcu(head, tbl, hash);		    \
-	     pos && rht_entry(tpos, pos, member);			    \
+	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	    \
 	     pos = rht_dereference_bucket_rcu(pos->next, tbl, hash))
 
 /**
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 312e3437c7b..cbad192d3b3 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -28,6 +28,9 @@
 #define HASH_MIN_SIZE		4UL
 #define BUCKET_LOCKS_PER_CPU   128UL
 
+/* Base bits plus 1 bit for nulls marker */
+#define HASH_RESERVED_SPACE	(RHT_BASE_BITS + 1)
+
 enum {
 	RHT_LOCK_NORMAL,
 	RHT_LOCK_NESTED,
@@ -86,7 +89,7 @@ static u32 obj_raw_hashfn(const struct rhashtable *ht, const void *ptr)
 		hash = ht->p.hashfn(ptr + ht->p.key_offset, ht->p.key_len,
 				    ht->p.hash_rnd);
 
-	return hash;
+	return hash >> HASH_RESERVED_SPACE;
 }
 
 static u32 key_hashfn(struct rhashtable *ht, const void *key, u32 len)
@@ -95,6 +98,7 @@ static u32 key_hashfn(struct rhashtable *ht, const void *key, u32 len)
 	u32 hash;
 
 	hash = ht->p.hashfn(key, len, ht->p.hash_rnd);
+	hash >>= HASH_RESERVED_SPACE;
 
 	return rht_bucket_index(tbl, hash);
 }
@@ -111,7 +115,7 @@ static struct rhash_head __rcu **bucket_tail(struct bucket_table *tbl, u32 n)
 	struct rhash_head __rcu **pprev;
 
 	for (pprev = &tbl->buckets[n];
-	     rht_dereference_bucket(*pprev, tbl, n);
+	     !rht_is_a_nulls(rht_dereference_bucket(*pprev, tbl, n));
 	     pprev = &rht_dereference_bucket(*pprev, tbl, n)->next)
 		;
 
@@ -164,6 +168,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 {
 	struct bucket_table *tbl;
 	size_t size;
+	int i;
 
 	size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]);
 	tbl = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
@@ -180,6 +185,9 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 		return NULL;
 	}
 
+	for (i = 0; i < nbuckets; i++)
+		INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i);
+
 	return tbl;
 }
 
@@ -221,7 +229,7 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 	/* Old bucket empty, no work needed. */
 	p = rht_dereference_bucket(old_tbl->buckets[old_hash], old_tbl,
 				   old_hash);
-	if (!p)
+	if (rht_is_a_nulls(p))
 		return;
 
 	new_hash = new_hash2 = head_hashfn(ht, new_tbl, p);
@@ -252,8 +260,8 @@ static void hashtable_chain_unzip(const struct rhashtable *ht,
 	/* Find the subsequent node which does hash to the same
 	 * bucket as node P, or NULL if no such node exists.
 	 */
-	next = NULL;
-	if (he) {
+	INIT_RHT_NULLS_HEAD(next, ht, old_hash);
+	if (!rht_is_a_nulls(he)) {
 		rht_for_each_continue(he, he->next, old_tbl, old_hash) {
 			if (head_hashfn(ht, new_tbl, he) == new_hash) {
 				next = he;
@@ -369,11 +377,15 @@ int rhashtable_expand(struct rhashtable *ht)
 		 */
 		complete = true;
 		for (old_hash = 0; old_hash < old_tbl->size; old_hash++) {
+			struct rhash_head *head;
+
 			old_bucket_lock = bucket_lock(old_tbl, old_hash);
 			spin_lock_bh(old_bucket_lock);
 
 			hashtable_chain_unzip(ht, new_tbl, old_tbl, old_hash);
-			if (old_tbl->buckets[old_hash] != NULL)
+			head = rht_dereference_bucket(old_tbl->buckets[old_hash],
+						      old_tbl, old_hash);
+			if (!rht_is_a_nulls(head))
 				complete = false;
 
 			spin_unlock_bh(old_bucket_lock);
@@ -498,6 +510,7 @@ static void rht_deferred_worker(struct work_struct *work)
 void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 {
 	struct bucket_table *tbl;
+	struct rhash_head *head;
 	spinlock_t *lock;
 	unsigned hash;
 
@@ -508,7 +521,12 @@ void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 	lock = bucket_lock(tbl, hash);
 
 	spin_lock_bh(lock);
-	RCU_INIT_POINTER(obj->next, tbl->buckets[hash]);
+	head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
+	if (rht_is_a_nulls(head))
+		INIT_RHT_NULLS_HEAD(obj->next, ht, hash);
+	else
+		RCU_INIT_POINTER(obj->next, head);
+
 	rcu_assign_pointer(tbl->buckets[hash], obj);
 	spin_unlock_bh(lock);
 
@@ -709,6 +727,7 @@ static size_t rounded_hashtable_size(struct rhashtable_params *params)
  *	.key_offset = offsetof(struct test_obj, key),
  *	.key_len = sizeof(int),
  *	.hashfn = jhash,
+ *	.nulls_base = (1U << RHT_BASE_SHIFT),
  * };
  *
  * Configuration Example 2: Variable length keys
@@ -741,6 +760,9 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
 	    (!params->key_len && !params->obj_hashfn))
 		return -EINVAL;
 
+	if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT))
+		return -EINVAL;
+
 	params->min_shift = max_t(size_t, params->min_shift,
 				  ilog2(HASH_MIN_SIZE));
 
@@ -974,6 +996,7 @@ static int __init test_rht_init(void)
 		.key_offset = offsetof(struct test_obj, value),
 		.key_len = sizeof(int),
 		.hashfn = jhash,
+		.nulls_base = (3U << RHT_BASE_SHIFT),
 		.grow_decision = rht_grow_above_75,
 		.shrink_decision = rht_shrink_below_30,
 	};
-- 
cgit v1.2.3-70-g09d2


From adc2ae0bb6daa2287d1a6567d18be01da546f7a7 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sat, 3 Jan 2015 17:56:14 +0100
Subject: ALSA: pcm: Remove unused functions declaration

Remove function declarations for functions that don't have a matching
implementation.

For snd_pcm_build_linear_format the implementation was removed in
64d27f96cb719cf8 ("[ALSA] Support 3-bytes 24bit format in PCM OSS
emulation"). All the others never had one (as far as git history goes).

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index bf32cea2202..cd09c1b05c2 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -518,7 +518,6 @@ void snd_pcm_release_substream(struct snd_pcm_substream *substream);
 int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream, struct file *file,
 			     struct snd_pcm_substream **rsubstream);
 void snd_pcm_detach_substream(struct snd_pcm_substream *substream);
-void snd_pcm_vma_notify_data(void *client, void *data);
 int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area);
 
 
@@ -984,21 +983,15 @@ int snd_pcm_format_physical_width(snd_pcm_format_t format);		/* in bits */
 ssize_t snd_pcm_format_size(snd_pcm_format_t format, size_t samples);
 const unsigned char *snd_pcm_format_silence_64(snd_pcm_format_t format);
 int snd_pcm_format_set_silence(snd_pcm_format_t format, void *buf, unsigned int frames);
-snd_pcm_format_t snd_pcm_build_linear_format(int width, int unsigned, int big_endian);
 
 void snd_pcm_set_ops(struct snd_pcm * pcm, int direction,
 		     const struct snd_pcm_ops *ops);
 void snd_pcm_set_sync(struct snd_pcm_substream *substream);
-int snd_pcm_lib_interleave_len(struct snd_pcm_substream *substream);
 int snd_pcm_lib_ioctl(struct snd_pcm_substream *substream,
 		      unsigned int cmd, void *arg);                      
 int snd_pcm_update_state(struct snd_pcm_substream *substream,
 			 struct snd_pcm_runtime *runtime);
 int snd_pcm_update_hw_ptr(struct snd_pcm_substream *substream);
-int snd_pcm_playback_xrun_check(struct snd_pcm_substream *substream);
-int snd_pcm_capture_xrun_check(struct snd_pcm_substream *substream);
-int snd_pcm_playback_xrun_asap(struct snd_pcm_substream *substream);
-int snd_pcm_capture_xrun_asap(struct snd_pcm_substream *substream);
 void snd_pcm_playback_silence(struct snd_pcm_substream *substream, snd_pcm_uframes_t new_hw_ptr);
 void snd_pcm_period_elapsed(struct snd_pcm_substream *substream);
 snd_pcm_sframes_t snd_pcm_lib_write(struct snd_pcm_substream *substream,
-- 
cgit v1.2.3-70-g09d2


From 043ec9bf7b9d7cdce84d2e8d3df9b9eb520d929e Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 2 Jan 2015 23:35:19 -0800
Subject: Bluetooth: Introduce HCI_QUIRK_FIXUP_INQUIRY_MODE option

The HCI_QUIRK_FIXUP_INQUIRY_MODE option allows to force Inquiry Result
with RSSI setting on controllers that do not indicate support for it,
but where it is known to be fully functional.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 12 ++++++++++++
 net/bluetooth/hci_core.c    |  3 ++-
 2 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index aee16bf5d34..d0bca316b43 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -102,6 +102,18 @@ enum {
 	 */
 	HCI_QUIRK_FIXUP_BUFFER_SIZE,
 
+	/* When this quirk is set, then a controller that does not
+	 * indicate support for Inquiry Result with RSSI is assumed to
+	 * support it anyway. Some early Bluetooth 1.2 controllers had
+	 * wrongly configured local features that will require forcing
+	 * them to enable this mode. Getting RSSI information with the
+	 * inquiry responses is preferred since it allows for a better
+	 * user expierence.
+	 *
+	 * This quirk must be set before hci_register_dev is called.
+	 */
+	HCI_QUIRK_FIXUP_INQUIRY_MODE,
+
 	/* When this quirk is set, then the HCI Read Local Supported
 	 * Commands command is not supported. In general Bluetooth 1.2
 	 * and later controllers should support this command. However
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ebac859e125..bc5486ea541 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -621,7 +621,8 @@ static void hci_init2_req(struct hci_request *req, unsigned long opt)
 		}
 	}
 
-	if (lmp_inq_rssi_capable(hdev)) {
+	if (lmp_inq_rssi_capable(hdev) ||
+	    test_bit(HCI_QUIRK_FIXUP_INQUIRY_MODE, &hdev->quirks)) {
 		u8 mode;
 
 		/* If Extended Inquiry Result events are supported, then
-- 
cgit v1.2.3-70-g09d2


From 61f3cade763dca46127146a52d829e30b8f48921 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Fri, 2 Jan 2015 18:26:02 -0800
Subject: geneve: Remove workqueue.

The work queue is used only to free the UDP socket upon destruction.
This is not necessary with Geneve and generally makes the code more
difficult to reason about. It also introduces nondeterministic
behavior such as when a socket is rapidly deleted and recreated, which
could fail as the the deletion happens asynchronously.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/geneve.h |  1 -
 net/ipv4/geneve.c    | 21 ++-------------------
 2 files changed, 2 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/geneve.h b/include/net/geneve.h
index 112132cf8e2..56c7e1ac216 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -71,7 +71,6 @@ struct geneve_sock {
 	struct hlist_node	hlist;
 	geneve_rcv_t		*rcv;
 	void			*rcv_data;
-	struct work_struct	del_work;
 	struct socket		*sock;
 	struct rcu_head		rcu;
 	atomic_t		refcnt;
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 19e256e1dd9..136a829e874 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -61,8 +61,6 @@ struct geneve_net {
 
 static int geneve_net_id;
 
-static struct workqueue_struct *geneve_wq;
-
 static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
 {
 	return (struct genevehdr *)(udp_hdr(skb) + 1);
@@ -307,15 +305,6 @@ error:
 	return 1;
 }
 
-static void geneve_del_work(struct work_struct *work)
-{
-	struct geneve_sock *gs = container_of(work, struct geneve_sock,
-					      del_work);
-
-	udp_tunnel_sock_release(gs->sock);
-	kfree_rcu(gs, rcu);
-}
-
 static struct socket *geneve_create_sock(struct net *net, bool ipv6,
 					 __be16 port)
 {
@@ -356,8 +345,6 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	if (!gs)
 		return ERR_PTR(-ENOMEM);
 
-	INIT_WORK(&gs->del_work, geneve_del_work);
-
 	sock = geneve_create_sock(net, ipv6, port);
 	if (IS_ERR(sock)) {
 		kfree(gs);
@@ -430,7 +417,8 @@ void geneve_sock_release(struct geneve_sock *gs)
 	geneve_notify_del_rx_port(gs);
 	spin_unlock(&gn->sock_lock);
 
-	queue_work(geneve_wq, &gs->del_work);
+	udp_tunnel_sock_release(gs->sock);
+	kfree_rcu(gs, rcu);
 }
 EXPORT_SYMBOL_GPL(geneve_sock_release);
 
@@ -458,10 +446,6 @@ static int __init geneve_init_module(void)
 {
 	int rc;
 
-	geneve_wq = alloc_workqueue("geneve", 0, 0);
-	if (!geneve_wq)
-		return -ENOMEM;
-
 	rc = register_pernet_subsys(&geneve_net_ops);
 	if (rc)
 		return rc;
@@ -474,7 +458,6 @@ late_initcall(geneve_init_module);
 
 static void __exit geneve_cleanup_module(void)
 {
-	destroy_workqueue(geneve_wq);
 	unregister_pernet_subsys(&geneve_net_ops);
 }
 module_exit(geneve_cleanup_module);
-- 
cgit v1.2.3-70-g09d2


From 829a3ada9cc7d4c30fa61f8033403fb6c8f8092a Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Fri, 2 Jan 2015 18:26:03 -0800
Subject: geneve: Simplify locking.

The existing Geneve locking scheme was pulled over directly from
VXLAN. However, VXLAN has a number of built in mechanisms which make
the locking more complex and are unlikely to be necessary with Geneve.
This simplifies the locking to use a basic scheme of a mutex
when doing updates plus RCU on receive.

In addition to making the code easier to read, this also avoids the
possibility of a race when creating or destroying sockets since
UDP sockets and the list of Geneve sockets are protected by different
locks. After this change, the entire operation is atomic.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/geneve.h |  2 +-
 net/ipv4/geneve.c    | 59 +++++++++++++++++++++++-----------------------------
 2 files changed, 27 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/net/geneve.h b/include/net/geneve.h
index 56c7e1ac216..b40f4affc4c 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -73,7 +73,7 @@ struct geneve_sock {
 	void			*rcv_data;
 	struct socket		*sock;
 	struct rcu_head		rcu;
-	atomic_t		refcnt;
+	int			refcnt;
 	struct udp_offload	udp_offloads;
 };
 
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 136a829e874..ad8dbae11d0 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -17,7 +17,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/skbuff.h>
-#include <linux/rculist.h>
+#include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/in.h>
 #include <linux/ip.h>
@@ -28,6 +28,7 @@
 #include <linux/if_vlan.h>
 #include <linux/hash.h>
 #include <linux/ethtool.h>
+#include <linux/mutex.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
 #include <net/ip.h>
@@ -50,13 +51,15 @@
 #include <net/ip6_checksum.h>
 #endif
 
+/* Protects sock_list and refcounts. */
+static DEFINE_MUTEX(geneve_mutex);
+
 #define PORT_HASH_BITS 8
 #define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
 
 /* per-network namespace private data for this module */
 struct geneve_net {
 	struct hlist_head	sock_list[PORT_HASH_SIZE];
-	spinlock_t		sock_lock;   /* Protects sock_list */
 };
 
 static int geneve_net_id;
@@ -78,7 +81,7 @@ static struct geneve_sock *geneve_find_sock(struct net *net, __be16 port)
 {
 	struct geneve_sock *gs;
 
-	hlist_for_each_entry_rcu(gs, gs_head(net, port), hlist) {
+	hlist_for_each_entry(gs, gs_head(net, port), hlist) {
 		if (inet_sk(gs->sock->sk)->inet_sport == port)
 			return gs;
 	}
@@ -336,7 +339,6 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 						geneve_rcv_t *rcv, void *data,
 						bool ipv6)
 {
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
 	struct socket *sock;
 	struct udp_tunnel_sock_cfg tunnel_cfg;
@@ -352,7 +354,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	}
 
 	gs->sock = sock;
-	atomic_set(&gs->refcnt, 1);
+	gs->refcnt = 1;
 	gs->rcv = rcv;
 	gs->rcv_data = data;
 
@@ -360,11 +362,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	gs->udp_offloads.port = port;
 	gs->udp_offloads.callbacks.gro_receive  = geneve_gro_receive;
 	gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete;
-
-	spin_lock(&gn->sock_lock);
-	hlist_add_head_rcu(&gs->hlist, gs_head(net, port));
 	geneve_notify_add_rx_port(gs);
-	spin_unlock(&gn->sock_lock);
 
 	/* Mark socket as an encapsulation socket */
 	tunnel_cfg.sk_user_data = gs;
@@ -373,6 +371,8 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	tunnel_cfg.encap_destroy = NULL;
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 
+	hlist_add_head(&gs->hlist, gs_head(net, port));
+
 	return gs;
 }
 
@@ -380,25 +380,21 @@ struct geneve_sock *geneve_sock_add(struct net *net, __be16 port,
 				    geneve_rcv_t *rcv, void *data,
 				    bool no_share, bool ipv6)
 {
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
 
-	gs = geneve_socket_create(net, port, rcv, data, ipv6);
-	if (!IS_ERR(gs))
-		return gs;
-
-	if (no_share)	/* Return error if sharing is not allowed. */
-		return ERR_PTR(-EINVAL);
+	mutex_lock(&geneve_mutex);
 
-	spin_lock(&gn->sock_lock);
 	gs = geneve_find_sock(net, port);
-	if (gs && ((gs->rcv != rcv) ||
-		   !atomic_add_unless(&gs->refcnt, 1, 0)))
+	if (gs) {
+		if (!no_share && gs->rcv == rcv)
+			gs->refcnt++;
+		else
 			gs = ERR_PTR(-EBUSY);
-	spin_unlock(&gn->sock_lock);
+	} else {
+		gs = geneve_socket_create(net, port, rcv, data, ipv6);
+	}
 
-	if (!gs)
-		gs = ERR_PTR(-EINVAL);
+	mutex_unlock(&geneve_mutex);
 
 	return gs;
 }
@@ -406,19 +402,18 @@ EXPORT_SYMBOL_GPL(geneve_sock_add);
 
 void geneve_sock_release(struct geneve_sock *gs)
 {
-	struct net *net = sock_net(gs->sock->sk);
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
+	mutex_lock(&geneve_mutex);
 
-	if (!atomic_dec_and_test(&gs->refcnt))
-		return;
+	if (--gs->refcnt)
+		goto unlock;
 
-	spin_lock(&gn->sock_lock);
-	hlist_del_rcu(&gs->hlist);
+	hlist_del(&gs->hlist);
 	geneve_notify_del_rx_port(gs);
-	spin_unlock(&gn->sock_lock);
-
 	udp_tunnel_sock_release(gs->sock);
 	kfree_rcu(gs, rcu);
+
+unlock:
+	mutex_unlock(&geneve_mutex);
 }
 EXPORT_SYMBOL_GPL(geneve_sock_release);
 
@@ -427,8 +422,6 @@ static __net_init int geneve_init_net(struct net *net)
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	unsigned int h;
 
-	spin_lock_init(&gn->sock_lock);
-
 	for (h = 0; h < PORT_HASH_SIZE; ++h)
 		INIT_HLIST_HEAD(&gn->sock_list[h]);
 
@@ -454,7 +447,7 @@ static int __init geneve_init_module(void)
 
 	return 0;
 }
-late_initcall(geneve_init_module);
+module_init(geneve_init_module);
 
 static void __exit geneve_cleanup_module(void)
 {
-- 
cgit v1.2.3-70-g09d2


From df5dba8e52be50e615e03ef73b34611d82587f42 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Fri, 2 Jan 2015 18:26:04 -0800
Subject: geneve: Remove socket hash table.

The hash table for open Geneve ports is used only on creation and
deletion time. It is not performance critical and is not likely to
grow to a large number of items. Therefore, this can be changed
to use a simple linked list.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/geneve.h |  2 +-
 net/ipv4/geneve.c    | 26 +++++++-------------------
 2 files changed, 8 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/geneve.h b/include/net/geneve.h
index b40f4affc4c..03aa2adb5ba 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -68,7 +68,7 @@ struct geneve_sock;
 typedef void (geneve_rcv_t)(struct geneve_sock *gs, struct sk_buff *skb);
 
 struct geneve_sock {
-	struct hlist_node	hlist;
+	struct list_head	list;
 	geneve_rcv_t		*rcv;
 	void			*rcv_data;
 	struct socket		*sock;
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index ad8dbae11d0..4fe5a592821 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -26,7 +26,6 @@
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
-#include <linux/hash.h>
 #include <linux/ethtool.h>
 #include <linux/mutex.h>
 #include <net/arp.h>
@@ -54,12 +53,9 @@
 /* Protects sock_list and refcounts. */
 static DEFINE_MUTEX(geneve_mutex);
 
-#define PORT_HASH_BITS 8
-#define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
-
 /* per-network namespace private data for this module */
 struct geneve_net {
-	struct hlist_head	sock_list[PORT_HASH_SIZE];
+	struct list_head	sock_list;
 };
 
 static int geneve_net_id;
@@ -69,19 +65,13 @@ static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
 	return (struct genevehdr *)(udp_hdr(skb) + 1);
 }
 
-static struct hlist_head *gs_head(struct net *net, __be16 port)
-{
-	struct geneve_net *gn = net_generic(net, geneve_net_id);
-
-	return &gn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
-}
-
 /* Find geneve socket based on network namespace and UDP port */
 static struct geneve_sock *geneve_find_sock(struct net *net, __be16 port)
 {
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
 
-	hlist_for_each_entry(gs, gs_head(net, port), hlist) {
+	list_for_each_entry(gs, &gn->sock_list, list) {
 		if (inet_sk(gs->sock->sk)->inet_sport == port)
 			return gs;
 	}
@@ -339,6 +329,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 						geneve_rcv_t *rcv, void *data,
 						bool ipv6)
 {
+	struct geneve_net *gn = net_generic(net, geneve_net_id);
 	struct geneve_sock *gs;
 	struct socket *sock;
 	struct udp_tunnel_sock_cfg tunnel_cfg;
@@ -371,7 +362,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 	tunnel_cfg.encap_destroy = NULL;
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 
-	hlist_add_head(&gs->hlist, gs_head(net, port));
+	list_add(&gs->list, &gn->sock_list);
 
 	return gs;
 }
@@ -407,7 +398,7 @@ void geneve_sock_release(struct geneve_sock *gs)
 	if (--gs->refcnt)
 		goto unlock;
 
-	hlist_del(&gs->hlist);
+	list_del(&gs->list);
 	geneve_notify_del_rx_port(gs);
 	udp_tunnel_sock_release(gs->sock);
 	kfree_rcu(gs, rcu);
@@ -420,17 +411,14 @@ EXPORT_SYMBOL_GPL(geneve_sock_release);
 static __net_init int geneve_init_net(struct net *net)
 {
 	struct geneve_net *gn = net_generic(net, geneve_net_id);
-	unsigned int h;
 
-	for (h = 0; h < PORT_HASH_SIZE; ++h)
-		INIT_HLIST_HEAD(&gn->sock_list[h]);
+	INIT_LIST_HEAD(&gn->sock_list);
 
 	return 0;
 }
 
 static struct pernet_operations geneve_net_ops = {
 	.init = geneve_init_net,
-	.exit = NULL,
 	.id   = &geneve_net_id,
 	.size = sizeof(struct geneve_net),
 };
-- 
cgit v1.2.3-70-g09d2


From 86b35b64ed7b6b38305dee67a0f2ddff2ca5455d Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Sun, 4 Jan 2015 15:25:09 +0800
Subject: rhashtable: fix missing header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixup below build error:

include/linux/rhashtable.h: At top level:
include/linux/rhashtable.h:118:34: error: field ‘mutex’ has incomplete type

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index de7cac753b0..de1459c74c4 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -20,6 +20,7 @@
 
 #include <linux/list_nulls.h>
 #include <linux/workqueue.h>
+#include <linux/mutex.h>
 
 /*
  * The end of the chain is marked with a special nulls marks which has
-- 
cgit v1.2.3-70-g09d2


From a3449ded128d037e6b2bd7a59b0741de56506066 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Sun, 4 Jan 2015 15:24:35 +0800
Subject: list_nulls: fix missing header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixup below build error:

include/linux/list_nulls.h: In function ‘hlist_nulls_del’:
include/linux/list_nulls.h:84:13: error: ‘LIST_POISON2’ undeclared (first use in this function)

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/list_nulls.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index e8c300e0643..f266661d266 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -1,6 +1,9 @@
 #ifndef _LINUX_LIST_NULLS_H
 #define _LINUX_LIST_NULLS_H
 
+#include <linux/poison.h>
+#include <linux/const.h>
+
 /*
  * Special version of lists, where end of list is not a NULL pointer,
  * but a 'nulls' marker, which can have many different values.
-- 
cgit v1.2.3-70-g09d2


From 1803f594cbf9bb2e662ac945038113d0d0cc5e89 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 5 Jan 2015 11:16:42 +0100
Subject: nl80211: document NL80211_BSS_STATUS_AUTHENTICATED isn't used

The flag is no longer used (and hasn't been for a long time)
since trying to track authentication (and make decisions based
on state) was just causing issues all over - see commit
95de817b9034d50860319f6033ec85d25024694c.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 18cb0aa0635..54f39114135 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3265,6 +3265,9 @@ enum nl80211_bss {
 /**
  * enum nl80211_bss_status - BSS "status"
  * @NL80211_BSS_STATUS_AUTHENTICATED: Authenticated with this BSS.
+ *	Note that this is no longer used since cfg80211 no longer
+ *	keeps track of whether or not authentication was done with
+ *	a given BSS.
  * @NL80211_BSS_STATUS_ASSOCIATED: Associated with this BSS.
  * @NL80211_BSS_STATUS_IBSS_JOINED: Joined to this IBSS.
  *
-- 
cgit v1.2.3-70-g09d2


From 149118d89355fb0e1a898f47977f8ae9be8e14e7 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Tue, 6 Jan 2015 01:04:21 +0100
Subject: netlink: Warn on unordered or illegal nla_nest_cancel() or
 nlmsg_cancel()

Calling nla_nest_cancel() in a different order as the nesting was
built up can lead to negative offsets being calculated which
results in skb_trim() being called with an underflowed unsigned
int. Warn if mark < skb->data as it's definitely a bug.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netlink.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index 64158353ecb..d5869b90bfb 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -520,8 +520,10 @@ static inline void *nlmsg_get_pos(struct sk_buff *skb)
  */
 static inline void nlmsg_trim(struct sk_buff *skb, const void *mark)
 {
-	if (mark)
+	if (mark) {
+		WARN_ON((unsigned char *) mark < skb->data);
 		skb_trim(skb, (unsigned char *) mark - skb->data);
+	}
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 224d019c4fbba242041e9b25a926ba873b7da1e2 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 5 Jan 2015 13:56:14 -0800
Subject: ip: Move checksum convert defines to inet

Move convert_csum from udp_sock to inet_sock. This allows the
possibility that we can use convert checksum for different types
of sockets and also allows convert checksum to be enabled from
inet layer (what we'll want to do when enabling IP_CHECKSUM cmsg).

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h     | 16 +---------------
 include/net/inet_sock.h | 17 +++++++++++++++++
 net/ipv4/fou.c          |  2 +-
 net/ipv4/udp.c          |  2 +-
 net/ipv4/udp_tunnel.c   |  2 +-
 net/ipv6/udp.c          |  2 +-
 6 files changed, 22 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/udp.h b/include/linux/udp.h
index ee327759322..247cfdcc4b0 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -49,11 +49,7 @@ struct udp_sock {
 	unsigned int	 corkflag;	/* Cork is required */
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
-			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
-			 convert_csum:1;/* On receive, convert checksum
-					 * unnecessary to checksum complete
-					 * if possible.
-					 */
+			 no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
@@ -102,16 +98,6 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 	return udp_sk(sk)->no_check6_rx;
 }
 
-static inline void udp_set_convert_csum(struct sock *sk, bool val)
-{
-	udp_sk(sk)->convert_csum = val;
-}
-
-static inline bool udp_get_convert_csum(struct sock *sk)
-{
-	return udp_sk(sk)->convert_csum;
-}
-
 #define udp_portaddr_for_each_entry(__sk, node, list) \
 	hlist_nulls_for_each_entry(__sk, node, list, __sk_common.skc_portaddr_node)
 
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index a829b77523c..360b110b3e3 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -184,6 +184,7 @@ struct inet_sock {
 				mc_all:1,
 				nodefrag:1;
 	__u8			rcv_tos;
+	__u8			convert_csum;
 	int			uc_index;
 	int			mc_index;
 	__be32			mc_addr;
@@ -250,4 +251,20 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
 	return flags;
 }
 
+static inline void inet_inc_convert_csum(struct sock *sk)
+{
+	inet_sk(sk)->convert_csum++;
+}
+
+static inline void inet_dec_convert_csum(struct sock *sk)
+{
+	if (inet_sk(sk)->convert_csum > 0)
+		inet_sk(sk)->convert_csum--;
+}
+
+static inline bool inet_get_convert_csum(struct sock *sk)
+{
+	return !!inet_sk(sk)->convert_csum;
+}
+
 #endif	/* _INET_SOCK_H */
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index b986298a7ba..2197c36f722 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -490,7 +490,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
 	sk->sk_user_data = fou;
 	fou->sock = sock;
 
-	udp_set_convert_csum(sk, true);
+	inet_inc_convert_csum(sk);
 
 	sk->sk_allocation = GFP_ATOMIC;
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 13b4dcf86ef..53358d88f11 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1806,7 +1806,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (sk != NULL) {
 		int ret;
 
-		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
 			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
 						 inet_compute_pseudo);
 
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 1671263e5fa..9996e63ed30 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -63,7 +63,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 	inet_sk(sk)->mc_loop = 0;
 
 	/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
-	udp_set_convert_csum(sk, true);
+	inet_inc_convert_csum(sk);
 
 	rcu_assign_sk_user_data(sk, cfg->sk_user_data);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 189dc4ae3ec..e41f017cd47 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -909,7 +909,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			goto csum_error;
 		}
 
-		if (udp_sk(sk)->convert_csum && uh->check && !IS_UDPLITE(sk))
+		if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
 			skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
 						 ip6_compute_pseudo);
 
-- 
cgit v1.2.3-70-g09d2


From c44d13d6f341ca59f3d6646f2337d4d3c8a814a6 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 5 Jan 2015 13:56:15 -0800
Subject: ip: IP cmsg cleanup

Move the IP_CMSG_* constants from ip_sockglue.c to inet_sock.h so that
they can be referenced in other source files.

Restructure ip_cmsg_recv to not go through flags using shift, check
for flags by 'and'. This eliminates both the shift and a conditional
per flag check.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h | 11 ++++++++-
 net/ipv4/ip_sockglue.c  | 64 ++++++++++++++++++++++++++++---------------------
 2 files changed, 47 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 360b110b3e3..605ca421d5a 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -16,7 +16,7 @@
 #ifndef _INET_SOCK_H
 #define _INET_SOCK_H
 
-
+#include <linux/bitops.h>
 #include <linux/kmemcheck.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -195,6 +195,15 @@ struct inet_sock {
 #define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
 #define IPCORK_ALLFRAG	2	/* always fragment (for ipv6 for now) */
 
+/* cmsg flags for inet */
+#define IP_CMSG_PKTINFO		BIT(0)
+#define IP_CMSG_TTL		BIT(1)
+#define IP_CMSG_TOS		BIT(2)
+#define IP_CMSG_RECVOPTS	BIT(3)
+#define IP_CMSG_RETOPTS		BIT(4)
+#define IP_CMSG_PASSSEC		BIT(5)
+#define IP_CMSG_ORIGDSTADDR	BIT(6)
+
 static inline struct inet_sock *inet_sk(const struct sock *sk)
 {
 	return (struct inet_sock *)sk;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 8a89c738b7a..80f78565b41 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -45,14 +45,6 @@
 #include <linux/errqueue.h>
 #include <asm/uaccess.h>
 
-#define IP_CMSG_PKTINFO		1
-#define IP_CMSG_TTL		2
-#define IP_CMSG_TOS		4
-#define IP_CMSG_RECVOPTS	8
-#define IP_CMSG_RETOPTS		16
-#define IP_CMSG_PASSSEC		32
-#define IP_CMSG_ORIGDSTADDR     64
-
 /*
  *	SOL_IP control messages.
  */
@@ -150,37 +142,55 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 	unsigned int flags = inet->cmsg_flags;
 
 	/* Ordered by supposed usage frequency */
-	if (flags & 1)
+	if (flags & IP_CMSG_PKTINFO) {
 		ip_cmsg_recv_pktinfo(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_PKTINFO;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_TTL) {
 		ip_cmsg_recv_ttl(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_TTL;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_TOS) {
 		ip_cmsg_recv_tos(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_TOS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_RECVOPTS) {
 		ip_cmsg_recv_opts(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_RECVOPTS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_RETOPTS) {
 		ip_cmsg_recv_retopts(msg, skb);
-	if ((flags >>= 1) == 0)
-		return;
 
-	if (flags & 1)
+		flags &= ~IP_CMSG_RETOPTS;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_PASSSEC) {
 		ip_cmsg_recv_security(msg, skb);
 
-	if ((flags >>= 1) == 0)
-		return;
-	if (flags & 1)
+		flags &= ~IP_CMSG_PASSSEC;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_ORIGDSTADDR)
 		ip_cmsg_recv_dstaddr(msg, skb);
 
 }
-- 
cgit v1.2.3-70-g09d2


From 5961de9f199bef6ff437d7d85fe69b6a1964739b Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 5 Jan 2015 13:56:16 -0800
Subject: ip: Add offset parameter to ip_cmsg_recv

Add ip_cmsg_recv_offset function which takes an offset argument
that indicates the starting offset in skb where data is being received
from. This will be useful in the case of UDP and provided checksum
to user space.

ip_cmsg_recv is an inline call to ip_cmsg_recv_offset with offset of
zero.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h       | 7 ++++++-
 net/ipv4/ip_sockglue.c | 5 +++--
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index 0bb62070292..0e5a0bae187 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -537,7 +537,7 @@ int ip_options_rcv_srr(struct sk_buff *skb);
  */
 
 void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
-void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb, int offset);
 int ip_cmsg_send(struct net *net, struct msghdr *msg,
 		 struct ipcm_cookie *ipc, bool allow_ipv6);
 int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
@@ -557,6 +557,11 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
 void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport,
 		    u32 info);
 
+static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
+{
+	ip_cmsg_recv_offset(msg, skb, 0);
+}
+
 bool icmp_global_allow(void);
 extern int sysctl_icmp_msgs_per_sec;
 extern int sysctl_icmp_msgs_burst;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 80f78565b41..513d506ffeb 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -136,7 +136,8 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin);
 }
 
-void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
+void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
+			 int offset)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
 	unsigned int flags = inet->cmsg_flags;
@@ -194,7 +195,7 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 		ip_cmsg_recv_dstaddr(msg, skb);
 
 }
-EXPORT_SYMBOL(ip_cmsg_recv);
+EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
 int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		 bool allow_ipv6)
-- 
cgit v1.2.3-70-g09d2


From ad6f939ab193750cc94a265f58e007fb598c97b7 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 5 Jan 2015 13:56:17 -0800
Subject: ip: Add offset parameter to ip_cmsg_recv

Add ip_cmsg_recv_offset function which takes an offset argument
that indicates the starting offset in skb where data is being received
from. This will be useful in the case of UDP and provided checksum
to user space.

ip_cmsg_recv is an inline call to ip_cmsg_recv_offset with offset of
zero.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h |  1 +
 include/uapi/linux/in.h |  1 +
 net/ipv4/ip_sockglue.c  | 41 ++++++++++++++++++++++++++++++++++++++++-
 net/ipv4/udp.c          |  2 +-
 4 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 605ca421d5a..eb16c7beed1 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -203,6 +203,7 @@ struct inet_sock {
 #define IP_CMSG_RETOPTS		BIT(4)
 #define IP_CMSG_PASSSEC		BIT(5)
 #define IP_CMSG_ORIGDSTADDR	BIT(6)
+#define IP_CMSG_CHECKSUM	BIT(7)
 
 static inline struct inet_sock *inet_sk(const struct sock *sk)
 {
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index c33a65e3d62..589ced069e8 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -109,6 +109,7 @@ struct in_addr {
 
 #define IP_MINTTL       21
 #define IP_NODEFRAG     22
+#define IP_CHECKSUM	23
 
 /* IP_MTU_DISCOVER values */
 #define IP_PMTUDISC_DONT		0	/* Never send DF frames */
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 513d506ffeb..a317797b3cd 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -37,6 +37,7 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 #include <net/compat.h>
+#include <net/checksum.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/transp_v6.h>
 #endif
@@ -96,6 +97,20 @@ static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb)
 	put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data);
 }
 
+static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb,
+				  int offset)
+{
+	__wsum csum = skb->csum;
+
+	if (skb->ip_summed != CHECKSUM_COMPLETE)
+		return;
+
+	if (offset != 0)
+		csum = csum_sub(csum, csum_partial(skb->data, offset, 0));
+
+	put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum);
+}
+
 static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 {
 	char *secdata;
@@ -191,9 +206,16 @@ void ip_cmsg_recv_offset(struct msghdr *msg, struct sk_buff *skb,
 			return;
 	}
 
-	if (flags & IP_CMSG_ORIGDSTADDR)
+	if (flags & IP_CMSG_ORIGDSTADDR) {
 		ip_cmsg_recv_dstaddr(msg, skb);
 
+		flags &= ~IP_CMSG_ORIGDSTADDR;
+		if (!flags)
+			return;
+	}
+
+	if (flags & IP_CMSG_CHECKSUM)
+		ip_cmsg_recv_checksum(msg, skb, offset);
 }
 EXPORT_SYMBOL(ip_cmsg_recv_offset);
 
@@ -533,6 +555,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 	case IP_MULTICAST_ALL:
 	case IP_MULTICAST_LOOP:
 	case IP_RECVORIGDSTADDR:
+	case IP_CHECKSUM:
 		if (optlen >= sizeof(int)) {
 			if (get_user(val, (int __user *) optval))
 				return -EFAULT;
@@ -630,6 +653,19 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 		else
 			inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR;
 		break;
+	case IP_CHECKSUM:
+		if (val) {
+			if (!(inet->cmsg_flags & IP_CMSG_CHECKSUM)) {
+				inet_inc_convert_csum(sk);
+				inet->cmsg_flags |= IP_CMSG_CHECKSUM;
+			}
+		} else {
+			if (inet->cmsg_flags & IP_CMSG_CHECKSUM) {
+				inet_dec_convert_csum(sk);
+				inet->cmsg_flags &= ~IP_CMSG_CHECKSUM;
+			}
+		}
+		break;
 	case IP_TOS:	/* This sets both TOS and Precedence */
 		if (sk->sk_type == SOCK_STREAM) {
 			val &= ~INET_ECN_MASK;
@@ -1233,6 +1269,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	case IP_RECVORIGDSTADDR:
 		val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
 		break;
+	case IP_CHECKSUM:
+		val = (inet->cmsg_flags & IP_CMSG_CHECKSUM) != 0;
+		break;
 	case IP_TOS:
 		val = inet->tos;
 		break;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 53358d88f11..97ef1f8b7be 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1329,7 +1329,7 @@ try_again:
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv(msg, skb);
+		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr));
 
 	err = copied;
 	if (flags & MSG_TRUNC)
-- 
cgit v1.2.3-70-g09d2


From e715b6d3a5ef55834778d49224e60e8ccb5bf45f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 5 Jan 2015 23:57:44 +0100
Subject: net: fib6: convert cfg metric to u32 outside of table write lock

Do the nla validation earlier, outside the write lock.

This is needed by followup patch which needs to be able to call
request_module (which can sleep) if needed.

Joint work with Daniel Borkmann.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip6_fib.h | 10 +++++---
 net/ipv6/ip6_fib.c    | 69 +++++++++++++++++++++++++++------------------------
 net/ipv6/route.c      | 57 ++++++++++++++++++++++++++++++++++--------
 3 files changed, 90 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 8eea35d32a7..20e80fa7bbd 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -74,6 +74,11 @@ struct fib6_node {
 #define FIB6_SUBTREE(fn)	((fn)->subtree)
 #endif
 
+struct mx6_config {
+	const u32 *mx;
+	DECLARE_BITMAP(mx_valid, RTAX_MAX);
+};
+
 /*
  *	routing information
  *
@@ -291,9 +296,8 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		    void *arg);
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
-	     struct nlattr *mx, int mx_len);
-
+int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+	     struct nl_info *info, struct mx6_config *mxc);
 int fib6_del(struct rt6_info *rt, struct nl_info *info);
 
 void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index db4984e13f2..03c520a4ebe 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -630,31 +630,35 @@ static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
 	       RTF_GATEWAY;
 }
 
-static int fib6_commit_metrics(struct dst_entry *dst,
-			       struct nlattr *mx, int mx_len)
+static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
 {
-	bool dst_host = dst->flags & DST_HOST;
-	struct nlattr *nla;
-	int remaining;
-	u32 *mp;
+	int i;
 
-	mp = dst_host ? dst_metrics_write_ptr(dst) :
-			kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
-	if (unlikely(!mp))
-		return -ENOMEM;
-	if (!dst_host)
-		dst_init_metrics(dst, mp, 0);
+	for (i = 0; i < RTAX_MAX; i++) {
+		if (test_bit(i, mxc->mx_valid))
+			mp[i] = mxc->mx[i];
+	}
+}
+
+static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
+{
+	if (!mxc->mx)
+		return 0;
 
-	nla_for_each_attr(nla, mx, mx_len, remaining) {
-		int type = nla_type(nla);
+	if (dst->flags & DST_HOST) {
+		u32 *mp = dst_metrics_write_ptr(dst);
 
-		if (type) {
-			if (type > RTAX_MAX)
-				return -EINVAL;
+		if (unlikely(!mp))
+			return -ENOMEM;
 
-			mp[type - 1] = nla_get_u32(nla);
-		}
+		fib6_copy_metrics(mp, mxc);
+	} else {
+		dst_init_metrics(dst, mxc->mx, false);
+
+		/* We've stolen mx now. */
+		mxc->mx = NULL;
 	}
+
 	return 0;
 }
 
@@ -663,7 +667,7 @@ static int fib6_commit_metrics(struct dst_entry *dst,
  */
 
 static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
-			    struct nl_info *info, struct nlattr *mx, int mx_len)
+			    struct nl_info *info, struct mx6_config *mxc)
 {
 	struct rt6_info *iter = NULL;
 	struct rt6_info **ins;
@@ -772,11 +776,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			pr_warn("NLM_F_CREATE should be set when creating new route\n");
 
 add:
-		if (mx) {
-			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
-			if (err)
-				return err;
-		}
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		rt->dst.rt6_next = iter;
 		*ins = rt;
 		rt->rt6i_node = fn;
@@ -796,11 +799,11 @@ add:
 			pr_warn("NLM_F_REPLACE set, but no existing node found!\n");
 			return -ENOENT;
 		}
-		if (mx) {
-			err = fib6_commit_metrics(&rt->dst, mx, mx_len);
-			if (err)
-				return err;
-		}
+
+		err = fib6_commit_metrics(&rt->dst, mxc);
+		if (err)
+			return err;
+
 		*ins = rt;
 		rt->rt6i_node = fn;
 		rt->dst.rt6_next = iter->dst.rt6_next;
@@ -837,8 +840,8 @@ void fib6_force_start_gc(struct net *net)
  *	with source addr info in sub-trees
  */
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
-	     struct nlattr *mx, int mx_len)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+	     struct nl_info *info, struct mx6_config *mxc)
 {
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
@@ -933,7 +936,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, mx, mx_len);
+	err = fib6_add_rt2node(fn, rt, info, mxc);
 	if (!err) {
 		fib6_start_gc(info->nl_net, rt);
 		if (!(rt->rt6i_flags & RTF_CACHE))
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c91083156ed..454771d20b2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -853,14 +853,14 @@ EXPORT_SYMBOL(rt6_lookup);
  */
 
 static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
-			struct nlattr *mx, int mx_len)
+			struct mx6_config *mxc)
 {
 	int err;
 	struct fib6_table *table;
 
 	table = rt->rt6i_table;
 	write_lock_bh(&table->tb6_lock);
-	err = fib6_add(&table->tb6_root, rt, info, mx, mx_len);
+	err = fib6_add(&table->tb6_root, rt, info, mxc);
 	write_unlock_bh(&table->tb6_lock);
 
 	return err;
@@ -868,10 +868,10 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
 
 int ip6_ins_rt(struct rt6_info *rt)
 {
-	struct nl_info info = {
-		.nl_net = dev_net(rt->dst.dev),
-	};
-	return __ip6_ins_rt(rt, &info, NULL, 0);
+	struct nl_info info = {	.nl_net = dev_net(rt->dst.dev), };
+	struct mx6_config mxc = { .mx = NULL, };
+
+	return __ip6_ins_rt(rt, &info, &mxc);
 }
 
 static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
@@ -1470,9 +1470,39 @@ out:
 	return entries > rt_max_size;
 }
 
-/*
- *
- */
+static int ip6_convert_metrics(struct mx6_config *mxc,
+			       const struct fib6_config *cfg)
+{
+	struct nlattr *nla;
+	int remaining;
+	u32 *mp;
+
+	if (cfg->fc_mx == NULL)
+		return 0;
+
+	mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+	if (unlikely(!mp))
+		return -ENOMEM;
+
+	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
+		int type = nla_type(nla);
+
+		if (type) {
+			if (unlikely(type > RTAX_MAX))
+				goto err;
+
+			mp[type - 1] = nla_get_u32(nla);
+			__set_bit(type - 1, mxc->mx_valid);
+		}
+	}
+
+	mxc->mx = mp;
+
+	return 0;
+ err:
+	kfree(mp);
+	return -EINVAL;
+}
 
 int ip6_route_add(struct fib6_config *cfg)
 {
@@ -1482,6 +1512,7 @@ int ip6_route_add(struct fib6_config *cfg)
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev = NULL;
 	struct fib6_table *table;
+	struct mx6_config mxc = { .mx = NULL, };
 	int addr_type;
 
 	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
@@ -1677,8 +1708,14 @@ install_route:
 
 	cfg->fc_nlinfo.nl_net = dev_net(dev);
 
-	return __ip6_ins_rt(rt, &cfg->fc_nlinfo, cfg->fc_mx, cfg->fc_mx_len);
+	err = ip6_convert_metrics(&mxc, cfg);
+	if (err)
+		goto out;
+
+	err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc);
 
+	kfree(mxc.mx);
+	return err;
 out:
 	if (dev)
 		dev_put(dev);
-- 
cgit v1.2.3-70-g09d2


From c5c6a8ab45ec0f18733afb4aaade0d4a139d80b3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 5 Jan 2015 23:57:46 +0100
Subject: net: tcp: add key management to congestion control

This patch adds necessary infrastructure to the congestion control
framework for later per route congestion control support.

For a per route congestion control possibility, our aim is to store
a unique u32 key identifier into dst metrics, which can then be
mapped into a tcp_congestion_ops struct. We argue that having a
RTAX key entry is the most simple, generic and easy way to manage,
and also keeps the memory footprint of dst entries lower on 64 bit
than with storing a pointer directly, for example. Having a unique
key id also allows for decoupling actual TCP congestion control
module management from the FIB layer, i.e. we don't have to care
about expensive module refcounting inside the FIB at this point.

We first thought of using an IDR store for the realization, which
takes over dynamic assignment of unused key space and also performs
the key to pointer mapping in RCU. While doing so, we stumbled upon
the issue that due to the nature of dynamic key distribution, it
just so happens, arguably in very rare occasions, that excessive
module loads and unloads can lead to a possible reuse of previously
used key space. Thus, previously stale keys in the dst metric are
now being reassigned to a different congestion control algorithm,
which might lead to unexpected behaviour. One way to resolve this
would have been to walk FIBs on the actually rare occasion of a
module unload and reset the metric keys for each FIB in each netns,
but that's just very costly.

Therefore, we argue a better solution is to reuse the unique
congestion control algorithm name member and map that into u32 key
space through jhash. For that, we split the flags attribute (as it
currently uses 2 bits only anyway) into two u32 attributes, flags
and key, so that we can keep the cacheline boundary of 2 cachelines
on x86_64 and cache the precalculated key at registration time for
the fast path. On average we might expect 2 - 4 modules being loaded
worst case perhaps 15, so a key collision possibility is extremely
low, and guaranteed collision-free on LE/BE for all in-tree modules.
Overall this results in much simpler code, and all without the
overhead of an IDR. Due to the deterministic nature, modules can
now be unloaded, the congestion control algorithm for a specific
but unloaded key will fall back to the default one, and on module
reload time it will switch back to the expected algorithm
transparently.

Joint work with Florian Westphal.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h |  3 +-
 include/net/tcp.h                  |  9 +++-
 net/ipv4/tcp_cong.c                | 97 +++++++++++++++++++++++++++++++-------
 3 files changed, 91 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 848e85cb5c6..5976bdecf58 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -98,7 +98,8 @@ struct inet_connection_sock {
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
-	__u8			  icsk_ca_state;
+	__u8			  icsk_ca_state:7,
+				  icsk_ca_dst_locked:1;
 	__u8			  icsk_retransmits;
 	__u8			  icsk_pending;
 	__u8			  icsk_backoff;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f50f29faf76..135b70c9a73 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -787,6 +787,8 @@ enum tcp_ca_ack_event_flags {
 #define TCP_CA_MAX	128
 #define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)
 
+#define TCP_CA_UNSPEC	0
+
 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
 #define TCP_CONG_NON_RESTRICTED 0x1
 /* Requires ECN/ECT set on all packets */
@@ -794,7 +796,8 @@ enum tcp_ca_ack_event_flags {
 
 struct tcp_congestion_ops {
 	struct list_head	list;
-	unsigned long flags;
+	u32 key;
+	u32 flags;
 
 	/* initialize private data (optional) */
 	void (*init)(struct sock *sk);
@@ -841,6 +844,10 @@ u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
 extern struct tcp_congestion_ops tcp_reno;
 
+struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
+u32 tcp_ca_get_key_by_name(const char *name);
+char *tcp_ca_get_name_by_key(u32 key, char *buffer);
+
 static inline bool tcp_ca_needs_ecn(const struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 38f2f8aa4ce..63c29dba68a 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/gfp.h>
+#include <linux/jhash.h>
 #include <net/tcp.h>
 
 static DEFINE_SPINLOCK(tcp_cong_list_lock);
@@ -31,6 +32,34 @@ static struct tcp_congestion_ops *tcp_ca_find(const char *name)
 	return NULL;
 }
 
+/* Must be called with rcu lock held */
+static const struct tcp_congestion_ops *__tcp_ca_find_autoload(const char *name)
+{
+	const struct tcp_congestion_ops *ca = tcp_ca_find(name);
+#ifdef CONFIG_MODULES
+	if (!ca && capable(CAP_NET_ADMIN)) {
+		rcu_read_unlock();
+		request_module("tcp_%s", name);
+		rcu_read_lock();
+		ca = tcp_ca_find(name);
+	}
+#endif
+	return ca;
+}
+
+/* Simple linear search, not much in here. */
+struct tcp_congestion_ops *tcp_ca_find_key(u32 key)
+{
+	struct tcp_congestion_ops *e;
+
+	list_for_each_entry_rcu(e, &tcp_cong_list, list) {
+		if (e->key == key)
+			return e;
+	}
+
+	return NULL;
+}
+
 /*
  * Attach new congestion control algorithm to the list
  * of available options.
@@ -45,9 +74,12 @@ int tcp_register_congestion_control(struct tcp_congestion_ops *ca)
 		return -EINVAL;
 	}
 
+	ca->key = jhash(ca->name, sizeof(ca->name), strlen(ca->name));
+
 	spin_lock(&tcp_cong_list_lock);
-	if (tcp_ca_find(ca->name)) {
-		pr_notice("%s already registered\n", ca->name);
+	if (ca->key == TCP_CA_UNSPEC || tcp_ca_find_key(ca->key)) {
+		pr_notice("%s already registered or non-unique key\n",
+			  ca->name);
 		ret = -EEXIST;
 	} else {
 		list_add_tail_rcu(&ca->list, &tcp_cong_list);
@@ -70,9 +102,50 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca)
 	spin_lock(&tcp_cong_list_lock);
 	list_del_rcu(&ca->list);
 	spin_unlock(&tcp_cong_list_lock);
+
+	/* Wait for outstanding readers to complete before the
+	 * module gets removed entirely.
+	 *
+	 * A try_module_get() should fail by now as our module is
+	 * in "going" state since no refs are held anymore and
+	 * module_exit() handler being called.
+	 */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control);
 
+u32 tcp_ca_get_key_by_name(const char *name)
+{
+	const struct tcp_congestion_ops *ca;
+	u32 key;
+
+	might_sleep();
+
+	rcu_read_lock();
+	ca = __tcp_ca_find_autoload(name);
+	key = ca ? ca->key : TCP_CA_UNSPEC;
+	rcu_read_unlock();
+
+	return key;
+}
+EXPORT_SYMBOL_GPL(tcp_ca_get_key_by_name);
+
+char *tcp_ca_get_name_by_key(u32 key, char *buffer)
+{
+	const struct tcp_congestion_ops *ca;
+	char *ret = NULL;
+
+	rcu_read_lock();
+	ca = tcp_ca_find_key(key);
+	if (ca)
+		ret = strncpy(buffer, ca->name,
+			      TCP_CA_NAME_MAX);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tcp_ca_get_name_by_key);
+
 /* Assign choice of congestion control. */
 void tcp_assign_congestion_control(struct sock *sk)
 {
@@ -253,25 +326,17 @@ out:
 int tcp_set_congestion_control(struct sock *sk, const char *name)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
-	struct tcp_congestion_ops *ca;
+	const struct tcp_congestion_ops *ca;
 	int err = 0;
 
-	rcu_read_lock();
-	ca = tcp_ca_find(name);
+	if (icsk->icsk_ca_dst_locked)
+		return -EPERM;
 
-	/* no change asking for existing value */
+	rcu_read_lock();
+	ca = __tcp_ca_find_autoload(name);
+	/* No change asking for existing value */
 	if (ca == icsk->icsk_ca_ops)
 		goto out;
-
-#ifdef CONFIG_MODULES
-	/* not found attempt to autoload module */
-	if (!ca && capable(CAP_NET_ADMIN)) {
-		rcu_read_unlock();
-		request_module("tcp_%s", name);
-		rcu_read_lock();
-		ca = tcp_ca_find(name);
-	}
-#endif
 	if (!ca)
 		err = -ENOENT;
 	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) ||
-- 
cgit v1.2.3-70-g09d2


From ea697639992d96da98016b8934e68a73876a2264 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 5 Jan 2015 23:57:47 +0100
Subject: net: tcp: add RTAX_CC_ALGO fib handling

This patch adds the minimum necessary for the RTAX_CC_ALGO congestion
control metric to be set up and dumped back to user space.

While the internal representation of RTAX_CC_ALGO is handled as a u32
key, we avoided to expose this implementation detail to user space, thus
instead, we chose the netlink attribute that is being exchanged between
user space to be the actual congestion control algorithm name, similarly
as in the setsockopt(2) API in order to allow for maximum flexibility,
even for 3rd party modules.

It is a bit unfortunate that RTAX_QUICKACK used up a whole RTAX slot as
it should have been stored in RTAX_FEATURES instead, we first thought
about reusing it for the congestion control key, but it brings more
complications and/or confusion than worth it.

Joint work with Florian Westphal.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h              |  7 +++++++
 include/uapi/linux/rtnetlink.h |  2 ++
 net/core/rtnetlink.c           | 15 +++++++++++++--
 net/decnet/dn_fib.c            |  3 ++-
 net/decnet/dn_table.c          |  4 +++-
 net/ipv4/fib_semantics.c       | 14 ++++++++++++--
 net/ipv6/route.c               | 17 +++++++++++++++--
 7 files changed, 54 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 135b70c9a73..95bb237152e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -846,7 +846,14 @@ extern struct tcp_congestion_ops tcp_reno;
 
 struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
 u32 tcp_ca_get_key_by_name(const char *name);
+#ifdef CONFIG_INET
 char *tcp_ca_get_name_by_key(u32 key, char *buffer);
+#else
+static inline char *tcp_ca_get_name_by_key(u32 key, char *buffer)
+{
+	return NULL;
+}
+#endif
 
 static inline bool tcp_ca_needs_ecn(const struct sock *sk)
 {
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 9c9b8b4480c..d81f22d5b39 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -389,6 +389,8 @@ enum {
 #define RTAX_INITRWND RTAX_INITRWND
 	RTAX_QUICKACK,
 #define RTAX_QUICKACK RTAX_QUICKACK
+	RTAX_CC_ALGO,
+#define RTAX_CC_ALGO RTAX_CC_ALGO
 	__RTAX_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index da983d4bac0..6a6cdade167 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -50,6 +50,7 @@
 #include <net/arp.h>
 #include <net/route.h>
 #include <net/udp.h>
+#include <net/tcp.h>
 #include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <net/fib_rules.h>
@@ -669,9 +670,19 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
 
 	for (i = 0; i < RTAX_MAX; i++) {
 		if (metrics[i]) {
+			if (i == RTAX_CC_ALGO - 1) {
+				char tmp[TCP_CA_NAME_MAX], *name;
+
+				name = tcp_ca_get_name_by_key(metrics[i], tmp);
+				if (!name)
+					continue;
+				if (nla_put_string(skb, i + 1, name))
+					goto nla_put_failure;
+			} else {
+				if (nla_put_u32(skb, i + 1, metrics[i]))
+					goto nla_put_failure;
+			}
 			valid++;
-			if (nla_put_u32(skb, i+1, metrics[i]))
-				goto nla_put_failure;
 		}
 	}
 
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index d332aefb084..df480343788 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -298,7 +298,8 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *att
 			int type = nla_type(attr);
 
 			if (type) {
-				if (type > RTAX_MAX || nla_len(attr) < 4)
+				if (type > RTAX_MAX || type == RTAX_CC_ALGO ||
+				    nla_len(attr) < 4)
 					goto err_inval;
 
 				fi->fib_metrics[type-1] = nla_get_u32(attr);
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 86e3807052e..3f19fcbf126 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -29,6 +29,7 @@
 #include <linux/route.h> /* RTF_xxx */
 #include <net/neighbour.h>
 #include <net/netlink.h>
+#include <net/tcp.h>
 #include <net/dst.h>
 #include <net/flow.h>
 #include <net/fib_rules.h>
@@ -273,7 +274,8 @@ static inline size_t dn_fib_nlmsg_size(struct dn_fib_info *fi)
 	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
 			 + nla_total_size(4) /* RTA_TABLE */
 			 + nla_total_size(2) /* RTA_DST */
-			 + nla_total_size(4); /* RTA_PRIORITY */
+			 + nla_total_size(4) /* RTA_PRIORITY */
+			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
 
 	/* space for nested metrics */
 	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index f99f41bd15b..d2b7b5521b1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -360,7 +360,8 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi)
 			 + nla_total_size(4) /* RTA_TABLE */
 			 + nla_total_size(4) /* RTA_DST */
 			 + nla_total_size(4) /* RTA_PRIORITY */
-			 + nla_total_size(4); /* RTA_PREFSRC */
+			 + nla_total_size(4) /* RTA_PREFSRC */
+			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
 
 	/* space for nested metrics */
 	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));
@@ -859,7 +860,16 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 
 				if (type > RTAX_MAX)
 					goto err_inval;
-				val = nla_get_u32(nla);
+				if (type == RTAX_CC_ALGO) {
+					char tmp[TCP_CA_NAME_MAX];
+
+					nla_strlcpy(tmp, nla, sizeof(tmp));
+					val = tcp_ca_get_key_by_name(tmp);
+					if (val == TCP_CA_UNSPEC)
+						goto err_inval;
+				} else {
+					val = nla_get_u32(nla);
+				}
 				if (type == RTAX_ADVMSS && val > 65535 - 40)
 					val = 65535 - 40;
 				if (type == RTAX_MTU && val > 65535 - 15)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 454771d20b2..34dcbb59df7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1488,10 +1488,22 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 		int type = nla_type(nla);
 
 		if (type) {
+			u32 val;
+
 			if (unlikely(type > RTAX_MAX))
 				goto err;
+			if (type == RTAX_CC_ALGO) {
+				char tmp[TCP_CA_NAME_MAX];
+
+				nla_strlcpy(tmp, nla, sizeof(tmp));
+				val = tcp_ca_get_key_by_name(tmp);
+				if (val == TCP_CA_UNSPEC)
+					goto err;
+			} else {
+				val = nla_get_u32(nla);
+			}
 
-			mp[type - 1] = nla_get_u32(nla);
+			mp[type - 1] = val;
 			__set_bit(type - 1, mxc->mx_valid);
 		}
 	}
@@ -2571,7 +2583,8 @@ static inline size_t rt6_nlmsg_size(void)
 	       + nla_total_size(4) /* RTA_OIF */
 	       + nla_total_size(4) /* RTA_PRIORITY */
 	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
-	       + nla_total_size(sizeof(struct rta_cacheinfo));
+	       + nla_total_size(sizeof(struct rta_cacheinfo))
+	       + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
 }
 
 static int rt6_fill_node(struct net *net,
-- 
cgit v1.2.3-70-g09d2


From 81164413ad096bafe8ad1068f3f095a7dd081d8b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 5 Jan 2015 23:57:48 +0100
Subject: net: tcp: add per route congestion control

This work adds the possibility to define a per route/destination
congestion control algorithm. Generally, this opens up the possibility
for a machine with different links to enforce specific congestion
control algorithms with optimal strategies for each of them based
on their network characteristics, even transparently for a single
application listening on all links.

For our specific use case, this additionally facilitates deployment
of DCTCP, for example, applications can easily serve internal
traffic/dsts in DCTCP and external one with CUBIC. Other scenarios
would also allow for utilizing e.g. long living, low priority
background flows for certain destinations/routes while still being
able for normal traffic to utilize the default congestion control
algorithm. We also thought about a per netns setting (where different
defaults are possible), but given its actually a link specific
property, we argue that a per route/destination setting is the most
natural and flexible.

The administrator can utilize this through ip-route(8) by appending
"congctl [lock] <name>", where <name> denotes the name of a
congestion control algorithm and the optional lock parameter allows
to enforce the given algorithm so that applications in user space
would not be allowed to overwrite that algorithm for that destination.

The dst metric lookups are being done when a dst entry is already
available in order to avoid a costly lookup and still before the
algorithms are being initialized, thus overhead is very low when the
feature is not being used. While the client side would need to drop
the current reference on the module, on server side this can actually
even be avoided as we just got a flat-copied socket clone.

Joint work with Florian Westphal.

Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        |  6 ++++++
 net/ipv4/tcp_ipv4.c      |  2 ++
 net/ipv4/tcp_minisocks.c | 30 ++++++++++++++++++++++++++----
 net/ipv4/tcp_output.c    | 21 +++++++++++++++++++++
 net/ipv6/tcp_ipv6.c      |  2 ++
 5 files changed, 57 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 95bb237152e..b8fdc6bab3f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -448,6 +448,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
 struct sock *tcp_create_openreq_child(struct sock *sk,
 				      struct request_sock *req,
 				      struct sk_buff *skb);
+void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst);
 struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst);
@@ -636,6 +637,11 @@ static inline u32 tcp_rto_min_us(struct sock *sk)
 	return jiffies_to_usecs(tcp_rto_min(sk));
 }
 
+static inline bool tcp_ca_dst_locked(const struct dst_entry *dst)
+{
+	return dst_metric_locked(dst, RTAX_CC_ALGO);
+}
+
 /* Compute the actual receive window we are currently advertising.
  * Rcv_nxt can be after the window if our peer push more data
  * than the offered window.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a3f72d7fc06..ad3e65bdd36 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1340,6 +1340,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	}
 	sk_setup_caps(newsk, dst);
 
+	tcp_ca_openreq_child(newsk, dst);
+
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
 	if (tcp_sk(sk)->rx_opt.user_mss &&
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63d2680b65d..bc9216dc9de 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -399,6 +399,32 @@ static void tcp_ecn_openreq_child(struct tcp_sock *tp,
 	tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
 }
 
+void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 ca_key = dst_metric(dst, RTAX_CC_ALGO);
+	bool ca_got_dst = false;
+
+	if (ca_key != TCP_CA_UNSPEC) {
+		const struct tcp_congestion_ops *ca;
+
+		rcu_read_lock();
+		ca = tcp_ca_find_key(ca_key);
+		if (likely(ca && try_module_get(ca->owner))) {
+			icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
+			icsk->icsk_ca_ops = ca;
+			ca_got_dst = true;
+		}
+		rcu_read_unlock();
+	}
+
+	if (!ca_got_dst && !try_module_get(icsk->icsk_ca_ops->owner))
+		tcp_assign_congestion_control(sk);
+
+	tcp_set_ca_state(sk, TCP_CA_Open);
+}
+EXPORT_SYMBOL_GPL(tcp_ca_openreq_child);
+
 /* This is not only more efficient than what we used to do, it eliminates
  * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
  *
@@ -451,10 +477,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		newtp->snd_cwnd = TCP_INIT_CWND;
 		newtp->snd_cwnd_cnt = 0;
 
-		if (!try_module_get(newicsk->icsk_ca_ops->owner))
-			tcp_assign_congestion_control(newsk);
-
-		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
 		__skb_queue_head_init(&newtp->out_of_order_queue);
 		newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7f18262e232..dc30cb563e4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2939,6 +2939,25 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 }
 EXPORT_SYMBOL(tcp_make_synack);
 
+static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct tcp_congestion_ops *ca;
+	u32 ca_key = dst_metric(dst, RTAX_CC_ALGO);
+
+	if (ca_key == TCP_CA_UNSPEC)
+		return;
+
+	rcu_read_lock();
+	ca = tcp_ca_find_key(ca_key);
+	if (likely(ca && try_module_get(ca->owner))) {
+		module_put(icsk->icsk_ca_ops->owner);
+		icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst);
+		icsk->icsk_ca_ops = ca;
+	}
+	rcu_read_unlock();
+}
+
 /* Do all connect socket setups that can be done AF independent. */
 static void tcp_connect_init(struct sock *sk)
 {
@@ -2964,6 +2983,8 @@ static void tcp_connect_init(struct sock *sk)
 	tcp_mtup_init(sk);
 	tcp_sync_mss(sk, dst_mtu(dst));
 
+	tcp_ca_dst_init(sk, dst);
+
 	if (!tp->window_clamp)
 		tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
 	tp->advmss = dst_metric_advmss(dst);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9c0b54e87b4..5d46832c6f7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1199,6 +1199,8 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
 						     newnp->opt->opt_flen);
 
+	tcp_ca_openreq_child(newsk, dst);
+
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric_advmss(dst);
 	if (tcp_sk(sk)->rx_opt.user_mss &&
-- 
cgit v1.2.3-70-g09d2


From d75bb06b61cb69ee6223d791d3bb230e68623b20 Mon Sep 17 00:00:00 2001
From: Gautam Kumar Shukla <gautams@broadcom.com>
Date: Tue, 23 Dec 2014 16:55:19 +0100
Subject: cfg80211: add extensible feature flag attribute

With the wiphy::features flag being used up this patch adds a
new field wiphy::ext_features. Considering extensibility this
new field is declared as a byte array. This extensible flag is
exposed to user-space by NL80211_ATTR_EXT_FEATURES.

Cc: Avinash Patil <patila@marvell.com>
Signed-off-by: Gautam (Gautam Kumar) Shukla <gautams@broadcom.com>
Signed-off-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 39 +++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/nl80211.h | 22 ++++++++++++++++++++++
 net/wireless/nl80211.c       |  5 +++++
 3 files changed, 66 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bd672ea08c9..f38645fb83b 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3016,6 +3016,8 @@ struct wiphy_vendor_command {
  * @regulatory_flags: wiphy regulatory flags, see
  *	&enum ieee80211_regulatory_flags
  * @features: features advertised to nl80211, see &enum nl80211_feature_flags.
+ * @ext_features: extended features advertised to nl80211, see
+ *	&enum nl80211_ext_feature_index.
  * @bss_priv_size: each BSS struct has private data allocated with it,
  *	this variable determines its size
  * @max_scan_ssids: maximum number of SSIDs the device can scan for in
@@ -3125,6 +3127,7 @@ struct wiphy {
 	u16 max_acl_mac_addrs;
 
 	u32 flags, regulatory_flags, features;
+	u8 ext_features[DIV_ROUND_UP(NUM_NL80211_EXT_FEATURES, 8)];
 
 	u32 ap_sme_capa;
 
@@ -5052,6 +5055,42 @@ void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev,
  */
 void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy);
 
+/**
+ * wiphy_ext_feature_set - set the extended feature flag
+ *
+ * @wiphy: the wiphy to modify.
+ * @ftidx: extended feature bit index.
+ *
+ * The extended features are flagged in multiple bytes (see
+ * &struct wiphy.@ext_features)
+ */
+static inline void wiphy_ext_feature_set(struct wiphy *wiphy,
+					 enum nl80211_ext_feature_index ftidx)
+{
+	u8 *ft_byte;
+
+	ft_byte = &wiphy->ext_features[ftidx / 8];
+	*ft_byte |= BIT(ftidx % 8);
+}
+
+/**
+ * wiphy_ext_feature_isset - check the extended feature flag
+ *
+ * @wiphy: the wiphy to modify.
+ * @ftidx: extended feature bit index.
+ *
+ * The extended features are flagged in multiple bytes (see
+ * &struct wiphy.@ext_features)
+ */
+static inline bool
+wiphy_ext_feature_isset(struct wiphy *wiphy,
+			enum nl80211_ext_feature_index ftidx)
+{
+	u8 ft_byte;
+
+	ft_byte = wiphy->ext_features[ftidx / 8];
+	return (ft_byte & BIT(ftidx % 8)) != 0;
+}
 
 /* ethtool helper */
 void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info);
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 54f39114135..f95d3548308 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1713,6 +1713,13 @@ enum nl80211_commands {
  *	obtained from it is coming from the device's wiphy and not the global
  *	cfg80211 regdomain.
  *
+ * @NL80211_ATTR_EXT_FEATURES: extended feature flags contained in a byte
+ *	array. The feature flags are identified by their bit index (see &enum
+ *	nl80211_ext_feature_index). The bit index is ordered starting at the
+ *	least-significant bit of the first byte in the array, ie. bit index 0
+ *	is located at bit 0 of byte 0. bit index 25 would be located at bit 1
+ *	of byte 3 (u8 array).
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2072,6 +2079,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_WIPHY_SELF_MANAGED_REG,
 
+	NL80211_ATTR_EXT_FEATURES,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -4223,6 +4232,19 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_ND_RANDOM_MAC_ADDR		= 1 << 31,
 };
 
+/**
+ * enum nl80211_ext_feature_index - bit index of extended features.
+ *
+ * @NUM_NL80211_EXT_FEATURES: number of extended features.
+ * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
+ */
+enum nl80211_ext_feature_index {
+
+	/* add new features before the definition below */
+	NUM_NL80211_EXT_FEATURES,
+	MAX_NL80211_EXT_FEATURES = NUM_NL80211_EXT_FEATURES - 1
+};
+
 /**
  * enum nl80211_probe_resp_offload_support_attr - optional supported
  *	protocols for probe-response offloading by the driver/FW.
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 702920134b3..689e1a8fd60 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1706,6 +1706,11 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
 			goto nla_put_failure;
 
+		if (nla_put(msg, NL80211_ATTR_EXT_FEATURES,
+			    sizeof(rdev->wiphy.ext_features),
+			    rdev->wiphy.ext_features))
+			goto nla_put_failure;
+
 		/* done */
 		state->split_start = 0;
 		break;
-- 
cgit v1.2.3-70-g09d2


From 71b836eca7f380fbd4c025f8c4371f9a071bc909 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 23 Dec 2014 17:17:38 +0100
Subject: nl80211: define multicast group names in header

Put the group names into the userspace API header file so that
userspace clients can use symbolic names from there instead of
hardcoding the actual names. This doesn't really change much,
but seems somewhat cleaner.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  7 +++++++
 net/wireless/nl80211.c       | 12 ++++++------
 2 files changed, 13 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f95d3548308..7ba9404b290 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -29,6 +29,13 @@
 
 #define NL80211_GENL_NAME "nl80211"
 
+#define NL80211_MULTICAST_GROUP_CONFIG		"config"
+#define NL80211_MULTICAST_GROUP_SCAN		"scan"
+#define NL80211_MULTICAST_GROUP_REG		"regulatory"
+#define NL80211_MULTICAST_GROUP_MLME		"mlme"
+#define NL80211_MULTICAST_GROUP_VENDOR		"vendor"
+#define NL80211_MULTICAST_GROUP_TESTMODE	"testmode"
+
 /**
  * DOC: Station handling
  *
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 689e1a8fd60..049f505e566 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -59,13 +59,13 @@ enum nl80211_multicast_groups {
 };
 
 static const struct genl_multicast_group nl80211_mcgrps[] = {
-	[NL80211_MCGRP_CONFIG] = { .name = "config", },
-	[NL80211_MCGRP_SCAN] = { .name = "scan", },
-	[NL80211_MCGRP_REGULATORY] = { .name = "regulatory", },
-	[NL80211_MCGRP_MLME] = { .name = "mlme", },
-	[NL80211_MCGRP_VENDOR] = { .name = "vendor", },
+	[NL80211_MCGRP_CONFIG] = { .name = NL80211_MULTICAST_GROUP_CONFIG },
+	[NL80211_MCGRP_SCAN] = { .name = NL80211_MULTICAST_GROUP_SCAN },
+	[NL80211_MCGRP_REGULATORY] = { .name = NL80211_MULTICAST_GROUP_REG },
+	[NL80211_MCGRP_MLME] = { .name = NL80211_MULTICAST_GROUP_MLME },
+	[NL80211_MCGRP_VENDOR] = { .name = NL80211_MULTICAST_GROUP_VENDOR },
 #ifdef CONFIG_NL80211_TESTMODE
-	[NL80211_MCGRP_TESTMODE] = { .name = "testmode", }
+	[NL80211_MCGRP_TESTMODE] = { .name = NL80211_MULTICAST_GROUP_TESTMODE }
 #endif
 };
 
-- 
cgit v1.2.3-70-g09d2


From 6810e4a394f9d781050107529b8d1465c00b7b13 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 6 Jan 2015 10:26:10 -0500
Subject: percpu_ref: remove unnecessary ACCESS_ONCE() in
 percpu_ref_tryget_live()

__ref_is_percpu() needs the implied ACCESS_ONCE() in
lockless_dereference() on @ref->percpu_count_ptr because the value is
tested for !__PERCPU_REF_ATOMIC, which may be set asynchronously, and
then used as a pointer.  If the compiler generates a separate fetch
when using it as a pointer, __PERCPU_REF_ATOMIC may be set in between
contaminating the pointer value.

percpu_ref_tryget_live() also uses ACCESS_ONCE() to test
__PERCPU_REF_DEAD; however, there's no reason for this.  I just copied
ACCESS_ONCE() usage blindly from __ref_is_percpu().  All it does is
confusing people trying to understand what's going on.

This patch removes the unnecessary ACCESS_ONCE() usage from
percpu_ref_tryget_live() and adds a comment explaining why
__ref_is_percpu() needs it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
---
 include/linux/percpu-refcount.h | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index b4337646388..6a7a670366a 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -128,8 +128,22 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
 static inline bool __ref_is_percpu(struct percpu_ref *ref,
 					  unsigned long __percpu **percpu_countp)
 {
-	/* paired with smp_store_release() in percpu_ref_reinit() */
-	unsigned long percpu_ptr = lockless_dereference(ref->percpu_count_ptr);
+	unsigned long percpu_ptr;
+
+	/*
+	 * The value of @ref->percpu_count_ptr is tested for
+	 * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then
+	 * used as a pointer.  If the compiler generates a separate fetch
+	 * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in
+	 * between contaminating the pointer value, meaning that
+	 * ACCESS_ONCE() is required when fetching it.
+	 *
+	 * Also, we need a data dependency barrier to be paired with
+	 * smp_store_release() in __percpu_ref_switch_to_percpu().
+	 *
+	 * Use lockless deref which contains both.
+	 */
+	percpu_ptr = lockless_dereference(ref->percpu_count_ptr);
 
 	/*
 	 * Theoretically, the following could test just ATOMIC; however,
@@ -233,7 +247,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 	if (__ref_is_percpu(ref, &percpu_count)) {
 		this_cpu_inc(*percpu_count);
 		ret = true;
-	} else if (!(ACCESS_ONCE(ref->percpu_count_ptr) & __PERCPU_REF_DEAD)) {
+	} else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
 		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 4c907baf36d8339f393bb576d0bab29194d0e6ad Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 6 Jan 2015 10:26:10 -0500
Subject: percpu_ref: implement percpu_ref_is_dying()

Implement percpu_ref_is_dying() which tests whether the ref is dying
or dead.  This is useful to determine the current state when a
percpu_ref is used as a cyclic on/off switch via kill and reinit.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Kent Overstreet <kmo@daterainc.com>
---
 include/linux/percpu-refcount.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include')

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 6a7a670366a..12c9b485beb 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -294,6 +294,20 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
 	percpu_ref_put_many(ref, 1);
 }
 
+/**
+ * percpu_ref_is_dying - test whether a percpu refcount is dying or dead
+ * @ref: percpu_ref to test
+ *
+ * Returns %true if @ref is dying or dead.
+ *
+ * This function is safe to call as long as @ref is between init and exit
+ * and the caller is responsible for synchronizing against state changes.
+ */
+static inline bool percpu_ref_is_dying(struct percpu_ref *ref)
+{
+	return ref->percpu_count_ptr & __PERCPU_REF_DEAD;
+}
+
 /**
  * percpu_ref_is_zero - test whether a percpu refcount reached zero
  * @ref: percpu_ref to test
-- 
cgit v1.2.3-70-g09d2


From 24dab7a7b3534ef40ecec20cfd7fb3ad99d9ff33 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 6 Jan 2015 12:02:46 -0500
Subject: cgroup: reorder SUBSYS(blkio) in cgroup_subsys.h

The scheduled cgroup writeback support requires blkio to be
initialized before memcg as memcg needs to provide certain blkcg
related functionalities.  Relocate blkio so that it's right above
memory.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup_subsys.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 98c4f9b12b0..e4a96fb1440 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -15,6 +15,10 @@ SUBSYS(cpu)
 SUBSYS(cpuacct)
 #endif
 
+#if IS_ENABLED(CONFIG_BLK_CGROUP)
+SUBSYS(blkio)
+#endif
+
 #if IS_ENABLED(CONFIG_MEMCG)
 SUBSYS(memory)
 #endif
@@ -31,10 +35,6 @@ SUBSYS(freezer)
 SUBSYS(net_cls)
 #endif
 
-#if IS_ENABLED(CONFIG_BLK_CGROUP)
-SUBSYS(blkio)
-#endif
-
 #if IS_ENABLED(CONFIG_CGROUP_PERF)
 SUBSYS(perf_event)
 #endif
-- 
cgit v1.2.3-70-g09d2


From f3ba53802eff25e3eedb60d7afe5262710e20bd5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 6 Jan 2015 12:02:46 -0500
Subject: cgroup: add dummy css_put() for !CONFIG_CGROUPS

This will later be depended upon by the scheduled cgroup writeback
support.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index da0dae0600e..b9cb94c3102 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -943,6 +943,8 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 
 #else /* !CONFIG_CGROUPS */
 
+struct cgroup_subsys_state;
+
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
 static inline void cgroup_fork(struct task_struct *p) {}
@@ -955,6 +957,8 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 	return -EINVAL;
 }
 
+static inline void css_put(struct cgroup_subsys_state *css) {}
+
 /* No cgroups - nothing to do */
 static inline int cgroup_attach_task_all(struct task_struct *from,
 					 struct task_struct *t)
-- 
cgit v1.2.3-70-g09d2


From 536fa402221f09633e7c5801b327055ab716a363 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 5 Sep 2014 11:14:48 -0700
Subject: compiler: Allow 1- and 2-byte smp_load_acquire() and
 smp_store_release()

CPUs without single-byte and double-byte loads and stores place some
"interesting" requirements on concurrent code.  For example (adapted
from Peter Hurley's test code), suppose we have the following structure:

	struct foo {
		spinlock_t lock1;
		spinlock_t lock2;
		char a; /* Protected by lock1. */
		char b; /* Protected by lock2. */
	};
	struct foo *foop;

Of course, it is common (and good) practice to place data protected
by different locks in separate cache lines.  However, if the locks are
rarely acquired (for example, only in rare error cases), and there are
a great many instances of the data structure, then memory footprint can
trump false-sharing concerns, so that it can be better to place them in
the same cache cache line as above.

But if the CPU does not support single-byte loads and stores, a store
to foop->a will do a non-atomic read-modify-write operation on foop->b,
which will come as a nasty surprise to someone holding foop->lock2.  So we
now require CPUs to support single-byte and double-byte loads and stores.
Therefore, this commit adjusts the definition of __native_word() to allow
these sizes to be used by smp_load_acquire() and smp_store_release().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
---
 include/linux/compiler.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index a1c81f80978..49811cdddaa 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -385,7 +385,7 @@ static __always_inline void __assign_once_size(volatile void *p, void *res, int
 
 /* Is this type a native word size -- useful for atomic operations */
 #ifndef __native_word
-# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+# define __native_word(t) (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 #endif
 
 /* Compile time object size, -1 for unknown */
-- 
cgit v1.2.3-70-g09d2


From ac59853c06993a442e8060bc19040b2ca3025aec Mon Sep 17 00:00:00 2001
From: Pranith Kumar <bobby.prani@gmail.com>
Date: Thu, 13 Nov 2014 14:24:14 -0500
Subject: rcupdate: Replace smp_read_barrier_depends() with
 lockless_dereference()

Recently lockless_dereference() was added which can be used in place of
hard-coding smp_read_barrier_depends(). The following PATCH makes the change.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ed4f5939a45..386ba288084 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -582,11 +582,11 @@ static inline void rcu_preempt_sleep_check(void)
 })
 #define __rcu_dereference_check(p, c, space) \
 ({ \
-	typeof(*p) *_________p1 = (typeof(*p) *__force)ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \
 	rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \
 	rcu_dereference_sparse(p, space); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
-	((typeof(*p) __force __kernel *)(_________p1)); \
+	((typeof(*p) __force __kernel *)(________p1)); \
 })
 #define __rcu_dereference_protected(p, c, space) \
 ({ \
@@ -603,10 +603,10 @@ static inline void rcu_preempt_sleep_check(void)
 })
 #define __rcu_dereference_index_check(p, c) \
 ({ \
-	typeof(p) _________p1 = ACCESS_ONCE(p); \
+	/* Dependency order vs. p above. */ \
+	typeof(p) _________p1 = lockless_dereference(p); \
 	rcu_lockdep_assert(c, \
 			   "suspicious rcu_dereference_index_check() usage"); \
-	smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
 	(_________p1); \
 })
 
-- 
cgit v1.2.3-70-g09d2


From f520c98e3e5212d8c282a86d9b7697dd70326192 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Fri, 12 Dec 2014 09:36:14 +0800
Subject: rculist: Fix sparse warning

This fixes the following sparse warnings:

make C=1 CF=-D__CHECK_ENDIAN__ net/ipv6/addrconf.o
net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces)
net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces)
net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces)
net/ipv6/addrconf.c:3495:9: error: incompatible types in comparison expression (different address spaces)

To silence these spare complaints, an RCU annotation should be added to
"next" pointer of hlist_node structure through hlist_next_rcu() macro
when iterating over a hlist with hlist_for_each_entry_continue_rcu_bh().

By the way, this commit also resolves the same error appearing in
hlist_for_each_entry_continue_rcu().

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rculist.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 529bc946f45..a18b16f1dc0 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -524,11 +524,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu(pos, member)			\
-	for (pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     pos;							\
-	     pos = hlist_entry_safe(rcu_dereference((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 /**
  * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point
@@ -536,11 +536,11 @@ static inline void hlist_add_behind_rcu(struct hlist_node *n,
  * @member:	the name of the hlist_node within the struct.
  */
 #define hlist_for_each_entry_continue_rcu_bh(pos, member)		\
-	for (pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member);			\
+	for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(  \
+			&(pos)->member)), typeof(*(pos)), member);	\
 	     pos;							\
-	     pos = hlist_entry_safe(rcu_dereference_bh((pos)->member.next),\
-			typeof(*(pos)), member))
+	     pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(	\
+			&(pos)->member)), typeof(*(pos)), member))
 
 /**
  * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point
-- 
cgit v1.2.3-70-g09d2


From a5c198f4f7da6cc48116ca239c59c9f44b753364 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 23 Nov 2014 20:30:06 -0800
Subject: rcu: Expand SRCU ->completed to 64 bits

When rcutorture used only the low-order 32 bits of the grace-period
number, it was not a problem for SRCU to use a 32-bit completed field.
However, rcutorture now uses the full 64 bits on 64-bit systems, so
this commit converts SRCU's ->completed field to unsigned long so as to
provide 64 bits on 64-bit systems.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/srcu.h | 4 ++--
 kernel/rcu/srcu.c    | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index a2783cb5d27..ef923dd9624 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -45,7 +45,7 @@ struct rcu_batch {
 #define RCU_BATCH_INIT(name) { NULL, &(name.head) }
 
 struct srcu_struct {
-	unsigned completed;
+	unsigned long completed;
 	struct srcu_struct_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
@@ -135,7 +135,7 @@ int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
 void synchronize_srcu(struct srcu_struct *sp);
 void synchronize_srcu_expedited(struct srcu_struct *sp);
-long srcu_batches_completed(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void srcu_barrier(struct srcu_struct *sp);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index e037f3eb2f7..445bf8ffe3f 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(srcu_barrier);
  * Report the number of batches, correlated with, but not necessarily
  * precisely the same as, the number of grace periods that have elapsed.
  */
-long srcu_batches_completed(struct srcu_struct *sp)
+unsigned long srcu_batches_completed(struct srcu_struct *sp)
 {
 	return sp->completed;
 }
-- 
cgit v1.2.3-70-g09d2


From 9735af5c78599703be633c057af3faee26482028 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 26 Nov 2014 10:42:50 -0800
Subject: rcu: Combine DEFINE_SRCU() and DEFINE_STATIC_SRCU()

The DEFINE_SRCU() and DEFINE_STATIC_SRCU() definitions are quite
similar, so this commit combines them, saving a bit of code and removing
redundancy.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/srcu.h | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index ef923dd9624..9cfd9623fb0 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -102,13 +102,11 @@ void process_srcu(struct work_struct *work);
  * define and init a srcu struct at build time.
  * dont't call init_srcu_struct() nor cleanup_srcu_struct() on it.
  */
-#define DEFINE_SRCU(name)						\
+#define __DEFINE_SRCU(name, is_static)					\
 	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	struct srcu_struct name = __SRCU_STRUCT_INIT(name);
-
-#define DEFINE_STATIC_SRCU(name)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	static struct srcu_struct name = __SRCU_STRUCT_INIT(name);
+	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+#define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
+#define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)
 
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
-- 
cgit v1.2.3-70-g09d2


From 8b3a38daff6f50027039d6979b9eb026907508eb Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend@broadcom.com>
Date: Tue, 23 Dec 2014 19:04:23 +0100
Subject: brcmfmac: Add support for bcm43340/1 wireless chipsets

This patch adds support for the bcm43340 and bcm43341 wireless
chipsets. These two chipsets are identical from wireless parts
perspective. As such they use the same firmware image.

Cc: Samuel Ortiz <sameo@linux.intel.com>
Cc: Rob Herring <rob.herring@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
[arend@broadcom.com: squash to single commit, remove 43341 chipid]
Reviewed-by: Pieter-Paul Giesberts <pieterpg@broadcom.com>
Reviewed-by: Hante Meuleman <meuleman@broadcom.com>
Signed-off-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c     | 2 ++
 drivers/net/wireless/brcm80211/brcmfmac/chip.c       | 1 +
 drivers/net/wireless/brcm80211/brcmfmac/sdio.c       | 5 +++++
 drivers/net/wireless/brcm80211/include/brcm_hw_ids.h | 3 +++
 include/linux/mmc/sdio_ids.h                         | 6 ++++--
 5 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
index 9880dae2a56..dffd9e44f5b 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
@@ -1005,6 +1005,8 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = {
 	BRCMF_SDIO_DEVICE(BRCM_SDIO_4329_DEVICE_ID),
 	BRCMF_SDIO_DEVICE(BRCM_SDIO_4330_DEVICE_ID),
 	BRCMF_SDIO_DEVICE(BRCM_SDIO_4334_DEVICE_ID),
+	BRCMF_SDIO_DEVICE(BRCM_SDIO_43340_DEVICE_ID),
+	BRCMF_SDIO_DEVICE(BRCM_SDIO_43341_DEVICE_ID),
 	BRCMF_SDIO_DEVICE(BRCM_SDIO_43362_DEVICE_ID),
 	BRCMF_SDIO_DEVICE(BRCM_SDIO_4335_4339_DEVICE_ID),
 	BRCMF_SDIO_DEVICE(BRCM_SDIO_4354_DEVICE_ID),
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/brcm80211/brcmfmac/chip.c
index 519b79ebaab..04d2ca0d87d 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/chip.c
@@ -481,6 +481,7 @@ static void brcmf_chip_get_raminfo(struct brcmf_chip_priv *ci)
 		ci->pub.ramsize = 0x48000;
 		break;
 	case BRCM_CC_4334_CHIP_ID:
+	case BRCM_CC_43340_CHIP_ID:
 		ci->pub.ramsize = 0x80000;
 		break;
 	case BRCM_CC_4335_CHIP_ID:
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/sdio.c
index 0b0d51a6106..551da356a5b 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/sdio.c
@@ -608,6 +608,8 @@ static const struct sdiod_drive_str sdiod_drvstr_tab2_3v3[] = {
 #define BCM4330_NVRAM_NAME		"brcm/brcmfmac4330-sdio.txt"
 #define BCM4334_FIRMWARE_NAME		"brcm/brcmfmac4334-sdio.bin"
 #define BCM4334_NVRAM_NAME		"brcm/brcmfmac4334-sdio.txt"
+#define BCM43340_FIRMWARE_NAME		"brcm/brcmfmac43340-sdio.bin"
+#define BCM43340_NVRAM_NAME		"brcm/brcmfmac43340-sdio.txt"
 #define BCM4335_FIRMWARE_NAME		"brcm/brcmfmac4335-sdio.bin"
 #define BCM4335_NVRAM_NAME		"brcm/brcmfmac4335-sdio.txt"
 #define BCM43362_FIRMWARE_NAME		"brcm/brcmfmac43362-sdio.bin"
@@ -629,6 +631,8 @@ MODULE_FIRMWARE(BCM4330_FIRMWARE_NAME);
 MODULE_FIRMWARE(BCM4330_NVRAM_NAME);
 MODULE_FIRMWARE(BCM4334_FIRMWARE_NAME);
 MODULE_FIRMWARE(BCM4334_NVRAM_NAME);
+MODULE_FIRMWARE(BCM43340_FIRMWARE_NAME);
+MODULE_FIRMWARE(BCM43340_NVRAM_NAME);
 MODULE_FIRMWARE(BCM4335_FIRMWARE_NAME);
 MODULE_FIRMWARE(BCM4335_NVRAM_NAME);
 MODULE_FIRMWARE(BCM43362_FIRMWARE_NAME);
@@ -660,6 +664,7 @@ static const struct brcmf_firmware_names brcmf_fwname_data[] = {
 	{ BRCM_CC_4329_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4329) },
 	{ BRCM_CC_4330_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4330) },
 	{ BRCM_CC_4334_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4334) },
+	{ BRCM_CC_43340_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM43340) },
 	{ BRCM_CC_4335_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4335) },
 	{ BRCM_CC_43362_CHIP_ID, 0xFFFFFFFE, BRCMF_FIRMWARE_NVRAM(BCM43362) },
 	{ BRCM_CC_4339_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4339) },
diff --git a/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h
index 6996fcc144c..00215efbc13 100644
--- a/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h
+++ b/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h
@@ -34,6 +34,7 @@
 #define BRCM_CC_4329_CHIP_ID		0x4329
 #define BRCM_CC_4330_CHIP_ID		0x4330
 #define BRCM_CC_4334_CHIP_ID		0x4334
+#define BRCM_CC_43340_CHIP_ID		43340
 #define BRCM_CC_43362_CHIP_ID		43362
 #define BRCM_CC_4335_CHIP_ID		0x4335
 #define BRCM_CC_4339_CHIP_ID		0x4339
@@ -51,6 +52,8 @@
 #define BRCM_SDIO_4329_DEVICE_ID	BRCM_CC_4329_CHIP_ID
 #define BRCM_SDIO_4330_DEVICE_ID	BRCM_CC_4330_CHIP_ID
 #define BRCM_SDIO_4334_DEVICE_ID	BRCM_CC_4334_CHIP_ID
+#define BRCM_SDIO_43340_DEVICE_ID	BRCM_CC_43340_CHIP_ID
+#define BRCM_SDIO_43341_DEVICE_ID	43341
 #define BRCM_SDIO_43362_DEVICE_ID	BRCM_CC_43362_CHIP_ID
 #define BRCM_SDIO_4335_4339_DEVICE_ID	BRCM_CC_4335_CHIP_ID
 #define BRCM_SDIO_4354_DEVICE_ID	BRCM_CC_4354_CHIP_ID
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index 0f01fe06542..99680796371 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -24,13 +24,15 @@
  * Vendors and devices.  Sort key: vendor first, device next.
  */
 #define SDIO_VENDOR_ID_BROADCOM			0x02d0
-#define SDIO_DEVICE_ID_BROADCOM_43143		43143
+#define SDIO_DEVICE_ID_BROADCOM_43143		0xa887
 #define SDIO_DEVICE_ID_BROADCOM_43241		0x4324
 #define SDIO_DEVICE_ID_BROADCOM_4329		0x4329
 #define SDIO_DEVICE_ID_BROADCOM_4330		0x4330
 #define SDIO_DEVICE_ID_BROADCOM_4334		0x4334
+#define SDIO_DEVICE_ID_BROADCOM_43340		0xa94c
+#define SDIO_DEVICE_ID_BROADCOM_43341		0xa94d
 #define SDIO_DEVICE_ID_BROADCOM_4335_4339	0x4335
-#define SDIO_DEVICE_ID_BROADCOM_43362		43362
+#define SDIO_DEVICE_ID_BROADCOM_43362		0xa962
 #define SDIO_DEVICE_ID_BROADCOM_4354		0x4354
 
 #define SDIO_VENDOR_ID_INTEL			0x0089
-- 
cgit v1.2.3-70-g09d2


From 2f4383667d57d1c719070db86b14277277752841 Mon Sep 17 00:00:00 2001
From: Ed Swierk <eswierk@skyportsystems.com>
Date: Fri, 2 Jan 2015 17:27:56 -0800
Subject: ethtool: Extend ethtool plugin module eeprom API to phylib

This patch extends the ethtool plugin module eeprom API to support cards
whose phy support is delegated to a separate driver.

The handlers for ETHTOOL_GMODULEINFO and ETHTOOL_GMODULEEEPROM call the
module_info and module_eeprom functions if the phy driver provides them;
otherwise the handlers call the equivalent ethtool_ops functions provided
by network drivers with built-in phy support.

Signed-off-by: Ed Swierk <eswierk@skyportsystems.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h |  9 +++++++++
 net/core/ethtool.c  | 45 ++++++++++++++++++++++++++++++++++-----------
 2 files changed, 43 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 22af8f8f580..9c189a1fa3a 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -565,6 +565,15 @@ struct phy_driver {
 	void (*write_mmd_indirect)(struct phy_device *dev, int ptrad,
 				   int devnum, int regnum, u32 val);
 
+	/* Get the size and type of the eeprom contained within a plug-in
+	 * module */
+	int (*module_info)(struct phy_device *dev,
+			   struct ethtool_modinfo *modinfo);
+
+	/* Get the eeprom information from the plug-in module */
+	int (*module_eeprom)(struct phy_device *dev,
+			     struct ethtool_eeprom *ee, u8 *data);
+
 	struct device_driver driver;
 };
 #define to_phy_driver(d) container_of(d, struct phy_driver, driver)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 550892cd6b3..91f74f3eb20 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1597,20 +1597,31 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr)
 	return err;
 }
 
+static int __ethtool_get_module_info(struct net_device *dev,
+				     struct ethtool_modinfo *modinfo)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct phy_device *phydev = dev->phydev;
+
+	if (phydev && phydev->drv && phydev->drv->module_info)
+		return phydev->drv->module_info(phydev, modinfo);
+
+	if (ops->get_module_info)
+		return ops->get_module_info(dev, modinfo);
+
+	return -EOPNOTSUPP;
+}
+
 static int ethtool_get_module_info(struct net_device *dev,
 				   void __user *useraddr)
 {
 	int ret;
 	struct ethtool_modinfo modinfo;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-
-	if (!ops->get_module_info)
-		return -EOPNOTSUPP;
 
 	if (copy_from_user(&modinfo, useraddr, sizeof(modinfo)))
 		return -EFAULT;
 
-	ret = ops->get_module_info(dev, &modinfo);
+	ret = __ethtool_get_module_info(dev, &modinfo);
 	if (ret)
 		return ret;
 
@@ -1620,21 +1631,33 @@ static int ethtool_get_module_info(struct net_device *dev,
 	return 0;
 }
 
+static int __ethtool_get_module_eeprom(struct net_device *dev,
+				       struct ethtool_eeprom *ee, u8 *data)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct phy_device *phydev = dev->phydev;
+
+	if (phydev && phydev->drv && phydev->drv->module_eeprom)
+		return phydev->drv->module_eeprom(phydev, ee, data);
+
+	if (ops->get_module_eeprom)
+		return ops->get_module_eeprom(dev, ee, data);
+
+	return -EOPNOTSUPP;
+}
+
 static int ethtool_get_module_eeprom(struct net_device *dev,
 				     void __user *useraddr)
 {
 	int ret;
 	struct ethtool_modinfo modinfo;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-
-	if (!ops->get_module_info || !ops->get_module_eeprom)
-		return -EOPNOTSUPP;
 
-	ret = ops->get_module_info(dev, &modinfo);
+	ret = __ethtool_get_module_info(dev, &modinfo);
 	if (ret)
 		return ret;
 
-	return ethtool_get_any_eeprom(dev, useraddr, ops->get_module_eeprom,
+	return ethtool_get_any_eeprom(dev, useraddr,
+				      __ethtool_get_module_eeprom,
 				      modinfo.eeprom_len);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 9da7dae94fb8adab5cc5f395640e30736a66e910 Mon Sep 17 00:00:00 2001
From: Valentin Rothberg <valentinrothberg@gmail.com>
Date: Tue, 6 Jan 2015 17:29:29 +0100
Subject: workqueue.h: remove loops of single statement macros

checkpatch.pl complained about two single statement macros in
do while (0) loops.  The loops and the trailing semicolons are
now removed, which makes checkpatch happy and the two macros
consistent with the rest of the file.

Signed-off-by: Valentin Rothberg <valentinrothberg@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/workqueue.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index b996e6cde6b..74db135f995 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -220,14 +220,10 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
 #endif
 
 #define INIT_WORK(_work, _func)						\
-	do {								\
-		__INIT_WORK((_work), (_func), 0);			\
-	} while (0)
+	__INIT_WORK((_work), (_func), 0)
 
 #define INIT_WORK_ONSTACK(_work, _func)					\
-	do {								\
-		__INIT_WORK((_work), (_func), 1);			\
-	} while (0)
+	__INIT_WORK((_work), (_func), 1)
 
 #define __INIT_DELAYED_WORK(_work, _func, _tflags)			\
 	do {								\
-- 
cgit v1.2.3-70-g09d2


From db12847ca84b7a315a3ba77c939c9d08df17d54f Mon Sep 17 00:00:00 2001
From: Ido Yariv <ido@wizery.com>
Date: Tue, 6 Jan 2015 08:39:02 -0500
Subject: mac80211: Re-fix accounting of the tailroom-needed counter

When hw acceleration is enabled, the GENERATE_IV or PUT_IV_SPACE flags
only require headroom space. Therefore, the tailroom-needed counter can
safely be decremented for most drivers.

The older incarnation of this patch (ca34e3b5) assumed that the above
holds true for all drivers. As reported by Christopher Chavez and
researched by Christian Lamparter and Larry Finger, this isn't a valid
assumption for p54 and cw1200.

Drivers that still require tailroom for ICV/MIC even when HW encryption
is enabled can use IEEE80211_KEY_FLAG_RESERVE_TAILROOM to indicate it.

Signed-off-by: Ido Yariv <idox.yariv@intel.com>
Cc: Christopher Chavez <chrischavez@gmx.us>
Cc: Christian Lamparter <chunkeey@googlemail.com>
Cc: Larry Finger <Larry.Finger@lwfinger.net>
Cc: Solomon Peachy <pizza@shaftnet.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/cw1200/sta.c |  3 ++-
 drivers/net/wireless/p54/main.c   |  2 ++
 include/net/mac80211.h            | 11 +++++++++--
 net/mac80211/key.c                |  9 +++------
 4 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/cw1200/sta.c b/drivers/net/wireless/cw1200/sta.c
index a1e3237c0be..4a47c7f8a24 100644
--- a/drivers/net/wireless/cw1200/sta.c
+++ b/drivers/net/wireless/cw1200/sta.c
@@ -709,7 +709,8 @@ int cw1200_set_key(struct ieee80211_hw *dev, enum set_key_cmd cmd,
 		if (sta)
 			peer_addr = sta->addr;
 
-		key->flags |= IEEE80211_KEY_FLAG_PUT_IV_SPACE;
+		key->flags |= IEEE80211_KEY_FLAG_PUT_IV_SPACE |
+			      IEEE80211_KEY_FLAG_RESERVE_TAILROOM;
 
 		switch (key->cipher) {
 		case WLAN_CIPHER_SUITE_WEP40:
diff --git a/drivers/net/wireless/p54/main.c b/drivers/net/wireless/p54/main.c
index 97aeff0edb8..13a30c4a27f 100644
--- a/drivers/net/wireless/p54/main.c
+++ b/drivers/net/wireless/p54/main.c
@@ -575,6 +575,8 @@ static int p54_set_key(struct ieee80211_hw *dev, enum set_key_cmd cmd,
 			key->hw_key_idx = 0xff;
 			goto out_unlock;
 		}
+
+		key->flags |= IEEE80211_KEY_FLAG_RESERVE_TAILROOM;
 	} else {
 		slot = key->hw_key_idx;
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ece1a546587..555a845ad51 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1281,7 +1281,8 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  *
  * @IEEE80211_KEY_FLAG_GENERATE_IV: This flag should be set by the
  *	driver to indicate that it requires IV generation for this
- *	particular key.
+ *	particular key. Setting this flag does not necessarily mean that SKBs
+ *	will have sufficient tailroom for ICV or MIC.
  * @IEEE80211_KEY_FLAG_GENERATE_MMIC: This flag should be set by
  *	the driver for a TKIP key if it requires Michael MIC
  *	generation in software.
@@ -1293,7 +1294,9 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver
  *	if space should be prepared for the IV, but the IV
  *	itself should not be generated. Do not set together with
- *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key.
+ *	@IEEE80211_KEY_FLAG_GENERATE_IV on the same key. Setting this flag does
+ *	not necessarily mean that SKBs will have sufficient tailroom for ICV or
+ *	MIC.
  * @IEEE80211_KEY_FLAG_RX_MGMT: This key will be used to decrypt received
  *	management frames. The flag can help drivers that have a hardware
  *	crypto implementation that doesn't deal with management frames
@@ -1304,6 +1307,9 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  * @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the
  *	driver for a CCMP key to indicate that is requires IV generation
  *	only for managment frames (MFP).
+ * @IEEE80211_KEY_FLAG_RESERVE_TAILROOM: This flag should be set by the
+ *	driver for a key to indicate that sufficient tailroom must always
+ *	be reserved for ICV or MIC, even when HW encryption is enabled.
  */
 enum ieee80211_key_flags {
 	IEEE80211_KEY_FLAG_GENERATE_IV_MGMT	= BIT(0),
@@ -1313,6 +1319,7 @@ enum ieee80211_key_flags {
 	IEEE80211_KEY_FLAG_SW_MGMT_TX		= BIT(4),
 	IEEE80211_KEY_FLAG_PUT_IV_SPACE		= BIT(5),
 	IEEE80211_KEY_FLAG_RX_MGMT		= BIT(6),
+	IEEE80211_KEY_FLAG_RESERVE_TAILROOM	= BIT(7),
 };
 
 /**
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index bd4e46ec32b..f8d9f0ee59b 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -141,8 +141,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 		key->flags |= KEY_FLAG_UPLOADED_TO_HARDWARE;
 
 		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
+		      (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
 			sdata->crypto_tx_tailroom_needed_cnt--;
 
 		WARN_ON((key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
@@ -191,8 +190,7 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
 	sdata = key->sdata;
 
 	if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-	      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
-	      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
+	      (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
 		increment_tailroom_need_count(sdata);
 
 	ret = drv_set_key(key->local, DISABLE_KEY, sdata,
@@ -889,8 +887,7 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf)
 		key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
 
 		if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV) ||
-		      (key->conf.flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)))
+		      (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM)))
 			increment_tailroom_need_count(key->sdata);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 6ada1fc0e1c4775de0e043e1bd3ae9d065491aa5 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Wed, 3 Dec 2014 19:22:48 -0500
Subject: time: settimeofday: Validate the values of tv from user

An unvalidated user input is multiplied by a constant, which can result in
an undefined behaviour for large values. While this is validated later,
we should avoid triggering undefined behaviour.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
[jstultz: include trivial milisecond->microsecond correction noticed
by Andy]
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/time.h | 13 +++++++++++++
 kernel/time/time.c   |  4 ++++
 2 files changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index 8c42cf8d244..5989b0ead1e 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -99,6 +99,19 @@ static inline bool timespec_valid_strict(const struct timespec *ts)
 	return true;
 }
 
+static inline bool timeval_valid(const struct timeval *tv)
+{
+	/* Dates before 1970 are bogus */
+	if (tv->tv_sec < 0)
+		return false;
+
+	/* Can't have more microseconds then a second */
+	if (tv->tv_usec < 0 || tv->tv_usec >= USEC_PER_SEC)
+		return false;
+
+	return true;
+}
+
 extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
 
 #define CURRENT_TIME		(current_kernel_time())
diff --git a/kernel/time/time.c b/kernel/time/time.c
index a9ae20fb0b1..22d5d3b7397 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -196,6 +196,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
 	if (tv) {
 		if (copy_from_user(&user_tv, tv, sizeof(*tv)))
 			return -EFAULT;
+
+		if (!timeval_valid(&user_tv))
+			return -EINVAL;
+
 		new_ts.tv_sec = user_tv.tv_sec;
 		new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
 	}
-- 
cgit v1.2.3-70-g09d2


From ce64c8b9cf5be2a93508af4667110dbe90904557 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 6 Jan 2015 15:17:20 +0100
Subject: ASoC: Add helper function for changing the DAI link format

For some setups it is necessary to change the DAI link format at runtime.
This patch factors out the code that does the initial static DAI link format
configuration into a separate helper function which can be used board
drivers as well.

This allows board drivers that have to change the DAI link format at runtime
to reuse it instead of having to manually change the format on all DAIs.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |   3 ++
 sound/soc/soc-core.c | 125 ++++++++++++++++++++++++++++-----------------------
 2 files changed, 72 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index b4fca9aed2a..edd4a0a11cc 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -429,6 +429,9 @@ bool snd_soc_runtime_ignore_pmdown_time(struct snd_soc_pcm_runtime *rtd);
 void snd_soc_runtime_activate(struct snd_soc_pcm_runtime *rtd, int stream);
 void snd_soc_runtime_deactivate(struct snd_soc_pcm_runtime *rtd, int stream);
 
+int snd_soc_runtime_set_dai_fmt(struct snd_soc_pcm_runtime *rtd,
+	unsigned int dai_fmt);
+
 /* Utility functions to get clock rates from various things */
 int snd_soc_calc_frame_size(int sample_size, int channels, int tdm_slots);
 int snd_soc_params_to_frame_size(struct snd_pcm_hw_params *params);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 985052b3fbe..80ea358d3ad 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1427,11 +1427,75 @@ static int snd_soc_init_codec_cache(struct snd_soc_codec *codec)
 	return 0;
 }
 
+/**
+ * snd_soc_runtime_set_dai_fmt() - Change DAI link format for a ASoC runtime
+ * @rtd: The runtime for which the DAI link format should be changed
+ * @dai_fmt: The new DAI link format
+ *
+ * This function updates the DAI link format for all DAIs connected to the DAI
+ * link for the specified runtime.
+ *
+ * Note: For setups with a static format set the dai_fmt field in the
+ * corresponding snd_dai_link struct instead of using this function.
+ *
+ * Returns 0 on success, otherwise a negative error code.
+ */
+int snd_soc_runtime_set_dai_fmt(struct snd_soc_pcm_runtime *rtd,
+	unsigned int dai_fmt)
+{
+	struct snd_soc_dai **codec_dais = rtd->codec_dais;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < rtd->num_codecs; i++) {
+		struct snd_soc_dai *codec_dai = codec_dais[i];
+
+		ret = snd_soc_dai_set_fmt(codec_dai, dai_fmt);
+		if (ret != 0 && ret != -ENOTSUPP) {
+			dev_warn(codec_dai->dev,
+				 "ASoC: Failed to set DAI format: %d\n", ret);
+			return ret;
+		}
+	}
+
+	/* Flip the polarity for the "CPU" end of a CODEC<->CODEC link */
+	if (cpu_dai->codec) {
+		unsigned int inv_dai_fmt;
+
+		inv_dai_fmt = dai_fmt & ~SND_SOC_DAIFMT_MASTER_MASK;
+		switch (dai_fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+		case SND_SOC_DAIFMT_CBM_CFM:
+			inv_dai_fmt |= SND_SOC_DAIFMT_CBS_CFS;
+			break;
+		case SND_SOC_DAIFMT_CBM_CFS:
+			inv_dai_fmt |= SND_SOC_DAIFMT_CBS_CFM;
+			break;
+		case SND_SOC_DAIFMT_CBS_CFM:
+			inv_dai_fmt |= SND_SOC_DAIFMT_CBM_CFS;
+			break;
+		case SND_SOC_DAIFMT_CBS_CFS:
+			inv_dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
+			break;
+		}
+
+		dai_fmt = inv_dai_fmt;
+	}
+
+	ret = snd_soc_dai_set_fmt(cpu_dai, dai_fmt);
+	if (ret != 0 && ret != -ENOTSUPP) {
+		dev_warn(cpu_dai->dev,
+			 "ASoC: Failed to set DAI format: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int snd_soc_instantiate_card(struct snd_soc_card *card)
 {
 	struct snd_soc_codec *codec;
-	struct snd_soc_dai_link *dai_link;
-	int ret, i, order, dai_fmt;
+	int ret, i, order;
 
 	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_INIT);
 
@@ -1542,60 +1606,9 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 					card->num_dapm_routes);
 
 	for (i = 0; i < card->num_links; i++) {
-		struct snd_soc_pcm_runtime *rtd = &card->rtd[i];
-		dai_link = &card->dai_link[i];
-		dai_fmt = dai_link->dai_fmt;
-
-		if (dai_fmt) {
-			struct snd_soc_dai **codec_dais = rtd->codec_dais;
-			int j;
-
-			for (j = 0; j < rtd->num_codecs; j++) {
-				struct snd_soc_dai *codec_dai = codec_dais[j];
-
-				ret = snd_soc_dai_set_fmt(codec_dai, dai_fmt);
-				if (ret != 0 && ret != -ENOTSUPP)
-					dev_warn(codec_dai->dev,
-						 "ASoC: Failed to set DAI format: %d\n",
-						 ret);
-			}
-		}
-
-		/* If this is a regular CPU link there will be a platform */
-		if (dai_fmt &&
-		    (dai_link->platform_name || dai_link->platform_of_node)) {
-			ret = snd_soc_dai_set_fmt(card->rtd[i].cpu_dai,
-						  dai_fmt);
-			if (ret != 0 && ret != -ENOTSUPP)
-				dev_warn(card->rtd[i].cpu_dai->dev,
-					 "ASoC: Failed to set DAI format: %d\n",
-					 ret);
-		} else if (dai_fmt) {
-			/* Flip the polarity for the "CPU" end */
-			dai_fmt &= ~SND_SOC_DAIFMT_MASTER_MASK;
-			switch (dai_link->dai_fmt &
-				SND_SOC_DAIFMT_MASTER_MASK) {
-			case SND_SOC_DAIFMT_CBM_CFM:
-				dai_fmt |= SND_SOC_DAIFMT_CBS_CFS;
-				break;
-			case SND_SOC_DAIFMT_CBM_CFS:
-				dai_fmt |= SND_SOC_DAIFMT_CBS_CFM;
-				break;
-			case SND_SOC_DAIFMT_CBS_CFM:
-				dai_fmt |= SND_SOC_DAIFMT_CBM_CFS;
-				break;
-			case SND_SOC_DAIFMT_CBS_CFS:
-				dai_fmt |= SND_SOC_DAIFMT_CBM_CFM;
-				break;
-			}
-
-			ret = snd_soc_dai_set_fmt(card->rtd[i].cpu_dai,
-						  dai_fmt);
-			if (ret != 0 && ret != -ENOTSUPP)
-				dev_warn(card->rtd[i].cpu_dai->dev,
-					 "ASoC: Failed to set DAI format: %d\n",
-					 ret);
-		}
+		if (card->dai_link[i].dai_fmt)
+			snd_soc_runtime_set_dai_fmt(&card->rtd[i],
+				card->dai_link[i].dai_fmt);
 	}
 
 	snprintf(card->snd_card->shortname, sizeof(card->snd_card->shortname),
-- 
cgit v1.2.3-70-g09d2


From 26e022727f5e88c6e5054e14d954425deacbe56a Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 18 Dec 2014 16:02:17 +0100
Subject: efi: Rename efi_guid_unparse to efi_guid_to_str

Call it what it does - "unparse" is plain-misleading.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
---
 block/partitions/efi.c         | 2 +-
 drivers/firmware/efi/efi.c     | 4 ++--
 drivers/firmware/efi/efivars.c | 6 +++---
 fs/efivarfs/super.c            | 2 +-
 include/linux/efi.h            | 2 +-
 5 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index 56d08fd75b1..26cb624ace0 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -715,7 +715,7 @@ int efi_partition(struct parsed_partitions *state)
 			state->parts[i + 1].flags = ADDPART_FLAG_RAID;
 
 		info = &state->parts[i + 1].info;
-		efi_guid_unparse(&ptes[i].unique_partition_guid, info->uuid);
+		efi_guid_to_str(&ptes[i].unique_partition_guid, info->uuid);
 
 		/* Naively convert UTF16-LE to 7 bits. */
 		label_max = min(ARRAY_SIZE(info->volname) - 1,
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 8590099ac14..ff0bbe383b3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -272,10 +272,10 @@ static __init int match_config_table(efi_guid_t *guid,
 	int i;
 
 	if (table_types) {
-		efi_guid_unparse(guid, str);
+		efi_guid_to_str(guid, str);
 
 		for (i = 0; efi_guidcmp(table_types[i].guid, NULL_GUID); i++) {
-			efi_guid_unparse(&table_types[i].guid, str);
+			efi_guid_to_str(&table_types[i].guid, str);
 
 			if (!efi_guidcmp(*guid, table_types[i].guid)) {
 				*(table_types[i].ptr) = table;
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index f256ecd8a17..7b2e0496e0c 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -39,7 +39,7 @@
  *   fix locking per Peter Chubb's findings
  *
  *  25 Mar 2002 - Matt Domsch <Matt_Domsch@dell.com>
- *   move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_unparse()
+ *   move uuid_unparse() to include/asm-ia64/efi.h:efi_guid_to_str()
  *
  *  12 Feb 2002 - Matt Domsch <Matt_Domsch@dell.com>
  *   use list_for_each_safe when deleting vars.
@@ -128,7 +128,7 @@ efivar_guid_read(struct efivar_entry *entry, char *buf)
 	if (!entry || !buf)
 		return 0;
 
-	efi_guid_unparse(&var->VendorGuid, str);
+	efi_guid_to_str(&var->VendorGuid, str);
 	str += strlen(str);
 	str += sprintf(str, "\n");
 
@@ -569,7 +569,7 @@ efivar_create_sysfs_entry(struct efivar_entry *new_var)
 	   private variables from another's.         */
 
 	*(short_name + strlen(short_name)) = '-';
-	efi_guid_unparse(&new_var->var.VendorGuid,
+	efi_guid_to_str(&new_var->var.VendorGuid,
 			 short_name + strlen(short_name));
 
 	new_var->kobj.kset = efivars_kset;
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 6dad1176ec5..ddbce42548c 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -140,7 +140,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 	name[len] = '-';
 
-	efi_guid_unparse(&entry->var.VendorGuid, name + len + 1);
+	efi_guid_to_str(&entry->var.VendorGuid, name + len + 1);
 
 	name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 0949f9c7e87..d762c81e62a 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -844,7 +844,7 @@ efi_guidcmp (efi_guid_t left, efi_guid_t right)
 }
 
 static inline char *
-efi_guid_unparse(efi_guid_t *guid, char *out)
+efi_guid_to_str(efi_guid_t *guid, char *out)
 {
 	sprintf(out, "%pUl", guid->b);
         return out;
-- 
cgit v1.2.3-70-g09d2


From ae406bd0572be97a46d72e8a5e97c33c3168388c Mon Sep 17 00:00:00 2001
From: Kristian Evensen <kristian.evensen@gmail.com>
Date: Wed, 24 Dec 2014 09:57:11 +0100
Subject: netfilter: conntrack: Remove nf_ct_conntrack_flush_report

The only user of nf_ct_conntrack_flush_report() was ctnetlink_del_conntrack().
After adding support for flushing connections with a given mark, this function
is no longer called.

Signed-off-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack.h | 2 --
 net/netfilter/nf_conntrack_core.c    | 6 ------
 2 files changed, 8 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index f0daed2b54d..74f271a172d 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -191,8 +191,6 @@ __nf_conntrack_find(struct net *net, u16 zone,
 int nf_conntrack_hash_check_insert(struct nf_conn *ct);
 bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report);
 
-void nf_conntrack_flush_report(struct net *net, u32 portid, int report);
-
 bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 		       u_int16_t l3num, struct nf_conntrack_tuple *tuple);
 bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index da58cd4f2cb..5a6990bc5a5 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1426,12 +1426,6 @@ void nf_ct_free_hashtable(void *hash, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
 
-void nf_conntrack_flush_report(struct net *net, u32 portid, int report)
-{
-	nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report);
-}
-EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
-
 static int untrack_refs(void)
 {
 	int cnt = 0, cpu;
-- 
cgit v1.2.3-70-g09d2


From 4ed20bebf51578229a1986efcf46344075ec8447 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 14 Nov 2014 16:35:34 +0100
Subject: cfg80211: remove "channel" from survey names

All of the survey data is (currently) per channel anyway,
so having the word "channel" in the name does nothing. In
the next patch I'll introduce global data to the survey,
where the word "channel" is actually confusing.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath10k/wmi.c         |  8 ++---
 drivers/net/wireless/ath/ath5k/mac80211-ops.c | 16 +++++-----
 drivers/net/wireless/ath/ath9k/link.c         | 16 +++++-----
 drivers/net/wireless/ath/carl9170/cmd.c       | 12 ++++----
 drivers/net/wireless/ath/carl9170/main.c      |  6 ++--
 drivers/net/wireless/mwifiex/cfg80211.c       |  7 +++--
 drivers/net/wireless/mwl8k.c                  | 12 ++++----
 drivers/net/wireless/p54/eeprom.c             |  6 ++--
 drivers/net/wireless/p54/main.c               |  8 ++---
 drivers/net/wireless/p54/txrx.c               | 12 ++++----
 drivers/net/wireless/rt2x00/rt2800lib.c       | 12 ++++----
 include/net/cfg80211.h                        | 44 +++++++++++++--------------
 include/uapi/linux/nl80211.h                  | 27 ++++++++++------
 net/mac80211/ethtool.c                        | 20 ++++++------
 net/wireless/nl80211.c                        | 30 +++++++++---------
 net/wireless/trace.h                          | 26 ++++++++--------
 16 files changed, 135 insertions(+), 127 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index c0f3e4d0926..721631c3dd3 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -1344,11 +1344,11 @@ static void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb)
 		rx_clear_count -= ar->survey_last_rx_clear_count;
 
 		survey = &ar->survey[idx];
-		survey->channel_time = WMI_CHAN_INFO_MSEC(cycle_count);
-		survey->channel_time_rx = WMI_CHAN_INFO_MSEC(rx_clear_count);
+		survey->time = WMI_CHAN_INFO_MSEC(cycle_count);
+		survey->time_rx = WMI_CHAN_INFO_MSEC(rx_clear_count);
 		survey->noise = noise_floor;
-		survey->filled = SURVEY_INFO_CHANNEL_TIME |
-				 SURVEY_INFO_CHANNEL_TIME_RX |
+		survey->filled = SURVEY_INFO_TIME |
+				 SURVEY_INFO_TIME_RX |
 				 SURVEY_INFO_NOISE_DBM;
 	}
 
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index 19eab2a69ad..3b4a6463d87 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -672,10 +672,10 @@ ath5k_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey)
 	spin_lock_bh(&common->cc_lock);
 	ath_hw_cycle_counters_update(common);
 	if (cc->cycles > 0) {
-		ah->survey.channel_time += cc->cycles / div;
-		ah->survey.channel_time_busy += cc->rx_busy / div;
-		ah->survey.channel_time_rx += cc->rx_frame / div;
-		ah->survey.channel_time_tx += cc->tx_frame / div;
+		ah->survey.time += cc->cycles / div;
+		ah->survey.time_busy += cc->rx_busy / div;
+		ah->survey.time_rx += cc->rx_frame / div;
+		ah->survey.time_tx += cc->tx_frame / div;
 	}
 	memset(cc, 0, sizeof(*cc));
 	spin_unlock_bh(&common->cc_lock);
@@ -686,10 +686,10 @@ ath5k_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey)
 	survey->noise = ah->ah_noise_floor;
 	survey->filled = SURVEY_INFO_NOISE_DBM |
 			SURVEY_INFO_IN_USE |
-			SURVEY_INFO_CHANNEL_TIME |
-			SURVEY_INFO_CHANNEL_TIME_BUSY |
-			SURVEY_INFO_CHANNEL_TIME_RX |
-			SURVEY_INFO_CHANNEL_TIME_TX;
+			SURVEY_INFO_TIME |
+			SURVEY_INFO_TIME_BUSY |
+			SURVEY_INFO_TIME_RX |
+			SURVEY_INFO_TIME_TX;
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/ath9k/link.c b/drivers/net/wireless/ath/ath9k/link.c
index b829263e3d0..90631d768a6 100644
--- a/drivers/net/wireless/ath/ath9k/link.c
+++ b/drivers/net/wireless/ath/ath9k/link.c
@@ -516,14 +516,14 @@ int ath_update_survey_stats(struct ath_softc *sc)
 		ath_hw_cycle_counters_update(common);
 
 	if (cc->cycles > 0) {
-		survey->filled |= SURVEY_INFO_CHANNEL_TIME |
-			SURVEY_INFO_CHANNEL_TIME_BUSY |
-			SURVEY_INFO_CHANNEL_TIME_RX |
-			SURVEY_INFO_CHANNEL_TIME_TX;
-		survey->channel_time += cc->cycles / div;
-		survey->channel_time_busy += cc->rx_busy / div;
-		survey->channel_time_rx += cc->rx_frame / div;
-		survey->channel_time_tx += cc->tx_frame / div;
+		survey->filled |= SURVEY_INFO_TIME |
+			SURVEY_INFO_TIME_BUSY |
+			SURVEY_INFO_TIME_RX |
+			SURVEY_INFO_TIME_TX;
+		survey->time += cc->cycles / div;
+		survey->time_busy += cc->rx_busy / div;
+		survey->time_rx += cc->rx_frame / div;
+		survey->time_tx += cc->tx_frame / div;
 	}
 
 	if (cc->cycles < div)
diff --git a/drivers/net/wireless/ath/carl9170/cmd.c b/drivers/net/wireless/ath/carl9170/cmd.c
index 39a63874b27..f2b4f537e4c 100644
--- a/drivers/net/wireless/ath/carl9170/cmd.c
+++ b/drivers/net/wireless/ath/carl9170/cmd.c
@@ -188,12 +188,12 @@ int carl9170_collect_tally(struct ar9170 *ar)
 
 		if (ar->channel) {
 			info = &ar->survey[ar->channel->hw_value];
-			info->channel_time = ar->tally.active;
-			info->channel_time_busy = ar->tally.cca;
-			info->channel_time_tx = ar->tally.tx_time;
-			do_div(info->channel_time, 1000);
-			do_div(info->channel_time_busy, 1000);
-			do_div(info->channel_time_tx, 1000);
+			info->time = ar->tally.active;
+			info->time_busy = ar->tally.cca;
+			info->time_tx = ar->tally.tx_time;
+			do_div(info->time, 1000);
+			do_div(info->time_busy, 1000);
+			do_div(info->time_tx, 1000);
 		}
 	}
 	return 0;
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index ef5b6dc7b7f..f1455a04cb6 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -1690,9 +1690,9 @@ found:
 		survey->filled |= SURVEY_INFO_IN_USE;
 
 	if (ar->fw.hw_counters) {
-		survey->filled |= SURVEY_INFO_CHANNEL_TIME |
-				  SURVEY_INFO_CHANNEL_TIME_BUSY |
-				  SURVEY_INFO_CHANNEL_TIME_TX;
+		survey->filled |= SURVEY_INFO_TIME |
+				  SURVEY_INFO_TIME_BUSY |
+				  SURVEY_INFO_TIME_TX;
 	}
 
 	return 0;
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 4a66a655536..8bd446b6965 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -1037,10 +1037,11 @@ mwifiex_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *dev,
 	survey->channel = ieee80211_get_channel(wiphy,
 	    ieee80211_channel_to_frequency(pchan_stats[idx].chan_num, band));
 	survey->filled = SURVEY_INFO_NOISE_DBM |
-		SURVEY_INFO_CHANNEL_TIME | SURVEY_INFO_CHANNEL_TIME_BUSY;
+			 SURVEY_INFO_TIME |
+			 SURVEY_INFO_TIME_BUSY;
 	survey->noise = pchan_stats[idx].noise;
-	survey->channel_time = pchan_stats[idx].cca_scan_dur;
-	survey->channel_time_busy = pchan_stats[idx].cca_busy_dur;
+	survey->time = pchan_stats[idx].cca_scan_dur;
+	survey->time_busy = pchan_stats[idx].cca_busy_dur;
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c
index b8d1e04aa9b..f9b1218c761 100644
--- a/drivers/net/wireless/mwl8k.c
+++ b/drivers/net/wireless/mwl8k.c
@@ -3098,14 +3098,14 @@ static void mwl8k_update_survey(struct mwl8k_priv *priv,
 
 	cca_cnt = ioread32(priv->regs + NOK_CCA_CNT_REG);
 	cca_cnt /= 1000; /* uSecs to mSecs */
-	survey->channel_time_busy = (u64) cca_cnt;
+	survey->time_busy = (u64) cca_cnt;
 
 	rx_rdy = ioread32(priv->regs + BBU_RXRDY_CNT_REG);
 	rx_rdy /= 1000; /* uSecs to mSecs */
-	survey->channel_time_rx = (u64) rx_rdy;
+	survey->time_rx = (u64) rx_rdy;
 
 	priv->channel_time = jiffies - priv->channel_time;
-	survey->channel_time = jiffies_to_msecs(priv->channel_time);
+	survey->time = jiffies_to_msecs(priv->channel_time);
 
 	survey->channel = channel;
 
@@ -3115,9 +3115,9 @@ static void mwl8k_update_survey(struct mwl8k_priv *priv,
 	survey->noise = nf * -1;
 
 	survey->filled = SURVEY_INFO_NOISE_DBM |
-			 SURVEY_INFO_CHANNEL_TIME |
-			 SURVEY_INFO_CHANNEL_TIME_BUSY |
-			 SURVEY_INFO_CHANNEL_TIME_RX;
+			 SURVEY_INFO_TIME |
+			 SURVEY_INFO_TIME_BUSY |
+			 SURVEY_INFO_TIME_RX;
 }
 
 /*
diff --git a/drivers/net/wireless/p54/eeprom.c b/drivers/net/wireless/p54/eeprom.c
index 0fe67d2da20..2fe713eda7a 100644
--- a/drivers/net/wireless/p54/eeprom.c
+++ b/drivers/net/wireless/p54/eeprom.c
@@ -196,9 +196,9 @@ static int p54_generate_band(struct ieee80211_hw *dev,
 		dest->max_power = chan->max_power;
 		priv->survey[*chan_num].channel = &tmp->channels[j];
 		priv->survey[*chan_num].filled = SURVEY_INFO_NOISE_DBM |
-			SURVEY_INFO_CHANNEL_TIME |
-			SURVEY_INFO_CHANNEL_TIME_BUSY |
-			SURVEY_INFO_CHANNEL_TIME_TX;
+			SURVEY_INFO_TIME |
+			SURVEY_INFO_TIME_BUSY |
+			SURVEY_INFO_TIME_TX;
 		dest->hw_value = (*chan_num);
 		j++;
 		(*chan_num)++;
diff --git a/drivers/net/wireless/p54/main.c b/drivers/net/wireless/p54/main.c
index 13a30c4a27f..b9250d75d25 100644
--- a/drivers/net/wireless/p54/main.c
+++ b/drivers/net/wireless/p54/main.c
@@ -305,9 +305,9 @@ static void p54_reset_stats(struct p54_common *priv)
 		struct survey_info *info = &priv->survey[chan->hw_value];
 
 		/* only reset channel statistics, don't touch .filled, etc. */
-		info->channel_time = 0;
-		info->channel_time_busy = 0;
-		info->channel_time_tx = 0;
+		info->time = 0;
+		info->time_busy = 0;
+		info->time_tx = 0;
 	}
 
 	priv->update_stats = true;
@@ -636,7 +636,7 @@ static int p54_get_survey(struct ieee80211_hw *dev, int idx,
 
 		if (in_use) {
 			/* test if the reported statistics are valid. */
-			if  (survey->channel_time != 0) {
+			if  (survey->time != 0) {
 				survey->filled |= SURVEY_INFO_IN_USE;
 			} else {
 				/*
diff --git a/drivers/net/wireless/p54/txrx.c b/drivers/net/wireless/p54/txrx.c
index 153c61539ec..24e5ff9a927 100644
--- a/drivers/net/wireless/p54/txrx.c
+++ b/drivers/net/wireless/p54/txrx.c
@@ -587,13 +587,13 @@ static void p54_rx_stats(struct p54_common *priv, struct sk_buff *skb)
 	if (chan) {
 		struct survey_info *survey = &priv->survey[chan->hw_value];
 		survey->noise = clamp(priv->noise, -128, 127);
-		survey->channel_time = priv->survey_raw.active;
-		survey->channel_time_tx = priv->survey_raw.tx;
-		survey->channel_time_busy = priv->survey_raw.tx +
+		survey->time = priv->survey_raw.active;
+		survey->time_tx = priv->survey_raw.tx;
+		survey->time_busy = priv->survey_raw.tx +
 			priv->survey_raw.cca;
-		do_div(survey->channel_time, 1024);
-		do_div(survey->channel_time_tx, 1024);
-		do_div(survey->channel_time_busy, 1024);
+		do_div(survey->time, 1024);
+		do_div(survey->time_tx, 1024);
+		do_div(survey->time_busy, 1024);
 	}
 
 	tmp = p54_find_and_unlink_skb(priv, hdr->req_id);
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 81ee481487c..be2d54f257b 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -8020,13 +8020,13 @@ int rt2800_get_survey(struct ieee80211_hw *hw, int idx,
 	rt2800_register_read(rt2x00dev, CH_BUSY_STA_SEC, &busy_ext);
 
 	if (idle || busy) {
-		survey->filled = SURVEY_INFO_CHANNEL_TIME |
-				 SURVEY_INFO_CHANNEL_TIME_BUSY |
-				 SURVEY_INFO_CHANNEL_TIME_EXT_BUSY;
+		survey->filled = SURVEY_INFO_TIME |
+				 SURVEY_INFO_TIME_BUSY |
+				 SURVEY_INFO_TIME_EXT_BUSY;
 
-		survey->channel_time = (idle + busy) / 1000;
-		survey->channel_time_busy = busy / 1000;
-		survey->channel_time_ext_busy = busy_ext / 1000;
+		survey->time = (idle + busy) / 1000;
+		survey->time_busy = busy / 1000;
+		survey->time_ext_busy = busy_ext / 1000;
 	}
 
 	if (!(hw->conf.flags & IEEE80211_CONF_OFFCHANNEL))
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f38645fb83b..3b489f8fc4c 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -520,23 +520,23 @@ ieee80211_chandef_max_power(struct cfg80211_chan_def *chandef)
  *
  * @SURVEY_INFO_NOISE_DBM: noise (in dBm) was filled in
  * @SURVEY_INFO_IN_USE: channel is currently being used
- * @SURVEY_INFO_CHANNEL_TIME: channel active time (in ms) was filled in
- * @SURVEY_INFO_CHANNEL_TIME_BUSY: channel busy time was filled in
- * @SURVEY_INFO_CHANNEL_TIME_EXT_BUSY: extension channel busy time was filled in
- * @SURVEY_INFO_CHANNEL_TIME_RX: channel receive time was filled in
- * @SURVEY_INFO_CHANNEL_TIME_TX: channel transmit time was filled in
+ * @SURVEY_INFO_TIME: active time (in ms) was filled in
+ * @SURVEY_INFO_TIME_BUSY: busy time was filled in
+ * @SURVEY_INFO_TIME_EXT_BUSY: extension channel busy time was filled in
+ * @SURVEY_INFO_TIME_RX: receive time was filled in
+ * @SURVEY_INFO_TIME_TX: transmit time was filled in
  *
  * Used by the driver to indicate which info in &struct survey_info
  * it has filled in during the get_survey().
  */
 enum survey_info_flags {
-	SURVEY_INFO_NOISE_DBM = 1<<0,
-	SURVEY_INFO_IN_USE = 1<<1,
-	SURVEY_INFO_CHANNEL_TIME = 1<<2,
-	SURVEY_INFO_CHANNEL_TIME_BUSY = 1<<3,
-	SURVEY_INFO_CHANNEL_TIME_EXT_BUSY = 1<<4,
-	SURVEY_INFO_CHANNEL_TIME_RX = 1<<5,
-	SURVEY_INFO_CHANNEL_TIME_TX = 1<<6,
+	SURVEY_INFO_NOISE_DBM		= BIT(0),
+	SURVEY_INFO_IN_USE		= BIT(1),
+	SURVEY_INFO_TIME		= BIT(2),
+	SURVEY_INFO_TIME_BUSY		= BIT(3),
+	SURVEY_INFO_TIME_EXT_BUSY	= BIT(4),
+	SURVEY_INFO_TIME_RX		= BIT(5),
+	SURVEY_INFO_TIME_TX		= BIT(6),
 };
 
 /**
@@ -546,11 +546,11 @@ enum survey_info_flags {
  * @filled: bitflag of flags from &enum survey_info_flags
  * @noise: channel noise in dBm. This and all following fields are
  *	optional
- * @channel_time: amount of time in ms the radio spent on the channel
- * @channel_time_busy: amount of time the primary channel was sensed busy
- * @channel_time_ext_busy: amount of time the extension channel was sensed busy
- * @channel_time_rx: amount of time the radio spent receiving data
- * @channel_time_tx: amount of time the radio spent transmitting data
+ * @time: amount of time in ms the radio was turn on (on the channel)
+ * @time_busy: amount of time the primary channel was sensed busy
+ * @time_ext_busy: amount of time the extension channel was sensed busy
+ * @time_rx: amount of time the radio spent receiving data
+ * @time_tx: amount of time the radio spent transmitting data
  *
  * Used by dump_survey() to report back per-channel survey information.
  *
@@ -559,11 +559,11 @@ enum survey_info_flags {
  */
 struct survey_info {
 	struct ieee80211_channel *channel;
-	u64 channel_time;
-	u64 channel_time_busy;
-	u64 channel_time_ext_busy;
-	u64 channel_time_rx;
-	u64 channel_time_tx;
+	u64 time;
+	u64 time_busy;
+	u64 time_ext_busy;
+	u64 time_rx;
+	u64 time_tx;
 	u32 filled;
 	s8 noise;
 };
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 7ba9404b290..1a5acc80ab8 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2815,15 +2815,15 @@ enum nl80211_user_reg_hint_type {
  * @NL80211_SURVEY_INFO_FREQUENCY: center frequency of channel
  * @NL80211_SURVEY_INFO_NOISE: noise level of channel (u8, dBm)
  * @NL80211_SURVEY_INFO_IN_USE: channel is currently being used
- * @NL80211_SURVEY_INFO_CHANNEL_TIME: amount of time (in ms) that the radio
+ * @NL80211_SURVEY_INFO_TIME: amount of time (in ms) that the radio
  *	spent on this channel
- * @NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY: amount of the time the primary
+ * @NL80211_SURVEY_INFO_TIME_BUSY: amount of the time the primary
  *	channel was sensed busy (either due to activity or energy detect)
- * @NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY: amount of time the extension
+ * @NL80211_SURVEY_INFO_TIME_EXT_BUSY: amount of time the extension
  *	channel was sensed busy
- * @NL80211_SURVEY_INFO_CHANNEL_TIME_RX: amount of time the radio spent
+ * @NL80211_SURVEY_INFO_TIME_RX: amount of time the radio spent
  *	receiving data
- * @NL80211_SURVEY_INFO_CHANNEL_TIME_TX: amount of time the radio spent
+ * @NL80211_SURVEY_INFO_TIME_TX: amount of time the radio spent
  *	transmitting data
  * @NL80211_SURVEY_INFO_MAX: highest survey info attribute number
  *	currently defined
@@ -2834,17 +2834,24 @@ enum nl80211_survey_info {
 	NL80211_SURVEY_INFO_FREQUENCY,
 	NL80211_SURVEY_INFO_NOISE,
 	NL80211_SURVEY_INFO_IN_USE,
-	NL80211_SURVEY_INFO_CHANNEL_TIME,
-	NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY,
-	NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY,
-	NL80211_SURVEY_INFO_CHANNEL_TIME_RX,
-	NL80211_SURVEY_INFO_CHANNEL_TIME_TX,
+	NL80211_SURVEY_INFO_TIME,
+	NL80211_SURVEY_INFO_TIME_BUSY,
+	NL80211_SURVEY_INFO_TIME_EXT_BUSY,
+	NL80211_SURVEY_INFO_TIME_RX,
+	NL80211_SURVEY_INFO_TIME_TX,
 
 	/* keep last */
 	__NL80211_SURVEY_INFO_AFTER_LAST,
 	NL80211_SURVEY_INFO_MAX = __NL80211_SURVEY_INFO_AFTER_LAST - 1
 };
 
+/* keep old names for compatibility */
+#define NL80211_SURVEY_INFO_CHANNEL_TIME		NL80211_SURVEY_INFO_TIME
+#define NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY		NL80211_SURVEY_INFO_TIME_BUSY
+#define NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY	NL80211_SURVEY_INFO_TIME_EXT_BUSY
+#define NL80211_SURVEY_INFO_CHANNEL_TIME_RX		NL80211_SURVEY_INFO_TIME_RX
+#define NL80211_SURVEY_INFO_CHANNEL_TIME_TX		NL80211_SURVEY_INFO_TIME_TX
+
 /**
  * enum nl80211_mntr_flags - monitor configuration flags
  *
diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c
index ebfc8091557..eea742710c0 100644
--- a/net/mac80211/ethtool.c
+++ b/net/mac80211/ethtool.c
@@ -175,24 +175,24 @@ do_survey:
 		data[i++] = (u8)survey.noise;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME)
-		data[i++] = survey.channel_time;
+	if (survey.filled & SURVEY_INFO_TIME)
+		data[i++] = survey.time;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_BUSY)
-		data[i++] = survey.channel_time_busy;
+	if (survey.filled & SURVEY_INFO_TIME_BUSY)
+		data[i++] = survey.time_busy;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY)
-		data[i++] = survey.channel_time_ext_busy;
+	if (survey.filled & SURVEY_INFO_TIME_EXT_BUSY)
+		data[i++] = survey.time_ext_busy;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_RX)
-		data[i++] = survey.channel_time_rx;
+	if (survey.filled & SURVEY_INFO_TIME_RX)
+		data[i++] = survey.time_rx;
 	else
 		data[i++] = -1LL;
-	if (survey.filled & SURVEY_INFO_CHANNEL_TIME_TX)
-		data[i++] = survey.channel_time_tx;
+	if (survey.filled & SURVEY_INFO_TIME_TX)
+		data[i++] = survey.time_tx;
 	else
 		data[i++] = -1LL;
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ad3e294acab..94ab2014fef 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6641,25 +6641,25 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 	if ((survey->filled & SURVEY_INFO_IN_USE) &&
 	    nla_put_flag(msg, NL80211_SURVEY_INFO_IN_USE))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME,
-			survey->channel_time))
+	if ((survey->filled & SURVEY_INFO_TIME) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME,
+			survey->time))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_BUSY) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_BUSY,
-			survey->channel_time_busy))
+	if ((survey->filled & SURVEY_INFO_TIME_BUSY) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_BUSY,
+			survey->time_busy))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_EXT_BUSY) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_EXT_BUSY,
-			survey->channel_time_ext_busy))
+	if ((survey->filled & SURVEY_INFO_TIME_EXT_BUSY) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_EXT_BUSY,
+			survey->time_ext_busy))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_RX) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_RX,
-			survey->channel_time_rx))
+	if ((survey->filled & SURVEY_INFO_TIME_RX) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_RX,
+			survey->time_rx))
 		goto nla_put_failure;
-	if ((survey->filled & SURVEY_INFO_CHANNEL_TIME_TX) &&
-	    nla_put_u64(msg, NL80211_SURVEY_INFO_CHANNEL_TIME_TX,
-			survey->channel_time_tx))
+	if ((survey->filled & SURVEY_INFO_TIME_TX) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_TX,
+			survey->time_tx))
 		goto nla_put_failure;
 
 	nla_nest_end(msg, infoattr);
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index ad38910f703..bbb7afc264a 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1604,11 +1604,11 @@ TRACE_EVENT(rdev_return_int_survey_info,
 		WIPHY_ENTRY
 		CHAN_ENTRY
 		__field(int, ret)
-		__field(u64, channel_time)
-		__field(u64, channel_time_busy)
-		__field(u64, channel_time_ext_busy)
-		__field(u64, channel_time_rx)
-		__field(u64, channel_time_tx)
+		__field(u64, time)
+		__field(u64, time_busy)
+		__field(u64, time_ext_busy)
+		__field(u64, time_rx)
+		__field(u64, time_tx)
 		__field(u32, filled)
 		__field(s8, noise)
 	),
@@ -1616,11 +1616,11 @@ TRACE_EVENT(rdev_return_int_survey_info,
 		WIPHY_ASSIGN;
 		CHAN_ASSIGN(info->channel);
 		__entry->ret = ret;
-		__entry->channel_time = info->channel_time;
-		__entry->channel_time_busy = info->channel_time_busy;
-		__entry->channel_time_ext_busy = info->channel_time_ext_busy;
-		__entry->channel_time_rx = info->channel_time_rx;
-		__entry->channel_time_tx = info->channel_time_tx;
+		__entry->time = info->time;
+		__entry->time_busy = info->time_busy;
+		__entry->time_ext_busy = info->time_ext_busy;
+		__entry->time_rx = info->time_rx;
+		__entry->time_tx = info->time_tx;
 		__entry->filled = info->filled;
 		__entry->noise = info->noise;
 	),
@@ -1629,9 +1629,9 @@ TRACE_EVENT(rdev_return_int_survey_info,
 		  "channel time extension busy: %llu, channel time rx: %llu, "
 		  "channel time tx: %llu, filled: %u, noise: %d",
 		  WIPHY_PR_ARG, __entry->ret, CHAN_PR_ARG,
-		  __entry->channel_time, __entry->channel_time_busy,
-		  __entry->channel_time_ext_busy, __entry->channel_time_rx,
-		  __entry->channel_time_tx, __entry->filled, __entry->noise)
+		  __entry->time, __entry->time_busy,
+		  __entry->time_ext_busy, __entry->time_rx,
+		  __entry->time_tx, __entry->filled, __entry->noise)
 );
 
 TRACE_EVENT(rdev_tdls_oper,
-- 
cgit v1.2.3-70-g09d2


From 11f78ac32b06648c1dde9371b70323168b51a83e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 14 Nov 2014 16:43:50 +0100
Subject: cfg80211: allow survey data to return global data

Not all devices are able to report survey data (particularly
time spent for various operations) per channel. As all these
statistics already exist in survey data, allow such devices
to report them (if userspace requested it)

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  3 ++-
 include/uapi/linux/nl80211.h | 16 +++++++++++++---
 net/wireless/nl80211.c       | 31 ++++++++++++++++++-------------
 3 files changed, 33 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 3b489f8fc4c..5a861440c12 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -542,7 +542,8 @@ enum survey_info_flags {
 /**
  * struct survey_info - channel survey response
  *
- * @channel: the channel this survey record reports, mandatory
+ * @channel: the channel this survey record reports, may be %NULL for a single
+ *	record to report global statistics
  * @filled: bitflag of flags from &enum survey_info_flags
  * @noise: channel noise in dBm. This and all following fields are
  *	optional
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 1a5acc80ab8..5e8b65f239a 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -1727,6 +1727,14 @@ enum nl80211_commands {
  *	is located at bit 0 of byte 0. bit index 25 would be located at bit 1
  *	of byte 3 (u8 array).
  *
+ * @NL80211_ATTR_SURVEY_RADIO_STATS: Request overall radio statistics to be
+ *	returned along with other survey data. If set, @NL80211_CMD_GET_SURVEY
+ *	may return a survey entry without a channel indicating global radio
+ *	statistics (only some values are valid and make sense.)
+ *	For devices that don't return such an entry even then, the information
+ *	should be contained in the result as the sum of the respective counters
+ *	over all channels.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2088,6 +2096,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_EXT_FEATURES,
 
+	NL80211_ATTR_SURVEY_RADIO_STATS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -2816,15 +2826,15 @@ enum nl80211_user_reg_hint_type {
  * @NL80211_SURVEY_INFO_NOISE: noise level of channel (u8, dBm)
  * @NL80211_SURVEY_INFO_IN_USE: channel is currently being used
  * @NL80211_SURVEY_INFO_TIME: amount of time (in ms) that the radio
- *	spent on this channel
+ *	was turned on (on channel or globally)
  * @NL80211_SURVEY_INFO_TIME_BUSY: amount of the time the primary
  *	channel was sensed busy (either due to activity or energy detect)
  * @NL80211_SURVEY_INFO_TIME_EXT_BUSY: amount of time the extension
  *	channel was sensed busy
  * @NL80211_SURVEY_INFO_TIME_RX: amount of time the radio spent
- *	receiving data
+ *	receiving data (on channel or globally)
  * @NL80211_SURVEY_INFO_TIME_TX: amount of time the radio spent
- *	transmitting data
+ *	transmitting data (on channel or globally)
  * @NL80211_SURVEY_INFO_MAX: highest survey info attribute number
  *	currently defined
  * @__NL80211_SURVEY_INFO_AFTER_LAST: internal use
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 94ab2014fef..9555ef9fd99 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6613,12 +6613,17 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb)
 }
 
 static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
-				int flags, struct net_device *dev,
-				struct survey_info *survey)
+			       int flags, struct net_device *dev,
+			       bool allow_radio_stats,
+			       struct survey_info *survey)
 {
 	void *hdr;
 	struct nlattr *infoattr;
 
+	/* skip radio stats if userspace didn't request them */
+	if (!survey->channel && !allow_radio_stats)
+		return 0;
+
 	hdr = nl80211hdr_put(msg, portid, seq, flags,
 			     NL80211_CMD_NEW_SURVEY_RESULTS);
 	if (!hdr)
@@ -6631,7 +6636,8 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 	if (!infoattr)
 		goto nla_put_failure;
 
-	if (nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY,
+	if (survey->channel &&
+	    nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY,
 			survey->channel->center_freq))
 		goto nla_put_failure;
 
@@ -6671,19 +6677,22 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 	return -EMSGSIZE;
 }
 
-static int nl80211_dump_survey(struct sk_buff *skb,
-			struct netlink_callback *cb)
+static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct survey_info survey;
 	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	int survey_idx = cb->args[2];
 	int res;
+	bool radio_stats;
 
 	res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (res)
 		return res;
 
+	/* prepare_wdev_dump parsed the attributes */
+	radio_stats = nl80211_fam.attrbuf[NL80211_ATTR_SURVEY_RADIO_STATS];
+
 	if (!wdev->netdev) {
 		res = -EINVAL;
 		goto out_err;
@@ -6701,13 +6710,9 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 		if (res)
 			goto out_err;
 
-		/* Survey without a channel doesn't make sense */
-		if (!survey.channel) {
-			res = -EINVAL;
-			goto out;
-		}
-
-		if (survey.channel->flags & IEEE80211_CHAN_DISABLED) {
+		/* don't send disabled channels, but do send non-channel data */
+		if (survey.channel &&
+		    survey.channel->flags & IEEE80211_CHAN_DISABLED) {
 			survey_idx++;
 			continue;
 		}
@@ -6715,7 +6720,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 		if (nl80211_send_survey(skb,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				wdev->netdev, &survey) < 0)
+				wdev->netdev, radio_stats, &survey) < 0)
 			goto out;
 		survey_idx++;
 	}
-- 
cgit v1.2.3-70-g09d2


From 052536abfa9144566599a7fbe8cc89e1086fa9a7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 14 Nov 2014 16:44:11 +0100
Subject: cfg80211: add scan time to survey data

Add the time spent scanning to the survey data so it can be
reported by drivers that collect such information.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 4 ++++
 include/uapi/linux/nl80211.h | 3 +++
 net/wireless/nl80211.c       | 4 ++++
 net/wireless/trace.h         | 7 +++++--
 4 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5a861440c12..f94f0d486d1 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -525,6 +525,7 @@ ieee80211_chandef_max_power(struct cfg80211_chan_def *chandef)
  * @SURVEY_INFO_TIME_EXT_BUSY: extension channel busy time was filled in
  * @SURVEY_INFO_TIME_RX: receive time was filled in
  * @SURVEY_INFO_TIME_TX: transmit time was filled in
+ * @SURVEY_INFO_TIME_SCAN: scan time was filled in
  *
  * Used by the driver to indicate which info in &struct survey_info
  * it has filled in during the get_survey().
@@ -537,6 +538,7 @@ enum survey_info_flags {
 	SURVEY_INFO_TIME_EXT_BUSY	= BIT(4),
 	SURVEY_INFO_TIME_RX		= BIT(5),
 	SURVEY_INFO_TIME_TX		= BIT(6),
+	SURVEY_INFO_TIME_SCAN		= BIT(7),
 };
 
 /**
@@ -552,6 +554,7 @@ enum survey_info_flags {
  * @time_ext_busy: amount of time the extension channel was sensed busy
  * @time_rx: amount of time the radio spent receiving data
  * @time_tx: amount of time the radio spent transmitting data
+ * @time_scan: amount of time the radio spent for scanning
  *
  * Used by dump_survey() to report back per-channel survey information.
  *
@@ -565,6 +568,7 @@ struct survey_info {
 	u64 time_ext_busy;
 	u64 time_rx;
 	u64 time_tx;
+	u64 time_scan;
 	u32 filled;
 	s8 noise;
 };
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 5e8b65f239a..2f549a25313 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2835,6 +2835,8 @@ enum nl80211_user_reg_hint_type {
  *	receiving data (on channel or globally)
  * @NL80211_SURVEY_INFO_TIME_TX: amount of time the radio spent
  *	transmitting data (on channel or globally)
+ * @NL80211_SURVEY_INFO_TIME_SCAN: time the radio spent for scan
+ *	(on this channel or globally)
  * @NL80211_SURVEY_INFO_MAX: highest survey info attribute number
  *	currently defined
  * @__NL80211_SURVEY_INFO_AFTER_LAST: internal use
@@ -2849,6 +2851,7 @@ enum nl80211_survey_info {
 	NL80211_SURVEY_INFO_TIME_EXT_BUSY,
 	NL80211_SURVEY_INFO_TIME_RX,
 	NL80211_SURVEY_INFO_TIME_TX,
+	NL80211_SURVEY_INFO_TIME_SCAN,
 
 	/* keep last */
 	__NL80211_SURVEY_INFO_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 9555ef9fd99..f56309bd21b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6667,6 +6667,10 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_TX,
 			survey->time_tx))
 		goto nla_put_failure;
+	if ((survey->filled & SURVEY_INFO_TIME_SCAN) &&
+	    nla_put_u64(msg, NL80211_SURVEY_INFO_TIME_SCAN,
+			survey->time_scan))
+		goto nla_put_failure;
 
 	nla_nest_end(msg, infoattr);
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index bbb7afc264a..b17b3692f8c 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1609,6 +1609,7 @@ TRACE_EVENT(rdev_return_int_survey_info,
 		__field(u64, time_ext_busy)
 		__field(u64, time_rx)
 		__field(u64, time_tx)
+		__field(u64, time_scan)
 		__field(u32, filled)
 		__field(s8, noise)
 	),
@@ -1621,17 +1622,19 @@ TRACE_EVENT(rdev_return_int_survey_info,
 		__entry->time_ext_busy = info->time_ext_busy;
 		__entry->time_rx = info->time_rx;
 		__entry->time_tx = info->time_tx;
+		__entry->time_scan = info->time_scan;
 		__entry->filled = info->filled;
 		__entry->noise = info->noise;
 	),
 	TP_printk(WIPHY_PR_FMT ", returned: %d, " CHAN_PR_FMT
 		  ", channel time: %llu, channel time busy: %llu, "
 		  "channel time extension busy: %llu, channel time rx: %llu, "
-		  "channel time tx: %llu, filled: %u, noise: %d",
+		  "channel time tx: %llu, scan time: %llu, filled: %u, noise: %d",
 		  WIPHY_PR_ARG, __entry->ret, CHAN_PR_ARG,
 		  __entry->time, __entry->time_busy,
 		  __entry->time_ext_busy, __entry->time_rx,
-		  __entry->time_tx, __entry->filled, __entry->noise)
+		  __entry->time_tx, __entry->time_scan,
+		  __entry->filled, __entry->noise)
 );
 
 TRACE_EVENT(rdev_tdls_oper,
-- 
cgit v1.2.3-70-g09d2


From cf5ead822d5db2d276616ccca91f00eb3b855db2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 14 Nov 2014 17:14:00 +0100
Subject: cfg80211: allow including station info in delete event

When a station is removed, its statistics may be interesting to
userspace, for example for further aggregation of statistics of
all stations that ever connected to an AP.

Introduce a new cfg80211_del_sta_sinfo() function (and make the
cfg80211_del_sta() a static inline calling it) to allow passing
a struct station_info along with this, and send the data in the
nl80211 event message.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 16 +++++++++++++++-
 net/wireless/nl80211.c | 38 ++++++++++++++++----------------------
 2 files changed, 31 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f94f0d486d1..42e3d74f190 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4591,6 +4591,16 @@ void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie,
 void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 		      struct station_info *sinfo, gfp_t gfp);
 
+/**
+ * cfg80211_del_sta_sinfo - notify userspace about deletion of a station
+ * @dev: the netdev
+ * @mac_addr: the station's address
+ * @sinfo: the station information/statistics
+ * @gfp: allocation flags
+ */
+void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr,
+			    struct station_info *sinfo, gfp_t gfp);
+
 /**
  * cfg80211_del_sta - notify userspace about deletion of a station
  *
@@ -4598,7 +4608,11 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
  * @mac_addr: the station's address
  * @gfp: allocation flags
  */
-void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp);
+static inline void cfg80211_del_sta(struct net_device *dev,
+				    const u8 *mac_addr, gfp_t gfp)
+{
+	cfg80211_del_sta_sinfo(dev, mac_addr, NULL, gfp);
+}
 
 /**
  * cfg80211_conn_failed - connection request failed notification
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f56309bd21b..a75dc91976d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3650,8 +3650,8 @@ static bool nl80211_put_signal(struct sk_buff *msg, u8 mask, s8 *signal,
 	return true;
 }
 
-static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
-				int flags,
+static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
+				u32 seq, int flags,
 				struct cfg80211_registered_device *rdev,
 				struct net_device *dev,
 				const u8 *mac_addr, struct station_info *sinfo)
@@ -3659,7 +3659,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
 	void *hdr;
 	struct nlattr *sinfoattr, *bss_param;
 
-	hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_STATION);
+	hdr = nl80211hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
 		return -1;
 
@@ -3854,7 +3854,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 		if (err)
 			goto out_err;
 
-		if (nl80211_send_station(skb,
+		if (nl80211_send_station(skb, NL80211_CMD_NEW_STATION,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				rdev, wdev->netdev, mac_addr,
@@ -3901,7 +3901,8 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info)
 	if (!msg)
 		return -ENOMEM;
 
-	if (nl80211_send_station(msg, info->snd_portid, info->snd_seq, 0,
+	if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION,
+				 info->snd_portid, info->snd_seq, 0,
 				 rdev, dev, mac_addr, &sinfo) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
@@ -11687,7 +11688,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 	if (!msg)
 		return;
 
-	if (nl80211_send_station(msg, 0, 0, 0,
+	if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, 0, 0, 0,
 				 rdev, dev, mac_addr, sinfo) < 0) {
 		nlmsg_free(msg);
 		return;
@@ -11698,12 +11699,16 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 }
 EXPORT_SYMBOL(cfg80211_new_sta);
 
-void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
+void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr,
+			    struct station_info *sinfo, gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
-	void *hdr;
+	struct station_info empty_sinfo = {};
+
+	if (!sinfo)
+		sinfo = &empty_sinfo;
 
 	trace_cfg80211_del_sta(dev, mac_addr);
 
@@ -11711,27 +11716,16 @@ void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
 	if (!msg)
 		return;
 
-	hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_DEL_STATION);
-	if (!hdr) {
+	if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0,
+				 rdev, dev, mac_addr, sinfo)) {
 		nlmsg_free(msg);
 		return;
 	}
 
-	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
-	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, mac_addr))
-		goto nla_put_failure;
-
-	genlmsg_end(msg, hdr);
-
 	genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0,
 				NL80211_MCGRP_MLME, gfp);
-	return;
-
- nla_put_failure:
-	genlmsg_cancel(msg, hdr);
-	nlmsg_free(msg);
 }
-EXPORT_SYMBOL(cfg80211_del_sta);
+EXPORT_SYMBOL(cfg80211_del_sta_sinfo);
 
 void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
 			  enum nl80211_connect_failed_reason reason,
-- 
cgit v1.2.3-70-g09d2


From 2b9a7e1bac24df8ddb0713ad1e5807a7243bcab0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 17 Nov 2014 11:35:23 +0100
Subject: mac80211: allow drivers to provide most station statistics

In many cases, drivers can filter things like beacons that will
skew statistics reported by mac80211. To get correct statistics
in these cases, call drivers to obtain statistics and let them
override all values, filling values from mac80211 if the driver
didn't provide them. Not all of them make sense for the driver
to fill, so some are still always done by mac80211.

Note that this doesn't currently allow a driver to say "I know
this value is wrong, don't report it at all", or to sum it up
with a mac80211 value (as could be useful for "dropped misc"),
that can be added if it turns out to be needed.

This also gets rid of the get_rssi() method as is can now be
implemented using sta_statistics().

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ti/wlcore/main.c | 20 ++++----
 include/net/mac80211.h                | 17 ++++--
 net/mac80211/driver-ops.h             | 30 +++++------
 net/mac80211/sta_info.c               | 97 +++++++++++++++++++++++------------
 net/mac80211/trace.h                  | 33 +++---------
 5 files changed, 110 insertions(+), 87 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 2a99456b6b8..8d11b0ca412 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -5376,14 +5376,15 @@ static void wlcore_op_sta_rc_update(struct ieee80211_hw *hw,
 	wlcore_hw_sta_rc_update(wl, wlvif, sta, changed);
 }
 
-static int wlcore_op_get_rssi(struct ieee80211_hw *hw,
-			       struct ieee80211_vif *vif,
-			       struct ieee80211_sta *sta,
-			       s8 *rssi_dbm)
+static void wlcore_op_sta_statistics(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta,
+				     struct station_info *sinfo)
 {
 	struct wl1271 *wl = hw->priv;
 	struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vif);
-	int ret = 0;
+	s8 rssi_dbm;
+	int ret;
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 get_rssi");
 
@@ -5396,17 +5397,18 @@ static int wlcore_op_get_rssi(struct ieee80211_hw *hw,
 	if (ret < 0)
 		goto out_sleep;
 
-	ret = wlcore_acx_average_rssi(wl, wlvif, rssi_dbm);
+	ret = wlcore_acx_average_rssi(wl, wlvif, &rssi_dbm);
 	if (ret < 0)
 		goto out_sleep;
 
+	sinfo->filled |= STATION_INFO_SIGNAL;
+	sinfo->signal = rssi_dbm;
+
 out_sleep:
 	wl1271_ps_elp_sleep(wl);
 
 out:
 	mutex_unlock(&wl->mutex);
-
-	return ret;
 }
 
 static bool wl1271_tx_frames_pending(struct ieee80211_hw *hw)
@@ -5606,7 +5608,7 @@ static const struct ieee80211_ops wl1271_ops = {
 	.assign_vif_chanctx = wlcore_op_assign_vif_chanctx,
 	.unassign_vif_chanctx = wlcore_op_unassign_vif_chanctx,
 	.sta_rc_update = wlcore_op_sta_rc_update,
-	.get_rssi = wlcore_op_get_rssi,
+	.sta_statistics = wlcore_op_sta_statistics,
 	CFG80211_TESTMODE_CMD(wl1271_tm_cmd)
 };
 
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 555a845ad51..123f2308958 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2708,6 +2708,14 @@ enum ieee80211_reconfig_type {
  *	is only used if the configured rate control algorithm actually uses
  *	the new rate table API, and is therefore optional. Must be atomic.
  *
+ * @sta_statistics: Get statistics for this station. For example with beacon
+ *	filtering, the statistics kept by mac80211 might not be accurate, so
+ *	let the driver pre-fill the statistics. The driver can fill most of
+ *	the values (indicating which by setting the filled bitmap), but not
+ *	all of them make sense - see the source for which ones are possible.
+ *	Statistics that the driver doesn't fill will be filled by mac80211.
+ *	The callback can sleep.
+ *
  * @conf_tx: Configure TX queue parameters (EDCF (aifs, cw_min, cw_max),
  *	bursting) for a hardware TX queue.
  *	Returns a negative error code on failure.
@@ -2868,9 +2876,6 @@ enum ieee80211_reconfig_type {
  * @get_et_strings:  Ethtool API to get a set of strings to describe stats
  *	and perhaps other supported types of ethtool data-sets.
  *
- * @get_rssi: Get current signal strength in dBm, the function is optional
- *	and can sleep.
- *
  * @mgd_prepare_tx: Prepare for transmitting a management frame for association
  *	before associated. In multi-channel scenarios, a virtual interface is
  *	bound to a channel before it is associated, but as it isn't associated
@@ -3071,6 +3076,10 @@ struct ieee80211_ops {
 	void (*sta_rate_tbl_update)(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_sta *sta);
+	void (*sta_statistics)(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta,
+			       struct station_info *sinfo);
 	int (*conf_tx)(struct ieee80211_hw *hw,
 		       struct ieee80211_vif *vif, u16 ac,
 		       const struct ieee80211_tx_queue_params *params);
@@ -3138,8 +3147,6 @@ struct ieee80211_ops {
 	void	(*get_et_strings)(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif,
 				  u32 sset, u8 *data);
-	int	(*get_rssi)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			    struct ieee80211_sta *sta, s8 *rssi_dbm);
 
 	void	(*mgd_prepare_tx)(struct ieee80211_hw *hw,
 				  struct ieee80211_vif *vif);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 2ebc9ead969..fdeda17b8dd 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -639,6 +639,21 @@ static inline void drv_sta_rate_tbl_update(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline void drv_sta_statistics(struct ieee80211_local *local,
+				      struct ieee80211_sub_if_data *sdata,
+				      struct ieee80211_sta *sta,
+				      struct station_info *sinfo)
+{
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_sta_statistics(local, sdata, sta);
+	if (local->ops->sta_statistics)
+		local->ops->sta_statistics(&local->hw, &sdata->vif, sta, sinfo);
+	trace_drv_return_void(local);
+}
+
 static inline int drv_conf_tx(struct ieee80211_local *local,
 			      struct ieee80211_sub_if_data *sdata, u16 ac,
 			      const struct ieee80211_tx_queue_params *params)
@@ -966,21 +981,6 @@ drv_allow_buffered_frames(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
-static inline int drv_get_rssi(struct ieee80211_local *local,
-				struct ieee80211_sub_if_data *sdata,
-				struct ieee80211_sta *sta,
-				s8 *rssi_dbm)
-{
-	int ret;
-
-	might_sleep();
-
-	ret = local->ops->get_rssi(&local->hw, &sdata->vif, sta, rssi_dbm);
-	trace_drv_get_rssi(local, sta, *rssi_dbm, ret);
-
-	return ret;
-}
-
 static inline void drv_mgd_prepare_tx(struct ieee80211_local *local,
 				      struct ieee80211_sub_if_data *sdata)
 {
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 388ff0b2ad2..967b42eae5c 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1746,7 +1746,6 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 	struct ieee80211_local *local = sdata->local;
 	struct rate_control_ref *ref = NULL;
 	struct timespec uptime;
-	u64 packets = 0;
 	u32 thr = 0;
 	int i, ac;
 
@@ -1755,47 +1754,74 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 
 	sinfo->generation = sdata->local->sta_generation;
 
-	sinfo->filled = STATION_INFO_INACTIVE_TIME |
-			STATION_INFO_RX_BYTES64 |
-			STATION_INFO_TX_BYTES64 |
-			STATION_INFO_RX_PACKETS |
-			STATION_INFO_TX_PACKETS |
-			STATION_INFO_TX_RETRIES |
-			STATION_INFO_TX_FAILED |
-			STATION_INFO_TX_BITRATE |
-			STATION_INFO_RX_BITRATE |
-			STATION_INFO_RX_DROP_MISC |
-			STATION_INFO_BSS_PARAM |
-			STATION_INFO_CONNECTED_TIME |
-			STATION_INFO_STA_FLAGS |
-			STATION_INFO_BEACON_LOSS_COUNT;
+	drv_sta_statistics(local, sdata, &sta->sta, sinfo);
+
+	sinfo->filled |= STATION_INFO_INACTIVE_TIME |
+			 STATION_INFO_STA_FLAGS |
+			 STATION_INFO_BSS_PARAM |
+			 STATION_INFO_CONNECTED_TIME |
+			 STATION_INFO_RX_DROP_MISC |
+			 STATION_INFO_BEACON_LOSS_COUNT;
 
 	ktime_get_ts(&uptime);
 	sinfo->connected_time = uptime.tv_sec - sta->last_connected;
-
 	sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx);
-	sinfo->tx_bytes = 0;
-	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
-		sinfo->tx_bytes += sta->tx_bytes[ac];
-		packets += sta->tx_packets[ac];
+
+	if (!(sinfo->filled & (STATION_INFO_TX_BYTES64 |
+			       STATION_INFO_TX_BYTES))) {
+		sinfo->tx_bytes = 0;
+		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
+			sinfo->tx_bytes += sta->tx_bytes[ac];
+		sinfo->filled |= STATION_INFO_TX_BYTES64;
+	}
+
+	if (!(sinfo->filled & STATION_INFO_TX_PACKETS)) {
+		sinfo->tx_packets = 0;
+		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
+			sinfo->tx_packets += sta->tx_packets[ac];
+		sinfo->filled |= STATION_INFO_TX_PACKETS;
+	}
+
+	if (!(sinfo->filled & (STATION_INFO_RX_BYTES64 |
+			       STATION_INFO_RX_BYTES))) {
+		sinfo->rx_bytes = sta->rx_bytes;
+		sinfo->filled |= STATION_INFO_RX_BYTES64;
+	}
+
+	if (!(sinfo->filled & STATION_INFO_RX_PACKETS)) {
+		sinfo->rx_packets = sta->rx_packets;
+		sinfo->filled |= STATION_INFO_RX_PACKETS;
+	}
+
+	if (!(sinfo->filled & STATION_INFO_TX_RETRIES)) {
+		sinfo->tx_retries = sta->tx_retry_count;
+		sinfo->filled |= STATION_INFO_TX_RETRIES;
+	}
+
+	if (!(sinfo->filled & STATION_INFO_TX_FAILED)) {
+		sinfo->tx_failed = sta->tx_retry_failed;
+		sinfo->filled |= STATION_INFO_TX_FAILED;
 	}
-	sinfo->tx_packets = packets;
-	sinfo->rx_bytes = sta->rx_bytes;
-	sinfo->rx_packets = sta->rx_packets;
-	sinfo->tx_retries = sta->tx_retry_count;
-	sinfo->tx_failed = sta->tx_retry_failed;
+
 	sinfo->rx_dropped_misc = sta->rx_dropped;
 	sinfo->beacon_loss_count = sta->beacon_loss_count;
 
 	if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) ||
 	    (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) {
-		sinfo->filled |= STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG;
-		if (!local->ops->get_rssi ||
-		    drv_get_rssi(local, sdata, &sta->sta, &sinfo->signal))
+		if (!(sinfo->filled & STATION_INFO_SIGNAL)) {
 			sinfo->signal = (s8)sta->last_signal;
-		sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal);
+			sinfo->filled |= STATION_INFO_SIGNAL;
+		}
+
+		if (!(sinfo->filled & STATION_INFO_SIGNAL_AVG)) {
+			sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal);
+			sinfo->filled |= STATION_INFO_SIGNAL_AVG;
+		}
 	}
-	if (sta->chains) {
+
+	if (sta->chains &&
+	    !(sinfo->filled & (STATION_INFO_CHAIN_SIGNAL |
+			       STATION_INFO_CHAIN_SIGNAL_AVG))) {
 		sinfo->filled |= STATION_INFO_CHAIN_SIGNAL |
 				 STATION_INFO_CHAIN_SIGNAL_AVG;
 
@@ -1807,8 +1833,15 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		}
 	}
 
-	sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate);
-	sta_set_rate_info_rx(sta, &sinfo->rxrate);
+	if (!(sinfo->filled & STATION_INFO_TX_BITRATE)) {
+		sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate);
+		sinfo->filled |= STATION_INFO_TX_BITRATE;
+	}
+
+	if (!(sinfo->filled & STATION_INFO_RX_BITRATE)) {
+		sta_set_rate_info_rx(sta, &sinfo->rxrate);
+		sinfo->filled |= STATION_INFO_RX_BITRATE;
+	}
 
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 8e461a02c6a..263a9561eb2 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -825,6 +825,13 @@ DECLARE_EVENT_CLASS(sta_event,
 	)
 );
 
+DEFINE_EVENT(sta_event, drv_sta_statistics,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta),
+	TP_ARGS(local, sdata, sta)
+);
+
 DEFINE_EVENT(sta_event, drv_sta_add,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
@@ -1329,32 +1336,6 @@ DEFINE_EVENT(release_evt, drv_allow_buffered_frames,
 	TP_ARGS(local, sta, tids, num_frames, reason, more_data)
 );
 
-TRACE_EVENT(drv_get_rssi,
-	TP_PROTO(struct ieee80211_local *local, struct ieee80211_sta *sta,
-		 s8 rssi, int ret),
-
-	TP_ARGS(local, sta, rssi, ret),
-
-	TP_STRUCT__entry(
-		LOCAL_ENTRY
-		STA_ENTRY
-		__field(s8, rssi)
-		__field(int, ret)
-	),
-
-	TP_fast_assign(
-		LOCAL_ASSIGN;
-		STA_ASSIGN;
-		__entry->rssi = rssi;
-		__entry->ret = ret;
-	),
-
-	TP_printk(
-		LOCAL_PR_FMT STA_PR_FMT " rssi:%d ret:%d",
-		LOCAL_PR_ARG, STA_PR_ARG, __entry->rssi, __entry->ret
-	)
-);
-
 DEFINE_EVENT(local_sdata_evt, drv_mgd_prepare_tx,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata),
-- 
cgit v1.2.3-70-g09d2


From 319090bf6c75e3ad42a8c74973be5e78ae4f948f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 17 Nov 2014 14:08:11 +0100
Subject: cfg80211: remove enum station_info_flags

This is really just duplicating the list of information that's
already available in the nl80211 attribute, so remove the list.
Two small changes are needed:
 * remove STATION_INFO_ASSOC_REQ_IES complete, but the length
   (assoc_req_ies_len) can be used instead
 * add NL80211_STA_INFO_RX_DROP_MISC which exists internally
   but not in nl80211 yet

This gets rid of the duplicate maintenance of the two lists.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c         |  14 +--
 drivers/net/wireless/ath/ath6kl/main.c             |   1 -
 drivers/net/wireless/ath/wil6210/cfg80211.c        |  18 +--
 drivers/net/wireless/ath/wil6210/wmi.c             |   1 -
 drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c |  11 +-
 drivers/net/wireless/libertas/cfg.c                |  12 +-
 drivers/net/wireless/mwifiex/cfg80211.c            |  10 +-
 drivers/net/wireless/mwifiex/uap_event.c           |   1 -
 drivers/net/wireless/rndis_wlan.c                  |   4 +-
 drivers/net/wireless/ti/wlcore/main.c              |   2 +-
 drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c  |   9 +-
 drivers/staging/wlan-ng/cfg80211.c                 |   4 +-
 include/net/cfg80211.h                             |  77 +-----------
 include/uapi/linux/nl80211.h                       |   3 +
 net/mac80211/ethtool.c                             |   6 +-
 net/mac80211/sta_info.c                            |  80 ++++++-------
 net/wireless/nl80211.c                             | 133 ++++++++-------------
 net/wireless/wext-compat.c                         |  10 +-
 18 files changed, 142 insertions(+), 254 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 7a5337877a0..44dd6ef923c 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1799,20 +1799,20 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 
 	if (vif->target_stats.rx_byte) {
 		sinfo->rx_bytes = vif->target_stats.rx_byte;
-		sinfo->filled |= STATION_INFO_RX_BYTES64;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
 		sinfo->rx_packets = vif->target_stats.rx_pkt;
-		sinfo->filled |= STATION_INFO_RX_PACKETS;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
 	}
 
 	if (vif->target_stats.tx_byte) {
 		sinfo->tx_bytes = vif->target_stats.tx_byte;
-		sinfo->filled |= STATION_INFO_TX_BYTES64;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
 		sinfo->tx_packets = vif->target_stats.tx_pkt;
-		sinfo->filled |= STATION_INFO_TX_PACKETS;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
 	}
 
 	sinfo->signal = vif->target_stats.cs_rssi;
-	sinfo->filled |= STATION_INFO_SIGNAL;
+	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 
 	rate = vif->target_stats.tx_ucast_rate;
 
@@ -1844,12 +1844,12 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 		return 0;
 	}
 
-	sinfo->filled |= STATION_INFO_TX_BITRATE;
+	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
 
 	if (test_bit(CONNECTED, &vif->flags) &&
 	    test_bit(DTIM_PERIOD_AVAIL, &vif->flags) &&
 	    vif->nw_type == INFRA_NETWORK) {
-		sinfo->filled |= STATION_INFO_BSS_PARAM;
+		sinfo->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
 		sinfo->bss_param.flags = 0;
 		sinfo->bss_param.dtim_period = vif->assoc_bss_dtim_period;
 		sinfo->bss_param.beacon_interval = vif->assoc_bss_beacon_int;
diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c
index 933aef02569..b42ba46b503 100644
--- a/drivers/net/wireless/ath/ath6kl/main.c
+++ b/drivers/net/wireless/ath/ath6kl/main.c
@@ -488,7 +488,6 @@ void ath6kl_connect_ap_mode_sta(struct ath6kl_vif *vif, u16 aid, u8 *mac_addr,
 
 	sinfo.assoc_req_ies = ies;
 	sinfo.assoc_req_ies_len = ies_len;
-	sinfo.filled |= STATION_INFO_ASSOC_REQ_IES;
 
 	cfg80211_new_sta(vif->ndev, mac_addr, &sinfo, GFP_KERNEL);
 
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 38332a6dfb3..e72a95d1ced 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -142,14 +142,14 @@ int wil_cid_fill_sinfo(struct wil6210_priv *wil, int cid,
 
 	sinfo->generation = wil->sinfo_gen;
 
-	sinfo->filled = STATION_INFO_RX_BYTES |
-			STATION_INFO_TX_BYTES |
-			STATION_INFO_RX_PACKETS |
-			STATION_INFO_TX_PACKETS |
-			STATION_INFO_RX_BITRATE |
-			STATION_INFO_TX_BITRATE |
-			STATION_INFO_RX_DROP_MISC |
-			STATION_INFO_TX_FAILED;
+	sinfo->filled = BIT(NL80211_STA_INFO_RX_BYTES) |
+			BIT(NL80211_STA_INFO_TX_BYTES) |
+			BIT(NL80211_STA_INFO_RX_PACKETS) |
+			BIT(NL80211_STA_INFO_TX_PACKETS) |
+			BIT(NL80211_STA_INFO_RX_BITRATE) |
+			BIT(NL80211_STA_INFO_TX_BITRATE) |
+			BIT(NL80211_STA_INFO_RX_DROP_MISC) |
+			BIT(NL80211_STA_INFO_TX_FAILED);
 
 	sinfo->txrate.flags = RATE_INFO_FLAGS_MCS | RATE_INFO_FLAGS_60G;
 	sinfo->txrate.mcs = le16_to_cpu(reply.evt.bf_mcs);
@@ -163,7 +163,7 @@ int wil_cid_fill_sinfo(struct wil6210_priv *wil, int cid,
 	sinfo->tx_failed = stats->tx_errors;
 
 	if (test_bit(wil_status_fwconnected, &wil->status)) {
-		sinfo->filled |= STATION_INFO_SIGNAL;
+		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 		sinfo->signal = reply.evt.sqi;
 	}
 
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 63476c86cd0..89975492095 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -457,7 +457,6 @@ static void wmi_evt_connect(struct wil6210_priv *wil, int id, void *d, int len)
 		if (assoc_req_ie) {
 			sinfo.assoc_req_ies = assoc_req_ie;
 			sinfo.assoc_req_ies_len = assoc_req_ielen;
-			sinfo.filled |= STATION_INFO_ASSOC_REQ_IES;
 		}
 
 		cfg80211_new_sta(ndev, evt->bssid, &sinfo, GFP_KERNEL);
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c
index 3aecc5f4871..4a88b2381a6 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/cfg80211.c
@@ -2333,10 +2333,10 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 			brcmf_err("GET STA INFO failed, %d\n", err);
 			goto done;
 		}
-		sinfo->filled = STATION_INFO_INACTIVE_TIME;
+		sinfo->filled = BIT(NL80211_STA_INFO_INACTIVE_TIME);
 		sinfo->inactive_time = le32_to_cpu(sta_info_le.idle) * 1000;
 		if (le32_to_cpu(sta_info_le.flags) & BRCMF_STA_ASSOC) {
-			sinfo->filled |= STATION_INFO_CONNECTED_TIME;
+			sinfo->filled |= BIT(NL80211_STA_INFO_CONNECTED_TIME);
 			sinfo->connected_time = le32_to_cpu(sta_info_le.in);
 		}
 		brcmf_dbg(TRACE, "STA idle time : %d ms, connected time :%d sec\n",
@@ -2354,7 +2354,7 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 			brcmf_err("Could not get rate (%d)\n", err);
 			goto done;
 		} else {
-			sinfo->filled |= STATION_INFO_TX_BITRATE;
+			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
 			sinfo->txrate.legacy = rate * 5;
 			brcmf_dbg(CONN, "Rate %d Mbps\n", rate / 2);
 		}
@@ -2369,7 +2369,7 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 				goto done;
 			} else {
 				rssi = le32_to_cpu(scb_val.val);
-				sinfo->filled |= STATION_INFO_SIGNAL;
+				sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 				sinfo->signal = rssi;
 				brcmf_dbg(CONN, "RSSI %d dBm\n", rssi);
 			}
@@ -2396,7 +2396,7 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 				brcmf_dbg(CONN, "DTIM peroid %d\n",
 					  dtim_period);
 			}
-			sinfo->filled |= STATION_INFO_BSS_PARAM;
+			sinfo->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
 		}
 	} else
 		err = -EPERM;
@@ -4778,7 +4778,6 @@ brcmf_notify_connect_status_ap(struct brcmf_cfg80211_info *cfg,
 	if (((event == BRCMF_E_ASSOC_IND) || (event == BRCMF_E_REASSOC_IND)) &&
 	    (reason == BRCMF_E_STATUS_SUCCESS)) {
 		memset(&sinfo, 0, sizeof(sinfo));
-		sinfo.filled = STATION_INFO_ASSOC_REQ_IES;
 		if (!data) {
 			brcmf_err("No IEs present in ASSOC/REASSOC_IND");
 			return -EINVAL;
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 34f09ef90bb..a92985a6ea2 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -1616,10 +1616,10 @@ static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
 
 	lbs_deb_enter(LBS_DEB_CFG80211);
 
-	sinfo->filled |= STATION_INFO_TX_BYTES |
-			 STATION_INFO_TX_PACKETS |
-			 STATION_INFO_RX_BYTES |
-			 STATION_INFO_RX_PACKETS;
+	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES) |
+			 BIT(NL80211_STA_INFO_TX_PACKETS) |
+			 BIT(NL80211_STA_INFO_RX_BYTES) |
+			 BIT(NL80211_STA_INFO_RX_PACKETS);
 	sinfo->tx_bytes = priv->dev->stats.tx_bytes;
 	sinfo->tx_packets = priv->dev->stats.tx_packets;
 	sinfo->rx_bytes = priv->dev->stats.rx_bytes;
@@ -1629,14 +1629,14 @@ static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
 	ret = lbs_get_rssi(priv, &signal, &noise);
 	if (ret == 0) {
 		sinfo->signal = signal;
-		sinfo->filled |= STATION_INFO_SIGNAL;
+		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 	}
 
 	/* Convert priv->cur_rate from hw_value to NL80211 value */
 	for (i = 0; i < ARRAY_SIZE(lbs_rates); i++) {
 		if (priv->cur_rate == lbs_rates[i].hw_value) {
 			sinfo->txrate.legacy = lbs_rates[i].bitrate;
-			sinfo->filled |= STATION_INFO_TX_BITRATE;
+			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
 			break;
 		}
 	}
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 8bd446b6965..71312ff5270 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -910,10 +910,10 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 {
 	u32 rate;
 
-	sinfo->filled = STATION_INFO_RX_BYTES | STATION_INFO_TX_BYTES |
-			STATION_INFO_RX_PACKETS | STATION_INFO_TX_PACKETS |
-			STATION_INFO_TX_BITRATE |
-			STATION_INFO_SIGNAL | STATION_INFO_SIGNAL_AVG;
+	sinfo->filled = BIT(NL80211_STA_INFO_RX_BYTES) | BIT(NL80211_STA_INFO_TX_BYTES) |
+			BIT(NL80211_STA_INFO_RX_PACKETS) | BIT(NL80211_STA_INFO_TX_PACKETS) |
+			BIT(NL80211_STA_INFO_TX_BITRATE) |
+			BIT(NL80211_STA_INFO_SIGNAL) | BIT(NL80211_STA_INFO_SIGNAL_AVG);
 
 	/* Get signal information from the firmware */
 	if (mwifiex_send_cmd(priv, HostCmd_CMD_RSSI_INFO,
@@ -944,7 +944,7 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 	sinfo->txrate.legacy = rate * 5;
 
 	if (priv->bss_mode == NL80211_IFTYPE_STATION) {
-		sinfo->filled |= STATION_INFO_BSS_PARAM;
+		sinfo->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
 		sinfo->bss_param.flags = 0;
 		if (priv->curr_bss_params.bss_descriptor.cap_info_bitmap &
 						WLAN_CAPABILITY_SHORT_PREAMBLE)
diff --git a/drivers/net/wireless/mwifiex/uap_event.c b/drivers/net/wireless/mwifiex/uap_event.c
index c54a537e31f..3b3a970e208 100644
--- a/drivers/net/wireless/mwifiex/uap_event.c
+++ b/drivers/net/wireless/mwifiex/uap_event.c
@@ -68,7 +68,6 @@ int mwifiex_process_uap_event(struct mwifiex_private *priv)
 				len = ETH_ALEN;
 
 			if (len != -1) {
-				sinfo.filled = STATION_INFO_ASSOC_REQ_IES;
 				sinfo.assoc_req_ies = &event->data[len];
 				len = (u8 *)sinfo.assoc_req_ies -
 				      (u8 *)&event->frame_control;
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 1a4facd1fbf..60d44ce9c01 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -2478,7 +2478,7 @@ static void rndis_fill_station_info(struct usbnet *usbdev,
 	ret = rndis_query_oid(usbdev, RNDIS_OID_GEN_LINK_SPEED, &linkspeed, &len);
 	if (ret == 0) {
 		sinfo->txrate.legacy = le32_to_cpu(linkspeed) / 1000;
-		sinfo->filled |= STATION_INFO_TX_BITRATE;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
 	}
 
 	len = sizeof(rssi);
@@ -2486,7 +2486,7 @@ static void rndis_fill_station_info(struct usbnet *usbdev,
 			      &rssi, &len);
 	if (ret == 0) {
 		sinfo->signal = level_to_qual(le32_to_cpu(rssi));
-		sinfo->filled |= STATION_INFO_SIGNAL;
+		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 	}
 }
 
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 8d11b0ca412..a2133b1fd63 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -5401,7 +5401,7 @@ static void wlcore_op_sta_statistics(struct ieee80211_hw *hw,
 	if (ret < 0)
 		goto out_sleep;
 
-	sinfo->filled |= STATION_INFO_SIGNAL;
+	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 	sinfo->signal = rssi_dbm;
 
 out_sleep:
diff --git a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
index 3d26955da72..c76874d72a2 100644
--- a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
@@ -1092,17 +1092,17 @@ static int cfg80211_rtw_get_station(struct wiphy *wiphy,
 			goto exit;
 		}
 
-		sinfo->filled |= STATION_INFO_SIGNAL;
+		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 		sinfo->signal = translate_percentage_to_dbm(padapter->recvpriv.
 							    signal_strength);
 
-		sinfo->filled |= STATION_INFO_TX_BITRATE;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
 		sinfo->txrate.legacy = rtw_get_cur_max_rate(padapter);
 
-		sinfo->filled |= STATION_INFO_RX_PACKETS;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
 		sinfo->rx_packets = sta_rx_data_pkts(psta);
 
-		sinfo->filled |= STATION_INFO_TX_PACKETS;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
 		sinfo->tx_packets = psta->sta_stats.tx_pkts;
 	}
 
@@ -2365,7 +2365,6 @@ void rtw_cfg80211_indicate_sta_assoc(struct rtw_adapter *padapter,
 					     u.reassoc_req.variable);
 
 		sinfo.filled = 0;
-		sinfo.filled = STATION_INFO_ASSOC_REQ_IES;
 		sinfo.assoc_req_ies = pmgmt_frame + ie_offset;
 		sinfo.assoc_req_ies_len = frame_len - ie_offset;
 		cfg80211_new_sta(ndev, hdr->addr2, &sinfo, GFP_ATOMIC);
diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c
index 8942dcb4418..7c87aecf474 100644
--- a/drivers/staging/wlan-ng/cfg80211.c
+++ b/drivers/staging/wlan-ng/cfg80211.c
@@ -325,9 +325,9 @@ static int prism2_get_station(struct wiphy *wiphy, struct net_device *dev,
 
 	if (result == 0) {
 		sinfo->txrate.legacy = quality.txrate.data;
-		sinfo->filled |= STATION_INFO_TX_BITRATE;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
 		sinfo->signal = quality.level.data;
-		sinfo->filled |= STATION_INFO_SIGNAL;
+		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 	}
 
 	return result;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 42e3d74f190..91c133626c3 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -865,75 +865,6 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
 				  struct station_parameters *params,
 				  enum cfg80211_station_type statype);
 
-/**
- * enum station_info_flags - station information flags
- *
- * Used by the driver to indicate which info in &struct station_info
- * it has filled in during get_station() or dump_station().
- *
- * @STATION_INFO_INACTIVE_TIME: @inactive_time filled
- * @STATION_INFO_RX_BYTES: @rx_bytes filled
- * @STATION_INFO_TX_BYTES: @tx_bytes filled
- * @STATION_INFO_RX_BYTES64: @rx_bytes filled with 64-bit value
- * @STATION_INFO_TX_BYTES64: @tx_bytes filled with 64-bit value
- * @STATION_INFO_LLID: @llid filled
- * @STATION_INFO_PLID: @plid filled
- * @STATION_INFO_PLINK_STATE: @plink_state filled
- * @STATION_INFO_SIGNAL: @signal filled
- * @STATION_INFO_TX_BITRATE: @txrate fields are filled
- *	(tx_bitrate, tx_bitrate_flags and tx_bitrate_mcs)
- * @STATION_INFO_RX_PACKETS: @rx_packets filled with 32-bit value
- * @STATION_INFO_TX_PACKETS: @tx_packets filled with 32-bit value
- * @STATION_INFO_TX_RETRIES: @tx_retries filled
- * @STATION_INFO_TX_FAILED: @tx_failed filled
- * @STATION_INFO_RX_DROP_MISC: @rx_dropped_misc filled
- * @STATION_INFO_SIGNAL_AVG: @signal_avg filled
- * @STATION_INFO_RX_BITRATE: @rxrate fields are filled
- * @STATION_INFO_BSS_PARAM: @bss_param filled
- * @STATION_INFO_CONNECTED_TIME: @connected_time filled
- * @STATION_INFO_ASSOC_REQ_IES: @assoc_req_ies filled
- * @STATION_INFO_STA_FLAGS: @sta_flags filled
- * @STATION_INFO_BEACON_LOSS_COUNT: @beacon_loss_count filled
- * @STATION_INFO_T_OFFSET: @t_offset filled
- * @STATION_INFO_LOCAL_PM: @local_pm filled
- * @STATION_INFO_PEER_PM: @peer_pm filled
- * @STATION_INFO_NONPEER_PM: @nonpeer_pm filled
- * @STATION_INFO_CHAIN_SIGNAL: @chain_signal filled
- * @STATION_INFO_CHAIN_SIGNAL_AVG: @chain_signal_avg filled
- * @STATION_INFO_EXPECTED_THROUGHPUT: @expected_throughput filled
- */
-enum station_info_flags {
-	STATION_INFO_INACTIVE_TIME		= BIT(0),
-	STATION_INFO_RX_BYTES			= BIT(1),
-	STATION_INFO_TX_BYTES			= BIT(2),
-	STATION_INFO_LLID			= BIT(3),
-	STATION_INFO_PLID			= BIT(4),
-	STATION_INFO_PLINK_STATE		= BIT(5),
-	STATION_INFO_SIGNAL			= BIT(6),
-	STATION_INFO_TX_BITRATE			= BIT(7),
-	STATION_INFO_RX_PACKETS			= BIT(8),
-	STATION_INFO_TX_PACKETS			= BIT(9),
-	STATION_INFO_TX_RETRIES			= BIT(10),
-	STATION_INFO_TX_FAILED			= BIT(11),
-	STATION_INFO_RX_DROP_MISC		= BIT(12),
-	STATION_INFO_SIGNAL_AVG			= BIT(13),
-	STATION_INFO_RX_BITRATE			= BIT(14),
-	STATION_INFO_BSS_PARAM			= BIT(15),
-	STATION_INFO_CONNECTED_TIME		= BIT(16),
-	STATION_INFO_ASSOC_REQ_IES		= BIT(17),
-	STATION_INFO_STA_FLAGS			= BIT(18),
-	STATION_INFO_BEACON_LOSS_COUNT		= BIT(19),
-	STATION_INFO_T_OFFSET			= BIT(20),
-	STATION_INFO_LOCAL_PM			= BIT(21),
-	STATION_INFO_PEER_PM			= BIT(22),
-	STATION_INFO_NONPEER_PM			= BIT(23),
-	STATION_INFO_RX_BYTES64			= BIT(24),
-	STATION_INFO_TX_BYTES64			= BIT(25),
-	STATION_INFO_CHAIN_SIGNAL		= BIT(26),
-	STATION_INFO_CHAIN_SIGNAL_AVG		= BIT(27),
-	STATION_INFO_EXPECTED_THROUGHPUT	= BIT(28),
-};
-
 /**
  * enum station_info_rate_flags - bitrate info flags
  *
@@ -1015,7 +946,8 @@ struct sta_bss_parameters {
  *
  * Station information filled by driver for get_station() and dump_station.
  *
- * @filled: bitflag of flags from &enum station_info_flags
+ * @filled: bitflag of flags using the bits of &enum nl80211_sta_info to
+ *	indicate the relevant values in this struct for them
  * @connected_time: time(in secs) since a station is last connected
  * @inactive_time: time since last station activity (tx/rx) in milliseconds
  * @rx_bytes: bytes received from this station
@@ -1094,11 +1026,6 @@ struct station_info {
 	enum nl80211_mesh_power_mode nonpeer_pm;
 
 	u32 expected_throughput;
-
-	/*
-	 * Note: Add a new enum station_info_flags value for each new field and
-	 * use it to check which fields are initialized.
-	 */
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 2f549a25313..e48ca0bbd07 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2373,6 +2373,8 @@ enum nl80211_sta_bss_param {
  *	Same format as NL80211_STA_INFO_CHAIN_SIGNAL.
  * @NL80211_STA_EXPECTED_THROUGHPUT: expected throughput considering also the
  *	802.11 header (u32, kbps)
+ * @NL80211_STA_INFO_RX_DROP_MISC: RX packets dropped for unspecified reasons
+ *	(u64)
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -2405,6 +2407,7 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_CHAIN_SIGNAL,
 	NL80211_STA_INFO_CHAIN_SIGNAL_AVG,
 	NL80211_STA_INFO_EXPECTED_THROUGHPUT,
+	NL80211_STA_INFO_RX_DROP_MISC,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c
index eea742710c0..52bcea6ad9e 100644
--- a/net/mac80211/ethtool.c
+++ b/net/mac80211/ethtool.c
@@ -117,16 +117,16 @@ static void ieee80211_get_stats(struct net_device *dev,
 		data[i++] = sta->sta_state;
 
 
-		if (sinfo.filled & STATION_INFO_TX_BITRATE)
+		if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE))
 			data[i] = 100000 *
 				cfg80211_calculate_bitrate(&sinfo.txrate);
 		i++;
-		if (sinfo.filled & STATION_INFO_RX_BITRATE)
+		if (sinfo.filled & BIT(NL80211_STA_INFO_RX_BITRATE))
 			data[i] = 100000 *
 				cfg80211_calculate_bitrate(&sinfo.rxrate);
 		i++;
 
-		if (sinfo.filled & STATION_INFO_SIGNAL_AVG)
+		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))
 			data[i] = (u8)sinfo.signal_avg;
 		i++;
 	} else {
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 967b42eae5c..64b53b943d9 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1756,51 +1756,51 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 
 	drv_sta_statistics(local, sdata, &sta->sta, sinfo);
 
-	sinfo->filled |= STATION_INFO_INACTIVE_TIME |
-			 STATION_INFO_STA_FLAGS |
-			 STATION_INFO_BSS_PARAM |
-			 STATION_INFO_CONNECTED_TIME |
-			 STATION_INFO_RX_DROP_MISC |
-			 STATION_INFO_BEACON_LOSS_COUNT;
+	sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) |
+			 BIT(NL80211_STA_INFO_STA_FLAGS) |
+			 BIT(NL80211_STA_INFO_BSS_PARAM) |
+			 BIT(NL80211_STA_INFO_CONNECTED_TIME) |
+			 BIT(NL80211_STA_INFO_RX_DROP_MISC) |
+			 BIT(NL80211_STA_INFO_BEACON_LOSS);
 
 	ktime_get_ts(&uptime);
 	sinfo->connected_time = uptime.tv_sec - sta->last_connected;
 	sinfo->inactive_time = jiffies_to_msecs(jiffies - sta->last_rx);
 
-	if (!(sinfo->filled & (STATION_INFO_TX_BYTES64 |
-			       STATION_INFO_TX_BYTES))) {
+	if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) |
+			       BIT(NL80211_STA_INFO_TX_BYTES)))) {
 		sinfo->tx_bytes = 0;
 		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
 			sinfo->tx_bytes += sta->tx_bytes[ac];
-		sinfo->filled |= STATION_INFO_TX_BYTES64;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
 	}
 
-	if (!(sinfo->filled & STATION_INFO_TX_PACKETS)) {
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_PACKETS))) {
 		sinfo->tx_packets = 0;
 		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
 			sinfo->tx_packets += sta->tx_packets[ac];
-		sinfo->filled |= STATION_INFO_TX_PACKETS;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
 	}
 
-	if (!(sinfo->filled & (STATION_INFO_RX_BYTES64 |
-			       STATION_INFO_RX_BYTES))) {
+	if (!(sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES64) |
+			       BIT(NL80211_STA_INFO_RX_BYTES)))) {
 		sinfo->rx_bytes = sta->rx_bytes;
-		sinfo->filled |= STATION_INFO_RX_BYTES64;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
 	}
 
-	if (!(sinfo->filled & STATION_INFO_RX_PACKETS)) {
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_PACKETS))) {
 		sinfo->rx_packets = sta->rx_packets;
-		sinfo->filled |= STATION_INFO_RX_PACKETS;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
 	}
 
-	if (!(sinfo->filled & STATION_INFO_TX_RETRIES)) {
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_RETRIES))) {
 		sinfo->tx_retries = sta->tx_retry_count;
-		sinfo->filled |= STATION_INFO_TX_RETRIES;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_RETRIES);
 	}
 
-	if (!(sinfo->filled & STATION_INFO_TX_FAILED)) {
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_FAILED))) {
 		sinfo->tx_failed = sta->tx_retry_failed;
-		sinfo->filled |= STATION_INFO_TX_FAILED;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
 	}
 
 	sinfo->rx_dropped_misc = sta->rx_dropped;
@@ -1808,22 +1808,22 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 
 	if ((sta->local->hw.flags & IEEE80211_HW_SIGNAL_DBM) ||
 	    (sta->local->hw.flags & IEEE80211_HW_SIGNAL_UNSPEC)) {
-		if (!(sinfo->filled & STATION_INFO_SIGNAL)) {
+		if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) {
 			sinfo->signal = (s8)sta->last_signal;
-			sinfo->filled |= STATION_INFO_SIGNAL;
+			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
 		}
 
-		if (!(sinfo->filled & STATION_INFO_SIGNAL_AVG)) {
+		if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) {
 			sinfo->signal_avg = (s8) -ewma_read(&sta->avg_signal);
-			sinfo->filled |= STATION_INFO_SIGNAL_AVG;
+			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
 		}
 	}
 
 	if (sta->chains &&
-	    !(sinfo->filled & (STATION_INFO_CHAIN_SIGNAL |
-			       STATION_INFO_CHAIN_SIGNAL_AVG))) {
-		sinfo->filled |= STATION_INFO_CHAIN_SIGNAL |
-				 STATION_INFO_CHAIN_SIGNAL_AVG;
+	    !(sinfo->filled & (BIT(NL80211_STA_INFO_CHAIN_SIGNAL) |
+			       BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) {
+		sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL) |
+				 BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG);
 
 		sinfo->chains = sta->chains;
 		for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) {
@@ -1833,30 +1833,30 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		}
 	}
 
-	if (!(sinfo->filled & STATION_INFO_TX_BITRATE)) {
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE))) {
 		sta_set_rate_info_tx(sta, &sta->last_tx_rate, &sinfo->txrate);
-		sinfo->filled |= STATION_INFO_TX_BITRATE;
+		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
 	}
 
-	if (!(sinfo->filled & STATION_INFO_RX_BITRATE)) {
+	if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE))) {
 		sta_set_rate_info_rx(sta, &sinfo->rxrate);
-		sinfo->filled |= STATION_INFO_RX_BITRATE;
+		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
 	}
 
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
-		sinfo->filled |= STATION_INFO_LLID |
-				 STATION_INFO_PLID |
-				 STATION_INFO_PLINK_STATE |
-				 STATION_INFO_LOCAL_PM |
-				 STATION_INFO_PEER_PM |
-				 STATION_INFO_NONPEER_PM;
+		sinfo->filled |= BIT(NL80211_STA_INFO_LLID) |
+				 BIT(NL80211_STA_INFO_PLID) |
+				 BIT(NL80211_STA_INFO_PLINK_STATE) |
+				 BIT(NL80211_STA_INFO_LOCAL_PM) |
+				 BIT(NL80211_STA_INFO_PEER_PM) |
+				 BIT(NL80211_STA_INFO_NONPEER_PM);
 
 		sinfo->llid = sta->llid;
 		sinfo->plid = sta->plid;
 		sinfo->plink_state = sta->plink_state;
 		if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) {
-			sinfo->filled |= STATION_INFO_T_OFFSET;
+			sinfo->filled |= BIT(NL80211_STA_INFO_T_OFFSET);
 			sinfo->t_offset = sta->t_offset;
 		}
 		sinfo->local_pm = sta->local_pm;
@@ -1905,7 +1905,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		thr = drv_get_expected_throughput(local, &sta->sta);
 
 	if (thr != 0) {
-		sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT;
+		sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT);
 		sinfo->expected_throughput = thr;
 	}
 }
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index a75dc91976d..68faf8a2aa4 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3671,115 +3671,77 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	sinfoattr = nla_nest_start(msg, NL80211_ATTR_STA_INFO);
 	if (!sinfoattr)
 		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_CONNECTED_TIME) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_CONNECTED_TIME,
-			sinfo->connected_time))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_INACTIVE_TIME) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_INACTIVE_TIME,
-			sinfo->inactive_time))
-		goto nla_put_failure;
-	if ((sinfo->filled & (STATION_INFO_RX_BYTES |
-			      STATION_INFO_RX_BYTES64)) &&
+
+#define PUT_SINFO(attr, memb, type) do {				\
+	if (sinfo->filled & BIT(NL80211_STA_INFO_ ## attr) &&		\
+	    nla_put_ ## type(msg, NL80211_STA_INFO_ ## attr,		\
+			     sinfo->memb))				\
+		goto nla_put_failure;					\
+	} while (0)
+
+	PUT_SINFO(CONNECTED_TIME, connected_time, u32);
+	PUT_SINFO(INACTIVE_TIME, inactive_time, u32);
+
+	if (sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES) |
+			     BIT(NL80211_STA_INFO_RX_BYTES64)) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_RX_BYTES,
 			(u32)sinfo->rx_bytes))
 		goto nla_put_failure;
-	if ((sinfo->filled & (STATION_INFO_TX_BYTES |
-			      STATION_INFO_TX_BYTES64)) &&
+
+	if (sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES) |
+			     BIT(NL80211_STA_INFO_TX_BYTES64)) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_TX_BYTES,
 			(u32)sinfo->tx_bytes))
 		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_RX_BYTES64) &&
-	    nla_put_u64(msg, NL80211_STA_INFO_RX_BYTES64,
-			sinfo->rx_bytes))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_BYTES64) &&
-	    nla_put_u64(msg, NL80211_STA_INFO_TX_BYTES64,
-			sinfo->tx_bytes))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_LLID) &&
-	    nla_put_u16(msg, NL80211_STA_INFO_LLID, sinfo->llid))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_PLID) &&
-	    nla_put_u16(msg, NL80211_STA_INFO_PLID, sinfo->plid))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_PLINK_STATE) &&
-	    nla_put_u8(msg, NL80211_STA_INFO_PLINK_STATE,
-		       sinfo->plink_state))
-		goto nla_put_failure;
+
+	PUT_SINFO(RX_BYTES64, rx_bytes, u64);
+	PUT_SINFO(TX_BYTES64, tx_bytes, u64);
+	PUT_SINFO(LLID, llid, u16);
+	PUT_SINFO(PLID, plid, u16);
+	PUT_SINFO(PLINK_STATE, plink_state, u8);
+
 	switch (rdev->wiphy.signal_type) {
 	case CFG80211_SIGNAL_TYPE_MBM:
-		if ((sinfo->filled & STATION_INFO_SIGNAL) &&
-		    nla_put_u8(msg, NL80211_STA_INFO_SIGNAL,
-			       sinfo->signal))
-			goto nla_put_failure;
-		if ((sinfo->filled & STATION_INFO_SIGNAL_AVG) &&
-		    nla_put_u8(msg, NL80211_STA_INFO_SIGNAL_AVG,
-			       sinfo->signal_avg))
-			goto nla_put_failure;
+		PUT_SINFO(SIGNAL, signal, u8);
+		PUT_SINFO(SIGNAL_AVG, signal_avg, u8);
 		break;
 	default:
 		break;
 	}
-	if (sinfo->filled & STATION_INFO_CHAIN_SIGNAL) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL)) {
 		if (!nl80211_put_signal(msg, sinfo->chains,
 					sinfo->chain_signal,
 					NL80211_STA_INFO_CHAIN_SIGNAL))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & STATION_INFO_CHAIN_SIGNAL_AVG) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) {
 		if (!nl80211_put_signal(msg, sinfo->chains,
 					sinfo->chain_signal_avg,
 					NL80211_STA_INFO_CHAIN_SIGNAL_AVG))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & STATION_INFO_TX_BITRATE) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE)) {
 		if (!nl80211_put_sta_rate(msg, &sinfo->txrate,
 					  NL80211_STA_INFO_TX_BITRATE))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & STATION_INFO_RX_BITRATE) {
+	if (sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE)) {
 		if (!nl80211_put_sta_rate(msg, &sinfo->rxrate,
 					  NL80211_STA_INFO_RX_BITRATE))
 			goto nla_put_failure;
 	}
-	if ((sinfo->filled & STATION_INFO_RX_PACKETS) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_RX_PACKETS,
-			sinfo->rx_packets))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_PACKETS) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_TX_PACKETS,
-			sinfo->tx_packets))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_RETRIES) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_TX_RETRIES,
-			sinfo->tx_retries))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_TX_FAILED) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_TX_FAILED,
-			sinfo->tx_failed))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_EXPECTED_THROUGHPUT) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_EXPECTED_THROUGHPUT,
-			sinfo->expected_throughput))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_BEACON_LOSS_COUNT) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_BEACON_LOSS,
-			sinfo->beacon_loss_count))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_LOCAL_PM) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_LOCAL_PM,
-			sinfo->local_pm))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_PEER_PM) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_PEER_PM,
-			sinfo->peer_pm))
-		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_NONPEER_PM) &&
-	    nla_put_u32(msg, NL80211_STA_INFO_NONPEER_PM,
-			sinfo->nonpeer_pm))
-		goto nla_put_failure;
-	if (sinfo->filled & STATION_INFO_BSS_PARAM) {
+
+	PUT_SINFO(RX_PACKETS, rx_packets, u32);
+	PUT_SINFO(TX_PACKETS, tx_packets, u32);
+	PUT_SINFO(TX_RETRIES, tx_retries, u32);
+	PUT_SINFO(TX_FAILED, tx_failed, u32);
+	PUT_SINFO(EXPECTED_THROUGHPUT, expected_throughput, u32);
+	PUT_SINFO(BEACON_LOSS, beacon_loss_count, u32);
+	PUT_SINFO(LOCAL_PM, local_pm, u32);
+	PUT_SINFO(PEER_PM, peer_pm, u32);
+	PUT_SINFO(NONPEER_PM, nonpeer_pm, u32);
+
+	if (sinfo->filled & BIT(NL80211_STA_INFO_BSS_PARAM)) {
 		bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM);
 		if (!bss_param)
 			goto nla_put_failure;
@@ -3798,18 +3760,19 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 
 		nla_nest_end(msg, bss_param);
 	}
-	if ((sinfo->filled & STATION_INFO_STA_FLAGS) &&
+	if ((sinfo->filled & BIT(NL80211_STA_INFO_STA_FLAGS)) &&
 	    nla_put(msg, NL80211_STA_INFO_STA_FLAGS,
 		    sizeof(struct nl80211_sta_flag_update),
 		    &sinfo->sta_flags))
 		goto nla_put_failure;
-	if ((sinfo->filled & STATION_INFO_T_OFFSET) &&
-		nla_put_u64(msg, NL80211_STA_INFO_T_OFFSET,
-			    sinfo->t_offset))
-		goto nla_put_failure;
+
+	PUT_SINFO(T_OFFSET, t_offset, u64);
+	PUT_SINFO(RX_DROP_MISC, rx_dropped_misc, u64);
+
+#undef PUT_SINFO
 	nla_nest_end(msg, sinfoattr);
 
-	if ((sinfo->filled & STATION_INFO_ASSOC_REQ_IES) &&
+	if (sinfo->assoc_req_ies_len &&
 	    nla_put(msg, NL80211_ATTR_IE, sinfo->assoc_req_ies_len,
 		    sinfo->assoc_req_ies))
 		goto nla_put_failure;
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 0f47948c572..5b24d39d790 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -1300,7 +1300,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev,
 	if (err)
 		return err;
 
-	if (!(sinfo.filled & STATION_INFO_TX_BITRATE))
+	if (!(sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)))
 		return -EOPNOTSUPP;
 
 	rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate);
@@ -1340,7 +1340,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 
 	switch (rdev->wiphy.signal_type) {
 	case CFG80211_SIGNAL_TYPE_MBM:
-		if (sinfo.filled & STATION_INFO_SIGNAL) {
+		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
 			int sig = sinfo.signal;
 			wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
 			wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
@@ -1354,7 +1354,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 			break;
 		}
 	case CFG80211_SIGNAL_TYPE_UNSPEC:
-		if (sinfo.filled & STATION_INFO_SIGNAL) {
+		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
 			wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
 			wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
 			wstats.qual.level = sinfo.signal;
@@ -1367,9 +1367,9 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 	}
 
 	wstats.qual.updated |= IW_QUAL_NOISE_INVALID;
-	if (sinfo.filled & STATION_INFO_RX_DROP_MISC)
+	if (sinfo.filled & BIT(NL80211_STA_INFO_RX_DROP_MISC))
 		wstats.discard.misc = sinfo.rx_dropped_misc;
-	if (sinfo.filled & STATION_INFO_TX_FAILED)
+	if (sinfo.filled & BIT(NL80211_STA_INFO_TX_FAILED))
 		wstats.discard.retries = sinfo.tx_failed;
 
 	return &wstats;
-- 
cgit v1.2.3-70-g09d2


From a76b1942a10293a94edf3c93c23a6231b63532f5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 17 Nov 2014 14:12:22 +0100
Subject: cfg80211: add nl80211 beacon-only statistics

Add these two values:
 * BEACON_RX: number of beacons received from this peer
 * BEACON_SIGNAL_AVG: signal strength average for beacons only

These can then be used for Android Lollipop's statistics request.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 6 ++++++
 include/uapi/linux/nl80211.h | 5 +++++
 net/wireless/nl80211.c       | 2 ++
 3 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 91c133626c3..ef26ce16b05 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -987,6 +987,9 @@ struct sta_bss_parameters {
  * @nonpeer_pm: non-peer mesh STA power save mode
  * @expected_throughput: expected throughput in kbps (including 802.11 headers)
  *	towards this station.
+ * @rx_beacon: number of beacons received from this peer
+ * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received
+ *	from this peer
  */
 struct station_info {
 	u32 filled;
@@ -1026,6 +1029,9 @@ struct station_info {
 	enum nl80211_mesh_power_mode nonpeer_pm;
 
 	u32 expected_throughput;
+
+	u64 rx_beacon;
+	u8 rx_beacon_signal_avg;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index e48ca0bbd07..0c3d341c0ae 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2375,6 +2375,9 @@ enum nl80211_sta_bss_param {
  *	802.11 header (u32, kbps)
  * @NL80211_STA_INFO_RX_DROP_MISC: RX packets dropped for unspecified reasons
  *	(u64)
+ * @NL80211_STA_INFO_BEACON_RX: number of beacons received from this peer (u64)
+ * @NL80211_STA_INFO_BEACON_SIGNAL_AVG: signal strength average
+ *	for beacons only (u8, dBm)
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -2408,6 +2411,8 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_CHAIN_SIGNAL_AVG,
 	NL80211_STA_INFO_EXPECTED_THROUGHPUT,
 	NL80211_STA_INFO_RX_DROP_MISC,
+	NL80211_STA_INFO_BEACON_RX,
+	NL80211_STA_INFO_BEACON_SIGNAL_AVG,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 68faf8a2aa4..42b968a1f99 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3768,6 +3768,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 
 	PUT_SINFO(T_OFFSET, t_offset, u64);
 	PUT_SINFO(RX_DROP_MISC, rx_dropped_misc, u64);
+	PUT_SINFO(BEACON_RX, rx_beacon, u64);
+	PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8);
 
 #undef PUT_SINFO
 	nla_nest_end(msg, sinfoattr);
-- 
cgit v1.2.3-70-g09d2


From 8d791361a4698ca6f01c361a47b39b30d26bf66c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 21 Nov 2014 12:40:05 +0100
Subject: nl80211: clarify packet statistics descriptions

The current statistics we keep aren't very clear, some are on
MPDUs and some on MSDUs/MMPDUs. Clarify the descriptions based
on the counters mac80211 keeps.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 12 ++++++------
 include/uapi/linux/nl80211.h | 24 +++++++++++++++---------
 2 files changed, 21 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ef26ce16b05..95420fb6160 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -950,8 +950,8 @@ struct sta_bss_parameters {
  *	indicate the relevant values in this struct for them
  * @connected_time: time(in secs) since a station is last connected
  * @inactive_time: time since last station activity (tx/rx) in milliseconds
- * @rx_bytes: bytes received from this station
- * @tx_bytes: bytes transmitted to this station
+ * @rx_bytes: bytes (size of MPDUs) received from this station
+ * @tx_bytes: bytes (size of MPDUs) transmitted to this station
  * @llid: mesh local link id
  * @plid: mesh peer link id
  * @plink_state: mesh peer link state
@@ -964,10 +964,10 @@ struct sta_bss_parameters {
  * @chain_signal_avg: per-chain signal strength average in dBm
  * @txrate: current unicast bitrate from this station
  * @rxrate: current unicast bitrate to this station
- * @rx_packets: packets received from this station
- * @tx_packets: packets transmitted to this station
- * @tx_retries: cumulative retry counts
- * @tx_failed: number of failed transmissions (retries exceeded, no ACK)
+ * @rx_packets: packets (MSDUs & MMPDUs) received from this station
+ * @tx_packets: packets (MSDUs & MMPDUs) transmitted to this station
+ * @tx_retries: cumulative retry counts (MPDUs)
+ * @tx_failed: number of failed transmissions (MPDUs) (retries exceeded, no ACK)
  * @rx_dropped_misc:  Dropped for un-specified reason.
  * @bss_param: current BSS parameters
  * @generation: generation number for nl80211 dumps.
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 0c3d341c0ae..b0fb5d59825 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2338,18 +2338,24 @@ enum nl80211_sta_bss_param {
  *
  * @__NL80211_STA_INFO_INVALID: attribute number 0 is reserved
  * @NL80211_STA_INFO_INACTIVE_TIME: time since last activity (u32, msecs)
- * @NL80211_STA_INFO_RX_BYTES: total received bytes (u32, from this station)
- * @NL80211_STA_INFO_TX_BYTES: total transmitted bytes (u32, to this station)
- * @NL80211_STA_INFO_RX_BYTES64: total received bytes (u64, from this station)
- * @NL80211_STA_INFO_TX_BYTES64: total transmitted bytes (u64, to this station)
+ * @NL80211_STA_INFO_RX_BYTES: total received bytes (MPDU length)
+ *	(u32, from this station)
+ * @NL80211_STA_INFO_TX_BYTES: total transmitted bytes (MPDU length)
+ *	(u32, to this station)
+ * @NL80211_STA_INFO_RX_BYTES64: total received bytes (MPDU length)
+ *	(u64, from this station)
+ * @NL80211_STA_INFO_TX_BYTES64: total transmitted bytes (MPDU length)
+ *	(u64, to this station)
  * @NL80211_STA_INFO_SIGNAL: signal strength of last received PPDU (u8, dBm)
  * @NL80211_STA_INFO_TX_BITRATE: current unicast tx rate, nested attribute
  * 	containing info as possible, see &enum nl80211_rate_info
- * @NL80211_STA_INFO_RX_PACKETS: total received packet (u32, from this station)
- * @NL80211_STA_INFO_TX_PACKETS: total transmitted packets (u32, to this
- *	station)
- * @NL80211_STA_INFO_TX_RETRIES: total retries (u32, to this station)
- * @NL80211_STA_INFO_TX_FAILED: total failed packets (u32, to this station)
+ * @NL80211_STA_INFO_RX_PACKETS: total received packet (MSDUs and MMPDUs)
+ *	(u32, from this station)
+ * @NL80211_STA_INFO_TX_PACKETS: total transmitted packets (MSDUs and MMPDUs)
+ *	(u32, to this station)
+ * @NL80211_STA_INFO_TX_RETRIES: total retries (MPDUs) (u32, to this station)
+ * @NL80211_STA_INFO_TX_FAILED: total failed packets (MPDUs)
+ *	(u32, to this station)
  * @NL80211_STA_INFO_SIGNAL_AVG: signal strength average (u8, dBm)
  * @NL80211_STA_INFO_LLID: the station's mesh LLID
  * @NL80211_STA_INFO_PLID: the station's mesh PLID
-- 
cgit v1.2.3-70-g09d2


From 6de39808cf1dd7b02bf42e7d8695d80f5eaf645d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 19 Dec 2014 12:34:00 +0100
Subject: nl80211: support per-TID station statistics

The base for the current statistics is pretty mixed up, support
exporting RX/TX statistics for MSDUs per TID. This (currently)
covers received MSDUs, transmitted MSDUs and retries/failures
thereof.

Doing it per TID for MSDUs makes more sense than say only per AC
because it's symmetric - we could export per-AC statistics for all
frames (which AC we used for transmission can be determined also
for management frames) but per TID is better and usually data
frames are really the ones we care about. Also, on RX we can't
determine the AC - but we do know the TID for any QoS MPDU we
received.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 21 +++++++++++++++++++++
 include/uapi/linux/nl80211.h | 31 +++++++++++++++++++++++++++++++
 net/wireless/nl80211.c       | 41 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 93 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 95420fb6160..197735788f1 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -939,6 +939,24 @@ struct sta_bss_parameters {
 	u16 beacon_interval;
 };
 
+/**
+ * struct cfg80211_tid_stats - per-TID statistics
+ * @filled: bitmap of flags using the bits of &enum nl80211_tid_stats to
+ *	indicate the relevant values in this struct are filled
+ * @rx_msdu: number of received MSDUs
+ * @tx_msdu: number of (attempted) transmitted MSDUs
+ * @tx_msdu_retries: number of retries (not counting the first) for
+ *	transmitted MSDUs
+ * @tx_msdu_failed: number of failed transmitted MSDUs
+ */
+struct cfg80211_tid_stats {
+	u32 filled;
+	u64 rx_msdu;
+	u64 tx_msdu;
+	u64 tx_msdu_retries;
+	u64 tx_msdu_failed;
+};
+
 #define IEEE80211_MAX_CHAINS	4
 
 /**
@@ -990,6 +1008,8 @@ struct sta_bss_parameters {
  * @rx_beacon: number of beacons received from this peer
  * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received
  *	from this peer
+ * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last
+ *	(IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs.
  */
 struct station_info {
 	u32 filled;
@@ -1032,6 +1052,7 @@ struct station_info {
 
 	u64 rx_beacon;
 	u8 rx_beacon_signal_avg;
+	struct cfg80211_tid_stats pertid[IEEE80211_NUM_TIDS + 1];
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index b0fb5d59825..a963d4824c5 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2384,6 +2384,11 @@ enum nl80211_sta_bss_param {
  * @NL80211_STA_INFO_BEACON_RX: number of beacons received from this peer (u64)
  * @NL80211_STA_INFO_BEACON_SIGNAL_AVG: signal strength average
  *	for beacons only (u8, dBm)
+ * @NL80211_STA_INFO_TID_STATS: per-TID statistics (see &enum nl80211_tid_stats)
+ *	This is a nested attribute where each the inner attribute number is the
+ *	TID+1 and the special TID 16 (i.e. value 17) is used for non-QoS frames;
+ *	each one of those is again nested with &enum nl80211_tid_stats
+ *	attributes carrying the actual values.
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -2419,12 +2424,38 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_RX_DROP_MISC,
 	NL80211_STA_INFO_BEACON_RX,
 	NL80211_STA_INFO_BEACON_SIGNAL_AVG,
+	NL80211_STA_INFO_TID_STATS,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
 	NL80211_STA_INFO_MAX = __NL80211_STA_INFO_AFTER_LAST - 1
 };
 
+/**
+ * enum nl80211_tid_stats - per TID statistics attributes
+ * @__NL80211_TID_STATS_INVALID: attribute number 0 is reserved
+ * @NL80211_TID_STATS_RX_MSDU: number of MSDUs received (u64)
+ * @NL80211_TID_STATS_TX_MSDU: number of MSDUs transmitted (or
+ *	attempted to transmit; u64)
+ * @NL80211_TID_STATS_TX_MSDU_RETRIES: number of retries for
+ *	transmitted MSDUs (not counting the first attempt; u64)
+ * @NL80211_TID_STATS_TX_MSDU_FAILED: number of failed transmitted
+ *	MSDUs (u64)
+ * @NUM_NL80211_TID_STATS: number of attributes here
+ * @NL80211_TID_STATS_MAX: highest numbered attribute here
+ */
+enum nl80211_tid_stats {
+	__NL80211_TID_STATS_INVALID,
+	NL80211_TID_STATS_RX_MSDU,
+	NL80211_TID_STATS_TX_MSDU,
+	NL80211_TID_STATS_TX_MSDU_RETRIES,
+	NL80211_TID_STATS_TX_MSDU_FAILED,
+
+	/* keep last */
+	NUM_NL80211_TID_STATS,
+	NL80211_TID_STATS_MAX = NUM_NL80211_TID_STATS - 1
+};
+
 /**
  * enum nl80211_mpath_flags - nl80211 mesh path flags
  *
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 42b968a1f99..7c2ce26e22d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3772,6 +3772,47 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8);
 
 #undef PUT_SINFO
+
+	if (sinfo->filled & BIT(NL80211_STA_INFO_TID_STATS)) {
+		struct nlattr *tidsattr;
+		int tid;
+
+		tidsattr = nla_nest_start(msg, NL80211_STA_INFO_TID_STATS);
+		if (!tidsattr)
+			goto nla_put_failure;
+
+		for (tid = 0; tid < IEEE80211_NUM_TIDS + 1; tid++) {
+			struct cfg80211_tid_stats *tidstats;
+			struct nlattr *tidattr;
+
+			tidstats = &sinfo->pertid[tid];
+
+			if (!tidstats->filled)
+				continue;
+
+			tidattr = nla_nest_start(msg, tid + 1);
+			if (!tidattr)
+				goto nla_put_failure;
+
+#define PUT_TIDVAL(attr, memb, type) do {				\
+	if (tidstats->filled & BIT(NL80211_TID_STATS_ ## attr) &&	\
+	    nla_put_ ## type(msg, NL80211_TID_STATS_ ## attr,		\
+			     tidstats->memb))				\
+		goto nla_put_failure;					\
+	} while (0)
+
+			PUT_TIDVAL(RX_MSDU, rx_msdu, u64);
+			PUT_TIDVAL(TX_MSDU, tx_msdu, u64);
+			PUT_TIDVAL(TX_MSDU_RETRIES, tx_msdu_retries, u64);
+			PUT_TIDVAL(TX_MSDU_FAILED, tx_msdu_failed, u64);
+
+#undef PUT_TIDVAL
+			nla_nest_end(msg, tidattr);
+		}
+
+		nla_nest_end(msg, tidsattr);
+	}
+
 	nla_nest_end(msg, sinfoattr);
 
 	if (sinfo->assoc_req_ies_len &&
-- 
cgit v1.2.3-70-g09d2


From e61f7d1c3c07a7e51036b0796749edb00deff845 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Thu, 8 Jan 2015 10:34:27 -0500
Subject: libata: Whitelist SSDs that are known to properly return zeroes after
 TRIM

As defined, the DRAT (Deterministic Read After Trim) and RZAT (Return
Zero After Trim) flags in the ATA Command Set are unreliable in the
sense that they only define what happens if the device successfully
executed the DSM TRIM command. TRIM is only advisory, however, and the
device is free to silently ignore all or parts of the request.

In practice this renders the DRAT and RZAT flags completely useless and
because the results are unpredictable we decided to disable discard in
MD for 3.18 to avoid the risk of data corruption.

Hardware vendors in the real world obviously need better guarantees than
what the standards bodies provide. Unfortuntely those guarantees are
encoded in product requirements documents rather than somewhere we can
key off of them programatically. So we are compelled to disabling
discard_zeroes_data for all devices unless we explicitly have data to
support whitelisting them.

This patch whitelists SSDs from a few of the main vendors. None of the
whitelists are based on written guarantees. They are purely based on
empirical evidence collected from internal and external users that have
tested or qualified these drives in RAID deployments.

The whitelist is only meant as a starting point and is by no means
comprehensive:

   - All intel SSD models except for 510
   - Micron M5?0/M600
   - Samsung SSDs
   - Seagate SSDs

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/libata-core.c | 31 +++++++++++++++++++++++++++----
 drivers/ata/libata-scsi.c | 10 ++++++----
 include/linux/libata.h    |  1 +
 3 files changed, 34 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 5c84fb5c337..23c2ae03a7a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4233,10 +4233,33 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "PIONEER DVD-RW  DVR-216D",	NULL,	ATA_HORKAGE_NOSETXFER },
 
 	/* devices that don't properly handle queued TRIM commands */
-	{ "Micron_M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
-	{ "Crucial_CT???M500SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
-	{ "Micron_M550*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
-	{ "Crucial_CT*M550SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Micron_M[56]*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
+						ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "Crucial_CT*SSD*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
+
+	/*
+	 * As defined, the DRAT (Deterministic Read After Trim) and RZAT
+	 * (Return Zero After Trim) flags in the ATA Command Set are
+	 * unreliable in the sense that they only define what happens if
+	 * the device successfully executed the DSM TRIM command. TRIM
+	 * is only advisory, however, and the device is free to silently
+	 * ignore all or parts of the request.
+	 *
+	 * Whitelist drives that are known to reliably return zeroes
+	 * after TRIM.
+	 */
+
+	/*
+	 * The intel 510 drive has buggy DRAT/RZAT. Explicitly exclude
+	 * that model before whitelisting all other intel SSDs.
+	 */
+	{ "INTEL*SSDSC2MH*",		NULL,	0, },
+
+	{ "INTEL*SSD*", 		NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "SSD*INTEL*",			NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "Samsung*SSD*",		NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "SAMSUNG*SSD*",		NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
+	{ "ST[1248][0248]0[FH]*",	NULL,	ATA_HORKAGE_ZERO_AFTER_TRIM, },
 
 	/*
 	 * Some WD SATA-I drives spin up and down erratically when the link
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index e364e86e84d..6abd17a85b1 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -2532,13 +2532,15 @@ static unsigned int ata_scsiop_read_cap(struct ata_scsi_args *args, u8 *rbuf)
 		rbuf[15] = lowest_aligned;
 
 		if (ata_id_has_trim(args->id)) {
-			rbuf[14] |= 0x80; /* TPE */
+			rbuf[14] |= 0x80; /* LBPME */
 
-			if (ata_id_has_zero_after_trim(args->id))
-				rbuf[14] |= 0x40; /* TPRZ */
+			if (ata_id_has_zero_after_trim(args->id) &&
+			    dev->horkage & ATA_HORKAGE_ZERO_AFTER_TRIM) {
+				ata_dev_info(dev, "Enabling discard_zeroes_data\n");
+				rbuf[14] |= 0x40; /* LBPRZ */
+			}
 		}
 	}
-
 	return 0;
 }
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 2d182413b1d..f2b440e44fd 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -422,6 +422,7 @@ enum {
 	ATA_HORKAGE_NO_NCQ_TRIM	= (1 << 19),	/* don't use queued TRIM */
 	ATA_HORKAGE_NOLPM	= (1 << 20),	/* don't use LPM */
 	ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21),	/* some WDs have broken LPM */
+	ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
-- 
cgit v1.2.3-70-g09d2


From ad26aa6c60974acf3228ed0ade97ba5793093dbe Mon Sep 17 00:00:00 2001
From: Jonghwa Lee <jonghwa3.lee@samsung.com>
Date: Thu, 8 Jan 2015 11:04:07 +0900
Subject: regulator: s2mps11: Fix wrong calculation of register offset

This patch adds missing registers('BUCK7_SW' & 'LDO29_CTRL'). Since BUCK7 has
1 more register (BUCK7_SW) than others, register offset should
be added one more for which has bigger address than BUCK7 registers.

Fixes: 76b9840b24ae04(regulator: s2mps11: Add support S2MPS13 regulator device)
Signed-off-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: <stable@vger.kernel.org>
---
 drivers/regulator/s2mps11.c         | 42 +++++++++++++++++++++++++++++++++----
 include/linux/mfd/samsung/s2mps13.h |  2 ++
 2 files changed, 40 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index c1444c3d84c..13ca20ed33a 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -405,6 +405,40 @@ static struct regulator_ops s2mps14_reg_ops;
 	.enable_mask	= S2MPS14_ENABLE_MASK			\
 }
 
+#define regulator_desc_s2mps13_buck7(num, min, step, min_sel) {	\
+	.name		= "BUCK"#num,				\
+	.id		= S2MPS13_BUCK##num,			\
+	.ops		= &s2mps14_reg_ops,			\
+	.type		= REGULATOR_VOLTAGE,			\
+	.owner		= THIS_MODULE,				\
+	.min_uV		= min,					\
+	.uV_step	= step,					\
+	.linear_min_sel	= min_sel,				\
+	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
+	.ramp_delay	= S2MPS13_BUCK_RAMP_DELAY,		\
+	.vsel_reg	= S2MPS13_REG_B1OUT + (num) * 2 - 1,	\
+	.vsel_mask	= S2MPS14_BUCK_VSEL_MASK,		\
+	.enable_reg	= S2MPS13_REG_B1CTRL + (num - 1) * 2,	\
+	.enable_mask	= S2MPS14_ENABLE_MASK			\
+}
+
+#define regulator_desc_s2mps13_buck8_10(num, min, step, min_sel) {	\
+	.name		= "BUCK"#num,				\
+	.id		= S2MPS13_BUCK##num,			\
+	.ops		= &s2mps14_reg_ops,			\
+	.type		= REGULATOR_VOLTAGE,			\
+	.owner		= THIS_MODULE,				\
+	.min_uV		= min,					\
+	.uV_step	= step,					\
+	.linear_min_sel	= min_sel,				\
+	.n_voltages	= S2MPS14_BUCK_N_VOLTAGES,		\
+	.ramp_delay	= S2MPS13_BUCK_RAMP_DELAY,		\
+	.vsel_reg	= S2MPS13_REG_B1OUT + (num) * 2 - 1,	\
+	.vsel_mask	= S2MPS14_BUCK_VSEL_MASK,		\
+	.enable_reg	= S2MPS13_REG_B1CTRL + (num) * 2 - 1,	\
+	.enable_mask	= S2MPS14_ENABLE_MASK			\
+}
+
 static const struct regulator_desc s2mps13_regulators[] = {
 	regulator_desc_s2mps13_ldo(1,  MIN_800_MV,  STEP_12_5_MV, 0x00),
 	regulator_desc_s2mps13_ldo(2,  MIN_1400_MV, STEP_50_MV,   0x0C),
@@ -452,10 +486,10 @@ static const struct regulator_desc s2mps13_regulators[] = {
 	regulator_desc_s2mps13_buck(4,  MIN_500_MV,  STEP_6_25_MV, 0x10),
 	regulator_desc_s2mps13_buck(5,  MIN_500_MV,  STEP_6_25_MV, 0x10),
 	regulator_desc_s2mps13_buck(6,  MIN_500_MV,  STEP_6_25_MV, 0x10),
-	regulator_desc_s2mps13_buck(7,  MIN_500_MV,  STEP_6_25_MV, 0x10),
-	regulator_desc_s2mps13_buck(8,  MIN_1000_MV, STEP_12_5_MV, 0x20),
-	regulator_desc_s2mps13_buck(9,  MIN_1000_MV, STEP_12_5_MV, 0x20),
-	regulator_desc_s2mps13_buck(10, MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck7(7,  MIN_500_MV,  STEP_6_25_MV, 0x10),
+	regulator_desc_s2mps13_buck8_10(8,  MIN_1000_MV, STEP_12_5_MV, 0x20),
+	regulator_desc_s2mps13_buck8_10(9,  MIN_1000_MV, STEP_12_5_MV, 0x20),
+	regulator_desc_s2mps13_buck8_10(10, MIN_500_MV,  STEP_6_25_MV, 0x10),
 };
 
 static int s2mps14_regulator_enable(struct regulator_dev *rdev)
diff --git a/include/linux/mfd/samsung/s2mps13.h b/include/linux/mfd/samsung/s2mps13.h
index ce5dda8958f..b1fd675fa36 100644
--- a/include/linux/mfd/samsung/s2mps13.h
+++ b/include/linux/mfd/samsung/s2mps13.h
@@ -59,6 +59,7 @@ enum s2mps13_reg {
 	S2MPS13_REG_B6CTRL,
 	S2MPS13_REG_B6OUT,
 	S2MPS13_REG_B7CTRL,
+	S2MPS13_REG_B7SW,
 	S2MPS13_REG_B7OUT,
 	S2MPS13_REG_B8CTRL,
 	S2MPS13_REG_B8OUT,
@@ -102,6 +103,7 @@ enum s2mps13_reg {
 	S2MPS13_REG_L26CTRL,
 	S2MPS13_REG_L27CTRL,
 	S2MPS13_REG_L28CTRL,
+	S2MPS13_REG_L29CTRL,
 	S2MPS13_REG_L30CTRL,
 	S2MPS13_REG_L31CTRL,
 	S2MPS13_REG_L32CTRL,
-- 
cgit v1.2.3-70-g09d2


From 277880a356c10adcb43604f6ab9ec9b2d64db8b2 Mon Sep 17 00:00:00 2001
From: Oder Chiou <oder_chiou@realtek.com>
Date: Thu, 8 Jan 2015 10:31:06 +0800
Subject: ASoC: rt5677: Add the MICBIAS VDD setting in the platform data

The patch adds the MICBIAS VDD setting in the platform data. It can be set to
1V8 or 3V3 in the MICBIAS VDD.

Signed-off-by: Oder Chiou <oder_chiou@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/rt5677.h    | 3 +++
 sound/soc/codecs/rt5677.c | 5 +++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/sound/rt5677.h b/include/sound/rt5677.h
index d9eb7d861cd..a6207043ac3 100644
--- a/include/sound/rt5677.h
+++ b/include/sound/rt5677.h
@@ -37,6 +37,9 @@ struct rt5677_platform_data {
 		OFF, GPIO4, GPIO5 and GPIO6 respectively */
 	unsigned int jd2_gpio;
 	unsigned int jd3_gpio;
+
+	/* Set MICBIAS1 VDD 1v8 or 3v3 */
+	bool micbias1_vdd_3v3;
 };
 
 #endif
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index cf39fe6d060..3b32c3ecbe0 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -4912,6 +4912,11 @@ static int rt5677_i2c_probe(struct i2c_client *i2c,
 					RT5677_GPIO5_DIR_OUT);
 	}
 
+	if (rt5677->pdata.micbias1_vdd_3v3)
+		regmap_update_bits(rt5677->regmap, RT5677_MICBIAS,
+			RT5677_MICBIAS1_CTRL_VDD_MASK,
+			RT5677_MICBIAS1_CTRL_VDD_3_3V);
+
 	rt5677_init_gpio(i2c);
 	rt5677_init_irq(i2c);
 
-- 
cgit v1.2.3-70-g09d2


From bfa21a0dfe6915dc85953b5d40ea9dae5fdf205f Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Mon, 5 Jan 2015 12:48:42 +0100
Subject: regulator: Allow parsing custom properties when using simplified DT
 parsing

When drivers use simplified DT parsing method (they provide
'regulator_desc.of_match') they still may want to parse custom
properties for some of the regulators. For example some of the
regulators support GPIO enable control.

Add a driver-supplied callback for such case. This way the regulator
core parses common bindings offloading a lot of code from drivers and
still custom properties may be used.

The callback, called for each parsed regulator, may modify the
'regulator_config' initially passed to regulator_register().

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c         |  2 +-
 drivers/regulator/internal.h     |  2 ++
 drivers/regulator/of_regulator.c | 11 +++++++++++
 include/linux/regulator/driver.h | 13 +++++++++++++
 4 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index c13b557a560..5fae8cabd25 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -3635,7 +3635,7 @@ regulator_register(const struct regulator_desc *regulator_desc,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	init_data = regulator_of_get_init_data(dev, regulator_desc,
+	init_data = regulator_of_get_init_data(dev, regulator_desc, config,
 					       &rdev->dev.of_node);
 	if (!init_data) {
 		init_data = config->init_data;
diff --git a/drivers/regulator/internal.h b/drivers/regulator/internal.h
index 80ba2a35a04..c74ac873402 100644
--- a/drivers/regulator/internal.h
+++ b/drivers/regulator/internal.h
@@ -38,11 +38,13 @@ struct regulator {
 #ifdef CONFIG_OF
 struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 			         const struct regulator_desc *desc,
+				 struct regulator_config *config,
 				 struct device_node **node);
 #else
 static inline struct regulator_init_data *
 regulator_of_get_init_data(struct device *dev,
 			   const struct regulator_desc *desc,
+			   struct regulator_config *config,
 			   struct device_node **node)
 {
 	return NULL;
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 91eaaf01052..24e812c48d9 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -270,6 +270,7 @@ EXPORT_SYMBOL_GPL(of_regulator_match);
 
 struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 					    const struct regulator_desc *desc,
+					    struct regulator_config *config,
 					    struct device_node **node)
 {
 	struct device_node *search, *child;
@@ -307,6 +308,16 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 			break;
 		}
 
+		if (desc->of_parse_cb) {
+			if (desc->of_parse_cb(child, desc, config)) {
+				dev_err(dev,
+					"driver callback failed to parse DT for regulator %s\n",
+					child->name);
+				init_data = NULL;
+				break;
+			}
+		}
+
 		of_node_get(child);
 		*node = child;
 		break;
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 5f1e9ca4741..d4ad5b5a02b 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -21,6 +21,7 @@
 
 struct regmap;
 struct regulator_dev;
+struct regulator_config;
 struct regulator_init_data;
 struct regulator_enable_gpio;
 
@@ -205,6 +206,15 @@ enum regulator_type {
  * @supply_name: Identifying the regulator supply
  * @of_match: Name used to identify regulator in DT.
  * @regulators_node: Name of node containing regulator definitions in DT.
+ * @of_parse_cb: Optional callback called only if of_match is present.
+ *               Will be called for each regulator parsed from DT, during
+ *               init_data parsing.
+ *               The regulator_config passed as argument to the callback will
+ *               be a copy of config passed to regulator_register, valid only
+ *               for this particular call. Callback may freely change the
+ *               config but it cannot store it for later usage.
+ *               Callback should return 0 on success or negative ERRNO
+ *               indicating failure.
  * @id: Numerical identifier for the regulator.
  * @ops: Regulator operations table.
  * @irq: Interrupt number for the regulator.
@@ -251,6 +261,9 @@ struct regulator_desc {
 	const char *supply_name;
 	const char *of_match;
 	const char *regulators_node;
+	int (*of_parse_cb)(struct device_node *,
+			    const struct regulator_desc *,
+			    struct regulator_config *);
 	int id;
 	bool continuous_voltage_range;
 	unsigned n_voltages;
-- 
cgit v1.2.3-70-g09d2


From 3b50d9029809b60a5081d90c282aa04d438d3ea1 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Tue, 6 Jan 2015 15:45:31 -0800
Subject: ipv6: fix redefinition of in6_pktinfo and ip6_mtuinfo
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both netinet/in.h and linux/ipv6.h define these two structs,
if we include both of them, we got:

	/usr/include/linux/ipv6.h:19:8: error: redefinition of ‘struct in6_pktinfo’
	 struct in6_pktinfo {
		^
	In file included from /usr/include/arpa/inet.h:22:0,
			 from txtimestamp.c:33:
	/usr/include/netinet/in.h:524:8: note: originally defined here
	 struct in6_pktinfo
		^
	In file included from txtimestamp.c:40:0:
	/usr/include/linux/ipv6.h:24:8: error: redefinition of ‘struct ip6_mtuinfo’
	 struct ip6_mtuinfo {
		^
	In file included from /usr/include/arpa/inet.h:22:0,
			 from txtimestamp.c:33:
	/usr/include/netinet/in.h:531:8: note: originally defined here
	 struct ip6_mtuinfo
		^
So similarly to what we did for in6_addr, we need to sync with
libc header on their definitions.

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ipv6.h        | 5 ++++-
 include/uapi/linux/libc-compat.h | 6 ++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index e863d088b9a..b9b1b7d1c83 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -15,16 +15,19 @@
  *	*under construction*
  */
 
-
+#if __UAPI_DEF_IN6_PKTINFO
 struct in6_pktinfo {
 	struct in6_addr	ipi6_addr;
 	int		ipi6_ifindex;
 };
+#endif
 
+#if __UAPI_DEF_IP6_MTUINFO
 struct ip6_mtuinfo {
 	struct sockaddr_in6	ip6m_addr;
 	__u32			ip6m_mtu;
 };
+#endif
 
 struct in6_ifreq {
 	struct in6_addr	ifr6_addr;
diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index e28807ad17f..fa673e9cc04 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -70,6 +70,8 @@
 #define __UAPI_DEF_IPV6_MREQ		0
 #define __UAPI_DEF_IPPROTO_V6		0
 #define __UAPI_DEF_IPV6_OPTIONS		0
+#define __UAPI_DEF_IN6_PKTINFO		0
+#define __UAPI_DEF_IP6_MTUINFO		0
 
 #else
 
@@ -84,6 +86,8 @@
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
 #define __UAPI_DEF_IPV6_OPTIONS		1
+#define __UAPI_DEF_IN6_PKTINFO		1
+#define __UAPI_DEF_IP6_MTUINFO		1
 
 #endif /* _NETINET_IN_H */
 
@@ -106,6 +110,8 @@
 #define __UAPI_DEF_IPV6_MREQ		1
 #define __UAPI_DEF_IPPROTO_V6		1
 #define __UAPI_DEF_IPV6_OPTIONS		1
+#define __UAPI_DEF_IN6_PKTINFO		1
+#define __UAPI_DEF_IP6_MTUINFO		1
 
 /* Definitions for xattr.h */
 #define __UAPI_DEF_XATTR		1
-- 
cgit v1.2.3-70-g09d2


From db30485408326a6f466a843b291b23535f63eda0 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Wed, 7 Jan 2015 13:41:54 +0800
Subject: rhashtable: involve rhashtable_lookup_insert routine

Involve a new function called rhashtable_lookup_insert() which makes
lookup and insertion atomic under bucket lock protection, helping us
avoid to introduce an extra lock when we search and insert an object
into hash table.

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Thomas Graf <tgraf@suug.ch>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  1 +
 lib/rhashtable.c           | 97 +++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 83 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index de1459c74c4..73c913f3157 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -168,6 +168,7 @@ int rhashtable_shrink(struct rhashtable *ht);
 void *rhashtable_lookup(struct rhashtable *ht, const void *key);
 void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key,
 				bool (*compare)(void *, void *), void *arg);
+bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj);
 
 void rhashtable_destroy(struct rhashtable *ht);
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 20006854fce..4430233c4e1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -505,8 +505,26 @@ static void rhashtable_wakeup_worker(struct rhashtable *ht)
 		schedule_delayed_work(&ht->run_work, 0);
 }
 
+static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
+				struct bucket_table *tbl, u32 hash)
+{
+	struct rhash_head *head = rht_dereference_bucket(tbl->buckets[hash],
+							 tbl, hash);
+
+	if (rht_is_a_nulls(head))
+		INIT_RHT_NULLS_HEAD(obj->next, ht, hash);
+	else
+		RCU_INIT_POINTER(obj->next, head);
+
+	rcu_assign_pointer(tbl->buckets[hash], obj);
+
+	atomic_inc(&ht->nelems);
+
+	rhashtable_wakeup_worker(ht);
+}
+
 /**
- * rhashtable_insert - insert object into hash hash table
+ * rhashtable_insert - insert object into hash table
  * @ht:		hash table
  * @obj:	pointer to hash head inside object
  *
@@ -523,7 +541,6 @@ static void rhashtable_wakeup_worker(struct rhashtable *ht)
 void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 {
 	struct bucket_table *tbl;
-	struct rhash_head *head;
 	spinlock_t *lock;
 	unsigned hash;
 
@@ -534,19 +551,9 @@ void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj)
 	lock = bucket_lock(tbl, hash);
 
 	spin_lock_bh(lock);
-	head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash);
-	if (rht_is_a_nulls(head))
-		INIT_RHT_NULLS_HEAD(obj->next, ht, hash);
-	else
-		RCU_INIT_POINTER(obj->next, head);
-
-	rcu_assign_pointer(tbl->buckets[hash], obj);
+	__rhashtable_insert(ht, obj, tbl, hash);
 	spin_unlock_bh(lock);
 
-	atomic_inc(&ht->nelems);
-
-	rhashtable_wakeup_worker(ht);
-
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(rhashtable_insert);
@@ -560,7 +567,7 @@ EXPORT_SYMBOL_GPL(rhashtable_insert);
  * walk the bucket chain upon removal. The removal operation is thus
  * considerable slow if the hash table is not correctly sized.
  *
- * Will automatically shrink the table via rhashtable_expand() if the the
+ * Will automatically shrink the table via rhashtable_expand() if the
  * shrink_decision function specified at rhashtable_init() returns true.
  *
  * The caller must ensure that no concurrent table mutations occur. It is
@@ -641,7 +648,7 @@ static bool rhashtable_compare(void *ptr, void *arg)
  * for a entry with an identical key. The first matching entry is returned.
  *
  * This lookup function may only be used for fixed key hash table (key_len
- * paramter set). It will BUG() if used inappropriately.
+ * parameter set). It will BUG() if used inappropriately.
  *
  * Lookups may occur in parallel with hashtable mutations and resizing.
  */
@@ -702,6 +709,66 @@ restart:
 }
 EXPORT_SYMBOL_GPL(rhashtable_lookup_compare);
 
+/**
+ * rhashtable_lookup_insert - lookup and insert object into hash table
+ * @ht:		hash table
+ * @obj:	pointer to hash head inside object
+ *
+ * Locks down the bucket chain in both the old and new table if a resize
+ * is in progress to ensure that writers can't remove from the old table
+ * and can't insert to the new table during the atomic operation of search
+ * and insertion. Searches for duplicates in both the old and new table if
+ * a resize is in progress.
+ *
+ * This lookup function may only be used for fixed key hash table (key_len
+ * parameter set). It will BUG() if used inappropriately.
+ *
+ * It is safe to call this function from atomic context.
+ *
+ * Will trigger an automatic deferred table resizing if the size grows
+ * beyond the watermark indicated by grow_decision() which can be passed
+ * to rhashtable_init().
+ */
+bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj)
+{
+	struct bucket_table *new_tbl, *old_tbl;
+	spinlock_t *new_bucket_lock, *old_bucket_lock;
+	u32 new_hash, old_hash;
+	bool success = true;
+
+	BUG_ON(!ht->p.key_len);
+
+	rcu_read_lock();
+
+	old_tbl = rht_dereference_rcu(ht->tbl, ht);
+	old_hash = head_hashfn(ht, old_tbl, obj);
+	old_bucket_lock = bucket_lock(old_tbl, old_hash);
+	spin_lock_bh(old_bucket_lock);
+
+	new_tbl = rht_dereference_rcu(ht->future_tbl, ht);
+	new_hash = head_hashfn(ht, new_tbl, obj);
+	new_bucket_lock = bucket_lock(new_tbl, new_hash);
+	if (unlikely(old_tbl != new_tbl))
+		spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
+
+	if (rhashtable_lookup(ht, rht_obj(ht, obj) + ht->p.key_offset)) {
+		success = false;
+		goto exit;
+	}
+
+	__rhashtable_insert(ht, obj, new_tbl, new_hash);
+
+exit:
+	if (unlikely(old_tbl != new_tbl))
+		spin_unlock_bh(new_bucket_lock);
+	spin_unlock_bh(old_bucket_lock);
+
+	rcu_read_unlock();
+
+	return success;
+}
+EXPORT_SYMBOL_GPL(rhashtable_lookup_insert);
+
 static size_t rounded_hashtable_size(struct rhashtable_params *params)
 {
 	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
-- 
cgit v1.2.3-70-g09d2


From c0c09bfdc4150b3918526660768585cd477adf35 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Wed, 7 Jan 2015 13:41:56 +0800
Subject: rhashtable: avoid unnecessary wakeup for worker queue

Move condition statements of verifying whether hash table size exceeds
its maximum threshold or reaches its minimum threshold from resizing
functions to resizing decision functions, avoiding unnecessary wakeup
for worker queue thread.

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Cc: Thomas Graf <tgraf@suug.ch>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  2 +-
 lib/rhashtable.c           | 18 +++++++-----------
 2 files changed, 8 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 73c913f3157..326acd8c2e9 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -113,7 +113,7 @@ struct rhashtable {
 	struct bucket_table __rcu	*tbl;
 	struct bucket_table __rcu       *future_tbl;
 	atomic_t			nelems;
-	size_t				shift;
+	atomic_t			shift;
 	struct rhashtable_params	p;
 	struct delayed_work             run_work;
 	struct mutex                    mutex;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 1aef942976f..7fb474b18f1 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -199,7 +199,8 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size)
 {
 	/* Expand table when exceeding 75% load */
-	return atomic_read(&ht->nelems) > (new_size / 4 * 3);
+	return atomic_read(&ht->nelems) > (new_size / 4 * 3) &&
+	       (ht->p.max_shift && atomic_read(&ht->shift) < ht->p.max_shift);
 }
 EXPORT_SYMBOL_GPL(rht_grow_above_75);
 
@@ -211,7 +212,8 @@ EXPORT_SYMBOL_GPL(rht_grow_above_75);
 bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size)
 {
 	/* Shrink table beneath 30% load */
-	return atomic_read(&ht->nelems) < (new_size * 3 / 10);
+	return atomic_read(&ht->nelems) < (new_size * 3 / 10) &&
+	       (atomic_read(&ht->shift) > ht->p.min_shift);
 }
 EXPORT_SYMBOL_GPL(rht_shrink_below_30);
 
@@ -318,14 +320,11 @@ int rhashtable_expand(struct rhashtable *ht)
 
 	ASSERT_RHT_MUTEX(ht);
 
-	if (ht->p.max_shift && ht->shift >= ht->p.max_shift)
-		return 0;
-
 	new_tbl = bucket_table_alloc(ht, old_tbl->size * 2);
 	if (new_tbl == NULL)
 		return -ENOMEM;
 
-	ht->shift++;
+	atomic_inc(&ht->shift);
 
 	/* Make insertions go into the new, empty table right away. Deletions
 	 * and lookups will be attempted in both tables until we synchronize.
@@ -421,9 +420,6 @@ int rhashtable_shrink(struct rhashtable *ht)
 
 	ASSERT_RHT_MUTEX(ht);
 
-	if (ht->shift <= ht->p.min_shift)
-		return 0;
-
 	new_tbl = bucket_table_alloc(ht, tbl->size / 2);
 	if (new_tbl == NULL)
 		return -ENOMEM;
@@ -462,7 +458,7 @@ int rhashtable_shrink(struct rhashtable *ht)
 
 	/* Publish the new, valid hash table */
 	rcu_assign_pointer(ht->tbl, new_tbl);
-	ht->shift--;
+	atomic_dec(&ht->shift);
 
 	/* Wait for readers. No new readers will have references to the
 	 * old hash table.
@@ -851,7 +847,7 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
 	if (tbl == NULL)
 		return -ENOMEM;
 
-	ht->shift = ilog2(tbl->size);
+	atomic_set(&ht->shift, ilog2(tbl->size));
 	RCU_INIT_POINTER(ht->tbl, tbl);
 	RCU_INIT_POINTER(ht->future_tbl, tbl);
 
-- 
cgit v1.2.3-70-g09d2


From e5a7a72cd51a585b8f1a1e299bf88fff44b94440 Mon Sep 17 00:00:00 2001
From: Robin Gong <b38343@freescale.com>
Date: Fri, 9 Jan 2015 09:57:33 +0800
Subject: regulator: pfuze100-regulator: add pfuze3000 support

Add pfuze3000 chip support.

Signed-off-by: Robin Gong <b38343@freescale.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/regulator/pfuze100.txt     |  94 ++++++++++++++-
 drivers/regulator/pfuze100-regulator.c             | 134 +++++++++++++++++++--
 include/linux/regulator/pfuze100.h                 |  14 +++
 3 files changed, 232 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt
index 34ef5d16d0f..9b40db88f63 100644
--- a/Documentation/devicetree/bindings/regulator/pfuze100.txt
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt
@@ -1,7 +1,7 @@
 PFUZE100 family of regulators
 
 Required properties:
-- compatible: "fsl,pfuze100" or "fsl,pfuze200"
+- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000"
 - reg: I2C slave address
 
 Required child node:
@@ -14,6 +14,8 @@ Required child node:
   sw1ab,sw1c,sw2,sw3a,sw3b,sw4,swbst,vsnvs,vrefddr,vgen1~vgen6
   --PFUZE200
   sw1ab,sw2,sw3a,sw3b,swbst,vsnvs,vrefddr,vgen1~vgen6
+  --PFUZE3000
+  sw1a,sw1b,sw2,sw3,swbst,vsnvs,vrefddr,vldo1,vldo2,vccsd,v33,vldo3,vldo4
 
 Each regulator is defined using the standard binding for regulators.
 
@@ -205,3 +207,93 @@ Example 2: PFUZE200
 			};
 		};
 	};
+
+Example 3: PFUZE3000
+
+	pmic: pfuze3000@08 {
+		compatible = "fsl,pfuze3000";
+		reg = <0x08>;
+
+		regulators {
+			sw1a_reg: sw1a {
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <1475000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+			/* use sw1c_reg to align with pfuze100/pfuze200 */
+			sw1c_reg: sw1b {
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <1475000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+
+			sw2_reg: sw2 {
+				regulator-min-microvolt = <2500000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3a_reg: sw3 {
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <1650000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			swbst_reg: swbst {
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5150000>;
+			};
+
+			snvs_reg: vsnvs {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vref_reg: vrefddr {
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vgen1_reg: vldo1 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen2_reg: vldo2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+			};
+
+			vgen3_reg: vccsd {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen4_reg: v33 {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			vgen5_reg: vldo3 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen6_reg: vldo4 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+		};
+	};
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index c879dff597e..8cc8d1877c4 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -56,7 +56,7 @@
 #define PFUZE100_VGEN5VOL	0x70
 #define PFUZE100_VGEN6VOL	0x71
 
-enum chips { PFUZE100, PFUZE200 };
+enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 };
 
 struct pfuze_regulator {
 	struct regulator_desc desc;
@@ -80,9 +80,18 @@ static const int pfuze100_vsnvs[] = {
 	1000000, 1100000, 1200000, 1300000, 1500000, 1800000, 3000000,
 };
 
+static const int pfuze3000_sw2lo[] = {
+	1500000, 1550000, 1600000, 1650000, 1700000, 1750000, 1800000, 1850000,
+};
+
+static const int pfuze3000_sw2hi[] = {
+	2500000, 2800000, 2850000, 3000000, 3100000, 3150000, 3200000, 3300000,
+};
+
 static const struct i2c_device_id pfuze_device_id[] = {
 	{.name = "pfuze100", .driver_data = PFUZE100},
 	{.name = "pfuze200", .driver_data = PFUZE200},
+	{.name = "pfuze3000", .driver_data = PFUZE3000},
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
@@ -90,6 +99,7 @@ MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
 static const struct of_device_id pfuze_dt_ids[] = {
 	{ .compatible = "fsl,pfuze100", .data = (void *)PFUZE100},
 	{ .compatible = "fsl,pfuze200", .data = (void *)PFUZE200},
+	{ .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pfuze_dt_ids);
@@ -219,6 +229,60 @@ static struct regulator_ops pfuze100_swb_regulator_ops = {
 		.stby_mask = 0x20,	\
 	}
 
+#define PFUZE3000_VCC_REG(_chip, _name, base, min, max, step)	{	\
+	.desc = {	\
+		.name = #_name,	\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.ops = &pfuze100_ldo_regulator_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = _chip ## _ ## _name,	\
+		.owner = THIS_MODULE,	\
+		.min_uV = (min),	\
+		.uV_step = (step),	\
+		.vsel_reg = (base),	\
+		.vsel_mask = 0x3,	\
+		.enable_reg = (base),	\
+		.enable_mask = 0x10,	\
+	},	\
+	.stby_reg = (base),	\
+	.stby_mask = 0x20,	\
+}
+
+
+#define PFUZE3000_SW2_REG(_chip, _name, base, min, max, step)	{	\
+	.desc = {	\
+		.name = #_name,\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.ops = &pfuze100_sw_regulator_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = _chip ## _ ## _name,	\
+		.owner = THIS_MODULE,	\
+		.min_uV = (min),	\
+		.uV_step = (step),	\
+		.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
+		.vsel_mask = 0x7,	\
+	},	\
+	.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
+	.stby_mask = 0x7,	\
+}
+
+#define PFUZE3000_SW3_REG(_chip, _name, base, min, max, step)	{	\
+	.desc = {	\
+		.name = #_name,\
+		.n_voltages = ((max) - (min)) / (step) + 1,	\
+		.ops = &pfuze100_sw_regulator_ops,	\
+		.type = REGULATOR_VOLTAGE,	\
+		.id = _chip ## _ ## _name,	\
+		.owner = THIS_MODULE,	\
+		.min_uV = (min),	\
+		.uV_step = (step),	\
+		.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
+		.vsel_mask = 0xf,	\
+	},	\
+	.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
+	.stby_mask = 0xf,	\
+}
+
 /* PFUZE100 */
 static struct pfuze_regulator pfuze100_regulators[] = {
 	PFUZE100_SW_REG(PFUZE100, SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000),
@@ -254,6 +318,22 @@ static struct pfuze_regulator pfuze200_regulators[] = {
 	PFUZE100_VGEN_REG(PFUZE200, VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
+static struct pfuze_regulator pfuze3000_regulators[] = {
+	PFUZE100_SW_REG(PFUZE3000, SW1A, PFUZE100_SW1ABVOL, 700000, 1475000, 25000),
+	PFUZE100_SW_REG(PFUZE3000, SW1B, PFUZE100_SW1CVOL, 700000, 1475000, 25000),
+	PFUZE100_SWB_REG(PFUZE3000, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW3_REG(PFUZE3000, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
+	PFUZE100_SWB_REG(PFUZE3000, SWBST, PFUZE100_SWBSTCON1, 0x3, pfuze100_swbst),
+	PFUZE100_SWB_REG(PFUZE3000, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
+	PFUZE100_FIXED_REG(PFUZE3000, VREFDDR, PFUZE100_VREFDDRCON, 750000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
+	PFUZE3000_VCC_REG(PFUZE3000, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000),
+	PFUZE3000_VCC_REG(PFUZE3000, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
+};
+
 static struct pfuze_regulator *pfuze_regulators;
 
 #ifdef CONFIG_OF
@@ -294,6 +374,24 @@ static struct of_regulator_match pfuze200_matches[] = {
 	{ .name = "vgen6",	},
 };
 
+/* PFUZE3000 */
+static struct of_regulator_match pfuze3000_matches[] = {
+
+	{ .name = "sw1a",	},
+	{ .name = "sw1b",	},
+	{ .name = "sw2",	},
+	{ .name = "sw3",	},
+	{ .name = "swbst",	},
+	{ .name = "vsnvs",	},
+	{ .name = "vrefddr",	},
+	{ .name = "vldo1",	},
+	{ .name = "vldo2",	},
+	{ .name = "vccsd",	},
+	{ .name = "v33",	},
+	{ .name = "vldo3",	},
+	{ .name = "vldo4",	},
+};
+
 static struct of_regulator_match *pfuze_matches;
 
 static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
@@ -313,6 +411,11 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 	}
 
 	switch (chip->chip_id) {
+	case PFUZE3000:
+		pfuze_matches = pfuze3000_matches;
+		ret = of_regulator_match(dev, parent, pfuze3000_matches,
+					 ARRAY_SIZE(pfuze3000_matches));
+		break;
 	case PFUZE200:
 		pfuze_matches = pfuze200_matches;
 		ret = of_regulator_match(dev, parent, pfuze200_matches,
@@ -378,7 +481,8 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip)
 		 * as ID=8 in PFUZE100
 		 */
 		dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8");
-	} else if ((value & 0x0f) != pfuze_chip->chip_id) {
+	} else if ((value & 0x0f) != pfuze_chip->chip_id &&
+		   (value & 0xf0) >> 4 != pfuze_chip->chip_id) {
 		/* device id NOT match with your setting */
 		dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value);
 		return -ENODEV;
@@ -417,7 +521,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	int i, ret;
 	const struct of_device_id *match;
 	u32 regulator_num;
-	u32 sw_check_start, sw_check_end;
+	u32 sw_check_start, sw_check_end, sw_hi = 0x40;
 
 	pfuze_chip = devm_kzalloc(&client->dev, sizeof(*pfuze_chip),
 			GFP_KERNEL);
@@ -458,13 +562,19 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 
 	/* use the right regulators after identify the right device */
 	switch (pfuze_chip->chip_id) {
+	case PFUZE3000:
+		pfuze_regulators = pfuze3000_regulators;
+		regulator_num = ARRAY_SIZE(pfuze3000_regulators);
+		sw_check_start = PFUZE3000_SW2;
+		sw_check_end = PFUZE3000_SW2;
+		sw_hi = 1 << 3;
+		break;
 	case PFUZE200:
 		pfuze_regulators = pfuze200_regulators;
 		regulator_num = ARRAY_SIZE(pfuze200_regulators);
 		sw_check_start = PFUZE200_SW2;
 		sw_check_end = PFUZE200_SW3B;
 		break;
-
 	case PFUZE100:
 	default:
 		pfuze_regulators = pfuze100_regulators;
@@ -474,7 +584,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		break;
 	}
 	dev_info(&client->dev, "pfuze%s found.\n",
-		(pfuze_chip->chip_id == PFUZE100) ? "100" : "200");
+		(pfuze_chip->chip_id == PFUZE100) ? "100" :
+		((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000"));
 
 	memcpy(pfuze_chip->regulator_descs, pfuze_regulators,
 		sizeof(pfuze_chip->regulator_descs));
@@ -498,10 +609,15 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		/* SW2~SW4 high bit check and modify the voltage value table */
 		if (i >= sw_check_start && i <= sw_check_end) {
 			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
-			if (val & 0x40) {
-				desc->min_uV = 800000;
-				desc->uV_step = 50000;
-				desc->n_voltages = 51;
+			if (val & sw_hi) {
+				if (pfuze_chip->chip_id == PFUZE3000) {
+					desc->volt_table = pfuze3000_sw2hi;
+					desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi);
+				} else {
+					desc->min_uV = 800000;
+					desc->uV_step = 50000;
+					desc->n_voltages = 51;
+				}
 			}
 		}
 
diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h
index 364f7a7c43d..70c6c66c5bc 100644
--- a/include/linux/regulator/pfuze100.h
+++ b/include/linux/regulator/pfuze100.h
@@ -49,6 +49,20 @@
 #define PFUZE200_VGEN5		11
 #define PFUZE200_VGEN6		12
 
+#define PFUZE3000_SW1A		0
+#define PFUZE3000_SW1B		1
+#define PFUZE3000_SW2		2
+#define PFUZE3000_SW3		3
+#define PFUZE3000_SWBST		4
+#define PFUZE3000_VSNVS		5
+#define PFUZE3000_VREFDDR	6
+#define PFUZE3000_VLDO1		7
+#define PFUZE3000_VLDO2		8
+#define PFUZE3000_VCCSD		9
+#define PFUZE3000_V33		10
+#define PFUZE3000_VLDO3		11
+#define PFUZE3000_VLDO4		12
+
 struct regulator_init_data;
 
 struct pfuze_regulator_platform_data {
-- 
cgit v1.2.3-70-g09d2


From ed09dcc8bd7fe0991af7737e675996cbd022f38f Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 30 Dec 2014 14:46:14 -0800
Subject: ses: close potential registration race

The slot and address fields have a small window of instability when
userspace can read them before initialization. Separate
enclosure_component
allocation from registration.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/enclosure.c  | 37 ++++++++++++++++++++++++++-----------
 drivers/scsi/ses.c        | 21 ++++++++++++++-------
 include/linux/enclosure.h |  5 +++--
 3 files changed, 43 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 180a5442fd4..e18278aa6bb 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -273,27 +273,26 @@ enclosure_component_find_by_name(struct enclosure_device *edev,
 static const struct attribute_group *enclosure_component_groups[];
 
 /**
- * enclosure_component_register - add a particular component to an enclosure
+ * enclosure_component_alloc - prepare a new enclosure component
  * @edev:	the enclosure to add the component
  * @num:	the device number
  * @type:	the type of component being added
  * @name:	an optional name to appear in sysfs (leave NULL if none)
  *
- * Registers the component.  The name is optional for enclosures that
- * give their components a unique name.  If not, leave the field NULL
- * and a name will be assigned.
+ * The name is optional for enclosures that give their components a unique
+ * name.  If not, leave the field NULL and a name will be assigned.
  *
  * Returns a pointer to the enclosure component or an error.
  */
 struct enclosure_component *
-enclosure_component_register(struct enclosure_device *edev,
-			     unsigned int number,
-			     enum enclosure_component_type type,
-			     const char *name)
+enclosure_component_alloc(struct enclosure_device *edev,
+			  unsigned int number,
+			  enum enclosure_component_type type,
+			  const char *name)
 {
 	struct enclosure_component *ecomp;
 	struct device *cdev;
-	int err, i;
+	int i;
 	char newname[COMPONENT_NAME_SIZE];
 
 	if (number >= edev->components)
@@ -327,14 +326,30 @@ enclosure_component_register(struct enclosure_device *edev,
 	cdev->release = enclosure_component_release;
 	cdev->groups = enclosure_component_groups;
 
+	return ecomp;
+}
+EXPORT_SYMBOL_GPL(enclosure_component_alloc);
+
+/**
+ * enclosure_component_register - publishes an initialized enclosure component
+ * @ecomp:	component to add
+ *
+ * Returns 0 on successful registration, releases the component otherwise
+ */
+int enclosure_component_register(struct enclosure_component *ecomp)
+{
+	struct device *cdev;
+	int err;
+
+	cdev = &ecomp->cdev;
 	err = device_register(cdev);
 	if (err) {
 		ecomp->number = -1;
 		put_device(cdev);
-		return ERR_PTR(err);
+		return err;
 	}
 
-	return ecomp;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(enclosure_component_register);
 
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index b7e79e7646a..7dd9cf55838 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -423,16 +423,23 @@ static void ses_enclosure_data_process(struct enclosure_device *edev,
 			    type_ptr[0] == ENCLOSURE_COMPONENT_ARRAY_DEVICE) {
 
 				if (create)
-					ecomp =	enclosure_component_register(edev,
-									     components++,
-									     type_ptr[0],
-									     name);
+					ecomp =	enclosure_component_alloc(
+						edev,
+						components++,
+						type_ptr[0],
+						name);
 				else
 					ecomp = &edev->component[components++];
 
-				if (!IS_ERR(ecomp) && addl_desc_ptr)
-					ses_process_descriptor(ecomp,
-							       addl_desc_ptr);
+				if (!IS_ERR(ecomp)) {
+					if (addl_desc_ptr)
+						ses_process_descriptor(
+							ecomp,
+							addl_desc_ptr);
+					if (create)
+						enclosure_component_register(
+							ecomp);
+				}
 			}
 			if (desc_ptr)
 				desc_ptr += len;
diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
index 9a33c5f7e12..a835d335b92 100644
--- a/include/linux/enclosure.h
+++ b/include/linux/enclosure.h
@@ -120,8 +120,9 @@ enclosure_register(struct device *, const char *, int,
 		   struct enclosure_component_callbacks *);
 void enclosure_unregister(struct enclosure_device *);
 struct enclosure_component *
-enclosure_component_register(struct enclosure_device *, unsigned int,
-				 enum enclosure_component_type, const char *);
+enclosure_component_alloc(struct enclosure_device *, unsigned int,
+			  enum enclosure_component_type, const char *);
+int enclosure_component_register(struct enclosure_component *);
 int enclosure_add_device(struct enclosure_device *enclosure, int component,
 			 struct device *dev);
 int enclosure_remove_device(struct enclosure_device *, struct device *);
-- 
cgit v1.2.3-70-g09d2


From 967f7bab0eaaa74d7d01a56d45aa309f78fb87dd Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 30 Dec 2014 14:46:16 -0800
Subject: ses: add enclosure logical id

Export the NAA logical id for the enclosure.  This is optionally
available from the sas_transport_class, but it is really a property of
the enclosure.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/enclosure.c  | 13 +++++++++++++
 drivers/scsi/ses.c        |  9 +++++++++
 include/linux/enclosure.h |  1 +
 3 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index e18278aa6bb..958ee988a1e 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -432,8 +432,21 @@ static ssize_t components_show(struct device *cdev,
 }
 static DEVICE_ATTR_RO(components);
 
+static ssize_t id_show(struct device *cdev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct enclosure_device *edev = to_enclosure_device(cdev);
+
+	if (edev->cb->show_id)
+		return edev->cb->show_id(edev, buf);
+	return -EINVAL;
+}
+static DEVICE_ATTR_RO(id);
+
 static struct attribute *enclosure_class_attrs[] = {
 	&dev_attr_components.attr,
+	&dev_attr_id.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(enclosure_class);
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 6662b0ca6cf..1041556cdbf 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -258,6 +258,14 @@ static int ses_set_active(struct enclosure_device *edev,
 	return ses_set_page2_descriptor(edev, ecomp, desc);
 }
 
+static int ses_show_id(struct enclosure_device *edev, char *buf)
+{
+	struct ses_device *ses_dev = edev->scratch;
+	unsigned long long id = get_unaligned_be64(ses_dev->page1+8+4);
+
+	return sprintf(buf, "%#llx\n", id);
+}
+
 static struct enclosure_component_callbacks ses_enclosure_callbacks = {
 	.get_fault		= ses_get_fault,
 	.set_fault		= ses_set_fault,
@@ -265,6 +273,7 @@ static struct enclosure_component_callbacks ses_enclosure_callbacks = {
 	.get_locate		= ses_get_locate,
 	.set_locate		= ses_set_locate,
 	.set_active		= ses_set_active,
+	.show_id		= ses_show_id,
 };
 
 struct ses_host_edev {
diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
index a835d335b92..807622b252a 100644
--- a/include/linux/enclosure.h
+++ b/include/linux/enclosure.h
@@ -79,6 +79,7 @@ struct enclosure_component_callbacks {
 	int (*set_locate)(struct enclosure_device *,
 			  struct enclosure_component *,
 			  enum enclosure_component_setting);
+	int (*show_id)(struct enclosure_device *, char *buf);
 };
 
 
-- 
cgit v1.2.3-70-g09d2


From 921ce7f5786052749a22a75780f5ce1a456bcdc6 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 30 Dec 2014 14:46:17 -0800
Subject: ses: add reliable slot attribute

The name provided by firmware is in a vendor specific format, publish
the slot number to have a reliable mechanism for identifying slots
across firmware implementations.  If the enclosure does not provide a
slot number fallback to the component number which is guaranteed unique,
and usually mirrors the slot number.

Cleaned up the unused ses_component.desc in the process.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/enclosure.c  | 20 +++++++++++++++++++-
 drivers/scsi/ses.c        | 17 ++++++++++++-----
 include/linux/enclosure.h |  1 +
 3 files changed, 32 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 958ee988a1e..b62314d627a 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -145,8 +145,10 @@ enclosure_register(struct device *dev, const char *name, int components,
 	if (err)
 		goto err;
 
-	for (i = 0; i < components; i++)
+	for (i = 0; i < components; i++) {
 		edev->component[i].number = -1;
+		edev->component[i].slot = -1;
+	}
 
 	mutex_lock(&container_list_lock);
 	list_add_tail(&edev->node, &container_list);
@@ -589,6 +591,20 @@ static ssize_t get_component_type(struct device *cdev,
 	return snprintf(buf, 40, "%s\n", enclosure_type[ecomp->type]);
 }
 
+static ssize_t get_component_slot(struct device *cdev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct enclosure_component *ecomp = to_enclosure_component(cdev);
+	int slot;
+
+	/* if the enclosure does not override then use 'number' as a stand-in */
+	if (ecomp->slot >= 0)
+		slot = ecomp->slot;
+	else
+		slot = ecomp->number;
+
+	return snprintf(buf, 40, "%d\n", slot);
+}
 
 static DEVICE_ATTR(fault, S_IRUGO | S_IWUSR, get_component_fault,
 		    set_component_fault);
@@ -599,6 +615,7 @@ static DEVICE_ATTR(active, S_IRUGO | S_IWUSR, get_component_active,
 static DEVICE_ATTR(locate, S_IRUGO | S_IWUSR, get_component_locate,
 		   set_component_locate);
 static DEVICE_ATTR(type, S_IRUGO, get_component_type, NULL);
+static DEVICE_ATTR(slot, S_IRUGO, get_component_slot, NULL);
 
 static struct attribute *enclosure_component_attrs[] = {
 	&dev_attr_fault.attr,
@@ -606,6 +623,7 @@ static struct attribute *enclosure_component_attrs[] = {
 	&dev_attr_active.attr,
 	&dev_attr_locate.attr,
 	&dev_attr_type.attr,
+	&dev_attr_slot.attr,
 	NULL
 };
 ATTRIBUTE_GROUPS(enclosure_component);
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 1041556cdbf..433de8e6f53 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -47,7 +47,6 @@ struct ses_device {
 
 struct ses_component {
 	u64 addr;
-	unsigned char *desc;
 };
 
 static int ses_probe(struct device *dev)
@@ -307,19 +306,26 @@ static void ses_process_descriptor(struct enclosure_component *ecomp,
 	int invalid = desc[0] & 0x80;
 	enum scsi_protocol proto = desc[0] & 0x0f;
 	u64 addr = 0;
+	int slot = -1;
 	struct ses_component *scomp = ecomp->scratch;
 	unsigned char *d;
 
-	scomp->desc = desc;
-
 	if (invalid)
 		return;
 
 	switch (proto) {
+	case SCSI_PROTOCOL_FCP:
+		if (eip) {
+			d = desc + 4;
+			slot = d[3];
+		}
+		break;
 	case SCSI_PROTOCOL_SAS:
-		if (eip)
+		if (eip) {
+			d = desc + 4;
+			slot = d[3];
 			d = desc + 8;
-		else
+		} else
 			d = desc + 4;
 		/* only take the phy0 addr */
 		addr = (u64)d[12] << 56 |
@@ -335,6 +341,7 @@ static void ses_process_descriptor(struct enclosure_component *ecomp,
 		/* FIXME: Need to add more protocols than just SAS */
 		break;
 	}
+	ecomp->slot = slot;
 	scomp->addr = addr;
 }
 
diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
index 807622b252a..0f826c14a33 100644
--- a/include/linux/enclosure.h
+++ b/include/linux/enclosure.h
@@ -92,6 +92,7 @@ struct enclosure_component {
 	int fault;
 	int active;
 	int locate;
+	int slot;
 	enum enclosure_status status;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 08024885a2a3ed432716e9d50046a620a5b2df05 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Tue, 30 Dec 2014 14:46:18 -0800
Subject: ses: Add power_status to SES device slot

Add power_status to SES device slot, so we can power on/off the
HDDs behind the enclosure.

Check firmware status in ses_set_* before sending control pages to
firmware.

Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/misc/enclosure.c  | 38 ++++++++++++++++++
 drivers/scsi/ses.c        | 98 ++++++++++++++++++++++++++++++++++++++++++-----
 include/linux/enclosure.h |  6 +++
 3 files changed, 133 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index b62314d627a..38552a31304 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -148,6 +148,7 @@ enclosure_register(struct device *dev, const char *name, int components,
 	for (i = 0; i < components; i++) {
 		edev->component[i].number = -1;
 		edev->component[i].slot = -1;
+		edev->component[i].power_status = 1;
 	}
 
 	mutex_lock(&container_list_lock);
@@ -583,6 +584,40 @@ static ssize_t set_component_locate(struct device *cdev,
 	return count;
 }
 
+static ssize_t get_component_power_status(struct device *cdev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct enclosure_device *edev = to_enclosure_device(cdev->parent);
+	struct enclosure_component *ecomp = to_enclosure_component(cdev);
+
+	if (edev->cb->get_power_status)
+		edev->cb->get_power_status(edev, ecomp);
+	return snprintf(buf, 40, "%s\n", ecomp->power_status ? "on" : "off");
+}
+
+static ssize_t set_component_power_status(struct device *cdev,
+					  struct device_attribute *attr,
+					  const char *buf, size_t count)
+{
+	struct enclosure_device *edev = to_enclosure_device(cdev->parent);
+	struct enclosure_component *ecomp = to_enclosure_component(cdev);
+	int val;
+
+	if (strncmp(buf, "on", 2) == 0 &&
+	    (buf[2] == '\n' || buf[2] == '\0'))
+		val = 1;
+	else if (strncmp(buf, "off", 3) == 0 &&
+	    (buf[3] == '\n' || buf[3] == '\0'))
+		val = 0;
+	else
+		return -EINVAL;
+
+	if (edev->cb->set_power_status)
+		edev->cb->set_power_status(edev, ecomp, val);
+	return count;
+}
+
 static ssize_t get_component_type(struct device *cdev,
 				  struct device_attribute *attr, char *buf)
 {
@@ -614,6 +649,8 @@ static DEVICE_ATTR(active, S_IRUGO | S_IWUSR, get_component_active,
 		   set_component_active);
 static DEVICE_ATTR(locate, S_IRUGO | S_IWUSR, get_component_locate,
 		   set_component_locate);
+static DEVICE_ATTR(power_status, S_IRUGO | S_IWUSR, get_component_power_status,
+		   set_component_power_status);
 static DEVICE_ATTR(type, S_IRUGO, get_component_type, NULL);
 static DEVICE_ATTR(slot, S_IRUGO, get_component_slot, NULL);
 
@@ -622,6 +659,7 @@ static struct attribute *enclosure_component_attrs[] = {
 	&dev_attr_status.attr,
 	&dev_attr_active.attr,
 	&dev_attr_locate.attr,
+	&dev_attr_power_status.attr,
 	&dev_attr_type.attr,
 	&dev_attr_slot.attr,
 	NULL
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 433de8e6f53..dcb0d76d731 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -67,6 +67,20 @@ static int ses_probe(struct device *dev)
 #define SES_TIMEOUT (30 * HZ)
 #define SES_RETRIES 3
 
+static void init_device_slot_control(unsigned char *dest_desc,
+				     struct enclosure_component *ecomp,
+				     unsigned char *status)
+{
+	memcpy(dest_desc, status, 4);
+	dest_desc[0] = 0;
+	/* only clear byte 1 for ENCLOSURE_COMPONENT_DEVICE */
+	if (ecomp->type == ENCLOSURE_COMPONENT_DEVICE)
+		dest_desc[1] = 0;
+	dest_desc[2] &= 0xde;
+	dest_desc[3] &= 0x3c;
+}
+
+
 static int ses_recv_diag(struct scsi_device *sdev, int page_code,
 			 void *buf, int bufflen)
 {
@@ -178,14 +192,22 @@ static int ses_set_fault(struct enclosure_device *edev,
 			  struct enclosure_component *ecomp,
 			 enum enclosure_component_setting val)
 {
-	unsigned char desc[4] = {0 };
+	unsigned char desc[4];
+	unsigned char *desc_ptr;
+
+	desc_ptr = ses_get_page2_descriptor(edev, ecomp);
+
+	if (!desc_ptr)
+		return -EIO;
+
+	init_device_slot_control(desc, ecomp, desc_ptr);
 
 	switch (val) {
 	case ENCLOSURE_SETTING_DISABLED:
-		/* zero is disabled */
+		desc[3] &= 0xdf;
 		break;
 	case ENCLOSURE_SETTING_ENABLED:
-		desc[3] = 0x20;
+		desc[3] |= 0x20;
 		break;
 	default:
 		/* SES doesn't do the SGPIO blink settings */
@@ -219,14 +241,22 @@ static int ses_set_locate(struct enclosure_device *edev,
 			  struct enclosure_component *ecomp,
 			  enum enclosure_component_setting val)
 {
-	unsigned char desc[4] = {0 };
+	unsigned char desc[4];
+	unsigned char *desc_ptr;
+
+	desc_ptr = ses_get_page2_descriptor(edev, ecomp);
+
+	if (!desc_ptr)
+		return -EIO;
+
+	init_device_slot_control(desc, ecomp, desc_ptr);
 
 	switch (val) {
 	case ENCLOSURE_SETTING_DISABLED:
-		/* zero is disabled */
+		desc[2] &= 0xfd;
 		break;
 	case ENCLOSURE_SETTING_ENABLED:
-		desc[2] = 0x02;
+		desc[2] |= 0x02;
 		break;
 	default:
 		/* SES doesn't do the SGPIO blink settings */
@@ -239,15 +269,23 @@ static int ses_set_active(struct enclosure_device *edev,
 			  struct enclosure_component *ecomp,
 			  enum enclosure_component_setting val)
 {
-	unsigned char desc[4] = {0 };
+	unsigned char desc[4];
+	unsigned char *desc_ptr;
+
+	desc_ptr = ses_get_page2_descriptor(edev, ecomp);
+
+	if (!desc_ptr)
+		return -EIO;
+
+	init_device_slot_control(desc, ecomp, desc_ptr);
 
 	switch (val) {
 	case ENCLOSURE_SETTING_DISABLED:
-		/* zero is disabled */
+		desc[2] &= 0x7f;
 		ecomp->active = 0;
 		break;
 	case ENCLOSURE_SETTING_ENABLED:
-		desc[2] = 0x80;
+		desc[2] |= 0x80;
 		ecomp->active = 1;
 		break;
 	default:
@@ -265,12 +303,53 @@ static int ses_show_id(struct enclosure_device *edev, char *buf)
 	return sprintf(buf, "%#llx\n", id);
 }
 
+static void ses_get_power_status(struct enclosure_device *edev,
+				 struct enclosure_component *ecomp)
+{
+	unsigned char *desc;
+
+	desc = ses_get_page2_descriptor(edev, ecomp);
+	if (desc)
+		ecomp->power_status = (desc[3] & 0x10) ? 0 : 1;
+}
+
+static int ses_set_power_status(struct enclosure_device *edev,
+				struct enclosure_component *ecomp,
+				int val)
+{
+	unsigned char desc[4];
+	unsigned char *desc_ptr;
+
+	desc_ptr = ses_get_page2_descriptor(edev, ecomp);
+
+	if (!desc_ptr)
+		return -EIO;
+
+	init_device_slot_control(desc, ecomp, desc_ptr);
+
+	switch (val) {
+	/* power = 1 is device_off = 0 and vice versa */
+	case 0:
+		desc[3] |= 0x10;
+		break;
+	case 1:
+		desc[3] &= 0xef;
+		break;
+	default:
+		return -EINVAL;
+	}
+	ecomp->power_status = val;
+	return ses_set_page2_descriptor(edev, ecomp, desc);
+}
+
 static struct enclosure_component_callbacks ses_enclosure_callbacks = {
 	.get_fault		= ses_get_fault,
 	.set_fault		= ses_set_fault,
 	.get_status		= ses_get_status,
 	.get_locate		= ses_get_locate,
 	.set_locate		= ses_set_locate,
+	.get_power_status	= ses_get_power_status,
+	.set_power_status	= ses_set_power_status,
 	.set_active		= ses_set_active,
 	.show_id		= ses_show_id,
 };
@@ -449,6 +528,7 @@ static void ses_enclosure_data_process(struct enclosure_device *edev,
 					ecomp = &edev->component[components++];
 
 				if (!IS_ERR(ecomp)) {
+					ses_get_power_status(edev, ecomp);
 					if (addl_desc_ptr)
 						ses_process_descriptor(
 							ecomp,
diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h
index 0f826c14a33..7be22da321f 100644
--- a/include/linux/enclosure.h
+++ b/include/linux/enclosure.h
@@ -79,6 +79,11 @@ struct enclosure_component_callbacks {
 	int (*set_locate)(struct enclosure_device *,
 			  struct enclosure_component *,
 			  enum enclosure_component_setting);
+	void (*get_power_status)(struct enclosure_device *,
+				 struct enclosure_component *);
+	int (*set_power_status)(struct enclosure_device *,
+				struct enclosure_component *,
+				int);
 	int (*show_id)(struct enclosure_device *, char *buf);
 };
 
@@ -94,6 +99,7 @@ struct enclosure_component {
 	int locate;
 	int slot;
 	enum enclosure_status status;
+	int power_status;
 };
 
 struct enclosure_device {
-- 
cgit v1.2.3-70-g09d2


From ded85c193a391a84076d5c6a7a5668fe164a490e Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Thu, 8 Jan 2015 07:43:42 +0100
Subject: scsi: Implement per-cpu logging buffer

Implement a per-cpu buffer for formatting messages to avoid line breaks
up under high load.  This patch implements scmd_printk() and
sdev_prefix_printk() using the per-cpu buffer and makes sdev_printk() a
wrapper for sdev_prefix_printk().

Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/Makefile       |   2 +-
 drivers/scsi/scsi_logging.c | 124 ++++++++++++++++++++++++++++++++++++++++++++
 include/scsi/scsi_device.h  |  21 +++-----
 3 files changed, 133 insertions(+), 14 deletions(-)
 create mode 100644 drivers/scsi/scsi_logging.c

(limited to 'include')

diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 58158f11ed7..447c2d24aaf 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -167,7 +167,7 @@ scsi_mod-y			+= scsi_scan.o scsi_sysfs.o scsi_devinfo.o
 scsi_mod-$(CONFIG_SCSI_NETLINK)	+= scsi_netlink.o
 scsi_mod-$(CONFIG_SYSCTL)	+= scsi_sysctl.o
 scsi_mod-$(CONFIG_SCSI_PROC_FS)	+= scsi_proc.o
-scsi_mod-y			+= scsi_trace.o
+scsi_mod-y			+= scsi_trace.o scsi_logging.o
 scsi_mod-$(CONFIG_PM)		+= scsi_pm.o
 
 hv_storvsc-y			:= storvsc_drv.o
diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c
new file mode 100644
index 00000000000..09d65dea9d5
--- /dev/null
+++ b/drivers/scsi/scsi_logging.c
@@ -0,0 +1,124 @@
+/*
+ * scsi_logging.c
+ *
+ * Copyright (C) 2014 SUSE Linux Products GmbH
+ * Copyright (C) 2014 Hannes Reinecke <hare@suse.de>
+ *
+ * This file is released under the GPLv2
+ */
+
+#include <linux/kernel.h>
+#include <linux/atomic.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_dbg.h>
+
+#define SCSI_LOG_SPOOLSIZE 4096
+#define SCSI_LOG_BUFSIZE 128
+
+#if (SCSI_LOG_SPOOLSIZE / SCSI_LOG_BUFSIZE) > BITS_PER_LONG
+#warning SCSI logging bitmask too large
+#endif
+
+struct scsi_log_buf {
+	char buffer[SCSI_LOG_SPOOLSIZE];
+	unsigned long map;
+};
+
+static DEFINE_PER_CPU(struct scsi_log_buf, scsi_format_log);
+
+static char *scsi_log_reserve_buffer(size_t *len)
+{
+	struct scsi_log_buf *buf;
+	unsigned long map_bits = sizeof(buf->buffer) / SCSI_LOG_BUFSIZE;
+	unsigned long idx = 0;
+
+	preempt_disable();
+	buf = this_cpu_ptr(&scsi_format_log);
+	idx = find_first_zero_bit(&buf->map, map_bits);
+	if (likely(idx < map_bits)) {
+		while (test_and_set_bit(idx, &buf->map)) {
+			idx = find_next_zero_bit(&buf->map, map_bits, idx);
+			if (idx >= map_bits)
+				break;
+		}
+	}
+	if (WARN_ON(idx >= map_bits)) {
+		preempt_enable();
+		return NULL;
+	}
+	*len = SCSI_LOG_BUFSIZE;
+	return buf->buffer + idx * SCSI_LOG_BUFSIZE;
+}
+
+static void scsi_log_release_buffer(char *bufptr)
+{
+	struct scsi_log_buf *buf;
+	unsigned long idx;
+	int ret;
+
+	buf = this_cpu_ptr(&scsi_format_log);
+	if (bufptr >= buf->buffer &&
+	    bufptr < buf->buffer + SCSI_LOG_SPOOLSIZE) {
+		idx = (bufptr - buf->buffer) / SCSI_LOG_BUFSIZE;
+		ret = test_and_clear_bit(idx, &buf->map);
+		WARN_ON(!ret);
+	}
+	preempt_enable();
+}
+
+int sdev_prefix_printk(const char *level, const struct scsi_device *sdev,
+		       const char *name, const char *fmt, ...)
+{
+	va_list args;
+	char *logbuf;
+	size_t off = 0, logbuf_len;
+	int ret;
+
+	if (!sdev)
+		return 0;
+
+	logbuf = scsi_log_reserve_buffer(&logbuf_len);
+	if (!logbuf)
+		return 0;
+
+	if (name)
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "[%s] ", name);
+	va_start(args, fmt);
+	off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
+	va_end(args);
+	ret = dev_printk(level, &sdev->sdev_gendev, "%s", logbuf);
+	scsi_log_release_buffer(logbuf);
+	return ret;
+}
+EXPORT_SYMBOL(sdev_prefix_printk);
+
+int scmd_printk(const char *level, const struct scsi_cmnd *scmd,
+		const char *fmt, ...)
+{
+	struct gendisk *disk = scmd->request->rq_disk;
+	va_list args;
+	char *logbuf;
+	size_t off = 0, logbuf_len;
+	int ret;
+
+	if (!scmd || !scmd->cmnd)
+		return 0;
+
+	logbuf = scsi_log_reserve_buffer(&logbuf_len);
+	if (!logbuf)
+		return 0;
+	if (disk)
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "[%s] ", disk->disk_name);
+	va_start(args, fmt);
+	off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
+	va_end(args);
+	ret = dev_printk(level, &scmd->device->sdev_gendev, "%s", logbuf);
+	scsi_log_release_buffer(logbuf);
+	return ret;
+}
+EXPORT_SYMBOL(scmd_printk);
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 3a4edd1f7db..d1aad4d0433 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -230,9 +230,6 @@ struct scsi_dh_data {
 #define transport_class_to_sdev(class_dev) \
 	to_scsi_device(class_dev->parent)
 
-#define sdev_printk(prefix, sdev, fmt, a...)	\
-	dev_printk(prefix, &(sdev)->sdev_gendev, fmt, ##a)
-
 #define sdev_dbg(sdev, fmt, a...) \
 	dev_dbg(&(sdev)->sdev_gendev, fmt, ##a)
 
@@ -240,16 +237,14 @@ struct scsi_dh_data {
  * like scmd_printk, but the device name is passed in
  * as a string pointer
  */
-#define sdev_prefix_printk(l, sdev, p, fmt, a...)			\
-	(p) ?								\
-	sdev_printk(l, sdev, "[%s] " fmt, p, ##a) :			\
-	sdev_printk(l, sdev, fmt, ##a)
-
-#define scmd_printk(prefix, scmd, fmt, a...)				\
-        (scmd)->request->rq_disk ?					\
-	sdev_printk(prefix, (scmd)->device, "[%s] " fmt,		\
-		    (scmd)->request->rq_disk->disk_name, ##a) :		\
-	sdev_printk(prefix, (scmd)->device, fmt, ##a)
+extern int sdev_prefix_printk(const char *, const struct scsi_device *,
+			      const char *, const char *, ...);
+
+#define sdev_printk(l, sdev, fmt, a...)				\
+	sdev_prefix_printk(l, sdev, NULL, fmt, ##a)
+
+extern int scmd_printk(const char *, const struct scsi_cmnd *,
+		       const char *, ...);
 
 #define scmd_dbg(scmd, fmt, a...)					   \
 	do {								   \
-- 
cgit v1.2.3-70-g09d2


From 9e5ed2a5b3662c6f398023042c02aaa527099a3d Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Thu, 8 Jan 2015 07:43:44 +0100
Subject: scsi: use external buffer for command logging

Use an external buffer for __scsi_print_command() and move command
logging over to use the per-cpu logging buffer.  With that we can
guarantee the command always will always be formatted in one line.
So we can even print out a variable length command correctly across
several lines. Finally rename __scsi_print_command() to
__scsi_format_comment() to better reflect the functionality.

Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/ch.c           |   6 +-
 drivers/scsi/constants.c    |  74 +-----------------
 drivers/scsi/scsi_logging.c | 182 ++++++++++++++++++++++++++++++++++++++++----
 drivers/scsi/sr_ioctl.c     |  13 +++-
 include/scsi/scsi.h         |   3 +
 include/scsi/scsi_dbg.h     |   6 +-
 6 files changed, 192 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 6bac8a746ee..79e462feae0 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -195,8 +195,10 @@ ch_do_scsi(scsi_changer *ch, unsigned char *cmd, int cmd_len,
  retry:
 	errno = 0;
 	if (debug) {
-		DPRINTK("command: ");
-		__scsi_print_command(cmd, cmd_len);
+		char logbuf[SCSI_LOG_BUFSIZE];
+
+		__scsi_format_command(logbuf, sizeof(logbuf), cmd, cmd_len);
+		DPRINTK("command: %s", logbuf);
 	}
 
 	result = scsi_execute_req(ch->device, cmd, direction, buffer,
diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 55a7157b6e2..77929601d6d 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -24,8 +24,6 @@
 #define THIRD_PARTY_COPY_OUT 0x83
 #define THIRD_PARTY_COPY_IN 0x84
 
-#define VENDOR_SPECIFIC_CDB 0xc0
-
 struct sa_name_list {
 	int opcode;
 	const struct value_name_pair *arr;
@@ -281,8 +279,8 @@ static struct sa_name_list sa_names_arr[] = {
 };
 #endif /* CONFIG_SCSI_CONSTANTS */
 
-static bool scsi_opcode_sa_name(int opcode, int service_action,
-				const char **cdb_name, const char **sa_name)
+bool scsi_opcode_sa_name(int opcode, int service_action,
+			 const char **cdb_name, const char **sa_name)
 {
 	struct sa_name_list *sa_name_ptr;
 	const struct value_name_pair *arr = NULL;
@@ -315,74 +313,6 @@ static bool scsi_opcode_sa_name(int opcode, int service_action,
 	return true;
 }
 
-static void print_opcode_name(const unsigned char *cdbp, size_t cdb_len)
-{
-	int sa, cdb0;
-	const char *cdb_name = NULL, *sa_name = NULL;
-
-	cdb0 = cdbp[0];
-	if (cdb0 == VARIABLE_LENGTH_CMD) {
-		if (cdb_len < 10) {
-			printk("short variable length command, len=%zu",
-			       cdb_len);
-			return;
-		}
-		sa = (cdbp[8] << 8) + cdbp[9];
-	} else
-		sa = cdbp[1] & 0x1f;
-
-	if (!scsi_opcode_sa_name(cdb0, sa, &cdb_name, &sa_name)) {
-		if (cdb_name)
-			printk("%s", cdb_name);
-		else if (cdb0 >= VENDOR_SPECIFIC_CDB)
-			printk("cdb[0]=0x%x (vendor)", cdb0);
-		else if (cdb0 >= 0x60 && cdb0 < 0x7e)
-			printk("cdb[0]=0x%x (reserved)", cdb0);
-		else
-			printk("cdb[0]=0x%x", cdb0);
-	} else {
-		if (sa_name)
-			printk("%s", sa_name);
-		else if (cdb_name)
-			printk("%s, sa=0x%x", cdb_name, sa);
-		else
-			printk("cdb[0]=0x%x, sa=0x%x", cdb0, sa);
-	}
-}
-
-void __scsi_print_command(const unsigned char *cdb, size_t cdb_len)
-{
-	int k, len;
-
-	print_opcode_name(cdb, cdb_len);
-	len = scsi_command_size(cdb);
-	if (cdb_len < len)
-		len = cdb_len;
-	/* print out all bytes in cdb */
-	for (k = 0; k < len; ++k)
-		printk(" %02x", cdb[k]);
-	printk("\n");
-}
-EXPORT_SYMBOL(__scsi_print_command);
-
-void scsi_print_command(struct scsi_cmnd *cmd)
-{
-	int k;
-
-	if (cmd->cmnd == NULL)
-		return;
-
-	scmd_printk(KERN_INFO, cmd, "CDB: ");
-	print_opcode_name(cmd->cmnd, cmd->cmd_len);
-
-	/* print out all bytes in cdb */
-	printk(":");
-	for (k = 0; k < cmd->cmd_len; ++k)
-		printk(" %02x", cmd->cmnd[k]);
-	printk("\n");
-}
-EXPORT_SYMBOL(scsi_print_command);
-
 #ifdef CONFIG_SCSI_CONSTANTS
 
 struct error_info {
diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c
index 4d20132c897..afba995b718 100644
--- a/drivers/scsi/scsi_logging.c
+++ b/drivers/scsi/scsi_logging.c
@@ -13,10 +13,10 @@
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
+#include <scsi/scsi_eh.h>
 #include <scsi/scsi_dbg.h>
 
 #define SCSI_LOG_SPOOLSIZE 4096
-#define SCSI_LOG_BUFSIZE 128
 
 #if (SCSI_LOG_SPOOLSIZE / SCSI_LOG_BUFSIZE) > BITS_PER_LONG
 #warning SCSI logging bitmask too large
@@ -69,6 +69,24 @@ static void scsi_log_release_buffer(char *bufptr)
 	preempt_enable();
 }
 
+static size_t scmd_format_header(char *logbuf, size_t logbuf_len,
+				 struct gendisk *disk, int tag)
+{
+	size_t off = 0;
+
+	if (disk)
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "[%s] ", disk->disk_name);
+
+	if (WARN_ON(off >= logbuf_len))
+		return off;
+
+	if (tag >= 0)
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "tag#%d ", tag);
+	return off;
+}
+
 int sdev_prefix_printk(const char *level, const struct scsi_device *sdev,
 		       const char *name, const char *fmt, ...)
 {
@@ -87,9 +105,11 @@ int sdev_prefix_printk(const char *level, const struct scsi_device *sdev,
 	if (name)
 		off += scnprintf(logbuf + off, logbuf_len - off,
 				 "[%s] ", name);
-	va_start(args, fmt);
-	off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
-	va_end(args);
+	if (!WARN_ON(off >= logbuf_len)) {
+		va_start(args, fmt);
+		off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
+		va_end(args);
+	}
 	ret = dev_printk(level, &sdev->sdev_gendev, "%s", logbuf);
 	scsi_log_release_buffer(logbuf);
 	return ret;
@@ -111,18 +131,152 @@ int scmd_printk(const char *level, const struct scsi_cmnd *scmd,
 	logbuf = scsi_log_reserve_buffer(&logbuf_len);
 	if (!logbuf)
 		return 0;
-	if (disk)
-		off += scnprintf(logbuf + off, logbuf_len - off,
-				 "[%s] ", disk->disk_name);
-
-	if (scmd->request->tag >= 0)
-		off += scnprintf(logbuf + off, logbuf_len - off,
-				 "tag#%d ", scmd->request->tag);
-	va_start(args, fmt);
-	off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
-	va_end(args);
+	off = scmd_format_header(logbuf, logbuf_len, disk,
+				 scmd->request->tag);
+	if (off < logbuf_len) {
+		va_start(args, fmt);
+		off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
+		va_end(args);
+	}
 	ret = dev_printk(level, &scmd->device->sdev_gendev, "%s", logbuf);
 	scsi_log_release_buffer(logbuf);
 	return ret;
 }
 EXPORT_SYMBOL(scmd_printk);
+
+static size_t scsi_format_opcode_name(char *buffer, size_t buf_len,
+				      const unsigned char *cdbp)
+{
+	int sa, cdb0;
+	const char *cdb_name = NULL, *sa_name = NULL;
+	size_t off;
+
+	cdb0 = cdbp[0];
+	if (cdb0 == VARIABLE_LENGTH_CMD) {
+		int len = scsi_varlen_cdb_length(cdbp);
+
+		if (len < 10) {
+			off = scnprintf(buffer, buf_len,
+					"short variable length command, len=%d",
+					len);
+			return off;
+		}
+		sa = (cdbp[8] << 8) + cdbp[9];
+	} else
+		sa = cdbp[1] & 0x1f;
+
+	if (!scsi_opcode_sa_name(cdb0, sa, &cdb_name, &sa_name)) {
+		if (cdb_name)
+			off = scnprintf(buffer, buf_len, "%s", cdb_name);
+		else {
+			off = scnprintf(buffer, buf_len, "opcode=0x%x", cdb0);
+			if (WARN_ON(off >= buf_len))
+				return off;
+			if (cdb0 >= VENDOR_SPECIFIC_CDB)
+				off += scnprintf(buffer + off, buf_len - off,
+						 " (vendor)");
+			else if (cdb0 >= 0x60 && cdb0 < 0x7e)
+				off += scnprintf(buffer + off, buf_len - off,
+						 " (reserved)");
+		}
+	} else {
+		if (sa_name)
+			off = scnprintf(buffer, buf_len, "%s", sa_name);
+		else if (cdb_name)
+			off = scnprintf(buffer, buf_len, "%s, sa=0x%x",
+					cdb_name, sa);
+		else
+			off = scnprintf(buffer, buf_len,
+					"opcode=0x%x, sa=0x%x", cdb0, sa);
+	}
+	WARN_ON(off >= buf_len);
+	return off;
+}
+
+size_t __scsi_format_command(char *logbuf, size_t logbuf_len,
+			     const unsigned char *cdb, size_t cdb_len)
+{
+	int len, k;
+	size_t off;
+
+	off = scsi_format_opcode_name(logbuf, logbuf_len, cdb);
+	if (off >= logbuf_len)
+		return off;
+	len = scsi_command_size(cdb);
+	if (cdb_len < len)
+		len = cdb_len;
+	/* print out all bytes in cdb */
+	for (k = 0; k < len; ++k) {
+		if (off > logbuf_len - 3)
+			break;
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 " %02x", cdb[k]);
+	}
+	return off;
+}
+EXPORT_SYMBOL(__scsi_format_command);
+
+void scsi_print_command(struct scsi_cmnd *cmd)
+{
+	struct gendisk *disk = cmd->request->rq_disk;
+	int k;
+	char *logbuf;
+	size_t off, logbuf_len;
+
+	if (!cmd->cmnd)
+		return;
+
+	logbuf = scsi_log_reserve_buffer(&logbuf_len);
+	if (!logbuf)
+		return;
+
+	off = scmd_format_header(logbuf, logbuf_len, disk, cmd->request->tag);
+	if (off >= logbuf_len)
+		goto out_printk;
+	off += scnprintf(logbuf + off, logbuf_len - off, "CDB: ");
+	if (WARN_ON(off >= logbuf_len))
+		goto out_printk;
+
+	off += scsi_format_opcode_name(logbuf + off, logbuf_len - off,
+				       cmd->cmnd);
+	if (off >= logbuf_len)
+		goto out_printk;
+
+	/* print out all bytes in cdb */
+	if (cmd->cmd_len > 16) {
+		/* Print opcode in one line and use separate lines for CDB */
+		off += scnprintf(logbuf + off, logbuf_len - off, "\n");
+		dev_printk(KERN_INFO, &cmd->device->sdev_gendev, logbuf);
+		scsi_log_release_buffer(logbuf);
+		for (k = 0; k < cmd->cmd_len; k += 16) {
+			size_t linelen = min(cmd->cmd_len - k, 16);
+
+			logbuf = scsi_log_reserve_buffer(&logbuf_len);
+			if (!logbuf)
+				break;
+			off = scmd_format_header(logbuf, logbuf_len, disk,
+						 cmd->request->tag);
+			if (!WARN_ON(off > logbuf_len - 58)) {
+				off += scnprintf(logbuf + off, logbuf_len - off,
+						 "CDB[%02x]: ", k);
+				hex_dump_to_buffer(&cmd->cmnd[k], linelen,
+						   16, 1, logbuf + off,
+						   logbuf_len - off, false);
+			}
+			dev_printk(KERN_INFO, &cmd->device->sdev_gendev,
+				   logbuf);
+			scsi_log_release_buffer(logbuf);
+		}
+		return;
+	}
+	if (!WARN_ON(off > logbuf_len - 49)) {
+		off += scnprintf(logbuf + off, logbuf_len - off, " ");
+		hex_dump_to_buffer(cmd->cmnd, cmd->cmd_len, 16, 1,
+				   logbuf + off, logbuf_len - off,
+				   false);
+	}
+out_printk:
+	dev_printk(KERN_INFO, &cmd->device->sdev_gendev, logbuf);
+	scsi_log_release_buffer(logbuf);
+}
+EXPORT_SYMBOL(scsi_print_command);
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index fb929fac22b..e8deb9ccf20 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -188,6 +188,7 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	struct scsi_sense_hdr sshdr;
 	int result, err = 0, retries = 0;
 	struct request_sense *sense = cgc->sense;
+	char logbuf[SCSI_LOG_BUFSIZE];
 
 	SDev = cd->device;
 
@@ -257,14 +258,20 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 				/* sense: Invalid command operation code */
 				err = -EDRIVE_CANT_DO_THIS;
 #ifdef DEBUG
-			__scsi_print_command(cgc->cmd, CDROM_PACKET_SIZE);
+			__scsi_format_command(logbuf, sizeof(logbuf),
+					      cgc->cmd, CDROM_PACKET_SIZE);
+			sr_printk(KERN_INFO, cd,
+				  "CDROM (ioctl) invalid command: %s\n",
+				  logbuf);
 			scsi_print_sense_hdr(cd->device, cd->cdi.name, &sshdr);
 #endif
 			break;
 		default:
+			__scsi_format_command(logbuf, sizeof(logbuf),
+					      cgc->cmd, CDROM_PACKET_SIZE);
 			sr_printk(KERN_ERR, cd,
-				  "CDROM (ioctl) error, command: ");
-			__scsi_print_command(cgc->cmd, CDROM_PACKET_SIZE);
+				  "CDROM (ioctl) error, command: %s\n",
+				  logbuf);
 			scsi_print_sense_hdr(cd->device, cd->cdi.name, &sshdr);
 			err = -EIO;
 		}
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 8a7f8ad58aa..d0a66aa1868 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -195,6 +195,9 @@ enum scsi_timeouts {
 #define	ATA_16		      0x85	/* 16-byte pass-thru */
 #define	ATA_12		      0xa1	/* 12-byte pass-thru */
 
+/* Vendor specific CDBs start here */
+#define VENDOR_SPECIFIC_CDB 0xc0
+
 /*
  *	SCSI command lengths
  */
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 7982795df59..c7ed7b81b33 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -5,8 +5,12 @@ struct scsi_cmnd;
 struct scsi_device;
 struct scsi_sense_hdr;
 
+#define SCSI_LOG_BUFSIZE 128
+
+extern bool scsi_opcode_sa_name(int, int, const char **, const char **);
 extern void scsi_print_command(struct scsi_cmnd *);
-extern void __scsi_print_command(const unsigned char *, size_t);
+extern size_t __scsi_format_command(char *, size_t,
+				   const unsigned char *, size_t);
 extern void scsi_show_extd_sense(const struct scsi_device *, const char *,
 				 unsigned char, unsigned char);
 extern void scsi_show_sense_hdr(const struct scsi_device *, const char *,
-- 
cgit v1.2.3-70-g09d2


From 026f8da8da4ce3423bf89e8e9091f55ae3863eda Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Thu, 8 Jan 2015 07:43:47 +0100
Subject: scsi: use per-cpu buffer for formatting scsi_print_result()

Convert scsi_print_result() to use the per-cpu buffer for decoding the
command result and disposition.

Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/constants.c    | 22 -----------------
 drivers/scsi/scsi.c         |  2 +-
 drivers/scsi/scsi_logging.c | 59 +++++++++++++++++++++++++++++++++++++++++++++
 include/scsi/scsi_dbg.h     |  2 +-
 4 files changed, 61 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index a23ef75533d..956fbdd3868 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1316,25 +1316,3 @@ const char *scsi_mlreturn_string(int result)
 	return NULL;
 }
 EXPORT_SYMBOL(scsi_mlreturn_string);
-
-void scsi_print_result(struct scsi_cmnd *cmd, const char *msg, int disposition)
-{
-	const char *mlret_string = scsi_mlreturn_string(disposition);
-	const char *hb_string = scsi_hostbyte_string(cmd->result);
-	const char *db_string = scsi_driverbyte_string(cmd->result);
-
-	if (hb_string || db_string)
-		scmd_printk(KERN_INFO, cmd,
-			    "%s%s Result: hostbyte=%s driverbyte=%s",
-			    msg ? msg : "",
-			    mlret_string ? mlret_string : "UNKNOWN",
-			    hb_string ? hb_string : "invalid",
-			    db_string ? db_string : "invalid");
-	else
-		scmd_printk(KERN_INFO, cmd,
-			    "%s%s Result: hostbyte=0x%02x driverbyte=0x%02x",
-			    msg ? msg : "",
-			    mlret_string ? mlret_string : "UNKNOWN",
-			    host_byte(cmd->result), driver_byte(cmd->result));
-}
-EXPORT_SYMBOL(scsi_print_result);
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index e0288545142..7f028cb1d09 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -572,7 +572,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
 				       SCSI_LOG_MLCOMPLETE_BITS);
 		if (((level > 0) && (cmd->result || disposition != SUCCESS)) ||
 		    (level > 1)) {
-			scsi_print_result(cmd, "Done: ", disposition);
+			scsi_print_result(cmd, "Done", disposition);
 			scsi_print_command(cmd);
 			if (status_byte(cmd->result) & CHECK_CONDITION)
 				scsi_print_sense(cmd);
diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c
index c7cba3113f3..6128303f9c5 100644
--- a/drivers/scsi/scsi_logging.c
+++ b/drivers/scsi/scsi_logging.c
@@ -428,3 +428,62 @@ void scsi_print_sense(const struct scsi_cmnd *cmd)
 			     cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE);
 }
 EXPORT_SYMBOL(scsi_print_sense);
+
+void scsi_print_result(const struct scsi_cmnd *cmd, const char *msg,
+		       int disposition)
+{
+	char *logbuf;
+	size_t off, logbuf_len;
+	const char *mlret_string = scsi_mlreturn_string(disposition);
+	const char *hb_string = scsi_hostbyte_string(cmd->result);
+	const char *db_string = scsi_driverbyte_string(cmd->result);
+
+	logbuf = scsi_log_reserve_buffer(&logbuf_len);
+	if (!logbuf)
+		return;
+
+	off = sdev_format_header(logbuf, logbuf_len,
+				 scmd_name(cmd), cmd->request->tag);
+
+	if (off >= logbuf_len)
+		goto out_printk;
+
+	if (msg) {
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "%s: ", msg);
+		if (WARN_ON(off >= logbuf_len))
+			goto out_printk;
+	}
+	if (mlret_string)
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "%s ", mlret_string);
+	else
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "UNKNOWN(0x%02x) ", disposition);
+	if (WARN_ON(off >= logbuf_len))
+		goto out_printk;
+
+	off += scnprintf(logbuf + off, logbuf_len - off, "Result: ");
+	if (WARN_ON(off >= logbuf_len))
+		goto out_printk;
+
+	if (hb_string)
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "hostbyte=%s ", hb_string);
+	else
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "hostbyte=0x%02x ", host_byte(cmd->result));
+	if (WARN_ON(off >= logbuf_len))
+		goto out_printk;
+
+	if (db_string)
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "driverbyte=%s", db_string);
+	else
+		off += scnprintf(logbuf + off, logbuf_len - off,
+				 "driverbyte=0x%02x", driver_byte(cmd->result));
+out_printk:
+	dev_printk(KERN_INFO, &cmd->device->sdev_gendev, logbuf);
+	scsi_log_release_buffer(logbuf);
+}
+EXPORT_SYMBOL(scsi_print_result);
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index c7ed7b81b33..365b6745dc1 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -21,7 +21,7 @@ extern void scsi_print_sense(const struct scsi_cmnd *);
 extern void __scsi_print_sense(const struct scsi_device *, const char *name,
 			       const unsigned char *sense_buffer,
 			       int sense_len);
-extern void scsi_print_result(struct scsi_cmnd *, const char *, int);
+extern void scsi_print_result(const struct scsi_cmnd *, const char *, int);
 extern const char *scsi_hostbyte_string(int);
 extern const char *scsi_driverbyte_string(int);
 extern const char *scsi_mlreturn_string(int);
-- 
cgit v1.2.3-70-g09d2


From 2dd951ecd511756f405ae9324db87bb0159f6225 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Thu, 8 Jan 2015 07:43:48 +0100
Subject: scsi: Conditionally compile in constants.c

Instead of having constants.c littered with ifdef statements we should
be moving dummy functions into the header and condintionally compile in
constants.c if selected. And update the Kconfig description to reflect
the actual size difference.

Suggested-by: Christoph Hellwig <hch@infradead.org>
Tested-by: Robert Elliott <elliott@hp.com>
Reviewed-by: Robert Elliott <elliott@hp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/scsi/Kconfig       |  4 +--
 drivers/scsi/Makefile      |  4 +--
 drivers/scsi/constants.c   | 44 ------------------------------
 drivers/xen/xen-scsiback.c |  1 +
 include/scsi/scsi_dbg.h    | 68 +++++++++++++++++++++++++++++++++++++++++++---
 5 files changed, 69 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 9c92f415229..b021bcb8853 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -201,12 +201,12 @@ config SCSI_ENCLOSURE
 	  certain enclosure conditions to be reported and is not required.
 
 config SCSI_CONSTANTS
-	bool "Verbose SCSI error reporting (kernel size +=12K)"
+	bool "Verbose SCSI error reporting (kernel size +=75K)"
 	depends on SCSI
 	help
 	  The error messages regarding your SCSI hardware will be easier to
 	  understand if you say Y here; it will enlarge your kernel by about
-	  12 KB. If in doubt, say Y.
+	  75 KB. If in doubt, say Y.
 
 config SCSI_LOGGING
 	bool "SCSI logging facility"
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 447c2d24aaf..dee160a4f16 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -159,9 +159,9 @@ obj-$(CONFIG_SCSI_OSD_INITIATOR) += osd/
 
 # This goes last, so that "real" scsi devices probe earlier
 obj-$(CONFIG_SCSI_DEBUG)	+= scsi_debug.o
-
-scsi_mod-y			+= scsi.o hosts.o scsi_ioctl.o constants.o \
+scsi_mod-y			+= scsi.o hosts.o scsi_ioctl.o \
 				   scsicam.o scsi_error.o scsi_lib.o
+scsi_mod-$(CONFIG_SCSI_CONSTANTS) += constants.o
 scsi_mod-$(CONFIG_SCSI_DMA)	+= scsi_lib_dma.o
 scsi_mod-y			+= scsi_scan.o scsi_sysfs.o scsi_devinfo.o
 scsi_mod-$(CONFIG_SCSI_NETLINK)	+= scsi_netlink.o
diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 956fbdd3868..fa09d4be2b5 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -18,8 +18,6 @@
 #include <scsi/scsi_eh.h>
 #include <scsi/scsi_dbg.h>
 
-
-
 /* Commands with service actions that change the command name */
 #define THIRD_PARTY_COPY_OUT 0x83
 #define THIRD_PARTY_COPY_IN 0x84
@@ -35,7 +33,6 @@ struct value_name_pair {
 	const char * name;
 };
 
-#ifdef CONFIG_SCSI_CONSTANTS
 static const char * cdb_byte0_names[] = {
 /* 00-03 */ "Test Unit Ready", "Rezero Unit/Rewind", NULL, "Request Sense",
 /* 04-07 */ "Format Unit/Medium", "Read Block Limits", NULL,
@@ -259,26 +256,6 @@ static struct sa_name_list sa_names_arr[] = {
 	{0, NULL, 0},
 };
 
-#else /* ifndef CONFIG_SCSI_CONSTANTS */
-static const char *cdb_byte0_names[0];
-
-static struct sa_name_list sa_names_arr[] = {
-	{VARIABLE_LENGTH_CMD, NULL, 0},
-	{MAINTENANCE_IN, NULL, 0},
-	{MAINTENANCE_OUT, NULL, 0},
-	{PERSISTENT_RESERVE_IN, NULL, 0},
-	{PERSISTENT_RESERVE_OUT, NULL, 0},
-	{SERVICE_ACTION_IN_12, NULL, 0},
-	{SERVICE_ACTION_OUT_12, NULL, 0},
-	{SERVICE_ACTION_BIDIRECTIONAL, NULL, 0},
-	{SERVICE_ACTION_IN_16, NULL, 0},
-	{SERVICE_ACTION_OUT_16, NULL, 0},
-	{THIRD_PARTY_COPY_IN, NULL, 0},
-	{THIRD_PARTY_COPY_OUT, NULL, 0},
-	{0, NULL, 0},
-};
-#endif /* CONFIG_SCSI_CONSTANTS */
-
 bool scsi_opcode_sa_name(int opcode, int service_action,
 			 const char **cdb_name, const char **sa_name)
 {
@@ -313,8 +290,6 @@ bool scsi_opcode_sa_name(int opcode, int service_action,
 	return true;
 }
 
-#ifdef CONFIG_SCSI_CONSTANTS
-
 struct error_info {
 	unsigned short code12;	/* 0x0302 looks better than 0x03,0x02 */
 	const char * text;
@@ -1203,15 +1178,12 @@ static const char * const snstext[] = {
 	"Completed",	    /* F: command completed sense data reported,
 				  may occur for successful command */
 };
-#endif
 
 /* Get sense key string or NULL if not available */
 const char *
 scsi_sense_key_string(unsigned char key) {
-#ifdef CONFIG_SCSI_CONSTANTS
 	if (key <= 0xE)
 		return snstext[key];
-#endif
 	return NULL;
 }
 EXPORT_SYMBOL(scsi_sense_key_string);
@@ -1223,7 +1195,6 @@ EXPORT_SYMBOL(scsi_sense_key_string);
 const char *
 scsi_extd_sense_format(unsigned char asc, unsigned char ascq, const char **fmt)
 {
-#ifdef CONFIG_SCSI_CONSTANTS
 	int i;
 	unsigned short code = ((asc << 8) | ascq);
 
@@ -1239,15 +1210,10 @@ scsi_extd_sense_format(unsigned char asc, unsigned char ascq, const char **fmt)
 			return additional2[i].str;
 		}
 	}
-#else
-	*fmt = NULL;
-#endif
 	return NULL;
 }
 EXPORT_SYMBOL(scsi_extd_sense_format);
 
-#ifdef CONFIG_SCSI_CONSTANTS
-
 static const char * const hostbyte_table[]={
 "DID_OK", "DID_NO_CONNECT", "DID_BUS_BUSY", "DID_TIME_OUT", "DID_BAD_TARGET",
 "DID_ABORT", "DID_PARITY", "DID_ERROR", "DID_RESET", "DID_BAD_INTR",
@@ -1259,17 +1225,13 @@ static const char * const driverbyte_table[]={
 "DRIVER_OK", "DRIVER_BUSY", "DRIVER_SOFT",  "DRIVER_MEDIA", "DRIVER_ERROR",
 "DRIVER_INVALID", "DRIVER_TIMEOUT", "DRIVER_HARD", "DRIVER_SENSE"};
 
-#endif
-
 const char *scsi_hostbyte_string(int result)
 {
 	const char *hb_string = NULL;
-#ifdef CONFIG_SCSI_CONSTANTS
 	int hb = host_byte(result);
 
 	if (hb < ARRAY_SIZE(hostbyte_table))
 		hb_string = hostbyte_table[hb];
-#endif
 	return hb_string;
 }
 EXPORT_SYMBOL(scsi_hostbyte_string);
@@ -1277,17 +1239,14 @@ EXPORT_SYMBOL(scsi_hostbyte_string);
 const char *scsi_driverbyte_string(int result)
 {
 	const char *db_string = NULL;
-#ifdef CONFIG_SCSI_CONSTANTS
 	int db = driver_byte(result);
 
 	if (db < ARRAY_SIZE(driverbyte_table))
 		db_string = driverbyte_table[db];
-#endif
 	return db_string;
 }
 EXPORT_SYMBOL(scsi_driverbyte_string);
 
-#ifdef CONFIG_SCSI_CONSTANTS
 #define scsi_mlreturn_name(result)	{ result, #result }
 static const struct value_name_pair scsi_mlreturn_arr[] = {
 	scsi_mlreturn_name(NEEDS_RETRY),
@@ -1300,11 +1259,9 @@ static const struct value_name_pair scsi_mlreturn_arr[] = {
 	scsi_mlreturn_name(SCSI_RETURN_NOT_HANDLED),
 	scsi_mlreturn_name(FAST_IO_FAIL)
 };
-#endif
 
 const char *scsi_mlreturn_string(int result)
 {
-#ifdef CONFIG_SCSI_CONSTANTS
 	const struct value_name_pair *arr = scsi_mlreturn_arr;
 	int k;
 
@@ -1312,7 +1269,6 @@ const char *scsi_mlreturn_string(int result)
 		if (result == arr->value)
 			return arr->name;
 	}
-#endif
 	return NULL;
 }
 EXPORT_SYMBOL(scsi_mlreturn_string);
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index e999496eda3..471ab066169 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -47,6 +47,7 @@
 
 #include <generated/utsrelease.h>
 
+#include <scsi/scsi.h>
 #include <scsi/scsi_dbg.h>
 #include <scsi/scsi_eh.h>
 #include <scsi/scsi_tcq.h>
diff --git a/include/scsi/scsi_dbg.h b/include/scsi/scsi_dbg.h
index 365b6745dc1..f8170e90b49 100644
--- a/include/scsi/scsi_dbg.h
+++ b/include/scsi/scsi_dbg.h
@@ -7,7 +7,6 @@ struct scsi_sense_hdr;
 
 #define SCSI_LOG_BUFSIZE 128
 
-extern bool scsi_opcode_sa_name(int, int, const char **, const char **);
 extern void scsi_print_command(struct scsi_cmnd *);
 extern size_t __scsi_format_command(char *, size_t,
 				   const unsigned char *, size_t);
@@ -22,11 +21,72 @@ extern void __scsi_print_sense(const struct scsi_device *, const char *name,
 			       const unsigned char *sense_buffer,
 			       int sense_len);
 extern void scsi_print_result(const struct scsi_cmnd *, const char *, int);
-extern const char *scsi_hostbyte_string(int);
-extern const char *scsi_driverbyte_string(int);
-extern const char *scsi_mlreturn_string(int);
+
+#ifdef CONFIG_SCSI_CONSTANTS
+extern bool scsi_opcode_sa_name(int, int, const char **, const char **);
 extern const char *scsi_sense_key_string(unsigned char);
 extern const char *scsi_extd_sense_format(unsigned char, unsigned char,
 					  const char **);
+extern const char *scsi_mlreturn_string(int);
+extern const char *scsi_hostbyte_string(int);
+extern const char *scsi_driverbyte_string(int);
+#else
+static inline bool
+scsi_opcode_sa_name(int cmd, int sa,
+		    const char **cdb_name, const char **sa_name)
+{
+	*cdb_name = NULL;
+	switch (cmd) {
+	case VARIABLE_LENGTH_CMD:
+	case MAINTENANCE_IN:
+	case MAINTENANCE_OUT:
+	case PERSISTENT_RESERVE_IN:
+	case PERSISTENT_RESERVE_OUT:
+	case SERVICE_ACTION_IN_12:
+	case SERVICE_ACTION_OUT_12:
+	case SERVICE_ACTION_BIDIRECTIONAL:
+	case SERVICE_ACTION_IN_16:
+	case SERVICE_ACTION_OUT_16:
+	case EXTENDED_COPY:
+	case RECEIVE_COPY_RESULTS:
+		*sa_name = NULL;
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline const char *
+scsi_sense_key_string(unsigned char key)
+{
+	return NULL;
+}
+
+static inline const char *
+scsi_extd_sense_format(unsigned char asc, unsigned char ascq, const char **fmt)
+{
+	*fmt = NULL;
+	return NULL;
+}
+
+static inline const char *
+scsi_mlreturn_string(int result)
+{
+	return NULL;
+}
+
+static inline const char *
+scsi_hostbyte_string(int result)
+{
+	return NULL;
+}
+
+static inline const char *
+scsi_driverbyte_string(int result)
+{
+	return NULL;
+}
+
+#endif
 
 #endif /* _SCSI_SCSI_DBG_H */
-- 
cgit v1.2.3-70-g09d2


From 9733e4f0a973a354034f5dd603b4142a3095c85f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 21 Nov 2014 12:49:13 -0800
Subject: rcu: Make _batches_completed() functions return unsigned long

Long ago, the various ->completed fields were of type long, but now are
unsigned long due to signed-integer-overflow concerns.  However, the
various _batches_completed() functions remained of type long, even though
their only purpose in life is to return the corresponding ->completed
field.  This patch cleans this up by changing these functions' return
types to unsigned long.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcutiny.h  | 4 ++--
 include/linux/rcutree.h  | 6 +++---
 kernel/rcu/tree.c        | 4 ++--
 kernel/rcu/tree.h        | 2 +-
 kernel/rcu/tree_plugin.h | 6 +++---
 5 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 0e536620015..91f7e4c3780 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -94,7 +94,7 @@ static inline void rcu_virt_note_context_switch(int cpu)
 /*
  * Return the number of grace periods.
  */
-static inline long rcu_batches_completed(void)
+static inline unsigned long rcu_batches_completed(void)
 {
 	return 0;
 }
@@ -102,7 +102,7 @@ static inline long rcu_batches_completed(void)
 /*
  * Return the number of bottom-half grace periods.
  */
-static inline long rcu_batches_completed_bh(void)
+static inline unsigned long rcu_batches_completed_bh(void)
 {
 	return 0;
 }
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 52953790dcc..9885bfb6b12 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -81,9 +81,9 @@ void cond_synchronize_rcu(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
-long rcu_batches_completed(void);
-long rcu_batches_completed_bh(void);
-long rcu_batches_completed_sched(void);
+unsigned long rcu_batches_completed(void);
+unsigned long rcu_batches_completed_bh(void);
+unsigned long rcu_batches_completed_sched(void);
 void show_rcu_gp_kthreads(void);
 
 void rcu_force_quiescent_state(void);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4c106fcc0d5..e26d78712e1 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -317,7 +317,7 @@ static int rcu_pending(void);
 /*
  * Return the number of RCU-sched batches processed thus far for debug & stats.
  */
-long rcu_batches_completed_sched(void)
+unsigned long rcu_batches_completed_sched(void)
 {
 	return rcu_sched_state.completed;
 }
@@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 /*
  * Return the number of RCU BH batches processed thus far for debug & stats.
  */
-long rcu_batches_completed_bh(void)
+unsigned long rcu_batches_completed_bh(void)
 {
 	return rcu_bh_state.completed;
 }
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8e7b1843896..1a07d7379ac 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -546,7 +546,7 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work);
 
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
-long rcu_batches_completed(void);
+unsigned long rcu_batches_completed(void);
 static void rcu_preempt_note_context_switch(void);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3ec85cb5d54..f69300d4a51 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -117,7 +117,7 @@ static void __init rcu_bootup_announce(void)
  * Return the number of RCU-preempt batches processed thus far
  * for debug and statistics.
  */
-static long rcu_batches_completed_preempt(void)
+static unsigned long rcu_batches_completed_preempt(void)
 {
 	return rcu_preempt_state.completed;
 }
@@ -126,7 +126,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);
 /*
  * Return the number of RCU batches processed thus far for debug & stats.
  */
-long rcu_batches_completed(void)
+unsigned long rcu_batches_completed(void)
 {
 	return rcu_batches_completed_preempt();
 }
@@ -935,7 +935,7 @@ static void __init rcu_bootup_announce(void)
 /*
  * Return the number of RCU batches processed thus far for debug & stats.
  */
-long rcu_batches_completed(void)
+unsigned long rcu_batches_completed(void)
 {
 	return rcu_batches_completed_sched();
 }
-- 
cgit v1.2.3-70-g09d2


From c1fe9cde4ae904fffb5b4d975d0a37e99136ff50 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 21 Nov 2014 15:45:27 -0800
Subject: rcu: Provide rcu_batches_completed_sched() for TINY_RCU

A bug in rcutorture has caused it to ignore completed batches.
In preparation for fixing that bug, this commit provides TINY_RCU with
the required rcu_batches_completed_sched().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcutiny.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 91f7e4c3780..1ce2d6b8f0c 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -107,6 +107,14 @@ static inline unsigned long rcu_batches_completed_bh(void)
 	return 0;
 }
 
+/*
+ * Return the number of sched grace periods.
+ */
+static inline unsigned long rcu_batches_completed_sched(void)
+{
+	return 0;
+}
+
 static inline void rcu_force_quiescent_state(void)
 {
 }
-- 
cgit v1.2.3-70-g09d2


From 917963d0b30f9c4153c372c165178501d97b6b55 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 21 Nov 2014 17:10:16 -0800
Subject: rcutorture: Check from beginning to end of grace period

Currently, rcutorture's Reader Batch checks measure from the end of
the previous grace period to the end of the current one.  This commit
tightens up these checks by measuring from the start and end of the same
grace period.  This involves adding rcu_batches_started() and friends
corresponding to the existing rcu_batches_completed() and friends.

We leave SRCU alone for the moment, as it does not yet have a way of
tracking both ends of its grace periods.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcutiny.h  | 30 +++++++++++++++++++++++++++---
 include/linux/rcutree.h  |  3 +++
 kernel/rcu/rcutorture.c  | 37 +++++++++++++++++++++++++++----------
 kernel/rcu/tree.c        | 40 ++++++++++++++++++++++++++++++++++++++--
 kernel/rcu/tree_plugin.h | 28 ----------------------------
 5 files changed, 95 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 1ce2d6b8f0c..984192160e9 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -92,7 +92,31 @@ static inline void rcu_virt_note_context_switch(int cpu)
 }
 
 /*
- * Return the number of grace periods.
+ * Return the number of grace periods started.
+ */
+static inline unsigned long rcu_batches_started(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of bottom-half grace periods started.
+ */
+static inline unsigned long rcu_batches_started_bh(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of sched grace periods started.
+ */
+static inline unsigned long rcu_batches_started_sched(void)
+{
+	return 0;
+}
+
+/*
+ * Return the number of grace periods completed.
  */
 static inline unsigned long rcu_batches_completed(void)
 {
@@ -100,7 +124,7 @@ static inline unsigned long rcu_batches_completed(void)
 }
 
 /*
- * Return the number of bottom-half grace periods.
+ * Return the number of bottom-half grace periods completed.
  */
 static inline unsigned long rcu_batches_completed_bh(void)
 {
@@ -108,7 +132,7 @@ static inline unsigned long rcu_batches_completed_bh(void)
 }
 
 /*
- * Return the number of sched grace periods.
+ * Return the number of sched grace periods completed.
  */
 static inline unsigned long rcu_batches_completed_sched(void)
 {
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 9885bfb6b12..c0dd124e69e 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -81,6 +81,9 @@ void cond_synchronize_rcu(unsigned long oldstate);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
+unsigned long rcu_batches_started(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_started_sched(void);
 unsigned long rcu_batches_completed(void);
 unsigned long rcu_batches_completed_bh(void);
 unsigned long rcu_batches_completed_sched(void);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index aadbc072ccf..24142c20090 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -244,6 +244,7 @@ struct rcu_torture_ops {
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
+	unsigned long (*started)(void);
 	unsigned long (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
@@ -372,6 +373,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
+	.started	= rcu_batches_started,
 	.completed	= rcu_batches_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
@@ -413,6 +415,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
+	.started	= rcu_batches_started_bh,
 	.completed	= rcu_batches_completed_bh,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
@@ -456,6 +459,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
@@ -554,6 +558,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
+	.started	= NULL,
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
@@ -590,6 +595,7 @@ static struct rcu_torture_ops sched_ops = {
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
+	.started	= rcu_batches_started_sched,
 	.completed	= rcu_batches_completed_sched,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
@@ -628,6 +634,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
+	.started	= rcu_no_completed,
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
@@ -1005,8 +1012,8 @@ static void rcutorture_trace_dump(void)
 static void rcu_torture_timer(unsigned long unused)
 {
 	int idx;
+	unsigned long started;
 	unsigned long completed;
-	unsigned long completed_end;
 	static DEFINE_TORTURE_RANDOM(rand);
 	static DEFINE_SPINLOCK(rand_lock);
 	struct rcu_torture *p;
@@ -1014,7 +1021,10 @@ static void rcu_torture_timer(unsigned long unused)
 	unsigned long long ts;
 
 	idx = cur_ops->readlock();
-	completed = cur_ops->completed();
+	if (cur_ops->started)
+		started = cur_ops->started();
+	else
+		started = cur_ops->completed();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1037,14 +1047,16 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed_end = cur_ops->completed();
+	completed = cur_ops->completed();
 	if (pipe_count > 1) {
 		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  completed, completed_end);
+					  started, completed);
 		rcutorture_trace_dump();
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed_end - completed;
+	completed = completed - started;
+	if (cur_ops->started)
+		completed++;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1063,8 +1075,8 @@ static void rcu_torture_timer(unsigned long unused)
 static int
 rcu_torture_reader(void *arg)
 {
+	unsigned long started;
 	unsigned long completed;
-	unsigned long completed_end;
 	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
 	struct rcu_torture *p;
@@ -1083,7 +1095,10 @@ rcu_torture_reader(void *arg)
 				mod_timer(&t, jiffies + 1);
 		}
 		idx = cur_ops->readlock();
-		completed = cur_ops->completed();
+		if (cur_ops->started)
+			started = cur_ops->started();
+		else
+			started = cur_ops->completed();
 		ts = rcu_trace_clock_local();
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
@@ -1104,14 +1119,16 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		completed_end = cur_ops->completed();
+		completed = cur_ops->completed();
 		if (pipe_count > 1) {
 			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, completed, completed_end);
+						  ts, started, completed);
 			rcutorture_trace_dump();
 		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed_end - completed;
+		completed = completed - started;
+		if (cur_ops->started)
+			completed++;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e26d78712e1..c0faad51ae8 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -315,7 +315,43 @@ static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(void);
 
 /*
- * Return the number of RCU-sched batches processed thus far for debug & stats.
+ * Return the number of RCU batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started(void)
+{
+	return rcu_state_p->gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started);
+
+/*
+ * Return the number of RCU-sched batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started_sched(void)
+{
+	return rcu_sched_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+
+/*
+ * Return the number of RCU BH batches started thus far for debug & stats.
+ */
+unsigned long rcu_batches_started_bh(void)
+{
+	return rcu_bh_state.gpnum;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
+
+/*
+ * Return the number of RCU batches completed thus far for debug & stats.
+ */
+unsigned long rcu_batches_completed(void)
+{
+	return rcu_state_p->completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Return the number of RCU-sched batches completed thus far for debug & stats.
  */
 unsigned long rcu_batches_completed_sched(void)
 {
@@ -324,7 +360,7 @@ unsigned long rcu_batches_completed_sched(void)
 EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
 /*
- * Return the number of RCU BH batches processed thus far for debug & stats.
+ * Return the number of RCU BH batches completed thus far for debug & stats.
  */
 unsigned long rcu_batches_completed_bh(void)
 {
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index f69300d4a51..07e61a04de1 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -113,25 +113,6 @@ static void __init rcu_bootup_announce(void)
 	rcu_bootup_announce_oddness();
 }
 
-/*
- * Return the number of RCU-preempt batches processed thus far
- * for debug and statistics.
- */
-static unsigned long rcu_batches_completed_preempt(void)
-{
-	return rcu_preempt_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_preempt);
-
-/*
- * Return the number of RCU batches processed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
-	return rcu_batches_completed_preempt();
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
 /*
  * Record a preemptible-RCU quiescent state for the specified CPU.  Note
  * that this just means that the task currently running on the CPU is
@@ -932,15 +913,6 @@ static void __init rcu_bootup_announce(void)
 	rcu_bootup_announce_oddness();
 }
 
-/*
- * Return the number of RCU batches processed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
-	return rcu_batches_completed_sched();
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
 /*
  * Because preemptible RCU does not exist, we never have to check for
  * CPUs being in quiescent states.
-- 
cgit v1.2.3-70-g09d2


From 31c89c959667194350f496947b576c149503ce98 Mon Sep 17 00:00:00 2001
From: Soren Brinkmann <soren.brinkmann@xilinx.com>
Date: Fri, 9 Jan 2015 07:43:45 -0800
Subject: pinctrl: pinconf-generic: Infer map type from DT property
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With the new 'groups' property, the DT parser can infer the map type
from the fact whether 'pins' or 'groups' is used to specify the pin
group to work on.

To maintain backwards compatibitliy with current usage of the DT
binding, this is only done when PIN_MAP_TYPE_INVALID is passed to the
parsing function as type.

Also, a new helper 'pinconf_generic_dt_node_to_map_all()' is introduced,
which can be used by drivers as generic callback for dt_node_to_map() to
leverage the new feature.

Changes since v2:
 - rename dt_pin_specifier to subnode_target_type
 - add additional comment in header file explaining passing an invalid
   map type
 - mention map_all() helper in commit message
Changes since RFC v2:
 - none

Signed-off-by: Soren Brinkmann <soren.brinkmann@xilinx.com>
Tested-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinconf-generic.c       | 17 ++++++++++++++---
 include/linux/pinctrl/pinconf-generic.h | 11 +++++++++++
 2 files changed, 25 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index f78b416d798..21b3d90ebb2 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -264,6 +264,7 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 	unsigned reserve;
 	struct property *prop;
 	const char *group;
+	const char *subnode_target_type = "pins";
 
 	ret = of_property_read_string(np, "function", &function);
 	if (ret < 0) {
@@ -284,10 +285,20 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		reserve++;
 	if (num_configs)
 		reserve++;
+
 	ret = of_property_count_strings(np, "pins");
 	if (ret < 0) {
-		dev_err(dev, "could not parse property pins\n");
-		goto exit;
+		ret = of_property_count_strings(np, "groups");
+		if (ret < 0) {
+			dev_err(dev, "could not parse property pins/groups\n");
+			goto exit;
+		}
+		if (type == PIN_MAP_TYPE_INVALID)
+			type = PIN_MAP_TYPE_CONFIGS_GROUP;
+		subnode_target_type = "groups";
+	} else {
+		if (type == PIN_MAP_TYPE_INVALID)
+			type = PIN_MAP_TYPE_CONFIGS_PIN;
 	}
 	reserve *= ret;
 
@@ -296,7 +307,7 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 	if (ret < 0)
 		goto exit;
 
-	of_property_for_each_string(np, "pins", prop, group) {
+	of_property_for_each_string(np, subnode_target_type, prop, group) {
 		if (function) {
 			ret = pinctrl_utils_add_map_mux(pctldev, map,
 					reserved_maps, num_maps, group,
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index d578a60eff2..83c89f5ab70 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -174,6 +174,17 @@ static inline int pinconf_generic_dt_node_to_map_pin(
 			PIN_MAP_TYPE_CONFIGS_PIN);
 }
 
+static inline int pinconf_generic_dt_node_to_map_all(
+		struct pinctrl_dev *pctldev, struct device_node *np_config,
+		struct pinctrl_map **map, unsigned *num_maps)
+{
+	/*
+	 * passing the type as PIN_MAP_TYPE_INVALID causes the underlying parser
+	 * to infer the map type from the DT properties used.
+	 */
+	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
+			PIN_MAP_TYPE_INVALID);
+}
 #endif
 
 #endif /* CONFIG_GENERIC_PINCONF */
-- 
cgit v1.2.3-70-g09d2


From dd4d01f7bad886c22687224bc7070b87de8deb51 Mon Sep 17 00:00:00 2001
From: Soren Brinkmann <soren.brinkmann@xilinx.com>
Date: Fri, 9 Jan 2015 07:43:46 -0800
Subject: pinctrl: pinconf-generic: Allow driver to specify DT params
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Additionally to the generic DT parameters, allow drivers to provide
driver-specific DT parameters to be used with the generic parser
infrastructure.

To achieve this 'struct pinctrl_desc' is extended to pass custom pinconf
option to the core. In order to pass this kind of information, the
related data structures - 'struct pinconf_generic_dt_params',
'pin_config_item' - are moved from pinconf internals to the
pinconf-generic header.

Additionally pinconfg-generic is refactored to not only iterate over the
generic pinconf parameters but also take the parameters into account
that are provided through the driver's 'struct pinctrl_desc'.
In particular 'pinconf_generic_parse_dt_config()' and
'pinconf_generic_dump' helpers are split into two parts each. In order
to have a more generic helper that can be used to process the generic
parameters as well as the driver-specific ones.

v2:
 - fix typo
 - add missing documentation for @conf_items member in struct
 - rebase to pinctrl/devel: conflict in abx500
 - rename _pinconf_generic_dump() to pinconf_generic_dump_one()
 - removed '_' from _parse_dt_cfg()
 - removed BUG_ONs, error condition is handled in if statements
 - removed pinconf_generic_dump_group() & pinconf_generic_dump_pin
   helpers
   - fixed up corresponding call sites
   - renamed pinconf_generic_dump() to pinconf_generic_dump_pins()
   - added kernel-doc to pinconf_generic_dump_pins()
 - add kernel-doc
 - more verbose commit message

Signed-off-by: Soren Brinkmann <soren.brinkmann@xilinx.com>
Tested-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/nomadik/pinctrl-abx500.c |   2 +-
 drivers/pinctrl/pinconf-generic.c        | 182 +++++++++++++++++--------------
 drivers/pinctrl/pinconf.c                |   4 +-
 drivers/pinctrl/pinconf.h                |  22 ++--
 drivers/pinctrl/pinctrl-rockchip.c       |   2 +-
 drivers/pinctrl/pinctrl-tz1090-pdc.c     |   2 +-
 drivers/pinctrl/pinctrl-tz1090.c         |   2 +-
 drivers/pinctrl/sh-pfc/pinctrl.c         |   2 +-
 include/linux/pinctrl/pinconf-generic.h  |  18 +++
 include/linux/pinctrl/pinctrl.h          |   9 ++
 10 files changed, 141 insertions(+), 104 deletions(-)

(limited to 'include')

diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 3d6d9722852..1806b24faa1 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -914,7 +914,7 @@ static int abx500_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		}
 	}
 
-	ret = pinconf_generic_parse_dt_config(np, &configs, &nconfigs);
+	ret = pinconf_generic_parse_dt_config(np, pctldev, &configs, &nconfigs);
 	if (nconfigs) {
 		const char *gpio_name;
 		const char *pin;
diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index 21b3d90ebb2..e0886665b70 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -27,17 +27,6 @@
 #include "pinctrl-utils.h"
 
 #ifdef CONFIG_DEBUG_FS
-
-struct pin_config_item {
-	const enum pin_config_param param;
-	const char * const display;
-	const char * const format;
-	bool has_arg;
-};
-
-#define PCONFDUMP(a, b, c, d) { .param = a, .display = b, .format = c, \
-				.has_arg = d }
-
 static const struct pin_config_item conf_items[] = {
 	PCONFDUMP(PIN_CONFIG_BIAS_DISABLE, "input bias disabled", NULL, false),
 	PCONFDUMP(PIN_CONFIG_BIAS_HIGH_IMPEDANCE, "input bias high impedance", NULL, false),
@@ -60,22 +49,25 @@ static const struct pin_config_item conf_items[] = {
 	PCONFDUMP(PIN_CONFIG_OUTPUT, "pin output", "level", true),
 };
 
-void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev,
-			      struct seq_file *s, unsigned pin)
+static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev,
+				     struct seq_file *s, const char *gname,
+				     unsigned pin,
+				     const struct pin_config_item *items,
+				     int nitems)
 {
-	const struct pinconf_ops *ops = pctldev->desc->confops;
 	int i;
 
-	if (!ops->is_generic)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(conf_items); i++) {
+	for (i = 0; i < nitems; i++) {
 		unsigned long config;
 		int ret;
 
 		/* We want to check out this parameter */
-		config = pinconf_to_config_packed(conf_items[i].param, 0);
-		ret = pin_config_get_for_pin(pctldev, pin, &config);
+		config = pinconf_to_config_packed(items[i].param, 0);
+		if (gname)
+			ret = pin_config_group_get(dev_name(pctldev->dev),
+						   gname, &config);
+		else
+			ret = pin_config_get_for_pin(pctldev, pin, &config);
 		/* These are legal errors */
 		if (ret == -EINVAL || ret == -ENOTSUPP)
 			continue;
@@ -85,56 +77,46 @@ void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev,
 		}
 		/* Space between multiple configs */
 		seq_puts(s, " ");
-		seq_puts(s, conf_items[i].display);
+		seq_puts(s, items[i].display);
 		/* Print unit if available */
-		if (conf_items[i].has_arg) {
+		if (items[i].has_arg) {
 			seq_printf(s, " (%u",
 				   pinconf_to_config_argument(config));
-			if (conf_items[i].format)
-				seq_printf(s, " %s)", conf_items[i].format);
+			if (items[i].format)
+				seq_printf(s, " %s)", items[i].format);
 			else
 				seq_puts(s, ")");
 		}
 	}
 }
 
-void pinconf_generic_dump_group(struct pinctrl_dev *pctldev,
-			      struct seq_file *s, const char *gname)
+/**
+ * pinconf_generic_dump_pins - Print information about pin or group of pins
+ * @pctldev:	Pincontrol device
+ * @s:		File to print to
+ * @gname:	Group name specifying pins
+ * @pin:	Pin number specyfying pin
+ *
+ * Print the pinconf configuration for the requested pin(s) to @s. Pins can be
+ * specified either by pin using @pin or by group using @gname. Only one needs
+ * to be specified the other can be NULL/0.
+ */
+void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, struct seq_file *s,
+			       const char *gname, unsigned pin)
 {
 	const struct pinconf_ops *ops = pctldev->desc->confops;
-	int i;
 
 	if (!ops->is_generic)
 		return;
 
-	for (i = 0; i < ARRAY_SIZE(conf_items); i++) {
-		unsigned long config;
-		int ret;
-
-		/* We want to check out this parameter */
-		config = pinconf_to_config_packed(conf_items[i].param, 0);
-		ret = pin_config_group_get(dev_name(pctldev->dev), gname,
-					   &config);
-		/* These are legal errors */
-		if (ret == -EINVAL || ret == -ENOTSUPP)
-			continue;
-		if (ret) {
-			seq_printf(s, "ERROR READING CONFIG SETTING %d ", i);
-			continue;
-		}
-		/* Space between multiple configs */
-		seq_puts(s, " ");
-		seq_puts(s, conf_items[i].display);
-		/* Print unit if available */
-		if (conf_items[i].has_arg) {
-			seq_printf(s, " (%u",
-				   pinconf_to_config_argument(config));
-			if (conf_items[i].format)
-				seq_printf(s, " %s)", conf_items[i].format);
-			else
-				seq_puts(s, ")");
-		}
-	}
+	/* generic parameters */
+	pinconf_generic_dump_one(pctldev, s, gname, pin, conf_items,
+				 ARRAY_SIZE(conf_items));
+	/* driver-specific parameters */
+	if (pctldev->desc->num_dt_params && pctldev->desc->conf_items)
+		pinconf_generic_dump_one(pctldev, s, gname, pin,
+					 pctldev->desc->conf_items,
+					 pctldev->desc->num_dt_params);
 }
 
 void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
@@ -148,17 +130,21 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 		seq_printf(s, "%s: 0x%x", conf_items[i].display,
 			   pinconf_to_config_argument(config));
 	}
+
+	if (!pctldev->desc->num_dt_params || !pctldev->desc->conf_items)
+		return;
+
+	for (i = 0; i < pctldev->desc->num_dt_params; i++) {
+		if (pinconf_to_config_param(config) != pctldev->desc->conf_items[i].param)
+			continue;
+		seq_printf(s, "%s: 0x%x", pctldev->desc->conf_items[i].display,
+			   pinconf_to_config_argument(config));
+	}
 }
 EXPORT_SYMBOL_GPL(pinconf_generic_dump_config);
 #endif
 
 #ifdef CONFIG_OF
-struct pinconf_generic_dt_params {
-	const char * const property;
-	enum pin_config_param param;
-	u32 default_value;
-};
-
 static const struct pinconf_generic_dt_params dt_params[] = {
 	{ "bias-disable", PIN_CONFIG_BIAS_DISABLE, 0 },
 	{ "bias-high-impedance", PIN_CONFIG_BIAS_HIGH_IMPEDANCE, 0 },
@@ -183,6 +169,47 @@ static const struct pinconf_generic_dt_params dt_params[] = {
 	{ "slew-rate", PIN_CONFIG_SLEW_RATE, 0},
 };
 
+/**
+ * parse_dt_cfg - Parse DT pinconf parameters
+ * @np:	DT node
+ * @params:	Array of describing DT parameters
+ * @count:	Number of entries in @params
+ * @cfg:	Array of parsed config options
+ * @ncfg:	Number of entries in @cfg
+ *
+ * Parse the config options described in @params from @np and puts the result
+ * in @cfg. @cfg does not need to be empty, entries are added beggining at
+ * @ncfg. @ncfg is updated to reflect the number of entries after parsing. @cfg
+ * needs to have enough memory allocated to hold all possible entries.
+ */
+static void parse_dt_cfg(struct device_node *np,
+			 const struct pinconf_generic_dt_params *params,
+			 unsigned int count, unsigned long *cfg,
+			 unsigned int *ncfg)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		u32 val;
+		int ret;
+		const struct pinconf_generic_dt_params *par = &params[i];
+
+		ret = of_property_read_u32(np, par->property, &val);
+
+		/* property not found */
+		if (ret == -EINVAL)
+			continue;
+
+		/* use default value, when no value is specified */
+		if (ret)
+			val = par->default_value;
+
+		pr_debug("found %s with value %u\n", par->property, val);
+		cfg[*ncfg] = pinconf_to_config_packed(par->param, val);
+		(*ncfg)++;
+	}
+}
+
 /**
  * pinconf_generic_parse_dt_config()
  * parse the config properties into generic pinconfig values.
@@ -191,39 +218,29 @@ static const struct pinconf_generic_dt_params dt_params[] = {
  * @nconfigs: umber of configurations
  */
 int pinconf_generic_parse_dt_config(struct device_node *np,
+				    struct pinctrl_dev *pctldev,
 				    unsigned long **configs,
 				    unsigned int *nconfigs)
 {
 	unsigned long *cfg;
-	unsigned int ncfg = 0;
+	unsigned int max_cfg, ncfg = 0;
 	int ret;
-	int i;
-	u32 val;
 
 	if (!np)
 		return -EINVAL;
 
 	/* allocate a temporary array big enough to hold one of each option */
-	cfg = kzalloc(sizeof(*cfg) * ARRAY_SIZE(dt_params), GFP_KERNEL);
+	max_cfg = ARRAY_SIZE(dt_params);
+	if (pctldev)
+		max_cfg += pctldev->desc->num_dt_params;
+	cfg = kcalloc(max_cfg, sizeof(*cfg), GFP_KERNEL);
 	if (!cfg)
 		return -ENOMEM;
 
-	for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
-		const struct pinconf_generic_dt_params *par = &dt_params[i];
-		ret = of_property_read_u32(np, par->property, &val);
-
-		/* property not found */
-		if (ret == -EINVAL)
-			continue;
-
-		/* use default value, when no value is specified */
-		if (ret)
-			val = par->default_value;
-
-		pr_debug("found %s with value %u\n", par->property, val);
-		cfg[ncfg] = pinconf_to_config_packed(par->param, val);
-		ncfg++;
-	}
+	parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg);
+	if (pctldev && pctldev->desc->num_dt_params && pctldev->desc->params)
+		parse_dt_cfg(np, pctldev->desc->params,
+			      pctldev->desc->num_dt_params, cfg, &ncfg);
 
 	ret = 0;
 
@@ -274,7 +291,8 @@ int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		function = NULL;
 	}
 
-	ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs);
+	ret = pinconf_generic_parse_dt_config(np, pctldev, &configs,
+					      &num_configs);
 	if (ret < 0) {
 		dev_err(dev, "could not parse node property\n");
 		return ret;
diff --git a/drivers/pinctrl/pinconf.c b/drivers/pinctrl/pinconf.c
index 8bfa0643e5d..1fc09dc2019 100644
--- a/drivers/pinctrl/pinconf.c
+++ b/drivers/pinctrl/pinconf.c
@@ -288,7 +288,7 @@ static void pinconf_dump_pin(struct pinctrl_dev *pctldev,
 	const struct pinconf_ops *ops = pctldev->desc->confops;
 
 	/* no-op when not using generic pin config */
-	pinconf_generic_dump_pin(pctldev, s, pin);
+	pinconf_generic_dump_pins(pctldev, s, NULL, pin);
 	if (ops && ops->pin_config_dbg_show)
 		ops->pin_config_dbg_show(pctldev, s, pin);
 }
@@ -333,7 +333,7 @@ static void pinconf_dump_group(struct pinctrl_dev *pctldev,
 	const struct pinconf_ops *ops = pctldev->desc->confops;
 
 	/* no-op when not using generic pin config */
-	pinconf_generic_dump_group(pctldev, s, gname);
+	pinconf_generic_dump_pins(pctldev, s, gname, 0);
 	if (ops && ops->pin_config_group_dbg_show)
 		ops->pin_config_group_dbg_show(pctldev, s, selector);
 }
diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h
index a4a5417e141..55c75780b3b 100644
--- a/drivers/pinctrl/pinconf.h
+++ b/drivers/pinctrl/pinconf.h
@@ -92,26 +92,17 @@ static inline void pinconf_init_device_debugfs(struct dentry *devroot,
 
 #if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_DEBUG_FS)
 
-void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev,
-			      struct seq_file *s, unsigned pin);
-
-void pinconf_generic_dump_group(struct pinctrl_dev *pctldev,
-			      struct seq_file *s, const char *gname);
+void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
+			       struct seq_file *s, const char *gname,
+			       unsigned pin);
 
 void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 				 struct seq_file *s, unsigned long config);
 #else
 
-static inline void pinconf_generic_dump_pin(struct pinctrl_dev *pctldev,
-					    struct seq_file *s,
-					    unsigned pin)
-{
-	return;
-}
-
-static inline void pinconf_generic_dump_group(struct pinctrl_dev *pctldev,
-					      struct seq_file *s,
-					      const char *gname)
+static inline void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
+					     struct seq_file *s,
+					     const char *gname, unsigned pin)
 {
 	return;
 }
@@ -126,6 +117,7 @@ static inline void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 
 #if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF)
 int pinconf_generic_parse_dt_config(struct device_node *np,
+				    struct pinctrl_dev *pctldev,
 				    unsigned long **configs,
 				    unsigned int *nconfigs);
 #endif
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index ba74f0aa60c..7625f333ab0 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -1140,7 +1140,7 @@ static int rockchip_pinctrl_parse_groups(struct device_node *np,
 			return -EINVAL;
 
 		np_config = of_find_node_by_phandle(be32_to_cpup(phandle));
-		ret = pinconf_generic_parse_dt_config(np_config,
+		ret = pinconf_generic_parse_dt_config(np_config, NULL,
 				&grp->data[j].configs, &grp->data[j].nconfigs);
 		if (ret)
 			return ret;
diff --git a/drivers/pinctrl/pinctrl-tz1090-pdc.c b/drivers/pinctrl/pinctrl-tz1090-pdc.c
index 146e48a9b83..fab6aafa6a9 100644
--- a/drivers/pinctrl/pinctrl-tz1090-pdc.c
+++ b/drivers/pinctrl/pinctrl-tz1090-pdc.c
@@ -415,7 +415,7 @@ static int tz1090_pdc_pinctrl_dt_subnode_to_map(struct device *dev,
 		function = NULL;
 	}
 
-	ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs);
+	ret = pinconf_generic_parse_dt_config(np, NULL, &configs, &num_configs);
 	if (ret)
 		return ret;
 
diff --git a/drivers/pinctrl/pinctrl-tz1090.c b/drivers/pinctrl/pinctrl-tz1090.c
index df8cb1e5b7b..8bd73075f9d 100644
--- a/drivers/pinctrl/pinctrl-tz1090.c
+++ b/drivers/pinctrl/pinctrl-tz1090.c
@@ -1131,7 +1131,7 @@ static int tz1090_pinctrl_dt_subnode_to_map(struct device *dev,
 		function = NULL;
 	}
 
-	ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs);
+	ret = pinconf_generic_parse_dt_config(np, NULL, &configs, &num_configs);
 	if (ret)
 		return ret;
 
diff --git a/drivers/pinctrl/sh-pfc/pinctrl.c b/drivers/pinctrl/sh-pfc/pinctrl.c
index 910deaefa0a..072e7c62cab 100644
--- a/drivers/pinctrl/sh-pfc/pinctrl.c
+++ b/drivers/pinctrl/sh-pfc/pinctrl.c
@@ -122,7 +122,7 @@ static int sh_pfc_dt_subnode_to_map(struct device *dev, struct device_node *np,
 		return ret;
 	}
 
-	ret = pinconf_generic_parse_dt_config(np, &configs, &num_configs);
+	ret = pinconf_generic_parse_dt_config(np, NULL, &configs, &num_configs);
 	if (ret < 0)
 		return ret;
 
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index 83c89f5ab70..342409f7f3e 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -115,6 +115,18 @@ enum pin_config_param {
 	PIN_CONFIG_END = 0x7FFF,
 };
 
+#ifdef CONFIG_DEBUG_FS
+#define PCONFDUMP(a, b, c, d) { .param = a, .display = b, .format = c, \
+				.has_arg = d }
+
+struct pin_config_item {
+	const enum pin_config_param param;
+	const char * const display;
+	const char * const format;
+	bool has_arg;
+};
+#endif /* CONFIG_DEBUG_FS */
+
 /*
  * Helpful configuration macro to be used in tables etc.
  */
@@ -150,6 +162,12 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param
 struct pinctrl_dev;
 struct pinctrl_map;
 
+struct pinconf_generic_dt_params {
+	const char * const property;
+	enum pin_config_param param;
+	u32 default_value;
+};
+
 int pinconf_generic_dt_subnode_to_map(struct pinctrl_dev *pctldev,
 		struct device_node *np, struct pinctrl_map **map,
 		unsigned *reserved_maps, unsigned *num_maps,
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index cc8e1aff0e2..c58b3e11ba8 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -24,6 +24,7 @@ struct pinctrl_dev;
 struct pinctrl_map;
 struct pinmux_ops;
 struct pinconf_ops;
+struct pin_config_item;
 struct gpio_chip;
 struct device_node;
 
@@ -117,6 +118,9 @@ struct pinctrl_ops {
  * @confops: pin config operations vtable, if you support pin configuration in
  *	your driver
  * @owner: module providing the pin controller, used for refcounting
+ * @num_dt_params: Number of driver-specific DT parameters
+ * @params: List of DT parameters
+ * @conf_items: Information how to print @params in debugfs
  */
 struct pinctrl_desc {
 	const char *name;
@@ -126,6 +130,11 @@ struct pinctrl_desc {
 	const struct pinmux_ops *pmxops;
 	const struct pinconf_ops *confops;
 	struct module *owner;
+#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF)
+	unsigned int num_dt_params;
+	const struct pinconf_generic_dt_params *params;
+	const struct pin_config_item *conf_items;
+#endif
 };
 
 /* External interface to pin controller */
-- 
cgit v1.2.3-70-g09d2


From 029b18361921a0a07b17bd89a2cf20df3d115de8 Mon Sep 17 00:00:00 2001
From: Gabriel Laskar <gabriel@lse.epita.fr>
Date: Sun, 11 Jan 2015 16:18:06 -0800
Subject: Input: uinput - fix ioctl nr overflow for UI_GET_SYSNAME/VERSION

Request number for ioctls are encoded as 8bit numbers, but unfortunately
UI_GET_SYSNAME and UI_GET_VERSION specifu values larger than that, so they
get truncated to 44 (0x2c) and 45 (0x2d). This change makes requested
values match their effective values (the ABI stays intact).

Signed-off-by: Gabriel Laskar <gabriel@lse.epita.fr>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/uapi/linux/uinput.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/uinput.h b/include/uapi/linux/uinput.h
index baeab83deb6..013c9d8db37 100644
--- a/include/uapi/linux/uinput.h
+++ b/include/uapi/linux/uinput.h
@@ -82,7 +82,7 @@ struct uinput_ff_erase {
  * The complete sysfs path is then /sys/devices/virtual/input/--NAME--
  * Usually, it is in the form "inputN"
  */
-#define UI_GET_SYSNAME(len)	_IOC(_IOC_READ, UINPUT_IOCTL_BASE, 300, len)
+#define UI_GET_SYSNAME(len)	_IOC(_IOC_READ, UINPUT_IOCTL_BASE, 44, len)
 
 /**
  * UI_GET_VERSION - Return version of uinput protocol
@@ -91,7 +91,7 @@ struct uinput_ff_erase {
  * the integer pointed to by the ioctl argument. The protocol version
  * is hard-coded in the kernel and is independent of the uinput device.
  */
-#define UI_GET_VERSION		_IOR(UINPUT_IOCTL_BASE, 301, unsigned int)
+#define UI_GET_VERSION		_IOR(UINPUT_IOCTL_BASE, 45, unsigned int)
 
 /*
  * To write a force-feedback-capable driver, the upload_effect
-- 
cgit v1.2.3-70-g09d2


From 58fddc288b5cec192ad9eb9221da7ed14d974a27 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 8 Jan 2015 17:54:14 +0200
Subject: drm/i915: add component support

Register a component to be used to interface with the snd_hda_intel
driver. This is meant to replace the same interface that is currently
based on module symbol lookup.

v2:
- change roles between the hda and i915 components (Daniel)
- add the implementation to a new file (Jani)
- use better namespacing (Jani)
v3:
- move the implementation to intel_audio.c (Daniel)
- rename display_component to audio_component (Daniel)
- add kerneldoc (Daniel)
v4:
- run forgotten git rm i915_component.c (Jani)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/i915_dma.c    |   4 ++
 drivers/gpu/drm/i915/i915_drv.h    |   3 +
 drivers/gpu/drm/i915/intel_audio.c | 110 +++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_drv.h   |   2 +
 include/drm/i915_component.h       |  38 +++++++++++++
 5 files changed, 157 insertions(+)
 create mode 100644 include/drm/i915_component.h

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index ecee3bcc877..26b3199e0af 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -830,6 +830,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	intel_runtime_pm_enable(dev_priv);
 
+	i915_audio_component_init(dev_priv);
+
 	return 0;
 
 out_power_well:
@@ -870,6 +872,8 @@ int i915_driver_unload(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
+	i915_audio_component_cleanup(dev_priv);
+
 	ret = i915_gem_suspend(dev);
 	if (ret) {
 		DRM_ERROR("failed to idle hardware: %d\n", ret);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a343f2f35df..176afc507f7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1698,6 +1698,9 @@ struct drm_i915_private {
 	struct drm_property *broadcast_rgb_property;
 	struct drm_property *force_audio_property;
 
+	/* hda/i915 audio component */
+	bool audio_component_registered;
+
 	uint32_t hw_context_size;
 	struct list_head context_list;
 
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 2c7ed5cb29c..ee41b882e71 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -22,6 +22,9 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/component.h>
+#include <drm/i915_component.h>
+#include "intel_drv.h"
 
 #include <drm/drmP.h>
 #include <drm/drm_edid.h>
@@ -461,3 +464,110 @@ void intel_init_audio(struct drm_device *dev)
 		dev_priv->display.audio_codec_disable = ilk_audio_codec_disable;
 	}
 }
+
+static void i915_audio_component_get_power(struct device *dev)
+{
+	intel_display_power_get(dev_to_i915(dev), POWER_DOMAIN_AUDIO);
+}
+
+static void i915_audio_component_put_power(struct device *dev)
+{
+	intel_display_power_put(dev_to_i915(dev), POWER_DOMAIN_AUDIO);
+}
+
+/* Get CDCLK in kHz  */
+static int i915_audio_component_get_cdclk_freq(struct device *dev)
+{
+	struct drm_i915_private *dev_priv = dev_to_i915(dev);
+	int ret;
+
+	if (WARN_ON_ONCE(!HAS_DDI(dev_priv)))
+		return -ENODEV;
+
+	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
+	ret = intel_ddi_get_cdclk_freq(dev_priv);
+	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
+
+	return ret;
+}
+
+static const struct i915_audio_component_ops i915_audio_component_ops = {
+	.owner		= THIS_MODULE,
+	.get_power	= i915_audio_component_get_power,
+	.put_power	= i915_audio_component_put_power,
+	.get_cdclk_freq	= i915_audio_component_get_cdclk_freq,
+};
+
+static int i915_audio_component_bind(struct device *i915_dev,
+				     struct device *hda_dev, void *data)
+{
+	struct i915_audio_component *acomp = data;
+
+	if (WARN_ON(acomp->ops || acomp->dev))
+		return -EEXIST;
+
+	acomp->ops = &i915_audio_component_ops;
+	acomp->dev = i915_dev;
+
+	return 0;
+}
+
+static void i915_audio_component_unbind(struct device *i915_dev,
+					struct device *hda_dev, void *data)
+{
+	struct i915_audio_component *acomp = data;
+
+	acomp->ops = NULL;
+	acomp->dev = NULL;
+}
+
+static const struct component_ops i915_audio_component_bind_ops = {
+	.bind	= i915_audio_component_bind,
+	.unbind	= i915_audio_component_unbind,
+};
+
+/**
+ * i915_audio_component_init - initialize and register the audio component
+ * @dev_priv: i915 device instance
+ *
+ * This will register with the component framework a child component which
+ * will bind dynamically to the snd_hda_intel driver's corresponding master
+ * component when the latter is registered. During binding the child
+ * initializes an instance of struct i915_audio_component which it receives
+ * from the master. The master can then start to use the interface defined by
+ * this struct. Each side can break the binding at any point by deregistering
+ * its own component after which each side's component unbind callback is
+ * called.
+ *
+ * We ignore any error during registration and continue with reduced
+ * functionality (i.e. without HDMI audio).
+ */
+void i915_audio_component_init(struct drm_i915_private *dev_priv)
+{
+	int ret;
+
+	ret = component_add(dev_priv->dev->dev, &i915_audio_component_bind_ops);
+	if (ret < 0) {
+		DRM_ERROR("failed to add audio component (%d)\n", ret);
+		/* continue with reduced functionality */
+		return;
+	}
+
+	dev_priv->audio_component_registered = true;
+}
+
+/**
+ * i915_audio_component_cleanup - deregister the audio component
+ * @dev_priv: i915 device instance
+ *
+ * Deregisters the audio component, breaking any existing binding to the
+ * corresponding snd_hda_intel driver's master component.
+ */
+void i915_audio_component_cleanup(struct drm_i915_private *dev_priv)
+{
+	if (!dev_priv->audio_component_registered)
+		return;
+
+	component_del(dev_priv->dev->dev, &i915_audio_component_bind_ops);
+	dev_priv->audio_component_registered = false;
+}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 25fdbb16d4e..e88fd5d12f0 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -872,6 +872,8 @@ void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire);
 void intel_init_audio(struct drm_device *dev);
 void intel_audio_codec_enable(struct intel_encoder *encoder);
 void intel_audio_codec_disable(struct intel_encoder *encoder);
+void i915_audio_component_init(struct drm_i915_private *dev_priv);
+void i915_audio_component_cleanup(struct drm_i915_private *dev_priv);
 
 /* intel_display.c */
 const char *intel_output_name(int output);
diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h
new file mode 100644
index 00000000000..3e2f22e5bf3
--- /dev/null
+++ b/include/drm/i915_component.h
@@ -0,0 +1,38 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _I915_COMPONENT_H_
+#define _I915_COMPONENT_H_
+
+struct i915_audio_component {
+	struct device *dev;
+
+	const struct i915_audio_component_ops {
+		struct module *owner;
+		void (*get_power)(struct device *);
+		void (*put_power)(struct device *);
+		int (*get_cdclk_freq)(struct device *);
+	} *ops;
+};
+
+#endif /* _I915_COMPONENT_H_ */
-- 
cgit v1.2.3-70-g09d2


From fcf3aac5fc307f0cae429f5844ddc25761662858 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 8 Jan 2015 17:54:18 +0200
Subject: drm/i915: remove unused power_well/get_cdclk_freq api

After switching to using the component interface this API isn't needed
any more.

v2-3: unchanged
v4:
- move the removal of i915_powerwell.h to this patch (Takashi)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_runtime_pm.c | 56 ---------------------------------
 include/drm/i915_powerwell.h            | 37 ----------------------
 2 files changed, 93 deletions(-)
 delete mode 100644 include/drm/i915_powerwell.h

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index ac6da7102fb..39ddf40171b 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -31,7 +31,6 @@
 
 #include "i915_drv.h"
 #include "intel_drv.h"
-#include <drm/i915_powerwell.h>
 
 /**
  * DOC: runtime pm
@@ -50,8 +49,6 @@
  * present for a given platform.
  */
 
-static struct i915_power_domains *hsw_pwr;
-
 #define for_each_power_well(i, power_well, domain_mask, power_domains)	\
 	for (i = 0;							\
 	     i < (power_domains)->power_well_count &&			\
@@ -1071,10 +1068,8 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	 */
 	if (IS_HASWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, hsw_power_wells);
-		hsw_pwr = power_domains;
 	} else if (IS_BROADWELL(dev_priv->dev)) {
 		set_power_wells(power_domains, bdw_power_wells);
-		hsw_pwr = power_domains;
 	} else if (IS_CHERRYVIEW(dev_priv->dev)) {
 		set_power_wells(power_domains, chv_power_wells);
 	} else if (IS_VALLEYVIEW(dev_priv->dev)) {
@@ -1118,8 +1113,6 @@ void intel_power_domains_fini(struct drm_i915_private *dev_priv)
 	 * the power well is not enabled, so just enable it in case
 	 * we're going to unload/reload. */
 	intel_display_set_init_power(dev_priv, true);
-
-	hsw_pwr = NULL;
 }
 
 static void intel_power_domains_resume(struct drm_i915_private *dev_priv)
@@ -1328,52 +1321,3 @@ void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 	pm_runtime_put_autosuspend(device);
 }
 
-/* Display audio driver power well request */
-int i915_request_power_well(void)
-{
-	struct drm_i915_private *dev_priv;
-
-	if (!hsw_pwr)
-		return -ENODEV;
-
-	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
-				power_domains);
-	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(i915_request_power_well);
-
-/* Display audio driver power well release */
-int i915_release_power_well(void)
-{
-	struct drm_i915_private *dev_priv;
-
-	if (!hsw_pwr)
-		return -ENODEV;
-
-	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
-				power_domains);
-	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(i915_release_power_well);
-
-/*
- * Private interface for the audio driver to get CDCLK in kHz.
- *
- * Caller must request power well using i915_request_power_well() prior to
- * making the call.
- */
-int i915_get_cdclk_freq(void)
-{
-	struct drm_i915_private *dev_priv;
-
-	if (!hsw_pwr)
-		return -ENODEV;
-
-	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
-				power_domains);
-
-	return intel_ddi_get_cdclk_freq(dev_priv);
-}
-EXPORT_SYMBOL_GPL(i915_get_cdclk_freq);
diff --git a/include/drm/i915_powerwell.h b/include/drm/i915_powerwell.h
deleted file mode 100644
index baa6f11b183..00000000000
--- a/include/drm/i915_powerwell.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/**************************************************************************
- *
- * Copyright 2013 Intel Inc.
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- *
- **************************************************************************/
-
-#ifndef _I915_POWERWELL_H_
-#define _I915_POWERWELL_H_
-
-/* For use by hda_i915 driver */
-extern int i915_request_power_well(void);
-extern int i915_release_power_well(void);
-extern int i915_get_cdclk_freq(void);
-
-#endif				/* _I915_POWERWELL_H_ */
-- 
cgit v1.2.3-70-g09d2


From 7bb68410ef22067b08fd52887875b8f337f89dcc Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Sat, 18 Oct 2014 15:04:15 +0200
Subject: efi: split off remapping code from efi_config_init()

Split of the remapping code from efi_config_init() so that the caller
can perform its own remapping. This is necessary to correctly handle
virtually remapped UEFI memory regions under kexec, as efi.systab will
have been updated to a virtual address.

Acked-by: Matt Fleming <matt.fleming@intel.com>
Tested-by: Leif Lindholm <leif.lindholm@linaro.org>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 drivers/firmware/efi/efi.c | 56 ++++++++++++++++++++++++++--------------------
 include/linux/efi.h        |  2 ++
 2 files changed, 34 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9035c1b74d5..b7ba9d8ec4b 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -293,29 +293,15 @@ static __init int match_config_table(efi_guid_t *guid,
 	return 0;
 }
 
-int __init efi_config_init(efi_config_table_type_t *arch_tables)
+int __init efi_config_parse_tables(void *config_tables, int count, int sz,
+				   efi_config_table_type_t *arch_tables)
 {
-	void *config_tables, *tablep;
-	int i, sz;
-
-	if (efi_enabled(EFI_64BIT))
-		sz = sizeof(efi_config_table_64_t);
-	else
-		sz = sizeof(efi_config_table_32_t);
-
-	/*
-	 * Let's see what config tables the firmware passed to us.
-	 */
-	config_tables = early_memremap(efi.systab->tables,
-				       efi.systab->nr_tables * sz);
-	if (config_tables == NULL) {
-		pr_err("Could not map Configuration table!\n");
-		return -ENOMEM;
-	}
+	void *tablep;
+	int i;
 
 	tablep = config_tables;
 	pr_info("");
-	for (i = 0; i < efi.systab->nr_tables; i++) {
+	for (i = 0; i < count; i++) {
 		efi_guid_t guid;
 		unsigned long table;
 
@@ -328,8 +314,6 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables)
 			if (table64 >> 32) {
 				pr_cont("\n");
 				pr_err("Table located above 4GB, disabling EFI.\n");
-				early_memunmap(config_tables,
-					       efi.systab->nr_tables * sz);
 				return -EINVAL;
 			}
 #endif
@@ -344,13 +328,37 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables)
 		tablep += sz;
 	}
 	pr_cont("\n");
-	early_memunmap(config_tables, efi.systab->nr_tables * sz);
-
 	set_bit(EFI_CONFIG_TABLES, &efi.flags);
-
 	return 0;
 }
 
+int __init efi_config_init(efi_config_table_type_t *arch_tables)
+{
+	void *config_tables;
+	int sz, ret;
+
+	if (efi_enabled(EFI_64BIT))
+		sz = sizeof(efi_config_table_64_t);
+	else
+		sz = sizeof(efi_config_table_32_t);
+
+	/*
+	 * Let's see what config tables the firmware passed to us.
+	 */
+	config_tables = early_memremap(efi.systab->tables,
+				       efi.systab->nr_tables * sz);
+	if (config_tables == NULL) {
+		pr_err("Could not map Configuration table!\n");
+		return -ENOMEM;
+	}
+
+	ret = efi_config_parse_tables(config_tables, efi.systab->nr_tables, sz,
+				      arch_tables);
+
+	early_memunmap(config_tables, efi.systab->nr_tables * sz);
+	return ret;
+}
+
 #ifdef CONFIG_EFI_VARS_MODULE
 static int __init efi_load_efivars(void)
 {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 0238d612750..5ffe5115951 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -875,6 +875,8 @@ static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned lon
 #endif
 extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
 extern int efi_config_init(efi_config_table_type_t *arch_tables);
+extern int efi_config_parse_tables(void *config_tables, int count, int sz,
+				   efi_config_table_type_t *arch_tables);
 extern u64 efi_get_iobase (void);
 extern u32 efi_mem_type (unsigned long phys_addr);
 extern u64 efi_mem_attributes (unsigned long phys_addr);
-- 
cgit v1.2.3-70-g09d2


From 1904a853fae40ee61bed7c231fc5bd2158984441 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Sun, 11 Jan 2015 13:50:44 -0800
Subject: Bluetooth: Add opcode parameter to hci_req_complete_t callback

When hci_req_run() calls its provided complete function and one of the
HCI commands in the sequence fails, then provide the opcode of failing
command. In case of success HCI_OP_NOP is provided since all commands
completed.

This patch fixes the prototype of hci_req_complete_t and all its users.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/bluetooth.h |  2 +-
 net/bluetooth/hci_conn.c          |  2 +-
 net/bluetooth/hci_core.c          |  9 ++++----
 net/bluetooth/hci_request.c       |  3 ++-
 net/bluetooth/mgmt.c              | 44 ++++++++++++++++++++++-----------------
 5 files changed, 34 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 58695ffeb13..e00455aab18 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -273,7 +273,7 @@ struct l2cap_ctrl {
 
 struct hci_dev;
 
-typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status);
+typedef void (*hci_req_complete_t)(struct hci_dev *hdev, u8 status, u16 opcode);
 
 struct hci_req_ctrl {
 	bool			start;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 75240aaca10..2e724e0b75b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -633,7 +633,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status)
 	mgmt_reenable_advertising(hdev);
 }
 
-static void create_le_conn_complete(struct hci_dev *hdev, u8 status)
+static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct hci_conn *conn;
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index bc5486ea541..ba0d1fdccbd 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -141,7 +141,7 @@ static const struct file_operations dut_mode_fops = {
 
 /* ---- HCI requests ---- */
 
-static void hci_req_sync_complete(struct hci_dev *hdev, u8 result)
+static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode)
 {
 	BT_DBG("%s result 0x%2.2x", hdev->name, result);
 
@@ -2754,7 +2754,7 @@ void hci_conn_params_clear_all(struct hci_dev *hdev)
 	BT_DBG("All LE connection parameters were removed");
 }
 
-static void inquiry_complete(struct hci_dev *hdev, u8 status)
+static void inquiry_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	if (status) {
 		BT_ERR("Failed to start inquiry: status %d", status);
@@ -2766,7 +2766,8 @@ static void inquiry_complete(struct hci_dev *hdev, u8 status)
 	}
 }
 
-static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status)
+static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status,
+					  u16 opcode)
 {
 	/* General inquiry access code (GIAC) */
 	u8 lap[3] = { 0x33, 0x8b, 0x9e };
@@ -4159,7 +4160,7 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status)
 
 call_complete:
 	if (req_complete)
-		req_complete(hdev, status);
+		req_complete(hdev, status, status ? opcode : HCI_OP_NOP);
 }
 
 static void hci_rx_work(struct work_struct *work)
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 324c6418b17..b59f92c6df0 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -533,7 +533,8 @@ void __hci_update_background_scan(struct hci_request *req)
 	}
 }
 
-static void update_background_scan_complete(struct hci_dev *hdev, u8 status)
+static void update_background_scan_complete(struct hci_dev *hdev, u8 status,
+					    u16 opcode)
 {
 	if (status)
 		BT_DBG("HCI request failed to update background scanning: "
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 6b3f5537e44..e531da80592 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1251,7 +1251,7 @@ static int send_settings_rsp(struct sock *sk, u16 opcode, struct hci_dev *hdev)
 			    sizeof(settings));
 }
 
-static void clean_up_hci_complete(struct hci_dev *hdev, u8 status)
+static void clean_up_hci_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("%s status 0x%02x", hdev->name, status);
 
@@ -1518,7 +1518,8 @@ static u8 mgmt_le_support(struct hci_dev *hdev)
 		return MGMT_STATUS_SUCCESS;
 }
 
-static void set_discoverable_complete(struct hci_dev *hdev, u8 status)
+static void set_discoverable_complete(struct hci_dev *hdev, u8 status,
+				      u16 opcode)
 {
 	struct pending_cmd *cmd;
 	struct mgmt_mode *cp;
@@ -1777,7 +1778,8 @@ static void write_fast_connectable(struct hci_request *req, bool enable)
 		hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type);
 }
 
-static void set_connectable_complete(struct hci_dev *hdev, u8 status)
+static void set_connectable_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode)
 {
 	struct pending_cmd *cmd;
 	struct mgmt_mode *cp;
@@ -2195,7 +2197,7 @@ unlock:
 	return err;
 }
 
-static void le_enable_complete(struct hci_dev *hdev, u8 status)
+static void le_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct cmd_lookup match = { NULL, hdev };
 
@@ -2385,7 +2387,7 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
-static void add_uuid_complete(struct hci_dev *hdev, u8 status)
+static void add_uuid_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("status 0x%02x", status);
 
@@ -2464,7 +2466,7 @@ static bool enable_service_cache(struct hci_dev *hdev)
 	return false;
 }
 
-static void remove_uuid_complete(struct hci_dev *hdev, u8 status)
+static void remove_uuid_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("status 0x%02x", status);
 
@@ -2549,7 +2551,7 @@ unlock:
 	return err;
 }
 
-static void set_class_complete(struct hci_dev *hdev, u8 status)
+static void set_class_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("status 0x%02x", status);
 
@@ -3483,7 +3485,7 @@ static void update_name(struct hci_request *req)
 	hci_req_add(req, HCI_OP_WRITE_LOCAL_NAME, sizeof(cp), &cp);
 }
 
-static void set_name_complete(struct hci_dev *hdev, u8 status)
+static void set_name_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct mgmt_cp_set_local_name *cp;
 	struct pending_cmd *cmd;
@@ -3834,7 +3836,8 @@ static bool trigger_discovery(struct hci_request *req, u8 *status)
 	return true;
 }
 
-static void start_discovery_complete(struct hci_dev *hdev, u8 status)
+static void start_discovery_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode)
 {
 	struct pending_cmd *cmd;
 	unsigned long timeout;
@@ -4063,7 +4066,7 @@ failed:
 	return err;
 }
 
-static void stop_discovery_complete(struct hci_dev *hdev, u8 status)
+static void stop_discovery_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct pending_cmd *cmd;
 
@@ -4289,7 +4292,8 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data,
 	return err;
 }
 
-static void set_advertising_complete(struct hci_dev *hdev, u8 status)
+static void set_advertising_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode)
 {
 	struct cmd_lookup match = { NULL, hdev };
 
@@ -4496,7 +4500,8 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
-static void fast_connectable_complete(struct hci_dev *hdev, u8 status)
+static void fast_connectable_complete(struct hci_dev *hdev, u8 status,
+				      u16 opcode)
 {
 	struct pending_cmd *cmd;
 
@@ -4594,7 +4599,7 @@ unlock:
 	return err;
 }
 
-static void set_bredr_complete(struct hci_dev *hdev, u8 status)
+static void set_bredr_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct pending_cmd *cmd;
 
@@ -5119,7 +5124,8 @@ static int conn_info_cmd_complete(struct pending_cmd *cmd, u8 status)
 	return err;
 }
 
-static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status)
+static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status,
+				       u16 opcode)
 {
 	struct hci_cp_read_rssi *cp;
 	struct pending_cmd *cmd;
@@ -5326,7 +5332,7 @@ complete:
 	return err;
 }
 
-static void get_clock_info_complete(struct hci_dev *hdev, u8 status)
+static void get_clock_info_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct hci_cp_read_clock *hci_cp;
 	struct pending_cmd *cmd;
@@ -5504,7 +5510,7 @@ static void device_added(struct sock *sk, struct hci_dev *hdev,
 	mgmt_event(MGMT_EV_DEVICE_ADDED, hdev, &ev, sizeof(ev), sk);
 }
 
-static void add_device_complete(struct hci_dev *hdev, u8 status)
+static void add_device_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct pending_cmd *cmd;
 
@@ -5627,7 +5633,7 @@ static void device_removed(struct sock *sk, struct hci_dev *hdev,
 	mgmt_event(MGMT_EV_DEVICE_REMOVED, hdev, &ev, sizeof(ev), sk);
 }
 
-static void remove_device_complete(struct hci_dev *hdev, u8 status)
+static void remove_device_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct pending_cmd *cmd;
 
@@ -6205,7 +6211,7 @@ static void restart_le_actions(struct hci_request *req)
 	__hci_update_background_scan(req);
 }
 
-static void powered_complete(struct hci_dev *hdev, u8 status)
+static void powered_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	struct cmd_lookup match = { NULL, hdev };
 
@@ -7316,7 +7322,7 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 	mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL);
 }
 
-static void adv_enable_complete(struct hci_dev *hdev, u8 status)
+static void adv_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	BT_DBG("%s status %u", hdev->name, status);
 }
-- 
cgit v1.2.3-70-g09d2


From cfcefe01265cbaf5ca7209226d043b07bfa8b587 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Thu, 8 Jan 2015 01:52:36 +0000
Subject: ASoC: rsnd: add recovery support for under/over flow error on SRC

L/R channel will be switched if under/over flow error happen on
Renesas R-Car sound device by the HW bugs. Then, HW restart is required
for salvage. This patch add salvage support for SRC.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/rcar_snd.h |   1 +
 sound/soc/sh/rcar/gen.c  |  15 ++++
 sound/soc/sh/rcar/rsnd.h |   8 +++
 sound/soc/sh/rcar/src.c  | 179 ++++++++++++++++++++++++++++++++++++++++++-----
 4 files changed, 184 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/sound/rcar_snd.h b/include/sound/rcar_snd.h
index 83284cae464..4cecd0c175f 100644
--- a/include/sound/rcar_snd.h
+++ b/include/sound/rcar_snd.h
@@ -55,6 +55,7 @@ struct rsnd_ssi_platform_info {
 struct rsnd_src_platform_info {
 	u32 convert_rate; /* sampling rate convert */
 	int dma_id; /* for Gen2 SCU */
+	int irq;
 };
 
 /*
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index 87a6f2d6277..de0685f2aba 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -309,8 +309,13 @@ static int rsnd_gen2_probe(struct platform_device *pdev,
 		RSND_GEN_M_REG(SRC_BUSIF_MODE,	0x0,	0x20),
 		RSND_GEN_M_REG(SRC_ROUTE_MODE0,	0xc,	0x20),
 		RSND_GEN_M_REG(SRC_CTRL,	0x10,	0x20),
+		RSND_GEN_M_REG(SRC_INT_ENABLE0,	0x18,	0x20),
 		RSND_GEN_M_REG(CMD_ROUTE_SLCT,	0x18c,	0x20),
 		RSND_GEN_M_REG(CMD_CTRL,	0x190,	0x20),
+		RSND_GEN_S_REG(SCU_SYS_STATUS0,	0x1c8),
+		RSND_GEN_S_REG(SCU_SYS_INT_EN0,	0x1cc),
+		RSND_GEN_S_REG(SCU_SYS_STATUS1,	0x1d0),
+		RSND_GEN_S_REG(SCU_SYS_INT_EN1,	0x1c4),
 		RSND_GEN_M_REG(SRC_SWRSR,	0x200,	0x40),
 		RSND_GEN_M_REG(SRC_SRCIR,	0x204,	0x40),
 		RSND_GEN_M_REG(SRC_ADINR,	0x214,	0x40),
@@ -403,6 +408,16 @@ static int rsnd_gen1_probe(struct platform_device *pdev,
 		RSND_GEN_M_REG(SRC_IFSVR,	0x220,	0x40),
 		RSND_GEN_M_REG(SRC_SRCCR,	0x224,	0x40),
 		RSND_GEN_M_REG(SRC_MNFSR,	0x228,	0x40),
+		/*
+		 * ADD US
+		 *
+		 * SRC_STATUS
+		 * SRC_INT_EN
+		 * SCU_SYS_STATUS0
+		 * SCU_SYS_STATUS1
+		 * SCU_SYS_INT_EN0
+		 * SCU_SYS_INT_EN1
+		 */
 	};
 	struct rsnd_regmap_field_conf conf_adg[] = {
 		RSND_GEN_S_REG(BRRA,		0x00),
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index 5826c8abf79..c45700380e5 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -44,6 +44,8 @@ enum rsnd_reg {
 	RSND_REG_SRC_IFSCR,
 	RSND_REG_SRC_IFSVR,
 	RSND_REG_SRC_SRCCR,
+	RSND_REG_SCU_SYS_STATUS0,
+	RSND_REG_SCU_SYS_INT_EN0,
 	RSND_REG_CMD_ROUTE_SLCT,
 	RSND_REG_DVC_SWRSR,
 	RSND_REG_DVC_DVUIR,
@@ -94,6 +96,9 @@ enum rsnd_reg {
 	RSND_REG_SHARE23,
 	RSND_REG_SHARE24,
 	RSND_REG_SHARE25,
+	RSND_REG_SHARE26,
+	RSND_REG_SHARE27,
+	RSND_REG_SHARE28,
 
 	RSND_REG_MAX,
 };
@@ -135,6 +140,9 @@ enum rsnd_reg {
 #define RSND_REG_DVC_VRCTR		RSND_REG_SHARE23
 #define RSND_REG_DVC_VRPDR		RSND_REG_SHARE24
 #define RSND_REG_DVC_VRDBR		RSND_REG_SHARE25
+#define RSND_REG_SCU_SYS_STATUS1	RSND_REG_SHARE26
+#define RSND_REG_SCU_SYS_INT_EN1	RSND_REG_SHARE27
+#define RSND_REG_SRC_INT_ENABLE0	RSND_REG_SHARE28
 
 struct rsnd_of_data;
 struct rsnd_priv;
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index eede3ac6eed..648b35e7eff 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -12,10 +12,18 @@
 
 #define SRC_NAME "src"
 
+/* SRCx_STATUS */
+#define OUF_SRCO	((1 << 12) | (1 << 13))
+#define OUF_SRCI	((1 <<  9) | (1 <<  8))
+
+/* SCU_SYSTEM_STATUS0/1 */
+#define OUF_SRC(id)	((1 << (id + 16)) | (1 << id))
+
 struct rsnd_src {
 	struct rsnd_src_platform_info *info; /* rcar_snd.h */
 	struct rsnd_mod mod;
 	struct clk *clk;
+	int err;
 };
 
 #define RSND_SRC_NAME_SIZE 16
@@ -280,6 +288,8 @@ static int rsnd_src_init(struct rsnd_mod *mod,
 
 	clk_prepare_enable(src->clk);
 
+	src->err = 0;
+
 	/*
 	 * Initialize the operation of the SRC internal circuits
 	 * see rsnd_src_start()
@@ -293,9 +303,14 @@ static int rsnd_src_quit(struct rsnd_mod *mod,
 			 struct rsnd_dai *rdai)
 {
 	struct rsnd_src *src = rsnd_mod_to_src(mod);
+	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
+	struct device *dev = rsnd_priv_to_dev(priv);
 
 	clk_disable_unprepare(src->clk);
 
+	if (src->err)
+		dev_warn(dev, "src under/over flow err = %d\n", src->err);
+
 	return 0;
 }
 
@@ -510,6 +525,110 @@ static struct rsnd_mod_ops rsnd_src_gen1_ops = {
 /*
  *		Gen2 functions
  */
+#define rsnd_src_irq_enable_gen2(mod)  rsnd_src_irq_ctrol_gen2(mod, 1)
+#define rsnd_src_irq_disable_gen2(mod) rsnd_src_irq_ctrol_gen2(mod, 0)
+static void rsnd_src_irq_ctrol_gen2(struct rsnd_mod *mod, int enable)
+{
+	struct rsnd_src *src = rsnd_mod_to_src(mod);
+	u32 sys_int_val, int_val, sys_int_mask;
+	int irq = src->info->irq;
+	int id = rsnd_mod_id(mod);
+
+	sys_int_val =
+	sys_int_mask = OUF_SRC(id);
+	int_val = 0x3300;
+
+	/*
+	 * IRQ is not supported on non-DT
+	 * see
+	 *	rsnd_src_probe_gen2()
+	 */
+	if ((irq <= 0) || !enable) {
+		sys_int_val = 0;
+		int_val = 0;
+	}
+
+	rsnd_mod_write(mod, SRC_INT_ENABLE0, int_val);
+	rsnd_mod_bset(mod, SCU_SYS_INT_EN0, sys_int_mask, sys_int_val);
+	rsnd_mod_bset(mod, SCU_SYS_INT_EN1, sys_int_mask, sys_int_val);
+}
+
+static void rsnd_src_error_clear_gen2(struct rsnd_mod *mod)
+{
+	u32 val = OUF_SRC(rsnd_mod_id(mod));
+
+	rsnd_mod_bset(mod, SCU_SYS_STATUS0, val, val);
+	rsnd_mod_bset(mod, SCU_SYS_STATUS1, val, val);
+}
+
+static bool rsnd_src_error_record_gen2(struct rsnd_mod *mod)
+{
+	u32 val = OUF_SRC(rsnd_mod_id(mod));
+	bool ret = false;
+
+	if ((rsnd_mod_read(mod, SCU_SYS_STATUS0) & val) ||
+	    (rsnd_mod_read(mod, SCU_SYS_STATUS1) & val)) {
+		struct rsnd_src *src = rsnd_mod_to_src(mod);
+
+		src->err++;
+		ret = true;
+	}
+
+	/* clear error static */
+	rsnd_src_error_clear_gen2(mod);
+
+	return ret;
+}
+
+static int _rsnd_src_start_gen2(struct rsnd_mod *mod)
+{
+	struct rsnd_dai_stream *io = rsnd_mod_to_io(mod);
+	u32 val = rsnd_io_to_mod_dvc(io) ? 0x01 : 0x11;
+
+	rsnd_mod_write(mod, SRC_CTRL, val);
+
+	rsnd_src_error_clear_gen2(mod);
+
+	rsnd_src_start(mod);
+
+	rsnd_src_irq_enable_gen2(mod);
+
+	return 0;
+}
+
+static int _rsnd_src_stop_gen2(struct rsnd_mod *mod)
+{
+	rsnd_src_irq_disable_gen2(mod);
+
+	rsnd_mod_write(mod, SRC_CTRL, 0);
+
+	rsnd_src_error_record_gen2(mod);
+
+	return rsnd_src_stop(mod);
+}
+
+static irqreturn_t rsnd_src_interrupt_gen2(int irq, void *data)
+{
+	struct rsnd_mod *mod = data;
+	struct rsnd_dai_stream *io = rsnd_mod_to_io(mod);
+
+	if (!io)
+		return IRQ_NONE;
+
+	if (rsnd_src_error_record_gen2(mod)) {
+		struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
+		struct device *dev = rsnd_priv_to_dev(priv);
+
+		_rsnd_src_stop_gen2(mod);
+		_rsnd_src_start_gen2(mod);
+
+		dev_dbg(dev, "%s[%d] restart\n",
+			rsnd_mod_name(mod), rsnd_mod_id(mod));
+	}
+
+	return IRQ_HANDLED;
+}
+
 static int rsnd_src_set_convert_rate_gen2(struct rsnd_mod *mod,
 					  struct rsnd_dai *rdai)
 {
@@ -588,18 +707,38 @@ static int rsnd_src_probe_gen2(struct rsnd_mod *mod,
 	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
 	struct rsnd_src *src = rsnd_mod_to_src(mod);
 	struct device *dev = rsnd_priv_to_dev(priv);
+	int irq = src->info->irq;
 	int ret;
 
+	if (irq > 0) {
+		/*
+		 * IRQ is not supported on non-DT
+		 * see
+		 *	rsnd_src_irq_enable_gen2()
+		 */
+		ret = devm_request_irq(dev, irq,
+				       rsnd_src_interrupt_gen2,
+				       IRQF_SHARED,
+				       dev_name(dev), mod);
+		if (ret)
+			goto rsnd_src_probe_gen2_fail;
+	}
+
 	ret = rsnd_dma_init(priv,
 			    rsnd_mod_to_dma(mod),
 			    rsnd_info_is_playback(priv, src),
 			    src->info->dma_id);
-	if (ret < 0)
-		dev_err(dev, "%s[%d] (Gen2) failed\n",
-			rsnd_mod_name(mod), rsnd_mod_id(mod));
-	else
-		dev_dbg(dev, "%s[%d] (Gen2) is probed\n",
-			rsnd_mod_name(mod), rsnd_mod_id(mod));
+	if (ret)
+		goto rsnd_src_probe_gen2_fail;
+
+	dev_dbg(dev, "%s[%d] (Gen2) is probed\n",
+		rsnd_mod_name(mod), rsnd_mod_id(mod));
+
+	return ret;
+
+rsnd_src_probe_gen2_fail:
+	dev_err(dev, "%s[%d] (Gen2) failed\n",
+		rsnd_mod_name(mod), rsnd_mod_id(mod));
 
 	return ret;
 }
@@ -635,27 +774,21 @@ static int rsnd_src_init_gen2(struct rsnd_mod *mod,
 static int rsnd_src_start_gen2(struct rsnd_mod *mod,
 			       struct rsnd_dai *rdai)
 {
-	struct rsnd_dai_stream *io = rsnd_mod_to_io(mod);
-	struct rsnd_src *src = rsnd_mod_to_src(mod);
-	u32 val = rsnd_io_to_mod_dvc(io) ? 0x01 : 0x11;
-
-	rsnd_dma_start(rsnd_mod_to_dma(&src->mod));
+	rsnd_dma_start(rsnd_mod_to_dma(mod));
 
-	rsnd_mod_write(mod, SRC_CTRL, val);
-
-	return rsnd_src_start(mod);
+	return _rsnd_src_start_gen2(mod);
 }
 
 static int rsnd_src_stop_gen2(struct rsnd_mod *mod,
 			      struct rsnd_dai *rdai)
 {
-	struct rsnd_src *src = rsnd_mod_to_src(mod);
+	int ret;
 
-	rsnd_mod_write(mod, SRC_CTRL, 0);
+	ret = _rsnd_src_stop_gen2(mod);
 
-	rsnd_dma_stop(rsnd_mod_to_dma(&src->mod));
+	rsnd_dma_stop(rsnd_mod_to_dma(mod));
 
-	return rsnd_src_stop(mod);
+	return ret;
 }
 
 static struct rsnd_mod_ops rsnd_src_gen2_ops = {
@@ -681,10 +814,11 @@ static void rsnd_of_parse_src(struct platform_device *pdev,
 			      struct rsnd_priv *priv)
 {
 	struct device_node *src_node;
+	struct device_node *np;
 	struct rcar_snd_info *info = rsnd_priv_to_info(priv);
 	struct rsnd_src_platform_info *src_info;
 	struct device *dev = &pdev->dev;
-	int nr;
+	int nr, i;
 
 	if (!of_data)
 		return;
@@ -708,6 +842,13 @@ static void rsnd_of_parse_src(struct platform_device *pdev,
 	info->src_info		= src_info;
 	info->src_info_nr	= nr;
 
+	i = 0;
+	for_each_child_of_node(src_node, np) {
+		src_info[i].irq = irq_of_parse_and_map(np, 0);
+
+		i++;
+	}
+
 rsnd_of_parse_src_end:
 	of_node_put(src_node);
 }
-- 
cgit v1.2.3-70-g09d2


From cb9627806ce898c436dc74252718e4a757b33bc3 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 12 Jan 2015 09:21:24 -0800
Subject: Bluetooth: Add defintions for HCI Read Stored Link Key command

This patch adds the missing commmand structure and command complete
structure for the HCI Read Store Link Key command.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index d0bca316b43..91cd9d302cd 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -855,6 +855,17 @@ struct hci_cp_set_event_flt {
 #define HCI_CONN_SETUP_AUTO_OFF	0x01
 #define HCI_CONN_SETUP_AUTO_ON	0x02
 
+#define HCI_OP_READ_STORED_LINK_KEY	0x0c0d
+struct hci_cp_read_stored_link_key {
+	bdaddr_t bdaddr;
+	__u8     read_all;
+} __packed;
+struct hci_rp_read_stored_link_key {
+	__u8     status;
+	__u8     max_keys;
+	__u8     num_keys;
+} __packed;
+
 #define HCI_OP_DELETE_STORED_LINK_KEY	0x0c12
 struct hci_cp_delete_stored_link_key {
 	bdaddr_t bdaddr;
-- 
cgit v1.2.3-70-g09d2


From c2f0f979276fc4911cef5da2fc113f0daeda3ebc Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 12 Jan 2015 09:21:25 -0800
Subject: Bluetooth: Handle command complete event for HCI Read Stored Link
 Keys

When the HCI Read Stored Link Keys command completes it gives useful
information of the current stored keys and maximum keys a controller
can actually store. So process this event and store these information
in hci_dev structure.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_event.c        | 22 ++++++++++++++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 89f4e3c8a09..1f21fe48b38 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -205,6 +205,8 @@ struct hci_dev {
 	__u16		lmp_subver;
 	__u16		voice_setting;
 	__u8		num_iac;
+	__u8		stored_max_keys;
+	__u8		stored_num_keys;
 	__u8		io_capability;
 	__s8		inq_tx_power;
 	__u16		page_scan_interval;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0881efd0ad2..b1580daede1 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -214,6 +214,24 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_bdaddr_list_clear(&hdev->le_white_list);
 }
 
+static void hci_cc_read_stored_link_key(struct hci_dev *hdev,
+					struct sk_buff *skb)
+{
+	struct hci_rp_read_stored_link_key *rp = (void *)skb->data;
+	struct hci_cp_read_stored_link_key *sent;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_READ_STORED_LINK_KEY);
+	if (!sent)
+		return;
+
+	if (!rp->status && sent->read_all == 0x01) {
+		hdev->stored_max_keys = rp->max_keys;
+		hdev->stored_num_keys = rp->num_keys;
+	}
+}
+
 static void hci_cc_write_local_name(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 status = *((__u8 *) skb->data);
@@ -2714,6 +2732,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_reset(hdev, skb);
 		break;
 
+	case HCI_OP_READ_STORED_LINK_KEY:
+		hci_cc_read_stored_link_key(hdev, skb);
+		break;
+
 	case HCI_OP_WRITE_LOCAL_NAME:
 		hci_cc_write_local_name(hdev, skb);
 		break;
-- 
cgit v1.2.3-70-g09d2


From 039d4e410c06ed446566105a0a1c6ce9cad6b56b Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 12 Jan 2015 09:21:27 -0800
Subject: Bluetooth: Add missing response structure for HCI Delete Stored Link
 Key

This patch adds this missing structure for processing the result of the
HCI Delete Stored Link Key command.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 91cd9d302cd..8e54f825153 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -871,6 +871,10 @@ struct hci_cp_delete_stored_link_key {
 	bdaddr_t bdaddr;
 	__u8     delete_all;
 } __packed;
+struct hci_rp_delete_stored_link_key {
+	__u8     status;
+	__u8     num_keys;
+} __packed;
 
 #define HCI_MAX_NAME_LENGTH		248
 
-- 
cgit v1.2.3-70-g09d2


From 3bf3947526c1053ddf2523f261395d682718f56c Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Thu, 8 Jan 2015 12:31:18 -0800
Subject: vxlan: Improve support for header flags

This patch cleans up the header flags of VXLAN in anticipation of
defining some new ones:

- Move header related definitions from vxlan.c to vxlan.h
- Change VXLAN_FLAGS to be VXLAN_HF_VNI (only currently defined flag)
- Move check for unknown flags to after we find vxlan_sock, this
  assumes that some flags may be processed based on tunnel
  configuration
- Add a comment about why the stack treating unknown set flags as an
  error instead of ignoring them

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 42 ++++++++++++++++++++++++++++--------------
 include/net/vxlan.h |  7 +++++++
 2 files changed, 35 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 2ab0922af0b..3a18d8ed89c 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -61,12 +61,6 @@
 #define FDB_AGE_DEFAULT 300 /* 5 min */
 #define FDB_AGE_INTERVAL (10 * HZ)	/* rescan interval */
 
-#define VXLAN_N_VID	(1u << 24)
-#define VXLAN_VID_MASK	(VXLAN_N_VID - 1)
-#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
-
-#define VXLAN_FLAGS 0x08000000	/* struct vxlanhdr.vx_flags required value. */
-
 /* UDP port for VXLAN traffic.
  * The IANA assigned port is 4789, but the Linux default is 8472
  * for compatibility with early adopters.
@@ -1095,18 +1089,21 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct vxlan_sock *vs;
 	struct vxlanhdr *vxh;
+	u32 flags, vni;
 
 	/* Need Vxlan and inner Ethernet header to be present */
 	if (!pskb_may_pull(skb, VXLAN_HLEN))
 		goto error;
 
-	/* Return packets with reserved bits set */
 	vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
-	if (vxh->vx_flags != htonl(VXLAN_FLAGS) ||
-	    (vxh->vx_vni & htonl(0xff))) {
-		netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
-			   ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
-		goto error;
+	flags = ntohl(vxh->vx_flags);
+	vni = ntohl(vxh->vx_vni);
+
+	if (flags & VXLAN_HF_VNI) {
+		flags &= ~VXLAN_HF_VNI;
+	} else {
+		/* VNI flag always required to be set */
+		goto bad_flags;
 	}
 
 	if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
@@ -1116,6 +1113,19 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	if (!vs)
 		goto drop;
 
+	if (flags || (vni & 0xff)) {
+		/* If there are any unprocessed flags remaining treat
+		 * this as a malformed packet. This behavior diverges from
+		 * VXLAN RFC (RFC7348) which stipulates that bits in reserved
+		 * in reserved fields are to be ignored. The approach here
+		 * maintains compatbility with previous stack code, and also
+		 * is more robust and provides a little more security in
+		 * adding extensions to VXLAN.
+		 */
+
+		goto bad_flags;
+	}
+
 	vs->rcv(vs, skb, vxh->vx_vni);
 	return 0;
 
@@ -1124,6 +1134,10 @@ drop:
 	kfree_skb(skb);
 	return 0;
 
+bad_flags:
+	netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
+		   ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
+
 error:
 	/* Return non vxlan pkt */
 	return 1;
@@ -1563,7 +1577,7 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	}
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
-	vxh->vx_flags = htonl(VXLAN_FLAGS);
+	vxh->vx_flags = htonl(VXLAN_HF_VNI);
 	vxh->vx_vni = vni;
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
@@ -1607,7 +1621,7 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 		return -ENOMEM;
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
-	vxh->vx_flags = htonl(VXLAN_FLAGS);
+	vxh->vx_flags = htonl(VXLAN_HF_VNI);
 	vxh->vx_vni = vni;
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 903461aa564..a0d80736224 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -17,6 +17,13 @@ struct vxlanhdr {
 	__be32 vx_vni;
 };
 
+/* VXLAN header flags. */
+#define VXLAN_HF_VNI 0x08000000
+
+#define VXLAN_N_VID     (1u << 24)
+#define VXLAN_VID_MASK  (VXLAN_N_VID - 1)
+#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+
 struct vxlan_sock;
 typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, __be32 key);
 
-- 
cgit v1.2.3-70-g09d2


From bdced7ef7838c1c4aebe9f295e44b7f0dcae2109 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sat, 10 Jan 2015 07:31:12 -0800
Subject: bridge: support for multiple vlans and vlan ranges in setlink and
 dellink requests

This patch changes bridge IFLA_AF_SPEC netlink attribute parser to
look for more than one IFLA_BRIDGE_VLAN_INFO attribute. This allows
userspace to pack more than one vlan in the setlink msg.

The dumps were already sending more than one vlan info in the getlink msg.

This patch also adds bridge_vlan_info flags BRIDGE_VLAN_INFO_RANGE_BEGIN and
BRIDGE_VLAN_INFO_RANGE_END to indicate start and end of vlan range

This patch also deletes unused ifla_br_policy.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_bridge.h |   2 +
 net/bridge/br_netlink.c        | 104 +++++++++++++++++++++++++++--------------
 2 files changed, 70 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index b03ee8f62d3..eaaea6208b4 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -125,6 +125,8 @@ enum {
 #define BRIDGE_VLAN_INFO_MASTER	(1<<0)	/* Operate on Bridge device as well */
 #define BRIDGE_VLAN_INFO_PVID	(1<<1)	/* VLAN is PVID, ingress untagged */
 #define BRIDGE_VLAN_INFO_UNTAGGED	(1<<2)	/* VLAN egresses untagged */
+#define BRIDGE_VLAN_INFO_RANGE_BEGIN	(1<<3) /* VLAN is start of vlan range */
+#define BRIDGE_VLAN_INFO_RANGE_END	(1<<4) /* VLAN is end of vlan range */
 
 struct bridge_vlan_info {
 	__u16 flags;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 9f5eb55a4d3..6f616a2df0b 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -218,57 +218,89 @@ out:
 	return err;
 }
 
-static const struct nla_policy ifla_br_policy[IFLA_MAX+1] = {
-	[IFLA_BRIDGE_FLAGS]	= { .type = NLA_U16 },
-	[IFLA_BRIDGE_MODE]	= { .type = NLA_U16 },
-	[IFLA_BRIDGE_VLAN_INFO]	= { .type = NLA_BINARY,
-				    .len = sizeof(struct bridge_vlan_info), },
-};
+static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
+			int cmd, struct bridge_vlan_info *vinfo)
+{
+	int err = 0;
+
+	switch (cmd) {
+	case RTM_SETLINK:
+		if (p) {
+			err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
+			if (err)
+				break;
+
+			if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
+				err = br_vlan_add(p->br, vinfo->vid,
+						  vinfo->flags);
+		} else {
+			err = br_vlan_add(br, vinfo->vid, vinfo->flags);
+		}
+		break;
+
+	case RTM_DELLINK:
+		if (p) {
+			nbp_vlan_delete(p, vinfo->vid);
+			if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
+				br_vlan_delete(p->br, vinfo->vid);
+		} else {
+			br_vlan_delete(br, vinfo->vid);
+		}
+		break;
+	}
+
+	return err;
+}
 
 static int br_afspec(struct net_bridge *br,
 		     struct net_bridge_port *p,
 		     struct nlattr *af_spec,
 		     int cmd)
 {
-	struct nlattr *tb[IFLA_BRIDGE_MAX+1];
+	struct bridge_vlan_info *vinfo_start = NULL;
+	struct bridge_vlan_info *vinfo = NULL;
+	struct nlattr *attr;
 	int err = 0;
+	int rem;
 
-	err = nla_parse_nested(tb, IFLA_BRIDGE_MAX, af_spec, ifla_br_policy);
-	if (err)
-		return err;
+	nla_for_each_nested(attr, af_spec, rem) {
+		if (nla_type(attr) != IFLA_BRIDGE_VLAN_INFO)
+			continue;
+		if (nla_len(attr) != sizeof(struct bridge_vlan_info))
+			return -EINVAL;
+		vinfo = nla_data(attr);
+		if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
+			if (vinfo_start)
+				return -EINVAL;
+			vinfo_start = vinfo;
+			continue;
+		}
+
+		if (vinfo_start) {
+			struct bridge_vlan_info tmp_vinfo;
+			int v;
 
-	if (tb[IFLA_BRIDGE_VLAN_INFO]) {
-		struct bridge_vlan_info *vinfo;
+			if (!(vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END))
+				return -EINVAL;
 
-		vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]);
+			if (vinfo->vid <= vinfo_start->vid)
+				return -EINVAL;
 
-		if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK)
-			return -EINVAL;
+			memcpy(&tmp_vinfo, vinfo_start,
+			       sizeof(struct bridge_vlan_info));
 
-		switch (cmd) {
-		case RTM_SETLINK:
-			if (p) {
-				err = nbp_vlan_add(p, vinfo->vid, vinfo->flags);
+			for (v = vinfo_start->vid; v <= vinfo->vid; v++) {
+				tmp_vinfo.vid = v;
+				err = br_vlan_info(br, p, cmd, &tmp_vinfo);
 				if (err)
 					break;
-
-				if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
-					err = br_vlan_add(p->br, vinfo->vid,
-							  vinfo->flags);
-			} else
-				err = br_vlan_add(br, vinfo->vid, vinfo->flags);
-
-			break;
-
-		case RTM_DELLINK:
-			if (p) {
-				nbp_vlan_delete(p, vinfo->vid);
-				if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER)
-					br_vlan_delete(p->br, vinfo->vid);
-			} else
-				br_vlan_delete(br, vinfo->vid);
-			break;
+			}
+			vinfo_start = NULL;
+		} else {
+			err = br_vlan_info(br, p, cmd, vinfo);
 		}
+		if (err)
+			break;
 	}
 
 	return err;
-- 
cgit v1.2.3-70-g09d2


From 35a27cee321e7c4e7cba3550b2f48c2ca44d8a72 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sat, 10 Jan 2015 07:31:13 -0800
Subject: rtnetlink: new filter RTEXT_FILTER_BRVLAN_COMPRESSED

This filter is same as RTEXT_FILTER_BRVLAN except that it tries
to compress the consecutive vlans into ranges.

This helps on systems with large number of configured vlans.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rtnetlink.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index d81f22d5b39..a1d18593f41 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -636,6 +636,7 @@ struct tcamsg {
 /* New extended info filters for IFLA_EXT_MASK */
 #define RTEXT_FILTER_VF		(1 << 0)
 #define RTEXT_FILTER_BRVLAN	(1 << 1)
+#define RTEXT_FILTER_BRVLAN_COMPRESSED	(1 << 2)
 
 /* End of information exported to user level */
 
-- 
cgit v1.2.3-70-g09d2


From 7b617289b699b5f7e4544bfd2794818cb880b928 Mon Sep 17 00:00:00 2001
From: Qais Yousef <qais.yousef@imgtec.com>
Date: Fri, 19 Dec 2014 11:38:30 +0000
Subject: ALSA: compress_driver.h: include sound/core.h explicitly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the following compilation error:

   include/sound/compress_driver.h: In function ‘snd_compr_drain_notify’:
   include/sound/compress_driver.h:177:2: error: implicit declaration of function ‘snd_BUG_ON’ [-Werror=implicit-function-declaration]
     if (snd_BUG_ON(!stream))

snd_BUG_ON() is defined in sound/core.h but the file is not included explicitly,
so include it.

Signed-off-by: Qais Yousef <qais.yousef@imgtec.com>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/compress_driver.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 396e8f73670..1e2531058b7 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -27,6 +27,7 @@
 
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <sound/core.h>
 #include <sound/compress_offload.h>
 #include <sound/asound.h>
 #include <sound/pcm.h>
-- 
cgit v1.2.3-70-g09d2


From cbf6ab52add20b845f903decc973afbd5463c527 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Mon, 5 Jan 2015 19:29:32 +0800
Subject: kprobes: Pass the original kprobe for preparing optimized kprobe

Pass the original kprobe for preparing an optimized kprobe arch-dep
part, since for some architecture (e.g. ARM32) requires the information
in original kprobe.

Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Signed-off-by: Jon Medhurst <tixy@linaro.org>
---
 arch/x86/kernel/kprobes/opt.c | 3 ++-
 include/linux/kprobes.h       | 3 ++-
 kernel/kprobes.c              | 4 ++--
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 7c523bbf3dc..0dd8d089c31 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -322,7 +322,8 @@ void arch_remove_optimized_kprobe(struct optimized_kprobe *op)
  * Target instructions MUST be relocatable (checked inside)
  * This is called when new aggr(opt)probe is allocated or reused.
  */
-int arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
+int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
+				  struct kprobe *__unused)
 {
 	u8 *buf;
 	int ret;
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 5297f9fa0ef..1ab54754a86 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -308,7 +308,8 @@ struct optimized_kprobe {
 /* Architecture dependent functions for direct jump optimization */
 extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn);
 extern int arch_check_optimized_kprobe(struct optimized_kprobe *op);
-extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op);
+extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
+					 struct kprobe *orig);
 extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op);
 extern void arch_optimize_kprobes(struct list_head *oplist);
 extern void arch_unoptimize_kprobes(struct list_head *oplist,
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 06f58309fed..bad4e959f2f 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -717,7 +717,7 @@ static void prepare_optimized_kprobe(struct kprobe *p)
 	struct optimized_kprobe *op;
 
 	op = container_of(p, struct optimized_kprobe, kp);
-	arch_prepare_optimized_kprobe(op);
+	arch_prepare_optimized_kprobe(op, p);
 }
 
 /* Allocate new optimized_kprobe and try to prepare optimized instructions */
@@ -731,7 +731,7 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 
 	INIT_LIST_HEAD(&op->list);
 	op->kp.addr = p->addr;
-	arch_prepare_optimized_kprobe(op);
+	arch_prepare_optimized_kprobe(op, p);
 
 	return &op->kp;
 }
-- 
cgit v1.2.3-70-g09d2


From 7a868d1e9ab3c534c5ad44e3e5dc46753a1e5636 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Mon, 12 Jan 2015 14:52:22 +0800
Subject: rhashtable: involve rhashtable_lookup_compare_insert routine

Introduce a new function called rhashtable_lookup_compare_insert()
which is very similar to rhashtable_lookup_insert(). But the former
makes use of users' given compare function to look for an object,
and then inserts it into hash table if found. As the entire process
of search and insertion is under protection of per bucket lock, this
can help users to avoid the involvement of extra lock.

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Cc: Thomas Graf <tgraf@suug.ch>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  5 +++++
 lib/rhashtable.c           | 42 ++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 45 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 326acd8c2e9..7b9bd77ed68 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -168,7 +168,12 @@ int rhashtable_shrink(struct rhashtable *ht);
 void *rhashtable_lookup(struct rhashtable *ht, const void *key);
 void *rhashtable_lookup_compare(struct rhashtable *ht, const void *key,
 				bool (*compare)(void *, void *), void *arg);
+
 bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj);
+bool rhashtable_lookup_compare_insert(struct rhashtable *ht,
+				      struct rhash_head *obj,
+				      bool (*compare)(void *, void *),
+				      void *arg);
 
 void rhashtable_destroy(struct rhashtable *ht);
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 8023b554905..ed6ae1ad304 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -726,6 +726,43 @@ EXPORT_SYMBOL_GPL(rhashtable_lookup_compare);
  * to rhashtable_init().
  */
 bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj)
+{
+	struct rhashtable_compare_arg arg = {
+		.ht = ht,
+		.key = rht_obj(ht, obj) + ht->p.key_offset,
+	};
+
+	BUG_ON(!ht->p.key_len);
+
+	return rhashtable_lookup_compare_insert(ht, obj, &rhashtable_compare,
+						&arg);
+}
+EXPORT_SYMBOL_GPL(rhashtable_lookup_insert);
+
+/**
+ * rhashtable_lookup_compare_insert - search and insert object to hash table
+ *                                    with compare function
+ * @ht:		hash table
+ * @obj:	pointer to hash head inside object
+ * @compare:	compare function, must return true on match
+ * @arg:	argument passed on to compare function
+ *
+ * Locks down the bucket chain in both the old and new table if a resize
+ * is in progress to ensure that writers can't remove from the old table
+ * and can't insert to the new table during the atomic operation of search
+ * and insertion. Searches for duplicates in both the old and new table if
+ * a resize is in progress.
+ *
+ * Lookups may occur in parallel with hashtable mutations and resizing.
+ *
+ * Will trigger an automatic deferred table resizing if the size grows
+ * beyond the watermark indicated by grow_decision() which can be passed
+ * to rhashtable_init().
+ */
+bool rhashtable_lookup_compare_insert(struct rhashtable *ht,
+				      struct rhash_head *obj,
+				      bool (*compare)(void *, void *),
+				      void *arg)
 {
 	struct bucket_table *new_tbl, *old_tbl;
 	spinlock_t *new_bucket_lock, *old_bucket_lock;
@@ -747,7 +784,8 @@ bool rhashtable_lookup_insert(struct rhashtable *ht, struct rhash_head *obj)
 	if (unlikely(old_tbl != new_tbl))
 		spin_lock_bh_nested(new_bucket_lock, RHT_LOCK_NESTED);
 
-	if (rhashtable_lookup(ht, rht_obj(ht, obj) + ht->p.key_offset)) {
+	if (rhashtable_lookup_compare(ht, rht_obj(ht, obj) + ht->p.key_offset,
+				      compare, arg)) {
 		success = false;
 		goto exit;
 	}
@@ -763,7 +801,7 @@ exit:
 
 	return success;
 }
-EXPORT_SYMBOL_GPL(rhashtable_lookup_insert);
+EXPORT_SYMBOL_GPL(rhashtable_lookup_compare_insert);
 
 static size_t rounded_hashtable_size(struct rhashtable_params *params)
 {
-- 
cgit v1.2.3-70-g09d2


From 6f73d3b13dc5e16ae06025cd1b12a36b2857caa2 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Mon, 12 Jan 2015 14:52:24 +0800
Subject: rhashtable: add a note for grow and shrink decision functions

As commit c0c09bfdc415 ("rhashtable: avoid unnecessary wakeup for
worker queue") moves condition statements of verifying whether hash
table size exceeds its maximum threshold or reaches its minimum
threshold from resizing functions to resizing decision functions,
we should add a note in rhashtable.h to indicate the implementation
of what the grow and shrink decision function must enforce min/max
shift, otherwise, it's failed to take min/max shift's set watermarks
into effect.

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Cc: Thomas Graf <tgraf@suug.ch>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 7b9bd77ed68..9570832ab07 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -79,6 +79,10 @@ struct rhashtable;
  * @obj_hashfn: Function to hash object
  * @grow_decision: If defined, may return true if table should expand
  * @shrink_decision: If defined, may return true if table should shrink
+ *
+ * Note: when implementing the grow and shrink decision function, min/max
+ * shift must be enforced, otherwise, resizing watermarks they set may be
+ * useless.
  */
 struct rhashtable_params {
 	size_t			nelem_hint;
-- 
cgit v1.2.3-70-g09d2


From d6613aa750ad66b25737231415050f1dca924eb7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 10 Dec 2014 14:54:28 +0100
Subject: ARM: dt: GIC: Spelling s/specific/specifier/, s/flaggs/flags/

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Stephen Warren <swarren@nvidia.com>
Cc: Rob Herring <robh+dt@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 include/dt-bindings/interrupt-controller/arm-gic.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/dt-bindings/interrupt-controller/arm-gic.h b/include/dt-bindings/interrupt-controller/arm-gic.h
index 1ea1b702fec..d4110d5caa3 100644
--- a/include/dt-bindings/interrupt-controller/arm-gic.h
+++ b/include/dt-bindings/interrupt-controller/arm-gic.h
@@ -7,14 +7,14 @@
 
 #include <dt-bindings/interrupt-controller/irq.h>
 
-/* interrupt specific cell 0 */
+/* interrupt specifier cell 0 */
 
 #define GIC_SPI 0
 #define GIC_PPI 1
 
 /*
  * Interrupt specifier cell 2.
- * The flaggs in irq.h are valid, plus those below.
+ * The flags in irq.h are valid, plus those below.
  */
 #define GIC_CPU_MASK_RAW(x) ((x) << 8)
 #define GIC_CPU_MASK_SIMPLE(num) GIC_CPU_MASK_RAW((1 << (num)) - 1)
-- 
cgit v1.2.3-70-g09d2


From c66ad9ca3f4f55886829a61bd24fc5612d0c05c1 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 12 Jan 2015 14:29:34 -0500
Subject: ipv6: directly include libc-compat.h in ipv6.h

Patch 3b50d9029809 ("ipv6: fix redefinition of in6_pktinfo ...")
fixed a libc compatibility issue in ipv6 structure definitions
as described in include/uapi/linux/libc-compat.h.

It relies on including linux/in6.h to include libc-compat.h itself.
Include that file directly to clearly communicate the dependency
(libc-compat.h: "This include must be as early as possible").

Signed-off-by: Willem de Bruijn <willemb@google.com>

----

As discussed in http://patchwork.ozlabs.org/patch/427384/
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ipv6.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index b9b1b7d1c83..73cb02dc306 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -1,6 +1,7 @@
 #ifndef _UAPI_IPV6_H
 #define _UAPI_IPV6_H
 
+#include <linux/libc-compat.h>
 #include <linux/types.h>
 #include <linux/in6.h>
 #include <asm/byteorder.h>
-- 
cgit v1.2.3-70-g09d2


From d8b9605d2697c48fb822c821c5751afbb4567003 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Tue, 13 Jan 2015 17:13:43 +0100
Subject: net: sched: fix skb->protocol use in case of accelerated vlan path

tc code implicitly considers skb->protocol even in case of accelerated
vlan paths and expects vlan protocol type here. However, on rx path,
if the vlan header was already stripped, skb->protocol contains value
of next header. Similar situation is on tx path.

So for skbs that use skb->vlan_tci for tagging, use skb->vlan_proto instead.

Reported-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_sched.h | 12 ++++++++++++
 net/sched/act_csum.c    |  2 +-
 net/sched/cls_flow.c    |  8 ++++----
 net/sched/em_ipset.c    |  2 +-
 net/sched/em_meta.c     |  2 +-
 net/sched/sch_api.c     |  2 +-
 net/sched/sch_dsmark.c  |  6 +++---
 net/sched/sch_teql.c    |  4 ++--
 8 files changed, 25 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 27a33833ff4..fe6e7aac3c5 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -3,6 +3,7 @@
 
 #include <linux/jiffies.h>
 #include <linux/ktime.h>
+#include <linux/if_vlan.h>
 #include <net/sch_generic.h>
 
 struct qdisc_walker {
@@ -114,6 +115,17 @@ int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
 int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		struct tcf_result *res);
 
+static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
+{
+	/* We need to take extra care in case the skb came via
+	 * vlan accelerated path. In that case, use skb->vlan_proto
+	 * as the original vlan header was already stripped.
+	 */
+	if (vlan_tx_tag_present(skb))
+		return skb->vlan_proto;
+	return skb->protocol;
+}
+
 /* Calculate maximal size of packet seen by hard_start_xmit
    routine of this device.
  */
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index edbf40dac70..4cd5cf1aedf 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -509,7 +509,7 @@ static int tcf_csum(struct sk_buff *skb,
 	if (unlikely(action == TC_ACT_SHOT))
 		goto drop;
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case cpu_to_be16(ETH_P_IP):
 		if (!tcf_csum_ipv4(skb, update_flags))
 			goto drop;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 15d68f24a52..461410394d0 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -77,7 +77,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
 	if (flow->dst)
 		return ntohl(flow->dst);
-	return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
+	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
 
 static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
@@ -98,7 +98,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys
 	if (flow->ports)
 		return ntohs(flow->port16[1]);
 
-	return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
+	return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
 }
 
 static u32 flow_get_iif(const struct sk_buff *skb)
@@ -144,7 +144,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 
 static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, src.u3.ip));
 	case htons(ETH_P_IPV6):
@@ -156,7 +156,7 @@ fallback:
 
 static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		return ntohl(CTTUPLE(skb, dst.u3.ip));
 	case htons(ETH_P_IPV6):
diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c
index 5b4a4efe468..a3d79c8bf3b 100644
--- a/net/sched/em_ipset.c
+++ b/net/sched/em_ipset.c
@@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em,
 	struct net_device *dev, *indev = NULL;
 	int ret, network_offset;
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		acpar.family = NFPROTO_IPV4;
 		if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index c8f8c399b99..2159981b604 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -197,7 +197,7 @@ META_COLLECTOR(int_priority)
 META_COLLECTOR(int_protocol)
 {
 	/* Let userspace take care of the byte ordering */
-	dst->value = skb->protocol;
+	dst->value = tc_skb_protocol(skb);
 }
 
 META_COLLECTOR(int_pkttype)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 76f402e05bd..243b7d169d6 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1807,7 +1807,7 @@ done:
 int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp,
 		       struct tcf_result *res)
 {
-	__be16 protocol = skb->protocol;
+	__be16 protocol = tc_skb_protocol(skb);
 	int err;
 
 	for (; tp; tp = rcu_dereference_bh(tp->next)) {
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 227114f27f9..66700a6116a 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -203,7 +203,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p);
 
 	if (p->set_tc_index) {
-		switch (skb->protocol) {
+		switch (tc_skb_protocol(skb)) {
 		case htons(ETH_P_IP):
 			if (skb_cow_head(skb, sizeof(struct iphdr)))
 				goto drop;
@@ -289,7 +289,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 	index = skb->tc_index & (p->indices - 1);
 	pr_debug("index %d->%d\n", skb->tc_index, index);
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
 		ipv4_change_dsfield(ip_hdr(skb), p->mask[index],
 				    p->value[index]);
@@ -306,7 +306,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch)
 		 */
 		if (p->mask[index] != 0xff || p->value[index])
 			pr_warn("%s: unsupported protocol %d\n",
-				__func__, ntohs(skb->protocol));
+				__func__, ntohs(tc_skb_protocol(skb)));
 		break;
 	}
 
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 4899d4a18aa..e02687185a5 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -242,8 +242,8 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
 		char haddr[MAX_ADDR_LEN];
 
 		neigh_ha_snapshot(haddr, n, dev);
-		err = dev_hard_header(skb, dev, ntohs(skb->protocol), haddr,
-				      NULL, skb->len);
+		err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)),
+				      haddr, NULL, skb->len);
 
 		if (err < 0)
 			err = -EINVAL;
-- 
cgit v1.2.3-70-g09d2


From df8a39defad46b83694ea6dd868d332976d62cc0 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Tue, 13 Jan 2015 17:13:44 +0100
Subject: net: rename vlan_tx_* helpers since "tx" is misleading there

The same macros are used for rx as well. So rename it.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/filter.txt                  |  4 ++--
 drivers/infiniband/hw/nes/nes_nic.c                  | 13 +++++++------
 drivers/net/ethernet/3com/typhoon.c                  |  4 ++--
 drivers/net/ethernet/alteon/acenic.c                 |  8 ++++----
 drivers/net/ethernet/amd/amd8111e.c                  |  4 ++--
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c             |  8 ++++----
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c      |  4 ++--
 drivers/net/ethernet/atheros/atl1e/atl1e_main.c      |  4 ++--
 drivers/net/ethernet/atheros/atlx/atl1.c             |  4 ++--
 drivers/net/ethernet/atheros/atlx/atl2.c             |  4 ++--
 drivers/net/ethernet/broadcom/bnx2.c                 |  4 ++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c      |  4 ++--
 drivers/net/ethernet/broadcom/tg3.c                  |  4 ++--
 drivers/net/ethernet/brocade/bna/bnad.c              |  4 ++--
 drivers/net/ethernet/chelsio/cxgb/sge.c              |  4 ++--
 drivers/net/ethernet/chelsio/cxgb3/sge.c             |  6 +++---
 drivers/net/ethernet/chelsio/cxgb4/sge.c             |  4 ++--
 drivers/net/ethernet/chelsio/cxgb4vf/sge.c           |  4 ++--
 drivers/net/ethernet/cisco/enic/enic_main.c          |  4 ++--
 drivers/net/ethernet/emulex/benet/be_main.c          | 12 ++++++------
 drivers/net/ethernet/freescale/gianfar.c             |  4 ++--
 drivers/net/ethernet/ibm/ehea/ehea_main.c            |  4 ++--
 drivers/net/ethernet/intel/e1000/e1000_main.c        |  5 +++--
 drivers/net/ethernet/intel/e1000e/netdev.c           |  9 +++++----
 drivers/net/ethernet/intel/fm10k/fm10k_main.c        |  4 ++--
 drivers/net/ethernet/intel/fm10k/fm10k_netdev.c      |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c          |  4 ++--
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c        |  4 ++--
 drivers/net/ethernet/intel/igb/igb_main.c            |  4 ++--
 drivers/net/ethernet/intel/igbvf/netdev.c            |  5 +++--
 drivers/net/ethernet/intel/ixgb/ixgb_main.c          |  4 ++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c        |  4 ++--
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c    |  4 ++--
 drivers/net/ethernet/jme.c                           |  4 ++--
 drivers/net/ethernet/marvell/sky2.c                  |  6 +++---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c           | 12 ++++++------
 drivers/net/ethernet/natsemi/ns83820.c               |  4 ++--
 drivers/net/ethernet/neterion/s2io.c                 |  4 ++--
 drivers/net/ethernet/neterion/vxge/vxge-main.c       |  4 ++--
 drivers/net/ethernet/nvidia/forcedeth.c              |  4 ++--
 drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c |  4 ++--
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c       |  8 ++++----
 drivers/net/ethernet/qlogic/qlge/qlge_main.c         |  6 +++---
 drivers/net/ethernet/realtek/8139cp.c                |  4 ++--
 drivers/net/ethernet/realtek/r8169.c                 |  4 ++--
 drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c      |  2 +-
 drivers/net/ethernet/tehuti/tehuti.c                 |  4 ++--
 drivers/net/ethernet/via/via-rhine.c                 |  6 +++---
 drivers/net/ethernet/via/via-velocity.c              |  4 ++--
 drivers/net/macvtap.c                                |  6 +++---
 drivers/net/tun.c                                    |  4 ++--
 drivers/net/usb/r8152.c                              |  4 ++--
 drivers/net/vmxnet3/vmxnet3_drv.c                    |  4 ++--
 drivers/net/vxlan.c                                  |  4 ++--
 drivers/s390/net/qeth_l3_main.c                      |  8 ++++----
 drivers/vhost/net.c                                  |  2 +-
 include/linux/if_vlan.h                              | 16 ++++++++--------
 include/net/pkt_sched.h                              |  2 +-
 include/trace/events/net.h                           |  8 ++++----
 net/8021q/vlan_core.c                                |  2 +-
 net/bridge/br_netfilter.c                            | 12 ++++++------
 net/bridge/br_private.h                              |  4 ++--
 net/bridge/br_vlan.c                                 |  4 ++--
 net/bridge/netfilter/ebt_vlan.c                      |  4 ++--
 net/bridge/netfilter/ebtables.c                      |  2 +-
 net/core/dev.c                                       | 10 +++++-----
 net/core/netpoll.c                                   |  2 +-
 net/core/skbuff.c                                    |  8 ++++----
 net/ipv4/geneve.c                                    |  2 +-
 net/openvswitch/actions.c                            |  4 ++--
 net/openvswitch/datapath.c                           |  2 +-
 net/openvswitch/flow.c                               |  4 ++--
 net/openvswitch/vport-gre.c                          |  2 +-
 net/openvswitch/vport.c                              |  3 ++-
 net/packet/af_packet.c                               | 12 ++++++------
 net/sched/em_meta.c                                  |  2 +-
 net/wireless/util.c                                  |  4 ++--
 77 files changed, 195 insertions(+), 190 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 58d08f8d8d8..9930ecfbb46 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -279,8 +279,8 @@ Possible BPF extensions are shown in the following table:
   hatype                                skb->dev->type
   rxhash                                skb->hash
   cpu                                   raw_smp_processor_id()
-  vlan_tci                              vlan_tx_tag_get(skb)
-  vlan_pr                               vlan_tx_tag_present(skb)
+  vlan_tci                              skb_vlan_tag_get(skb)
+  vlan_pr                               skb_vlan_tag_present(skb)
   rand                                  prandom_u32()
 
 These extensions can also be prefixed with '#'.
diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c
index 49eb5111d2c..70acda91eb2 100644
--- a/drivers/infiniband/hw/nes/nes_nic.c
+++ b/drivers/infiniband/hw/nes/nes_nic.c
@@ -373,11 +373,11 @@ static int nes_nic_send(struct sk_buff *skb, struct net_device *netdev)
 	wqe_fragment_length = (__le16 *)&nic_sqe->wqe_words[NES_NIC_SQ_WQE_LENGTH_0_TAG_IDX];
 
 	/* setup the VLAN tag if present */
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		nes_debug(NES_DBG_NIC_TX, "%s: VLAN packet to send... VLAN = %08X\n",
-				netdev->name, vlan_tx_tag_get(skb));
+				netdev->name, skb_vlan_tag_get(skb));
 		wqe_misc = NES_NIC_SQ_WQE_TAGVALUE_ENABLE;
-		wqe_fragment_length[0] = (__force __le16) vlan_tx_tag_get(skb);
+		wqe_fragment_length[0] = (__force __le16) skb_vlan_tag_get(skb);
 	} else
 		wqe_misc = 0;
 
@@ -576,11 +576,12 @@ tso_sq_no_longer_full:
 				wqe_fragment_length =
 						(__le16 *)&nic_sqe->wqe_words[NES_NIC_SQ_WQE_LENGTH_0_TAG_IDX];
 				/* setup the VLAN tag if present */
-				if (vlan_tx_tag_present(skb)) {
+				if (skb_vlan_tag_present(skb)) {
 					nes_debug(NES_DBG_NIC_TX, "%s: VLAN packet to send... VLAN = %08X\n",
-							netdev->name, vlan_tx_tag_get(skb) );
+							netdev->name,
+						  skb_vlan_tag_get(skb));
 					wqe_misc = NES_NIC_SQ_WQE_TAGVALUE_ENABLE;
-					wqe_fragment_length[0] = (__force __le16) vlan_tx_tag_get(skb);
+					wqe_fragment_length[0] = (__force __le16) skb_vlan_tag_get(skb);
 				} else
 					wqe_misc = 0;
 
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index dede43f4ce0..8f8418d2ac4 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -769,11 +769,11 @@ typhoon_start_tx(struct sk_buff *skb, struct net_device *dev)
 		first_txd->processFlags |= TYPHOON_TX_PF_IP_CHKSUM;
 	}
 
-	if(vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		first_txd->processFlags |=
 		    TYPHOON_TX_PF_INSERT_VLAN | TYPHOON_TX_PF_VLAN_PRIORITY;
 		first_txd->processFlags |=
-		    cpu_to_le32(htons(vlan_tx_tag_get(skb)) <<
+		    cpu_to_le32(htons(skb_vlan_tag_get(skb)) <<
 				TYPHOON_TX_PF_VLAN_TAG_SHIFT);
 	}
 
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index b68074803de..b90a26b13fd 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -2429,9 +2429,9 @@ restart:
 		flagsize = (skb->len << 16) | (BD_FLG_END);
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			flagsize |= BD_FLG_TCP_UDP_SUM;
-		if (vlan_tx_tag_present(skb)) {
+		if (skb_vlan_tag_present(skb)) {
 			flagsize |= BD_FLG_VLAN_TAG;
-			vlan_tag = vlan_tx_tag_get(skb);
+			vlan_tag = skb_vlan_tag_get(skb);
 		}
 		desc = ap->tx_ring + idx;
 		idx = (idx + 1) % ACE_TX_RING_ENTRIES(ap);
@@ -2450,9 +2450,9 @@ restart:
 		flagsize = (skb_headlen(skb) << 16);
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			flagsize |= BD_FLG_TCP_UDP_SUM;
-		if (vlan_tx_tag_present(skb)) {
+		if (skb_vlan_tag_present(skb)) {
 			flagsize |= BD_FLG_VLAN_TAG;
-			vlan_tag = vlan_tx_tag_get(skb);
+			vlan_tag = skb_vlan_tag_get(skb);
 		}
 
 		ace_load_tx_bd(ap, ap->tx_ring + idx, mapping, flagsize, vlan_tag);
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 841e6558db6..4c2ae222178 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1299,11 +1299,11 @@ static netdev_tx_t amd8111e_start_xmit(struct sk_buff *skb,
 	lp->tx_ring[tx_index].tx_flags = 0;
 
 #if AMD8111E_VLAN_TAG_USED
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		lp->tx_ring[tx_index].tag_ctrl_cmd |=
 				cpu_to_le16(TCC_VLAN_INSERT);
 		lp->tx_ring[tx_index].tag_ctrl_info =
-				cpu_to_le16(vlan_tx_tag_get(skb));
+				cpu_to_le16(skb_vlan_tag_get(skb));
 
 	}
 #endif
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 7bb5f07dbee..2ba1dd22ad6 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1165,8 +1165,8 @@ static void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata,
 
 static void xgbe_prep_vlan(struct sk_buff *skb, struct xgbe_packet_data *packet)
 {
-	if (vlan_tx_tag_present(skb))
-		packet->vlan_ctag = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb))
+		packet->vlan_ctag = skb_vlan_tag_get(skb);
 }
 
 static int xgbe_prep_tso(struct sk_buff *skb, struct xgbe_packet_data *packet)
@@ -1247,9 +1247,9 @@ static void xgbe_packet_info(struct xgbe_prv_data *pdata,
 		XGMAC_SET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
 			       CSUM_ENABLE, 1);
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		/* VLAN requires an extra descriptor if tag is different */
-		if (vlan_tx_tag_get(skb) != ring->tx.cur_vlan_ctag)
+		if (skb_vlan_tag_get(skb) != ring->tx.cur_vlan_ctag)
 			/* We can share with the TSO context descriptor */
 			if (!context_desc) {
 				context_desc = 1;
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index c9946c6c119..587f63e8758 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2235,8 +2235,8 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
-	if (unlikely(vlan_tx_tag_present(skb))) {
-		u16 vlan = vlan_tx_tag_get(skb);
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		u16 vlan = skb_vlan_tag_get(skb);
 		__le16 tag;
 
 		vlan = cpu_to_le16(vlan);
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index c88abf5b641..59a03a193e8 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1892,8 +1892,8 @@ static netdev_tx_t atl1e_xmit_frame(struct sk_buff *skb,
 
 	tpd = atl1e_get_tpd(adapter);
 
-	if (vlan_tx_tag_present(skb)) {
-		u16 vlan_tag = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		u16 vlan_tag = skb_vlan_tag_get(skb);
 		u16 atl1e_vlan_tag;
 
 		tpd->word3 |= 1 << TPD_INS_VL_TAG_SHIFT;
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 2c8f398aeda..eca1d113fee 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -2415,8 +2415,8 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 		(u16) atomic_read(&tpd_ring->next_to_use));
 	memset(ptpd, 0, sizeof(struct tx_packet_desc));
 
-	if (vlan_tx_tag_present(skb)) {
-		vlan_tag = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		vlan_tag = skb_vlan_tag_get(skb);
 		vlan_tag = (vlan_tag << 4) | (vlan_tag >> 13) |
 			((vlan_tag >> 9) & 0x8);
 		ptpd->word3 |= 1 << TPD_INS_VL_TAG_SHIFT;
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 482a7cabb0a..46a535318c7 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -887,8 +887,8 @@ static netdev_tx_t atl2_xmit_frame(struct sk_buff *skb,
 		offset = ((u32)(skb->len-copy_len + 3) & ~3);
 	}
 #ifdef NETIF_F_HW_VLAN_CTAG_TX
-	if (vlan_tx_tag_present(skb)) {
-		u16 vlan_tag = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		u16 vlan_tag = skb_vlan_tag_get(skb);
 		vlan_tag = (vlan_tag << 4) |
 			(vlan_tag >> 13) |
 			((vlan_tag >> 9) & 0x8);
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 823d01c5684..02bf0b86995 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -6597,9 +6597,9 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		vlan_tag_flags |= TX_BD_FLAGS_TCP_UDP_CKSUM;
 	}
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		vlan_tag_flags |=
-			(TX_BD_FLAGS_VLAN_TAG | (vlan_tx_tag_get(skb) << 16));
+			(TX_BD_FLAGS_VLAN_TAG | (skb_vlan_tag_get(skb) << 16));
 	}
 
 	if ((mss = skb_shinfo(skb)->gso_size)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 1d1147c93d5..b51a18a09d4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3865,9 +3865,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	   "sending pkt %u @%p  next_idx %u  bd %u @%p\n",
 	   pkt_prod, tx_buf, txdata->tx_pkt_prod, bd_prod, tx_start_bd);
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		tx_start_bd->vlan_or_ethertype =
-		    cpu_to_le16(vlan_tx_tag_get(skb));
+		    cpu_to_le16(skb_vlan_tag_get(skb));
 		tx_start_bd->bd_flags.as_bitfield |=
 		    (X_ETH_OUTBAND_VLAN << ETH_TX_BD_FLAGS_VLAN_MODE_SHIFT);
 	} else {
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 356bd5b022a..4cf43bfbc95 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -8002,9 +8002,9 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	    !mss && skb->len > VLAN_ETH_FRAME_LEN)
 		base_flags |= TXD_FLAG_JMB_PKT;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		base_flags |= TXD_FLAG_VLAN;
-		vlan = vlan_tx_tag_get(skb);
+		vlan = skb_vlan_tag_get(skb);
 	}
 
 	if ((unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) &&
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 323721838cf..7714d779008 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -2824,8 +2824,8 @@ bnad_txq_wi_prepare(struct bnad *bnad, struct bna_tcb *tcb,
 	u32 gso_size;
 	u16 vlan_tag = 0;
 
-	if (vlan_tx_tag_present(skb)) {
-		vlan_tag = (u16)vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		vlan_tag = (u16)skb_vlan_tag_get(skb);
 		flags |= (BNA_TXQ_WI_CF_INS_PRIO | BNA_TXQ_WI_CF_INS_VLAN);
 	}
 	if (test_bit(BNAD_RF_CEE_RUNNING, &bnad->run_flags)) {
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index babe2a915b0..526ea74e82d 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1860,9 +1860,9 @@ netdev_tx_t t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 	cpl->iff = dev->if_port;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		cpl->vlan_valid = 1;
-		cpl->vlan = htons(vlan_tx_tag_get(skb));
+		cpl->vlan = htons(skb_vlan_tag_get(skb));
 		st->vlan_insert++;
 	} else
 		cpl->vlan_valid = 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 3dfcf600fcc..d6aa602f168 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -1148,8 +1148,8 @@ static void write_tx_pkt_wr(struct adapter *adap, struct sk_buff *skb,
 	cpl->len = htonl(skb->len);
 	cntrl = V_TXPKT_INTF(pi->port_id);
 
-	if (vlan_tx_tag_present(skb))
-		cntrl |= F_TXPKT_VLAN_VLD | V_TXPKT_VLAN(vlan_tx_tag_get(skb));
+	if (skb_vlan_tag_present(skb))
+		cntrl |= F_TXPKT_VLAN_VLD | V_TXPKT_VLAN(skb_vlan_tag_get(skb));
 
 	tso_info = V_LSO_MSS(skb_shinfo(skb)->gso_size);
 	if (tso_info) {
@@ -1282,7 +1282,7 @@ netdev_tx_t t3_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 		qs->port_stats[SGE_PSTAT_TX_CSUM]++;
 	if (skb_shinfo(skb)->gso_size)
 		qs->port_stats[SGE_PSTAT_TSO]++;
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		qs->port_stats[SGE_PSTAT_VLANINS]++;
 
 	/*
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index ca42e2e9dec..619156112b2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1154,9 +1154,9 @@ out_free:	dev_kfree_skb_any(skb);
 			cntrl = TXPKT_L4CSUM_DIS | TXPKT_IPCSUM_DIS;
 	}
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		q->vlan_ins++;
-		cntrl |= TXPKT_VLAN_VLD | TXPKT_VLAN(vlan_tx_tag_get(skb));
+		cntrl |= TXPKT_VLAN_VLD | TXPKT_VLAN(skb_vlan_tag_get(skb));
 	}
 
 	cpl->ctrl0 = htonl(TXPKT_OPCODE(CPL_TX_PKT_XT) |
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 4424277a7e4..0545f0de1c5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -1326,9 +1326,9 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * If there's a VLAN tag present, add that to the list of things to
 	 * do in this Work Request.
 	 */
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		txq->vlan_ins++;
-		cntrl |= TXPKT_VLAN_VLD | TXPKT_VLAN(vlan_tx_tag_get(skb));
+		cntrl |= TXPKT_VLAN_VLD | TXPKT_VLAN(skb_vlan_tag_get(skb));
 	}
 
 	/*
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 9a952df6606..0535f6fbdc7 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -520,10 +520,10 @@ static inline void enic_queue_wq_skb(struct enic *enic,
 	int loopback = 0;
 	int err;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		/* VLAN tag from trunking driver */
 		vlan_tag_insert = 1;
-		vlan_tag = vlan_tx_tag_get(skb);
+		vlan_tag = skb_vlan_tag_get(skb);
 	} else if (enic->loop_enable) {
 		vlan_tag = enic->loop_tag;
 		loopback = 1;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 37a26b0b7e3..ed46610e545 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -694,7 +694,7 @@ static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
 	u8 vlan_prio;
 	u16 vlan_tag;
 
-	vlan_tag = vlan_tx_tag_get(skb);
+	vlan_tag = skb_vlan_tag_get(skb);
 	vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 	/* If vlan priority provided by OS is NOT in available bmap */
 	if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
@@ -745,7 +745,7 @@ static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
 			SET_TX_WRB_HDR_BITS(udpcs, hdr, 1);
 	}
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		SET_TX_WRB_HDR_BITS(vlan, hdr, 1);
 		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
 		SET_TX_WRB_HDR_BITS(vlan_tag, hdr, vlan_tag);
@@ -864,7 +864,7 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 	if (unlikely(!skb))
 		return skb;
 
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
 
 	if (qnq_async_evt_rcvd(adapter) && adapter->pvid) {
@@ -923,7 +923,7 @@ static bool be_ipv6_exthdr_check(struct sk_buff *skb)
 
 static int be_vlan_tag_tx_chk(struct be_adapter *adapter, struct sk_buff *skb)
 {
-	return vlan_tx_tag_present(skb) || adapter->pvid || adapter->qnq_vid;
+	return skb_vlan_tag_present(skb) || adapter->pvid || adapter->qnq_vid;
 }
 
 static int be_ipv6_tx_stall_chk(struct be_adapter *adapter, struct sk_buff *skb)
@@ -946,7 +946,7 @@ static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
 	eth_hdr_len = ntohs(skb->protocol) == ETH_P_8021Q ?
 						VLAN_ETH_HLEN : ETH_HLEN;
 	if (skb->len <= 60 &&
-	    (lancer_chip(adapter) || vlan_tx_tag_present(skb)) &&
+	    (lancer_chip(adapter) || skb_vlan_tag_present(skb)) &&
 	    is_ipv4_pkt(skb)) {
 		ip = (struct iphdr *)ip_hdr(skb);
 		pskb_trim(skb, eth_hdr_len + ntohs(ip->tot_len));
@@ -964,7 +964,7 @@ static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
 	 * Manually insert VLAN in pkt.
 	 */
 	if (skb->ip_summed != CHECKSUM_PARTIAL &&
-	    vlan_tx_tag_present(skb)) {
+	    skb_vlan_tag_present(skb)) {
 		skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan);
 		if (unlikely(!skb))
 			goto err;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index e54b1e39f9b..93ff846e96f 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2170,7 +2170,7 @@ static inline void gfar_tx_checksum(struct sk_buff *skb, struct txfcb *fcb,
 void inline gfar_tx_vlan(struct sk_buff *skb, struct txfcb *fcb)
 {
 	fcb->flags |= TXFCB_VLN;
-	fcb->vlctl = vlan_tx_tag_get(skb);
+	fcb->vlctl = skb_vlan_tag_get(skb);
 }
 
 static inline struct txbd8 *skip_txbd(struct txbd8 *bdp, int stride,
@@ -2230,7 +2230,7 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	regs = tx_queue->grp->regs;
 
 	do_csum = (CHECKSUM_PARTIAL == skb->ip_summed);
-	do_vlan = vlan_tx_tag_present(skb);
+	do_vlan = skb_vlan_tag_present(skb);
 	do_tstamp = (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 		    priv->hwts_tx_en;
 
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 566b17db135..e8a1adb7a96 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -2064,9 +2064,9 @@ static int ehea_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	memset(swqe, 0, SWQE_HEADER_SIZE);
 	atomic_dec(&pr->swqe_avail);
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		swqe->tx_control |= EHEA_SWQE_VLAN_INSERT;
-		swqe->vlan_tag = vlan_tx_tag_get(skb);
+		swqe->vlan_tag = skb_vlan_tag_get(skb);
 	}
 
 	pr->tx_packets++;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 83140cbb5f0..9242982db3e 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3226,9 +3226,10 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= E1000_TX_FLAGS_VLAN;
-		tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT);
+		tx_flags |= (skb_vlan_tag_get(skb) <<
+			     E1000_TX_FLAGS_VLAN_SHIFT);
 	}
 
 	first = tx_ring->next_to_use;
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 332a298e95b..38cb586b1bf 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5463,8 +5463,8 @@ static int e1000_transfer_dhcp_info(struct e1000_adapter *adapter,
 	struct e1000_hw *hw = &adapter->hw;
 	u16 length, offset;
 
-	if (vlan_tx_tag_present(skb) &&
-	    !((vlan_tx_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) &&
+	if (skb_vlan_tag_present(skb) &&
+	    !((skb_vlan_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) &&
 	      (adapter->hw.mng_cookie.status &
 	       E1000_MNG_DHCP_COOKIE_STATUS_VLAN)))
 		return 0;
@@ -5603,9 +5603,10 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 	if (e1000_maybe_stop_tx(tx_ring, count + 2))
 		return NETDEV_TX_BUSY;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= E1000_TX_FLAGS_VLAN;
-		tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT);
+		tx_flags |= (skb_vlan_tag_get(skb) <<
+			     E1000_TX_FLAGS_VLAN_SHIFT);
 	}
 
 	first = tx_ring->next_to_use;
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index eb088b129bc..caa43f7c293 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -965,8 +965,8 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 	tx_desc = FM10K_TX_DESC(tx_ring, i);
 
 	/* add HW VLAN tag */
-	if (vlan_tx_tag_present(skb))
-		tx_desc->vlan = cpu_to_le16(vlan_tx_tag_get(skb));
+	if (skb_vlan_tag_present(skb))
+		tx_desc->vlan = cpu_to_le16(skb_vlan_tag_get(skb));
 	else
 		tx_desc->vlan = 0;
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
index 8811364b91c..945b35d31c7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c
@@ -609,7 +609,7 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 	int err;
 
 	if ((skb->protocol ==  htons(ETH_P_8021Q)) &&
-	    !vlan_tx_tag_present(skb)) {
+	    !skb_vlan_tag_present(skb)) {
 		/* FM10K only supports hardware tagging, any tags in frame
 		 * are considered 2nd level or "outer" tags
 		 */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 04b441460bb..9f536dd8e1e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1772,8 +1772,8 @@ static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 	u32  tx_flags = 0;
 
 	/* if we have a HW VLAN tag being added, default to the HW one */
-	if (vlan_tx_tag_present(skb)) {
-		tx_flags |= vlan_tx_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
+	if (skb_vlan_tag_present(skb)) {
+		tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= I40E_TX_FLAGS_HW_VLAN;
 	/* else if it is a SW VLAN, check the next protocol and store the tag */
 	} else if (protocol == htons(ETH_P_8021Q)) {
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 04c7c1557a0..82c3798fdd3 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -1122,8 +1122,8 @@ static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb,
 	u32  tx_flags = 0;
 
 	/* if we have a HW VLAN tag being added, default to the HW one */
-	if (vlan_tx_tag_present(skb)) {
-		tx_flags |= vlan_tx_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
+	if (skb_vlan_tag_present(skb)) {
+		tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= I40E_TX_FLAGS_HW_VLAN;
 	/* else if it is a SW VLAN, check the next protocol and store the tag */
 	} else if (protocol == htons(ETH_P_8021Q)) {
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ff59897a946..6c25ec31418 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5035,9 +5035,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 
 	skb_tx_timestamp(skb);
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= IGB_TX_FLAGS_VLAN;
-		tx_flags |= (vlan_tx_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
+		tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
 	}
 
 	/* record initial flags and protocol */
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 63c807c9b21..ad2b4897b39 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2234,9 +2234,10 @@ static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= IGBVF_TX_FLAGS_VLAN;
-		tx_flags |= (vlan_tx_tag_get(skb) << IGBVF_TX_FLAGS_VLAN_SHIFT);
+		tx_flags |= (skb_vlan_tag_get(skb) <<
+			     IGBVF_TX_FLAGS_VLAN_SHIFT);
 	}
 
 	if (skb->protocol == htons(ETH_P_IP))
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index aa87605b144..11a1bdbe3fd 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -1532,9 +1532,9 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
                      DESC_NEEDED)))
 		return NETDEV_TX_BUSY;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= IXGB_TX_FLAGS_VLAN;
-		vlan_id = vlan_tx_tag_get(skb);
+		vlan_id = skb_vlan_tag_get(skb);
 	}
 
 	first = adapter->tx_ring.next_to_use;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2ed2c7de230..7bb421bfd84 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7217,8 +7217,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 	first->gso_segs = 1;
 
 	/* if we have a HW VLAN tag being added default to the HW one */
-	if (vlan_tx_tag_present(skb)) {
-		tx_flags |= vlan_tx_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT;
+	if (skb_vlan_tag_present(skb)) {
+		tx_flags |= skb_vlan_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= IXGBE_TX_FLAGS_HW_VLAN;
 	/* else if it is a SW VLAN check the next protocol and store the tag */
 	} else if (protocol == htons(ETH_P_8021Q)) {
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 62a0d8e0f17..c9b49bfb51b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3452,8 +3452,8 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
 
-	if (vlan_tx_tag_present(skb)) {
-		tx_flags |= vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		tx_flags |= skb_vlan_tag_get(skb);
 		tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= IXGBE_TX_FLAGS_VLAN;
 	}
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 44ce7d88f55..6e9a792097d 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -2154,9 +2154,9 @@ jme_tx_csum(struct jme_adapter *jme, struct sk_buff *skb, u8 *flags)
 static inline void
 jme_tx_vlan(struct sk_buff *skb, __le16 *vlan, u8 *flags)
 {
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		*flags |= TXFLAG_TAGON;
-		*vlan = cpu_to_le16(vlan_tx_tag_get(skb));
+		*vlan = cpu_to_le16(skb_vlan_tag_get(skb));
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 867a6a3ef81..d9f4498832a 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -1895,14 +1895,14 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb,
 	ctrl = 0;
 
 	/* Add VLAN tag, can piggyback on LRGLEN or ADDR64 */
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		if (!le) {
 			le = get_tx_le(sky2, &slot);
 			le->addr = 0;
 			le->opcode = OP_VLAN|HW_OWNER;
 		} else
 			le->opcode |= OP_VLAN;
-		le->length = cpu_to_be16(vlan_tx_tag_get(skb));
+		le->length = cpu_to_be16(skb_vlan_tag_get(skb));
 		ctrl |= INS_VLAN;
 	}
 
@@ -2594,7 +2594,7 @@ static struct sk_buff *sky2_receive(struct net_device *dev,
 	sky2->rx_next = (sky2->rx_next + 1) % sky2->rx_pending;
 	prefetch(sky2->rx_ring + sky2->rx_next);
 
-	if (vlan_tx_tag_present(re->skb))
+	if (skb_vlan_tag_present(re->skb))
 		count -= VLAN_HLEN;	/* Account for vlan tag */
 
 	/* This chip has hardware problems that generates bogus status.
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index e3357bf523d..359bb1286eb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -682,8 +682,8 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (dev->num_tc)
 		return skb_tx_hash(dev, skb);
 
-	if (vlan_tx_tag_present(skb))
-		up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT;
+	if (skb_vlan_tag_present(skb))
+		up = skb_vlan_tag_get(skb) >> VLAN_PRIO_SHIFT;
 
 	return fallback(dev, skb) % rings_p_up + up * rings_p_up;
 }
@@ -742,8 +742,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_drop;
 	}
 
-	if (vlan_tx_tag_present(skb))
-		vlan_tag = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb))
+		vlan_tag = skb_vlan_tag_get(skb);
 
 
 	netdev_txq_bql_enqueue_prefetchw(ring->tx_queue);
@@ -930,7 +930,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	real_size = (real_size / 16) & 0x3f;
 
 	if (ring->bf_enabled && desc_size <= MAX_BF && !bounce &&
-	    !vlan_tx_tag_present(skb) && send_doorbell) {
+	    !skb_vlan_tag_present(skb) && send_doorbell) {
 		tx_desc->ctrl.bf_qpn = ring->doorbell_qpn |
 				       cpu_to_be32(real_size);
 
@@ -952,7 +952,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
 		tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
-			!!vlan_tx_tag_present(skb);
+			!!skb_vlan_tag_present(skb);
 		tx_desc->ctrl.fence_size = real_size;
 
 		/* Ensure new descriptor hits memory
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 2552e550a78..eb807b0dc72 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -1122,12 +1122,12 @@ again:
 	}
 
 #ifdef NS83820_VLAN_ACCEL_SUPPORT
-	if(vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		/* fetch the vlan tag info out of the
 		 * ancillary data if the vlan code
 		 * is using hw vlan acceleration
 		 */
-		short tag = vlan_tx_tag_get(skb);
+		short tag = skb_vlan_tag_get(skb);
 		extsts |= (EXTSTS_VPKT | htons(tag));
 	}
 #endif
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index f5e4b820128..0529cad75b1 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -4045,8 +4045,8 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	queue = 0;
-	if (vlan_tx_tag_present(skb))
-		vlan_tag = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb))
+		vlan_tag = skb_vlan_tag_get(skb);
 	if (sp->config.tx_steering_type == TX_DEFAULT_STEERING) {
 		if (skb->protocol == htons(ETH_P_IP)) {
 			struct iphdr *ip;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index cc0485e3c62..50d5604833e 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -890,8 +890,8 @@ vxge_xmit(struct sk_buff *skb, struct net_device *dev)
 		dev->name, __func__, __LINE__,
 		fifo_hw, dtr, dtr_priv);
 
-	if (vlan_tx_tag_present(skb)) {
-		u16 vlan_tag = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		u16 vlan_tag = skb_vlan_tag_get(skb);
 		vxge_hw_fifo_txdl_vlan_set(dtr, vlan_tag);
 	}
 
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index f39cae620f6..a41bb5e6b95 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -2462,9 +2462,9 @@ static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
 			 NV_TX2_CHECKSUM_L3 | NV_TX2_CHECKSUM_L4 : 0;
 
 	/* vlan tag */
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		start_tx->txvlan = cpu_to_le32(NV_TX3_VLAN_TAG_PRESENT |
-					vlan_tx_tag_get(skb));
+					skb_vlan_tag_get(skb));
 	else
 		start_tx->txvlan = 0;
 
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 613037584d0..a47fe67fdf5 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -1893,9 +1893,9 @@ netxen_tso_check(struct net_device *netdev,
 		protocol = vh->h_vlan_encapsulated_proto;
 		flags = FLAGS_VLAN_TAGGED;
 
-	} else if (vlan_tx_tag_present(skb)) {
+	} else if (skb_vlan_tag_present(skb)) {
 		flags = FLAGS_VLAN_OOB;
-		vid = vlan_tx_tag_get(skb);
+		vid = skb_vlan_tag_get(skb);
 		netxen_set_tx_vlan_tci(first_desc, vid);
 		vlan_oob = 1;
 	}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index d166e534925..4d2496f28b8 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -321,8 +321,8 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
 		if (protocol == ETH_P_8021Q) {
 			vh = (struct vlan_ethhdr *)skb->data;
 			vlan_id = ntohs(vh->h_vlan_TCI);
-		} else if (vlan_tx_tag_present(skb)) {
-			vlan_id = vlan_tx_tag_get(skb);
+		} else if (skb_vlan_tag_present(skb)) {
+			vlan_id = skb_vlan_tag_get(skb);
 		}
 	}
 
@@ -473,9 +473,9 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter,
 		flags = QLCNIC_FLAGS_VLAN_TAGGED;
 		vlan_tci = ntohs(vh->h_vlan_TCI);
 		protocol = ntohs(vh->h_vlan_encapsulated_proto);
-	} else if (vlan_tx_tag_present(skb)) {
+	} else if (skb_vlan_tag_present(skb)) {
 		flags = QLCNIC_FLAGS_VLAN_OOB;
-		vlan_tci = vlan_tx_tag_get(skb);
+		vlan_tci = skb_vlan_tag_get(skb);
 	}
 	if (unlikely(adapter->tx_pvid)) {
 		if (vlan_tci && !(adapter->flags & QLCNIC_TAGGING_ENABLED))
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 6c904a6cad2..dc0058f9037 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2660,11 +2660,11 @@ static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev)
 
 	mac_iocb_ptr->frame_len = cpu_to_le16((u16) skb->len);
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev,
-			     "Adding a vlan tag %d.\n", vlan_tx_tag_get(skb));
+			     "Adding a vlan tag %d.\n", skb_vlan_tag_get(skb));
 		mac_iocb_ptr->flags3 |= OB_MAC_IOCB_V;
-		mac_iocb_ptr->vlan_tci = cpu_to_le16(vlan_tx_tag_get(skb));
+		mac_iocb_ptr->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb));
 	}
 	tso = ql_tso(skb, (struct ob_mac_tso_iocb_req *)mac_iocb_ptr);
 	if (tso < 0) {
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 9c31e46d1ee..d79e33b3c19 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -708,8 +708,8 @@ static void cp_tx (struct cp_private *cp)
 
 static inline u32 cp_tx_vlan_tag(struct sk_buff *skb)
 {
-	return vlan_tx_tag_present(skb) ?
-		TxVlanTag | swab16(vlan_tx_tag_get(skb)) : 0x00;
+	return skb_vlan_tag_present(skb) ?
+		TxVlanTag | swab16(skb_vlan_tag_get(skb)) : 0x00;
 }
 
 static void unwind_tx_frag_mapping(struct cp_private *cp, struct sk_buff *skb,
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3a280598a15..cd286b0356a 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -2073,8 +2073,8 @@ static int rtl8169_set_features(struct net_device *dev,
 
 static inline u32 rtl8169_tx_vlan_tag(struct sk_buff *skb)
 {
-	return (vlan_tx_tag_present(skb)) ?
-		TxVlanTag | swab16(vlan_tx_tag_get(skb)) : 0x00;
+	return (skb_vlan_tag_present(skb)) ?
+		TxVlanTag | swab16(skb_vlan_tag_get(skb)) : 0x00;
 }
 
 static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index b6612d6090a..23545e1e605 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -1272,7 +1272,7 @@ static netdev_tx_t sxgbe_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(skb_is_gso(skb) && tqueue->prev_mss != cur_mss))
 		ctxt_desc_req = 1;
 
-	if (unlikely(vlan_tx_tag_present(skb) ||
+	if (unlikely(skb_vlan_tag_present(skb) ||
 		     ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 		      tqueue->hwts_tx_en)))
 		ctxt_desc_req = 1;
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 6ab36d9ff2a..a9cac8413e4 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1650,9 +1650,9 @@ static netdev_tx_t bdx_tx_transmit(struct sk_buff *skb,
 		    txd_mss);
 	}
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		/*Cut VLAN ID to 12 bits */
-		txd_vlan_id = vlan_tx_tag_get(skb) & BITS_MASK(12);
+		txd_vlan_id = skb_vlan_tag_get(skb) & BITS_MASK(12);
 		txd_vtag = 1;
 	}
 
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index a191afc23b5..0ac76102b33 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -1781,8 +1781,8 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 	rp->tx_ring[entry].desc_length =
 		cpu_to_le32(TXDESC | (skb->len >= ETH_ZLEN ? skb->len : ETH_ZLEN));
 
-	if (unlikely(vlan_tx_tag_present(skb))) {
-		u16 vid_pcp = vlan_tx_tag_get(skb);
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		u16 vid_pcp = skb_vlan_tag_get(skb);
 
 		/* drop CFI/DEI bit, register needs VID and PCP */
 		vid_pcp = (vid_pcp & VLAN_VID_MASK) |
@@ -1803,7 +1803,7 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 
 	/* Non-x86 Todo: explicitly flush cache lines here. */
 
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		/* Tx queues are bits 7-0 (first Tx queue: bit 7) */
 		BYTE_REG_BITS_ON(1 << 7, ioaddr + TQWake);
 
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 282f83a63b6..c20206f83cc 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -2611,8 +2611,8 @@ static netdev_tx_t velocity_xmit(struct sk_buff *skb,
 
 	td_ptr->tdesc1.cmd = TCPLS_NORMAL + (tdinfo->nskb_dma + 1) * 16;
 
-	if (vlan_tx_tag_present(skb)) {
-		td_ptr->tdesc1.vlan = cpu_to_le16(vlan_tx_tag_get(skb));
+	if (skb_vlan_tag_present(skb)) {
+		td_ptr->tdesc1.vlan = cpu_to_le16(skb_vlan_tag_get(skb));
 		td_ptr->tdesc1.TCR |= TCR0_VETAG;
 	}
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 7df221788cd..d0ed5694dd7 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -645,7 +645,7 @@ static void macvtap_skb_to_vnet_hdr(struct macvtap_queue *q,
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
-		if (vlan_tx_tag_present(skb))
+		if (skb_vlan_tag_present(skb))
 			vnet_hdr->csum_start = cpu_to_macvtap16(q,
 				skb_checksum_start_offset(skb) + VLAN_HLEN);
 		else
@@ -821,13 +821,13 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 	total = vnet_hdr_len;
 	total += skb->len;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		struct {
 			__be16 h_vlan_proto;
 			__be16 h_vlan_TCI;
 		} veth;
 		veth.h_vlan_proto = skb->vlan_proto;
-		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
+		veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb));
 
 		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
 		total += VLAN_HLEN;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 74fdf115844..be196e89ab6 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1260,7 +1260,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	int vlan_hlen = 0;
 	int vnet_hdr_sz = 0;
 
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		vlan_hlen = VLAN_HLEN;
 
 	if (tun->flags & IFF_VNET_HDR)
@@ -1337,7 +1337,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		} veth;
 
 		veth.h_vlan_proto = skb->vlan_proto;
-		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
+		veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb));
 
 		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
 
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index b23426e4952..e519e6a269b 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1421,10 +1421,10 @@ static int msdn_giant_send_check(struct sk_buff *skb)
 
 static inline void rtl_tx_vlan_tag(struct tx_desc *desc, struct sk_buff *skb)
 {
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		u32 opts2;
 
-		opts2 = TX_VLAN_TAG | swab16(vlan_tx_tag_get(skb));
+		opts2 = TX_VLAN_TAG | swab16(skb_vlan_tag_get(skb));
 		desc->opts2 |= cpu_to_le32(opts2);
 	}
 }
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 31439818c27..294214c1529 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1038,9 +1038,9 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq,
 		le32_add_cpu(&tq->shared->txNumDeferred, 1);
 	}
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		gdesc->txd.ti = 1;
-		gdesc->txd.tci = vlan_tx_tag_get(skb);
+		gdesc->txd.tci = skb_vlan_tag_get(skb);
 	}
 
 	/* finally flips the GEN bit of the SOP desc. */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 3a18d8ed89c..985359dd603 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1561,7 +1561,7 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 
 	min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
 			+ VXLAN_HLEN + sizeof(struct ipv6hdr)
-			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	/* Need space for new headers (invalidates iph ptr) */
 	err = skb_cow_head(skb, min_headroom);
@@ -1607,7 +1607,7 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ VXLAN_HLEN + sizeof(struct iphdr)
-			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	/* Need space for new headers (invalidates iph ptr) */
 	err = skb_cow_head(skb, min_headroom);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 625227ad16e..dd4ab8d73d3 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2800,12 +2800,12 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 	 * before we're going to overwrite this location with next hop ip.
 	 * v6 uses passthrough, v4 sets the tag in the QDIO header.
 	 */
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		if ((ipv == 4) || (card->info.type == QETH_CARD_TYPE_IQD))
 			hdr->hdr.l3.ext_flags = QETH_HDR_EXT_VLAN_FRAME;
 		else
 			hdr->hdr.l3.ext_flags = QETH_HDR_EXT_INCLUDE_VLAN_TAG;
-		hdr->hdr.l3.vlan_id = vlan_tx_tag_get(skb);
+		hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb);
 	}
 
 	hdr->hdr.l3.length = skb->len - sizeof(struct qeth_hdr);
@@ -2986,7 +2986,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			skb_pull(new_skb, ETH_HLEN);
 		}
 
-		if (ipv != 4 && vlan_tx_tag_present(new_skb)) {
+		if (ipv != 4 && skb_vlan_tag_present(new_skb)) {
 			skb_push(new_skb, VLAN_HLEN);
 			skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4);
 			skb_copy_to_linear_data_offset(new_skb, 4,
@@ -2995,7 +2995,7 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 				new_skb->data + 12, 4);
 			tag = (u16 *)(new_skb->data + 12);
 			*tag = __constant_htons(ETH_P_8021Q);
-			*(tag + 1) = htons(vlan_tx_tag_get(new_skb));
+			*(tag + 1) = htons(skb_vlan_tag_get(new_skb));
 		}
 	}
 
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 14419a8ccbb..bcaf4cabb85 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -469,7 +469,7 @@ static int peek_head_len(struct sock *sk)
 	head = skb_peek(&sk->sk_receive_queue);
 	if (likely(head)) {
 		len = head->len;
-		if (vlan_tx_tag_present(head))
+		if (skb_vlan_tag_present(head))
 			len += VLAN_HLEN;
 	}
 
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 515a35e2a48..bea465f24eb 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -78,9 +78,9 @@ static inline bool is_vlan_dev(struct net_device *dev)
         return dev->priv_flags & IFF_802_1Q_VLAN;
 }
 
-#define vlan_tx_tag_present(__skb)	((__skb)->vlan_tci & VLAN_TAG_PRESENT)
-#define vlan_tx_tag_get(__skb)		((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
-#define vlan_tx_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
+#define skb_vlan_tag_present(__skb)	((__skb)->vlan_tci & VLAN_TAG_PRESENT)
+#define skb_vlan_tag_get(__skb)		((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
+#define skb_vlan_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
 
 /**
  *	struct vlan_pcpu_stats - VLAN percpu rx/tx stats
@@ -376,7 +376,7 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
 static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
 {
 	skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-					vlan_tx_tag_get(skb));
+					skb_vlan_tag_get(skb));
 	if (likely(skb))
 		skb->vlan_tci = 0;
 	return skb;
@@ -393,7 +393,7 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
  */
 static inline struct sk_buff *vlan_hwaccel_push_inside(struct sk_buff *skb)
 {
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		skb = __vlan_hwaccel_push_inside(skb);
 	return skb;
 }
@@ -442,8 +442,8 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
 					 u16 *vlan_tci)
 {
-	if (vlan_tx_tag_present(skb)) {
-		*vlan_tci = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		*vlan_tci = skb_vlan_tag_get(skb);
 		return 0;
 	} else {
 		*vlan_tci = 0;
@@ -480,7 +480,7 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 {
 	__be16 protocol = 0;
 
-	if (vlan_tx_tag_present(skb) ||
+	if (skb_vlan_tag_present(skb) ||
 	     skb->protocol != cpu_to_be16(ETH_P_8021Q))
 		protocol = skb->protocol;
 	else {
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index fe6e7aac3c5..2342bf12cb7 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -121,7 +121,7 @@ static inline __be16 tc_skb_protocol(const struct sk_buff *skb)
 	 * vlan accelerated path. In that case, use skb->vlan_proto
 	 * as the original vlan header was already stripped.
 	 */
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		return skb->vlan_proto;
 	return skb->protocol;
 }
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 1de256b3580..49cc7c3de25 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -40,9 +40,9 @@ TRACE_EVENT(net_dev_start_xmit,
 		__assign_str(name, dev->name);
 		__entry->queue_mapping = skb->queue_mapping;
 		__entry->skbaddr = skb;
-		__entry->vlan_tagged = vlan_tx_tag_present(skb);
+		__entry->vlan_tagged = skb_vlan_tag_present(skb);
 		__entry->vlan_proto = ntohs(skb->vlan_proto);
-		__entry->vlan_tci = vlan_tx_tag_get(skb);
+		__entry->vlan_tci = skb_vlan_tag_get(skb);
 		__entry->protocol = ntohs(skb->protocol);
 		__entry->ip_summed = skb->ip_summed;
 		__entry->len = skb->len;
@@ -174,9 +174,9 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template,
 #endif
 		__entry->queue_mapping = skb->queue_mapping;
 		__entry->skbaddr = skb;
-		__entry->vlan_tagged = vlan_tx_tag_present(skb);
+		__entry->vlan_tagged = skb_vlan_tag_present(skb);
 		__entry->vlan_proto = ntohs(skb->vlan_proto);
-		__entry->vlan_tci = vlan_tx_tag_get(skb);
+		__entry->vlan_tci = skb_vlan_tag_get(skb);
 		__entry->protocol = ntohs(skb->protocol);
 		__entry->ip_summed = skb->ip_summed;
 		__entry->hash = skb->hash;
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 90cc2bdd406..61bf2a06e85 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
 {
 	struct sk_buff *skb = *skbp;
 	__be16 vlan_proto = skb->vlan_proto;
-	u16 vlan_id = vlan_tx_tag_get_id(skb);
+	u16 vlan_id = skb_vlan_tag_get_id(skb);
 	struct net_device *vlan_dev;
 	struct vlan_pcpu_stats *rx_stats;
 
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index c190d22b6b3..65728e0dc4f 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -66,17 +66,17 @@ static int brnf_pass_vlan_indev __read_mostly = 0;
 #endif
 
 #define IS_IP(skb) \
-	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IP))
+	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IP))
 
 #define IS_IPV6(skb) \
-	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6))
+	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_IPV6))
 
 #define IS_ARP(skb) \
-	(!vlan_tx_tag_present(skb) && skb->protocol == htons(ETH_P_ARP))
+	(!skb_vlan_tag_present(skb) && skb->protocol == htons(ETH_P_ARP))
 
 static inline __be16 vlan_proto(const struct sk_buff *skb)
 {
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		return skb->protocol;
 	else if (skb->protocol == htons(ETH_P_8021Q))
 		return vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
@@ -436,11 +436,11 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
 	struct net_device *vlan, *br;
 
 	br = bridge_parent(dev);
-	if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb))
+	if (brnf_pass_vlan_indev == 0 || !skb_vlan_tag_present(skb))
 		return br;
 
 	vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto,
-				    vlan_tx_tag_get(skb) & VLAN_VID_MASK);
+				    skb_vlan_tag_get(skb) & VLAN_VID_MASK);
 
 	return vlan ? vlan : br;
 }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index aea3d1339b3..d808d766334 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -628,8 +628,8 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid)
 {
 	int err = 0;
 
-	if (vlan_tx_tag_present(skb))
-		*vid = vlan_tx_tag_get(skb) & VLAN_VID_MASK;
+	if (skb_vlan_tag_present(skb))
+		*vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK;
 	else {
 		*vid = 0;
 		err = -EINVAL;
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 97b8ddf5736..13013fe8db2 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -187,7 +187,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	 * sent from vlan device on the bridge device, it does not have
 	 * HW accelerated vlan tag.
 	 */
-	if (unlikely(!vlan_tx_tag_present(skb) &&
+	if (unlikely(!skb_vlan_tag_present(skb) &&
 		     skb->protocol == proto)) {
 		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
@@ -200,7 +200,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 			/* Protocol-mismatch, empty out vlan_tci for new tag */
 			skb_push(skb, ETH_HLEN);
 			skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
-							vlan_tx_tag_get(skb));
+							skb_vlan_tag_get(skb));
 			if (unlikely(!skb))
 				return false;
 
diff --git a/net/bridge/netfilter/ebt_vlan.c b/net/bridge/netfilter/ebt_vlan.c
index 8d3f8c7651f..61856888812 100644
--- a/net/bridge/netfilter/ebt_vlan.c
+++ b/net/bridge/netfilter/ebt_vlan.c
@@ -45,8 +45,8 @@ ebt_vlan_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	/* VLAN encapsulated Type/Length field, given from orig frame */
 	__be16 encap;
 
-	if (vlan_tx_tag_present(skb)) {
-		TCI = vlan_tx_tag_get(skb);
+	if (skb_vlan_tag_present(skb)) {
+		TCI = skb_vlan_tag_get(skb);
 		encap = skb->protocol;
 	} else {
 		const struct vlan_hdr *fp;
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index d9a8c05d995..91180a7fc94 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -133,7 +133,7 @@ ebt_basic_match(const struct ebt_entry *e, const struct sk_buff *skb,
 	__be16 ethproto;
 	int verdict, i;
 
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		ethproto = htons(ETH_P_8021Q);
 	else
 		ethproto = h->h_proto;
diff --git a/net/core/dev.c b/net/core/dev.c
index 805456147c3..1e325adc436 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2578,7 +2578,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
 	if (skb->encapsulation)
 		features &= dev->hw_enc_features;
 
-	if (!vlan_tx_tag_present(skb)) {
+	if (!skb_vlan_tag_present(skb)) {
 		if (unlikely(protocol == htons(ETH_P_8021Q) ||
 			     protocol == htons(ETH_P_8021AD))) {
 			struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
@@ -2659,7 +2659,7 @@ out:
 static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
 					  netdev_features_t features)
 {
-	if (vlan_tx_tag_present(skb) &&
+	if (skb_vlan_tag_present(skb) &&
 	    !vlan_hw_offload_capable(features, skb->vlan_proto))
 		skb = __vlan_hwaccel_push_inside(skb);
 	return skb;
@@ -3676,7 +3676,7 @@ ncls:
 	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
 		goto drop;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = NULL;
@@ -3708,8 +3708,8 @@ ncls:
 		}
 	}
 
-	if (unlikely(vlan_tx_tag_present(skb))) {
-		if (vlan_tx_tag_get_id(skb))
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		if (skb_vlan_tag_get_id(skb))
 			skb->pkt_type = PACKET_OTHERHOST;
 		/* Note: we might in the future use prio bits
 		 * and set skb->priority like in vlan_do_receive()
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e0ad5d16c9c..c126a878c47 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -77,7 +77,7 @@ static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	features = netif_skb_features(skb);
 
-	if (vlan_tx_tag_present(skb) &&
+	if (skb_vlan_tag_present(skb) &&
 	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
 		skb = __vlan_hwaccel_push_inside(skb);
 		if (unlikely(!skb)) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5a2a2e887a1..56db472e9b8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4197,7 +4197,7 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 	struct vlan_hdr *vhdr;
 	u16 vlan_tci;
 
-	if (unlikely(vlan_tx_tag_present(skb))) {
+	if (unlikely(skb_vlan_tag_present(skb))) {
 		/* vlan_tci is already set-up so leave this for another time */
 		return skb;
 	}
@@ -4283,7 +4283,7 @@ int skb_vlan_pop(struct sk_buff *skb)
 	__be16 vlan_proto;
 	int err;
 
-	if (likely(vlan_tx_tag_present(skb))) {
+	if (likely(skb_vlan_tag_present(skb))) {
 		skb->vlan_tci = 0;
 	} else {
 		if (unlikely((skb->protocol != htons(ETH_P_8021Q) &&
@@ -4313,7 +4313,7 @@ EXPORT_SYMBOL(skb_vlan_pop);
 
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 {
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		unsigned int offset = skb->data - skb_mac_header(skb);
 		int err;
 
@@ -4323,7 +4323,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 		 */
 		__skb_push(skb, offset);
 		err = __vlan_insert_tag(skb, skb->vlan_proto,
-					vlan_tx_tag_get(skb));
+					skb_vlan_tag_get(skb));
 		if (err)
 			return err;
 		skb->protocol = skb->vlan_proto;
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 5b52046ec7a..23744c7a971 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -119,7 +119,7 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr)
-			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	err = skb_cow_head(skb, min_headroom);
 	if (unlikely(err)) {
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 770064c8371..b4cffe68612 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -212,7 +212,7 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 	int err;
 
 	err = skb_vlan_pop(skb);
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		invalidate_flow_key(key);
 	else
 		key->eth.tci = 0;
@@ -222,7 +222,7 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_vlan *vlan)
 {
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		invalidate_flow_key(key);
 	else
 		key->eth.tci = vlan->vlan_tci;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 4e9a5f035cb..54854e3ecd8 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -419,7 +419,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	if (!dp_ifindex)
 		return -ENODEV;
 
-	if (vlan_tx_tag_present(skb)) {
+	if (skb_vlan_tag_present(skb)) {
 		nskb = skb_clone(skb, GFP_ATOMIC);
 		if (!nskb)
 			return -ENOMEM;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index da2fae0873a..df334fe43d7 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -70,7 +70,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 {
 	struct flow_stats *stats;
 	int node = numa_node_id();
-	int len = skb->len + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
 	stats = rcu_dereference(flow->stats[node]);
 
@@ -472,7 +472,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	 */
 
 	key->eth.tci = 0;
-	if (vlan_tx_tag_present(skb))
+	if (skb_vlan_tag_present(skb))
 		key->eth.tci = htons(skb->vlan_tci);
 	else if (eth->h_proto == htons(ETH_P_8021Q))
 		if (unlikely(parse_vlan(skb, key)))
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index d4168c442db..e9aedb7c710 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -166,7 +166,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ tunnel_hlen + sizeof(struct iphdr)
-			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+			+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
 		int head_delta = SKB_DATA_ALIGN(min_headroom -
 						skb_headroom(skb) +
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 2034c6d9cb5..464739aac0f 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -480,7 +480,8 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
 	stats = this_cpu_ptr(vport->percpu_stats);
 	u64_stats_update_begin(&stats->syncp);
 	stats->rx_packets++;
-	stats->rx_bytes += skb->len + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
+	stats->rx_bytes += skb->len +
+			   (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 	u64_stats_update_end(&stats->syncp);
 
 	OVS_CB(skb)->input_vport = vport;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0f02668dc21..d37075b0d6d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -986,8 +986,8 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
 static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
 			struct tpacket3_hdr *ppd)
 {
-	if (vlan_tx_tag_present(pkc->skb)) {
-		ppd->hv1.tp_vlan_tci = vlan_tx_tag_get(pkc->skb);
+	if (skb_vlan_tag_present(pkc->skb)) {
+		ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
 		ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
 		ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 	} else {
@@ -2000,8 +2000,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		h.h2->tp_net = netoff;
 		h.h2->tp_sec = ts.tv_sec;
 		h.h2->tp_nsec = ts.tv_nsec;
-		if (vlan_tx_tag_present(skb)) {
-			h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+		if (skb_vlan_tag_present(skb)) {
+			h.h2->tp_vlan_tci = skb_vlan_tag_get(skb);
 			h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
 			status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
@@ -3010,8 +3010,8 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 		aux.tp_snaplen = skb->len;
 		aux.tp_mac = 0;
 		aux.tp_net = skb_network_offset(skb);
-		if (vlan_tx_tag_present(skb)) {
-			aux.tp_vlan_tci = vlan_tx_tag_get(skb);
+		if (skb_vlan_tag_present(skb)) {
+			aux.tp_vlan_tci = skb_vlan_tag_get(skb);
 			aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
 			aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
 		} else {
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 2159981b604..b5294ce20cd 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -176,7 +176,7 @@ META_COLLECTOR(int_vlan_tag)
 {
 	unsigned short tag;
 
-	tag = vlan_tx_tag_get(skb);
+	tag = skb_vlan_tag_get(skb);
 	if (!tag && __vlan_get_tag(skb, &tag))
 		*err = -1;
 	else
diff --git a/net/wireless/util.c b/net/wireless/util.c
index d0ac795445b..1d2fcfad06c 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -708,8 +708,8 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
 	if (skb->priority >= 256 && skb->priority <= 263)
 		return skb->priority - 256;
 
-	if (vlan_tx_tag_present(skb)) {
-		vlan_priority = (vlan_tx_tag_get(skb) & VLAN_PRIO_MASK)
+	if (skb_vlan_tag_present(skb)) {
+		vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK)
 			>> VLAN_PRIO_SHIFT;
 		if (vlan_priority > 0)
 			return vlan_priority;
-- 
cgit v1.2.3-70-g09d2


From 28e98c2c20e9d791cf58a624a5a2b1fca63ea47b Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Tue, 13 Jan 2015 17:16:42 +0000
Subject: xen: add page_to_mfn()

pfn_to_mfn(page_to_pfn(p)) is a common use case so add a generic
helper for it.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/xen/page.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/xen/page.h b/include/xen/page.h
index 12765b6f951..c5ed20bb3fe 100644
--- a/include/xen/page.h
+++ b/include/xen/page.h
@@ -3,6 +3,11 @@
 
 #include <asm/xen/page.h>
 
+static inline unsigned long page_to_mfn(struct page *page)
+{
+	return pfn_to_mfn(page_to_pfn(page));
+}
+
 struct xen_memory_region {
 	phys_addr_t start;
 	phys_addr_t size;
-- 
cgit v1.2.3-70-g09d2


From 2c3e861c94a29a30c75f60f2561b4ee70b3fb3a4 Mon Sep 17 00:00:00 2001
From: Arik Nemtsov <arik@wizery.com>
Date: Wed, 7 Jan 2015 16:47:19 +0200
Subject: cfg80211: introduce sync regdom set API for self-managed

A self-managed device will sometimes need to set its regdomain synchronously.
Notably it should be set before usermode has a chance to query it. Expose
a new API to accomplish this which requires the RTNL.

Signed-off-by: Arik Nemtsov <arikx.nemtsov@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 14 ++++++++++++++
 net/wireless/reg.c     | 31 +++++++++++++++++++++++++++++--
 2 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 197735788f1..38abc07503f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3788,6 +3788,20 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2);
 int regulatory_set_wiphy_regd(struct wiphy *wiphy,
 			      struct ieee80211_regdomain *rd);
 
+/**
+ * regulatory_set_wiphy_regd_sync_rtnl - set regdom for self-managed drivers
+ * @wiphy: the wireless device we want to process the regulatory domain on
+ * @rd: the regulatory domain information to use for this wiphy
+ *
+ * This functions requires the RTNL to be held and applies the new regdomain
+ * synchronously to this wiphy. For more details see
+ * regulatory_set_wiphy_regd().
+ *
+ * Return: 0 on success. -EINVAL, -EPERM
+ */
+int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy,
+					struct ieee80211_regdomain *rd);
+
 /**
  * wiphy_apply_custom_regulatory - apply a custom driver regulatory domain
  * @wiphy: the wireless device we want to process the regulatory domain on
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 8d232b90421..f8ed79729eb 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2897,8 +2897,8 @@ int set_regdom(const struct ieee80211_regdomain *rd)
 	return 0;
 }
 
-int regulatory_set_wiphy_regd(struct wiphy *wiphy,
-			      struct ieee80211_regdomain *rd)
+static int __regulatory_set_wiphy_regd(struct wiphy *wiphy,
+				       struct ieee80211_regdomain *rd)
 {
 	const struct ieee80211_regdomain *regd;
 	const struct ieee80211_regdomain *prev_regd;
@@ -2928,12 +2928,39 @@ int regulatory_set_wiphy_regd(struct wiphy *wiphy,
 	spin_unlock(&reg_requests_lock);
 
 	kfree(prev_regd);
+	return 0;
+}
+
+int regulatory_set_wiphy_regd(struct wiphy *wiphy,
+			      struct ieee80211_regdomain *rd)
+{
+	int ret = __regulatory_set_wiphy_regd(wiphy, rd);
+
+	if (ret)
+		return ret;
 
 	schedule_work(&reg_work);
 	return 0;
 }
 EXPORT_SYMBOL(regulatory_set_wiphy_regd);
 
+int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy,
+					struct ieee80211_regdomain *rd)
+{
+	int ret;
+
+	ASSERT_RTNL();
+
+	ret = __regulatory_set_wiphy_regd(wiphy, rd);
+	if (ret)
+		return ret;
+
+	/* process the request immediately */
+	reg_process_self_managed_hints();
+	return 0;
+}
+EXPORT_SYMBOL(regulatory_set_wiphy_regd_sync_rtnl);
+
 void wiphy_regulatory_register(struct wiphy *wiphy)
 {
 	struct regulatory_request *lr;
-- 
cgit v1.2.3-70-g09d2


From 75453ccb61120885d6715a49496c57930dbe6253 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Fri, 9 Jan 2015 14:06:37 +0200
Subject: nl80211: send netdetect configuration info in NL80211_CMD_GET_WOWLAN

Send the netdetect configuration information in the response to
NL8021_CMD_GET_WOWLAN commands.  This includes the scan interval,
SSIDs to match and frequencies to scan.

Additionally, add the NL80211_WOWLAN_TRIG_NET_DETECT with
NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  4 +++-
 net/wireless/nl80211.c       | 52 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index a963d4824c5..b6c1a00bd8d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3734,7 +3734,9 @@ struct nl80211_pattern_support {
  *	same attributes used with @NL80211_CMD_START_SCHED_SCAN.  It
  *	specifies how the scan is performed (e.g. the interval and the
  *	channels to scan) as well as the scan results that will
- *	trigger a wake (i.e. the matchsets).
+ *	trigger a wake (i.e. the matchsets).  This attribute is also
+ *	sent in a response to @NL80211_CMD_GET_WIPHY, indicating the
+ *	number of match sets supported by the driver (u32).
  * @NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS: nested attribute
  *	containing an array with information about what triggered the
  *	wake up.  If no elements are present in the array, it means
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7c2ce26e22d..380784378df 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1088,6 +1088,11 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 			return -ENOBUFS;
 	}
 
+	if ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_NET_DETECT) &&
+	    nla_put_u32(msg, NL80211_WOWLAN_TRIG_NET_DETECT,
+			rdev->wiphy.wowlan->max_nd_match_sets))
+		return -ENOBUFS;
+
 	if (large && nl80211_send_wowlan_tcp_caps(rdev, msg))
 		return -ENOBUFS;
 
@@ -8747,6 +8752,48 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg,
 	return 0;
 }
 
+static int nl80211_send_wowlan_nd(struct sk_buff *msg,
+				  struct cfg80211_sched_scan_request *req)
+{
+	struct nlattr *nd, *freqs, *matches, *match;
+	int i;
+
+	if (!req)
+		return 0;
+
+	nd = nla_nest_start(msg, NL80211_WOWLAN_TRIG_NET_DETECT);
+	if (!nd)
+		return -ENOBUFS;
+
+	if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, req->interval))
+		return -ENOBUFS;
+
+	freqs = nla_nest_start(msg, NL80211_ATTR_SCAN_FREQUENCIES);
+	if (!freqs)
+		return -ENOBUFS;
+
+	for (i = 0; i < req->n_channels; i++)
+		nla_put_u32(msg, i, req->channels[i]->center_freq);
+
+	nla_nest_end(msg, freqs);
+
+	if (req->n_match_sets) {
+		matches = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_MATCH);
+		for (i = 0; i < req->n_match_sets; i++) {
+			match = nla_nest_start(msg, i);
+			nla_put(msg, NL80211_SCHED_SCAN_MATCH_ATTR_SSID,
+				req->match_sets[i].ssid.ssid_len,
+				req->match_sets[i].ssid.ssid);
+			nla_nest_end(msg, match);
+		}
+		nla_nest_end(msg, matches);
+	}
+
+	nla_nest_end(msg, nd);
+
+	return 0;
+}
+
 static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
@@ -8804,6 +8851,11 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info)
 					    rdev->wiphy.wowlan_config->tcp))
 			goto nla_put_failure;
 
+		if (nl80211_send_wowlan_nd(
+			    msg,
+			    rdev->wiphy.wowlan_config->nd_config))
+			goto nla_put_failure;
+
 		nla_nest_end(msg, nl_wowlan);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From f684e4ac9f4bae4e6ecff92eef9645a44764fc04 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 12 Jan 2015 00:45:55 +0100
Subject: pinctrl: pinconf-generic: loose DT dependence

New pin controllers such as ACPI-based may also have custom properties
to parse, and should be able to use generic pin config. Let's make the
code compile on !OF systems and rename members a bit to underscore it
is custom parameters and not necessarily DT parameters.

This fixes a build regression for x86_64 on the zeroday kernel builds.

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Reviewed-and-tested-by: Soren Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinconf-generic.c        | 39 ++++++++++++++++++--------------
 drivers/pinctrl/pinctrl-zynq.c           |  8 +++----
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c |  8 +++----
 include/linux/pinctrl/pinconf-generic.h  |  2 +-
 include/linux/pinctrl/pinctrl.h          | 17 ++++++++------
 5 files changed, 41 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c
index e0886665b70..4db92f64b4d 100644
--- a/drivers/pinctrl/pinconf-generic.c
+++ b/drivers/pinctrl/pinconf-generic.c
@@ -113,10 +113,11 @@ void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev, struct seq_file *s,
 	pinconf_generic_dump_one(pctldev, s, gname, pin, conf_items,
 				 ARRAY_SIZE(conf_items));
 	/* driver-specific parameters */
-	if (pctldev->desc->num_dt_params && pctldev->desc->conf_items)
+	if (pctldev->desc->num_custom_params &&
+	    pctldev->desc->custom_conf_items)
 		pinconf_generic_dump_one(pctldev, s, gname, pin,
-					 pctldev->desc->conf_items,
-					 pctldev->desc->num_dt_params);
+					 pctldev->desc->custom_conf_items,
+					 pctldev->desc->num_custom_params);
 }
 
 void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
@@ -131,21 +132,24 @@ void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
 			   pinconf_to_config_argument(config));
 	}
 
-	if (!pctldev->desc->num_dt_params || !pctldev->desc->conf_items)
+	if (!pctldev->desc->num_custom_params ||
+	    !pctldev->desc->custom_conf_items)
 		return;
 
-	for (i = 0; i < pctldev->desc->num_dt_params; i++) {
-		if (pinconf_to_config_param(config) != pctldev->desc->conf_items[i].param)
+	for (i = 0; i < pctldev->desc->num_custom_params; i++) {
+		if (pinconf_to_config_param(config) !=
+		    pctldev->desc->custom_conf_items[i].param)
 			continue;
-		seq_printf(s, "%s: 0x%x", pctldev->desc->conf_items[i].display,
-			   pinconf_to_config_argument(config));
+		seq_printf(s, "%s: 0x%x",
+				pctldev->desc->custom_conf_items[i].display,
+				pinconf_to_config_argument(config));
 	}
 }
 EXPORT_SYMBOL_GPL(pinconf_generic_dump_config);
 #endif
 
 #ifdef CONFIG_OF
-static const struct pinconf_generic_dt_params dt_params[] = {
+static const struct pinconf_generic_params dt_params[] = {
 	{ "bias-disable", PIN_CONFIG_BIAS_DISABLE, 0 },
 	{ "bias-high-impedance", PIN_CONFIG_BIAS_HIGH_IMPEDANCE, 0 },
 	{ "bias-bus-hold", PIN_CONFIG_BIAS_BUS_HOLD, 0 },
@@ -170,9 +174,9 @@ static const struct pinconf_generic_dt_params dt_params[] = {
 };
 
 /**
- * parse_dt_cfg - Parse DT pinconf parameters
+ * parse_dt_cfg() - Parse DT pinconf parameters
  * @np:	DT node
- * @params:	Array of describing DT parameters
+ * @params:	Array of describing generic parameters
  * @count:	Number of entries in @params
  * @cfg:	Array of parsed config options
  * @ncfg:	Number of entries in @cfg
@@ -183,7 +187,7 @@ static const struct pinconf_generic_dt_params dt_params[] = {
  * needs to have enough memory allocated to hold all possible entries.
  */
 static void parse_dt_cfg(struct device_node *np,
-			 const struct pinconf_generic_dt_params *params,
+			 const struct pinconf_generic_params *params,
 			 unsigned int count, unsigned long *cfg,
 			 unsigned int *ncfg)
 {
@@ -192,7 +196,7 @@ static void parse_dt_cfg(struct device_node *np,
 	for (i = 0; i < count; i++) {
 		u32 val;
 		int ret;
-		const struct pinconf_generic_dt_params *par = &params[i];
+		const struct pinconf_generic_params *par = &params[i];
 
 		ret = of_property_read_u32(np, par->property, &val);
 
@@ -232,15 +236,16 @@ int pinconf_generic_parse_dt_config(struct device_node *np,
 	/* allocate a temporary array big enough to hold one of each option */
 	max_cfg = ARRAY_SIZE(dt_params);
 	if (pctldev)
-		max_cfg += pctldev->desc->num_dt_params;
+		max_cfg += pctldev->desc->num_custom_params;
 	cfg = kcalloc(max_cfg, sizeof(*cfg), GFP_KERNEL);
 	if (!cfg)
 		return -ENOMEM;
 
 	parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg);
-	if (pctldev && pctldev->desc->num_dt_params && pctldev->desc->params)
-		parse_dt_cfg(np, pctldev->desc->params,
-			      pctldev->desc->num_dt_params, cfg, &ncfg);
+	if (pctldev && pctldev->desc->num_custom_params &&
+		pctldev->desc->custom_params)
+		parse_dt_cfg(np, pctldev->desc->custom_params,
+			     pctldev->desc->num_custom_params, cfg, &ncfg);
 
 	ret = 0;
 
diff --git a/drivers/pinctrl/pinctrl-zynq.c b/drivers/pinctrl/pinctrl-zynq.c
index 62534234da7..8aa05e2eb70 100644
--- a/drivers/pinctrl/pinctrl-zynq.c
+++ b/drivers/pinctrl/pinctrl-zynq.c
@@ -920,7 +920,7 @@ enum zynq_pin_config_param {
 	PIN_CONFIG_IOSTANDARD = PIN_CONFIG_END + 1,
 };
 
-static const struct pinconf_generic_dt_params zynq_dt_params[] = {
+static const struct pinconf_generic_params zynq_dt_params[] = {
 	{"io-standard", PIN_CONFIG_IOSTANDARD, zynq_iostd_lvcmos18},
 };
 
@@ -1099,9 +1099,9 @@ static struct pinctrl_desc zynq_desc = {
 	.pctlops = &zynq_pctrl_ops,
 	.pmxops = &zynq_pinmux_ops,
 	.confops = &zynq_pinconf_ops,
-	.num_dt_params = ARRAY_SIZE(zynq_dt_params),
-	.params = zynq_dt_params,
-	.conf_items = zynq_conf_items,
+	.num_custom_params = ARRAY_SIZE(zynq_dt_params),
+	.custom_params = zynq_dt_params,
+	.custom_conf_items = zynq_conf_items,
 	.owner = THIS_MODULE,
 };
 
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index 17f811c9c2c..bbf99a715b6 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -131,7 +131,7 @@ struct pmic_gpio_state {
 	struct gpio_chip chip;
 };
 
-static const struct pinconf_generic_dt_params pmic_gpio_bindings[] = {
+static const struct pinconf_generic_params pmic_gpio_bindings[] = {
 	{"qcom,pull-up-strength",	PMIC_GPIO_CONF_PULL_UP,		0},
 	{"qcom,drive-strength",		PMIC_GPIO_CONF_STRENGTH,	0},
 };
@@ -742,9 +742,9 @@ static int pmic_gpio_probe(struct platform_device *pdev)
 	pctrldesc->name = dev_name(dev);
 	pctrldesc->pins = pindesc;
 	pctrldesc->npins = npins;
-	pctrldesc->num_dt_params = ARRAY_SIZE(pmic_gpio_bindings);
-	pctrldesc->params = pmic_gpio_bindings;
-	pctrldesc->conf_items = pmic_conf_items;
+	pctrldesc->num_custom_params = ARRAY_SIZE(pmic_gpio_bindings);
+	pctrldesc->custom_params = pmic_gpio_bindings;
+	pctrldesc->custom_conf_items = pmic_conf_items;
 
 	for (i = 0; i < npins; i++, pindesc++) {
 		pad = &pads[i];
diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h
index 342409f7f3e..fe65962b264 100644
--- a/include/linux/pinctrl/pinconf-generic.h
+++ b/include/linux/pinctrl/pinconf-generic.h
@@ -162,7 +162,7 @@ static inline unsigned long pinconf_to_config_packed(enum pin_config_param param
 struct pinctrl_dev;
 struct pinctrl_map;
 
-struct pinconf_generic_dt_params {
+struct pinconf_generic_params {
 	const char * const property;
 	enum pin_config_param param;
 	u32 default_value;
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index c58b3e11ba8..66e4697516d 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -118,9 +118,12 @@ struct pinctrl_ops {
  * @confops: pin config operations vtable, if you support pin configuration in
  *	your driver
  * @owner: module providing the pin controller, used for refcounting
- * @num_dt_params: Number of driver-specific DT parameters
- * @params: List of DT parameters
- * @conf_items: Information how to print @params in debugfs
+ * @num_custom_params: Number of driver-specific custom parameters to be parsed
+ *	from the hardware description
+ * @custom_params: List of driver_specific custom parameters to be parsed from
+ *	the hardware description
+ * @custom_conf_items: Information how to print @params in debugfs, must be
+ *	the same size as the @custom_params, i.e. @num_custom_params
  */
 struct pinctrl_desc {
 	const char *name;
@@ -130,10 +133,10 @@ struct pinctrl_desc {
 	const struct pinmux_ops *pmxops;
 	const struct pinconf_ops *confops;
 	struct module *owner;
-#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF)
-	unsigned int num_dt_params;
-	const struct pinconf_generic_dt_params *params;
-	const struct pin_config_item *conf_items;
+#ifdef CONFIG_GENERIC_PINCONF
+	unsigned int num_custom_params;
+	const struct pinconf_generic_params *custom_params;
+	const struct pin_config_item *custom_conf_items;
 #endif
 };
 
-- 
cgit v1.2.3-70-g09d2


From 5a7d2efdd93f6c4bb6cd3d5df3d2f5611c9b87ac Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Tue, 16 Dec 2014 10:59:17 +0100
Subject: pinctrl: consumer: use correct retval for placeholder functions

These functions are supposed to return an error pointer, not NULL.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/pinctrl/consumer.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h
index 18eccefea06..72c0415d6c2 100644
--- a/include/linux/pinctrl/consumer.h
+++ b/include/linux/pinctrl/consumer.h
@@ -82,7 +82,7 @@ static inline int pinctrl_gpio_direction_output(unsigned gpio)
 
 static inline struct pinctrl * __must_check pinctrl_get(struct device *dev)
 {
-	return NULL;
+	return ERR_PTR(-ENOSYS);
 }
 
 static inline void pinctrl_put(struct pinctrl *p)
@@ -93,7 +93,7 @@ static inline struct pinctrl_state * __must_check pinctrl_lookup_state(
 							struct pinctrl *p,
 							const char *name)
 {
-	return NULL;
+	return ERR_PTR(-ENOSYS);
 }
 
 static inline int pinctrl_select_state(struct pinctrl *p,
@@ -104,7 +104,7 @@ static inline int pinctrl_select_state(struct pinctrl *p,
 
 static inline struct pinctrl * __must_check devm_pinctrl_get(struct device *dev)
 {
-	return NULL;
+	return ERR_PTR(-ENOSYS);
 }
 
 static inline void devm_pinctrl_put(struct pinctrl *p)
-- 
cgit v1.2.3-70-g09d2


From d84b6728c54dcf73bcef3e3f7cf6767e2d224e39 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Tue, 6 Jan 2015 11:45:07 -0800
Subject: locking/mcs: Better differentiate between MCS variants

We have two flavors of the MCS spinlock: standard and cancelable (OSQ).
While each one is independent of the other, we currently mix and match
them. This patch:

  - Moves the OSQ code out of mcs_spinlock.h (which only deals with the traditional
    version) into include/linux/osq_lock.h. No unnecessary code is added to the
    more global header file, anything locks that make use of OSQ must include
    it anyway.

  - Renames mcs_spinlock.c to osq_lock.c. This file only contains osq code.

  - Introduces a CONFIG_LOCK_SPIN_ON_OWNER in order to only build osq_lock
    if there is support for it.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Link: http://lkml.kernel.org/r/1420573509-24774-5-git-send-email-dave@stgolabs.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/osq_lock.h      |  12 ++-
 kernel/Kconfig.locks          |   4 +
 kernel/locking/Makefile       |   3 +-
 kernel/locking/mcs_spinlock.c | 208 ------------------------------------------
 kernel/locking/mcs_spinlock.h |  16 ----
 kernel/locking/osq_lock.c     | 203 +++++++++++++++++++++++++++++++++++++++++
 6 files changed, 219 insertions(+), 227 deletions(-)
 delete mode 100644 kernel/locking/mcs_spinlock.c
 create mode 100644 kernel/locking/osq_lock.c

(limited to 'include')

diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 90230d5811c..3a6490e81b2 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -5,8 +5,11 @@
  * An MCS like lock especially tailored for optimistic spinning for sleeping
  * lock implementations (mutex, rwsem, etc).
  */
-
-#define OSQ_UNLOCKED_VAL (0)
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
+	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # + 1 value */
+};
 
 struct optimistic_spin_queue {
 	/*
@@ -16,6 +19,8 @@ struct optimistic_spin_queue {
 	atomic_t tail;
 };
 
+#define OSQ_UNLOCKED_VAL (0)
+
 /* Init macro and function. */
 #define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) }
 
@@ -24,4 +29,7 @@ static inline void osq_lock_init(struct optimistic_spin_queue *lock)
 	atomic_set(&lock->tail, OSQ_UNLOCKED_VAL);
 }
 
+extern bool osq_lock(struct optimistic_spin_queue *lock);
+extern void osq_unlock(struct optimistic_spin_queue *lock);
+
 #endif
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 76768ee812b..08561f1acd1 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -231,6 +231,10 @@ config RWSEM_SPIN_ON_OWNER
        def_bool y
        depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
 
+config LOCK_SPIN_ON_OWNER
+       def_bool y
+       depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER
+
 config ARCH_USE_QUEUE_RWLOCK
 	bool
 
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 8541bfdfd23..4ca8eb15197 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,5 +1,5 @@
 
-obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o
+obj-y += mutex.o semaphore.o rwsem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = -pg
@@ -14,6 +14,7 @@ ifeq ($(CONFIG_PROC_FS),y)
 obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
 endif
 obj-$(CONFIG_SMP) += spinlock.o
+obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
 obj-$(CONFIG_SMP) += lglock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
deleted file mode 100644
index 9887a905a76..00000000000
--- a/kernel/locking/mcs_spinlock.c
+++ /dev/null
@@ -1,208 +0,0 @@
-#include <linux/percpu.h>
-#include <linux/sched.h>
-#include "mcs_spinlock.h"
-
-#ifdef CONFIG_SMP
-
-/*
- * An MCS like lock especially tailored for optimistic spinning for sleeping
- * lock implementations (mutex, rwsem, etc).
- *
- * Using a single mcs node per CPU is safe because sleeping locks should not be
- * called from interrupt context and we have preemption disabled while
- * spinning.
- */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
-
-/*
- * We use the value 0 to represent "no CPU", thus the encoded value
- * will be the CPU number incremented by 1.
- */
-static inline int encode_cpu(int cpu_nr)
-{
-	return cpu_nr + 1;
-}
-
-static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
-{
-	int cpu_nr = encoded_cpu_val - 1;
-
-	return per_cpu_ptr(&osq_node, cpu_nr);
-}
-
-/*
- * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
- * Can return NULL in case we were the last queued and we updated @lock instead.
- */
-static inline struct optimistic_spin_node *
-osq_wait_next(struct optimistic_spin_queue *lock,
-	      struct optimistic_spin_node *node,
-	      struct optimistic_spin_node *prev)
-{
-	struct optimistic_spin_node *next = NULL;
-	int curr = encode_cpu(smp_processor_id());
-	int old;
-
-	/*
-	 * If there is a prev node in queue, then the 'old' value will be
-	 * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
-	 * we're currently last in queue, then the queue will then become empty.
-	 */
-	old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
-
-	for (;;) {
-		if (atomic_read(&lock->tail) == curr &&
-		    atomic_cmpxchg(&lock->tail, curr, old) == curr) {
-			/*
-			 * We were the last queued, we moved @lock back. @prev
-			 * will now observe @lock and will complete its
-			 * unlock()/unqueue().
-			 */
-			break;
-		}
-
-		/*
-		 * We must xchg() the @node->next value, because if we were to
-		 * leave it in, a concurrent unlock()/unqueue() from
-		 * @node->next might complete Step-A and think its @prev is
-		 * still valid.
-		 *
-		 * If the concurrent unlock()/unqueue() wins the race, we'll
-		 * wait for either @lock to point to us, through its Step-B, or
-		 * wait for a new @node->next from its Step-C.
-		 */
-		if (node->next) {
-			next = xchg(&node->next, NULL);
-			if (next)
-				break;
-		}
-
-		cpu_relax_lowlatency();
-	}
-
-	return next;
-}
-
-bool osq_lock(struct optimistic_spin_queue *lock)
-{
-	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
-	struct optimistic_spin_node *prev, *next;
-	int curr = encode_cpu(smp_processor_id());
-	int old;
-
-	node->locked = 0;
-	node->next = NULL;
-	node->cpu = curr;
-
-	old = atomic_xchg(&lock->tail, curr);
-	if (old == OSQ_UNLOCKED_VAL)
-		return true;
-
-	prev = decode_cpu(old);
-	node->prev = prev;
-	ACCESS_ONCE(prev->next) = node;
-
-	/*
-	 * Normally @prev is untouchable after the above store; because at that
-	 * moment unlock can proceed and wipe the node element from stack.
-	 *
-	 * However, since our nodes are static per-cpu storage, we're
-	 * guaranteed their existence -- this allows us to apply
-	 * cmpxchg in an attempt to undo our queueing.
-	 */
-
-	while (!smp_load_acquire(&node->locked)) {
-		/*
-		 * If we need to reschedule bail... so we can block.
-		 */
-		if (need_resched())
-			goto unqueue;
-
-		cpu_relax_lowlatency();
-	}
-	return true;
-
-unqueue:
-	/*
-	 * Step - A  -- stabilize @prev
-	 *
-	 * Undo our @prev->next assignment; this will make @prev's
-	 * unlock()/unqueue() wait for a next pointer since @lock points to us
-	 * (or later).
-	 */
-
-	for (;;) {
-		if (prev->next == node &&
-		    cmpxchg(&prev->next, node, NULL) == node)
-			break;
-
-		/*
-		 * We can only fail the cmpxchg() racing against an unlock(),
-		 * in which case we should observe @node->locked becomming
-		 * true.
-		 */
-		if (smp_load_acquire(&node->locked))
-			return true;
-
-		cpu_relax_lowlatency();
-
-		/*
-		 * Or we race against a concurrent unqueue()'s step-B, in which
-		 * case its step-C will write us a new @node->prev pointer.
-		 */
-		prev = ACCESS_ONCE(node->prev);
-	}
-
-	/*
-	 * Step - B -- stabilize @next
-	 *
-	 * Similar to unlock(), wait for @node->next or move @lock from @node
-	 * back to @prev.
-	 */
-
-	next = osq_wait_next(lock, node, prev);
-	if (!next)
-		return false;
-
-	/*
-	 * Step - C -- unlink
-	 *
-	 * @prev is stable because its still waiting for a new @prev->next
-	 * pointer, @next is stable because our @node->next pointer is NULL and
-	 * it will wait in Step-A.
-	 */
-
-	ACCESS_ONCE(next->prev) = prev;
-	ACCESS_ONCE(prev->next) = next;
-
-	return false;
-}
-
-void osq_unlock(struct optimistic_spin_queue *lock)
-{
-	struct optimistic_spin_node *node, *next;
-	int curr = encode_cpu(smp_processor_id());
-
-	/*
-	 * Fast path for the uncontended case.
-	 */
-	if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr))
-		return;
-
-	/*
-	 * Second most likely case.
-	 */
-	node = this_cpu_ptr(&osq_node);
-	next = xchg(&node->next, NULL);
-	if (next) {
-		ACCESS_ONCE(next->locked) = 1;
-		return;
-	}
-
-	next = osq_wait_next(lock, node, NULL);
-	if (next)
-		ACCESS_ONCE(next->locked) = 1;
-}
-
-#endif
-
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 4d60986fcbe..d1fe2ba5bac 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -108,20 +108,4 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 	arch_mcs_spin_unlock_contended(&next->locked);
 }
 
-/*
- * Cancellable version of the MCS lock above.
- *
- * Intended for adaptive spinning of sleeping locks:
- * mutex_lock()/rwsem_down_{read,write}() etc.
- */
-
-struct optimistic_spin_node {
-	struct optimistic_spin_node *next, *prev;
-	int locked; /* 1 if lock acquired */
-	int cpu; /* encoded CPU # value */
-};
-
-extern bool osq_lock(struct optimistic_spin_queue *lock);
-extern void osq_unlock(struct optimistic_spin_queue *lock);
-
 #endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
new file mode 100644
index 00000000000..ec83d4db8ec
--- /dev/null
+++ b/kernel/locking/osq_lock.c
@@ -0,0 +1,203 @@
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/osq_lock.h>
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ *
+ * Using a single mcs node per CPU is safe because sleeping locks should not be
+ * called from interrupt context and we have preemption disabled while
+ * spinning.
+ */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
+
+/*
+ * We use the value 0 to represent "no CPU", thus the encoded value
+ * will be the CPU number incremented by 1.
+ */
+static inline int encode_cpu(int cpu_nr)
+{
+	return cpu_nr + 1;
+}
+
+static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
+{
+	int cpu_nr = encoded_cpu_val - 1;
+
+	return per_cpu_ptr(&osq_node, cpu_nr);
+}
+
+/*
+ * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
+ * Can return NULL in case we were the last queued and we updated @lock instead.
+ */
+static inline struct optimistic_spin_node *
+osq_wait_next(struct optimistic_spin_queue *lock,
+	      struct optimistic_spin_node *node,
+	      struct optimistic_spin_node *prev)
+{
+	struct optimistic_spin_node *next = NULL;
+	int curr = encode_cpu(smp_processor_id());
+	int old;
+
+	/*
+	 * If there is a prev node in queue, then the 'old' value will be
+	 * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
+	 * we're currently last in queue, then the queue will then become empty.
+	 */
+	old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
+
+	for (;;) {
+		if (atomic_read(&lock->tail) == curr &&
+		    atomic_cmpxchg(&lock->tail, curr, old) == curr) {
+			/*
+			 * We were the last queued, we moved @lock back. @prev
+			 * will now observe @lock and will complete its
+			 * unlock()/unqueue().
+			 */
+			break;
+		}
+
+		/*
+		 * We must xchg() the @node->next value, because if we were to
+		 * leave it in, a concurrent unlock()/unqueue() from
+		 * @node->next might complete Step-A and think its @prev is
+		 * still valid.
+		 *
+		 * If the concurrent unlock()/unqueue() wins the race, we'll
+		 * wait for either @lock to point to us, through its Step-B, or
+		 * wait for a new @node->next from its Step-C.
+		 */
+		if (node->next) {
+			next = xchg(&node->next, NULL);
+			if (next)
+				break;
+		}
+
+		cpu_relax_lowlatency();
+	}
+
+	return next;
+}
+
+bool osq_lock(struct optimistic_spin_queue *lock)
+{
+	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
+	struct optimistic_spin_node *prev, *next;
+	int curr = encode_cpu(smp_processor_id());
+	int old;
+
+	node->locked = 0;
+	node->next = NULL;
+	node->cpu = curr;
+
+	old = atomic_xchg(&lock->tail, curr);
+	if (old == OSQ_UNLOCKED_VAL)
+		return true;
+
+	prev = decode_cpu(old);
+	node->prev = prev;
+	ACCESS_ONCE(prev->next) = node;
+
+	/*
+	 * Normally @prev is untouchable after the above store; because at that
+	 * moment unlock can proceed and wipe the node element from stack.
+	 *
+	 * However, since our nodes are static per-cpu storage, we're
+	 * guaranteed their existence -- this allows us to apply
+	 * cmpxchg in an attempt to undo our queueing.
+	 */
+
+	while (!smp_load_acquire(&node->locked)) {
+		/*
+		 * If we need to reschedule bail... so we can block.
+		 */
+		if (need_resched())
+			goto unqueue;
+
+		cpu_relax_lowlatency();
+	}
+	return true;
+
+unqueue:
+	/*
+	 * Step - A  -- stabilize @prev
+	 *
+	 * Undo our @prev->next assignment; this will make @prev's
+	 * unlock()/unqueue() wait for a next pointer since @lock points to us
+	 * (or later).
+	 */
+
+	for (;;) {
+		if (prev->next == node &&
+		    cmpxchg(&prev->next, node, NULL) == node)
+			break;
+
+		/*
+		 * We can only fail the cmpxchg() racing against an unlock(),
+		 * in which case we should observe @node->locked becomming
+		 * true.
+		 */
+		if (smp_load_acquire(&node->locked))
+			return true;
+
+		cpu_relax_lowlatency();
+
+		/*
+		 * Or we race against a concurrent unqueue()'s step-B, in which
+		 * case its step-C will write us a new @node->prev pointer.
+		 */
+		prev = ACCESS_ONCE(node->prev);
+	}
+
+	/*
+	 * Step - B -- stabilize @next
+	 *
+	 * Similar to unlock(), wait for @node->next or move @lock from @node
+	 * back to @prev.
+	 */
+
+	next = osq_wait_next(lock, node, prev);
+	if (!next)
+		return false;
+
+	/*
+	 * Step - C -- unlink
+	 *
+	 * @prev is stable because its still waiting for a new @prev->next
+	 * pointer, @next is stable because our @node->next pointer is NULL and
+	 * it will wait in Step-A.
+	 */
+
+	ACCESS_ONCE(next->prev) = prev;
+	ACCESS_ONCE(prev->next) = next;
+
+	return false;
+}
+
+void osq_unlock(struct optimistic_spin_queue *lock)
+{
+	struct optimistic_spin_node *node, *next;
+	int curr = encode_cpu(smp_processor_id());
+
+	/*
+	 * Fast path for the uncontended case.
+	 */
+	if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr))
+		return;
+
+	/*
+	 * Second most likely case.
+	 */
+	node = this_cpu_ptr(&osq_node);
+	next = xchg(&node->next, NULL);
+	if (next) {
+		ACCESS_ONCE(next->locked) = 1;
+		return;
+	}
+
+	next = osq_wait_next(lock, node, NULL);
+	if (next)
+		ACCESS_ONCE(next->locked) = 1;
+}
-- 
cgit v1.2.3-70-g09d2


From 86038c5ea81b519a8a1fcfcd5e4599aab0cdd119 Mon Sep 17 00:00:00 2001
From: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Date: Tue, 16 Dec 2014 12:47:34 +0100
Subject: perf: Avoid horrible stack usage

Both Linus (most recent) and Steve (a while ago) reported that perf
related callbacks have massive stack bloat.

The problem is that software events need a pt_regs in order to
properly report the event location and unwind stack. And because we
could not assume one was present we allocated one on stack and filled
it with minimal bits required for operation.

Now, pt_regs is quite large, so this is undesirable. Furthermore it
turns out that most sites actually have a pt_regs pointer available,
making this even more onerous, as the stack space is pointless waste.

This patch addresses the problem by observing that software events
have well defined nesting semantics, therefore we can use static
per-cpu storage instead of on-stack.

Linus made the further observation that all but the scheduler callers
of perf_sw_event() have a pt_regs available, so we change the regular
perf_sw_event() to require a valid pt_regs (where it used to be
optional) and add perf_sw_event_sched() for the scheduler.

We have a scheduler specific call instead of a more generic _noregs()
like construct because we can assume non-recursion from the scheduler
and thereby simplify the code further (_noregs would have to put the
recursion context call inline in order to assertain which __perf_regs
element to use).

One last note on the implementation of perf_trace_buf_prepare(); we
allow .regs = NULL for those cases where we already have a pt_regs
pointer available and do not need another.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Javi Merino <javi.merino@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Petr Mladek <pmladek@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tom Zanussi <tom.zanussi@linux.intel.com>
Cc: Vaibhav Nagarnaik <vnagarnaik@google.com>
Link: http://lkml.kernel.org/r/20141216115041.GW3337@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/ftrace_event.h    |  2 +-
 include/linux/perf_event.h      | 28 +++++++++++++++++++++-------
 include/trace/ftrace.h          |  7 ++++---
 kernel/events/core.c            | 23 +++++++++++++++++------
 kernel/sched/core.c             |  2 +-
 kernel/trace/trace_event_perf.c |  4 +++-
 kernel/trace/trace_kprobe.c     |  4 ++--
 kernel/trace/trace_syscalls.c   |  4 ++--
 kernel/trace/trace_uprobe.c     |  2 +-
 9 files changed, 52 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 0bebb5c348b..d36f68b08ac 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -595,7 +595,7 @@ extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
 extern void *perf_trace_buf_prepare(int size, unsigned short type,
-				    struct pt_regs *regs, int *rctxp);
+				    struct pt_regs **regs, int *rctxp);
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4f7a61ca4b3..3a7bd80b4db 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -665,6 +665,7 @@ static inline int is_software_event(struct perf_event *event)
 
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
+extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
 extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
 
 #ifndef perf_arch_fetch_caller_regs
@@ -689,14 +690,25 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
-	struct pt_regs hot_regs;
+	if (static_key_false(&perf_swevent_enabled[event_id]))
+		__perf_sw_event(event_id, nr, regs, addr);
+}
+
+DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
 
+/*
+ * 'Special' version for the scheduler, it hard assumes no recursion,
+ * which is guaranteed by us not actually scheduling inside other swevents
+ * because those disable preemption.
+ */
+static __always_inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
+{
 	if (static_key_false(&perf_swevent_enabled[event_id])) {
-		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs);
-			regs = &hot_regs;
-		}
-		__perf_sw_event(event_id, nr, regs, addr);
+		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+		perf_fetch_caller_regs(regs);
+		___perf_sw_event(event_id, nr, regs, addr);
 	}
 }
 
@@ -712,7 +724,7 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
 static inline void perf_event_task_sched_out(struct task_struct *prev,
 					     struct task_struct *next)
 {
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
+	perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
 
 	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_out(prev, next);
@@ -823,6 +835,8 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh)
 static inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)	{ }
 static inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)			{ }
+static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
 static inline int perf_register_guest_info_callbacks
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 139b5067345..27609dfcce2 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -763,7 +763,7 @@ perf_trace_##call(void *__data, proto)					\
 	struct ftrace_event_call *event_call = __data;			\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
-	struct pt_regs __regs;						\
+	struct pt_regs *__regs;						\
 	u64 __addr = 0, __count = 1;					\
 	struct task_struct *__task = NULL;				\
 	struct hlist_head *head;					\
@@ -782,18 +782,19 @@ perf_trace_##call(void *__data, proto)					\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	perf_fetch_caller_regs(&__regs);				\
 	entry = perf_trace_buf_prepare(__entry_size,			\
 			event_call->event.type, &__regs, &rctx);	\
 	if (!entry)							\
 		return;							\
 									\
+	perf_fetch_caller_regs(__regs);					\
+									\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
-		__count, &__regs, head, __task);			\
+		__count, __regs, head, __task);				\
 }
 
 /*
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 882f835a0d8..c10124b772c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5889,6 +5889,8 @@ end:
 	rcu_read_unlock();
 }
 
+DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]);
+
 int perf_swevent_get_recursion_context(void)
 {
 	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
@@ -5904,21 +5906,30 @@ inline void perf_swevent_put_recursion_context(int rctx)
 	put_recursion_context(swhash->recursion, rctx);
 }
 
-void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
+void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
 	struct perf_sample_data data;
-	int rctx;
 
-	preempt_disable_notrace();
-	rctx = perf_swevent_get_recursion_context();
-	if (rctx < 0)
+	if (WARN_ON_ONCE(!regs))
 		return;
 
 	perf_sample_data_init(&data, addr, 0);
-
 	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, &data, regs);
+}
+
+void __perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
+{
+	int rctx;
+
+	preempt_disable_notrace();
+	rctx = perf_swevent_get_recursion_context();
+	if (unlikely(rctx < 0))
+		goto fail;
+
+	___perf_sw_event(event_id, nr, regs, addr);
 
 	perf_swevent_put_recursion_context(rctx);
+fail:
 	preempt_enable_notrace();
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c0accc00566..d22fb16a715 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1082,7 +1082,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
-		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
 	}
 
 	__set_task_cpu(p, new_cpu);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 4b9c114ee9d..6fa484de2ba 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -261,7 +261,7 @@ void perf_trace_del(struct perf_event *p_event, int flags)
 }
 
 void *perf_trace_buf_prepare(int size, unsigned short type,
-			     struct pt_regs *regs, int *rctxp)
+			     struct pt_regs **regs, int *rctxp)
 {
 	struct trace_entry *entry;
 	unsigned long flags;
@@ -280,6 +280,8 @@ void *perf_trace_buf_prepare(int size, unsigned short type,
 	if (*rctxp < 0)
 		return NULL;
 
+	if (regs)
+		*regs = this_cpu_ptr(&__perf_regs[*rctxp]);
 	raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
 
 	/* zero the dead bytes from align to not leak stack to user */
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5edb518be34..296079ae658 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1148,7 +1148,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		return;
 
@@ -1179,7 +1179,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		return;
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index c6ee36fcbf9..f97f6e3a676 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -574,7 +574,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	size -= sizeof(u32);
 
 	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
-				sys_data->enter_event->event.type, regs, &rctx);
+				sys_data->enter_event->event.type, NULL, &rctx);
 	if (!rec)
 		return;
 
@@ -647,7 +647,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	size -= sizeof(u32);
 
 	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
-				sys_data->exit_event->event.type, regs, &rctx);
+				sys_data->exit_event->event.type, NULL, &rctx);
 	if (!rec)
 		return;
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 8520acc34b1..b11441321e7 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1111,7 +1111,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 	if (hlist_empty(head))
 		goto out;
 
-	entry = perf_trace_buf_prepare(size, call->event.type, regs, &rctx);
+	entry = perf_trace_buf_prepare(size, call->event.type, NULL, &rctx);
 	if (!entry)
 		goto out;
 
-- 
cgit v1.2.3-70-g09d2


From 0d40c61279510b8ce2368e1c6adcc2c4dc1af279 Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <s.nawrocki@samsung.com>
Date: Wed, 14 Jan 2015 19:42:38 +0100
Subject: ASoC: samsung: i2s: Add clk provider DT binding documentation

The new DT properties required for the I2S device node to be referred
as a clock provider and corresponding clock indices definition is added.

Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/samsung-i2s.txt      | 22 ++++++++++++++++++++++
 include/dt-bindings/sound/samsung-i2s.h            |  8 ++++++++
 2 files changed, 30 insertions(+)
 create mode 100644 include/dt-bindings/sound/samsung-i2s.h

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/samsung-i2s.txt b/Documentation/devicetree/bindings/sound/samsung-i2s.txt
index d188296bb6e..09e0e18591a 100644
--- a/Documentation/devicetree/bindings/sound/samsung-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/samsung-i2s.txt
@@ -33,6 +33,25 @@ Required SoC Specific Properties:
   "iis" is the i2s bus clock and i2s_opclk0, i2s_opclk1 are sources of the root
   clk. i2s0 has internal mux to select the source of root clk and i2s1 and i2s2
   doesn't have any such mux.
+- #clock-cells: should be 1, this property must be present if the I2S device
+  is a clock provider in terms of the common clock bindings, described in
+  ../clock/clock-bindings.txt.
+- clock-output-names: from the common clock bindings, names of the CDCLK
+  I2S output clocks, suggested values are "i2s_cdclk0", "i2s_cdclk1",
+  "i2s_cdclk3" for the I2S0, I2S1, I2S2 devices recpectively.
+
+There are following clocks available at the I2S device nodes:
+ CLK_I2S_CDCLK    - the CDCLK (CODECLKO) gate clock,
+ CLK_I2S_RCLK_PSR - the RCLK prescaler divider clock (corresponding to the
+		    IISPSR register),
+ CLK_I2S_RCLK_SRC - the RCLKSRC mux clock (corresponding to RCLKSRC bit in
+		    IISMOD register).
+
+Refer to the SoC datasheet for availability of the above clocks.
+The CLK_I2S_RCLK_PSR and CLK_I2S_RCLK_SRC clocks are usually only available
+in the IIS Multi Audio Interface (I2S0).
+Note: Old DTs may not have the #clock-cells, clock-output-names properties
+and then not use the I2S node as a clock supplier.
 
 Optional SoC Specific Properties:
 
@@ -41,6 +60,7 @@ Optional SoC Specific Properties:
 - pinctrl-0: Should specify pin control groups used for this controller.
 - pinctrl-names: Should contain only one value - "default".
 
+
 Example:
 
 i2s0: i2s@03830000 {
@@ -54,6 +74,8 @@ i2s0: i2s@03830000 {
 		<&clock_audss EXYNOS_I2S_BUS>,
 		<&clock_audss EXYNOS_SCLK_I2S>;
 	clock-names = "iis", "i2s_opclk0", "i2s_opclk1";
+	#clock-cells;
+	clock-output-names = "i2s_cdclk0";
 	samsung,idma-addr = <0x03000000>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2s0_bus>;
diff --git a/include/dt-bindings/sound/samsung-i2s.h b/include/dt-bindings/sound/samsung-i2s.h
new file mode 100644
index 00000000000..0c69818d530
--- /dev/null
+++ b/include/dt-bindings/sound/samsung-i2s.h
@@ -0,0 +1,8 @@
+#ifndef _DT_BINDINGS_SAMSUNG_I2S_H
+#define _DT_BINDINGS_SAMSUNG_I2S_H
+
+#define CLK_I2S_CDCLK		0
+#define CLK_I2S_RCLK_SRC	1
+#define CLK_I2S_RCLK_PSR	2
+
+#endif /* _DT_BINDINGS_SAMSUNG_I2S_H */
-- 
cgit v1.2.3-70-g09d2


From a2b12f3c7ac1ea43ae646db74faf0b56c2bba563 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 12 Jan 2015 17:00:37 -0800
Subject: udp: pass udp_offload struct to UDP gro callbacks

This patch introduces udp_offload_callbacks which has the same
GRO functions (but not a GSO function) as offload_callbacks,
except there is an argument to a udp_offload struct passed to
gro_receive and gro_complete functions. This additional argument
can be used to retrieve the per port structure of the encapsulation
for use in gro processing (mostly by doing container_of on the
structure).

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c       |  7 +++++--
 include/linux/netdevice.h | 15 +++++++++++++--
 net/ipv4/fou.c            | 12 ++++++++----
 net/ipv4/geneve.c         |  6 ++++--
 net/ipv4/udp_offload.c    |  7 +++++--
 5 files changed, 35 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 985359dd603..5c56a3ff25a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -539,7 +539,9 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
 	return 1;
 }
 
-static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
+					  struct sk_buff *skb,
+					  struct udp_offload *uoff)
 {
 	struct sk_buff *p, **pp = NULL;
 	struct vxlanhdr *vh, *vh2;
@@ -578,7 +580,8 @@ out:
 	return pp;
 }
 
-static int vxlan_gro_complete(struct sk_buff *skb, int nhoff)
+static int vxlan_gro_complete(struct sk_buff *skb, int nhoff,
+			      struct udp_offload *uoff)
 {
 	udp_tunnel_gro_complete(skb, nhoff);
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 679e6e90aa4..47921c291dd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1969,7 +1969,7 @@ struct offload_callbacks {
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
 						netdev_features_t features);
 	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
-					       struct sk_buff *skb);
+						 struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb, int nhoff);
 };
 
@@ -1979,10 +1979,21 @@ struct packet_offload {
 	struct list_head	 list;
 };
 
+struct udp_offload;
+
+struct udp_offload_callbacks {
+	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
+						 struct sk_buff *skb,
+						 struct udp_offload *uoff);
+	int			(*gro_complete)(struct sk_buff *skb,
+						int nhoff,
+						struct udp_offload *uoff);
+};
+
 struct udp_offload {
 	__be16			 port;
 	u8			 ipproto;
-	struct offload_callbacks callbacks;
+	struct udp_offload_callbacks callbacks;
 };
 
 /* often modified stats are per cpu, other are shared (netdev->stats) */
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 2197c36f722..3bc0cf07661 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -174,7 +174,8 @@ drop:
 }
 
 static struct sk_buff **fou_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					struct udp_offload *uoff)
 {
 	const struct net_offload *ops;
 	struct sk_buff **pp = NULL;
@@ -195,7 +196,8 @@ out_unlock:
 	return pp;
 }
 
-static int fou_gro_complete(struct sk_buff *skb, int nhoff)
+static int fou_gro_complete(struct sk_buff *skb, int nhoff,
+			    struct udp_offload *uoff)
 {
 	const struct net_offload *ops;
 	u8 proto = NAPI_GRO_CB(skb)->proto;
@@ -254,7 +256,8 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 }
 
 static struct sk_buff **gue_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					struct udp_offload *uoff)
 {
 	const struct net_offload **offloads;
 	const struct net_offload *ops;
@@ -360,7 +363,8 @@ out:
 	return pp;
 }
 
-static int gue_gro_complete(struct sk_buff *skb, int nhoff)
+static int gue_gro_complete(struct sk_buff *skb, int nhoff,
+			    struct udp_offload *uoff)
 {
 	const struct net_offload **offloads;
 	struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 23744c7a971..9568594ca2f 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -147,7 +147,8 @@ static int geneve_hlen(struct genevehdr *gh)
 }
 
 static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
-					   struct sk_buff *skb)
+					   struct sk_buff *skb,
+					   struct udp_offload *uoff)
 {
 	struct sk_buff *p, **pp = NULL;
 	struct genevehdr *gh, *gh2;
@@ -211,7 +212,8 @@ out:
 	return pp;
 }
 
-static int geneve_gro_complete(struct sk_buff *skb, int nhoff)
+static int geneve_gro_complete(struct sk_buff *skb, int nhoff,
+			       struct udp_offload *uoff)
 {
 	struct genevehdr *gh;
 	struct packet_offload *ptype;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index d3e537ef6b7..d10f6f4ead2 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -339,7 +339,8 @@ unflush:
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
 	NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-	pp = uo_priv->offload->callbacks.gro_receive(head, skb);
+	pp = uo_priv->offload->callbacks.gro_receive(head, skb,
+						     uo_priv->offload);
 
 out_unlock:
 	rcu_read_unlock();
@@ -395,7 +396,9 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
 
 	if (uo_priv != NULL) {
 		NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-		err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr));
+		err = uo_priv->offload->callbacks.gro_complete(skb,
+				nhoff + sizeof(struct udphdr),
+				uo_priv->offload);
 	}
 
 	rcu_read_unlock();
-- 
cgit v1.2.3-70-g09d2


From dfd8645ea1bd91277f841e74c33e1f4dbbede808 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 12 Jan 2015 17:00:38 -0800
Subject: vxlan: Remote checksum offload

Add support for remote checksum offload in VXLAN. This uses a
reserved bit to indicate that RCO is being done, and uses the low order
reserved eight bits of the VNI to hold the start and offset values in a
compressed manner.

Start is encoded in the low order seven bits of VNI. This is start >> 1
so that the checksum start offset is 0-254 using even values only.
Checksum offset (transport checksum field) is indicated in the high
order bit in the low order byte of the VNI. If the bit is set, the
checksum field is for UDP (so offset = start + 6), else checksum
field is for TCP (so offset = start + 16). Only TCP and UDP are
supported in this implementation.

Remote checksum offload for VXLAN is described in:

https://tools.ietf.org/html/draft-herbert-vxlan-rco-00

Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4).

With UDP checksums and Remote Checksum Offload
  IPv4
      Client
        11.84% CPU utilization
      Server
        12.96% CPU utilization
      9197 Mbps
  IPv6
      Client
        12.46% CPU utilization
      Server
        14.48% CPU utilization
      8963 Mbps

With UDP checksums, no remote checksum offload
  IPv4
      Client
        15.67% CPU utilization
      Server
        14.83% CPU utilization
      9094 Mbps
  IPv6
      Client
        16.21% CPU utilization
      Server
        14.32% CPU utilization
      9058 Mbps

No UDP checksums
  IPv4
      Client
        15.03% CPU utilization
      Server
        23.09% CPU utilization
      9089 Mbps
  IPv6
      Client
        16.18% CPU utilization
      Server
        26.57% CPU utilization
       8954 Mbps

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c          | 191 +++++++++++++++++++++++++++++++++++++++++--
 include/net/vxlan.h          |  11 +++
 include/uapi/linux/if_link.h |   2 +
 3 files changed, 198 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 5c56a3ff25a..99df0d76157 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -539,6 +539,46 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
 	return 1;
 }
 
+static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
+					  unsigned int off,
+					  struct vxlanhdr *vh, size_t hdrlen,
+					  u32 data)
+{
+	size_t start, offset, plen;
+	__wsum delta;
+
+	if (skb->remcsum_offload)
+		return vh;
+
+	if (!NAPI_GRO_CB(skb)->csum_valid)
+		return NULL;
+
+	start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
+	offset = start + ((data & VXLAN_RCO_UDP) ?
+			  offsetof(struct udphdr, check) :
+			  offsetof(struct tcphdr, check));
+
+	plen = hdrlen + offset + sizeof(u16);
+
+	/* Pull checksum that will be written */
+	if (skb_gro_header_hard(skb, off + plen)) {
+		vh = skb_gro_header_slow(skb, off + plen, off);
+		if (!vh)
+			return NULL;
+	}
+
+	delta = remcsum_adjust((void *)vh + hdrlen,
+			       NAPI_GRO_CB(skb)->csum, start, offset);
+
+	/* Adjust skb->csum since we changed the packet */
+	skb->csum = csum_add(skb->csum, delta);
+	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+
+	skb->remcsum_offload = 1;
+
+	return vh;
+}
+
 static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 					  struct sk_buff *skb,
 					  struct udp_offload *uoff)
@@ -547,6 +587,9 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 	struct vxlanhdr *vh, *vh2;
 	unsigned int hlen, off_vx;
 	int flush = 1;
+	struct vxlan_sock *vs = container_of(uoff, struct vxlan_sock,
+					     udp_offloads);
+	u32 flags;
 
 	off_vx = skb_gro_offset(skb);
 	hlen = off_vx + sizeof(*vh);
@@ -557,6 +600,19 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 			goto out;
 	}
 
+	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
+	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
+
+	flags = ntohl(vh->vx_flags);
+
+	if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) {
+		vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr),
+				       ntohl(vh->vx_vni));
+
+		if (!vh)
+			goto out;
+	}
+
 	flush = 0;
 
 	for (p = *head; p; p = p->next) {
@@ -570,8 +626,6 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 		}
 	}
 
-	skb_gro_pull(skb, sizeof(struct vxlanhdr));
-	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
 	pp = eth_gro_receive(head, skb);
 
 out:
@@ -1087,6 +1141,42 @@ static void vxlan_igmp_leave(struct work_struct *work)
 	dev_put(vxlan->dev);
 }
 
+static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
+				      size_t hdrlen, u32 data)
+{
+	size_t start, offset, plen;
+	__wsum delta;
+
+	if (skb->remcsum_offload) {
+		/* Already processed in GRO path */
+		skb->remcsum_offload = 0;
+		return vh;
+	}
+
+	start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
+	offset = start + ((data & VXLAN_RCO_UDP) ?
+			  offsetof(struct udphdr, check) :
+			  offsetof(struct tcphdr, check));
+
+	plen = hdrlen + offset + sizeof(u16);
+
+	if (!pskb_may_pull(skb, plen))
+		return NULL;
+
+	vh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
+
+	if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
+		__skb_checksum_complete(skb);
+
+	delta = remcsum_adjust((void *)vh + hdrlen,
+			       skb->csum, start, offset);
+
+	/* Adjust skb->csum since we changed the packet */
+	skb->csum = csum_add(skb->csum, delta);
+
+	return vh;
+}
+
 /* Callback from net/ipv4/udp.c to receive packets */
 static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
@@ -1111,12 +1201,22 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
 		goto drop;
+	vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
 
 	vs = rcu_dereference_sk_user_data(sk);
 	if (!vs)
 		goto drop;
 
-	if (flags || (vni & 0xff)) {
+	if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) {
+		vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr), vni);
+		if (!vxh)
+			goto drop;
+
+		flags &= ~VXLAN_HF_RCO;
+		vni &= VXLAN_VID_MASK;
+	}
+
+	if (flags || (vni & ~VXLAN_VID_MASK)) {
 		/* If there are any unprocessed flags remaining treat
 		 * this as a malformed packet. This behavior diverges from
 		 * VXLAN RFC (RFC7348) which stipulates that bits in reserved
@@ -1553,8 +1653,23 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	int min_headroom;
 	int err;
 	bool udp_sum = !udp_get_no_check6_tx(vs->sock->sk);
+	int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+	u16 hdrlen = sizeof(struct vxlanhdr);
+
+	if ((vs->flags & VXLAN_F_REMCSUM_TX) &&
+	    skb->ip_summed == CHECKSUM_PARTIAL) {
+		int csum_start = skb_checksum_start_offset(skb);
+
+		if (csum_start <= VXLAN_MAX_REMCSUM_START &&
+		    !(csum_start & VXLAN_RCO_SHIFT_MASK) &&
+		    (skb->csum_offset == offsetof(struct udphdr, check) ||
+		     skb->csum_offset == offsetof(struct tcphdr, check))) {
+			udp_sum = false;
+			type |= SKB_GSO_TUNNEL_REMCSUM;
+		}
+	}
 
-	skb = udp_tunnel_handle_offloads(skb, udp_sum);
+	skb = iptunnel_handle_offloads(skb, udp_sum, type);
 	if (IS_ERR(skb)) {
 		err = -EINVAL;
 		goto err;
@@ -1583,6 +1698,22 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	vxh->vx_flags = htonl(VXLAN_HF_VNI);
 	vxh->vx_vni = vni;
 
+	if (type & SKB_GSO_TUNNEL_REMCSUM) {
+		u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
+			   VXLAN_RCO_SHIFT;
+
+		if (skb->csum_offset == offsetof(struct udphdr, check))
+			data |= VXLAN_RCO_UDP;
+
+		vxh->vx_vni |= htonl(data);
+		vxh->vx_flags |= htonl(VXLAN_HF_RCO);
+
+		if (!skb_is_gso(skb)) {
+			skb->ip_summed = CHECKSUM_NONE;
+			skb->encapsulation = 0;
+		}
+	}
+
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
 	udp_tunnel6_xmit_skb(vs->sock, dst, skb, dev, saddr, daddr, prio,
@@ -1603,8 +1734,23 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 	int min_headroom;
 	int err;
 	bool udp_sum = !vs->sock->sk->sk_no_check_tx;
+	int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+	u16 hdrlen = sizeof(struct vxlanhdr);
+
+	if ((vs->flags & VXLAN_F_REMCSUM_TX) &&
+	    skb->ip_summed == CHECKSUM_PARTIAL) {
+		int csum_start = skb_checksum_start_offset(skb);
+
+		if (csum_start <= VXLAN_MAX_REMCSUM_START &&
+		    !(csum_start & VXLAN_RCO_SHIFT_MASK) &&
+		    (skb->csum_offset == offsetof(struct udphdr, check) ||
+		     skb->csum_offset == offsetof(struct tcphdr, check))) {
+			udp_sum = false;
+			type |= SKB_GSO_TUNNEL_REMCSUM;
+		}
+	}
 
-	skb = udp_tunnel_handle_offloads(skb, udp_sum);
+	skb = iptunnel_handle_offloads(skb, udp_sum, type);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
@@ -1627,6 +1773,22 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 	vxh->vx_flags = htonl(VXLAN_HF_VNI);
 	vxh->vx_vni = vni;
 
+	if (type & SKB_GSO_TUNNEL_REMCSUM) {
+		u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
+			   VXLAN_RCO_SHIFT;
+
+		if (skb->csum_offset == offsetof(struct udphdr, check))
+			data |= VXLAN_RCO_UDP;
+
+		vxh->vx_vni |= htonl(data);
+		vxh->vx_flags |= htonl(VXLAN_HF_RCO);
+
+		if (!skb_is_gso(skb)) {
+			skb->ip_summed = CHECKSUM_NONE;
+			skb->encapsulation = 0;
+		}
+	}
+
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
 	return udp_tunnel_xmit_skb(vs->sock, rt, skb, src, dst, tos,
@@ -2218,6 +2380,8 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_UDP_CSUM]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_REMCSUM_TX]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_REMCSUM_RX]	= { .type = NLA_U8 },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -2339,6 +2503,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	atomic_set(&vs->refcnt, 1);
 	vs->rcv = rcv;
 	vs->data = data;
+	vs->flags = flags;
 
 	/* Initialize the vxlan udp offloads structure */
 	vs->udp_offloads.port = port;
@@ -2533,6 +2698,14 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
 
+	if (data[IFLA_VXLAN_REMCSUM_TX] &&
+	    nla_get_u8(data[IFLA_VXLAN_REMCSUM_TX]))
+		vxlan->flags |= VXLAN_F_REMCSUM_TX;
+
+	if (data[IFLA_VXLAN_REMCSUM_RX] &&
+	    nla_get_u8(data[IFLA_VXLAN_REMCSUM_RX]))
+		vxlan->flags |= VXLAN_F_REMCSUM_RX;
+
 	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
 			   vxlan->dst_port)) {
 		pr_info("duplicate VNI %u\n", vni);
@@ -2601,6 +2774,8 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */
 		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */
 		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */
+		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */
+		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */
 		0;
 }
 
@@ -2666,7 +2841,11 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
 			!!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) ||
 	    nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
-			!!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)))
+			!!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX,
+			!!(vxlan->flags & VXLAN_F_REMCSUM_TX)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX,
+			!!(vxlan->flags & VXLAN_F_REMCSUM_RX)))
 		goto nla_put_failure;
 
 	if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports))
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index a0d80736224..0a7443b4913 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -19,6 +19,14 @@ struct vxlanhdr {
 
 /* VXLAN header flags. */
 #define VXLAN_HF_VNI 0x08000000
+#define VXLAN_HF_RCO 0x00200000
+
+/* Remote checksum offload header option */
+#define VXLAN_RCO_MASK  0x7f    /* Last byte of vni field */
+#define VXLAN_RCO_UDP   0x80    /* Indicate UDP RCO (TCP when not set *) */
+#define VXLAN_RCO_SHIFT 1       /* Left shift of start */
+#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
+#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
 
 #define VXLAN_N_VID     (1u << 24)
 #define VXLAN_VID_MASK  (VXLAN_N_VID - 1)
@@ -38,6 +46,7 @@ struct vxlan_sock {
 	struct hlist_head vni_list[VNI_HASH_SIZE];
 	atomic_t	  refcnt;
 	struct udp_offload udp_offloads;
+	u32		  flags;
 };
 
 #define VXLAN_F_LEARN			0x01
@@ -49,6 +58,8 @@ struct vxlan_sock {
 #define VXLAN_F_UDP_CSUM		0x40
 #define VXLAN_F_UDP_ZERO_CSUM6_TX	0x80
 #define VXLAN_F_UDP_ZERO_CSUM6_RX	0x100
+#define VXLAN_F_REMCSUM_TX		0x200
+#define VXLAN_F_REMCSUM_RX		0x400
 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index f7d0d2d7173..b2723f65846 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -370,6 +370,8 @@ enum {
 	IFLA_VXLAN_UDP_CSUM,
 	IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
 	IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+	IFLA_VXLAN_REMCSUM_TX,
+	IFLA_VXLAN_REMCSUM_RX,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
-- 
cgit v1.2.3-70-g09d2


From 3511494ce2f3d3b77544c79b87511a4ddb61dc89 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Thu, 15 Jan 2015 03:53:55 +0100
Subject: vxlan: Group Policy extension

Implements supports for the Group Policy VXLAN extension [0] to provide
a lightweight and simple security label mechanism across network peers
based on VXLAN. The security context and associated metadata is mapped
to/from skb->mark. This allows further mapping to a SELinux context
using SECMARK, to implement ACLs directly with nftables, iptables, OVS,
tc, etc.

The group membership is defined by the lower 16 bits of skb->mark, the
upper 16 bits are used for flags.

SELinux allows to manage label to secure local resources. However,
distributed applications require ACLs to implemented across hosts. This
is typically achieved by matching on L2-L4 fields to identify the
original sending host and process on the receiver. On top of that,
netlabel and specifically CIPSO [1] allow to map security contexts to
universal labels.  However, netlabel and CIPSO are relatively complex.
This patch provides a lightweight alternative for overlay network
environments with a trusted underlay. No additional control protocol
is required.

           Host 1:                       Host 2:

      Group A        Group B        Group B     Group A
      +-----+   +-------------+    +-------+   +-----+
      | lxc |   | SELinux CTX |    | httpd |   | VM  |
      +--+--+   +--+----------+    +---+---+   +--+--+
	  \---+---/                     \----+---/
	      |                              |
	  +---+---+                      +---+---+
	  | vxlan |                      | vxlan |
	  +---+---+                      +---+---+
	      +------------------------------+

Backwards compatibility:
A VXLAN-GBP socket can receive standard VXLAN frames and will assign
the default group 0x0000 to such frames. A Linux VXLAN socket will
drop VXLAN-GBP  frames. The extension is therefore disabled by default
and needs to be specifically enabled:

   ip link add [...] type vxlan [...] gbp

In a mixed environment with VXLAN and VXLAN-GBP sockets, the GBP socket
must run on a separate port number.

Examples:
 iptables:
  host1# iptables -I OUTPUT -m owner --uid-owner 101 -j MARK --set-mark 0x200
  host2# iptables -I INPUT -m mark --mark 0x200 -j DROP

 OVS:
  # ovs-ofctl add-flow br0 'in_port=1,actions=load:0x200->NXM_NX_TUN_GBP_ID[],NORMAL'
  # ovs-ofctl add-flow br0 'in_port=2,tun_gbp_id=0x200,actions=drop'

[0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy
[1] http://lwn.net/Articles/204905/

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c           | 84 ++++++++++++++++++++++++++++++++++++-------
 include/net/vxlan.h           | 79 +++++++++++++++++++++++++++++++++++++---
 include/uapi/linux/if_link.h  |  1 +
 net/openvswitch/vport-vxlan.c |  9 +++--
 4 files changed, 152 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 99df0d76157..6dbf8e04192 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -620,7 +620,8 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 			continue;
 
 		vh2 = (struct vxlanhdr *)(p->data + off_vx);
-		if (vh->vx_vni != vh2->vx_vni) {
+		if (vh->vx_flags != vh2->vx_flags ||
+		    vh->vx_vni != vh2->vx_vni) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
@@ -1183,6 +1184,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	struct vxlan_sock *vs;
 	struct vxlanhdr *vxh;
 	u32 flags, vni;
+	struct vxlan_metadata md = {0};
 
 	/* Need Vxlan and inner Ethernet header to be present */
 	if (!pskb_may_pull(skb, VXLAN_HLEN))
@@ -1216,6 +1218,24 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		vni &= VXLAN_VID_MASK;
 	}
 
+	/* For backwards compatibility, only allow reserved fields to be
+	 * used by VXLAN extensions if explicitly requested.
+	 */
+	if ((flags & VXLAN_HF_GBP) && (vs->flags & VXLAN_F_GBP)) {
+		struct vxlanhdr_gbp *gbp;
+
+		gbp = (struct vxlanhdr_gbp *)vxh;
+		md.gbp = ntohs(gbp->policy_id);
+
+		if (gbp->dont_learn)
+			md.gbp |= VXLAN_GBP_DONT_LEARN;
+
+		if (gbp->policy_applied)
+			md.gbp |= VXLAN_GBP_POLICY_APPLIED;
+
+		flags &= ~VXLAN_GBP_USED_BITS;
+	}
+
 	if (flags || (vni & ~VXLAN_VID_MASK)) {
 		/* If there are any unprocessed flags remaining treat
 		 * this as a malformed packet. This behavior diverges from
@@ -1229,7 +1249,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 		goto bad_flags;
 	}
 
-	vs->rcv(vs, skb, vxh->vx_vni);
+	md.vni = vxh->vx_vni;
+	vs->rcv(vs, skb, &md);
 	return 0;
 
 drop:
@@ -1246,8 +1267,8 @@ error:
 	return 1;
 }
 
-static void vxlan_rcv(struct vxlan_sock *vs,
-		      struct sk_buff *skb, __be32 vx_vni)
+static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
+		      struct vxlan_metadata *md)
 {
 	struct iphdr *oip = NULL;
 	struct ipv6hdr *oip6 = NULL;
@@ -1258,7 +1279,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,
 	int err = 0;
 	union vxlan_addr *remote_ip;
 
-	vni = ntohl(vx_vni) >> 8;
+	vni = ntohl(md->vni) >> 8;
 	/* Is this VNI defined? */
 	vxlan = vxlan_vs_find_vni(vs, vni);
 	if (!vxlan)
@@ -1292,6 +1313,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,
 		goto drop;
 
 	skb_reset_network_header(skb);
+	skb->mark = md->gbp;
 
 	if (oip6)
 		err = IP6_ECN_decapsulate(oip6, skb);
@@ -1641,13 +1663,30 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
+static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, struct vxlan_sock *vs,
+				struct vxlan_metadata *md)
+{
+	struct vxlanhdr_gbp *gbp;
+
+	gbp = (struct vxlanhdr_gbp *)vxh;
+	vxh->vx_flags |= htonl(VXLAN_HF_GBP);
+
+	if (md->gbp & VXLAN_GBP_DONT_LEARN)
+		gbp->dont_learn = 1;
+
+	if (md->gbp & VXLAN_GBP_POLICY_APPLIED)
+		gbp->policy_applied = 1;
+
+	gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
+}
+
 #if IS_ENABLED(CONFIG_IPV6)
 static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 			   struct dst_entry *dst, struct sk_buff *skb,
 			   struct net_device *dev, struct in6_addr *saddr,
 			   struct in6_addr *daddr, __u8 prio, __u8 ttl,
-			   __be16 src_port, __be16 dst_port, __be32 vni,
-			   bool xnet)
+			   __be16 src_port, __be16 dst_port,
+			   struct vxlan_metadata *md, bool xnet)
 {
 	struct vxlanhdr *vxh;
 	int min_headroom;
@@ -1696,7 +1735,7 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
 	vxh->vx_flags = htonl(VXLAN_HF_VNI);
-	vxh->vx_vni = vni;
+	vxh->vx_vni = md->vni;
 
 	if (type & SKB_GSO_TUNNEL_REMCSUM) {
 		u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
@@ -1714,6 +1753,9 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 		}
 	}
 
+	if (vs->flags & VXLAN_F_GBP)
+		vxlan_build_gbp_hdr(vxh, vs, md);
+
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
 	udp_tunnel6_xmit_skb(vs->sock, dst, skb, dev, saddr, daddr, prio,
@@ -1728,7 +1770,8 @@ err:
 int vxlan_xmit_skb(struct vxlan_sock *vs,
 		   struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
-		   __be16 src_port, __be16 dst_port, __be32 vni, bool xnet)
+		   __be16 src_port, __be16 dst_port,
+		   struct vxlan_metadata *md, bool xnet)
 {
 	struct vxlanhdr *vxh;
 	int min_headroom;
@@ -1771,7 +1814,7 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 
 	vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
 	vxh->vx_flags = htonl(VXLAN_HF_VNI);
-	vxh->vx_vni = vni;
+	vxh->vx_vni = md->vni;
 
 	if (type & SKB_GSO_TUNNEL_REMCSUM) {
 		u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
@@ -1789,6 +1832,9 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 		}
 	}
 
+	if (vs->flags & VXLAN_F_GBP)
+		vxlan_build_gbp_hdr(vxh, vs, md);
+
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
 	return udp_tunnel_xmit_skb(vs->sock, rt, skb, src, dst, tos,
@@ -1849,6 +1895,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	const struct iphdr *old_iph;
 	struct flowi4 fl4;
 	union vxlan_addr *dst;
+	struct vxlan_metadata md;
 	__be16 src_port = 0, dst_port;
 	u32 vni;
 	__be16 df = 0;
@@ -1919,11 +1966,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
 		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+		md.vni = htonl(vni << 8);
+		md.gbp = skb->mark;
 
 		err = vxlan_xmit_skb(vxlan->vn_sock, rt, skb,
 				     fl4.saddr, dst->sin.sin_addr.s_addr,
-				     tos, ttl, df, src_port, dst_port,
-				     htonl(vni << 8),
+				     tos, ttl, df, src_port, dst_port, &md,
 				     !net_eq(vxlan->net, dev_net(vxlan->dev)));
 		if (err < 0) {
 			/* skb is already freed. */
@@ -1976,10 +2024,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		ttl = ttl ? : ip6_dst_hoplimit(ndst);
+		md.vni = htonl(vni << 8);
+		md.gbp = skb->mark;
 
 		err = vxlan6_xmit_skb(vxlan->vn_sock, ndst, skb,
 				      dev, &fl6.saddr, &fl6.daddr, 0, ttl,
-				      src_port, dst_port, htonl(vni << 8),
+				      src_port, dst_port, &md,
 				      !net_eq(vxlan->net, dev_net(vxlan->dev)));
 #endif
 	}
@@ -2382,6 +2432,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
 	[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_REMCSUM_TX]	= { .type = NLA_U8 },
 	[IFLA_VXLAN_REMCSUM_RX]	= { .type = NLA_U8 },
+	[IFLA_VXLAN_GBP]	= { .type = NLA_FLAG, },
 };
 
 static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -2706,6 +2757,9 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	    nla_get_u8(data[IFLA_VXLAN_REMCSUM_RX]))
 		vxlan->flags |= VXLAN_F_REMCSUM_RX;
 
+	if (data[IFLA_VXLAN_GBP])
+		vxlan->flags |= VXLAN_F_GBP;
+
 	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
 			   vxlan->dst_port)) {
 		pr_info("duplicate VNI %u\n", vni);
@@ -2851,6 +2905,10 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports))
 		goto nla_put_failure;
 
+	if (vxlan->flags & VXLAN_F_GBP &&
+	    nla_put_flag(skb, IFLA_VXLAN_GBP))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 0a7443b4913..f4a3583171b 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -11,15 +11,76 @@
 #define VNI_HASH_BITS	10
 #define VNI_HASH_SIZE	(1<<VNI_HASH_BITS)
 
-/* VXLAN protocol header */
+/*
+ * VXLAN Group Based Policy Extension:
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |1|-|-|-|1|-|-|-|R|D|R|R|A|R|R|R|        Group Policy ID        |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                VXLAN Network Identifier (VNI) |   Reserved    |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * D = Don't Learn bit. When set, this bit indicates that the egress
+ *     VTEP MUST NOT learn the source address of the encapsulated frame.
+ *
+ * A = Indicates that the group policy has already been applied to
+ *     this packet. Policies MUST NOT be applied by devices when the
+ *     A bit is set.
+ *
+ * [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy
+ */
+struct vxlanhdr_gbp {
+	__u8	vx_flags;
+#ifdef __LITTLE_ENDIAN_BITFIELD
+	__u8	reserved_flags1:3,
+		policy_applied:1,
+		reserved_flags2:2,
+		dont_learn:1,
+		reserved_flags3:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	__u8	reserved_flags1:1,
+		dont_learn:1,
+		reserved_flags2:2,
+		policy_applied:1,
+		reserved_flags3:3;
+#else
+#error	"Please fix <asm/byteorder.h>"
+#endif
+	__be16	policy_id;
+	__be32	vx_vni;
+};
+
+#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF)
+
+/* skb->mark mapping
+ *
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|R|R|R|R|R|D|R|R|A|R|R|R|        Group Policy ID        |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ */
+#define VXLAN_GBP_DONT_LEARN		(BIT(6) << 16)
+#define VXLAN_GBP_POLICY_APPLIED	(BIT(3) << 16)
+#define VXLAN_GBP_ID_MASK		(0xFFFF)
+
+/* VXLAN protocol header:
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |G|R|R|R|I|R|R|C|               Reserved                        |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                VXLAN Network Identifier (VNI) |   Reserved    |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * G = 1	Group Policy (VXLAN-GBP)
+ * I = 1	VXLAN Network Identifier (VNI) present
+ * C = 1	Remote checksum offload (RCO)
+ */
 struct vxlanhdr {
 	__be32 vx_flags;
 	__be32 vx_vni;
 };
 
 /* VXLAN header flags. */
-#define VXLAN_HF_VNI 0x08000000
-#define VXLAN_HF_RCO 0x00200000
+#define VXLAN_HF_RCO BIT(24)
+#define VXLAN_HF_VNI BIT(27)
+#define VXLAN_HF_GBP BIT(31)
 
 /* Remote checksum offload header option */
 #define VXLAN_RCO_MASK  0x7f    /* Last byte of vni field */
@@ -32,8 +93,14 @@ struct vxlanhdr {
 #define VXLAN_VID_MASK  (VXLAN_N_VID - 1)
 #define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
 
+struct vxlan_metadata {
+	__be32		vni;
+	u32		gbp;
+};
+
 struct vxlan_sock;
-typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, __be32 key);
+typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb,
+			   struct vxlan_metadata *md);
 
 /* per UDP socket information */
 struct vxlan_sock {
@@ -60,6 +127,7 @@ struct vxlan_sock {
 #define VXLAN_F_UDP_ZERO_CSUM6_RX	0x100
 #define VXLAN_F_REMCSUM_TX		0x200
 #define VXLAN_F_REMCSUM_RX		0x400
+#define VXLAN_F_GBP			0x800
 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,
@@ -70,7 +138,8 @@ void vxlan_sock_release(struct vxlan_sock *vs);
 int vxlan_xmit_skb(struct vxlan_sock *vs,
 		   struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
-		   __be16 src_port, __be16 dst_port, __be32 vni, bool xnet);
+		   __be16 src_port, __be16 dst_port, struct vxlan_metadata *md,
+		   bool xnet);
 
 static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
 						     netdev_features_t features)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index b2723f65846..2a8380edbb7 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -372,6 +372,7 @@ enum {
 	IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
 	IFLA_VXLAN_REMCSUM_TX,
 	IFLA_VXLAN_REMCSUM_RX,
+	IFLA_VXLAN_GBP,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 1435a053a87..9919d71c52c 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -59,7 +59,8 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
 }
 
 /* Called with rcu_read_lock and BH disabled. */
-static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
+static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
+		      struct vxlan_metadata *md)
 {
 	struct ovs_tunnel_info tun_info;
 	struct vport *vport = vs->data;
@@ -68,7 +69,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
 
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
-	key = cpu_to_be64(ntohl(vx_vni) >> 8);
+	key = cpu_to_be64(ntohl(md->vni) >> 8);
 	ovs_flow_tun_info_init(&tun_info, iph,
 			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
 			       key, TUNNEL_KEY, NULL, 0);
@@ -146,6 +147,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	struct vxlan_port *vxlan_port = vxlan_vport(vport);
 	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
 	const struct ovs_key_ipv4_tunnel *tun_key;
+	struct vxlan_metadata md = {0};
 	struct rtable *rt;
 	struct flowi4 fl;
 	__be16 src_port;
@@ -170,12 +172,13 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	skb->ignore_df = 1;
 
 	src_port = udp_flow_src_port(net, skb, 0, 0, true);
+	md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
 
 	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
 			     fl.saddr, tun_key->ipv4_dst,
 			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
 			     src_port, dst_port,
-			     htonl(be64_to_cpu(tun_key->tun_id) << 8),
+			     &md,
 			     false);
 	if (err < 0)
 		ip_rt_put(rt);
-- 
cgit v1.2.3-70-g09d2


From ac5132d1a03fe1ebbefb2382b36e829dff056283 Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Thu, 15 Jan 2015 03:53:56 +0100
Subject: vxlan: Only bind to sockets with compatible flags enabled

A VXLAN net_device looking for an appropriate socket may only consider
a socket which has a matching set of flags/extensions enabled. If
incompatible flags are enabled, return a conflict to have the caller
create a distinct socket with distinct port.

The OVS VXLAN port is kept unaware of extensions at this point.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 29 ++++++++++++++++++-----------
 include/net/vxlan.h |  3 +++
 2 files changed, 21 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 6dbf8e04192..6b6b45622a0 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -263,15 +263,19 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
 	return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
 }
 
-/* Find VXLAN socket based on network namespace, address family and UDP port */
-static struct vxlan_sock *vxlan_find_sock(struct net *net,
-					  sa_family_t family, __be16 port)
+/* Find VXLAN socket based on network namespace, address family and UDP port
+ * and enabled unshareable flags.
+ */
+static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
+					  __be16 port, u32 flags)
 {
 	struct vxlan_sock *vs;
+	u32 match_flags = flags & VXLAN_F_UNSHAREABLE;
 
 	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
 		if (inet_sk(vs->sock->sk)->inet_sport == port &&
-		    inet_sk(vs->sock->sk)->sk.sk_family == family)
+		    inet_sk(vs->sock->sk)->sk.sk_family == family &&
+		    (vs->flags & VXLAN_F_UNSHAREABLE) == match_flags)
 			return vs;
 	}
 	return NULL;
@@ -291,11 +295,12 @@ static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id)
 
 /* Look up VNI in a per net namespace table */
 static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id,
-					sa_family_t family, __be16 port)
+					sa_family_t family, __be16 port,
+					u32 flags)
 {
 	struct vxlan_sock *vs;
 
-	vs = vxlan_find_sock(net, family, port);
+	vs = vxlan_find_sock(net, family, port, flags);
 	if (!vs)
 		return NULL;
 
@@ -1957,7 +1962,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 			ip_rt_put(rt);
 			dst_vxlan = vxlan_find_vni(vxlan->net, vni,
-						   dst->sa.sa_family, dst_port);
+						   dst->sa.sa_family, dst_port,
+						   vxlan->flags);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -2016,7 +2022,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 			dst_release(ndst);
 			dst_vxlan = vxlan_find_vni(vxlan->net, vni,
-						   dst->sa.sa_family, dst_port);
+						   dst->sa.sa_family, dst_port,
+						   vxlan->flags);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -2186,7 +2193,7 @@ static int vxlan_init(struct net_device *dev)
 
 	spin_lock(&vn->sock_lock);
 	vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
-			     vxlan->dst_port);
+			     vxlan->dst_port, vxlan->flags);
 	if (vs && atomic_add_unless(&vs->refcnt, 1, 0)) {
 		/* If we have a socket with same port already, reuse it */
 		vxlan_vs_add_dev(vs, vxlan);
@@ -2593,7 +2600,7 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 		return vs;
 
 	spin_lock(&vn->sock_lock);
-	vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port);
+	vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port, flags);
 	if (vs && ((vs->rcv != rcv) ||
 		   !atomic_add_unless(&vs->refcnt, 1, 0)))
 			vs = ERR_PTR(-EBUSY);
@@ -2761,7 +2768,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 		vxlan->flags |= VXLAN_F_GBP;
 
 	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
-			   vxlan->dst_port)) {
+			   vxlan->dst_port, vxlan->flags)) {
 		pr_info("duplicate VNI %u\n", vni);
 		return -EEXIST;
 	}
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index f4a3583171b..7be8c342fc9 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -129,6 +129,9 @@ struct vxlan_sock {
 #define VXLAN_F_REMCSUM_RX		0x400
 #define VXLAN_F_GBP			0x800
 
+/* These flags must match in order for a socket to be shareable */
+#define VXLAN_F_UNSHAREABLE		VXLAN_F_GBP
+
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,
 				  bool no_share, u32 flags);
-- 
cgit v1.2.3-70-g09d2


From 1dd144cf5b4b47e12438c2c6883925ce1a9b499f Mon Sep 17 00:00:00 2001
From: Thomas Graf <tgraf@suug.ch>
Date: Thu, 15 Jan 2015 03:53:59 +0100
Subject: openvswitch: Support VXLAN Group Policy extension

Introduces support for the group policy extension to the VXLAN virtual
port. The extension is disabled by default and only enabled if the user
has provided the respective configuration.

  ovs-vsctl add-port br0 vxlan0 -- \
     set Interface vxlan0 type=vxlan options:exts=gbp

The configuration interface to enable the extension is based on a new
attribute OVS_VXLAN_EXT_GBP nested inside OVS_TUNNEL_ATTR_EXTENSION
which can carry additional extensions as needed in the future.

The group policy metadata is stored as binary blob (struct ovs_vxlan_opts)
internally just like Geneve options but transported as nested Netlink
attributes to user space.

Renames the existing TUNNEL_OPTIONS_PRESENT to TUNNEL_GENEVE_OPT with the
binary value kept intact, a new flag TUNNEL_VXLAN_OPT is introduced.

The attributes OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS and existing
OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS are implemented mutually exclusive.

Signed-off-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_tunnels.h         |   5 +-
 include/uapi/linux/openvswitch.h |  11 ++++
 net/openvswitch/flow_netlink.c   | 114 ++++++++++++++++++++++++++++++++++-----
 net/openvswitch/vport-geneve.c   |  15 ++++--
 net/openvswitch/vport-vxlan.c    |  82 +++++++++++++++++++++++++++-
 net/openvswitch/vport-vxlan.h    |  11 ++++
 6 files changed, 218 insertions(+), 20 deletions(-)
 create mode 100644 net/openvswitch/vport-vxlan.h

(limited to 'include')

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 25a59eb388a..ce4db3cc564 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -97,7 +97,10 @@ struct ip_tunnel {
 #define TUNNEL_DONT_FRAGMENT    __cpu_to_be16(0x0100)
 #define TUNNEL_OAM		__cpu_to_be16(0x0200)
 #define TUNNEL_CRIT_OPT		__cpu_to_be16(0x0400)
-#define TUNNEL_OPTIONS_PRESENT	__cpu_to_be16(0x0800)
+#define TUNNEL_GENEVE_OPT	__cpu_to_be16(0x0800)
+#define TUNNEL_VXLAN_OPT	__cpu_to_be16(0x1000)
+
+#define TUNNEL_OPTIONS_PRESENT	(TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT)
 
 struct tnl_ptk_info {
 	__be16 flags;
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index f714e863335..cd8d933963c 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -252,11 +252,21 @@ enum ovs_vport_attr {
 
 #define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1)
 
+enum {
+	OVS_VXLAN_EXT_UNSPEC,
+	OVS_VXLAN_EXT_GBP,	/* Flag or __u32 */
+	__OVS_VXLAN_EXT_MAX,
+};
+
+#define OVS_VXLAN_EXT_MAX (__OVS_VXLAN_EXT_MAX - 1)
+
+
 /* OVS_VPORT_ATTR_OPTIONS attributes for tunnels.
  */
 enum {
 	OVS_TUNNEL_ATTR_UNSPEC,
 	OVS_TUNNEL_ATTR_DST_PORT, /* 16-bit UDP port, used by L4 tunnels. */
+	OVS_TUNNEL_ATTR_EXTENSION,
 	__OVS_TUNNEL_ATTR_MAX
 };
 
@@ -328,6 +338,7 @@ enum ovs_tunnel_key_attr {
 	OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,        /* Array of Geneve options. */
 	OVS_TUNNEL_KEY_ATTR_TP_SRC,		/* be16 src Transport Port. */
 	OVS_TUNNEL_KEY_ATTR_TP_DST,		/* be16 dst Transport Port. */
+	OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS,		/* Nested OVS_VXLAN_EXT_* */
 	__OVS_TUNNEL_KEY_ATTR_MAX
 };
 
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 518941c5bdf..d210d1be347 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -49,6 +49,7 @@
 #include <net/mpls.h>
 
 #include "flow_netlink.h"
+#include "vport-vxlan.h"
 
 struct ovs_len_tbl {
 	int len;
@@ -268,6 +269,9 @@ size_t ovs_tun_key_attr_size(void)
 		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_CSUM */
 		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_OAM */
 		+ nla_total_size(256)  /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+		/* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS is mutually exclusive with
+		 * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it.
+		 */
 		+ nla_total_size(2)    /* OVS_TUNNEL_KEY_ATTR_TP_SRC */
 		+ nla_total_size(2);   /* OVS_TUNNEL_KEY_ATTR_TP_DST */
 }
@@ -308,6 +312,7 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1]
 	[OVS_TUNNEL_KEY_ATTR_TP_DST]	    = { .len = sizeof(u16) },
 	[OVS_TUNNEL_KEY_ATTR_OAM]	    = { .len = 0 },
 	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_NESTED },
+	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED },
 };
 
 /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
@@ -460,6 +465,41 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a,
 	return 0;
 }
 
+static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = {
+	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_U32 },
+};
+
+static int vxlan_tun_opt_from_nlattr(const struct nlattr *a,
+				     struct sw_flow_match *match, bool is_mask,
+				     bool log)
+{
+	struct nlattr *tb[OVS_VXLAN_EXT_MAX+1];
+	unsigned long opt_key_offset;
+	struct ovs_vxlan_opts opts;
+	int err;
+
+	BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));
+
+	err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy);
+	if (err < 0)
+		return err;
+
+	memset(&opts, 0, sizeof(opts));
+
+	if (tb[OVS_VXLAN_EXT_GBP])
+		opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]);
+
+	if (!is_mask)
+		SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false);
+	else
+		SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);
+
+	opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts));
+	SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts),
+				  is_mask);
+	return 0;
+}
+
 static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 				struct sw_flow_match *match, bool is_mask,
 				bool log)
@@ -468,6 +508,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 	int rem;
 	bool ttl = false;
 	__be16 tun_flags = 0;
+	int opts_type = 0;
 
 	nla_for_each_nested(a, attr, rem) {
 		int type = nla_type(a);
@@ -527,11 +568,30 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 			tun_flags |= TUNNEL_OAM;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+			if (opts_type) {
+				OVS_NLERR(log, "Multiple metadata blocks provided");
+				return -EINVAL;
+			}
+
 			err = genev_tun_opt_from_nlattr(a, match, is_mask, log);
 			if (err)
 				return err;
 
-			tun_flags |= TUNNEL_OPTIONS_PRESENT;
+			tun_flags |= TUNNEL_GENEVE_OPT;
+			opts_type = type;
+			break;
+		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+			if (opts_type) {
+				OVS_NLERR(log, "Multiple metadata blocks provided");
+				return -EINVAL;
+			}
+
+			err = vxlan_tun_opt_from_nlattr(a, match, is_mask, log);
+			if (err)
+				return err;
+
+			tun_flags |= TUNNEL_VXLAN_OPT;
+			opts_type = type;
 			break;
 		default:
 			OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
@@ -560,6 +620,23 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
 		}
 	}
 
+	return opts_type;
+}
+
+static int vxlan_opt_to_nlattr(struct sk_buff *skb,
+			       const void *tun_opts, int swkey_tun_opts_len)
+{
+	const struct ovs_vxlan_opts *opts = tun_opts;
+	struct nlattr *nla;
+
+	nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS);
+	if (!nla)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, OVS_VXLAN_EXT_GBP, opts->gbp) < 0)
+		return -EMSGSIZE;
+
+	nla_nest_end(skb, nla);
 	return 0;
 }
 
@@ -596,10 +673,15 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
 	if ((output->tun_flags & TUNNEL_OAM) &&
 	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
 		return -EMSGSIZE;
-	if (tun_opts &&
-	    nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
-		    swkey_tun_opts_len, tun_opts))
-		return -EMSGSIZE;
+	if (tun_opts) {
+		if (output->tun_flags & TUNNEL_GENEVE_OPT &&
+		    nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
+			    swkey_tun_opts_len, tun_opts))
+			return -EMSGSIZE;
+		else if (output->tun_flags & TUNNEL_VXLAN_OPT &&
+			 vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len))
+			return -EMSGSIZE;
+	}
 
 	return 0;
 }
@@ -680,7 +762,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 	}
 	if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) {
 		if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
-					 is_mask, log))
+					 is_mask, log) < 0)
 			return -EINVAL;
 		*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
 	}
@@ -1578,17 +1660,23 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	struct sw_flow_key key;
 	struct ovs_tunnel_info *tun_info;
 	struct nlattr *a;
-	int err, start;
+	int err, start, opts_type;
 
 	ovs_match_init(&match, &key, NULL);
-	err = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
-	if (err)
-		return err;
+	opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
+	if (opts_type < 0)
+		return opts_type;
 
 	if (key.tun_opts_len) {
-		err = validate_geneve_opts(&key);
-		if (err < 0)
-			return err;
+		switch (opts_type) {
+		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+			err = validate_geneve_opts(&key);
+			if (err < 0)
+				return err;
+			break;
+		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+			break;
+		}
 	};
 
 	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log);
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index 88a010c98c0..7ca3d454ff3 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -88,7 +88,7 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
 
 	opts_len = geneveh->opt_len * 4;
 
-	flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT |
+	flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
 		(udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) |
 		(geneveh->oam ? TUNNEL_OAM : 0) |
 		(geneveh->critical ? TUNNEL_CRIT_OPT : 0);
@@ -178,7 +178,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 	__be16 sport;
 	struct rtable *rt;
 	struct flowi4 fl;
-	u8 vni[3];
+	u8 vni[3], opts_len, *opts;
 	__be16 df;
 	int err;
 
@@ -200,11 +200,18 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 	tunnel_id_to_vni(tun_key->tun_id, vni);
 	skb->ignore_df = 1;
 
+	if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) {
+		opts = (u8 *)tun_info->options;
+		opts_len = tun_info->options_len;
+	} else {
+		opts = NULL;
+		opts_len = 0;
+	}
+
 	err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr,
 			      tun_key->ipv4_dst, tun_key->ipv4_tos,
 			      tun_key->ipv4_ttl, df, sport, dport,
-			      tun_key->tun_flags, vni,
-			      tun_info->options_len, (u8 *)tun_info->options,
+			      tun_key->tun_flags, vni, opts_len, opts,
 			      false);
 	if (err < 0)
 		ip_rt_put(rt);
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 9919d71c52c..8a2d54cba9b 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -40,6 +40,7 @@
 
 #include "datapath.h"
 #include "vport.h"
+#include "vport-vxlan.h"
 
 /**
  * struct vxlan_port - Keeps track of open UDP ports
@@ -49,6 +50,7 @@
 struct vxlan_port {
 	struct vxlan_sock *vs;
 	char name[IFNAMSIZ];
+	u32 exts; /* VXLAN_F_* in <net/vxlan.h> */
 };
 
 static struct vport_ops ovs_vxlan_vport_ops;
@@ -63,16 +65,26 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 		      struct vxlan_metadata *md)
 {
 	struct ovs_tunnel_info tun_info;
+	struct vxlan_port *vxlan_port;
 	struct vport *vport = vs->data;
 	struct iphdr *iph;
+	struct ovs_vxlan_opts opts = {
+		.gbp = md->gbp,
+	};
 	__be64 key;
+	__be16 flags;
+
+	flags = TUNNEL_KEY;
+	vxlan_port = vxlan_vport(vport);
+	if (vxlan_port->exts & VXLAN_F_GBP)
+		flags |= TUNNEL_VXLAN_OPT;
 
 	/* Save outer tunnel values */
 	iph = ip_hdr(skb);
 	key = cpu_to_be64(ntohl(md->vni) >> 8);
 	ovs_flow_tun_info_init(&tun_info, iph,
 			       udp_hdr(skb)->source, udp_hdr(skb)->dest,
-			       key, TUNNEL_KEY, NULL, 0);
+			       key, flags, &opts, sizeof(opts));
 
 	ovs_vport_receive(vport, skb, &tun_info);
 }
@@ -84,6 +96,21 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
 
 	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
 		return -EMSGSIZE;
+
+	if (vxlan_port->exts) {
+		struct nlattr *exts;
+
+		exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION);
+		if (!exts)
+			return -EMSGSIZE;
+
+		if (vxlan_port->exts & VXLAN_F_GBP &&
+		    nla_put_flag(skb, OVS_VXLAN_EXT_GBP))
+			return -EMSGSIZE;
+
+		nla_nest_end(skb, exts);
+	}
+
 	return 0;
 }
 
@@ -96,6 +123,31 @@ static void vxlan_tnl_destroy(struct vport *vport)
 	ovs_vport_deferred_free(vport);
 }
 
+static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = {
+	[OVS_VXLAN_EXT_GBP]	= { .type = NLA_FLAG, },
+};
+
+static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr)
+{
+	struct nlattr *exts[OVS_VXLAN_EXT_MAX+1];
+	struct vxlan_port *vxlan_port;
+	int err;
+
+	if (nla_len(attr) < sizeof(struct nlattr))
+		return -EINVAL;
+
+	err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy);
+	if (err < 0)
+		return err;
+
+	vxlan_port = vxlan_vport(vport);
+
+	if (exts[OVS_VXLAN_EXT_GBP])
+		vxlan_port->exts |= VXLAN_F_GBP;
+
+	return 0;
+}
+
 static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 {
 	struct net *net = ovs_dp_get_net(parms->dp);
@@ -128,7 +180,17 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	vxlan_port = vxlan_vport(vport);
 	strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
 
-	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0);
+	a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION);
+	if (a) {
+		err = vxlan_configure_exts(vport, a);
+		if (err) {
+			ovs_vport_free(vport);
+			goto error;
+		}
+	}
+
+	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true,
+			    vxlan_port->exts);
 	if (IS_ERR(vs)) {
 		ovs_vport_free(vport);
 		return (void *)vs;
@@ -141,6 +203,21 @@ error:
 	return ERR_PTR(err);
 }
 
+static int vxlan_ext_gbp(struct sk_buff *skb)
+{
+	const struct ovs_tunnel_info *tun_info;
+	const struct ovs_vxlan_opts *opts;
+
+	tun_info = OVS_CB(skb)->egress_tun_info;
+	opts = tun_info->options;
+
+	if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT &&
+	    tun_info->options_len >= sizeof(*opts))
+		return opts->gbp;
+	else
+		return 0;
+}
+
 static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
 	struct net *net = ovs_dp_get_net(vport->dp);
@@ -173,6 +250,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 
 	src_port = udp_flow_src_port(net, skb, 0, 0, true);
 	md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
+	md.gbp = vxlan_ext_gbp(skb);
 
 	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
 			     fl.saddr, tun_key->ipv4_dst,
diff --git a/net/openvswitch/vport-vxlan.h b/net/openvswitch/vport-vxlan.h
new file mode 100644
index 00000000000..4b08233e73d
--- /dev/null
+++ b/net/openvswitch/vport-vxlan.h
@@ -0,0 +1,11 @@
+#ifndef VPORT_VXLAN_H
+#define VPORT_VXLAN_H 1
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+struct ovs_vxlan_opts {
+	__u32 gbp;
+};
+
+#endif
-- 
cgit v1.2.3-70-g09d2


From c38fda3fe8163898f538a45d3c1419e6870625ed Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Wed, 14 Jan 2015 22:59:13 -0800
Subject: jbd: drop jbd_ENOSYS debug

A quick search shows that there are no users, drop the
macro for both jbd and jbd2.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 include/linux/jbd.h  | 9 ---------
 include/linux/jbd2.h | 9 ---------
 2 files changed, 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 31229e0be90..d32615280be 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -956,15 +956,6 @@ void __log_wait_for_space(journal_t *journal);
 extern void	__journal_drop_transaction(journal_t *, transaction_t *);
 extern int	cleanup_journal_tail(journal_t *);
 
-/* Debugging code only: */
-
-#define jbd_ENOSYS() \
-do {								           \
-	printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \
-	current->state = TASK_UNINTERRUPTIBLE;			           \
-	schedule();						           \
-} while (1)
-
 /*
  * is_journal_abort
  *
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 704b9a599b2..20e7f78041c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1251,15 +1251,6 @@ void __jbd2_log_wait_for_space(journal_t *journal);
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
 extern int jbd2_cleanup_journal_tail(journal_t *);
 
-/* Debugging code only: */
-
-#define jbd_ENOSYS() \
-do {								           \
-	printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \
-	current->state = TASK_UNINTERRUPTIBLE;			           \
-	schedule();						           \
-} while (1)
-
 /*
  * is_journal_abort
  *
-- 
cgit v1.2.3-70-g09d2


From 37715f556a0776356300391f8ac41ace91bea447 Mon Sep 17 00:00:00 2001
From: David Ung <davidu@nvidia.com>
Date: Tue, 13 Jan 2015 19:04:25 -0800
Subject: video: fbdev: Add additional vesa modes

Add high resolution modes to vesa_modes struct.

Signed-off-by: David Ung <davidu@nvidia.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/fbdev/core/modedb.c | 27 +++++++++++++++++++++++++++
 include/linux/fb.h                |  2 +-
 2 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c
index 388f7971494..0b57c1df73e 100644
--- a/drivers/video/fbdev/core/modedb.c
+++ b/drivers/video/fbdev/core/modedb.c
@@ -468,6 +468,33 @@ const struct fb_videomode vesa_modes[] = {
 	/* 33 1920x1440-75 VESA */
 	{ NULL, 75, 1920, 1440, 3367, 352, 144, 56, 1, 224, 3,
 	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 34 1920x1200-60 RB VESA */
+	{ NULL, 60, 1920, 1200, 6493, 80, 48, 26, 3, 32, 6,
+	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 35 1920x1200-60 VESA */
+	{ NULL, 60, 1920, 1200, 5174, 336, 136, 36, 3, 200, 6,
+	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 36 1920x1200-75 VESA */
+	{ NULL, 75, 1920, 1200, 4077, 344, 136, 46, 3, 208, 6,
+	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 37 1920x1200-85 VESA */
+	{ NULL, 85, 1920, 1200, 3555, 352, 144, 53, 3, 208, 6,
+	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 38 2560x1600-60 RB VESA */
+	{ NULL, 60, 2560, 1600, 3724, 80, 48, 37, 3, 32, 6,
+	  FB_SYNC_HOR_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 39 2560x1600-60 VESA */
+	{ NULL, 60, 2560, 1600, 2869, 472, 192, 49, 3, 280, 6,
+	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 40 2560x1600-75 VESA */
+	{ NULL, 75, 2560, 1600, 2256, 488, 208, 63, 3, 280, 6,
+	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 41 2560x1600-85 VESA */
+	{ NULL, 85, 2560, 1600, 1979, 488, 208, 73, 3, 280, 6,
+	  FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
+	/* 42 2560x1600-120 RB VESA */
+	{ NULL, 120, 2560, 1600, 1809, 80, 48, 85, 3, 32, 6,
+	  FB_SYNC_HOR_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
 };
 EXPORT_SYMBOL(vesa_modes);
 #endif /* CONFIG_FB_MODE_HELPERS */
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 09bb7a18d28..882dbd1a87b 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -726,7 +726,7 @@ extern int fb_videomode_from_videomode(const struct videomode *vm,
 				       struct fb_videomode *fbmode);
 
 /* drivers/video/modedb.c */
-#define VESA_MODEDB_SIZE 34
+#define VESA_MODEDB_SIZE 43
 extern void fb_var_to_videomode(struct fb_videomode *mode,
 				const struct fb_var_screeninfo *var);
 extern void fb_videomode_to_var(struct fb_var_screeninfo *var,
-- 
cgit v1.2.3-70-g09d2


From 8f5ee77bb8d162abe28ff8cd56f36e825d143207 Mon Sep 17 00:00:00 2001
From: David Ung <davidu@nvidia.com>
Date: Tue, 13 Jan 2015 19:04:26 -0800
Subject: video: fbdev: Check Standard Timing against DMT

Add the VESA Display Monitor Timing (DMT) table.
During parsing of Standard Timings, it compare the 2 byte STD code
with DMT to see what the VESA mode should be.  If there is no entry
in the vesa_modes table or no match found, it fallsback to the
GTF timings.

Signed-off-by: David Ung <davidu@nvidia.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/fbdev/core/fbmon.c  | 76 +++++++++++++++++++----------------
 drivers/video/fbdev/core/modedb.c | 84 +++++++++++++++++++++++++++++++++++++++
 include/linux/fb.h                | 10 +++++
 3 files changed, 136 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c
index 5b0e313849b..0f234c15ece 100644
--- a/drivers/video/fbdev/core/fbmon.c
+++ b/drivers/video/fbdev/core/fbmon.c
@@ -498,44 +498,52 @@ static int get_est_timing(unsigned char *block, struct fb_videomode *mode)
 static int get_std_timing(unsigned char *block, struct fb_videomode *mode,
 		int ver, int rev)
 {
-	int xres, yres = 0, refresh, ratio, i;
-
-	xres = (block[0] + 31) * 8;
-	if (xres <= 256)
-		return 0;
+	int i;
 
-	ratio = (block[1] & 0xc0) >> 6;
-	switch (ratio) {
-	case 0:
-		/* in EDID 1.3 the meaning of 0 changed to 16:10 (prior 1:1) */
-		if (ver < 1 || (ver == 1 && rev < 3))
-			yres = xres;
-		else
-			yres = (xres * 10)/16;
-		break;
-	case 1:
-		yres = (xres * 3)/4;
-		break;
-	case 2:
-		yres = (xres * 4)/5;
-		break;
-	case 3:
-		yres = (xres * 9)/16;
-		break;
+	for (i = 0; i < DMT_SIZE; i++) {
+		u32 std_2byte_code = block[0] << 8 | block[1];
+		if (std_2byte_code == dmt_modes[i].std_2byte_code)
+			break;
 	}
-	refresh = (block[1] & 0x3f) + 60;
-
-	DPRINTK("      %dx%d@%dHz\n", xres, yres, refresh);
-	for (i = 0; i < VESA_MODEDB_SIZE; i++) {
-		if (vesa_modes[i].xres == xres &&
-		    vesa_modes[i].yres == yres &&
-		    vesa_modes[i].refresh == refresh) {
-			*mode = vesa_modes[i];
-			mode->flag |= FB_MODE_IS_STANDARD;
-			return 1;
+
+	if (i < DMT_SIZE && dmt_modes[i].mode) {
+		/* DMT mode found */
+		*mode = *dmt_modes[i].mode;
+		mode->flag |= FB_MODE_IS_STANDARD;
+		DPRINTK("        DMT id=%d\n", dmt_modes[i].dmt_id);
+
+	} else {
+		int xres, yres = 0, refresh, ratio;
+
+		xres = (block[0] + 31) * 8;
+		if (xres <= 256)
+			return 0;
+
+		ratio = (block[1] & 0xc0) >> 6;
+		switch (ratio) {
+		case 0:
+			/* in EDID 1.3 the meaning of 0 changed to 16:10 (prior 1:1) */
+			if (ver < 1 || (ver == 1 && rev < 3))
+				yres = xres;
+			else
+				yres = (xres * 10)/16;
+			break;
+		case 1:
+			yres = (xres * 3)/4;
+			break;
+		case 2:
+			yres = (xres * 4)/5;
+			break;
+		case 3:
+			yres = (xres * 9)/16;
+			break;
 		}
+		refresh = (block[1] & 0x3f) + 60;
+		DPRINTK("      %dx%d@%dHz\n", xres, yres, refresh);
+
+		calc_mode_timings(xres, yres, refresh, mode);
 	}
-	calc_mode_timings(xres, yres, refresh, mode);
+
 	return 1;
 }
 
diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c
index 0b57c1df73e..858a97e0320 100644
--- a/drivers/video/fbdev/core/modedb.c
+++ b/drivers/video/fbdev/core/modedb.c
@@ -497,6 +497,90 @@ const struct fb_videomode vesa_modes[] = {
 	  FB_SYNC_HOR_HIGH_ACT, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA },
 };
 EXPORT_SYMBOL(vesa_modes);
+
+const struct dmt_videomode dmt_modes[DMT_SIZE] = {
+	{ 0x01, 0x0000, 0x000000, &vesa_modes[0] },
+	{ 0x02, 0x3119, 0x000000, &vesa_modes[1] },
+	{ 0x03, 0x0000, 0x000000, &vesa_modes[2] },
+	{ 0x04, 0x3140, 0x000000, &vesa_modes[3] },
+	{ 0x05, 0x314c, 0x000000, &vesa_modes[4] },
+	{ 0x06, 0x314f, 0x000000, &vesa_modes[5] },
+	{ 0x07, 0x3159, 0x000000, &vesa_modes[6] },
+	{ 0x08, 0x0000, 0x000000, &vesa_modes[7] },
+	{ 0x09, 0x4540, 0x000000, &vesa_modes[8] },
+	{ 0x0a, 0x454c, 0x000000, &vesa_modes[9] },
+	{ 0x0b, 0x454f, 0x000000, &vesa_modes[10] },
+	{ 0x0c, 0x4559, 0x000000, &vesa_modes[11] },
+	{ 0x0d, 0x0000, 0x000000, 0 },
+	{ 0x0e, 0x0000, 0x000000, 0 },
+	{ 0x0f, 0x0000, 0x000000, &vesa_modes[12] },
+	{ 0x10, 0x6140, 0x000000, &vesa_modes[13] },
+	{ 0x11, 0x614a, 0x000000, &vesa_modes[14] },
+	{ 0x12, 0x614f, 0x000000, &vesa_modes[15] },
+	{ 0x13, 0x6159, 0x000000, &vesa_modes[16] },
+	{ 0x14, 0x0000, 0x000000, 0 },
+	{ 0x15, 0x714f, 0x000000, &vesa_modes[17] },
+	{ 0x16, 0x0000, 0x7f1c21, 0 },
+	{ 0x17, 0x0000, 0x7f1c28, 0 },
+	{ 0x18, 0x0000, 0x7f1c44, 0 },
+	{ 0x19, 0x0000, 0x7f1c62, 0 },
+	{ 0x1a, 0x0000, 0x000000, 0 },
+	{ 0x1b, 0x0000, 0x8f1821, 0 },
+	{ 0x1c, 0x8100, 0x8f1828, 0 },
+	{ 0x1d, 0x810f, 0x8f1844, 0 },
+	{ 0x1e, 0x8119, 0x8f1862, 0 },
+	{ 0x1f, 0x0000, 0x000000, 0 },
+	{ 0x20, 0x8140, 0x000000, &vesa_modes[18] },
+	{ 0x21, 0x8159, 0x000000, &vesa_modes[19] },
+	{ 0x22, 0x0000, 0x000000, 0 },
+	{ 0x23, 0x8180, 0x000000, &vesa_modes[20] },
+	{ 0x24, 0x818f, 0x000000, &vesa_modes[21] },
+	{ 0x25, 0x8199, 0x000000, &vesa_modes[22] },
+	{ 0x26, 0x0000, 0x000000, 0 },
+	{ 0x27, 0x0000, 0x000000, 0 },
+	{ 0x28, 0x0000, 0x000000, 0 },
+	{ 0x29, 0x0000, 0x0c2021, 0 },
+	{ 0x2a, 0x9040, 0x0c2028, 0 },
+	{ 0x2b, 0x904f, 0x0c2044, 0 },
+	{ 0x2c, 0x9059, 0x0c2062, 0 },
+	{ 0x2d, 0x0000, 0x000000, 0 },
+	{ 0x2e, 0x9500, 0xc11821, 0 },
+	{ 0x2f, 0x9500, 0xc11828, 0 },
+	{ 0x30, 0x950f, 0xc11844, 0 },
+	{ 0x31, 0x9519, 0xc11868, 0 },
+	{ 0x32, 0x0000, 0x000000, 0 },
+	{ 0x33, 0xa940, 0x000000, &vesa_modes[23] },
+	{ 0x34, 0xa945, 0x000000, &vesa_modes[24] },
+	{ 0x35, 0xa94a, 0x000000, &vesa_modes[25] },
+	{ 0x36, 0xa94f, 0x000000, &vesa_modes[26] },
+	{ 0x37, 0xa959, 0x000000, &vesa_modes[27] },
+	{ 0x38, 0x0000, 0x000000, 0 },
+	{ 0x39, 0x0000, 0x0c2821, 0 },
+	{ 0x3a, 0xb300, 0x0c2828, 0 },
+	{ 0x3b, 0xb30f, 0x0c2844, 0 },
+	{ 0x3c, 0xb319, 0x0c2868, 0 },
+	{ 0x3d, 0x0000, 0x000000, 0 },
+	{ 0x3e, 0xc140, 0x000000, &vesa_modes[28] },
+	{ 0x3f, 0xc14f, 0x000000, &vesa_modes[29] },
+	{ 0x40, 0x0000, 0x000000, 0 },
+	{ 0x41, 0xc940, 0x000000, &vesa_modes[30] },
+	{ 0x42, 0xc94f, 0x000000, &vesa_modes[31] },
+	{ 0x43, 0x0000, 0x000000, 0 },
+	{ 0x44, 0x0000, 0x572821, &vesa_modes[34] },
+	{ 0x45, 0xd100, 0x572828, &vesa_modes[35] },
+	{ 0x46, 0xd10f, 0x572844, &vesa_modes[36] },
+	{ 0x47, 0xd119, 0x572862, &vesa_modes[37] },
+	{ 0x48, 0x0000, 0x000000, 0 },
+	{ 0x49, 0xd140, 0x000000, &vesa_modes[32] },
+	{ 0x4a, 0xd14f, 0x000000, &vesa_modes[33] },
+	{ 0x4b, 0x0000, 0x000000, 0 },
+	{ 0x4c, 0x0000, 0x1f3821, &vesa_modes[38] },
+	{ 0x4d, 0x0000, 0x1f3828, &vesa_modes[39] },
+	{ 0x4e, 0x0000, 0x1f3844, &vesa_modes[40] },
+	{ 0x4f, 0x0000, 0x1f3862, &vesa_modes[41] },
+	{ 0x50, 0x0000, 0x000000, &vesa_modes[42] },
+};
+EXPORT_SYMBOL(dmt_modes);
 #endif /* CONFIG_FB_MODE_HELPERS */
 
 /**
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 882dbd1a87b..043f3283b71 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -727,6 +727,8 @@ extern int fb_videomode_from_videomode(const struct videomode *vm,
 
 /* drivers/video/modedb.c */
 #define VESA_MODEDB_SIZE 43
+#define DMT_SIZE 0x50
+
 extern void fb_var_to_videomode(struct fb_videomode *mode,
 				const struct fb_var_screeninfo *var);
 extern void fb_videomode_to_var(struct fb_var_screeninfo *var,
@@ -777,9 +779,17 @@ struct fb_videomode {
 	u32 flag;
 };
 
+struct dmt_videomode {
+	u32 dmt_id;
+	u32 std_2byte_code;
+	u32 cvt_3byte_code;
+	const struct fb_videomode *mode;
+};
+
 extern const char *fb_mode_option;
 extern const struct fb_videomode vesa_modes[];
 extern const struct fb_videomode cea_modes[64];
+extern const struct dmt_videomode dmt_modes[];
 
 struct fb_modelist {
 	struct list_head list;
-- 
cgit v1.2.3-70-g09d2


From f9911803e82a32c126c40dd6246ade2faf472cbc Mon Sep 17 00:00:00 2001
From: Jyri Sarha <jsarha@ti.com>
Date: Tue, 13 Jan 2015 21:16:34 +0200
Subject: ASoC: simple-card: Enable and disable DAI clocks as needed

Call clk_prepare_enable() and clk_disable_unprepare() for cpu dai
clock and codec dai clock in dai statup and shutdown callbacks. This
to make sure the related clock are enabled when the audio device is
used.

Signed-off-by: Jyri Sarha <jsarha@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/simple-card.txt      |  5 ++++
 include/sound/simple_card.h                        |  1 +
 sound/soc/generic/simple-card.c                    | 34 ++++++++++++++++++++++
 3 files changed, 40 insertions(+)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/simple-card.txt b/Documentation/devicetree/bindings/sound/simple-card.txt
index c3cba600bf1..73bf314f724 100644
--- a/Documentation/devicetree/bindings/sound/simple-card.txt
+++ b/Documentation/devicetree/bindings/sound/simple-card.txt
@@ -75,6 +75,11 @@ Optional CPU/CODEC subnodes properties:
 					  it can be specified via "clocks" if system has
 					  clock node (= common clock), or "system-clock-frequency"
 					  (if system doens't support common clock)
+					  If a clock is specified, it is
+					  enabled with clk_prepare_enable()
+					  in dai startup() and disabled with
+					  clk_disable_unprepare() in dai
+					  shutdown().
 
 Example 1 - single DAI link:
 
diff --git a/include/sound/simple_card.h b/include/sound/simple_card.h
index 9b0ac77177b..1255ddb1d3e 100644
--- a/include/sound/simple_card.h
+++ b/include/sound/simple_card.h
@@ -20,6 +20,7 @@ struct asoc_simple_dai {
 	unsigned int sysclk;
 	int slots;
 	int slot_width;
+	struct clk *clk;
 };
 
 struct asoc_simple_card_info {
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index fb9240fdc9b..cb3998d96cc 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -39,6 +39,37 @@ struct simple_card_data {
 #define simple_priv_to_link(priv, i) ((priv)->snd_card.dai_link + i)
 #define simple_priv_to_props(priv, i) ((priv)->dai_props + i)
 
+static int asoc_simple_card_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct simple_card_data *priv =	snd_soc_card_get_drvdata(rtd->card);
+	struct simple_dai_props *dai_props =
+		&priv->dai_props[rtd - rtd->card->rtd];
+	int ret;
+
+	ret = clk_prepare_enable(dai_props->cpu_dai.clk);
+	if (ret)
+		return ret;
+	
+	ret = clk_prepare_enable(dai_props->codec_dai.clk);
+	if (ret)
+		clk_disable_unprepare(dai_props->cpu_dai.clk);
+
+	return ret;
+}
+
+static void asoc_simple_card_shutdown(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct simple_card_data *priv =	snd_soc_card_get_drvdata(rtd->card);
+	struct simple_dai_props *dai_props =
+		&priv->dai_props[rtd - rtd->card->rtd];
+
+	clk_disable_unprepare(dai_props->cpu_dai.clk);
+
+	clk_disable_unprepare(dai_props->codec_dai.clk);
+}
+
 static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 				      struct snd_pcm_hw_params *params)
 {
@@ -58,6 +89,8 @@ static int asoc_simple_card_hw_params(struct snd_pcm_substream *substream,
 }
 
 static struct snd_soc_ops asoc_simple_card_ops = {
+	.startup = asoc_simple_card_startup,
+	.shutdown = asoc_simple_card_shutdown,
 	.hw_params = asoc_simple_card_hw_params,
 };
 
@@ -219,6 +252,7 @@ asoc_simple_card_sub_parse_of(struct device_node *np,
 		}
 
 		dai->sysclk = clk_get_rate(clk);
+		dai->clk = clk;
 	} else if (!of_property_read_u32(np, "system-clock-frequency", &val)) {
 		dai->sysclk = val;
 	} else {
-- 
cgit v1.2.3-70-g09d2


From 96da4e5b2e1d04478fb6d540085f2859256ca788 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Thu, 15 Jan 2015 12:52:17 +0100
Subject: ASoC: Remove codec field from snd_soc_dapm_widget

There are no more users of this field left so it can finally be removed.
New users should use snd_soc_dapm_to_codec(w->dapm);

The reason why it is removed is because it doesn't fit to well anymore in
the componentized ASoC hierarchy, where DAPM works on the snd_soc_component
level. And the alternative of snd_soc_dapm_to_codec(w->dapm) typically
generates the same amount of code, so there is really no reason to keep it.

For automatic conversion the following coccinelle semantic patch can be used:
// <smpl>
@@
struct snd_soc_dapm_widget *w;
@@
-w->codec
+snd_soc_dapm_to_codec(w->dapm)
// </smpl>

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h | 1 -
 sound/soc/soc-dapm.c     | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 89823cfe6f0..cc7104ab966 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -526,7 +526,6 @@ struct snd_soc_dapm_widget {
 	enum snd_soc_dapm_type id;
 	const char *name;		/* widget name */
 	const char *sname;	/* stream name */
-	struct snd_soc_codec *codec;
 	struct list_head list;
 	struct snd_soc_dapm_context *dapm;
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c5136bb1f98..f6ae254e33e 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3130,8 +3130,6 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
 	}
 
 	w->dapm = dapm;
-	if (dapm->component)
-		w->codec = dapm->component->codec;
 	INIT_LIST_HEAD(&w->sources);
 	INIT_LIST_HEAD(&w->sinks);
 	INIT_LIST_HEAD(&w->list);
-- 
cgit v1.2.3-70-g09d2


From f89903d53f4d39577be98940f7cfa49d66f86db5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 15 Jan 2015 16:02:46 +0100
Subject: mac80211: remove 80+80 MHz rate reporting

These rates are treated the same as 160 MHz in the spec,
so it makes no sense to distinguish them. As no driver
uses them yet, this is also not a problem, just remove
them.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 6 ++----
 net/mac80211/cfg.c     | 2 --
 net/mac80211/rx.c      | 5 -----
 net/mac80211/util.c    | 2 --
 4 files changed, 2 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 123f2308958..275ee56152a 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -931,15 +931,13 @@ enum mac80211_rx_flags {
  * These flags are used with the @vht_flag member of
  *	&struct ieee80211_rx_status.
  * @RX_VHT_FLAG_80MHZ: 80 MHz was used
- * @RX_VHT_FLAG_80P80MHZ: 80+80 MHz was used
  * @RX_VHT_FLAG_160MHZ: 160 MHz was used
  * @RX_VHT_FLAG_BF: packet was beamformed
  */
 enum mac80211_rx_vht_flags {
 	RX_VHT_FLAG_80MHZ		= BIT(0),
-	RX_VHT_FLAG_80P80MHZ		= BIT(1),
-	RX_VHT_FLAG_160MHZ		= BIT(2),
-	RX_VHT_FLAG_BF			= BIT(3),
+	RX_VHT_FLAG_160MHZ		= BIT(1),
+	RX_VHT_FLAG_BF			= BIT(2),
 };
 
 /**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index fd6860d7f55..6d5076fbf87 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -465,8 +465,6 @@ void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo)
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
 	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80MHZ)
 		rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80P80MHZ)
-		rinfo->flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
 	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_160MHZ)
 		rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
 }
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3a1a3ba40bd..3d79d498e7f 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -361,9 +361,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		u16 known = local->hw.radiotap_vht_details;
 
 		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_VHT);
-		/* known field - how to handle 80+80? */
-		if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
-			known &= ~IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH;
 		put_unaligned_le16(known, pos);
 		pos += 2;
 		/* flags */
@@ -378,8 +375,6 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		/* bandwidth */
 		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
 			*pos++ = 4;
-		else if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
-			*pos++ = 0; /* marked not known above */
 		else if (status->vht_flag & RX_VHT_FLAG_160MHZ)
 			*pos++ = 11;
 		else if (status->flag & RX_FLAG_40MHZ)
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 83ba6cd9cf8..db721612473 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2552,8 +2552,6 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
 		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
 			ri.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-		if (status->vht_flag & RX_VHT_FLAG_80P80MHZ)
-			ri.flags |= RATE_INFO_FLAGS_80P80_MHZ_WIDTH;
 		if (status->vht_flag & RX_VHT_FLAG_160MHZ)
 			ri.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
 		if (status->flag & RX_FLAG_SHORT_GI)
-- 
cgit v1.2.3-70-g09d2


From 97d910d0aaa619ca530d08e2b1125b8014ccb030 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 15 Jan 2015 16:05:21 +0100
Subject: cfg80211: remove 80+80 MHz rate reporting

These rates are treated the same as 160 MHz in the spec, so
it makes no sense to distinguish them. As no driver uses them
yet, this is also not a problem, just remove them.

In the userspace API the field remains reserved to preserve
API and ABI.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 8 +++-----
 include/uapi/linux/nl80211.h | 3 ++-
 net/wireless/nl80211.c       | 3 ---
 net/wireless/util.c          | 3 +--
 4 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 38abc07503f..0322048fdda 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -875,7 +875,6 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
  * @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS
  * @RATE_INFO_FLAGS_40_MHZ_WIDTH: 40 MHz width transmission
  * @RATE_INFO_FLAGS_80_MHZ_WIDTH: 80 MHz width transmission
- * @RATE_INFO_FLAGS_80P80_MHZ_WIDTH: 80+80 MHz width transmission
  * @RATE_INFO_FLAGS_160_MHZ_WIDTH: 160 MHz width transmission
  * @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval
  * @RATE_INFO_FLAGS_60G: 60GHz MCS
@@ -885,10 +884,9 @@ enum rate_info_flags {
 	RATE_INFO_FLAGS_VHT_MCS			= BIT(1),
 	RATE_INFO_FLAGS_40_MHZ_WIDTH		= BIT(2),
 	RATE_INFO_FLAGS_80_MHZ_WIDTH		= BIT(3),
-	RATE_INFO_FLAGS_80P80_MHZ_WIDTH		= BIT(4),
-	RATE_INFO_FLAGS_160_MHZ_WIDTH		= BIT(5),
-	RATE_INFO_FLAGS_SHORT_GI		= BIT(6),
-	RATE_INFO_FLAGS_60G			= BIT(7),
+	RATE_INFO_FLAGS_160_MHZ_WIDTH		= BIT(4),
+	RATE_INFO_FLAGS_SHORT_GI		= BIT(5),
+	RATE_INFO_FLAGS_60G			= BIT(6),
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index b6c1a00bd8d..11cdb85ac64 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2278,7 +2278,8 @@ struct nl80211_sta_flag_update {
  * @NL80211_RATE_INFO_VHT_MCS: MCS index for VHT (u8)
  * @NL80211_RATE_INFO_VHT_NSS: number of streams in VHT (u8)
  * @NL80211_RATE_INFO_80_MHZ_WIDTH: 80 MHz VHT rate
- * @NL80211_RATE_INFO_80P80_MHZ_WIDTH: 80+80 MHz VHT rate
+ * @NL80211_RATE_INFO_80P80_MHZ_WIDTH: unused - 80+80 is treated the
+ *	same as 160 for purposes of the bitrates
  * @NL80211_RATE_INFO_160_MHZ_WIDTH: 160 MHz VHT rate
  * @__NL80211_RATE_INFO_AFTER_LAST: internal use
  */
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 380784378df..8998484ea97 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3614,9 +3614,6 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 		if (info->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH &&
 		    nla_put_flag(msg, NL80211_RATE_INFO_80_MHZ_WIDTH))
 			return false;
-		if (info->flags & RATE_INFO_FLAGS_80P80_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_80P80_MHZ_WIDTH))
-			return false;
 		if (info->flags & RATE_INFO_FLAGS_160_MHZ_WIDTH &&
 		    nla_put_flag(msg, NL80211_RATE_INFO_160_MHZ_WIDTH))
 			return false;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index d0ac795445b..6942d48f1ac 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1073,8 +1073,7 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
 	if (WARN_ON_ONCE(rate->mcs > 9))
 		return 0;
 
-	idx = rate->flags & (RATE_INFO_FLAGS_160_MHZ_WIDTH |
-			     RATE_INFO_FLAGS_80P80_MHZ_WIDTH) ? 3 :
+	idx = rate->flags & RATE_INFO_FLAGS_160_MHZ_WIDTH ? 3 :
 		  rate->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH ? 2 :
 		  rate->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH ? 1 : 0;
 
-- 
cgit v1.2.3-70-g09d2


From 6cfda7fbebe8a4fd33ea5722fa0212f98f643c35 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 5 Jan 2015 19:47:43 +0100
Subject: can: m_can: tag current CAN FD controllers as non-ISO

During the CAN FD standardization process within the ISO it turned out that
the failure detection capability has to be improved.

The CAN in Automation organization (CiA) defined the already implemented CAN
FD controllers as 'non-ISO' and the upcoming improved CAN FD controllers as
'ISO' compliant. See at http://www.can-cia.com/index.php?id=1937

Finally there will be three types of CAN FD controllers in the future:

1. ISO compliant (fixed)
2. non-ISO compliant (fixed, like the M_CAN IP v3.0.1 in m_can.c)
3. ISO/non-ISO CAN FD controllers (switchable, like the PEAK USB FD)

So the current M_CAN driver for the M_CAN IP v3.0.1 has to expose its non-ISO
implementation by setting the CAN_CTRLMODE_FD_NON_ISO ctrlmode at startup.
As this bit cannot be switched at configuration time CAN_CTRLMODE_FD_NON_ISO
must not be set in ctrlmode_supported of the current M_CAN driver.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Cc: linux-stable <stable@vger.kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c    | 5 +++++
 include/uapi/linux/can/netlink.h | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index d7bc462aafd..244529881be 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -955,6 +955,11 @@ static struct net_device *alloc_m_can_dev(void)
 	priv->can.data_bittiming_const = &m_can_data_bittiming_const;
 	priv->can.do_set_mode = m_can_set_mode;
 	priv->can.do_get_berr_counter = m_can_get_berr_counter;
+
+	/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.1 */
+	priv->can.ctrlmode = CAN_CTRLMODE_FD_NON_ISO;
+
+	/* CAN_CTRLMODE_FD_NON_ISO can not be changed with M_CAN IP v3.0.1 */
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 					CAN_CTRLMODE_LISTENONLY |
 					CAN_CTRLMODE_BERR_REPORTING |
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index 3e4323a3918..94ffe0c83ce 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -98,6 +98,7 @@ struct can_ctrlmode {
 #define CAN_CTRLMODE_BERR_REPORTING	0x10	/* Bus-error reporting */
 #define CAN_CTRLMODE_FD			0x20	/* CAN FD mode */
 #define CAN_CTRLMODE_PRESUME_ACK	0x40	/* Ignore missing CAN ACKs */
+#define CAN_CTRLMODE_FD_NON_ISO		0x80	/* CAN FD in non-ISO mode */
 
 /*
  * CAN device statistics
-- 
cgit v1.2.3-70-g09d2


From d621e8bae5ac9c67de4de90c5cded12adc8ee1e1 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Date: Wed, 17 Dec 2014 16:51:13 +0100
Subject: gpio/gpiolib-of: Create of_mm_gpiochip_remove

Create counterpart of of_mm_gpiochip_add(). This way the modules that
can be removable do not duplicate the cleanup code.

Suggested-by: Alexandre Courbot <gnurou@gmail.com>
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-of.c | 17 +++++++++++++++++
 include/linux/of_gpio.h   |  1 +
 2 files changed, 18 insertions(+)

(limited to 'include')

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 604dbe60bde..3e2c6afeab1 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -204,6 +204,23 @@ err0:
 }
 EXPORT_SYMBOL(of_mm_gpiochip_add);
 
+/**
+ * of_mm_gpiochip_remove - Remove memory mapped GPIO chip (bank)
+ * @mm_gc:	pointer to the of_mm_gpio_chip allocated structure
+ */
+void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc)
+{
+	struct gpio_chip *gc = &mm_gc->gc;
+
+	if (!mm_gc)
+		return;
+
+	gpiochip_remove(gc);
+	iounmap(mm_gc->regs);
+	kfree(gc->label);
+}
+EXPORT_SYMBOL(of_mm_gpiochip_remove);
+
 #ifdef CONFIG_PINCTRL
 static void of_gpiochip_add_pin_range(struct gpio_chip *chip)
 {
diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h
index 38fc0503601..69dbe312b11 100644
--- a/include/linux/of_gpio.h
+++ b/include/linux/of_gpio.h
@@ -52,6 +52,7 @@ extern int of_get_named_gpio_flags(struct device_node *np,
 
 extern int of_mm_gpiochip_add(struct device_node *np,
 			      struct of_mm_gpio_chip *mm_gc);
+extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc);
 
 extern void of_gpiochip_add(struct gpio_chip *gc);
 extern void of_gpiochip_remove(struct gpio_chip *gc);
-- 
cgit v1.2.3-70-g09d2


From 53e41f554a0cbad139ee5072bbb49b4951f680c2 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 15 Dec 2014 10:39:47 +0100
Subject: gpio: tc3589x: get rid of platform data

This device is only used from the device tree, and the startup()
and remove() callbacks are not used anywhere in the kernel, so
retire them and the pdata altogether.

Cc: Samuel Ortiz <sameo@linux.intel.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tc3589x.c | 15 ++-------------
 include/linux/mfd/tc3589x.h | 12 ------------
 2 files changed, 2 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index abdcf58935f..11aed267106 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -232,16 +232,13 @@ static irqreturn_t tc3589x_gpio_irq(int irq, void *dev)
 static int tc3589x_gpio_probe(struct platform_device *pdev)
 {
 	struct tc3589x *tc3589x = dev_get_drvdata(pdev->dev.parent);
-	struct tc3589x_gpio_platform_data *pdata;
 	struct device_node *np = pdev->dev.of_node;
 	struct tc3589x_gpio *tc3589x_gpio;
 	int ret;
 	int irq;
 
-	pdata = tc3589x->pdata->gpio;
-
-	if (!(pdata || np)) {
-		dev_err(&pdev->dev, "No platform data or Device Tree found\n");
+	if (!np) {
+		dev_err(&pdev->dev, "No Device Tree node found\n");
 		return -EINVAL;
 	}
 
@@ -305,9 +302,6 @@ static int tc3589x_gpio_probe(struct platform_device *pdev)
 				     irq,
 				     NULL);
 
-	if (pdata && pdata->setup)
-		pdata->setup(tc3589x, tc3589x_gpio->chip.base);
-
 	platform_set_drvdata(pdev, tc3589x_gpio);
 
 	return 0;
@@ -316,11 +310,6 @@ static int tc3589x_gpio_probe(struct platform_device *pdev)
 static int tc3589x_gpio_remove(struct platform_device *pdev)
 {
 	struct tc3589x_gpio *tc3589x_gpio = platform_get_drvdata(pdev);
-	struct tc3589x *tc3589x = tc3589x_gpio->tc3589x;
-	struct tc3589x_gpio_platform_data *pdata = tc3589x->pdata->gpio;
-
-	if (pdata && pdata->remove)
-		pdata->remove(tc3589x, tc3589x_gpio->chip.base);
 
 	gpiochip_remove(&tc3589x_gpio->chip);
 
diff --git a/include/linux/mfd/tc3589x.h b/include/linux/mfd/tc3589x.h
index e1c12d84c26..c203c9c5677 100644
--- a/include/linux/mfd/tc3589x.h
+++ b/include/linux/mfd/tc3589x.h
@@ -162,25 +162,13 @@ struct tc3589x_keypad_platform_data {
 	bool                    no_autorepeat;
 };
 
-/**
- * struct tc3589x_gpio_platform_data - TC3589x GPIO platform data
- * @setup: callback for board-specific initialization
- * @remove: callback for board-specific teardown
- */
-struct tc3589x_gpio_platform_data {
-	void (*setup)(struct tc3589x *tc3589x, unsigned gpio_base);
-	void (*remove)(struct tc3589x *tc3589x, unsigned gpio_base);
-};
-
 /**
  * struct tc3589x_platform_data - TC3589x platform data
  * @block: bitmask of blocks to enable (use TC3589x_BLOCK_*)
- * @gpio: GPIO-specific platform data
  * @keypad: keypad-specific platform data
  */
 struct tc3589x_platform_data {
 	unsigned int block;
-	struct tc3589x_gpio_platform_data *gpio;
 	const struct tc3589x_keypad_platform_data *keypad;
 };
 
-- 
cgit v1.2.3-70-g09d2


From d34541bc48eb7d7cb2ead5ff0284acf65af96f17 Mon Sep 17 00:00:00 2001
From: Olliver Schinagl <oliver@schinagl.nl>
Date: Wed, 7 Jan 2015 09:44:57 +0100
Subject: gpio: Make the vararg hacks not pass magic values

Right now, in consumer.h, there's some vararg hacks that pass 0 as the
flags. What actually is passed however is GPIOD_ASIS, which naturally is
also 0. Using the define/enum rather then the magic 0 makes it the
define more readable to a passer by.

Signed-off-by: Olliver Schinagl <oliver@schinagl.nl>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/consumer.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index fd85cb120ee..45afc2dee56 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -340,31 +340,32 @@ static inline int desc_to_gpio(const struct gpio_desc *desc)
  * etc.
  */
 #define __gpiod_get(dev, con_id, flags, ...) __gpiod_get(dev, con_id, flags)
-#define gpiod_get(varargs...) __gpiod_get(varargs, 0)
+#define gpiod_get(varargs...) __gpiod_get(varargs, GPIOD_ASIS)
 #define __gpiod_get_index(dev, con_id, index, flags, ...)		\
 	__gpiod_get_index(dev, con_id, index, flags)
-#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, 0)
+#define gpiod_get_index(varargs...) __gpiod_get_index(varargs, GPIOD_ASIS)
 #define __gpiod_get_optional(dev, con_id, flags, ...)			\
 	__gpiod_get_optional(dev, con_id, flags)
-#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, 0)
+#define gpiod_get_optional(varargs...) __gpiod_get_optional(varargs, GPIOD_ASIS)
 #define __gpiod_get_index_optional(dev, con_id, index, flags, ...)	\
 	__gpiod_get_index_optional(dev, con_id, index, flags)
 #define gpiod_get_index_optional(varargs...)				\
-	__gpiod_get_index_optional(varargs, 0)
+	__gpiod_get_index_optional(varargs, GPIOD_ASIS)
 #define __devm_gpiod_get(dev, con_id, flags, ...)			\
 	__devm_gpiod_get(dev, con_id, flags)
-#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, 0)
+#define devm_gpiod_get(varargs...) __devm_gpiod_get(varargs, GPIOD_ASIS)
 #define __devm_gpiod_get_index(dev, con_id, index, flags, ...)		\
 	__devm_gpiod_get_index(dev, con_id, index, flags)
-#define devm_gpiod_get_index(varargs...) __devm_gpiod_get_index(varargs, 0)
+#define devm_gpiod_get_index(varargs...)				\
+	__devm_gpiod_get_index(varargs, GPIOD_ASIS)
 #define __devm_gpiod_get_optional(dev, con_id, flags, ...)		\
 	__devm_gpiod_get_optional(dev, con_id, flags)
 #define devm_gpiod_get_optional(varargs...)				\
-	__devm_gpiod_get_optional(varargs, 0)
+	__devm_gpiod_get_optional(varargs, GPIOD_ASIS)
 #define __devm_gpiod_get_index_optional(dev, con_id, index, flags, ...)	\
 	__devm_gpiod_get_index_optional(dev, con_id, index, flags)
 #define devm_gpiod_get_index_optional(varargs...)			\
-	__devm_gpiod_get_index_optional(varargs, 0)
+	__devm_gpiod_get_index_optional(varargs, GPIOD_ASIS)
 
 #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_GPIO_SYSFS)
 
-- 
cgit v1.2.3-70-g09d2


From 2397aa8b515f7bd77c8d5698170b6a98fdd6721c Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 13 Jan 2015 11:02:54 -0500
Subject: svcrdma: Clean up read chunk counting

The byte_count argument is not used, and the function is called
only from one place.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h         |  2 --
 net/sunrpc/xprtrdma/svc_rdma_marshal.c  | 16 ----------------
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 15 ++++++++++++---
 3 files changed, 12 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 975da754c77..2280325e4c8 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -178,8 +178,6 @@ struct svcxprt_rdma {
 #define RPCRDMA_MAX_REQ_SIZE    4096
 
 /* svc_rdma_marshal.c */
-extern void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *,
-				      int *, int *);
 extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *);
 extern int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *);
 extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 65b146297f5..b681855cf97 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -70,22 +70,6 @@ static u32 *decode_read_list(u32 *va, u32 *vaend)
 	return (u32 *)&ch->rc_position;
 }
 
-/*
- * Determine number of chunks and total bytes in chunk list. The chunk
- * list has already been verified to fit within the RPCRDMA header.
- */
-void svc_rdma_rcl_chunk_counts(struct rpcrdma_read_chunk *ch,
-			       int *ch_count, int *byte_count)
-{
-	/* compute the number of bytes represented by read chunks */
-	*byte_count = 0;
-	*ch_count = 0;
-	for (; ch->rc_discrim != 0; ch++) {
-		*byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
-		*ch_count = *ch_count + 1;
-	}
-}
-
 /*
  * Decodes a write chunk list. The expected format is as follows:
  *    descrim  : xdr_one
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 2c67de03200..b3b7bb85844 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -365,12 +365,22 @@ static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 	return ret;
 }
 
+static unsigned int
+rdma_rcl_chunk_count(struct rpcrdma_read_chunk *ch)
+{
+	unsigned int count;
+
+	for (count = 0; ch->rc_discrim != xdr_zero; ch++)
+		count++;
+	return count;
+}
+
 static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			    struct rpcrdma_msg *rmsgp,
 			    struct svc_rqst *rqstp,
 			    struct svc_rdma_op_ctxt *head)
 {
-	int page_no, ch_count, ret;
+	int page_no, ret;
 	struct rpcrdma_read_chunk *ch;
 	u32 page_offset, byte_count;
 	u64 rs_offset;
@@ -381,8 +391,7 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	if (!ch)
 		return 0;
 
-	svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count);
-	if (ch_count > RPCSVC_MAXPAGES)
+	if (rdma_rcl_chunk_count(ch) > RPCSVC_MAXPAGES)
 		return -EINVAL;
 
 	/* The request is completed when the RDMA_READs complete. The
-- 
cgit v1.2.3-70-g09d2


From e54524111f51eac1900cf91aca3d38a92a6b11c0 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 13 Jan 2015 11:03:20 -0500
Subject: svcrdma: Plant reader function in struct svcxprt_rdma

The RDMA reader function doesn't change once an svcxprt_rdma is
instantiated. Instead of checking sc_devcap during every incoming
RPC, set the reader function once when the connection is accepted.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h          | 10 +++++
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  | 71 ++++++++++++--------------------
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  2 +
 3 files changed, 39 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 2280325e4c8..f161e309f25 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -150,6 +150,10 @@ struct svcxprt_rdma {
 	struct ib_cq         *sc_rq_cq;
 	struct ib_cq         *sc_sq_cq;
 	struct ib_mr         *sc_phys_mr;	/* MR for server memory */
+	int		     (*sc_reader)(struct svcxprt_rdma *,
+					  struct svc_rqst *,
+					  struct svc_rdma_op_ctxt *,
+					  int *, u32 *, u32, u32, u64, bool);
 	u32		     sc_dev_caps;	/* distilled device caps */
 	u32		     sc_dma_lkey;	/* local dma key */
 	unsigned int	     sc_frmr_pg_list_len;
@@ -195,6 +199,12 @@ extern int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *);
 
 /* svc_rdma_recvfrom.c */
 extern int svc_rdma_recvfrom(struct svc_rqst *);
+extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *,
+			       struct svc_rdma_op_ctxt *, int *, u32 *,
+			       u32, u32, u64, bool);
+extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
+				struct svc_rdma_op_ctxt *, int *, u32 *,
+				u32, u32, u64, bool);
 
 /* svc_rdma_sendto.c */
 extern int svc_rdma_sendto(struct svc_rqst *);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 577f8659ca3..c3aebc1bf0a 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -117,26 +117,16 @@ static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
 		return min_t(int, sge_count, xprt->sc_max_sge);
 }
 
-typedef int (*rdma_reader_fn)(struct svcxprt_rdma *xprt,
-			      struct svc_rqst *rqstp,
-			      struct svc_rdma_op_ctxt *head,
-			      int *page_no,
-			      u32 *page_offset,
-			      u32 rs_handle,
-			      u32 rs_length,
-			      u64 rs_offset,
-			      int last);
-
 /* Issue an RDMA_READ using the local lkey to map the data sink */
-static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
-			       struct svc_rqst *rqstp,
-			       struct svc_rdma_op_ctxt *head,
-			       int *page_no,
-			       u32 *page_offset,
-			       u32 rs_handle,
-			       u32 rs_length,
-			       u64 rs_offset,
-			       int last)
+int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
+			struct svc_rqst *rqstp,
+			struct svc_rdma_op_ctxt *head,
+			int *page_no,
+			u32 *page_offset,
+			u32 rs_handle,
+			u32 rs_length,
+			u64 rs_offset,
+			bool last)
 {
 	struct ib_send_wr read_wr;
 	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
@@ -221,15 +211,15 @@ static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
 }
 
 /* Issue an RDMA_READ using an FRMR to map the data sink */
-static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
-				struct svc_rqst *rqstp,
-				struct svc_rdma_op_ctxt *head,
-				int *page_no,
-				u32 *page_offset,
-				u32 rs_handle,
-				u32 rs_length,
-				u64 rs_offset,
-				int last)
+int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
+			 struct svc_rqst *rqstp,
+			 struct svc_rdma_op_ctxt *head,
+			 int *page_no,
+			 u32 *page_offset,
+			 u32 rs_handle,
+			 u32 rs_length,
+			 u64 rs_offset,
+			 bool last)
 {
 	struct ib_send_wr read_wr;
 	struct ib_send_wr inv_wr;
@@ -374,9 +364,9 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 {
 	int page_no, ret;
 	struct rpcrdma_read_chunk *ch;
-	u32 page_offset, byte_count;
+	u32 handle, page_offset, byte_count;
 	u64 rs_offset;
-	rdma_reader_fn reader;
+	bool last;
 
 	/* If no read list is present, return 0 */
 	ch = svc_rdma_get_read_chunk(rmsgp);
@@ -399,27 +389,20 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	head->arg.len = rqstp->rq_arg.len;
 	head->arg.buflen = rqstp->rq_arg.buflen;
 
-	/* Use FRMR if supported */
-	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)
-		reader = rdma_read_chunk_frmr;
-	else
-		reader = rdma_read_chunk_lcl;
-
 	page_no = 0; page_offset = 0;
 	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	     ch->rc_discrim != 0; ch++) {
-
+		handle = be32_to_cpu(ch->rc_target.rs_handle);
+		byte_count = be32_to_cpu(ch->rc_target.rs_length);
 		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
 				 &rs_offset);
-		byte_count = ntohl(ch->rc_target.rs_length);
 
 		while (byte_count > 0) {
-			ret = reader(xprt, rqstp, head,
-				     &page_no, &page_offset,
-				     ntohl(ch->rc_target.rs_handle),
-				     byte_count, rs_offset,
-				     ((ch+1)->rc_discrim == 0) /* last */
-				     );
+			last = (ch + 1)->rc_discrim == xdr_zero;
+			ret = xprt->sc_reader(xprt, rqstp, head,
+					      &page_no, &page_offset,
+					      handle, byte_count,
+					      rs_offset, last);
 			if (ret < 0)
 				goto err;
 			byte_count -= ret;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index f2e059bbab4..f609c1c2d38 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -974,10 +974,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 	 * NB:	iWARP requires remote write access for the data sink
 	 *	of an RDMA_READ. IB does not.
 	 */
+	newxprt->sc_reader = rdma_read_chunk_lcl;
 	if (devattr.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
 		newxprt->sc_frmr_pg_list_len =
 			devattr.max_fast_reg_page_list_len;
 		newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
+		newxprt->sc_reader = rdma_read_chunk_frmr;
 	}
 
 	/*
-- 
cgit v1.2.3-70-g09d2


From 0b056c224bea63060ce8a981e84193c93fac6f5d Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 13 Jan 2015 11:03:37 -0500
Subject: svcrdma: Support RDMA_NOMSG requests

Currently the Linux server can not decode RDMA_NOMSG type requests.
Operations whose length exceeds the fixed size of RDMA SEND buffers,
like large NFSv4 CREATE(NF4LNK) operations, must be conveyed via
RDMA_NOMSG.

For an RDMA_MSG type request, the client sends the RPC/RDMA, RPC
headers, and some or all of the NFS arguments via RDMA SEND.

For an RDMA_NOMSG type request, the client sends just the RPC/RDMA
header via RDMA SEND. The request's read list contains elements for
the entire RPC message, including the RPC header.

NFSD expects the RPC/RMDA header and RPC header to be contiguous in
page zero of the XDR buffer. Add logic in the RDMA READ path to make
the read list contents land where the server prefers, when the
incoming message is a type RDMA_NOMSG message.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/svc_rdma.h         |  1 +
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 39 ++++++++++++++++++++++++++++++---
 2 files changed, 37 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index f161e309f25..c343a94bc79 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -79,6 +79,7 @@ struct svc_rdma_op_ctxt {
 	enum ib_wr_opcode wr_op;
 	enum ib_wc_status wc_status;
 	u32 byte_len;
+	u32 position;
 	struct svcxprt_rdma *xprt;
 	unsigned long flags;
 	enum dma_data_direction direction;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index a67dd1a081d..36cf51a3eab 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -60,6 +60,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 			       struct svc_rdma_op_ctxt *ctxt,
 			       u32 byte_count)
 {
+	struct rpcrdma_msg *rmsgp;
 	struct page *page;
 	u32 bc;
 	int sge_no;
@@ -82,7 +83,14 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	/* If data remains, store it in the pagelist */
 	rqstp->rq_arg.page_len = bc;
 	rqstp->rq_arg.page_base = 0;
-	rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
+	if (be32_to_cpu(rmsgp->rm_type) == RDMA_NOMSG)
+		rqstp->rq_arg.pages = &rqstp->rq_pages[0];
+	else
+		rqstp->rq_arg.pages = &rqstp->rq_pages[1];
+
 	sge_no = 1;
 	while (bc && sge_no < ctxt->count) {
 		page = ctxt->pages[sge_no];
@@ -383,7 +391,6 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	 */
 	head->arg.head[0] = rqstp->rq_arg.head[0];
 	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->arg.pages = &head->pages[head->count];
 	head->hdr_count = head->count;
 	head->arg.page_base = 0;
 	head->arg.page_len = 0;
@@ -393,9 +400,17 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
 	position = be32_to_cpu(ch->rc_position);
 
+	/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
+	if (position == 0) {
+		head->arg.pages = &head->pages[0];
+		page_offset = head->byte_len;
+	} else {
+		head->arg.pages = &head->pages[head->count];
+		page_offset = 0;
+	}
+
 	ret = 0;
 	page_no = 0;
-	page_offset = 0;
 	for (; ch->rc_discrim != xdr_zero; ch++) {
 		if (be32_to_cpu(ch->rc_position) != position)
 			goto err;
@@ -418,7 +433,10 @@ static int rdma_read_chunks(struct svcxprt_rdma *xprt,
 			head->arg.buflen += ret;
 		}
 	}
+
 	ret = 1;
+	head->position = position;
+
  err:
 	/* Detach arg pages. svc_recv will replenish them */
 	for (page_no = 0;
@@ -465,6 +483,21 @@ static int rdma_read_complete(struct svc_rqst *rqstp,
 		put_page(rqstp->rq_pages[page_no]);
 		rqstp->rq_pages[page_no] = head->pages[page_no];
 	}
+
+	/* Adjustments made for RDMA_NOMSG type requests */
+	if (head->position == 0) {
+		if (head->arg.len <= head->sge[0].length) {
+			head->arg.head[0].iov_len = head->arg.len -
+							head->byte_len;
+			head->arg.page_len = 0;
+		} else {
+			head->arg.head[0].iov_len = head->sge[0].length -
+								head->byte_len;
+			head->arg.page_len = head->arg.len -
+						head->sge[0].length;
+		}
+	}
+
 	/* Point rq_arg.pages past header */
 	rdma_fix_xdr_pad(&head->arg);
 	rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count];
-- 
cgit v1.2.3-70-g09d2


From b51f3beecfbbfc946749a91fb444cb8917cf444f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 15 Jan 2015 16:14:02 +0100
Subject: cfg80211: change bandwidth reporting to explicit field

For some reason, we made the bandwidth separate flags, which
is rather confusing - a single rate cannot have different
bandwidths at the same time.

Change this to no longer be flags but use a separate field
for the bandwidth ('bw') instead.

While at it, add support for 5 and 10 MHz rates - these are
reported as regular legacy rates with their real bitrate,
but tagged as 5/10 now to make it easier to distinguish them.

In the nl80211 API, the flags are preserved, but the code
now can also clearly only set a single one of the flags.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c |  3 ++-
 drivers/net/wireless/mwifiex/cfg80211.c    | 11 ++++----
 include/net/cfg80211.h                     | 33 ++++++++++++++++++------
 include/uapi/linux/nl80211.h               |  8 ++++++
 net/mac80211/cfg.c                         | 31 +++++++++++++++--------
 net/mac80211/util.c                        | 25 +++++++++++++------
 net/wireless/nl80211.c                     | 40 +++++++++++++++++++++---------
 net/wireless/util.c                        | 24 ++++++++++++++----
 8 files changed, 125 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 44dd6ef923c..85da63a67fa 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1827,6 +1827,7 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 		}
 
 		sinfo->txrate.flags |= RATE_INFO_FLAGS_MCS;
+		sinfo->txrate.bw = RATE_INFO_BW_20;
 	} else if (is_rate_ht40(rate, &mcs, &sgi)) {
 		if (sgi) {
 			sinfo->txrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
@@ -1835,7 +1836,7 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 			sinfo->txrate.mcs = mcs;
 		}
 
-		sinfo->txrate.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+		sinfo->txrate.bw = RATE_INFO_BW_40;
 		sinfo->txrate.flags |= RATE_INFO_FLAGS_MCS;
 	} else {
 		ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 71312ff5270..1996a8b612d 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -856,16 +856,16 @@ mwifiex_parse_htinfo(struct mwifiex_private *priv, u8 tx_htinfo,
 			/* HT or VHT */
 			switch (tx_htinfo & (BIT(3) | BIT(2))) {
 			case 0:
-				/* This will be 20MHz */
+				rate->bw = RATE_INFO_BW_20;
 				break;
 			case (BIT(2)):
-				rate->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+				rate->bw = RATE_INFO_BW_40;
 				break;
 			case (BIT(3)):
-				rate->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
+				rate->bw = RATE_INFO_BW_80;
 				break;
 			case (BIT(3) | BIT(2)):
-				rate->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+				rate->bw = RATE_INFO_BW_160;
 				break;
 			}
 
@@ -885,8 +885,9 @@ mwifiex_parse_htinfo(struct mwifiex_private *priv, u8 tx_htinfo,
 		if ((tx_htinfo & BIT(0)) && (priv->tx_rate < 16)) {
 			rate->mcs = priv->tx_rate;
 			rate->flags |= RATE_INFO_FLAGS_MCS;
+			rate->bw = RATE_INFO_BW_20;
 			if (tx_htinfo & BIT(1))
-				rate->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+				rate->bw = RATE_INFO_BW_40;
 			if (tx_htinfo & BIT(2))
 				rate->flags |= RATE_INFO_FLAGS_SHORT_GI;
 		}
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 0322048fdda..7b44ba0a763 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -873,20 +873,35 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
  *
  * @RATE_INFO_FLAGS_MCS: mcs field filled with HT MCS
  * @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS
- * @RATE_INFO_FLAGS_40_MHZ_WIDTH: 40 MHz width transmission
- * @RATE_INFO_FLAGS_80_MHZ_WIDTH: 80 MHz width transmission
- * @RATE_INFO_FLAGS_160_MHZ_WIDTH: 160 MHz width transmission
  * @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval
  * @RATE_INFO_FLAGS_60G: 60GHz MCS
  */
 enum rate_info_flags {
 	RATE_INFO_FLAGS_MCS			= BIT(0),
 	RATE_INFO_FLAGS_VHT_MCS			= BIT(1),
-	RATE_INFO_FLAGS_40_MHZ_WIDTH		= BIT(2),
-	RATE_INFO_FLAGS_80_MHZ_WIDTH		= BIT(3),
-	RATE_INFO_FLAGS_160_MHZ_WIDTH		= BIT(4),
-	RATE_INFO_FLAGS_SHORT_GI		= BIT(5),
-	RATE_INFO_FLAGS_60G			= BIT(6),
+	RATE_INFO_FLAGS_SHORT_GI		= BIT(2),
+	RATE_INFO_FLAGS_60G			= BIT(3),
+};
+
+/**
+ * enum rate_info_bw - rate bandwidth information
+ *
+ * Used by the driver to indicate the rate bandwidth.
+ *
+ * @RATE_INFO_BW_5: 5 MHz bandwidth
+ * @RATE_INFO_BW_10: 10 MHz bandwidth
+ * @RATE_INFO_BW_20: 20 MHz bandwidth
+ * @RATE_INFO_BW_40: 40 MHz bandwidth
+ * @RATE_INFO_BW_80: 80 MHz bandwidth
+ * @RATE_INFO_BW_160: 160 MHz bandwidth
+ */
+enum rate_info_bw {
+	RATE_INFO_BW_5,
+	RATE_INFO_BW_10,
+	RATE_INFO_BW_20,
+	RATE_INFO_BW_40,
+	RATE_INFO_BW_80,
+	RATE_INFO_BW_160,
 };
 
 /**
@@ -898,12 +913,14 @@ enum rate_info_flags {
  * @mcs: mcs index if struct describes a 802.11n bitrate
  * @legacy: bitrate in 100kbit/s for 802.11abg
  * @nss: number of streams (VHT only)
+ * @bw: bandwidth (from &enum rate_info_bw)
  */
 struct rate_info {
 	u8 flags;
 	u8 mcs;
 	u16 legacy;
 	u8 nss;
+	u8 bw;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 11cdb85ac64..f52797a9081 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2281,6 +2281,12 @@ struct nl80211_sta_flag_update {
  * @NL80211_RATE_INFO_80P80_MHZ_WIDTH: unused - 80+80 is treated the
  *	same as 160 for purposes of the bitrates
  * @NL80211_RATE_INFO_160_MHZ_WIDTH: 160 MHz VHT rate
+ * @NL80211_RATE_INFO_10_MHZ_WIDTH: 10 MHz width - note that this is
+ *	a legacy rate and will be reported as the actual bitrate, i.e.
+ *	half the base (20 MHz) rate
+ * @NL80211_RATE_INFO_5_MHZ_WIDTH: 5 MHz width - note that this is
+ *	a legacy rate and will be reported as the actual bitrate, i.e.
+ *	a quarter of the base (20 MHz) rate
  * @__NL80211_RATE_INFO_AFTER_LAST: internal use
  */
 enum nl80211_rate_info {
@@ -2295,6 +2301,8 @@ enum nl80211_rate_info {
 	NL80211_RATE_INFO_80_MHZ_WIDTH,
 	NL80211_RATE_INFO_80P80_MHZ_WIDTH,
 	NL80211_RATE_INFO_160_MHZ_WIDTH,
+	NL80211_RATE_INFO_10_MHZ_WIDTH,
+	NL80211_RATE_INFO_5_MHZ_WIDTH,
 
 	/* keep last */
 	__NL80211_RATE_INFO_AFTER_LAST,
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 6d5076fbf87..ff090ef1ea2 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -428,11 +428,13 @@ void sta_set_rate_info_tx(struct sta_info *sta,
 		rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
 	}
 	if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-		rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
-	if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
-		rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-	if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
-		rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+		rinfo->bw = RATE_INFO_BW_40;
+	else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+		rinfo->bw = RATE_INFO_BW_80;
+	else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
+		rinfo->bw = RATE_INFO_BW_160;
+	else
+		rinfo->bw = RATE_INFO_BW_20;
 	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
 }
@@ -459,14 +461,21 @@ void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo)
 		rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
 	}
 
-	if (sta->last_rx_rate_flag & RX_FLAG_40MHZ)
-		rinfo->flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
 	if (sta->last_rx_rate_flag & RX_FLAG_SHORT_GI)
 		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
-	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80MHZ)
-		rinfo->flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-	if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_160MHZ)
-		rinfo->flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+
+	if (sta->last_rx_rate_flag & RX_FLAG_5MHZ)
+		rinfo->bw = RATE_INFO_BW_5;
+	else if (sta->last_rx_rate_flag & RX_FLAG_10MHZ)
+		rinfo->bw = RATE_INFO_BW_10;
+	else if (sta->last_rx_rate_flag & RX_FLAG_40MHZ)
+		rinfo->bw = RATE_INFO_BW_40;
+	else if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_80MHZ)
+		rinfo->bw = RATE_INFO_BW_80;
+	else if (sta->last_rx_rate_vht_flag & RX_VHT_FLAG_160MHZ)
+		rinfo->bw = RATE_INFO_BW_160;
+	else
+		rinfo->bw = RATE_INFO_BW_20;
 }
 
 static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index db721612473..fbd37d43dfc 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2541,7 +2541,9 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		ri.mcs = status->rate_idx;
 		ri.flags |= RATE_INFO_FLAGS_MCS;
 		if (status->flag & RX_FLAG_40MHZ)
-			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
+			ri.bw = RATE_INFO_BW_40;
+		else
+			ri.bw = RATE_INFO_BW_20;
 		if (status->flag & RX_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
 	} else if (status->flag & RX_FLAG_VHT) {
@@ -2549,11 +2551,13 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		ri.mcs = status->rate_idx;
 		ri.nss = status->vht_nss;
 		if (status->flag & RX_FLAG_40MHZ)
-			ri.flags |= RATE_INFO_FLAGS_40_MHZ_WIDTH;
-		if (status->vht_flag & RX_VHT_FLAG_80MHZ)
-			ri.flags |= RATE_INFO_FLAGS_80_MHZ_WIDTH;
-		if (status->vht_flag & RX_VHT_FLAG_160MHZ)
-			ri.flags |= RATE_INFO_FLAGS_160_MHZ_WIDTH;
+			ri.bw = RATE_INFO_BW_40;
+		else if (status->vht_flag & RX_VHT_FLAG_80MHZ)
+			ri.bw = RATE_INFO_BW_80;
+		else if (status->vht_flag & RX_VHT_FLAG_160MHZ)
+			ri.bw = RATE_INFO_BW_160;
+		else
+			ri.bw = RATE_INFO_BW_20;
 		if (status->flag & RX_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
 	} else {
@@ -2561,10 +2565,15 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		int shift = 0;
 		int bitrate;
 
-		if (status->flag & RX_FLAG_10MHZ)
+		if (status->flag & RX_FLAG_10MHZ) {
 			shift = 1;
-		if (status->flag & RX_FLAG_5MHZ)
+			ri.bw = RATE_INFO_BW_10;
+		} else if (status->flag & RX_FLAG_5MHZ) {
 			shift = 2;
+			ri.bw = RATE_INFO_BW_5;
+		} else {
+			ri.bw = RATE_INFO_BW_20;
+		}
 
 		sband = local->hw.wiphy->bands[status->band];
 		bitrate = sband->bitrates[status->rate_idx].bitrate;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 8998484ea97..8e56eeb583a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3578,6 +3578,7 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 	struct nlattr *rate;
 	u32 bitrate;
 	u16 bitrate_compat;
+	enum nl80211_attrs rate_flg;
 
 	rate = nla_nest_start(msg, attr);
 	if (!rate)
@@ -3594,12 +3595,36 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 	    nla_put_u16(msg, NL80211_RATE_INFO_BITRATE, bitrate_compat))
 		return false;
 
+	switch (info->bw) {
+	case RATE_INFO_BW_5:
+		rate_flg = NL80211_RATE_INFO_5_MHZ_WIDTH;
+		break;
+	case RATE_INFO_BW_10:
+		rate_flg = NL80211_RATE_INFO_10_MHZ_WIDTH;
+		break;
+	default:
+		WARN_ON(1);
+		/* fall through */
+	case RATE_INFO_BW_20:
+		rate_flg = 0;
+		break;
+	case RATE_INFO_BW_40:
+		rate_flg = NL80211_RATE_INFO_40_MHZ_WIDTH;
+		break;
+	case RATE_INFO_BW_80:
+		rate_flg = NL80211_RATE_INFO_80_MHZ_WIDTH;
+		break;
+	case RATE_INFO_BW_160:
+		rate_flg = NL80211_RATE_INFO_160_MHZ_WIDTH;
+		break;
+	}
+
+	if (rate_flg && nla_put_flag(msg, rate_flg))
+		return false;
+
 	if (info->flags & RATE_INFO_FLAGS_MCS) {
 		if (nla_put_u8(msg, NL80211_RATE_INFO_MCS, info->mcs))
 			return false;
-		if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH))
-			return false;
 		if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
 		    nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
 			return false;
@@ -3608,15 +3633,6 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 			return false;
 		if (nla_put_u8(msg, NL80211_RATE_INFO_VHT_NSS, info->nss))
 			return false;
-		if (info->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_40_MHZ_WIDTH))
-			return false;
-		if (info->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_80_MHZ_WIDTH))
-			return false;
-		if (info->flags & RATE_INFO_FLAGS_160_MHZ_WIDTH &&
-		    nla_put_flag(msg, NL80211_RATE_INFO_160_MHZ_WIDTH))
-			return false;
 		if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
 		    nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
 			return false;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 6942d48f1ac..3535e8ade48 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1073,9 +1073,24 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
 	if (WARN_ON_ONCE(rate->mcs > 9))
 		return 0;
 
-	idx = rate->flags & RATE_INFO_FLAGS_160_MHZ_WIDTH ? 3 :
-		  rate->flags & RATE_INFO_FLAGS_80_MHZ_WIDTH ? 2 :
-		  rate->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH ? 1 : 0;
+	switch (rate->bw) {
+	case RATE_INFO_BW_160:
+		idx = 3;
+		break;
+	case RATE_INFO_BW_80:
+		idx = 2;
+		break;
+	case RATE_INFO_BW_40:
+		idx = 1;
+		break;
+	case RATE_INFO_BW_5:
+	case RATE_INFO_BW_10:
+	default:
+		WARN_ON(1);
+		/* fall through */
+	case RATE_INFO_BW_20:
+		idx = 0;
+	}
 
 	bitrate = base[idx][rate->mcs];
 	bitrate *= rate->nss;
@@ -1106,8 +1121,7 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 	modulation = rate->mcs & 7;
 	streams = (rate->mcs >> 3) + 1;
 
-	bitrate = (rate->flags & RATE_INFO_FLAGS_40_MHZ_WIDTH) ?
-			13500000 : 6500000;
+	bitrate = (rate->bw == RATE_INFO_BW_40) ? 13500000 : 6500000;
 
 	if (modulation < 4)
 		bitrate *= (modulation + 1);
-- 
cgit v1.2.3-70-g09d2


From 5055c371bfd53fd369b895051b541318c2bad495 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 14 Jan 2015 15:17:06 -0800
Subject: ipv4: per cpu uncached list

RAW sockets with hdrinc suffer from contention on rt_uncached_lock
spinlock.

One solution is to use percpu lists, since most routes are destroyed
by the cpu that created them.

It is unclear why we even have to put these routes in uncached_list,
as all outgoing packets should be freed when a device is dismantled.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: caacf05e5ad1 ("ipv4: Properly purge netdev references on uncached routes.")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h |  2 ++
 net/ipv4/route.c    | 46 +++++++++++++++++++++++++++++++++-------------
 2 files changed, 35 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/route.h b/include/net/route.h
index b17cf28f996..fe22d03afb6 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -46,6 +46,7 @@
 
 struct fib_nh;
 struct fib_info;
+struct uncached_list;
 struct rtable {
 	struct dst_entry	dst;
 
@@ -64,6 +65,7 @@ struct rtable {
 	u32			rt_pmtu;
 
 	struct list_head	rt_uncached;
+	struct uncached_list	*rt_uncached_list;
 };
 
 static inline bool rt_is_input_route(const struct rtable *rt)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a2155b0260..ce112d0f269 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1325,14 +1325,22 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	return ret;
 }
 
-static DEFINE_SPINLOCK(rt_uncached_lock);
-static LIST_HEAD(rt_uncached_list);
+struct uncached_list {
+	spinlock_t		lock;
+	struct list_head	head;
+};
+
+static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list);
 
 static void rt_add_uncached_list(struct rtable *rt)
 {
-	spin_lock_bh(&rt_uncached_lock);
-	list_add_tail(&rt->rt_uncached, &rt_uncached_list);
-	spin_unlock_bh(&rt_uncached_lock);
+	struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list);
+
+	rt->rt_uncached_list = ul;
+
+	spin_lock_bh(&ul->lock);
+	list_add_tail(&rt->rt_uncached, &ul->head);
+	spin_unlock_bh(&ul->lock);
 }
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
@@ -1340,27 +1348,32 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 	struct rtable *rt = (struct rtable *) dst;
 
 	if (!list_empty(&rt->rt_uncached)) {
-		spin_lock_bh(&rt_uncached_lock);
+		struct uncached_list *ul = rt->rt_uncached_list;
+
+		spin_lock_bh(&ul->lock);
 		list_del(&rt->rt_uncached);
-		spin_unlock_bh(&rt_uncached_lock);
+		spin_unlock_bh(&ul->lock);
 	}
 }
 
 void rt_flush_dev(struct net_device *dev)
 {
-	if (!list_empty(&rt_uncached_list)) {
-		struct net *net = dev_net(dev);
-		struct rtable *rt;
+	struct net *net = dev_net(dev);
+	struct rtable *rt;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
 
-		spin_lock_bh(&rt_uncached_lock);
-		list_for_each_entry(rt, &rt_uncached_list, rt_uncached) {
+		spin_lock_bh(&ul->lock);
+		list_for_each_entry(rt, &ul->head, rt_uncached) {
 			if (rt->dst.dev != dev)
 				continue;
 			rt->dst.dev = net->loopback_dev;
 			dev_hold(rt->dst.dev);
 			dev_put(dev);
 		}
-		spin_unlock_bh(&rt_uncached_lock);
+		spin_unlock_bh(&ul->lock);
 	}
 }
 
@@ -2717,6 +2730,7 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
 int __init ip_rt_init(void)
 {
 	int rc = 0;
+	int cpu;
 
 	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
 	if (!ip_idents)
@@ -2724,6 +2738,12 @@ int __init ip_rt_init(void)
 
 	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
 
+	for_each_possible_cpu(cpu) {
+		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);
+
+		INIT_LIST_HEAD(&ul->head);
+		spin_lock_init(&ul->lock);
+	}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
-- 
cgit v1.2.3-70-g09d2


From 57699a40b4f2694d3ee63fd5e6465ec8f600b620 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Fri, 16 Jan 2015 11:13:09 +0800
Subject: rhashtable: Fix race in rhashtable_destroy() and use regular
 work_struct

When we put our declared work task in the global workqueue with
schedule_delayed_work(), its delay parameter is always zero.
Therefore, we should define a regular work in rhashtable structure
instead of a delayed work.

By the way, we add a condition to check whether resizing functions
are NULL before cancelling the work, avoiding to cancel an
uninitialized work.

Lastly, while we wait for all work items we submitted before to run
to completion with cancel_delayed_work(), ht->mutex has been taken in
rhashtable_destroy(). Moreover, cancel_delayed_work() doesn't return
until all work items are accomplished, and when work items are
scheduled, the work's function - rht_deferred_worker() will be called.
However, as rht_deferred_worker() also needs to acquire the lock,
deadlock might happen at the moment as the lock is already held before.
So if the cancel work function is moved out of the lock covered scope,
this will avoid the deadlock.

Fixes: 97defe1 ("rhashtable: Per bucket locks & deferred expansion/shrinking")
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Cc: Thomas Graf <tgraf@suug.ch>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  2 +-
 lib/rhashtable.c           | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 9570832ab07..a2562ed53ea 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -119,7 +119,7 @@ struct rhashtable {
 	atomic_t			nelems;
 	atomic_t			shift;
 	struct rhashtable_params	p;
-	struct delayed_work             run_work;
+	struct work_struct		run_work;
 	struct mutex                    mutex;
 	bool                            being_destroyed;
 };
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index aca699813ba..84a78e396a5 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -485,7 +485,7 @@ static void rht_deferred_worker(struct work_struct *work)
 	struct rhashtable *ht;
 	struct bucket_table *tbl;
 
-	ht = container_of(work, struct rhashtable, run_work.work);
+	ht = container_of(work, struct rhashtable, run_work);
 	mutex_lock(&ht->mutex);
 	tbl = rht_dereference(ht->tbl, ht);
 
@@ -507,7 +507,7 @@ static void rhashtable_wakeup_worker(struct rhashtable *ht)
 	if (tbl == new_tbl &&
 	    ((ht->p.grow_decision && ht->p.grow_decision(ht, size)) ||
 	     (ht->p.shrink_decision && ht->p.shrink_decision(ht, size))))
-		schedule_delayed_work(&ht->run_work, 0);
+		schedule_work(&ht->run_work);
 }
 
 static void __rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj,
@@ -903,7 +903,7 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
 		get_random_bytes(&ht->p.hash_rnd, sizeof(ht->p.hash_rnd));
 
 	if (ht->p.grow_decision || ht->p.shrink_decision)
-		INIT_DEFERRABLE_WORK(&ht->run_work, rht_deferred_worker);
+		INIT_WORK(&ht->run_work, rht_deferred_worker);
 
 	return 0;
 }
@@ -921,11 +921,11 @@ void rhashtable_destroy(struct rhashtable *ht)
 {
 	ht->being_destroyed = true;
 
-	mutex_lock(&ht->mutex);
+	if (ht->p.grow_decision || ht->p.shrink_decision)
+		cancel_work_sync(&ht->run_work);
 
-	cancel_delayed_work(&ht->run_work);
+	mutex_lock(&ht->mutex);
 	bucket_table_free(rht_dereference(ht->tbl, ht));
-
 	mutex_unlock(&ht->mutex);
 }
 EXPORT_SYMBOL_GPL(rhashtable_destroy);
-- 
cgit v1.2.3-70-g09d2


From 5cd37193ce8539be1e6ef76be226f4bcc984e0f5 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 13 Dec 2014 20:32:04 -0800
Subject: rcu: Make cond_resched_rcu_qs() apply to normal RCU flavors

Although cond_resched_rcu_qs() only applies to TASKS_RCU, it is used
in places where it would be useful for it to apply to the normal RCU
flavors, rcu_preempt, rcu_sched, and rcu_bh.  This is especially the
case for workloads that aggressively overload the system, particularly
those that generate large numbers of RCU updates on systems running
NO_HZ_FULL CPUs.  This commit therefore communicates quiescent states
from cond_resched_rcu_qs() to the normal RCU flavors.

Note that it is unfortunately necessary to leave the old ->passed_quiesce
mechanism in place to allow quiescent states that apply to only one
flavor to be recorded.  (Yes, we could decrement ->rcu_qs_ctr_snap in
that case, but that is not so good for debugging of RCU internals.)
In addition, if one of the RCU flavor's grace period has stalled, this
will invoke rcu_momentary_dyntick_idle(), resulting in a heavy-weight
quiescent state visible from other CPUs.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Merge commit from Sasha Levin fixing a bug where __this_cpu()
  was used in preemptible code. ]
---
 Documentation/RCU/trace.txt | 32 ++++++++++++++++----------------
 include/linux/rcupdate.h    |  3 ++-
 include/linux/rcutiny.h     |  5 ++++-
 include/linux/rcutree.h     |  2 ++
 kernel/rcu/tree.c           | 38 +++++++++++++++++++++++++++++++++-----
 kernel/rcu/tree.h           |  2 ++
 kernel/rcu/tree_trace.c     |  8 ++++++--
 7 files changed, 65 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index b63b9bb3bc0..08651da1544 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -56,14 +56,14 @@ rcuboost:
 
 The output of "cat rcu/rcu_preempt/rcudata" looks as follows:
 
-  0!c=30455 g=30456 pq=1 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716
-  1!c=30719 g=30720 pq=1 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982
-  2!c=30150 g=30151 pq=1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458
-  3 c=31249 g=31250 pq=1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622
-  4!c=29502 g=29503 pq=1 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521
-  5 c=31201 g=31202 pq=1 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698
-  6!c=30253 g=30254 pq=1 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353
-  7 c=31178 g=31178 pq=1 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969
+  0!c=30455 g=30456 pq=1/0 qp=1 dt=126535/140000000000000/0 df=2002 of=4 ql=0/0 qs=N... b=10 ci=74572 nci=0 co=1131 ca=716
+  1!c=30719 g=30720 pq=1/0 qp=0 dt=132007/140000000000000/0 df=1874 of=10 ql=0/0 qs=N... b=10 ci=123209 nci=0 co=685 ca=982
+  2!c=30150 g=30151 pq=1/1 qp=1 dt=138537/140000000000000/0 df=1707 of=8 ql=0/0 qs=N... b=10 ci=80132 nci=0 co=1328 ca=1458
+  3 c=31249 g=31250 pq=1/1 qp=0 dt=107255/140000000000000/0 df=1749 of=6 ql=0/450 qs=NRW. b=10 ci=151700 nci=0 co=509 ca=622
+  4!c=29502 g=29503 pq=1/0 qp=1 dt=83647/140000000000000/0 df=965 of=5 ql=0/0 qs=N... b=10 ci=65643 nci=0 co=1373 ca=1521
+  5 c=31201 g=31202 pq=1/0 qp=1 dt=70422/0/0 df=535 of=7 ql=0/0 qs=.... b=10 ci=58500 nci=0 co=764 ca=698
+  6!c=30253 g=30254 pq=1/0 qp=1 dt=95363/140000000000000/0 df=780 of=5 ql=0/0 qs=N... b=10 ci=100607 nci=0 co=1414 ca=1353
+  7 c=31178 g=31178 pq=1/0 qp=0 dt=91536/0/0 df=547 of=4 ql=0/0 qs=.... b=10 ci=109819 nci=0 co=1115 ca=969
 
 This file has one line per CPU, or eight for this 8-CPU system.
 The fields are as follows:
@@ -188,14 +188,14 @@ o	"ca" is the number of RCU callbacks that have been adopted by this
 Kernels compiled with CONFIG_RCU_BOOST=y display the following from
 /debug/rcu/rcu_preempt/rcudata:
 
-  0!c=12865 g=12866 pq=1 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871
-  1 c=14407 g=14408 pq=1 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485
-  2 c=14407 g=14408 pq=1 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490
-  3 c=14407 g=14408 pq=1 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290
-  4 c=14405 g=14406 pq=1 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114
-  5!c=14168 g=14169 pq=1 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722
-  6 c=14404 g=14405 pq=1 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811
-  7 c=14407 g=14408 pq=1 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042
+  0!c=12865 g=12866 pq=1/0 qp=1 dt=83113/140000000000000/0 df=288 of=11 ql=0/0 qs=N... kt=0/O ktl=944 b=10 ci=60709 nci=0 co=748 ca=871
+  1 c=14407 g=14408 pq=1/0 qp=0 dt=100679/140000000000000/0 df=378 of=7 ql=0/119 qs=NRW. kt=0/W ktl=9b6 b=10 ci=109740 nci=0 co=589 ca=485
+  2 c=14407 g=14408 pq=1/0 qp=0 dt=105486/0/0 df=90 of=9 ql=0/89 qs=NRW. kt=0/W ktl=c0c b=10 ci=83113 nci=0 co=533 ca=490
+  3 c=14407 g=14408 pq=1/0 qp=0 dt=107138/0/0 df=142 of=8 ql=0/188 qs=NRW. kt=0/W ktl=b96 b=10 ci=121114 nci=0 co=426 ca=290
+  4 c=14405 g=14406 pq=1/0 qp=1 dt=50238/0/0 df=706 of=7 ql=0/0 qs=.... kt=0/W ktl=812 b=10 ci=34929 nci=0 co=643 ca=114
+  5!c=14168 g=14169 pq=1/0 qp=0 dt=45465/140000000000000/0 df=161 of=11 ql=0/0 qs=N... kt=0/O ktl=b4d b=10 ci=47712 nci=0 co=677 ca=722
+  6 c=14404 g=14405 pq=1/0 qp=0 dt=59454/0/0 df=94 of=6 ql=0/0 qs=.... kt=0/W ktl=e57 b=10 ci=55597 nci=0 co=701 ca=811
+  7 c=14407 g=14408 pq=1/0 qp=1 dt=68850/0/0 df=31 of=8 ql=0/0 qs=.... kt=0/W ktl=14bd b=10 ci=77475 nci=0 co=508 ca=1042
 
 This is similar to the output discussed above, but contains the following
 additional fields:
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ed4f5939a45..46822875029 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -331,12 +331,13 @@ static inline void rcu_init_nohz(void)
 extern struct srcu_struct tasks_rcu_exit_srcu;
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
+		rcu_all_qs(); \
 		if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \
 			ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \
 	} while (0)
 #else /* #ifdef CONFIG_TASKS_RCU */
 #define TASKS_RCU(x) do { } while (0)
-#define rcu_note_voluntary_context_switch(t)	do { } while (0)
+#define rcu_note_voluntary_context_switch(t)	rcu_all_qs()
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /**
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 0e536620015..fabd3fad851 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -154,7 +154,10 @@ static inline bool rcu_is_watching(void)
 	return true;
 }
 
-
 #endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
+static inline void rcu_all_qs(void)
+{
+}
+
 #endif /* __LINUX_RCUTINY_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 52953790dcc..ddba927f731 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -97,4 +97,6 @@ extern int rcu_scheduler_active __read_mostly;
 
 bool rcu_is_watching(void);
 
+void rcu_all_qs(void);
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 75ce12316b4..cb00e038c2f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -219,6 +219,9 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 };
 
+DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
+
 /*
  * Let the RCU core know that this CPU has gone through the scheduler,
  * which is a quiescent state.  This is called when the need for a
@@ -288,6 +291,22 @@ void rcu_note_context_switch(void)
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
+/*
+ * Register a quiesecent state for all RCU flavors.  If there is an
+ * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight
+ * dyntick-idle quiescent state visible to other CPUs (but only for those
+ * RCU flavors in desparate need of a quiescent state, which will normally
+ * be none of them).  Either way, do a lightweight quiescent state for
+ * all RCU flavors.
+ */
+void rcu_all_qs(void)
+{
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+		rcu_momentary_dyntick_idle();
+	this_cpu_inc(rcu_qs_ctr);
+}
+EXPORT_SYMBOL_GPL(rcu_all_qs);
+
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
 static long qhimark = 10000;	/* If this many pending, ignore blimit. */
 static long qlowmark = 100;	/* Once only this many pending, use blimit. */
@@ -1609,6 +1628,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		rdp->gpnum = rnp->gpnum;
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
 		rdp->passed_quiesce = 0;
+		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
 		ACCESS_ONCE(rdp->gpwrap) = false;
@@ -2075,8 +2095,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
-	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
-	    rnp->completed == rnp->gpnum || rdp->gpwrap) {
+	if ((rdp->passed_quiesce == 0 &&
+	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
+	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
+	    rdp->gpwrap) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -2085,6 +2107,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 * within the current grace period.
 		 */
 		rdp->passed_quiesce = 0;	/* need qs for new gp. */
+		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
@@ -2129,7 +2152,8 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * Was there a quiescent state since the beginning of the grace
 	 * period? If no, then exit and wait for the next call.
 	 */
-	if (!rdp->passed_quiesce)
+	if (!rdp->passed_quiesce &&
+	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
 		return;
 
 	/*
@@ -3174,9 +3198,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
-	    rdp->qs_pending && !rdp->passed_quiesce) {
+	    rdp->qs_pending && !rdp->passed_quiesce &&
+	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
 		rdp->n_rp_qs_pending++;
-	} else if (rdp->qs_pending && rdp->passed_quiesce) {
+	} else if (rdp->qs_pending &&
+		   (rdp->passed_quiesce ||
+		    rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
 		rdp->n_rp_report_qs++;
 		return 1;
 	}
@@ -3510,6 +3537,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 			rdp->gpnum = rnp->completed;
 			rdp->completed = rnp->completed;
 			rdp->passed_quiesce = 0;
+			rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 			rdp->qs_pending = 0;
 			trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 		}
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 7472ff388d5..1e7f8b05714 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -257,6 +257,8 @@ struct rcu_data {
 					/*  in order to detect GP end. */
 	unsigned long	gpnum;		/* Highest gp number that this CPU */
 					/*  is aware of having started. */
+	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
+					/*  for rcu_all_qs() invocations. */
 	bool		passed_quiesce;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 5cdc62e1bee..fbb6240509e 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -46,6 +46,8 @@
 #define RCU_TREE_NONCORE
 #include "tree.h"
 
+DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+
 static int r_open(struct inode *inode, struct file *file,
 					const struct seq_operations *op)
 {
@@ -115,11 +117,13 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d qp=%d",
+	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   ulong2long(rdp->completed), ulong2long(rdp->gpnum),
-		   rdp->passed_quiesce, rdp->qs_pending);
+		   rdp->passed_quiesce,
+		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
+		   rdp->qs_pending);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-- 
cgit v1.2.3-70-g09d2


From 0026b6551b51a9520b912f41b8d447b89a825f5a Mon Sep 17 00:00:00 2001
From: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Date: Sun, 4 Jan 2015 16:55:14 +0100
Subject: Bluetooth: Remove unused function

Remove the function hci_conn_change_link_key() that is not used anywhere.

This was partially found by using a static code analysis program called
cppcheck.

Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_conn.c         | 15 ---------------
 2 files changed, 16 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 1f21fe48b38..7777124bff5 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -781,7 +781,6 @@ int hci_conn_check_link_mode(struct hci_conn *conn);
 int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level);
 int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type,
 		      bool initiator);
-int hci_conn_change_link_key(struct hci_conn *conn);
 int hci_conn_switch_role(struct hci_conn *conn, __u8 role);
 
 void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 2e724e0b75b..c9b8fa54478 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1084,21 +1084,6 @@ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level)
 }
 EXPORT_SYMBOL(hci_conn_check_secure);
 
-/* Change link key */
-int hci_conn_change_link_key(struct hci_conn *conn)
-{
-	BT_DBG("hcon %p", conn);
-
-	if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
-		struct hci_cp_change_conn_link_key cp;
-		cp.handle = cpu_to_le16(conn->handle);
-		hci_send_cmd(conn->hdev, HCI_OP_CHANGE_CONN_LINK_KEY,
-			     sizeof(cp), &cp);
-	}
-
-	return 0;
-}
-
 /* Switch role */
 int hci_conn_switch_role(struct hci_conn *conn, __u8 role)
 {
-- 
cgit v1.2.3-70-g09d2


From 076c3b8e03e2737659a89660bb8e54e13587d974 Mon Sep 17 00:00:00 2001
From: James Ban <james.ban.opensource@diasemi.com>
Date: Fri, 16 Jan 2015 12:13:27 +0900
Subject: regulator: da9211: fix unmatched of_node

This is a patch for fixing unmatched of_node.

Signed-off-by: James Ban <james.ban.opensource@diasemi.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/da9211-regulator.c | 4 ++--
 include/linux/regulator/da9211.h     | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index c78d2106d6c..8e6957c63a6 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -276,7 +276,7 @@ static struct da9211_pdata *da9211_parse_regulators_dt(
 			continue;
 
 		pdata->init_data[n] = da9211_matches[i].init_data;
-
+		pdata->reg_node[n] = da9211_matches[i].of_node;
 		n++;
 	}
 
@@ -364,7 +364,7 @@ static int da9211_regulator_init(struct da9211 *chip)
 		config.dev = chip->dev;
 		config.driver_data = chip;
 		config.regmap = chip->regmap;
-		config.of_node = chip->dev->of_node;
+		config.of_node = chip->pdata->reg_node[i];
 
 		chip->rdev[i] = devm_regulator_register(chip->dev,
 			&da9211_regulators[i], &config);
diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h
index 5479394fefc..d1d9d3849bd 100644
--- a/include/linux/regulator/da9211.h
+++ b/include/linux/regulator/da9211.h
@@ -32,6 +32,7 @@ struct da9211_pdata {
 	 * 2 : 2 phase 2 buck
 	 */
 	int num_buck;
+	struct device_node *reg_node[DA9211_MAX_REGULATORS];
 	struct regulator_init_data *init_data[DA9211_MAX_REGULATORS];
 };
 #endif
-- 
cgit v1.2.3-70-g09d2


From 67c2b9cb30f561325b010e046b7bbe2a327e69a0 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Tue, 18 Nov 2014 12:18:18 +0100
Subject: ARM: 8207/1: amba: Use inlines instead of macros for
 amba_pclk_enable/disable

Replace the amba_pclk_enable and amba_pclk_disable macros with static
inline functions and remove checks for IS_ERR. The amba bus clock won't
be ERR because probe would fail before the use of these functions.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 include/linux/amba/bus.h | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 2afc618b15c..0ab5f8e0dea 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -92,11 +92,15 @@ struct amba_device *amba_find_device(const char *, struct device *, unsigned int
 int amba_request_regions(struct amba_device *, const char *);
 void amba_release_regions(struct amba_device *);
 
-#define amba_pclk_enable(d)	\
-	(IS_ERR((d)->pclk) ? 0 : clk_enable((d)->pclk))
+static inline int amba_pclk_enable(struct amba_device *dev)
+{
+	return clk_enable(dev->pclk);
+}
 
-#define amba_pclk_disable(d)	\
-	do { if (!IS_ERR((d)->pclk)) clk_disable((d)->pclk); } while (0)
+static inline void amba_pclk_disable(struct amba_device *dev)
+{
+	clk_disable(dev->pclk);
+}
 
 static inline int amba_pclk_prepare(struct amba_device *dev)
 {
-- 
cgit v1.2.3-70-g09d2


From 78e1f974dd351ac82d978e3aac2d27422013f914 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Sun, 14 Dec 2014 02:37:09 +0200
Subject: iommu/ipmmu-vmsa: Remove platform data support

No board file instantiates the IPMMU using platform data. Now that we
have DT support, get rid of platform data.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 drivers/iommu/ipmmu-vmsa.c               | 24 ------------------------
 include/linux/platform_data/ipmmu-vmsa.h | 24 ------------------------
 2 files changed, 48 deletions(-)
 delete mode 100644 include/linux/platform_data/ipmmu-vmsa.h

(limited to 'include')

diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 5d080cf11ba..791c3daec7c 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -17,7 +17,6 @@
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/platform_data/ipmmu-vmsa.h>
 #include <linux/platform_device.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
@@ -30,7 +29,6 @@ struct ipmmu_vmsa_device {
 	void __iomem *base;
 	struct list_head list;
 
-	const struct ipmmu_vmsa_platform_data *pdata;
 	unsigned int num_utlbs;
 
 	struct dma_iommu_mapping *mapping;
@@ -1015,27 +1013,6 @@ static int ipmmu_find_utlbs(struct ipmmu_vmsa_device *mmu, struct device *dev,
 	unsigned int i;
 	int count;
 
-	if (mmu->pdata) {
-		const struct ipmmu_vmsa_master *master = mmu->pdata->masters;
-		const char *devname = dev_name(dev);
-		unsigned int i;
-
-		for (i = 0; i < mmu->pdata->num_masters; ++i, ++master) {
-			if (strcmp(master->name, devname) == 0) {
-				utlbs = kmalloc(sizeof(*utlbs), GFP_KERNEL);
-				if (!utlbs)
-					return -ENOMEM;
-
-				utlbs[0] = master->utlb;
-
-				*_utlbs = utlbs;
-				return 1;
-			}
-		}
-
-		return -EINVAL;
-	}
-
 	count = of_count_phandle_with_args(dev->of_node, "iommus",
 					   "#iommu-cells");
 	if (count < 0)
@@ -1246,7 +1223,6 @@ static int ipmmu_probe(struct platform_device *pdev)
 	}
 
 	mmu->dev = &pdev->dev;
-	mmu->pdata = pdev->dev.platform_data;
 	mmu->num_utlbs = 32;
 
 	/* Map I/O memory and request IRQ. */
diff --git a/include/linux/platform_data/ipmmu-vmsa.h b/include/linux/platform_data/ipmmu-vmsa.h
deleted file mode 100644
index 5275b3ac6d3..00000000000
--- a/include/linux/platform_data/ipmmu-vmsa.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * IPMMU VMSA Platform Data
- *
- * Copyright (C) 2014 Renesas Electronics Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- */
-
-#ifndef __IPMMU_VMSA_H__
-#define __IPMMU_VMSA_H__
-
-struct ipmmu_vmsa_master {
-	const char *name;
-	unsigned int utlb;
-};
-
-struct ipmmu_vmsa_platform_data {
-	const struct ipmmu_vmsa_master *masters;
-	unsigned int num_masters;
-};
-
-#endif /* __IPMMU_VMSA_H__ */
-- 
cgit v1.2.3-70-g09d2


From f331a859e0ee5a898c1f47596eddad4c4f02d657 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Thu, 15 Jan 2015 18:16:04 -0600
Subject: PCI: Add flag for devices where we can't use bus reset

Enable a mechanism for devices to quirk that they do not behave when
doing a PCI bus reset.  We require a modest level of spec compliant
behavior in order to do a reset, for instance the device should come
out of reset without throwing errors and PCI config space should be
accessible after reset.  This is too much to ask for some devices.

Link: http://lkml.kernel.org/r/20140923210318.498dacbd@dualc.maya.org
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: stable@vger.kernel.org	# v3.14+
---
 drivers/pci/pci.c   | 40 ++++++++++++++++++++++++++++++++++++----
 include/linux/pci.h |  2 ++
 2 files changed, 38 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index cab05f31223..e9d4fd861ba 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3271,7 +3271,8 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 {
 	struct pci_dev *pdev;
 
-	if (pci_is_root_bus(dev->bus) || dev->subordinate || !dev->bus->self)
+	if (pci_is_root_bus(dev->bus) || dev->subordinate ||
+	    !dev->bus->self || dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
 		return -ENOTTY;
 
 	list_for_each_entry(pdev, &dev->bus->devices, bus_list)
@@ -3305,7 +3306,8 @@ static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe)
 {
 	struct pci_dev *pdev;
 
-	if (dev->subordinate || !dev->slot)
+	if (dev->subordinate || !dev->slot ||
+	    dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
 		return -ENOTTY;
 
 	list_for_each_entry(pdev, &dev->bus->devices, bus_list)
@@ -3557,6 +3559,20 @@ int pci_try_reset_function(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_try_reset_function);
 
+/* Do any devices on or below this bus prevent a bus reset? */
+static bool pci_bus_resetable(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
+		    (dev->subordinate && !pci_bus_resetable(dev->subordinate)))
+			return false;
+	}
+
+	return true;
+}
+
 /* Lock devices from the top of the tree down */
 static void pci_bus_lock(struct pci_bus *bus)
 {
@@ -3607,6 +3623,22 @@ unlock:
 	return 0;
 }
 
+/* Do any devices on or below this slot prevent a bus reset? */
+static bool pci_slot_resetable(struct pci_slot *slot)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
+		if (!dev->slot || dev->slot != slot)
+			continue;
+		if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET ||
+		    (dev->subordinate && !pci_bus_resetable(dev->subordinate)))
+			return false;
+	}
+
+	return true;
+}
+
 /* Lock devices from the top of the tree down */
 static void pci_slot_lock(struct pci_slot *slot)
 {
@@ -3728,7 +3760,7 @@ static int pci_slot_reset(struct pci_slot *slot, int probe)
 {
 	int rc;
 
-	if (!slot)
+	if (!slot || !pci_slot_resetable(slot))
 		return -ENOTTY;
 
 	if (!probe)
@@ -3820,7 +3852,7 @@ EXPORT_SYMBOL_GPL(pci_try_reset_slot);
 
 static int pci_bus_reset(struct pci_bus *bus, int probe)
 {
-	if (!bus->self)
+	if (!bus->self || !pci_bus_resetable(bus))
 		return -ENOTTY;
 
 	if (probe)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 360a966a97a..44627f1df4c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -175,6 +175,8 @@ enum pci_dev_flags {
 	PCI_DEV_FLAGS_DMA_ALIAS_DEVFN = (__force pci_dev_flags_t) (1 << 4),
 	/* Use a PCIe-to-PCI bridge alias even if !pci_is_pcie */
 	PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5),
+	/* Do not use bus resets for device */
+	PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6),
 };
 
 enum pci_irq_reroute_variant {
-- 
cgit v1.2.3-70-g09d2


From 8505e729a2f6eb0803ff943a15f133dd10afff3a Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Thu, 15 Jan 2015 16:21:49 -0600
Subject: PCI: Add pci_claim_bridge_resource() to clip window if necessary

Add pci_claim_bridge_resource() to claim a PCI-PCI bridge window.  This is
like regular pci_claim_resource(), except that if we fail to claim the
window, we check to see if we can reduce the size of the window and try
again.

This is for scenarios like this:

  pci_bus 0000:00: root bus resource [mem 0xc0000000-0xffffffff]
  pci 0000:00:01.0:   bridge window [mem 0xbdf00000-0xddefffff 64bit pref]
  pci 0000:01:00.0: reg 0x10: [mem 0xc0000000-0xcfffffff pref]

The 00:01.0 window is illegal: it starts before the host bridge window, so
we have to assume the [0xbdf00000-0xbfffffff] region is inaccessible.  We
can make it legal by clipping it to [mem 0xc0000000-0xddefffff 64bit pref].

Previously we discarded the 00:01.0 window and tried to reassign that part
of the hierarchy from scratch.  That is a problem because Linux doesn't
always assign things optimally.  For example, in this case, BIOS put the
01:00.0 device in a prefetchable window below 4GB, but after 5b28541552ef,
Linux puts the prefetchable window above 4GB where the 32-bit 01:00.0
device can't use it.

Clipping the 00:01.0 window is less intrusive than completely reassigning
things and is sufficient to let us use most of the BIOS configuration.  Of
course, it's possible that devices below 00:01.0 will no longer fit.  If
that's the case, we'll have to reassign things.  But that's a separate
problem.

[bhelgaas: changelog, split into separate patch]
Link: https://bugzilla.kernel.org/show_bug.cgi?id=85491
Reported-by: Marek Kordik <kordikmarek@gmail.com>
Fixes: 5b28541552ef ("PCI: Restrict 64-bit prefetchable bridge windows to 64-bit resources")
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: stable@vger.kernel.org	# v3.16+
---
 drivers/pci/setup-bus.c | 35 +++++++++++++++++++++++++++++++++++
 include/linux/pci.h     |  1 +
 2 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 802f56be214..e3e17f3c0f0 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -646,6 +646,41 @@ void pci_setup_bridge(struct pci_bus *bus)
 	__pci_setup_bridge(bus, type);
 }
 
+
+int pci_claim_bridge_resource(struct pci_dev *bridge, int i)
+{
+	if (i < PCI_BRIDGE_RESOURCES || i > PCI_BRIDGE_RESOURCE_END)
+		return 0;
+
+	if (pci_claim_resource(bridge, i) == 0)
+		return 0;	/* claimed the window */
+
+	if ((bridge->class >> 8) != PCI_CLASS_BRIDGE_PCI)
+		return 0;
+
+	if (!pci_bus_clip_resource(bridge, i))
+		return -EINVAL;	/* clipping didn't change anything */
+
+	switch (i - PCI_BRIDGE_RESOURCES) {
+	case 0:
+		pci_setup_bridge_io(bridge);
+		break;
+	case 1:
+		pci_setup_bridge_mmio(bridge);
+		break;
+	case 2:
+		pci_setup_bridge_mmio_pref(bridge);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (pci_claim_resource(bridge, i) == 0)
+		return 0;	/* claimed a smaller window */
+
+	return -EINVAL;
+}
+
 /* Check whether the bridge supports optional I/O and
    prefetchable memory ranges. If not, the respective
    base/limit registers must be read-only and read as 0. */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 44627f1df4c..9603094ed59 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1067,6 +1067,7 @@ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx);
 void pci_bus_assign_resources(const struct pci_bus *bus);
 void pci_bus_size_bridges(struct pci_bus *bus);
 int pci_claim_resource(struct pci_dev *, int);
+int pci_claim_bridge_resource(struct pci_dev *bridge, int i);
 void pci_assign_unassigned_resources(void);
 void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge);
 void pci_assign_unassigned_bus_resources(struct pci_bus *bus);
-- 
cgit v1.2.3-70-g09d2


From 51e537387990dc1f00752103f314fd135cb94bc6 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Fri, 21 Nov 2014 11:24:08 -0700
Subject: PCI: Add flag for devices that don't reset on D3hot->D0 transition

Per the PCI Power Management spec r1.2, sec 3.2.4, a device that advertises
No_Soft_Reset == 0 in the PMCSR register (reported by lspci as "NoSoftRst-")
should perform an internal reset when transitioning from D3hot to D0 via
software control.  Configuration context is lost and the device requires a
full reinitialization sequence.

Unfortunately the definition of "internal reset", beyond the application of
the configuration context, is largely left to the interpretation of the
specific device.  Some devices don't seem to perform an "internal reset"
even if they report No_Soft_Reset == 0.

We still need to honor the PCI specification and restore PCI config context
in the event that we do a PM reset, so we don't cache and modify the
PCI_PM_CTRL_NO_SOFT_RESET bit for the device, but for interfaces where the
intention is to reset the device, like pci_reset_function(), we need a
mechanism to flag that PM reset (a D3hot->D0 transition) doesn't perform
any significant "internal reset" of the device.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 2 +-
 include/linux/pci.h | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e9d4fd861ba..422bc0179e9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3197,7 +3197,7 @@ static int pci_pm_reset(struct pci_dev *dev, int probe)
 {
 	u16 csr;
 
-	if (!dev->pm_cap)
+	if (!dev->pm_cap || dev->dev_flags & PCI_DEV_FLAGS_NO_PM_RESET)
 		return -ENOTTY;
 
 	pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &csr);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 44627f1df4c..7bed32b3fd5 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -177,6 +177,8 @@ enum pci_dev_flags {
 	PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5),
 	/* Do not use bus resets for device */
 	PCI_DEV_FLAGS_NO_BUS_RESET = (__force pci_dev_flags_t) (1 << 6),
+	/* Do not use PM reset even if device advertises NoSoftRst- */
+	PCI_DEV_FLAGS_NO_PM_RESET = (__force pci_dev_flags_t) (1 << 7),
 };
 
 enum pci_irq_reroute_variant {
-- 
cgit v1.2.3-70-g09d2


From 6dee60f69d48fcef021b4b53b3431797ec440764 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:54 -0500
Subject: locks: add new struct list_head to struct file_lock

...that we can use to queue file_locks to per-ctx list_heads. Go ahead
and convert locks_delete_lock and locks_dispose_list to use it instead
of the fl_block list.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 fs/locks.c         | 8 +++++---
 include/linux/fs.h | 1 +
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index 59e2f905e4f..bfe5f17401d 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -207,6 +207,7 @@ static struct kmem_cache *filelock_cache __read_mostly;
 static void locks_init_lock_heads(struct file_lock *fl)
 {
 	INIT_HLIST_NODE(&fl->fl_link);
+	INIT_LIST_HEAD(&fl->fl_list);
 	INIT_LIST_HEAD(&fl->fl_block);
 	init_waitqueue_head(&fl->fl_wait);
 }
@@ -243,6 +244,7 @@ EXPORT_SYMBOL_GPL(locks_release_private);
 void locks_free_lock(struct file_lock *fl)
 {
 	BUG_ON(waitqueue_active(&fl->fl_wait));
+	BUG_ON(!list_empty(&fl->fl_list));
 	BUG_ON(!list_empty(&fl->fl_block));
 	BUG_ON(!hlist_unhashed(&fl->fl_link));
 
@@ -257,8 +259,8 @@ locks_dispose_list(struct list_head *dispose)
 	struct file_lock *fl;
 
 	while (!list_empty(dispose)) {
-		fl = list_first_entry(dispose, struct file_lock, fl_block);
-		list_del_init(&fl->fl_block);
+		fl = list_first_entry(dispose, struct file_lock, fl_list);
+		list_del_init(&fl->fl_list);
 		locks_free_lock(fl);
 	}
 }
@@ -691,7 +693,7 @@ static void locks_delete_lock(struct file_lock **thisfl_p,
 
 	locks_unlink_lock(thisfl_p);
 	if (dispose)
-		list_add(&fl->fl_block, dispose);
+		list_add(&fl->fl_list, dispose);
 	else
 		locks_free_lock(fl);
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42efe13077b..cd681811516 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -934,6 +934,7 @@ int locks_in_grace(struct net *);
  */
 struct file_lock {
 	struct file_lock *fl_next;	/* singly linked list for this inode  */
+	struct list_head fl_list;	/* link into file_lock_context */
 	struct hlist_node fl_link;	/* node in global lists */
 	struct list_head fl_block;	/* circular list of blocked processes */
 	fl_owner_t fl_owner;
-- 
cgit v1.2.3-70-g09d2


From 4a075e39c86490cc0f0c10ac6abe3592d1689463 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:54 -0500
Subject: locks: add a new struct file_locking_context pointer to struct inode

The current scheme of using the i_flock list is really difficult to
manage. There is also a legitimate desire for a per-inode spinlock to
manage these lists that isn't the i_lock.

Start conversion to a new scheme to eventually replace the old i_flock
list with a new "file_lock_context" object.

We start by adding a new i_flctx to struct inode. For now, it lives in
parallel with i_flock list, but will eventually replace it. The idea is
to allocate a structure to sit in that pointer and act as a locus for
all things file locking.

We allocate a file_lock_context for an inode when the first lock is
added to it, and it's only freed when the inode is freed. We use the
i_lock to protect the assignment, but afterward it should mostly be
accessed locklessly.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 fs/inode.c         |  3 ++-
 fs/locks.c         | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h | 11 +++++++++++
 3 files changed, 57 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/inode.c b/fs/inode.c
index aa149e7262a..f30872ade6d 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -194,7 +194,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 #ifdef CONFIG_FSNOTIFY
 	inode->i_fsnotify_mask = 0;
 #endif
-
+	inode->i_flctx = NULL;
 	this_cpu_inc(nr_inodes);
 
 	return 0;
@@ -237,6 +237,7 @@ void __destroy_inode(struct inode *inode)
 	BUG_ON(inode_has_buffers(inode));
 	security_inode_free(inode);
 	fsnotify_inode_delete(inode);
+	locks_free_lock_context(inode->i_flctx);
 	if (!inode->i_nlink) {
 		WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
 		atomic_long_dec(&inode->i_sb->s_remove_count);
diff --git a/fs/locks.c b/fs/locks.c
index ae1e7cf721d..526d5fca67c 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -202,8 +202,49 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
  */
 static DEFINE_SPINLOCK(blocked_lock_lock);
 
+static struct kmem_cache *flctx_cache __read_mostly;
 static struct kmem_cache *filelock_cache __read_mostly;
 
+static struct file_lock_context *
+locks_get_lock_context(struct inode *inode)
+{
+	struct file_lock_context *new;
+
+	if (likely(inode->i_flctx))
+		goto out;
+
+	new = kmem_cache_alloc(flctx_cache, GFP_KERNEL);
+	if (!new)
+		goto out;
+
+	INIT_LIST_HEAD(&new->flc_flock);
+
+	/*
+	 * Assign the pointer if it's not already assigned. If it is, then
+	 * free the context we just allocated.
+	 */
+	spin_lock(&inode->i_lock);
+	if (likely(!inode->i_flctx)) {
+		inode->i_flctx = new;
+		new = NULL;
+	}
+	spin_unlock(&inode->i_lock);
+
+	if (new)
+		kmem_cache_free(flctx_cache, new);
+out:
+	return inode->i_flctx;
+}
+
+void
+locks_free_lock_context(struct file_lock_context *ctx)
+{
+	if (ctx) {
+		WARN_ON_ONCE(!list_empty(&ctx->flc_flock));
+		kmem_cache_free(flctx_cache, ctx);
+	}
+}
+
 static void locks_init_lock_heads(struct file_lock *fl)
 {
 	INIT_HLIST_NODE(&fl->fl_link);
@@ -2636,6 +2677,9 @@ static int __init filelock_init(void)
 {
 	int i;
 
+	flctx_cache = kmem_cache_create("file_lock_ctx",
+			sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL);
+
 	filelock_cache = kmem_cache_create("file_lock_cache",
 			sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cd681811516..dec0d38b05d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -626,6 +626,7 @@ struct inode {
 #endif
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
 	struct file_lock	*i_flock;
+	struct file_lock_context	*i_flctx;
 	struct address_space	i_data;
 	struct list_head	i_devices;
 	union {
@@ -965,6 +966,10 @@ struct file_lock {
 	} fl_u;
 };
 
+struct file_lock_context {
+	struct list_head	flc_flock;
+};
+
 /* The following constant reflects the upper bound of the file/locking space */
 #ifndef OFFSET_MAX
 #define INT_LIMIT(x)	(~((x)1 << (sizeof(x)*8 - 1)))
@@ -991,6 +996,7 @@ extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
 extern int fcntl_getlease(struct file *filp);
 
 /* fs/locks.c */
+void locks_free_lock_context(struct file_lock_context *ctx);
 void locks_free_lock(struct file_lock *fl);
 extern void locks_init_lock(struct file_lock *);
 extern struct file_lock * locks_alloc_lock(void);
@@ -1048,6 +1054,11 @@ static inline int fcntl_getlease(struct file *filp)
 	return F_UNLCK;
 }
 
+static inline void
+locks_free_lock_context(struct file_lock_context *ctx)
+{
+}
+
 static inline void locks_init_lock(struct file_lock *fl)
 {
 	return;
-- 
cgit v1.2.3-70-g09d2


From bd61e0a9c852de2d705b6f1bb2cc54c5774db570 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:55 -0500
Subject: locks: convert posix locks to file_lock_context

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 fs/ceph/locks.c     |  58 +++++++++++++---------------
 fs/cifs/file.c      |  26 +++++--------
 fs/lockd/svcsubs.c  |  20 ++++++----
 fs/locks.c          | 108 +++++++++++++++++++++++++++-------------------------
 fs/nfs/delegation.c |  28 +++++---------
 fs/nfs/nfs4state.c  |  52 +++++--------------------
 fs/nfs/pagelist.c   |   8 ++--
 fs/nfs/write.c      |  30 +++++++--------
 fs/nfsd/nfs4state.c |  18 +++++----
 fs/read_write.c     |   2 +-
 include/linux/fs.h  |   3 +-
 11 files changed, 155 insertions(+), 198 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 917656ea8dc..19beeed8323 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -253,18 +253,15 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 	*fcntl_count = 0;
 	*flock_count = 0;
 
-	spin_lock(&inode->i_lock);
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX)
-			++(*fcntl_count);
-	}
-
 	ctx = inode->i_flctx;
 	if (ctx) {
+		spin_lock(&inode->i_lock);
+		list_for_each_entry(lock, &ctx->flc_posix, fl_list)
+			++(*fcntl_count);
 		list_for_each_entry(lock, &ctx->flc_flock, fl_list)
 			++(*flock_count);
+		spin_unlock(&inode->i_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	dout("counted %d flock locks and %d fcntl locks",
 	     *flock_count, *fcntl_count);
 }
@@ -279,7 +276,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 				int num_fcntl_locks, int num_flock_locks)
 {
 	struct file_lock *lock;
-	struct file_lock_context *ctx;
+	struct file_lock_context *ctx = inode->i_flctx;
 	int err = 0;
 	int seen_fcntl = 0;
 	int seen_flock = 0;
@@ -288,34 +285,31 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 	dout("encoding %d flock and %d fcntl locks", num_flock_locks,
 	     num_fcntl_locks);
 
+	if (!ctx)
+		return 0;
+
 	spin_lock(&inode->i_lock);
-	for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
-		if (lock->fl_flags & FL_POSIX) {
-			++seen_fcntl;
-			if (seen_fcntl > num_fcntl_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+		++seen_fcntl;
+		if (seen_fcntl > num_fcntl_locks) {
+			err = -ENOSPC;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
-
-	ctx = inode->i_flctx;
-	if (ctx) {
-		list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
-			++seen_flock;
-			if (seen_flock > num_flock_locks) {
-				err = -ENOSPC;
-				goto fail;
-			}
-			err = lock_to_ceph_filelock(lock, &flocks[l]);
-			if (err)
-				goto fail;
-			++l;
+	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+		++seen_flock;
+		if (seen_flock > num_flock_locks) {
+			err = -ENOSPC;
+			goto fail;
 		}
+		err = lock_to_ceph_filelock(lock, &flocks[l]);
+		if (err)
+			goto fail;
+		++l;
 	}
 fail:
 	spin_unlock(&inode->i_lock);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 96b7e9b7706..ea78f6f81ce 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1109,11 +1109,6 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 	return rc;
 }
 
-/* copied from fs/locks.c with a name change */
-#define cifs_for_each_lock(inode, lockp) \
-	for (lockp = &inode->i_flock; *lockp != NULL; \
-	     lockp = &(*lockp)->fl_next)
-
 struct lock_to_push {
 	struct list_head llist;
 	__u64 offset;
@@ -1128,8 +1123,9 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 {
 	struct inode *inode = cfile->dentry->d_inode;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
-	struct file_lock *flock, **before;
-	unsigned int count = 0, i = 0;
+	struct file_lock *flock;
+	struct file_lock_context *flctx = inode->i_flctx;
+	unsigned int count = 0, i;
 	int rc = 0, xid, type;
 	struct list_head locks_to_send, *el;
 	struct lock_to_push *lck, *tmp;
@@ -1137,10 +1133,12 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 
 	xid = get_xid();
 
+	if (!flctx)
+		goto out;
+
 	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		if ((*before)->fl_flags & FL_POSIX)
-			count++;
+	list_for_each(el, &flctx->flc_posix) {
+		count++;
 	}
 	spin_unlock(&inode->i_lock);
 
@@ -1151,7 +1149,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	 * added to the list while we are holding cinode->lock_sem that
 	 * protects locking operations of this inode.
 	 */
-	for (; i < count; i++) {
+	for (i = 0; i < count; i++) {
 		lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
 		if (!lck) {
 			rc = -ENOMEM;
@@ -1162,10 +1160,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 
 	el = locks_to_send.next;
 	spin_lock(&inode->i_lock);
-	cifs_for_each_lock(inode, before) {
-		flock = *before;
-		if ((flock->fl_flags & FL_POSIX) == 0)
-			continue;
+	list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
 		if (el == &locks_to_send) {
 			/*
 			 * The list ended. We don't have enough allocated
@@ -1185,7 +1180,6 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 		lck->length = length;
 		lck->type = type;
 		lck->offset = flock->fl_start;
-		el = el->next;
 	}
 	spin_unlock(&inode->i_lock);
 
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index d12ff4e2dbe..5300bb53835 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -164,12 +164,15 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 {
 	struct inode	 *inode = nlmsvc_file_inode(file);
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
 	struct nlm_host	 *lockhost;
 
+	if (!flctx || list_empty_careful(&flctx->flc_posix))
+		return 0;
 again:
 	file->f_locks = 0;
 	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl; fl = fl->fl_next) {
+	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
 		if (fl->fl_lmops != &nlmsvc_lock_operations)
 			continue;
 
@@ -223,18 +226,21 @@ nlm_file_inuse(struct nlm_file *file)
 {
 	struct inode	 *inode = nlmsvc_file_inode(file);
 	struct file_lock *fl;
+	struct file_lock_context *flctx = inode->i_flctx;
 
 	if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares)
 		return 1;
 
-	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl; fl = fl->fl_next) {
-		if (fl->fl_lmops == &nlmsvc_lock_operations) {
-			spin_unlock(&inode->i_lock);
-			return 1;
+	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
+		spin_lock(&inode->i_lock);
+		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+			if (fl->fl_lmops == &nlmsvc_lock_operations) {
+				spin_unlock(&inode->i_lock);
+				return 1;
+			}
 		}
+		spin_unlock(&inode->i_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	file->f_locks = 0;
 	return 0;
 }
diff --git a/fs/locks.c b/fs/locks.c
index 055df53f19d..e50bb4d9e75 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -157,9 +157,6 @@ static int target_leasetype(struct file_lock *fl)
 int leases_enable = 1;
 int lease_break_time = 45;
 
-#define for_each_lock(inode, lockp) \
-	for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next)
-
 /*
  * The global file_lock_list is only used for displaying /proc/locks, so we
  * keep a list on each CPU, with each list protected by its own spinlock via
@@ -218,6 +215,7 @@ locks_get_lock_context(struct inode *inode)
 		goto out;
 
 	INIT_LIST_HEAD(&new->flc_flock);
+	INIT_LIST_HEAD(&new->flc_posix);
 
 	/*
 	 * Assign the pointer if it's not already assigned. If it is, then
@@ -241,6 +239,7 @@ locks_free_lock_context(struct file_lock_context *ctx)
 {
 	if (ctx) {
 		WARN_ON_ONCE(!list_empty(&ctx->flc_flock));
+		WARN_ON_ONCE(!list_empty(&ctx->flc_posix));
 		kmem_cache_free(flctx_cache, ctx);
 	}
 }
@@ -809,21 +808,26 @@ void
 posix_test_lock(struct file *filp, struct file_lock *fl)
 {
 	struct file_lock *cfl;
+	struct file_lock_context *ctx;
 	struct inode *inode = file_inode(filp);
 
+	ctx = inode->i_flctx;
+	if (!ctx || list_empty_careful(&ctx->flc_posix)) {
+		fl->fl_type = F_UNLCK;
+		return;
+	}
+
 	spin_lock(&inode->i_lock);
-	for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) {
-		if (!IS_POSIX(cfl))
-			continue;
-		if (posix_locks_conflict(fl, cfl))
-			break;
+	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
+		if (posix_locks_conflict(fl, cfl)) {
+			locks_copy_conflock(fl, cfl);
+			if (cfl->fl_nspid)
+				fl->fl_pid = pid_vnr(cfl->fl_nspid);
+			goto out;
+		}
 	}
-	if (cfl) {
-		locks_copy_conflock(fl, cfl);
-		if (cfl->fl_nspid)
-			fl->fl_pid = pid_vnr(cfl->fl_nspid);
-	} else
-		fl->fl_type = F_UNLCK;
+	fl->fl_type = F_UNLCK;
+out:
 	spin_unlock(&inode->i_lock);
 	return;
 }
@@ -983,16 +987,20 @@ out:
 
 static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
 {
-	struct file_lock *fl;
+	struct file_lock *fl, *tmp;
 	struct file_lock *new_fl = NULL;
 	struct file_lock *new_fl2 = NULL;
 	struct file_lock *left = NULL;
 	struct file_lock *right = NULL;
-	struct file_lock **before;
+	struct file_lock_context *ctx;
 	int error;
 	bool added = false;
 	LIST_HEAD(dispose);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	/*
 	 * We may need two file_lock structures for this operation,
 	 * so we get them in advance to avoid races.
@@ -1013,8 +1021,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 	 * blocker's list of waiters and the global blocked_hash.
 	 */
 	if (request->fl_type != F_UNLCK) {
-		for_each_lock(inode, before) {
-			fl = *before;
+		list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 			if (!IS_POSIX(fl))
 				continue;
 			if (!posix_locks_conflict(request, fl))
@@ -1044,29 +1051,25 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 	if (request->fl_flags & FL_ACCESS)
 		goto out;
 
-	/*
-	 * Find the first old lock with the same owner as the new lock.
-	 */
-	
-	before = &inode->i_flock;
-
-	/* First skip locks owned by other processes.  */
-	while ((fl = *before) && (!IS_POSIX(fl) ||
-				  !posix_same_owner(request, fl))) {
-		before = &fl->fl_next;
+	/* Find the first old lock with the same owner as the new lock */
+	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
+		if (posix_same_owner(request, fl))
+			break;
 	}
 
 	/* Process locks with this owner. */
-	while ((fl = *before) && posix_same_owner(request, fl)) {
-		/* Detect adjacent or overlapping regions (if same lock type)
-		 */
+	list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) {
+		if (!posix_same_owner(request, fl))
+			break;
+
+		/* Detect adjacent or overlapping regions (if same lock type) */
 		if (request->fl_type == fl->fl_type) {
 			/* In all comparisons of start vs end, use
 			 * "start - 1" rather than "end + 1". If end
 			 * is OFFSET_MAX, end + 1 will become negative.
 			 */
 			if (fl->fl_end < request->fl_start - 1)
-				goto next_lock;
+				continue;
 			/* If the next lock in the list has entirely bigger
 			 * addresses than the new one, insert the lock here.
 			 */
@@ -1087,18 +1090,17 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			else
 				request->fl_end = fl->fl_end;
 			if (added) {
-				locks_delete_lock(before, &dispose);
+				locks_delete_lock_ctx(fl, &dispose);
 				continue;
 			}
 			request = fl;
 			added = true;
-		}
-		else {
+		} else {
 			/* Processing for different lock types is a bit
 			 * more complex.
 			 */
 			if (fl->fl_end < request->fl_start)
-				goto next_lock;
+				continue;
 			if (fl->fl_start > request->fl_end)
 				break;
 			if (request->fl_type == F_UNLCK)
@@ -1117,7 +1119,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				 * one (This may happen several times).
 				 */
 				if (added) {
-					locks_delete_lock(before, &dispose);
+					locks_delete_lock_ctx(fl, &dispose);
 					continue;
 				}
 				/*
@@ -1133,15 +1135,11 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				locks_copy_lock(new_fl, request);
 				request = new_fl;
 				new_fl = NULL;
-				locks_delete_lock(before, &dispose);
-				locks_insert_lock(before, request);
+				locks_insert_lock_ctx(request, &fl->fl_list);
+				locks_delete_lock_ctx(fl, &dispose);
 				added = true;
 			}
 		}
-		/* Go on to next lock.
-		 */
-	next_lock:
-		before = &fl->fl_next;
 	}
 
 	/*
@@ -1166,7 +1164,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			goto out;
 		}
 		locks_copy_lock(new_fl, request);
-		locks_insert_lock(before, new_fl);
+		locks_insert_lock_ctx(new_fl, &fl->fl_list);
 		new_fl = NULL;
 	}
 	if (right) {
@@ -1177,7 +1175,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			left = new_fl2;
 			new_fl2 = NULL;
 			locks_copy_lock(left, right);
-			locks_insert_lock(before, left);
+			locks_insert_lock_ctx(left, &fl->fl_list);
 		}
 		right->fl_start = request->fl_end + 1;
 		locks_wake_up_blocks(right);
@@ -1257,22 +1255,29 @@ EXPORT_SYMBOL(posix_lock_file_wait);
  */
 int locks_mandatory_locked(struct file *file)
 {
+	int ret;
 	struct inode *inode = file_inode(file);
+	struct file_lock_context *ctx;
 	struct file_lock *fl;
 
+	ctx = inode->i_flctx;
+	if (!ctx || list_empty_careful(&ctx->flc_posix))
+		return 0;
+
 	/*
 	 * Search the lock list for this inode for any POSIX locks.
 	 */
 	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!IS_POSIX(fl))
-			continue;
+	ret = 0;
+	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 		if (fl->fl_owner != current->files &&
-		    fl->fl_owner != file)
+		    fl->fl_owner != file) {
+			ret = -EAGAIN;
 			break;
+		}
 	}
 	spin_unlock(&inode->i_lock);
-	return fl ? -EAGAIN : 0;
+	return ret;
 }
 
 /**
@@ -2389,13 +2394,14 @@ out:
 void locks_remove_posix(struct file *filp, fl_owner_t owner)
 {
 	struct file_lock lock;
+	struct file_lock_context *ctx = file_inode(filp)->i_flctx;
 
 	/*
 	 * If there are no locks held on this file, we don't need to call
 	 * posix_lock_file().  Another process could be setting a lock on this
 	 * file at the same time, but we wouldn't remove that lock anyway.
 	 */
-	if (!file_inode(filp)->i_flock)
+	if (!ctx || list_empty(&ctx->flc_posix))
 		return;
 
 	lock.fl_type = F_UNLCK;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 9f9f67b17e2..3fb1caa3874 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -85,17 +85,17 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 {
 	struct inode *inode = state->inode;
 	struct file_lock *fl;
-	struct file_lock_context *flctx;
+	struct file_lock_context *flctx = inode->i_flctx;
+	struct list_head *list;
 	int status = 0;
 
-	if (inode->i_flock == NULL && inode->i_flctx == NULL)
+	if (flctx == NULL)
 		goto out;
 
-	/* Protect inode->i_flock using the i_lock */
+	list = &flctx->flc_posix;
 	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!(fl->fl_flags & (FL_POSIX)))
-			continue;
+restart:
+	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file) != ctx)
 			continue;
 		spin_unlock(&inode->i_lock);
@@ -104,19 +104,9 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 			goto out;
 		spin_lock(&inode->i_lock);
 	}
-
-	flctx = inode->i_flctx;
-	if (flctx) {
-		list_for_each_entry(fl, &flctx->flc_flock, fl_list) {
-			if (nfs_file_open_context(fl->fl_file) != ctx)
-				continue;
-			spin_unlock(&inode->i_lock);
-			status = nfs4_lock_delegation_recall(fl, state,
-								stateid);
-			if (status < 0)
-				goto out;
-			spin_lock(&inode->i_lock);
-		}
+	if (list == &flctx->flc_posix) {
+		list = &flctx->flc_flock;
+		goto restart;
 	}
 	spin_unlock(&inode->i_lock);
 out:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 65c404bf61a..6084c267f3a 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1367,53 +1367,18 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 	struct file_lock *fl;
 	int status = 0;
 	struct file_lock_context *flctx = inode->i_flctx;
+	struct list_head *list;
 
-	if (inode->i_flock == NULL && flctx == NULL)
+	if (flctx == NULL)
 		return 0;
 
+	list = &flctx->flc_posix;
+
 	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
-	/* Protect inode->i_flock using the BKL */
 	spin_lock(&inode->i_lock);
-	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
-		if (!(fl->fl_flags & FL_POSIX))
-			continue;
-		if (nfs_file_open_context(fl->fl_file)->state != state)
-			continue;
-		spin_unlock(&inode->i_lock);
-		status = ops->recover_lock(state, fl);
-		switch (status) {
-			case 0:
-				break;
-			case -ESTALE:
-			case -NFS4ERR_ADMIN_REVOKED:
-			case -NFS4ERR_STALE_STATEID:
-			case -NFS4ERR_BAD_STATEID:
-			case -NFS4ERR_EXPIRED:
-			case -NFS4ERR_NO_GRACE:
-			case -NFS4ERR_STALE_CLIENTID:
-			case -NFS4ERR_BADSESSION:
-			case -NFS4ERR_BADSLOT:
-			case -NFS4ERR_BAD_HIGH_SLOT:
-			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-				goto out;
-			default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d\n",
-					 __func__, status);
-			case -ENOMEM:
-			case -NFS4ERR_DENIED:
-			case -NFS4ERR_RECLAIM_BAD:
-			case -NFS4ERR_RECLAIM_CONFLICT:
-				/* kill_proc(fl->fl_pid, SIGLOST, 1); */
-				status = 0;
-		}
-		spin_lock(&inode->i_lock);
-	}
-
-	if (!flctx)
-		goto out_unlock;
-
-	list_for_each_entry(fl, &flctx->flc_flock, fl_list) {
+restart:
+	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
 		spin_unlock(&inode->i_lock);
@@ -1445,7 +1410,10 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 		}
 		spin_lock(&inode->i_lock);
 	}
-out_unlock:
+	if (list == &flctx->flc_posix) {
+		list = &flctx->flc_flock;
+		goto restart;
+	}
 	spin_unlock(&inode->i_lock);
 out:
 	up_write(&nfsi->rwsem);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index a3b62e15b44..29c7f33c9cf 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -831,12 +831,10 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 	if (prev) {
 		if (!nfs_match_open_context(req->wb_context, prev->wb_context))
 			return false;
-		if (req->wb_context->dentry->d_inode->i_flock != NULL &&
-		    !nfs_match_lock_context(req->wb_lock_context,
-					    prev->wb_lock_context))
-			return false;
 		flctx = req->wb_context->dentry->d_inode->i_flctx;
-		if (flctx != NULL && !list_empty_careful(&flctx->flc_flock) &&
+		if (flctx != NULL &&
+		    !(list_empty_careful(&flctx->flc_posix) &&
+		      list_empty_careful(&flctx->flc_flock)) &&
 		    !nfs_match_lock_context(req->wb_lock_context,
 					    prev->wb_lock_context))
 			return false;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e072aeb3419..784c13485b3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1091,6 +1091,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct nfs_lock_context *l_ctx;
+	struct file_lock_context *flctx = file_inode(file)->i_flctx;
 	struct nfs_page	*req;
 	int do_flush, status;
 	/*
@@ -1109,12 +1110,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		do_flush = req->wb_page != page || req->wb_context != ctx;
 		/* for now, flush if more than 1 request in page_group */
 		do_flush |= req->wb_this_page != req;
-		if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) {
-			do_flush |= l_ctx->lockowner.l_owner != current->files
-				|| l_ctx->lockowner.l_pid != current->tgid;
-		}
-		if (l_ctx && ctx->dentry->d_inode->i_flctx &&
-		    !list_empty_careful(&ctx->dentry->d_inode->i_flctx->flc_flock)) {
+		if (l_ctx && flctx &&
+		    !(list_empty_careful(&flctx->flc_posix) &&
+		      list_empty_careful(&flctx->flc_flock))) {
 			do_flush |= l_ctx->lockowner.l_owner != current->files
 				|| l_ctx->lockowner.l_pid != current->tgid;
 		}
@@ -1202,26 +1200,24 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino
 		return 0;
 	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
 		return 1;
-	if (!inode->i_flock && !flctx)
+	if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
+		       list_empty_careful(&flctx->flc_posix)))
 		return 0;
 
 	/* Check to see if there are whole file write locks */
-	spin_lock(&inode->i_lock);
 	ret = 0;
-
-	fl = inode->i_flock;
-	if (fl && is_whole_file_wrlock(fl)) {
-		ret = 1;
-		goto out;
-	}
-
-	if (!list_empty(&flctx->flc_flock)) {
+	spin_lock(&inode->i_lock);
+	if (!list_empty(&flctx->flc_posix)) {
+		fl = list_first_entry(&flctx->flc_posix, struct file_lock,
+					fl_list);
+		if (is_whole_file_wrlock(fl))
+			ret = 1;
+	} else if (!list_empty(&flctx->flc_flock)) {
 		fl = list_first_entry(&flctx->flc_flock, struct file_lock,
 					fl_list);
 		if (fl->fl_type == F_WRLCK)
 			ret = 1;
 	}
-out:
 	spin_unlock(&inode->i_lock);
 	return ret;
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c06a1ba80d7..fad82199136 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5556,10 +5556,11 @@ out_nfserr:
 static bool
 check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 {
-	struct file_lock **flpp;
+	struct file_lock *fl;
 	int status = false;
 	struct file *filp = find_any_file(fp);
 	struct inode *inode;
+	struct file_lock_context *flctx;
 
 	if (!filp) {
 		/* Any valid lock stateid should have some sort of access */
@@ -5568,15 +5569,18 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 	}
 
 	inode = file_inode(filp);
+	flctx = inode->i_flctx;
 
-	spin_lock(&inode->i_lock);
-	for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) {
-		if ((*flpp)->fl_owner == (fl_owner_t)lowner) {
-			status = true;
-			break;
+	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
+		spin_lock(&inode->i_lock);
+		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
+			if (fl->fl_owner == (fl_owner_t)lowner) {
+				status = true;
+				break;
+			}
 		}
+		spin_unlock(&inode->i_lock);
 	}
-	spin_unlock(&inode->i_lock);
 	fput(filp);
 	return status;
 }
diff --git a/fs/read_write.c b/fs/read_write.c
index c0805c93b6f..4060691e78f 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -358,7 +358,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 			return retval;
 	}
 
-	if (unlikely(inode->i_flock && mandatory_lock(inode))) {
+	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
 		retval = locks_mandatory_area(
 			read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
 			inode, file, pos, count);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dec0d38b05d..571f113588e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -968,6 +968,7 @@ struct file_lock {
 
 struct file_lock_context {
 	struct list_head	flc_flock;
+	struct list_head	flc_posix;
 };
 
 /* The following constant reflects the upper bound of the file/locking space */
@@ -1971,7 +1972,7 @@ static inline int locks_verify_truncate(struct inode *inode,
 				    struct file *filp,
 				    loff_t size)
 {
-	if (inode->i_flock && mandatory_lock(inode))
+	if (inode->i_flctx && mandatory_lock(inode))
 		return locks_mandatory_area(
 			FLOCK_VERIFY_WRITE, inode, filp,
 			size < inode->i_size ? size : inode->i_size,
-- 
cgit v1.2.3-70-g09d2


From 8634b51f6ca298fb8b07aa4847340764903533ab Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:55 -0500
Subject: locks: convert lease handling to file_lock_context

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 fs/locks.c         | 252 +++++++++++++++++++++--------------------------------
 include/linux/fs.h |   5 +-
 2 files changed, 102 insertions(+), 155 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index e50bb4d9e75..d46e70567b9 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -216,6 +216,7 @@ locks_get_lock_context(struct inode *inode)
 
 	INIT_LIST_HEAD(&new->flc_flock);
 	INIT_LIST_HEAD(&new->flc_posix);
+	INIT_LIST_HEAD(&new->flc_lease);
 
 	/*
 	 * Assign the pointer if it's not already assigned. If it is, then
@@ -240,6 +241,7 @@ locks_free_lock_context(struct file_lock_context *ctx)
 	if (ctx) {
 		WARN_ON_ONCE(!list_empty(&ctx->flc_flock));
 		WARN_ON_ONCE(!list_empty(&ctx->flc_posix));
+		WARN_ON_ONCE(!list_empty(&ctx->flc_lease));
 		kmem_cache_free(flctx_cache, ctx);
 	}
 }
@@ -677,22 +679,6 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 	spin_unlock(&blocked_lock_lock);
 }
 
-/* Insert file lock fl into an inode's lock list at the position indicated
- * by pos. At the same time add the lock to the global file lock list.
- *
- * Must be called with the i_lock held!
- */
-static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
-{
-	fl->fl_nspid = get_pid(task_tgid(current));
-
-	/* insert into file's list */
-	fl->fl_next = *pos;
-	*pos = fl;
-
-	locks_insert_global_locks(fl);
-}
-
 static void
 locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
 {
@@ -701,63 +687,28 @@ locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
 	locks_insert_global_locks(fl);
 }
 
-/**
- * locks_delete_lock - Delete a lock and then free it.
- * @thisfl_p: pointer that points to the fl_next field of the previous
- * 	      inode->i_flock list entry
- *
- * Unlink a lock from all lists and free the namespace reference, but don't
- * free it yet. Wake up processes that are blocked waiting for this lock and
- * notify the FS that the lock has been cleared.
- *
- * Must be called with the i_lock held!
- */
-static void locks_unlink_lock(struct file_lock **thisfl_p)
+static void
+locks_unlink_lock_ctx(struct file_lock *fl)
 {
-	struct file_lock *fl = *thisfl_p;
-
 	locks_delete_global_locks(fl);
-
-	*thisfl_p = fl->fl_next;
-	fl->fl_next = NULL;
-
+	list_del_init(&fl->fl_list);
 	if (fl->fl_nspid) {
 		put_pid(fl->fl_nspid);
 		fl->fl_nspid = NULL;
 	}
-
 	locks_wake_up_blocks(fl);
 }
 
-/*
- * Unlink a lock from all lists and free it.
- *
- * Must be called with i_lock held!
- */
-static void locks_delete_lock(struct file_lock **thisfl_p,
-			      struct list_head *dispose)
+static void
+locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
 {
-	struct file_lock *fl = *thisfl_p;
-
-	locks_unlink_lock(thisfl_p);
+	locks_unlink_lock_ctx(fl);
 	if (dispose)
 		list_add(&fl->fl_list, dispose);
 	else
 		locks_free_lock(fl);
 }
 
-static void
-locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
-{
-	locks_delete_global_locks(fl);
-	if (fl->fl_nspid) {
-		put_pid(fl->fl_nspid);
-		fl->fl_nspid = NULL;
-	}
-	locks_wake_up_blocks(fl);
-	list_move(&fl->fl_list, dispose);
-}
-
 /* Determine if lock sys_fl blocks lock caller_fl. Common functionality
  * checks for shared/exclusive status of overlapping locks.
  */
@@ -1376,7 +1327,7 @@ int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock(before, dispose);
+		locks_delete_lock_ctx(fl, dispose);
 	}
 	return 0;
 }
@@ -1392,20 +1343,17 @@ static bool past_time(unsigned long then)
 
 static void time_out_leases(struct inode *inode, struct list_head *dispose)
 {
-	struct file_lock **before;
-	struct file_lock *fl;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl, *tmp;
 
 	lockdep_assert_held(&inode->i_lock);
 
-	before = &inode->i_flock;
-	while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) {
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
-			lease_modify(before, F_RDLCK, dispose);
+			lease_modify(&fl, F_RDLCK, dispose);
 		if (past_time(fl->fl_break_time))
-			lease_modify(before, F_UNLCK, dispose);
-		if (fl == *before)	/* lease_modify may have freed fl */
-			before = &fl->fl_next;
+			lease_modify(&fl, F_UNLCK, dispose);
 	}
 }
 
@@ -1419,11 +1367,12 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 static bool
 any_leases_conflict(struct inode *inode, struct file_lock *breaker)
 {
+	struct file_lock_context *ctx = inode->i_flctx;
 	struct file_lock *fl;
 
 	lockdep_assert_held(&inode->i_lock);
 
-	for (fl = inode->i_flock ; fl && IS_LEASE(fl); fl = fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (leases_conflict(fl, breaker))
 			return true;
 	}
@@ -1447,7 +1396,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 {
 	int error = 0;
 	struct file_lock *new_fl;
-	struct file_lock *fl, **before;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl;
 	unsigned long break_time;
 	int want_write = (mode & O_ACCMODE) != O_RDONLY;
 	LIST_HEAD(dispose);
@@ -1457,6 +1407,12 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 		return PTR_ERR(new_fl);
 	new_fl->fl_flags = type;
 
+	/* typically we will check that ctx is non-NULL before calling */
+	if (!ctx) {
+		WARN_ON_ONCE(1);
+		return error;
+	}
+
 	spin_lock(&inode->i_lock);
 
 	time_out_leases(inode, &dispose);
@@ -1471,9 +1427,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			break_time++;	/* so that 0 means no break time */
 	}
 
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (!leases_conflict(fl, new_fl))
 			continue;
 		if (want_write) {
@@ -1482,17 +1436,16 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			fl->fl_flags |= FL_UNLOCK_PENDING;
 			fl->fl_break_time = break_time;
 		} else {
-			if (lease_breaking(inode->i_flock))
+			if (lease_breaking(fl))
 				continue;
 			fl->fl_flags |= FL_DOWNGRADE_PENDING;
 			fl->fl_downgrade_time = break_time;
 		}
 		if (fl->fl_lmops->lm_break(fl))
-			locks_delete_lock(before, &dispose);
+			locks_delete_lock_ctx(fl, &dispose);
 	}
 
-	fl = inode->i_flock;
-	if (!fl || !IS_LEASE(fl))
+	if (list_empty(&ctx->flc_lease))
 		goto out;
 
 	if (mode & O_NONBLOCK) {
@@ -1502,12 +1455,13 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 	}
 
 restart:
-	break_time = inode->i_flock->fl_break_time;
+	fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list);
+	break_time = fl->fl_break_time;
 	if (break_time != 0)
 		break_time -= jiffies;
 	if (break_time == 0)
 		break_time++;
-	locks_insert_block(inode->i_flock, new_fl);
+	locks_insert_block(fl, new_fl);
 	trace_break_lease_block(inode, new_fl);
 	spin_unlock(&inode->i_lock);
 	locks_dispose_list(&dispose);
@@ -1525,10 +1479,8 @@ restart:
 			time_out_leases(inode, &dispose);
 		if (any_leases_conflict(inode, new_fl))
 			goto restart;
-
 		error = 0;
 	}
-
 out:
 	spin_unlock(&inode->i_lock);
 	locks_dispose_list(&dispose);
@@ -1550,13 +1502,17 @@ EXPORT_SYMBOL(__break_lease);
 void lease_get_mtime(struct inode *inode, struct timespec *time)
 {
 	bool has_lease = false;
-	struct file_lock *flock;
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl;
 
-	if (inode->i_flock) {
+	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
 		spin_lock(&inode->i_lock);
-		flock = inode->i_flock;
-		if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK))
-			has_lease = true;
+		if (!list_empty(&ctx->flc_lease)) {
+			fl = list_first_entry(&ctx->flc_lease,
+						struct file_lock, fl_list);
+			if (fl->fl_type == F_WRLCK)
+				has_lease = true;
+		}
 		spin_unlock(&inode->i_lock);
 	}
 
@@ -1595,20 +1551,22 @@ int fcntl_getlease(struct file *filp)
 {
 	struct file_lock *fl;
 	struct inode *inode = file_inode(filp);
+	struct file_lock_context *ctx = inode->i_flctx;
 	int type = F_UNLCK;
 	LIST_HEAD(dispose);
 
-	spin_lock(&inode->i_lock);
-	time_out_leases(file_inode(filp), &dispose);
-	for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl);
-			fl = fl->fl_next) {
-		if (fl->fl_file == filp) {
+	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
+		spin_lock(&inode->i_lock);
+		time_out_leases(file_inode(filp), &dispose);
+		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+			if (fl->fl_file != filp)
+				continue;
 			type = target_leasetype(fl);
 			break;
 		}
+		spin_unlock(&inode->i_lock);
+		locks_dispose_list(&dispose);
 	}
-	spin_unlock(&inode->i_lock);
-	locks_dispose_list(&dispose);
 	return type;
 }
 
@@ -1641,9 +1599,10 @@ check_conflicting_open(const struct dentry *dentry, const long arg)
 static int
 generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv)
 {
-	struct file_lock *fl, **before, **my_before = NULL, *lease;
+	struct file_lock *fl, *my_fl = NULL, *lease;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	struct file_lock_context *ctx;
 	bool is_deleg = (*flp)->fl_flags & FL_DELEG;
 	int error;
 	LIST_HEAD(dispose);
@@ -1651,6 +1610,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	lease = *flp;
 	trace_generic_add_lease(inode, lease);
 
+	ctx = locks_get_lock_context(inode);
+	if (!ctx)
+		return -ENOMEM;
+
 	/*
 	 * In the delegation case we need mutual exclusion with
 	 * a number of operations that take the i_mutex.  We trylock
@@ -1684,13 +1647,12 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * except for this filp.
 	 */
 	error = -EAGAIN;
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (fl->fl_file == filp) {
-			my_before = before;
+			my_fl = fl;
 			continue;
 		}
+
 		/*
 		 * No exclusive leases if someone else has a lease on
 		 * this file:
@@ -1705,9 +1667,8 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 			goto out;
 	}
 
-	if (my_before != NULL) {
-		lease = *my_before;
-		error = lease->fl_lmops->lm_change(my_before, arg, &dispose);
+	if (my_fl != NULL) {
+		error = lease->fl_lmops->lm_change(&my_fl, arg, &dispose);
 		if (error)
 			goto out;
 		goto out_setup;
@@ -1717,7 +1678,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	if (!leases_enable)
 		goto out;
 
-	locks_insert_lock(before, lease);
+	locks_insert_lock_ctx(lease, &ctx->flc_lease);
 	/*
 	 * The check in break_lease() is lockless. It's possible for another
 	 * open to race in after we did the earlier check for a conflicting
@@ -1729,8 +1690,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 */
 	smp_mb();
 	error = check_conflicting_open(dentry, arg);
-	if (error)
-		goto out_unlink;
+	if (error) {
+		locks_unlink_lock_ctx(lease);
+		goto out;
+	}
 
 out_setup:
 	if (lease->fl_lmops->lm_setup)
@@ -1740,33 +1703,35 @@ out:
 	locks_dispose_list(&dispose);
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
-	if (!error && !my_before)
+	if (!error && !my_fl)
 		*flp = NULL;
 	return error;
-out_unlink:
-	locks_unlink_lock(before);
-	goto out;
 }
 
 static int generic_delete_lease(struct file *filp)
 {
 	int error = -EAGAIN;
-	struct file_lock *fl, **before;
+	struct file_lock *fl, *victim = NULL;
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
+	struct file_lock_context *ctx = inode->i_flctx;
 	LIST_HEAD(dispose);
 
+	if (!ctx) {
+		trace_generic_delete_lease(inode, NULL);
+		return error;
+	}
+
 	spin_lock(&inode->i_lock);
-	time_out_leases(inode, &dispose);
-	for (before = &inode->i_flock;
-			((fl = *before) != NULL) && IS_LEASE(fl);
-			before = &fl->fl_next) {
-		if (fl->fl_file == filp)
+	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
+		if (fl->fl_file == filp) {
+			victim = fl;
 			break;
+		}
 	}
 	trace_generic_delete_lease(inode, fl);
-	if (fl && IS_LEASE(fl))
-		error = fl->fl_lmops->lm_change(before, F_UNLCK, &dispose);
+	if (victim)
+		error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose);
 	spin_unlock(&inode->i_lock);
 	locks_dispose_list(&dispose);
 	return error;
@@ -2447,56 +2412,37 @@ locks_remove_flock(struct file *filp)
 		fl.fl_ops->fl_release_private(&fl);
 }
 
+static void
+locks_remove_lease(struct file *filp)
+{
+	struct inode *inode = file_inode(filp);
+	struct file_lock_context *ctx = inode->i_flctx;
+	struct file_lock *fl, *tmp;
+	LIST_HEAD(dispose);
+
+	if (!ctx || list_empty(&ctx->flc_lease))
+		return;
+
+	spin_lock(&inode->i_lock);
+	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
+		lease_modify(&fl, F_UNLCK, &dispose);
+	spin_unlock(&inode->i_lock);
+	locks_dispose_list(&dispose);
+}
+
 /*
  * This function is called on the last close of an open file.
  */
 void locks_remove_file(struct file *filp)
 {
-	struct inode * inode = file_inode(filp);
-	struct file_lock *fl;
-	struct file_lock **before;
-	LIST_HEAD(dispose);
-
 	/* remove any OFD locks */
 	locks_remove_posix(filp, filp);
 
 	/* remove flock locks */
 	locks_remove_flock(filp);
 
-	if (!inode->i_flock)
-		return;
-
-	spin_lock(&inode->i_lock);
-	before = &inode->i_flock;
-
-	while ((fl = *before) != NULL) {
-		if (fl->fl_file == filp) {
-			if (IS_LEASE(fl)) {
-				lease_modify(before, F_UNLCK, &dispose);
-				continue;
-			}
-
-			/*
-			 * There's a leftover lock on the list of a type that
-			 * we didn't expect to see. Most likely a classic
-			 * POSIX lock that ended up not getting released
-			 * properly, or that raced onto the list somehow. Log
-			 * some info about it and then just remove it from
-			 * the list.
-			 */
-			WARN(1, "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n",
-				MAJOR(inode->i_sb->s_dev),
-				MINOR(inode->i_sb->s_dev), inode->i_ino,
-				fl->fl_type, fl->fl_flags,
-				fl->fl_start, fl->fl_end);
-
-			locks_delete_lock(before, &dispose);
-			continue;
- 		}
-		before = &fl->fl_next;
-	}
-	spin_unlock(&inode->i_lock);
-	locks_dispose_list(&dispose);
+	/* remove any leases */
+	locks_remove_lease(filp);
 }
 
 /**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 571f113588e..2ddec3cf81b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -969,6 +969,7 @@ struct file_lock {
 struct file_lock_context {
 	struct list_head	flc_flock;
 	struct list_head	flc_posix;
+	struct list_head	flc_lease;
 };
 
 /* The following constant reflects the upper bound of the file/locking space */
@@ -1990,7 +1991,7 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 	 * end up racing with tasks trying to set a new lease on this file.
 	 */
 	smp_mb();
-	if (inode->i_flock)
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
 		return __break_lease(inode, mode, FL_LEASE);
 	return 0;
 }
@@ -2003,7 +2004,7 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 	 * end up racing with tasks trying to set a new lease on this file.
 	 */
 	smp_mb();
-	if (inode->i_flock)
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
 		return __break_lease(inode, mode, FL_DELEG);
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From a7231a97467d5a0c36f82f581c76c12c034e4b80 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:56 -0500
Subject: locks: remove i_flock field from struct inode

Nothing uses it anymore. Also add a forward declaration for struct
file_lock to silence some compiler warnings that the removal triggers.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/fs.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2ddec3cf81b..ce0873af0b9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -625,7 +625,6 @@ struct inode {
 	atomic_t		i_readcount; /* struct files open RO */
 #endif
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
-	struct file_lock	*i_flock;
 	struct file_lock_context	*i_flctx;
 	struct address_space	i_data;
 	struct list_head	i_devices;
@@ -886,6 +885,8 @@ static inline struct file *get_file(struct file *f)
 /* legacy typedef, should eventually be removed */
 typedef void *fl_owner_t;
 
+struct file_lock;
+
 struct file_lock_operations {
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 	void (*fl_release_private)(struct file_lock *);
-- 
cgit v1.2.3-70-g09d2


From 6109c85037e53443f29fd39c0de69f578a1cf285 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:57 -0500
Subject: locks: add a dedicated spinlock to protect i_flctx lists

We can now add a dedicated spinlock without expanding struct inode.
Change to using that to protect the various i_flctx lists.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 fs/ceph/locks.c     |  8 ++---
 fs/cifs/file.c      |  8 ++---
 fs/lockd/svcsubs.c  | 12 ++++----
 fs/locks.c          | 87 +++++++++++++++++++++++++++--------------------------
 fs/nfs/delegation.c |  8 ++---
 fs/nfs/nfs4state.c  |  8 ++---
 fs/nfs/write.c      |  4 +--
 fs/nfsd/nfs4state.c |  4 +--
 include/linux/fs.h  |  1 +
 9 files changed, 71 insertions(+), 69 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 19beeed8323..0303da8e323 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -255,12 +255,12 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 
 	ctx = inode->i_flctx;
 	if (ctx) {
-		spin_lock(&inode->i_lock);
+		spin_lock(&ctx->flc_lock);
 		list_for_each_entry(lock, &ctx->flc_posix, fl_list)
 			++(*fcntl_count);
 		list_for_each_entry(lock, &ctx->flc_flock, fl_list)
 			++(*flock_count);
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&ctx->flc_lock);
 	}
 	dout("counted %d flock locks and %d fcntl locks",
 	     *flock_count, *fcntl_count);
@@ -288,7 +288,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 	if (!ctx)
 		return 0;
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
@@ -312,7 +312,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 		++l;
 	}
 fail:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	return err;
 }
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ea78f6f81ce..b65166eb111 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1136,11 +1136,11 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	if (!flctx)
 		goto out;
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&flctx->flc_lock);
 	list_for_each(el, &flctx->flc_posix) {
 		count++;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	INIT_LIST_HEAD(&locks_to_send);
 
@@ -1159,7 +1159,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	}
 
 	el = locks_to_send.next;
-	spin_lock(&inode->i_lock);
+	spin_lock(&flctx->flc_lock);
 	list_for_each_entry(flock, &flctx->flc_posix, fl_list) {
 		if (el == &locks_to_send) {
 			/*
@@ -1181,7 +1181,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 		lck->type = type;
 		lck->offset = flock->fl_start;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
 		int stored_rc;
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 5300bb53835..665ef5a0518 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -171,7 +171,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 		return 0;
 again:
 	file->f_locks = 0;
-	spin_lock(&inode->i_lock);
+	spin_lock(&flctx->flc_lock);
 	list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
 		if (fl->fl_lmops != &nlmsvc_lock_operations)
 			continue;
@@ -183,7 +183,7 @@ again:
 		if (match(lockhost, host)) {
 			struct file_lock lock = *fl;
 
-			spin_unlock(&inode->i_lock);
+			spin_unlock(&flctx->flc_lock);
 			lock.fl_type  = F_UNLCK;
 			lock.fl_start = 0;
 			lock.fl_end   = OFFSET_MAX;
@@ -195,7 +195,7 @@ again:
 			goto again;
 		}
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 
 	return 0;
 }
@@ -232,14 +232,14 @@ nlm_file_inuse(struct nlm_file *file)
 		return 1;
 
 	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
 			if (fl->fl_lmops == &nlmsvc_lock_operations) {
-				spin_unlock(&inode->i_lock);
+				spin_unlock(&flctx->flc_lock);
 				return 1;
 			}
 		}
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 	}
 	file->f_locks = 0;
 	return 0;
diff --git a/fs/locks.c b/fs/locks.c
index d46e70567b9..a268d959ccd 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -161,7 +161,7 @@ int lease_break_time = 45;
  * The global file_lock_list is only used for displaying /proc/locks, so we
  * keep a list on each CPU, with each list protected by its own spinlock via
  * the file_lock_lglock. Note that alterations to the list also require that
- * the relevant i_lock is held.
+ * the relevant flc_lock is held.
  */
 DEFINE_STATIC_LGLOCK(file_lock_lglock);
 static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
@@ -189,13 +189,13 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
  * contrast to those that are acting as records of acquired locks).
  *
  * Note that when we acquire this lock in order to change the above fields,
- * we often hold the i_lock as well. In certain cases, when reading the fields
+ * we often hold the flc_lock as well. In certain cases, when reading the fields
  * protected by this lock, we can skip acquiring it iff we already hold the
- * i_lock.
+ * flc_lock.
  *
  * In particular, adding an entry to the fl_block list requires that you hold
- * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting
- * an entry from the list however only requires the file_lock_lock.
+ * both the flc_lock and the blocked_lock_lock (acquired in that order).
+ * Deleting an entry from the list however only requires the file_lock_lock.
  */
 static DEFINE_SPINLOCK(blocked_lock_lock);
 
@@ -214,6 +214,7 @@ locks_get_lock_context(struct inode *inode)
 	if (!new)
 		goto out;
 
+	spin_lock_init(&new->flc_lock);
 	INIT_LIST_HEAD(&new->flc_flock);
 	INIT_LIST_HEAD(&new->flc_posix);
 	INIT_LIST_HEAD(&new->flc_lease);
@@ -557,7 +558,7 @@ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2)
 	return fl1->fl_owner == fl2->fl_owner;
 }
 
-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
 static void locks_insert_global_locks(struct file_lock *fl)
 {
 	lg_local_lock(&file_lock_lglock);
@@ -566,12 +567,12 @@ static void locks_insert_global_locks(struct file_lock *fl)
 	lg_local_unlock(&file_lock_lglock);
 }
 
-/* Must be called with the i_lock held! */
+/* Must be called with the flc_lock held! */
 static void locks_delete_global_locks(struct file_lock *fl)
 {
 	/*
 	 * Avoid taking lock if already unhashed. This is safe since this check
-	 * is done while holding the i_lock, and new insertions into the list
+	 * is done while holding the flc_lock, and new insertions into the list
 	 * also require that it be held.
 	 */
 	if (hlist_unhashed(&fl->fl_link))
@@ -623,10 +624,10 @@ static void locks_delete_block(struct file_lock *waiter)
  * the order they blocked. The documentation doesn't require this but
  * it seems like the reasonable thing to do.
  *
- * Must be called with both the i_lock and blocked_lock_lock held. The fl_block
- * list itself is protected by the blocked_lock_lock, but by ensuring that the
- * i_lock is also held on insertions we can avoid taking the blocked_lock_lock
- * in some cases when we see that the fl_block list is empty.
+ * Must be called with both the flc_lock and blocked_lock_lock held. The
+ * fl_block list itself is protected by the blocked_lock_lock, but by ensuring
+ * that the flc_lock is also held on insertions we can avoid taking the
+ * blocked_lock_lock in some cases when we see that the fl_block list is empty.
  */
 static void __locks_insert_block(struct file_lock *blocker,
 					struct file_lock *waiter)
@@ -638,7 +639,7 @@ static void __locks_insert_block(struct file_lock *blocker,
 		locks_insert_global_blocked(waiter);
 }
 
-/* Must be called with i_lock held. */
+/* Must be called with flc_lock held. */
 static void locks_insert_block(struct file_lock *blocker,
 					struct file_lock *waiter)
 {
@@ -650,15 +651,15 @@ static void locks_insert_block(struct file_lock *blocker,
 /*
  * Wake up processes blocked waiting for blocker.
  *
- * Must be called with the inode->i_lock held!
+ * Must be called with the inode->flc_lock held!
  */
 static void locks_wake_up_blocks(struct file_lock *blocker)
 {
 	/*
 	 * Avoid taking global lock if list is empty. This is safe since new
-	 * blocked requests are only added to the list under the i_lock, and
-	 * the i_lock is always held here. Note that removal from the fl_block
-	 * list does not require the i_lock, so we must recheck list_empty()
+	 * blocked requests are only added to the list under the flc_lock, and
+	 * the flc_lock is always held here. Note that removal from the fl_block
+	 * list does not require the flc_lock, so we must recheck list_empty()
 	 * after acquiring the blocked_lock_lock.
 	 */
 	if (list_empty(&blocker->fl_block))
@@ -768,7 +769,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 		return;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(cfl, &ctx->flc_posix, fl_list) {
 		if (posix_locks_conflict(fl, cfl)) {
 			locks_copy_conflock(fl, cfl);
@@ -779,7 +780,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
 	}
 	fl->fl_type = F_UNLCK;
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	return;
 }
 EXPORT_SYMBOL(posix_test_lock);
@@ -880,7 +881,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
 			return -ENOMEM;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	if (request->fl_flags & FL_ACCESS)
 		goto find_conflict;
 
@@ -905,9 +906,9 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
 	 * give it the opportunity to lock the file.
 	 */
 	if (found) {
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&ctx->flc_lock);
 		cond_resched();
-		spin_lock(&inode->i_lock);
+		spin_lock(&ctx->flc_lock);
 	}
 
 find_conflict:
@@ -929,7 +930,7 @@ find_conflict:
 	error = 0;
 
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	if (new_fl)
 		locks_free_lock(new_fl);
 	locks_dispose_list(&dispose);
@@ -965,7 +966,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 		new_fl2 = locks_alloc_lock();
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	/*
 	 * New lock request. Walk all POSIX locks and look for conflicts. If
 	 * there are any, either return error or put the request on the
@@ -1136,7 +1137,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 		locks_wake_up_blocks(left);
 	}
  out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	/*
 	 * Free any unused locks.
 	 */
@@ -1218,7 +1219,7 @@ int locks_mandatory_locked(struct file *file)
 	/*
 	 * Search the lock list for this inode for any POSIX locks.
 	 */
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	ret = 0;
 	list_for_each_entry(fl, &ctx->flc_posix, fl_list) {
 		if (fl->fl_owner != current->files &&
@@ -1227,7 +1228,7 @@ int locks_mandatory_locked(struct file *file)
 			break;
 		}
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	return ret;
 }
 
@@ -1346,7 +1347,7 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
 	struct file_lock_context *ctx = inode->i_flctx;
 	struct file_lock *fl, *tmp;
 
-	lockdep_assert_held(&inode->i_lock);
+	lockdep_assert_held(&ctx->flc_lock);
 
 	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
 		trace_time_out_leases(inode, fl);
@@ -1370,7 +1371,7 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker)
 	struct file_lock_context *ctx = inode->i_flctx;
 	struct file_lock *fl;
 
-	lockdep_assert_held(&inode->i_lock);
+	lockdep_assert_held(&ctx->flc_lock);
 
 	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (leases_conflict(fl, breaker))
@@ -1413,7 +1414,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 		return error;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 
 	time_out_leases(inode, &dispose);
 
@@ -1463,11 +1464,11 @@ restart:
 		break_time++;
 	locks_insert_block(fl, new_fl);
 	trace_break_lease_block(inode, new_fl);
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	trace_break_lease_unblock(inode, new_fl);
 	locks_delete_block(new_fl);
 	if (error >= 0) {
@@ -1482,7 +1483,7 @@ restart:
 		error = 0;
 	}
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	locks_free_lock(new_fl);
 	return error;
@@ -1506,14 +1507,14 @@ void lease_get_mtime(struct inode *inode, struct timespec *time)
 	struct file_lock *fl;
 
 	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
-		spin_lock(&inode->i_lock);
+		spin_lock(&ctx->flc_lock);
 		if (!list_empty(&ctx->flc_lease)) {
 			fl = list_first_entry(&ctx->flc_lease,
 						struct file_lock, fl_list);
 			if (fl->fl_type == F_WRLCK)
 				has_lease = true;
 		}
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&ctx->flc_lock);
 	}
 
 	if (has_lease)
@@ -1556,7 +1557,7 @@ int fcntl_getlease(struct file *filp)
 	LIST_HEAD(dispose);
 
 	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
-		spin_lock(&inode->i_lock);
+		spin_lock(&ctx->flc_lock);
 		time_out_leases(file_inode(filp), &dispose);
 		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 			if (fl->fl_file != filp)
@@ -1564,7 +1565,7 @@ int fcntl_getlease(struct file *filp)
 			type = target_leasetype(fl);
 			break;
 		}
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&ctx->flc_lock);
 		locks_dispose_list(&dispose);
 	}
 	return type;
@@ -1632,7 +1633,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 		return -EINVAL;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
 	error = check_conflicting_open(dentry, arg);
 	if (error)
@@ -1699,7 +1700,7 @@ out_setup:
 	if (lease->fl_lmops->lm_setup)
 		lease->fl_lmops->lm_setup(lease, priv);
 out:
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
@@ -1722,7 +1723,7 @@ static int generic_delete_lease(struct file *filp)
 		return error;
 	}
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (fl->fl_file == filp) {
 			victim = fl;
@@ -1732,7 +1733,7 @@ static int generic_delete_lease(struct file *filp)
 	trace_generic_delete_lease(inode, fl);
 	if (victim)
 		error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose);
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	return error;
 }
@@ -2423,10 +2424,10 @@ locks_remove_lease(struct file *filp)
 	if (!ctx || list_empty(&ctx->flc_lease))
 		return;
 
-	spin_lock(&inode->i_lock);
+	spin_lock(&ctx->flc_lock);
 	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
 		lease_modify(&fl, F_UNLCK, &dispose);
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 }
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 3fb1caa3874..8cdb2b28a10 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -93,22 +93,22 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 		goto out;
 
 	list = &flctx->flc_posix;
-	spin_lock(&inode->i_lock);
+	spin_lock(&flctx->flc_lock);
 restart:
 	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file) != ctx)
 			continue;
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
 		if (status < 0)
 			goto out;
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 	}
 	if (list == &flctx->flc_posix) {
 		list = &flctx->flc_flock;
 		goto restart;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 out:
 	return status;
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6084c267f3a..a3bb22ab68c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1376,12 +1376,12 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
 
 	/* Guard against delegation returns and new lock/unlock calls */
 	down_write(&nfsi->rwsem);
-	spin_lock(&inode->i_lock);
+	spin_lock(&flctx->flc_lock);
 restart:
 	list_for_each_entry(fl, list, fl_list) {
 		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 		status = ops->recover_lock(state, fl);
 		switch (status) {
 		case 0:
@@ -1408,13 +1408,13 @@ restart:
 			/* kill_proc(fl->fl_pid, SIGLOST, 1); */
 			status = 0;
 		}
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 	}
 	if (list == &flctx->flc_posix) {
 		list = &flctx->flc_flock;
 		goto restart;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 out:
 	up_write(&nfsi->rwsem);
 	return status;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 784c13485b3..4ae66f416eb 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1206,7 +1206,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino
 
 	/* Check to see if there are whole file write locks */
 	ret = 0;
-	spin_lock(&inode->i_lock);
+	spin_lock(&flctx->flc_lock);
 	if (!list_empty(&flctx->flc_posix)) {
 		fl = list_first_entry(&flctx->flc_posix, struct file_lock,
 					fl_list);
@@ -1218,7 +1218,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino
 		if (fl->fl_type == F_WRLCK)
 			ret = 1;
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(&flctx->flc_lock);
 	return ret;
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index fad82199136..80242f5bd62 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5572,14 +5572,14 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 	flctx = inode->i_flctx;
 
 	if (flctx && !list_empty_careful(&flctx->flc_posix)) {
-		spin_lock(&inode->i_lock);
+		spin_lock(&flctx->flc_lock);
 		list_for_each_entry(fl, &flctx->flc_posix, fl_list) {
 			if (fl->fl_owner == (fl_owner_t)lowner) {
 				status = true;
 				break;
 			}
 		}
-		spin_unlock(&inode->i_lock);
+		spin_unlock(&flctx->flc_lock);
 	}
 	fput(filp);
 	return status;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ce0873af0b9..32eafa9b5c9 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -968,6 +968,7 @@ struct file_lock {
 };
 
 struct file_lock_context {
+	spinlock_t		flc_lock;
 	struct list_head	flc_flock;
 	struct list_head	flc_posix;
 	struct list_head	flc_lease;
-- 
cgit v1.2.3-70-g09d2


From 7448cc37b1a6b620d948aaee3bb30960c06d5d5d Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:57 -0500
Subject: locks: clean up the lm_change prototype

Now that we use standard list_heads for tracking leases, we can have
lm_change take a pointer to the lease to be modified instead of a
double pointer.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 fs/locks.c          | 13 ++++++-------
 fs/nfsd/nfs4state.c |  3 ++-
 include/linux/fs.h  |  6 +++---
 3 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index a268d959ccd..864f2460a0a 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1309,9 +1309,8 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 }
 
 /* We already had a lease on this file; just change its type */
-int lease_modify(struct file_lock **before, int arg, struct list_head *dispose)
+int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
 {
-	struct file_lock *fl = *before;
 	int error = assign_type(fl, arg);
 
 	if (error)
@@ -1352,9 +1351,9 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
 	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) {
 		trace_time_out_leases(inode, fl);
 		if (past_time(fl->fl_downgrade_time))
-			lease_modify(&fl, F_RDLCK, dispose);
+			lease_modify(fl, F_RDLCK, dispose);
 		if (past_time(fl->fl_break_time))
-			lease_modify(&fl, F_UNLCK, dispose);
+			lease_modify(fl, F_UNLCK, dispose);
 	}
 }
 
@@ -1669,7 +1668,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	}
 
 	if (my_fl != NULL) {
-		error = lease->fl_lmops->lm_change(&my_fl, arg, &dispose);
+		error = lease->fl_lmops->lm_change(my_fl, arg, &dispose);
 		if (error)
 			goto out;
 		goto out_setup;
@@ -1732,7 +1731,7 @@ static int generic_delete_lease(struct file *filp)
 	}
 	trace_generic_delete_lease(inode, fl);
 	if (victim)
-		error = fl->fl_lmops->lm_change(&victim, F_UNLCK, &dispose);
+		error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
 	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 	return error;
@@ -2426,7 +2425,7 @@ locks_remove_lease(struct file *filp)
 
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
-		lease_modify(&fl, F_UNLCK, &dispose);
+		lease_modify(fl, F_UNLCK, &dispose);
 	spin_unlock(&ctx->flc_lock);
 	locks_dispose_list(&dispose);
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 80242f5bd62..532a60cca2f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3477,7 +3477,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 }
 
 static int
-nfsd_change_deleg_cb(struct file_lock **onlist, int arg, struct list_head *dispose)
+nfsd_change_deleg_cb(struct file_lock *onlist, int arg,
+		     struct list_head *dispose)
 {
 	if (arg & F_UNLCK)
 		return lease_modify(onlist, arg, dispose);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 32eafa9b5c9..94e706a0a40 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -900,7 +900,7 @@ struct lock_manager_operations {
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
 	bool (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock **, int, struct list_head *);
+	int (*lm_change)(struct file_lock *, int, struct list_head *);
 	void (*lm_setup)(struct file_lock *, void **);
 };
 
@@ -1021,7 +1021,7 @@ extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int t
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
 extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
-extern int lease_modify(struct file_lock **, int, struct list_head *);
+extern int lease_modify(struct file_lock *, int, struct list_head *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, unsigned int cmd,
 			      struct flock __user *user)
@@ -1153,7 +1153,7 @@ static inline int vfs_setlease(struct file *filp, long arg,
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock **before, int arg,
+static inline int lease_modify(struct file_lock *fl, int arg,
 			       struct list_head *dispose)
 {
 	return -EINVAL;
-- 
cgit v1.2.3-70-g09d2


From 9bd0f45b7037fcfa8b575c7e27d0431d6e6dc3bb Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Fri, 16 Jan 2015 15:05:57 -0500
Subject: locks: keep a count of locks on the flctx lists

This makes things a bit more efficient in the cifs and ceph lock
pushing code.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Acked-by: Christoph Hellwig <hch@lst.de>
---
 fs/ceph/locks.c    | 11 ++---------
 fs/cifs/file.c     | 14 ++++----------
 fs/locks.c         | 45 +++++++++++++++++++++++++++++----------------
 include/linux/fs.h |  3 +++
 4 files changed, 38 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 0303da8e323..06ea5cd05cd 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -242,12 +242,9 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 /*
  * Fills in the passed counter variables, so you can prepare pagelist metadata
  * before calling ceph_encode_locks.
- *
- * FIXME: add counters to struct file_lock_context so we don't need to do this?
  */
 void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 {
-	struct file_lock *lock;
 	struct file_lock_context *ctx;
 
 	*fcntl_count = 0;
@@ -255,12 +252,8 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
 
 	ctx = inode->i_flctx;
 	if (ctx) {
-		spin_lock(&ctx->flc_lock);
-		list_for_each_entry(lock, &ctx->flc_posix, fl_list)
-			++(*fcntl_count);
-		list_for_each_entry(lock, &ctx->flc_flock, fl_list)
-			++(*flock_count);
-		spin_unlock(&ctx->flc_lock);
+		*fcntl_count = ctx->flc_posix_cnt;
+		*flock_count = ctx->flc_flock_cnt;
 	}
 	dout("counted %d flock locks and %d fcntl locks",
 	     *flock_count, *fcntl_count);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index b65166eb111..8c2ca6f62ba 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1125,7 +1125,7 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	struct file_lock *flock;
 	struct file_lock_context *flctx = inode->i_flctx;
-	unsigned int count = 0, i;
+	unsigned int i;
 	int rc = 0, xid, type;
 	struct list_head locks_to_send, *el;
 	struct lock_to_push *lck, *tmp;
@@ -1136,20 +1136,14 @@ cifs_push_posix_locks(struct cifsFileInfo *cfile)
 	if (!flctx)
 		goto out;
 
-	spin_lock(&flctx->flc_lock);
-	list_for_each(el, &flctx->flc_posix) {
-		count++;
-	}
-	spin_unlock(&flctx->flc_lock);
-
 	INIT_LIST_HEAD(&locks_to_send);
 
 	/*
-	 * Allocating count locks is enough because no FL_POSIX locks can be
-	 * added to the list while we are holding cinode->lock_sem that
+	 * Allocating flc_posix_cnt locks is enough because no FL_POSIX locks
+	 * can be added to the list while we are holding cinode->lock_sem that
 	 * protects locking operations of this inode.
 	 */
-	for (i = 0; i < count; i++) {
+	for (i = 0; i < flctx->flc_posix_cnt; i++) {
 		lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
 		if (!lck) {
 			rc = -ENOMEM;
diff --git a/fs/locks.c b/fs/locks.c
index 864f2460a0a..bd578700342 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -681,18 +681,21 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 }
 
 static void
-locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
+locks_insert_lock_ctx(struct file_lock *fl, int *counter,
+		      struct list_head *before)
 {
 	fl->fl_nspid = get_pid(task_tgid(current));
 	list_add_tail(&fl->fl_list, before);
+	++*counter;
 	locks_insert_global_locks(fl);
 }
 
 static void
-locks_unlink_lock_ctx(struct file_lock *fl)
+locks_unlink_lock_ctx(struct file_lock *fl, int *counter)
 {
 	locks_delete_global_locks(fl);
 	list_del_init(&fl->fl_list);
+	--*counter;
 	if (fl->fl_nspid) {
 		put_pid(fl->fl_nspid);
 		fl->fl_nspid = NULL;
@@ -701,9 +704,10 @@ locks_unlink_lock_ctx(struct file_lock *fl)
 }
 
 static void
-locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose)
+locks_delete_lock_ctx(struct file_lock *fl, int *counter,
+		      struct list_head *dispose)
 {
-	locks_unlink_lock_ctx(fl);
+	locks_unlink_lock_ctx(fl, counter);
 	if (dispose)
 		list_add(&fl->fl_list, dispose);
 	else
@@ -891,7 +895,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
 		if (request->fl_type == fl->fl_type)
 			goto out;
 		found = true;
-		locks_delete_lock_ctx(fl, &dispose);
+		locks_delete_lock_ctx(fl, &ctx->flc_flock_cnt, &dispose);
 		break;
 	}
 
@@ -925,7 +929,7 @@ find_conflict:
 	if (request->fl_flags & FL_ACCESS)
 		goto out;
 	locks_copy_lock(new_fl, request);
-	locks_insert_lock_ctx(new_fl, &ctx->flc_flock);
+	locks_insert_lock_ctx(new_fl, &ctx->flc_flock_cnt, &ctx->flc_flock);
 	new_fl = NULL;
 	error = 0;
 
@@ -1042,7 +1046,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			else
 				request->fl_end = fl->fl_end;
 			if (added) {
-				locks_delete_lock_ctx(fl, &dispose);
+				locks_delete_lock_ctx(fl, &ctx->flc_posix_cnt,
+							&dispose);
 				continue;
 			}
 			request = fl;
@@ -1071,7 +1076,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				 * one (This may happen several times).
 				 */
 				if (added) {
-					locks_delete_lock_ctx(fl, &dispose);
+					locks_delete_lock_ctx(fl,
+						&ctx->flc_posix_cnt, &dispose);
 					continue;
 				}
 				/*
@@ -1087,8 +1093,10 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 				locks_copy_lock(new_fl, request);
 				request = new_fl;
 				new_fl = NULL;
-				locks_insert_lock_ctx(request, &fl->fl_list);
-				locks_delete_lock_ctx(fl, &dispose);
+				locks_insert_lock_ctx(request,
+					&ctx->flc_posix_cnt, &fl->fl_list);
+				locks_delete_lock_ctx(fl,
+					&ctx->flc_posix_cnt, &dispose);
 				added = true;
 			}
 		}
@@ -1116,7 +1124,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			goto out;
 		}
 		locks_copy_lock(new_fl, request);
-		locks_insert_lock_ctx(new_fl, &fl->fl_list);
+		locks_insert_lock_ctx(new_fl, &ctx->flc_posix_cnt,
+					&fl->fl_list);
 		new_fl = NULL;
 	}
 	if (right) {
@@ -1127,7 +1136,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
 			left = new_fl2;
 			new_fl2 = NULL;
 			locks_copy_lock(left, right);
-			locks_insert_lock_ctx(left, &fl->fl_list);
+			locks_insert_lock_ctx(left, &ctx->flc_posix_cnt,
+						&fl->fl_list);
 		}
 		right->fl_start = request->fl_end + 1;
 		locks_wake_up_blocks(right);
@@ -1311,6 +1321,7 @@ static void lease_clear_pending(struct file_lock *fl, int arg)
 /* We already had a lease on this file; just change its type */
 int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
 {
+	struct file_lock_context *flctx;
 	int error = assign_type(fl, arg);
 
 	if (error)
@@ -1320,6 +1331,7 @@ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
 	if (arg == F_UNLCK) {
 		struct file *filp = fl->fl_file;
 
+		flctx = file_inode(filp)->i_flctx;
 		f_delown(filp);
 		filp->f_owner.signum = 0;
 		fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync);
@@ -1327,7 +1339,7 @@ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose)
 			printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync);
 			fl->fl_fasync = NULL;
 		}
-		locks_delete_lock_ctx(fl, dispose);
+		locks_delete_lock_ctx(fl, &flctx->flc_lease_cnt, dispose);
 	}
 	return 0;
 }
@@ -1442,7 +1454,8 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 			fl->fl_downgrade_time = break_time;
 		}
 		if (fl->fl_lmops->lm_break(fl))
-			locks_delete_lock_ctx(fl, &dispose);
+			locks_delete_lock_ctx(fl, &ctx->flc_lease_cnt,
+						&dispose);
 	}
 
 	if (list_empty(&ctx->flc_lease))
@@ -1678,7 +1691,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	if (!leases_enable)
 		goto out;
 
-	locks_insert_lock_ctx(lease, &ctx->flc_lease);
+	locks_insert_lock_ctx(lease, &ctx->flc_lease_cnt, &ctx->flc_lease);
 	/*
 	 * The check in break_lease() is lockless. It's possible for another
 	 * open to race in after we did the earlier check for a conflicting
@@ -1691,7 +1704,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	smp_mb();
 	error = check_conflicting_open(dentry, arg);
 	if (error) {
-		locks_unlink_lock_ctx(lease);
+		locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt);
 		goto out;
 	}
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 94e706a0a40..f87cb2f0310 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -972,6 +972,9 @@ struct file_lock_context {
 	struct list_head	flc_flock;
 	struct list_head	flc_posix;
 	struct list_head	flc_lease;
+	int			flc_flock_cnt;
+	int			flc_posix_cnt;
+	int			flc_lease_cnt;
 };
 
 /* The following constant reflects the upper bound of the file/locking space */
-- 
cgit v1.2.3-70-g09d2


From f555f3d76aaade29c7e221a37ee64fe722955c09 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 16 Jan 2015 11:37:12 +0100
Subject: genetlink: document parallel_ops

The kernel-doc for the parallel_ops family struct member is
missing, add it.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 84125088c30..2ea2c55bdc8 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -27,6 +27,8 @@ struct genl_info;
  * @maxattr: maximum number of attributes supported
  * @netnsok: set to true if the family can handle network
  *	namespaces and should be presented in all of them
+ * @parallel_ops: operations can be called in parallel and aren't
+ *	synchronized by the core genetlink code
  * @pre_doit: called before an operation's doit callback, it may
  *	do additional, common, filtering and return an error
  * @post_doit: called after an operation's doit callback, it may
-- 
cgit v1.2.3-70-g09d2


From ee1c244219fd652964710a6cc3e4f922e86aa492 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 16 Jan 2015 11:37:14 +0100
Subject: genetlink: synchronize socket closing and family removal

In addition to the problem Jeff Layton reported, I looked at the code
and reproduced the same warning by subscribing and removing the genl
family with a socket still open. This is a fairly tricky race which
originates in the fact that generic netlink allows the family to go
away while sockets are still open - unlike regular netlink which has
a module refcount for every open socket so in general this cannot be
triggered.

Trying to resolve this issue by the obvious locking isn't possible as
it will result in deadlocks between unregistration and group unbind
notification (which incidentally lockdep doesn't find due to the home
grown locking in the netlink table.)

To really resolve this, introduce a "closing socket" reference counter
(for generic netlink only, as it's the only affected family) in the
core netlink code and use that in generic netlink to wait for all the
sockets that are being closed at the same time as a generic netlink
family is removed.

This fixes the race that when a socket is closed, it will should call
the unbind, but if the family is removed at the same time the unbind
will not find it, leading to the warning. The real problem though is
that in this case the unbind could actually find a new family that is
registered to have a multicast group with the same ID, and call its
mcast_unbind() leading to confusing.

Also remove the warning since it would still trigger, but is now no
longer a problem.

This also moves the code in af_netlink.c to before unreferencing the
module to avoid having the same problem in the normal non-genl case.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/genetlink.h |  4 ++++
 include/net/genetlink.h   |  5 ++++-
 net/netlink/af_netlink.c  | 24 +++++++++++++++++-------
 net/netlink/af_netlink.h  |  1 +
 net/netlink/genetlink.c   | 16 +++++++++-------
 5 files changed, 35 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h
index 55b685719d5..09460d6d668 100644
--- a/include/linux/genetlink.h
+++ b/include/linux/genetlink.h
@@ -11,6 +11,10 @@ extern void genl_unlock(void);
 extern int lockdep_genl_is_held(void);
 #endif
 
+/* for synchronisation between af_netlink and genetlink */
+extern atomic_t genl_sk_destructing_cnt;
+extern wait_queue_head_t genl_sk_destructing_waitq;
+
 /**
  * rcu_dereference_genl - rcu_dereference with debug checking
  * @p: The pointer to read, prior to dereferencing
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 2ea2c55bdc8..6c92415311c 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -35,7 +35,10 @@ struct genl_info;
  *	undo operations done by pre_doit, for example release locks
  * @mcast_bind: a socket bound to the given multicast group (which
  *	is given as the offset into the groups array)
- * @mcast_unbind: a socket was unbound from the given multicast group
+ * @mcast_unbind: a socket was unbound from the given multicast group.
+ *	Note that unbind() will not be called symmetrically if the
+ *	generic netlink family is removed while there are still open
+ *	sockets.
  * @attrbuf: buffer to store parsed attributes
  * @family_list: family list
  * @mcgrps: multicast groups used by this family (private)
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 84ea76ca3f1..02fdde28dad 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -61,6 +61,7 @@
 #include <linux/rhashtable.h>
 #include <asm/cacheflush.h>
 #include <linux/hash.h>
+#include <linux/genetlink.h>
 
 #include <net/net_namespace.h>
 #include <net/sock.h>
@@ -1095,6 +1096,8 @@ static void netlink_remove(struct sock *sk)
 		__sk_del_bind_node(sk);
 		netlink_update_listeners(sk);
 	}
+	if (sk->sk_protocol == NETLINK_GENERIC)
+		atomic_inc(&genl_sk_destructing_cnt);
 	netlink_table_ungrab();
 }
 
@@ -1211,6 +1214,20 @@ static int netlink_release(struct socket *sock)
 	 * will be purged.
 	 */
 
+	/* must not acquire netlink_table_lock in any way again before unbind
+	 * and notifying genetlink is done as otherwise it might deadlock
+	 */
+	if (nlk->netlink_unbind) {
+		int i;
+
+		for (i = 0; i < nlk->ngroups; i++)
+			if (test_bit(i, nlk->groups))
+				nlk->netlink_unbind(sock_net(sk), i + 1);
+	}
+	if (sk->sk_protocol == NETLINK_GENERIC &&
+	    atomic_dec_return(&genl_sk_destructing_cnt) == 0)
+		wake_up(&genl_sk_destructing_waitq);
+
 	sock->sk = NULL;
 	wake_up_interruptible_all(&nlk->wait);
 
@@ -1246,13 +1263,6 @@ static int netlink_release(struct socket *sock)
 		netlink_table_ungrab();
 	}
 
-	if (nlk->netlink_unbind) {
-		int i;
-
-		for (i = 0; i < nlk->ngroups; i++)
-			if (test_bit(i, nlk->groups))
-				nlk->netlink_unbind(sock_net(sk), i + 1);
-	}
 	kfree(nlk->groups);
 	nlk->groups = NULL;
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index f123a88496f..f1c31b39aa3 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -2,6 +2,7 @@
 #define _AF_NETLINK_H
 
 #include <linux/rhashtable.h>
+#include <linux/atomic.h>
 #include <net/sock.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index c18d3f5624b..ee57459fc25 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -23,6 +23,9 @@
 static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */
 static DECLARE_RWSEM(cb_lock);
 
+atomic_t genl_sk_destructing_cnt = ATOMIC_INIT(0);
+DECLARE_WAIT_QUEUE_HEAD(genl_sk_destructing_waitq);
+
 void genl_lock(void)
 {
 	mutex_lock(&genl_mutex);
@@ -435,15 +438,18 @@ int genl_unregister_family(struct genl_family *family)
 
 	genl_lock_all();
 
-	genl_unregister_mc_groups(family);
-
 	list_for_each_entry(rc, genl_family_chain(family->id), family_list) {
 		if (family->id != rc->id || strcmp(rc->name, family->name))
 			continue;
 
+		genl_unregister_mc_groups(family);
+
 		list_del(&rc->family_list);
 		family->n_ops = 0;
-		genl_unlock_all();
+		up_write(&cb_lock);
+		wait_event(genl_sk_destructing_waitq,
+			   atomic_read(&genl_sk_destructing_cnt) == 0);
+		genl_unlock();
 
 		kfree(family->attrbuf);
 		genl_ctrl_event(CTRL_CMD_DELFAMILY, family, NULL, 0);
@@ -1014,7 +1020,6 @@ static int genl_bind(struct net *net, int group)
 static void genl_unbind(struct net *net, int group)
 {
 	int i;
-	bool found = false;
 
 	down_read(&cb_lock);
 	for (i = 0; i < GENL_FAM_TAB_SIZE; i++) {
@@ -1027,14 +1032,11 @@ static void genl_unbind(struct net *net, int group)
 
 				if (f->mcast_unbind)
 					f->mcast_unbind(net, fam_grp);
-				found = true;
 				break;
 			}
 		}
 	}
 	up_read(&cb_lock);
-
-	WARN_ON(!found);
 }
 
 static int __net_init genl_pernet_init(struct net *net)
-- 
cgit v1.2.3-70-g09d2


From 9d5438f462abd6398cdb7b3211bdcec271873a3b Mon Sep 17 00:00:00 2001
From: Mark Salyzyn <salyzyn@android.com>
Date: Fri, 16 Jan 2015 16:01:10 -0800
Subject: pstore: Add pmsg - user-space accessible pstore object

A secured user-space accessible pstore object. Writes
to /dev/pmsg0 are appended to the buffer, on reboot
the persistent contents are available in
/sys/fs/pstore/pmsg-ramoops-[ID].

One possible use is syslogd, or other daemon, can
write messages, then on reboot provides a means to
triage user-space activities leading up to a panic
as a companion to the pstore dmesg or console logs.

Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 fs/pstore/Kconfig          |  10 ++++
 fs/pstore/Makefile         |   2 +
 fs/pstore/inode.c          |   3 ++
 fs/pstore/internal.h       |   6 +++
 fs/pstore/platform.c       |   1 +
 fs/pstore/pmsg.c           | 114 +++++++++++++++++++++++++++++++++++++++++++++
 fs/pstore/ram.c            |  34 +++++++++++++-
 include/linux/pstore.h     |   1 +
 include/linux/pstore_ram.h |   1 +
 9 files changed, 170 insertions(+), 2 deletions(-)
 create mode 100644 fs/pstore/pmsg.c

(limited to 'include')

diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 983d9510bec..916b8e23d96 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -21,6 +21,16 @@ config PSTORE_CONSOLE
 	  When the option is enabled, pstore will log all kernel
 	  messages, even if no oops or panic happened.
 
+config PSTORE_PMSG
+	bool "Log user space messages"
+	depends on PSTORE
+	help
+	  When the option is enabled, pstore will export a character
+	  interface /dev/pmsg0 to log user space messages. On reboot
+	  data can be retrieved from /sys/fs/pstore/pmsg-ramoops-[ID].
+
+	  If unsure, say N.
+
 config PSTORE_FTRACE
 	bool "Persistent function tracer"
 	depends on PSTORE
diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile
index 4c9095c2781..e647d8e8171 100644
--- a/fs/pstore/Makefile
+++ b/fs/pstore/Makefile
@@ -7,5 +7,7 @@ obj-y += pstore.o
 pstore-objs += inode.o platform.o
 obj-$(CONFIG_PSTORE_FTRACE)	+= ftrace.o
 
+obj-$(CONFIG_PSTORE_PMSG)	+= pmsg.o
+
 ramoops-objs += ram.o ram_core.o
 obj-$(CONFIG_PSTORE_RAM)	+= ramoops.o
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index d69586f09ff..b32ce53d24e 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -361,6 +361,9 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 		scnprintf(name, sizeof(name), "powerpc-common-%s-%lld",
 			  psname, id);
 		break;
+	case PSTORE_TYPE_PMSG:
+		scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id);
+		break;
 	case PSTORE_TYPE_UNKNOWN:
 		scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id);
 		break;
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 3b3d305277c..c36ba2cd0b5 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -45,6 +45,12 @@ extern void pstore_register_ftrace(void);
 static inline void pstore_register_ftrace(void) {}
 #endif
 
+#ifdef CONFIG_PSTORE_PMSG
+extern void pstore_register_pmsg(void);
+#else
+static inline void pstore_register_pmsg(void) {}
+#endif
+
 extern struct pstore_info *psinfo;
 
 extern void	pstore_set_kmsg_bytes(int);
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 0a9b72cdfec..15ee78c5020 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -447,6 +447,7 @@ int pstore_register(struct pstore_info *psi)
 	if ((psi->flags & PSTORE_FLAGS_FRAGILE) == 0) {
 		pstore_register_console();
 		pstore_register_ftrace();
+		pstore_register_pmsg();
 	}
 
 	if (pstore_update_ms >= 0) {
diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c
new file mode 100644
index 00000000000..feb5dd2948b
--- /dev/null
+++ b/fs/pstore/pmsg.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright 2014  Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include "internal.h"
+
+static DEFINE_MUTEX(pmsg_lock);
+#define PMSG_MAX_BOUNCE_BUFFER_SIZE (2*PAGE_SIZE)
+
+static ssize_t write_pmsg(struct file *file, const char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	size_t i, buffer_size;
+	char *buffer;
+
+	if (!count)
+		return 0;
+
+	if (!access_ok(VERIFY_READ, buf, count))
+		return -EFAULT;
+
+	buffer_size = count;
+	if (buffer_size > PMSG_MAX_BOUNCE_BUFFER_SIZE)
+		buffer_size = PMSG_MAX_BOUNCE_BUFFER_SIZE;
+	buffer = vmalloc(buffer_size);
+
+	mutex_lock(&pmsg_lock);
+	for (i = 0; i < count; ) {
+		size_t c = min(count - i, buffer_size);
+		u64 id;
+		long ret;
+
+		ret = __copy_from_user(buffer, buf + i, c);
+		if (unlikely(ret != 0)) {
+			mutex_unlock(&pmsg_lock);
+			vfree(buffer);
+			return -EFAULT;
+		}
+		psinfo->write_buf(PSTORE_TYPE_PMSG, 0, &id, 0, buffer, 0, c,
+				  psinfo);
+
+		i += c;
+	}
+
+	mutex_unlock(&pmsg_lock);
+	vfree(buffer);
+	return count;
+}
+
+static const struct file_operations pmsg_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= noop_llseek,
+	.write		= write_pmsg,
+};
+
+static struct class *pmsg_class;
+static int pmsg_major;
+#define PMSG_NAME "pmsg"
+#undef pr_fmt
+#define pr_fmt(fmt) PMSG_NAME ": " fmt
+
+static char *pmsg_devnode(struct device *dev, umode_t *mode)
+{
+	if (mode)
+		*mode = 0220;
+	return NULL;
+}
+
+void pstore_register_pmsg(void)
+{
+	struct device *pmsg_device;
+
+	pmsg_major = register_chrdev(0, PMSG_NAME, &pmsg_fops);
+	if (pmsg_major < 0) {
+		pr_err("register_chrdev failed\n");
+		goto err;
+	}
+
+	pmsg_class = class_create(THIS_MODULE, PMSG_NAME);
+	if (IS_ERR(pmsg_class)) {
+		pr_err("device class file already in use\n");
+		goto err_class;
+	}
+	pmsg_class->devnode = pmsg_devnode;
+
+	pmsg_device = device_create(pmsg_class, NULL, MKDEV(pmsg_major, 0),
+					NULL, "%s%d", PMSG_NAME, 0);
+	if (IS_ERR(pmsg_device)) {
+		pr_err("failed to create device\n");
+		goto err_device;
+	}
+	return;
+
+err_device:
+	class_destroy(pmsg_class);
+err_class:
+	unregister_chrdev(pmsg_major, PMSG_NAME);
+err:
+	return;
+}
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 6150e54eed3..39d1373128e 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -51,6 +51,10 @@ static ulong ramoops_ftrace_size = MIN_MEM_SIZE;
 module_param_named(ftrace_size, ramoops_ftrace_size, ulong, 0400);
 MODULE_PARM_DESC(ftrace_size, "size of ftrace log");
 
+static ulong ramoops_pmsg_size = MIN_MEM_SIZE;
+module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400);
+MODULE_PARM_DESC(pmsg_size, "size of user space message log");
+
 static ulong mem_address;
 module_param(mem_address, ulong, 0400);
 MODULE_PARM_DESC(mem_address,
@@ -82,12 +86,14 @@ struct ramoops_context {
 	struct persistent_ram_zone **przs;
 	struct persistent_ram_zone *cprz;
 	struct persistent_ram_zone *fprz;
+	struct persistent_ram_zone *mprz;
 	phys_addr_t phys_addr;
 	unsigned long size;
 	unsigned int memtype;
 	size_t record_size;
 	size_t console_size;
 	size_t ftrace_size;
+	size_t pmsg_size;
 	int dump_oops;
 	struct persistent_ram_ecc_info ecc_info;
 	unsigned int max_dump_cnt;
@@ -96,6 +102,7 @@ struct ramoops_context {
 	unsigned int dump_read_cnt;
 	unsigned int console_read_cnt;
 	unsigned int ftrace_read_cnt;
+	unsigned int pmsg_read_cnt;
 	struct pstore_info pstore;
 };
 
@@ -109,6 +116,7 @@ static int ramoops_pstore_open(struct pstore_info *psi)
 	cxt->dump_read_cnt = 0;
 	cxt->console_read_cnt = 0;
 	cxt->ftrace_read_cnt = 0;
+	cxt->pmsg_read_cnt = 0;
 	return 0;
 }
 
@@ -190,6 +198,9 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->fprz, &cxt->ftrace_read_cnt,
 					   1, id, type, PSTORE_TYPE_FTRACE, 0);
+	if (!prz_ok(prz))
+		prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt,
+					   1, id, type, PSTORE_TYPE_PMSG, 0);
 	if (!prz_ok(prz))
 		return 0;
 
@@ -258,6 +269,11 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 			return -ENOMEM;
 		persistent_ram_write(cxt->fprz, buf, size);
 		return 0;
+	} else if (type == PSTORE_TYPE_PMSG) {
+		if (!cxt->mprz)
+			return -ENOMEM;
+		persistent_ram_write(cxt->mprz, buf, size);
+		return 0;
 	}
 
 	if (type != PSTORE_TYPE_DMESG)
@@ -315,6 +331,9 @@ static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count,
 	case PSTORE_TYPE_FTRACE:
 		prz = cxt->fprz;
 		break;
+	case PSTORE_TYPE_PMSG:
+		prz = cxt->mprz;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -441,7 +460,7 @@ static int ramoops_probe(struct platform_device *pdev)
 		goto fail_out;
 
 	if (!pdata->mem_size || (!pdata->record_size && !pdata->console_size &&
-			!pdata->ftrace_size)) {
+			!pdata->ftrace_size && !pdata->pmsg_size)) {
 		pr_err("The memory size and the record/console size must be "
 			"non-zero\n");
 		goto fail_out;
@@ -453,6 +472,8 @@ static int ramoops_probe(struct platform_device *pdev)
 		pdata->console_size = rounddown_pow_of_two(pdata->console_size);
 	if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size))
 		pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size);
+	if (pdata->pmsg_size && !is_power_of_2(pdata->pmsg_size))
+		pdata->pmsg_size = rounddown_pow_of_two(pdata->pmsg_size);
 
 	cxt->size = pdata->mem_size;
 	cxt->phys_addr = pdata->mem_address;
@@ -460,12 +481,14 @@ static int ramoops_probe(struct platform_device *pdev)
 	cxt->record_size = pdata->record_size;
 	cxt->console_size = pdata->console_size;
 	cxt->ftrace_size = pdata->ftrace_size;
+	cxt->pmsg_size = pdata->pmsg_size;
 	cxt->dump_oops = pdata->dump_oops;
 	cxt->ecc_info = pdata->ecc_info;
 
 	paddr = cxt->phys_addr;
 
-	dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size;
+	dump_mem_sz = cxt->size - cxt->console_size - cxt->ftrace_size
+			- cxt->pmsg_size;
 	err = ramoops_init_przs(dev, cxt, &paddr, dump_mem_sz);
 	if (err)
 		goto fail_out;
@@ -480,6 +503,10 @@ static int ramoops_probe(struct platform_device *pdev)
 	if (err)
 		goto fail_init_fprz;
 
+	err = ramoops_init_prz(dev, cxt, &cxt->mprz, &paddr, cxt->pmsg_size, 0);
+	if (err)
+		goto fail_init_mprz;
+
 	cxt->pstore.data = cxt;
 	/*
 	 * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we
@@ -523,6 +550,8 @@ fail_buf:
 	kfree(cxt->pstore.buf);
 fail_clear:
 	cxt->pstore.bufsize = 0;
+	kfree(cxt->mprz);
+fail_init_mprz:
 	kfree(cxt->fprz);
 fail_init_fprz:
 	kfree(cxt->cprz);
@@ -580,6 +609,7 @@ static void ramoops_register_dummy(void)
 	dummy_data->record_size = record_size;
 	dummy_data->console_size = ramoops_console_size;
 	dummy_data->ftrace_size = ramoops_ftrace_size;
+	dummy_data->pmsg_size = ramoops_pmsg_size;
 	dummy_data->dump_oops = dump_oops;
 	/*
 	 * For backwards compatibility ramoops.ecc=1 means 16 bytes ECC
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index ece0c6bbfcc..8884f6e507f 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -39,6 +39,7 @@ enum pstore_type_id {
 	PSTORE_TYPE_PPC_RTAS	= 4,
 	PSTORE_TYPE_PPC_OF	= 5,
 	PSTORE_TYPE_PPC_COMMON	= 6,
+	PSTORE_TYPE_PMSG	= 7,
 	PSTORE_TYPE_UNKNOWN	= 255
 };
 
diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h
index 4af3fdc85b0..9c9d6c154c8 100644
--- a/include/linux/pstore_ram.h
+++ b/include/linux/pstore_ram.h
@@ -81,6 +81,7 @@ struct ramoops_platform_data {
 	unsigned long	record_size;
 	unsigned long	console_size;
 	unsigned long	ftrace_size;
+	unsigned long	pmsg_size;
 	int		dump_oops;
 	struct persistent_ram_ecc_info ecc_info;
 };
-- 
cgit v1.2.3-70-g09d2


From b9626f32876debc356fadb6e19aebcfe9d70c5ff Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Mon, 1 Dec 2014 19:32:51 +0100
Subject: tpm/tpm_i2c_stm_st33: Add new tpm_stm_dev structure and remove
 tpm_i2c_buffer[0], [1] buffer.

In order to clean big buffers in st33zp24_platform_data structure,
replace with tpm_stm_dev for driver internal usage.
As only one buffer is really necessary replace with buf field.

In the mean time move tpm_i2c_stm_st33.h to include/linux/platform_data.

Reviewed-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Peter Huewe <peterhuewe@gmx.de>
---
 drivers/char/tpm/tpm_i2c_stm_st33.c            | 204 +++++++++++--------------
 drivers/char/tpm/tpm_i2c_stm_st33.h            |  44 ------
 include/linux/platform_data/tpm_i2c_stm_st33.h |  40 +++++
 3 files changed, 132 insertions(+), 156 deletions(-)
 delete mode 100644 drivers/char/tpm/tpm_i2c_stm_st33.h
 create mode 100644 include/linux/platform_data/tpm_i2c_stm_st33.h

(limited to 'include')

diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 44a02103ad4..4f725386385 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -40,7 +40,6 @@
 #include <linux/wait.h>
 #include <linux/string.h>
 #include <linux/interrupt.h>
-#include <linux/spinlock.h>
 #include <linux/sysfs.h>
 #include <linux/gpio.h>
 #include <linux/sched.h>
@@ -48,6 +47,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 
+#include <linux/platform_data/tpm_i2c_stm_st33.h>
 #include "tpm.h"
 
 #define TPM_ACCESS			0x0
@@ -66,7 +66,7 @@
 #define TPM_BUFSIZE			2048
 
 #define LOCALITY0		0
-#include "tpm_i2c_stm_st33.h"
+
 
 enum stm33zp24_access {
 	TPM_ACCESS_VALID = 0x80,
@@ -98,6 +98,15 @@ enum tis_defaults {
 	TIS_LONG_TIMEOUT = 2000,
 };
 
+struct tpm_stm_dev {
+	struct i2c_client *client;
+	struct completion irq_detection;
+	struct tpm_chip *chip;
+	u8 buf[TPM_BUFSIZE + 1];
+	int io_serirq;
+	int io_lpcpd;
+};
+
 /*
  * write8_reg
  * Send byte to the TIS register according to the ST33ZP24 I2C protocol.
@@ -106,17 +115,12 @@ enum tis_defaults {
  * @param: tpm_size, The length of the data
  * @return: Returns negative errno, or else the number of bytes written.
  */
-static int write8_reg(struct i2c_client *client, u8 tpm_register,
+static int write8_reg(struct tpm_stm_dev *tpm_dev, u8 tpm_register,
 		      u8 *tpm_data, u16 tpm_size)
 {
-	struct st33zp24_platform_data *pin_infos;
-
-	pin_infos = client->dev.platform_data;
-
-	pin_infos->tpm_i2c_buffer[0][0] = tpm_register;
-	memcpy(&pin_infos->tpm_i2c_buffer[0][1], tpm_data, tpm_size);
-	return i2c_master_send(client, pin_infos->tpm_i2c_buffer[0],
-				tpm_size + 1);
+	tpm_dev->buf[0] = tpm_register;
+	memcpy(tpm_dev->buf + 1, tpm_data, tpm_size);
+	return i2c_master_send(tpm_dev->client, tpm_dev->buf, tpm_size + 1);
 } /* write8_reg() */
 
 /*
@@ -127,56 +131,56 @@ static int write8_reg(struct i2c_client *client, u8 tpm_register,
  * @param: tpm_size, tpm TPM response size to read.
  * @return: number of byte read successfully: should be one if success.
  */
-static int read8_reg(struct i2c_client *client, u8 tpm_register,
+static int read8_reg(struct tpm_stm_dev *tpm_dev, u8 tpm_register,
 		    u8 *tpm_data, int tpm_size)
 {
 	u8 status = 0;
 	u8 data;
 
 	data = TPM_DUMMY_BYTE;
-	status = write8_reg(client, tpm_register, &data, 1);
+	status = write8_reg(tpm_dev, tpm_register, &data, 1);
 	if (status == 2)
-		status = i2c_master_recv(client, tpm_data, tpm_size);
+		status = i2c_master_recv(tpm_dev->client, tpm_data, tpm_size);
 	return status;
 } /* read8_reg() */
 
 /*
  * I2C_WRITE_DATA
  * Send byte to the TIS register according to the ST33ZP24 I2C protocol.
- * @param: client, the chip description
+ * @param: tpm_dev, the chip description
  * @param: tpm_register, the tpm tis register where the data should be written
  * @param: tpm_data, the tpm_data to write inside the tpm_register
  * @param: tpm_size, The length of the data
  * @return: number of byte written successfully: should be one if success.
  */
-#define I2C_WRITE_DATA(client, tpm_register, tpm_data, tpm_size) \
-	(write8_reg(client, tpm_register | \
+#define I2C_WRITE_DATA(tpm_dev, tpm_register, tpm_data, tpm_size) \
+	(write8_reg(tpm_dev, tpm_register | \
 	TPM_WRITE_DIRECTION, tpm_data, tpm_size))
 
 /*
  * I2C_READ_DATA
  * Recv byte from the TIS register according to the ST33ZP24 I2C protocol.
- * @param: tpm, the chip description
+ * @param: tpm_dev, the chip description
  * @param: tpm_register, the tpm tis register where the data should be read
  * @param: tpm_data, the TPM response
  * @param: tpm_size, tpm TPM response size to read.
  * @return: number of byte read successfully: should be one if success.
  */
-#define I2C_READ_DATA(client, tpm_register, tpm_data, tpm_size) \
-	(read8_reg(client, tpm_register, tpm_data, tpm_size))
+#define I2C_READ_DATA(tpm_dev, tpm_register, tpm_data, tpm_size) \
+	(read8_reg(tpm_dev, tpm_register, tpm_data, tpm_size))
 
 /*
  * clear_interruption
  * clear the TPM interrupt register.
  * @param: tpm, the chip description
  */
-static void clear_interruption(struct i2c_client *client)
+static void clear_interruption(struct tpm_stm_dev *tpm_dev)
 {
 	u8 interrupt;
 
-	I2C_READ_DATA(client, TPM_INT_STATUS, &interrupt, 1);
-	I2C_WRITE_DATA(client, TPM_INT_STATUS, &interrupt, 1);
-	I2C_READ_DATA(client, TPM_INT_STATUS, &interrupt, 1);
+	I2C_READ_DATA(tpm_dev, TPM_INT_STATUS, &interrupt, 1);
+	I2C_WRITE_DATA(tpm_dev, TPM_INT_STATUS, &interrupt, 1);
+	I2C_READ_DATA(tpm_dev, TPM_INT_STATUS, &interrupt, 1);
 } /* clear_interruption() */
 
 /*
@@ -190,17 +194,16 @@ static long _wait_for_interrupt_serirq_timeout(struct tpm_chip *chip,
 {
 	long status;
 	struct i2c_client *client;
-	struct st33zp24_platform_data *pin_infos;
+	struct tpm_stm_dev *tpm_dev;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
-	pin_infos = client->dev.platform_data;
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
+	client = tpm_dev->client;
 
 	status = wait_for_completion_interruptible_timeout(
-					&pin_infos->irq_detection,
-						timeout);
+					&tpm_dev->irq_detection,
+					timeout);
 	if (status > 0)
-		enable_irq(gpio_to_irq(pin_infos->io_serirq));
-	gpio_direction_input(pin_infos->io_serirq);
+		enable_irq(client->irq);
 
 	return status;
 } /* wait_for_interrupt_serirq_timeout() */
@@ -209,15 +212,15 @@ static int wait_for_serirq_timeout(struct tpm_chip *chip, bool condition,
 				 unsigned long timeout)
 {
 	int status = 2;
-	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 
 	status = _wait_for_interrupt_serirq_timeout(chip, timeout);
 	if (!status) {
 		status = -EBUSY;
 	} else {
-		clear_interruption(client);
+		clear_interruption(tpm_dev);
 		if (condition)
 			status = 1;
 	}
@@ -230,13 +233,13 @@ static int wait_for_serirq_timeout(struct tpm_chip *chip, bool condition,
  */
 static void tpm_stm_i2c_cancel(struct tpm_chip *chip)
 {
-	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 	u8 data;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 
 	data = TPM_STS_COMMAND_READY;
-	I2C_WRITE_DATA(client, TPM_STS, &data, 1);
+	I2C_WRITE_DATA(tpm_dev, TPM_STS, &data, 1);
 	if (chip->vendor.irq)
 		wait_for_serirq_timeout(chip, 1, chip->vendor.timeout_a);
 }	/* tpm_stm_i2c_cancel() */
@@ -248,12 +251,12 @@ static void tpm_stm_i2c_cancel(struct tpm_chip *chip)
  */
 static u8 tpm_stm_i2c_status(struct tpm_chip *chip)
 {
-	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 	u8 data;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 
-	I2C_READ_DATA(client, TPM_STS, &data, 1);
+	I2C_READ_DATA(tpm_dev, TPM_STS, &data, 1);
 	return data;
 }				/* tpm_stm_i2c_status() */
 
@@ -265,13 +268,13 @@ static u8 tpm_stm_i2c_status(struct tpm_chip *chip)
  */
 static int check_locality(struct tpm_chip *chip)
 {
-	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 	u8 data;
 	u8 status;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 
-	status = I2C_READ_DATA(client, TPM_ACCESS, &data, 1);
+	status = I2C_READ_DATA(tpm_dev, TPM_ACCESS, &data, 1);
 	if (status && (data &
 		(TPM_ACCESS_ACTIVE_LOCALITY | TPM_ACCESS_VALID)) ==
 		(TPM_ACCESS_ACTIVE_LOCALITY | TPM_ACCESS_VALID))
@@ -290,16 +293,16 @@ static int request_locality(struct tpm_chip *chip)
 {
 	unsigned long stop;
 	long rc;
-	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 	u8 data;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 
 	if (check_locality(chip) == chip->vendor.locality)
 		return chip->vendor.locality;
 
 	data = TPM_ACCESS_REQUEST_USE;
-	rc = I2C_WRITE_DATA(client, TPM_ACCESS, &data, 1);
+	rc = I2C_WRITE_DATA(tpm_dev, TPM_ACCESS, &data, 1);
 	if (rc < 0)
 		goto end;
 
@@ -328,13 +331,13 @@ end:
  */
 static void release_locality(struct tpm_chip *chip)
 {
-	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 	u8 data;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 	data = TPM_ACCESS_ACTIVE_LOCALITY;
 
-	I2C_WRITE_DATA(client, TPM_ACCESS, &data, 1);
+	I2C_WRITE_DATA(tpm_dev, TPM_ACCESS, &data, 1);
 }
 
 /*
@@ -347,19 +350,20 @@ static int get_burstcount(struct tpm_chip *chip)
 	unsigned long stop;
 	int burstcnt, status;
 	u8 tpm_reg, temp;
+	struct tpm_stm_dev *tpm_dev;
 
-	struct i2c_client *client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 
 	stop = jiffies + chip->vendor.timeout_d;
 	do {
 		tpm_reg = TPM_STS + 1;
-		status = I2C_READ_DATA(client, tpm_reg, &temp, 1);
+		status = I2C_READ_DATA(tpm_dev, tpm_reg, &temp, 1);
 		if (status < 0)
 			goto end;
 
 		tpm_reg = tpm_reg + 1;
 		burstcnt = temp;
-		status = I2C_READ_DATA(client, tpm_reg, &temp, 1);
+		status = I2C_READ_DATA(tpm_dev, tpm_reg, &temp, 1);
 		if (status < 0)
 			goto end;
 
@@ -416,9 +420,9 @@ static int wait_for_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
 static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count)
 {
 	int size = 0, burstcnt, len;
-	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
 
 	while (size < count &&
 	       wait_for_stat(chip,
@@ -430,7 +434,7 @@ static int recv_data(struct tpm_chip *chip, u8 *buf, size_t count)
 		if (burstcnt < 0)
 			return burstcnt;
 		len = min_t(int, burstcnt, count - size);
-		I2C_READ_DATA(client, TPM_DATA_FIFO, buf + size, len);
+		I2C_READ_DATA(tpm_dev, TPM_DATA_FIFO, buf + size, len);
 		size += len;
 	}
 	return size;
@@ -446,14 +450,14 @@ static irqreturn_t tpm_ioserirq_handler(int irq, void *dev_id)
 {
 	struct tpm_chip *chip = dev_id;
 	struct i2c_client *client;
-	struct st33zp24_platform_data *pin_infos;
+	struct tpm_stm_dev *tpm_dev;
 
 	disable_irq_nosync(irq);
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
-	pin_infos = client->dev.platform_data;
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
+	client = tpm_dev->client;
 
-	complete(&pin_infos->irq_detection);
+	complete(&tpm_dev->irq_detection);
 	return IRQ_HANDLED;
 } /* tpm_ioserirq_handler() */
 
@@ -475,13 +479,15 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 	int ret;
 	u8 data;
 	struct i2c_client *client;
+	struct tpm_stm_dev *tpm_dev;
 
 	if (chip == NULL)
 		return -EBUSY;
 	if (len < TPM_HEADER_SIZE)
 		return -EBUSY;
 
-	client = (struct i2c_client *)TPM_VPRIV(chip);
+	tpm_dev = (struct tpm_stm_dev *)TPM_VPRIV(chip);
+	client = tpm_dev->client;
 
 	client->flags = 0;
 
@@ -505,7 +511,7 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 		if (burstcnt < 0)
 			return burstcnt;
 		size = min_t(int, len - i - 1, burstcnt);
-		ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf + i, size);
+		ret = I2C_WRITE_DATA(tpm_dev, TPM_DATA_FIFO, buf + i, size);
 		if (ret < 0)
 			goto out_err;
 
@@ -518,7 +524,7 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 		goto out_err;
 	}
 
-	ret = I2C_WRITE_DATA(client, TPM_DATA_FIFO, buf + len - 1, 1);
+	ret = I2C_WRITE_DATA(tpm_dev, TPM_DATA_FIFO, buf + len - 1, 1);
 	if (ret < 0)
 		goto out_err;
 
@@ -529,7 +535,7 @@ static int tpm_stm_i2c_send(struct tpm_chip *chip, unsigned char *buf,
 	}
 
 	data = TPM_STS_GO;
-	I2C_WRITE_DATA(client, TPM_STS, &data, 1);
+	I2C_WRITE_DATA(tpm_dev, TPM_STS, &data, 1);
 
 	return len;
 out_err:
@@ -623,6 +629,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	u8 intmask;
 	struct tpm_chip *chip;
 	struct st33zp24_platform_data *platform_data;
+	struct tpm_stm_dev *tpm_dev;
 
 	if (client == NULL) {
 		pr_info("%s: i2c client is NULL. Device not accessible.\n",
@@ -637,11 +644,11 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		goto end;
 	}
 
-	chip = tpm_register_hardware(&client->dev, &st_i2c_tpm);
-	if (!chip) {
-		dev_info(&client->dev, "fail chip\n");
-		err = -ENODEV;
-		goto end;
+	tpm_dev = devm_kzalloc(&client->dev, sizeof(struct tpm_stm_dev),
+			       GFP_KERNEL);
+	if (!tpm_dev) {
+		err = -ENOMEM;
+		goto _tpm_clean_answer;
 	}
 
 	platform_data = client->dev.platform_data;
@@ -652,20 +659,14 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		goto _tpm_clean_answer;
 	}
 
-	platform_data->tpm_i2c_buffer[0] =
-	    kmalloc(TPM_BUFSIZE, GFP_KERNEL);
-	if (platform_data->tpm_i2c_buffer[0] == NULL) {
-		err = -ENOMEM;
-		goto _tpm_clean_answer;
-	}
-	platform_data->tpm_i2c_buffer[1] =
-	    kmalloc(TPM_BUFSIZE, GFP_KERNEL);
-	if (platform_data->tpm_i2c_buffer[1] == NULL) {
-		err = -ENOMEM;
-		goto _tpm_clean_response1;
+	chip = tpm_register_hardware(&client->dev, &st_i2c_tpm);
+	if (!chip) {
+		dev_info(&client->dev, "fail chip\n");
+		return -ENODEV;
 	}
 
-	TPM_VPRIV(chip) = client;
+	TPM_VPRIV(chip) = tpm_dev;
+	tpm_dev->client = client;
 
 	chip->vendor.timeout_a = msecs_to_jiffies(TIS_SHORT_TIMEOUT);
 	chip->vendor.timeout_b = msecs_to_jiffies(TIS_LONG_TIMEOUT);
@@ -682,16 +683,16 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	}
 
 	if (interrupts) {
-		init_completion(&platform_data->irq_detection);
+		init_completion(&tpm_dev->irq_detection);
 		if (request_locality(chip) != LOCALITY0) {
 			err = -ENODEV;
-			goto _tpm_clean_response2;
+			goto _tpm_clean_answer;
 		}
 		err = gpio_request(platform_data->io_serirq, "TPM IO_SERIRQ");
 		if (err)
 			goto _gpio_init2;
 
-		clear_interruption(client);
+		clear_interruption(tpm_dev);
 		err = request_irq(gpio_to_irq(platform_data->io_serirq),
 				&tpm_ioserirq_handler,
 				IRQF_TRIGGER_HIGH,
@@ -702,7 +703,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 			goto _irq_set;
 		}
 
-		err = I2C_READ_DATA(client, TPM_INT_ENABLE, &intmask, 1);
+		err = I2C_READ_DATA(tpm_dev, TPM_INT_ENABLE, &intmask, 1);
 		if (err < 0)
 			goto _irq_set;
 
@@ -713,16 +714,17 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 			|  TPM_INTF_STS_VALID_INT
 			|  TPM_INTF_DATA_AVAIL_INT;
 
-		err = I2C_WRITE_DATA(client, TPM_INT_ENABLE, &intmask, 1);
+		err = I2C_WRITE_DATA(tpm_dev, TPM_INT_ENABLE, &intmask, 1);
 		if (err < 0)
 			goto _irq_set;
 
 		intmask = TPM_GLOBAL_INT_ENABLE;
-		err = I2C_WRITE_DATA(client, (TPM_INT_ENABLE + 3), &intmask, 1);
+		err = I2C_WRITE_DATA(tpm_dev, (TPM_INT_ENABLE + 3),
+				     &intmask, 1);
 		if (err < 0)
 			goto _irq_set;
 
-		err = I2C_READ_DATA(client, TPM_INT_STATUS, &intmask, 1);
+		err = I2C_READ_DATA(tpm_dev, TPM_INT_STATUS, &intmask, 1);
 		if (err < 0)
 			goto _irq_set;
 
@@ -744,12 +746,6 @@ _gpio_init2:
 _gpio_init1:
 	if (power_mgt)
 		gpio_free(platform_data->io_lpcpd);
-_tpm_clean_response2:
-	kzfree(platform_data->tpm_i2c_buffer[1]);
-	platform_data->tpm_i2c_buffer[1] = NULL;
-_tpm_clean_response1:
-	kzfree(platform_data->tpm_i2c_buffer[0]);
-	platform_data->tpm_i2c_buffer[0] = NULL;
 _tpm_clean_answer:
 	tpm_remove_hardware(chip->dev);
 end:
@@ -765,28 +761,12 @@ end:
  */
 static int tpm_st33_i2c_remove(struct i2c_client *client)
 {
-	struct tpm_chip *chip = (struct tpm_chip *)i2c_get_clientdata(client);
-	struct st33zp24_platform_data *pin_infos =
-		((struct i2c_client *)TPM_VPRIV(chip))->dev.platform_data;
-
-	if (pin_infos != NULL) {
-		free_irq(pin_infos->io_serirq, chip);
-
-		gpio_free(pin_infos->io_serirq);
-		gpio_free(pin_infos->io_lpcpd);
+	struct tpm_chip *chip =
+		(struct tpm_chip *) i2c_get_clientdata(client);
 
+	if (chip)
 		tpm_remove_hardware(chip->dev);
 
-		if (pin_infos->tpm_i2c_buffer[1] != NULL) {
-			kzfree(pin_infos->tpm_i2c_buffer[1]);
-			pin_infos->tpm_i2c_buffer[1] = NULL;
-		}
-		if (pin_infos->tpm_i2c_buffer[0] != NULL) {
-			kzfree(pin_infos->tpm_i2c_buffer[0]);
-			pin_infos->tpm_i2c_buffer[0] = NULL;
-		}
-	}
-
 	return 0;
 }
 
diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.h b/drivers/char/tpm/tpm_i2c_stm_st33.h
deleted file mode 100644
index 3041271342e..00000000000
--- a/drivers/char/tpm/tpm_i2c_stm_st33.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- * STMicroelectronics TPM I2C Linux driver for TPM ST33ZP24
- * Copyright (C) 2009, 2010  STMicroelectronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
- *
- * STMicroelectronics version 1.2.0, Copyright (C) 2010
- * STMicroelectronics comes with ABSOLUTELY NO WARRANTY.
- * This is free software, and you are welcome to redistribute it
- * under certain conditions.
- *
- * @Author: Christophe RICARD tpmsupport@st.com
- *
- * @File: stm_st33_tpm_i2c.h
- *
- * @Date: 09/15/2010
- */
-#ifndef __STM_ST33_TPM_I2C_MAIN_H__
-#define __STM_ST33_TPM_I2C_MAIN_H__
-
-#define TPM_ST33_I2C			"st33zp24_i2c"
-
-struct st33zp24_platform_data {
-	int io_serirq;
-	int io_lpcpd;
-	struct i2c_client *client;
-	u8 *tpm_i2c_buffer[2]; /* 0 Request 1 Response */
-	struct completion irq_detection;
-	struct mutex lock;
-};
-
-#endif /* __STM_ST33_TPM_I2C_MAIN_H__ */
diff --git a/include/linux/platform_data/tpm_i2c_stm_st33.h b/include/linux/platform_data/tpm_i2c_stm_st33.h
new file mode 100644
index 00000000000..88f9cb18113
--- /dev/null
+++ b/include/linux/platform_data/tpm_i2c_stm_st33.h
@@ -0,0 +1,40 @@
+/*
+ * STMicroelectronics TPM I2C Linux driver for TPM ST33ZP24
+ * Copyright (C) 2009, 2010  STMicroelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * STMicroelectronics version 1.2.0, Copyright (C) 2010
+ * STMicroelectronics comes with ABSOLUTELY NO WARRANTY.
+ * This is free software, and you are welcome to redistribute it
+ * under certain conditions.
+ *
+ * @Author: Christophe RICARD tpmsupport@st.com
+ *
+ * @File: stm_st33_tpm_i2c.h
+ *
+ * @Date: 09/15/2010
+ */
+#ifndef __STM_ST33_TPM_I2C_MAIN_H__
+#define __STM_ST33_TPM_I2C_MAIN_H__
+
+
+#define TPM_ST33_I2C			"st33zp24_i2c"
+
+struct st33zp24_platform_data {
+	int io_serirq;
+	int io_lpcpd;
+};
+
+#endif /* __STM_ST33_TPM_I2C_MAIN_H__ */
-- 
cgit v1.2.3-70-g09d2


From 76182b6b008b694d095aec1e2eb6c07fae787128 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Mon, 1 Dec 2014 19:32:52 +0100
Subject: tpm/tpm_i2c_stm_st33: Remove reference to io_serirq

The serirq gpio pin is used only as interrupt. After driver initialization,
the serirq signal is always used through interrupt and never with gpio
kernel API.

The irq can then be initialized during the platform_data definition within the client->irq pin.

Reviewed-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Peter Huewe <peterhuewe@gmx.de>
---
 drivers/char/tpm/tpm_i2c_stm_st33.c            | 13 +++----------
 include/linux/platform_data/tpm_i2c_stm_st33.h |  1 -
 2 files changed, 3 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 4f725386385..728611638d1 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -103,7 +103,6 @@ struct tpm_stm_dev {
 	struct completion irq_detection;
 	struct tpm_chip *chip;
 	u8 buf[TPM_BUFSIZE + 1];
-	int io_serirq;
 	int io_lpcpd;
 };
 
@@ -688,18 +687,15 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 			err = -ENODEV;
 			goto _tpm_clean_answer;
 		}
-		err = gpio_request(platform_data->io_serirq, "TPM IO_SERIRQ");
-		if (err)
-			goto _gpio_init2;
 
 		clear_interruption(tpm_dev);
-		err = request_irq(gpio_to_irq(platform_data->io_serirq),
+		err = request_irq(client->irq,
 				&tpm_ioserirq_handler,
 				IRQF_TRIGGER_HIGH,
 				"TPM SERIRQ management", chip);
 		if (err < 0) {
 			dev_err(chip->dev , "TPM SERIRQ signals %d not available\n",
-				gpio_to_irq(platform_data->io_serirq));
+				client->irq);
 			goto _irq_set;
 		}
 
@@ -739,10 +735,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	dev_info(chip->dev, "TPM I2C Initialized\n");
 	return 0;
 _irq_set:
-	free_irq(gpio_to_irq(platform_data->io_serirq), (void *)chip);
-_gpio_init2:
-	if (interrupts)
-		gpio_free(platform_data->io_serirq);
+	free_irq(client->irq, (void *)chip);
 _gpio_init1:
 	if (power_mgt)
 		gpio_free(platform_data->io_lpcpd);
diff --git a/include/linux/platform_data/tpm_i2c_stm_st33.h b/include/linux/platform_data/tpm_i2c_stm_st33.h
index 88f9cb18113..85775cf5f9a 100644
--- a/include/linux/platform_data/tpm_i2c_stm_st33.h
+++ b/include/linux/platform_data/tpm_i2c_stm_st33.h
@@ -33,7 +33,6 @@
 #define TPM_ST33_I2C			"st33zp24_i2c"
 
 struct st33zp24_platform_data {
-	int io_serirq;
 	int io_lpcpd;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 3eda7d0ea3a0365aa72a2007f9450f314d92f065 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 13 Jan 2015 23:13:13 +0100
Subject: tpm/tpm_i2c_stm_st33: Change tpm_i2c_stm_st33.h to tpm_stm_st33.h

include/linux/platform_data/tpm_i2c_stm_st33.h can be used by other st33
tpm device driver not using i2c protocol.

Reviewed-by: Jason Gunthorpe <jason.gunthorpe@obsidianresearch.com>
Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Reviewed-by: Peter Huewe <peterhuewe@gmx.de>
Signed-off-by: Peter Huewe <peterhuewe@gmx.de>
---
 drivers/char/tpm/tpm_i2c_stm_st33.c            |  2 +-
 include/linux/platform_data/tpm_i2c_stm_st33.h | 39 --------------------------
 include/linux/platform_data/tpm_stm_st33.h     | 39 ++++++++++++++++++++++++++
 3 files changed, 40 insertions(+), 40 deletions(-)
 delete mode 100644 include/linux/platform_data/tpm_i2c_stm_st33.h
 create mode 100644 include/linux/platform_data/tpm_stm_st33.h

(limited to 'include')

diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 86a24ced66c..dbab8d0d875 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -50,7 +50,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_gpio.h>
 
-#include <linux/platform_data/tpm_i2c_stm_st33.h>
+#include <linux/platform_data/tpm_stm_st33.h>
 #include "tpm.h"
 
 #define TPM_ACCESS			0x0
diff --git a/include/linux/platform_data/tpm_i2c_stm_st33.h b/include/linux/platform_data/tpm_i2c_stm_st33.h
deleted file mode 100644
index 85775cf5f9a..00000000000
--- a/include/linux/platform_data/tpm_i2c_stm_st33.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * STMicroelectronics TPM I2C Linux driver for TPM ST33ZP24
- * Copyright (C) 2009, 2010  STMicroelectronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
- * STMicroelectronics version 1.2.0, Copyright (C) 2010
- * STMicroelectronics comes with ABSOLUTELY NO WARRANTY.
- * This is free software, and you are welcome to redistribute it
- * under certain conditions.
- *
- * @Author: Christophe RICARD tpmsupport@st.com
- *
- * @File: stm_st33_tpm_i2c.h
- *
- * @Date: 09/15/2010
- */
-#ifndef __STM_ST33_TPM_I2C_MAIN_H__
-#define __STM_ST33_TPM_I2C_MAIN_H__
-
-
-#define TPM_ST33_I2C			"st33zp24_i2c"
-
-struct st33zp24_platform_data {
-	int io_lpcpd;
-};
-
-#endif /* __STM_ST33_TPM_I2C_MAIN_H__ */
diff --git a/include/linux/platform_data/tpm_stm_st33.h b/include/linux/platform_data/tpm_stm_st33.h
new file mode 100644
index 00000000000..ff75310c0f4
--- /dev/null
+++ b/include/linux/platform_data/tpm_stm_st33.h
@@ -0,0 +1,39 @@
+/*
+ * STMicroelectronics TPM I2C Linux driver for TPM ST33ZP24
+ * Copyright (C) 2009, 2010  STMicroelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * STMicroelectronics version 1.2.0, Copyright (C) 2010
+ * STMicroelectronics comes with ABSOLUTELY NO WARRANTY.
+ * This is free software, and you are welcome to redistribute it
+ * under certain conditions.
+ *
+ * @Author: Christophe RICARD tpmsupport@st.com
+ *
+ * @File: stm_st33_tpm.h
+ *
+ * @Date: 09/15/2010
+ */
+#ifndef __STM_ST33_TPM_H__
+#define __STM_ST33_TPM_H__
+
+#define TPM_ST33_I2C			"st33zp24-i2c"
+#define TPM_ST33_SPI			"st33zp24-spi"
+
+struct st33zp24_platform_data {
+	int io_lpcpd;
+};
+
+#endif /* __STM_ST33_TPM_H__ */
-- 
cgit v1.2.3-70-g09d2


From d23b8ad8ab23f5a18b91e2396fb63d10f66b08d6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Thu, 15 Jan 2015 09:52:39 +0100
Subject: tc: add BPF based action

This action provides a possibility to exec custom BPF code.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_bpf.h        |  25 +++++
 include/uapi/linux/tc_act/Kbuild   |   1 +
 include/uapi/linux/tc_act/tc_bpf.h |  31 ++++++
 net/sched/Kconfig                  |  12 +++
 net/sched/Makefile                 |   1 +
 net/sched/act_bpf.c                | 205 +++++++++++++++++++++++++++++++++++++
 6 files changed, 275 insertions(+)
 create mode 100644 include/net/tc_act/tc_bpf.h
 create mode 100644 include/uapi/linux/tc_act/tc_bpf.h
 create mode 100644 net/sched/act_bpf.c

(limited to 'include')

diff --git a/include/net/tc_act/tc_bpf.h b/include/net/tc_act/tc_bpf.h
new file mode 100644
index 00000000000..86a070ffc93
--- /dev/null
+++ b/include/net/tc_act/tc_bpf.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __NET_TC_BPF_H
+#define __NET_TC_BPF_H
+
+#include <linux/filter.h>
+#include <net/act_api.h>
+
+struct tcf_bpf {
+	struct tcf_common	common;
+	struct bpf_prog		*filter;
+	struct sock_filter	*bpf_ops;
+	u16			bpf_num_ops;
+};
+#define to_bpf(a) \
+	container_of(a->priv, struct tcf_bpf, common)
+
+#endif /* __NET_TC_BPF_H */
diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild
index b057da2b87a..19d5219b0b9 100644
--- a/include/uapi/linux/tc_act/Kbuild
+++ b/include/uapi/linux/tc_act/Kbuild
@@ -8,3 +8,4 @@ header-y += tc_nat.h
 header-y += tc_pedit.h
 header-y += tc_skbedit.h
 header-y += tc_vlan.h
+header-y += tc_bpf.h
diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 00000000000..5288bd77e63
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+	tc_gen;
+};
+
+enum {
+	TCA_ACT_BPF_UNSPEC,
+	TCA_ACT_BPF_TM,
+	TCA_ACT_BPF_PARMS,
+	TCA_ACT_BPF_OPS_LEN,
+	TCA_ACT_BPF_OPS,
+	__TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index c54c9d9d1ff..46694355158 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -698,6 +698,18 @@ config NET_ACT_VLAN
 	  To compile this code as a module, choose M here: the
 	  module will be called act_vlan.
 
+config NET_ACT_BPF
+        tristate "BPF based action"
+        depends on NET_CLS_ACT
+        ---help---
+	  Say Y here to execute BPF code on packets. The BPF code will decide
+	  if the packet should be dropped or not.
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_bpf.
+
 config NET_CLS_IND
 	bool "Incoming device classification"
 	depends on NET_CLS_U32 || NET_CLS_FW
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 679f24ae7f9..7ca2b4e7631 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_NET_ACT_SIMP)	+= act_simple.o
 obj-$(CONFIG_NET_ACT_SKBEDIT)	+= act_skbedit.o
 obj-$(CONFIG_NET_ACT_CSUM)	+= act_csum.o
 obj-$(CONFIG_NET_ACT_VLAN)	+= act_vlan.o
+obj-$(CONFIG_NET_ACT_BPF)	+= act_bpf.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
 obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
new file mode 100644
index 00000000000..1bd257e473a
--- /dev/null
+++ b/net/sched/act_bpf.c
@@ -0,0 +1,205 @@
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/filter.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+
+#include <linux/tc_act/tc_bpf.h>
+#include <net/tc_act/tc_bpf.h>
+
+#define BPF_TAB_MASK     15
+
+static int tcf_bpf(struct sk_buff *skb, const struct tc_action *a,
+		   struct tcf_result *res)
+{
+	struct tcf_bpf *b = a->priv;
+	int action;
+	int filter_res;
+
+	spin_lock(&b->tcf_lock);
+	b->tcf_tm.lastuse = jiffies;
+	bstats_update(&b->tcf_bstats, skb);
+	action = b->tcf_action;
+
+	filter_res = BPF_PROG_RUN(b->filter, skb);
+	if (filter_res == 0) {
+		/* Return code 0 from the BPF program
+		 * is being interpreted as a drop here.
+		 */
+		action = TC_ACT_SHOT;
+		b->tcf_qstats.drops++;
+	}
+
+	spin_unlock(&b->tcf_lock);
+	return action;
+}
+
+static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *a,
+			int bind, int ref)
+{
+	unsigned char *tp = skb_tail_pointer(skb);
+	struct tcf_bpf *b = a->priv;
+	struct tc_act_bpf opt = {
+		.index    = b->tcf_index,
+		.refcnt   = b->tcf_refcnt - ref,
+		.bindcnt  = b->tcf_bindcnt - bind,
+		.action   = b->tcf_action,
+	};
+	struct tcf_t t;
+	struct nlattr *nla;
+
+	if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, b->bpf_num_ops))
+		goto nla_put_failure;
+
+	nla = nla_reserve(skb, TCA_ACT_BPF_OPS, b->bpf_num_ops *
+			  sizeof(struct sock_filter));
+	if (!nla)
+		goto nla_put_failure;
+
+	memcpy(nla_data(nla), b->bpf_ops, nla_len(nla));
+
+	t.install = jiffies_to_clock_t(jiffies - b->tcf_tm.install);
+	t.lastuse = jiffies_to_clock_t(jiffies - b->tcf_tm.lastuse);
+	t.expires = jiffies_to_clock_t(b->tcf_tm.expires);
+	if (nla_put(skb, TCA_ACT_BPF_TM, sizeof(t), &t))
+		goto nla_put_failure;
+	return skb->len;
+
+nla_put_failure:
+	nlmsg_trim(skb, tp);
+	return -1;
+}
+
+static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = {
+	[TCA_ACT_BPF_PARMS]	= { .len = sizeof(struct tc_act_bpf) },
+	[TCA_ACT_BPF_OPS_LEN]	= { .type = NLA_U16 },
+	[TCA_ACT_BPF_OPS]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
+};
+
+static int tcf_bpf_init(struct net *net, struct nlattr *nla,
+			struct nlattr *est, struct tc_action *a,
+			int ovr, int bind)
+{
+	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	struct tc_act_bpf *parm;
+	struct tcf_bpf *b;
+	u16 bpf_size, bpf_num_ops;
+	struct sock_filter *bpf_ops;
+	struct sock_fprog_kern tmp;
+	struct bpf_prog *fp;
+	int ret;
+
+	if (!nla)
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy);
+	if (ret < 0)
+		return ret;
+
+	if (!tb[TCA_ACT_BPF_PARMS] ||
+	    !tb[TCA_ACT_BPF_OPS_LEN] || !tb[TCA_ACT_BPF_OPS])
+		return -EINVAL;
+	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
+
+	bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]);
+	if (bpf_num_ops	> BPF_MAXINSNS || bpf_num_ops == 0)
+		return -EINVAL;
+
+	bpf_size = bpf_num_ops * sizeof(*bpf_ops);
+	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	if (!bpf_ops)
+		return -ENOMEM;
+
+	memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size);
+
+	tmp.len = bpf_num_ops;
+	tmp.filter = bpf_ops;
+
+	ret = bpf_prog_create(&fp, &tmp);
+	if (ret)
+		goto free_bpf_ops;
+
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*b), bind);
+		if (ret)
+			goto destroy_fp;
+
+		ret = ACT_P_CREATED;
+	} else {
+		if (bind)
+			goto destroy_fp;
+		tcf_hash_release(a, bind);
+		if (!ovr) {
+			ret = -EEXIST;
+			goto destroy_fp;
+		}
+	}
+
+	b = to_bpf(a);
+	spin_lock_bh(&b->tcf_lock);
+	b->tcf_action = parm->action;
+	b->bpf_num_ops = bpf_num_ops;
+	b->bpf_ops = bpf_ops;
+	b->filter = fp;
+	spin_unlock_bh(&b->tcf_lock);
+
+	if (ret == ACT_P_CREATED)
+		tcf_hash_insert(a);
+	return ret;
+
+destroy_fp:
+	bpf_prog_destroy(fp);
+free_bpf_ops:
+	kfree(bpf_ops);
+	return ret;
+}
+
+static void tcf_bpf_cleanup(struct tc_action *a, int bind)
+{
+	struct tcf_bpf *b = a->priv;
+
+	bpf_prog_destroy(b->filter);
+}
+
+static struct tc_action_ops act_bpf_ops = {
+	.kind =		"bpf",
+	.type =		TCA_ACT_BPF,
+	.owner =	THIS_MODULE,
+	.act =		tcf_bpf,
+	.dump =		tcf_bpf_dump,
+	.cleanup =	tcf_bpf_cleanup,
+	.init =		tcf_bpf_init,
+};
+
+static int __init bpf_init_module(void)
+{
+	return tcf_register_action(&act_bpf_ops, BPF_TAB_MASK);
+}
+
+static void __exit bpf_cleanup_module(void)
+{
+	tcf_unregister_action(&act_bpf_ops);
+}
+
+module_init(bpf_init_module);
+module_exit(bpf_cleanup_module);
+
+MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
+MODULE_DESCRIPTION("TC BPF based action");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3-70-g09d2


From 03bf0c281234028388108d0aee720954f5fe6924 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Thu, 15 Jan 2015 23:49:36 +0100
Subject: switchdev: introduce switchdev notifier

This patch introduces new notifier for purposes of exposing events which happen
on switch driver side. The consumers of the event messages are mainly involved
masters, namely bridge and ovs.

Suggested-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   | 31 ++++++++++++++++++++++
 net/switchdev/switchdev.c | 65 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 96 insertions(+)

(limited to 'include')

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 8a6d1641fd9..7f8d74372d8 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -11,12 +11,27 @@
 #define _LINUX_SWITCHDEV_H_
 
 #include <linux/netdevice.h>
+#include <linux/notifier.h>
+
+struct netdev_switch_notifier_info {
+	struct net_device *dev;
+};
+
+static inline struct net_device *
+netdev_switch_notifier_info_to_dev(const struct netdev_switch_notifier_info *info)
+{
+	return info->dev;
+}
 
 #ifdef CONFIG_NET_SWITCHDEV
 
 int netdev_switch_parent_id_get(struct net_device *dev,
 				struct netdev_phys_item_id *psid);
 int netdev_switch_port_stp_update(struct net_device *dev, u8 state);
+int register_netdev_switch_notifier(struct notifier_block *nb);
+int unregister_netdev_switch_notifier(struct notifier_block *nb);
+int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
+				 struct netdev_switch_notifier_info *info);
 
 #else
 
@@ -32,6 +47,22 @@ static inline int netdev_switch_port_stp_update(struct net_device *dev,
 	return -EOPNOTSUPP;
 }
 
+static inline int register_netdev_switch_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int unregister_netdev_switch_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
+					       struct netdev_switch_notifier_info *info);
+{
+	return NOTIFY_DONE;
+}
+
 #endif
 
 #endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index d162b21b14b..22e02f4edd9 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -11,6 +11,8 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
 #include <linux/netdevice.h>
 #include <net/switchdev.h>
 
@@ -50,3 +52,66 @@ int netdev_switch_port_stp_update(struct net_device *dev, u8 state)
 	return ops->ndo_switch_port_stp_update(dev, state);
 }
 EXPORT_SYMBOL(netdev_switch_port_stp_update);
+
+static DEFINE_MUTEX(netdev_switch_mutex);
+static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain);
+
+/**
+ *	register_netdev_switch_notifier - Register nofifier
+ *	@nb: notifier_block
+ *
+ *	Register switch device notifier. This should be used by code
+ *	which needs to monitor events happening in particular device.
+ *	Return values are same as for atomic_notifier_chain_register().
+ */
+int register_netdev_switch_notifier(struct notifier_block *nb)
+{
+	int err;
+
+	mutex_lock(&netdev_switch_mutex);
+	err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb);
+	mutex_unlock(&netdev_switch_mutex);
+	return err;
+}
+EXPORT_SYMBOL(register_netdev_switch_notifier);
+
+/**
+ *	unregister_netdev_switch_notifier - Unregister nofifier
+ *	@nb: notifier_block
+ *
+ *	Unregister switch device notifier.
+ *	Return values are same as for atomic_notifier_chain_unregister().
+ */
+int unregister_netdev_switch_notifier(struct notifier_block *nb)
+{
+	int err;
+
+	mutex_lock(&netdev_switch_mutex);
+	err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb);
+	mutex_unlock(&netdev_switch_mutex);
+	return err;
+}
+EXPORT_SYMBOL(unregister_netdev_switch_notifier);
+
+/**
+ *	call_netdev_switch_notifiers - Call nofifiers
+ *	@val: value passed unmodified to notifier function
+ *	@dev: port device
+ *	@info: notifier information data
+ *
+ *	Call all network notifier blocks. This should be called by driver
+ *	when it needs to propagate hardware event.
+ *	Return values are same as for atomic_notifier_call_chain().
+ */
+int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
+				 struct netdev_switch_notifier_info *info)
+{
+	int err;
+
+	info->dev = dev;
+	mutex_lock(&netdev_switch_mutex);
+	err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info);
+	mutex_unlock(&netdev_switch_mutex);
+	return err;
+}
+EXPORT_SYMBOL(call_netdev_switch_notifiers);
-- 
cgit v1.2.3-70-g09d2


From 3aeb66176ffa8fefd7a9f7d37bda1d8adcf469a1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Thu, 15 Jan 2015 23:49:37 +0100
Subject: net: replace br_fdb_external_learn_* calls with switchdev notifier
 events

This patch benefits from newly introduced switchdev notifier and uses it
to propagate fdb learn events from rocker driver to bridge. That avoids
direct function calls and possible use by other listeners (ovs).

Suggested-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/rocker/rocker.c | 10 +++++--
 include/linux/if_bridge.h            | 18 -------------
 include/net/switchdev.h              | 11 ++++++++
 net/bridge/br.c                      | 52 +++++++++++++++++++++++++++++++++++-
 net/bridge/br_fdb.c                  | 38 +++-----------------------
 net/bridge/br_private.h              |  4 +++
 6 files changed, 78 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index cad8cf962cd..964d719b150 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -3026,11 +3026,17 @@ static void rocker_port_fdb_learn_work(struct work_struct *work)
 		container_of(work, struct rocker_fdb_learn_work, work);
 	bool removing = (lw->flags & ROCKER_OP_FLAG_REMOVE);
 	bool learned = (lw->flags & ROCKER_OP_FLAG_LEARNED);
+	struct netdev_switch_notifier_fdb_info info;
+
+	info.addr = lw->addr;
+	info.vid = lw->vid;
 
 	if (learned && removing)
-		br_fdb_external_learn_del(lw->dev, lw->addr, lw->vid);
+		call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_DEL,
+					     lw->dev, &info.info);
 	else if (learned && !removing)
-		br_fdb_external_learn_add(lw->dev, lw->addr, lw->vid);
+		call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_ADD,
+					     lw->dev, &info.info);
 
 	kfree(work);
 }
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 0a8ce762a47..a57bca2ea97 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -50,24 +50,6 @@ extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __use
 typedef int br_should_route_hook_t(struct sk_buff *skb);
 extern br_should_route_hook_t __rcu *br_should_route_hook;
 
-#if IS_ENABLED(CONFIG_BRIDGE)
-int br_fdb_external_learn_add(struct net_device *dev,
-			      const unsigned char *addr, u16 vid);
-int br_fdb_external_learn_del(struct net_device *dev,
-			      const unsigned char *addr, u16 vid);
-#else
-static inline int br_fdb_external_learn_add(struct net_device *dev,
-					    const unsigned char *addr, u16 vid)
-{
-	return 0;
-}
-static inline int br_fdb_external_learn_del(struct net_device *dev,
-					    const unsigned char *addr, u16 vid)
-{
-	return 0;
-}
-#endif
-
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
 int br_multicast_list_adjacent(struct net_device *dev,
 			       struct list_head *br_ip_list);
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 7f8d74372d8..201120e18e4 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -13,10 +13,21 @@
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
 
+enum netdev_switch_notifier_type {
+	NETDEV_SWITCH_FDB_ADD = 1,
+	NETDEV_SWITCH_FDB_DEL,
+};
+
 struct netdev_switch_notifier_info {
 	struct net_device *dev;
 };
 
+struct netdev_switch_notifier_fdb_info {
+	struct netdev_switch_notifier_info info; /* must be first */
+	const unsigned char *addr;
+	u16 vid;
+};
+
 static inline struct net_device *
 netdev_switch_notifier_info_to_dev(const struct netdev_switch_notifier_info *info)
 {
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 44425aff7cb..fb57ab6b24f 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -19,6 +19,7 @@
 #include <linux/llc.h>
 #include <net/llc.h>
 #include <net/stp.h>
+#include <net/switchdev.h>
 
 #include "br_private.h"
 
@@ -120,6 +121,48 @@ static struct notifier_block br_device_notifier = {
 	.notifier_call = br_device_event
 };
 
+static int br_netdev_switch_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_switch_notifier_info_to_dev(ptr);
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	struct netdev_switch_notifier_fdb_info *fdb_info;
+	int err = NOTIFY_DONE;
+
+	rtnl_lock();
+	p = br_port_get_rtnl(dev);
+	if (!p)
+		goto out;
+
+	br = p->br;
+
+	switch (event) {
+	case NETDEV_SWITCH_FDB_ADD:
+		fdb_info = ptr;
+		err = br_fdb_external_learn_add(br, p, fdb_info->addr,
+						fdb_info->vid);
+		if (err)
+			err = notifier_from_errno(err);
+		break;
+	case NETDEV_SWITCH_FDB_DEL:
+		fdb_info = ptr;
+		err = br_fdb_external_learn_del(br, p, fdb_info->addr,
+						fdb_info->vid);
+		if (err)
+			err = notifier_from_errno(err);
+		break;
+	}
+
+out:
+	rtnl_unlock();
+	return err;
+}
+
+static struct notifier_block br_netdev_switch_notifier = {
+	.notifier_call = br_netdev_switch_event,
+};
+
 static void __net_exit br_net_exit(struct net *net)
 {
 	struct net_device *dev;
@@ -169,10 +212,14 @@ static int __init br_init(void)
 	if (err)
 		goto err_out3;
 
-	err = br_netlink_init();
+	err = register_netdev_switch_notifier(&br_netdev_switch_notifier);
 	if (err)
 		goto err_out4;
 
+	err = br_netlink_init();
+	if (err)
+		goto err_out5;
+
 	brioctl_set(br_ioctl_deviceless_stub);
 
 #if IS_ENABLED(CONFIG_ATM_LANE)
@@ -185,6 +232,8 @@ static int __init br_init(void)
 
 	return 0;
 
+err_out5:
+	unregister_netdev_switch_notifier(&br_netdev_switch_notifier);
 err_out4:
 	unregister_netdevice_notifier(&br_device_notifier);
 err_out3:
@@ -202,6 +251,7 @@ static void __exit br_deinit(void)
 {
 	stp_proto_unregister(&br_stp_proto);
 	br_netlink_fini();
+	unregister_netdev_switch_notifier(&br_netdev_switch_notifier);
 	unregister_netdevice_notifier(&br_device_notifier);
 	brioctl_set(NULL);
 	unregister_pernet_subsys(&br_net_ops);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index e6e0372bc3c..03667e65cc2 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -990,26 +990,14 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
 	}
 }
 
-int br_fdb_external_learn_add(struct net_device *dev,
+int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
 			      const unsigned char *addr, u16 vid)
 {
-	struct net_bridge_port *p;
-	struct net_bridge *br;
 	struct hlist_head *head;
 	struct net_bridge_fdb_entry *fdb;
 	int err = 0;
 
-	rtnl_lock();
-
-	p = br_port_get_rtnl(dev);
-	if (!p) {
-		pr_info("bridge: %s not a bridge port\n", dev->name);
-		err = -EINVAL;
-		goto err_rtnl_unlock;
-	}
-
-	br = p->br;
-
+	ASSERT_RTNL();
 	spin_lock_bh(&br->hash_lock);
 
 	head = &br->hash[br_mac_hash(addr, vid)];
@@ -1034,33 +1022,18 @@ int br_fdb_external_learn_add(struct net_device *dev,
 
 err_unlock:
 	spin_unlock_bh(&br->hash_lock);
-err_rtnl_unlock:
-	rtnl_unlock();
 
 	return err;
 }
-EXPORT_SYMBOL(br_fdb_external_learn_add);
 
-int br_fdb_external_learn_del(struct net_device *dev,
+int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
 			      const unsigned char *addr, u16 vid)
 {
-	struct net_bridge_port *p;
-	struct net_bridge *br;
 	struct hlist_head *head;
 	struct net_bridge_fdb_entry *fdb;
 	int err = 0;
 
-	rtnl_lock();
-
-	p = br_port_get_rtnl(dev);
-	if (!p) {
-		pr_info("bridge: %s not a bridge port\n", dev->name);
-		err = -EINVAL;
-		goto err_rtnl_unlock;
-	}
-
-	br = p->br;
-
+	ASSERT_RTNL();
 	spin_lock_bh(&br->hash_lock);
 
 	head = &br->hash[br_mac_hash(addr, vid)];
@@ -1071,9 +1044,6 @@ int br_fdb_external_learn_del(struct net_device *dev,
 		err = -ENOENT;
 
 	spin_unlock_bh(&br->hash_lock);
-err_rtnl_unlock:
-	rtnl_unlock();
 
 	return err;
 }
-EXPORT_SYMBOL(br_fdb_external_learn_del);
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d808d766334..e8e3f368168 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -402,6 +402,10 @@ int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		struct net_device *dev, struct net_device *fdev, int idx);
 int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
 void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
+int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid);
+int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
+			      const unsigned char *addr, u16 vid);
 
 /* br_forward.c */
 void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
-- 
cgit v1.2.3-70-g09d2


From 053c095a82cf773075e83d7233b5cc19a1f73ece Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 16 Jan 2015 22:09:00 +0100
Subject: netlink: make nlmsg_end() and genlmsg_end() void

Contrary to common expectations for an "int" return, these functions
return only a positive value -- if used correctly they cannot even
return 0 because the message header will necessarily be in the skb.

This makes the very common pattern of

  if (genlmsg_end(...) < 0) { ... }

be a whole bunch of dead code. Many places also simply do

  return nlmsg_end(...);

and the caller is expected to deal with it.

This also commonly (at least for me) causes errors, because it is very
common to write

  if (my_function(...))
    /* error condition */

and if my_function() does "return nlmsg_end()" this is of course wrong.

Additionally, there's not a single place in the kernel that actually
needs the message length returned, and if anyone needs it later then
it'll be very easy to just use skb->len there.

Remove this, and make the functions void. This removes a bunch of dead
code as described above. The patch adds lines because I did

-	return nlmsg_end(...);
+	nlmsg_end(...);
+	return 0;

I could have preserved all the function's return values by returning
skb->len, but instead I've audited all the places calling the affected
functions and found that none cared. A few places actually compared
the return value with <= 0 in dump functionality, but that could just
be changed to < 0 with no change in behaviour, so I opted for the more
efficient version.

One instance of the error I've made numerous times now is also present
in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't
check for <0 or <=0 and thus broke out of the loop every single time.
I've preserved this since it will (I think) have caused the messages to
userspace to be formatted differently with just a single message for
every SKB returned to userspace. It's possible that this isn't needed
for the tools that actually use this, but I don't even know what they
are so couldn't test that changing this behaviour would be acceptable.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/acpi/event.c                  |  7 +------
 drivers/net/ethernet/rocker/rocker.c  |  3 ++-
 drivers/net/vxlan.c                   |  3 ++-
 drivers/net/wireless/mac80211_hwsim.c |  3 ++-
 drivers/scsi/pmcraid.c                |  8 +-------
 drivers/target/target_core_user.c     |  4 +---
 drivers/thermal/thermal_core.c        |  6 +-----
 fs/dlm/netlink.c                      |  7 +------
 include/net/genetlink.h               |  4 ++--
 include/net/netlink.h                 |  6 +-----
 kernel/taskstats.c                    | 13 ++-----------
 net/bridge/br_fdb.c                   |  3 ++-
 net/bridge/br_mdb.c                   |  3 ++-
 net/bridge/br_netlink.c               |  3 ++-
 net/can/gw.c                          |  3 ++-
 net/core/fib_rules.c                  |  3 ++-
 net/core/neighbour.c                  | 12 ++++++++----
 net/core/rtnetlink.c                  |  9 ++++++---
 net/decnet/dn_dev.c                   |  3 ++-
 net/decnet/dn_route.c                 |  3 ++-
 net/decnet/dn_table.c                 |  3 ++-
 net/ieee802154/netlink.c              | 12 ++----------
 net/ieee802154/nl-mac.c               |  3 ++-
 net/ieee802154/nl-phy.c               |  3 ++-
 net/ieee802154/nl802154.c             |  6 ++++--
 net/ipv4/devinet.c                    |  8 +++++---
 net/ipv4/fib_semantics.c              |  3 ++-
 net/ipv4/inet_diag.c                  |  9 ++++++---
 net/ipv4/ipmr.c                       |  3 ++-
 net/ipv4/route.c                      |  3 ++-
 net/ipv4/tcp_metrics.c                |  3 ++-
 net/ipv6/addrconf.c                   | 32 +++++++++++++++++++-------------
 net/ipv6/addrlabel.c                  |  5 +++--
 net/ipv6/ip6_fib.c                    |  1 -
 net/ipv6/ip6mr.c                      |  3 ++-
 net/ipv6/route.c                      |  3 ++-
 net/l2tp/l2tp_netlink.c               | 10 ++++++----
 net/netfilter/ipvs/ip_vs_ctl.c        |  9 ++++++---
 net/netfilter/nf_tables_api.c         | 18 ++++++++++++------
 net/netlabel/netlabel_cipso_v4.c      |  3 ++-
 net/netlabel/netlabel_mgmt.c          |  6 ++++--
 net/netlabel/netlabel_unlabeled.c     |  3 ++-
 net/netlink/diag.c                    |  3 ++-
 net/netlink/genetlink.c               |  6 ++++--
 net/nfc/netlink.c                     | 12 +++++++-----
 net/openvswitch/datapath.c            |  9 ++++++---
 net/packet/diag.c                     |  3 ++-
 net/phonet/pn_netlink.c               | 16 +++++++++++-----
 net/unix/diag.c                       |  3 ++-
 net/wireless/nl80211.c                | 27 ++++++++++++++++++---------
 net/xfrm/xfrm_user.c                  | 27 ++++++++++++++++++---------
 51 files changed, 203 insertions(+), 158 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index ef2d730734d..e24ea4e796e 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -100,7 +100,6 @@ int acpi_bus_generate_netlink_event(const char *device_class,
 	struct acpi_genl_event *event;
 	void *msg_header;
 	int size;
-	int result;
 
 	/* allocate memory */
 	size = nla_total_size(sizeof(struct acpi_genl_event)) +
@@ -137,11 +136,7 @@ int acpi_bus_generate_netlink_event(const char *device_class,
 	event->data = data;
 
 	/* send multicast genetlink message */
-	result = genlmsg_end(skb, msg_header);
-	if (result < 0) {
-		nlmsg_free(skb);
-		return result;
-	}
+	genlmsg_end(skb, msg_header);
 
 	genlmsg_multicast(&acpi_event_genl_family, skb, 0, 0, GFP_ATOMIC);
 	return 0;
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 964d719b150..d54781e71cd 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -3674,7 +3674,8 @@ static int rocker_fdb_fill_info(struct sk_buff *skb,
 	if (vid && nla_put_u16(skb, NDA_VLAN, vid))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 6b6b45622a0..c5f79e7513a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -363,7 +363,8 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 494e7335aa6..4a4c6586a8d 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2557,7 +2557,8 @@ static int mac80211_hwsim_get_radio(struct sk_buff *skb,
 	if (res < 0)
 		goto out_err;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 out_err:
 	genlmsg_cancel(skb, hdr);
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 8c27b6a77ec..cf222f46eac 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -1473,13 +1473,7 @@ static int pmcraid_notify_aen(
 	}
 
 	/* send genetlink multicast message to notify appplications */
-	result = genlmsg_end(skb, msg_header);
-
-	if (result < 0) {
-		pmcraid_err("genlmsg_end failed\n");
-		nlmsg_free(skb);
-		return result;
-	}
+	genlmsg_end(skb, msg_header);
 
 	result = genlmsg_multicast(&pmcraid_event_family, skb,
 				   0, 0, GFP_ATOMIC);
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 1157b559683..1a1bcf71ec9 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -784,9 +784,7 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, int mino
 	if (ret < 0)
 		goto free_skb;
 
-	ret = genlmsg_end(skb, msg_header);
-	if (ret < 0)
-		goto free_skb;
+	genlmsg_end(skb, msg_header);
 
 	ret = genlmsg_multicast(&tcmu_genl_family, skb, 0,
 				TCMU_MCGRP_CONFIG, GFP_KERNEL);
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 87e0b078202..48491d1a81d 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1759,11 +1759,7 @@ int thermal_generate_netlink_event(struct thermal_zone_device *tz,
 	thermal_event->event = event;
 
 	/* send multicast genetlink message */
-	result = genlmsg_end(skb, msg_header);
-	if (result < 0) {
-		nlmsg_free(skb);
-		return result;
-	}
+	genlmsg_end(skb, msg_header);
 
 	result = genlmsg_multicast(&thermal_event_genl_family, skb, 0,
 				   0, GFP_ATOMIC);
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index e7cfbaf8d0e..1e6e227134d 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -56,13 +56,8 @@ static int send_data(struct sk_buff *skb)
 {
 	struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data);
 	void *data = genlmsg_data(genlhdr);
-	int rv;
 
-	rv = genlmsg_end(skb, data);
-	if (rv < 0) {
-		nlmsg_free(skb);
-		return rv;
-	}
+	genlmsg_end(skb, data);
 
 	return genlmsg_unicast(&init_net, skb, listener_nlportid);
 }
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 84125088c30..f24aa83b80b 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -245,9 +245,9 @@ static inline void *genlmsg_put_reply(struct sk_buff *skb,
  * @skb: socket buffer the message is stored in
  * @hdr: user specific header
  */
-static inline int genlmsg_end(struct sk_buff *skb, void *hdr)
+static inline void genlmsg_end(struct sk_buff *skb, void *hdr)
 {
-	return nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN);
+	nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN);
 }
 
 /**
diff --git a/include/net/netlink.h b/include/net/netlink.h
index d5869b90bfb..e010ee8da41 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -490,14 +490,10 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags)
  * Corrects the netlink message header to include the appeneded
  * attributes. Only necessary if attributes have been added to
  * the message.
- *
- * Returns the total data length of the skb.
  */
-static inline int nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh)
+static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh;
-
-	return skb->len;
 }
 
 /**
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 670fff88a96..21f82c29c91 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -111,13 +111,8 @@ static int send_reply(struct sk_buff *skb, struct genl_info *info)
 {
 	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
 	void *reply = genlmsg_data(genlhdr);
-	int rc;
 
-	rc = genlmsg_end(skb, reply);
-	if (rc < 0) {
-		nlmsg_free(skb);
-		return rc;
-	}
+	genlmsg_end(skb, reply);
 
 	return genlmsg_reply(skb, info);
 }
@@ -134,11 +129,7 @@ static void send_cpu_listeners(struct sk_buff *skb,
 	void *reply = genlmsg_data(genlhdr);
 	int rc, delcount = 0;
 
-	rc = genlmsg_end(skb, reply);
-	if (rc < 0) {
-		nlmsg_free(skb);
-		return;
-	}
+	genlmsg_end(skb, reply);
 
 	rc = 0;
 	down_read(&listeners->sem);
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 03667e65cc2..08bf04bdac5 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -633,7 +633,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 	if (fdb->vlan_id && nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index fed61c971b1..40960896089 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -190,7 +190,8 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
 
 	nla_nest_end(skb, nest2);
 	nla_nest_end(skb, nest);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 end:
 	nla_nest_end(skb, nest);
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 163950b10d8..528cf2790a5 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -263,7 +263,8 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 	}
 
 done:
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/can/gw.c b/net/can/gw.c
index 295f62e62eb..a6f448e18ea 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -575,7 +575,8 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
 			goto cancel;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 cancel:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 185c341fafb..44706e81b2e 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -609,7 +609,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	if (ops->fill(rule, skb, frh) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8d614c93f86..d36d564f149 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1884,7 +1884,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
 		goto nla_put_failure;
 
 	read_unlock_bh(&tbl->lock);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	read_unlock_bh(&tbl->lock);
@@ -1917,7 +1918,8 @@ static int neightbl_fill_param_info(struct sk_buff *skb,
 		goto errout;
 
 	read_unlock_bh(&tbl->lock);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 errout:
 	read_unlock_bh(&tbl->lock);
 	nlmsg_cancel(skb, nlh);
@@ -2202,7 +2204,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
 	    nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2232,7 +2235,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index eadc5c0e2df..e13b9dbdf15 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1199,7 +1199,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 
 	nla_nest_end(skb, af_spec);
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2326,7 +2327,8 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
 	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -2809,7 +2811,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 	nla_nest_end(skb, protinfo);
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
 	return -EMSGSIZE;
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 4400da7739d..b2c26b08113 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -702,7 +702,8 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa,
 	     nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
 	     nla_put_u32(skb, IFA_FLAGS, ifa_flags))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index daccc4a36d8..812e5e6e88f 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1616,7 +1616,8 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 	    nla_put_u32(skb, RTA_IIF, rt->fld.flowidn_iif) < 0)
 		goto errout;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 errout:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c
index 3f19fcbf126..1540b506e3e 100644
--- a/net/decnet/dn_table.c
+++ b/net/decnet/dn_table.c
@@ -367,7 +367,8 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		nla_nest_end(skb, mp_head);
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 errout:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index fa1464762d0..c8133c07cee 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -63,13 +63,9 @@ int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group)
 	struct nlmsghdr *nlh = nlmsg_hdr(msg);
 	void *hdr = genlmsg_data(nlmsg_data(nlh));
 
-	if (genlmsg_end(msg, hdr) < 0)
-		goto out;
+	genlmsg_end(msg, hdr);
 
 	return genlmsg_multicast(&nl802154_family, msg, 0, group, GFP_ATOMIC);
-out:
-	nlmsg_free(msg);
-	return -ENOBUFS;
 }
 
 struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info,
@@ -96,13 +92,9 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
 	struct nlmsghdr *nlh = nlmsg_hdr(msg);
 	void *hdr = genlmsg_data(nlmsg_data(nlh));
 
-	if (genlmsg_end(msg, hdr) < 0)
-		goto out;
+	genlmsg_end(msg, hdr);
 
 	return genlmsg_reply(msg, info);
-out:
-	nlmsg_free(msg);
-	return -ENOBUFS;
 }
 
 static const struct genl_ops ieee8021154_ops[] = {
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 3c902e9516f..9105265920f 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -136,7 +136,8 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 	}
 
 	wpan_phy_put(phy);
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	wpan_phy_put(phy);
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 7baf98b1461..1b9d25f6e89 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -65,7 +65,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 		goto nla_put_failure;
 	mutex_unlock(&phy->pib_lock);
 	kfree(buf);
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	mutex_unlock(&phy->pib_lock);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index a25b9bbd077..a4daf91b8d0 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -306,7 +306,8 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev,
 		goto nla_put_failure;
 
 finish:
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -489,7 +490,8 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags,
 	if (nla_put_u8(msg, NL802154_ATTR_LBT_MODE, wpan_dev->lbt))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 214882e7d6d..5f344eb3fc2 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1522,7 +1522,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
 			  preferred, valid))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -1566,7 +1567,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 				if (inet_fill_ifaddr(skb, ifa,
 					     NETLINK_CB(cb->skb).portid,
 					     cb->nlh->nlmsg_seq,
-					     RTM_NEWADDR, NLM_F_MULTI) <= 0) {
+					     RTM_NEWADDR, NLM_F_MULTI) < 0) {
 					rcu_read_unlock();
 					goto done;
 				}
@@ -1749,7 +1750,8 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d2b7b5521b1..265cb72b7c1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1091,7 +1091,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		nla_nest_end(skb, mp);
 	}
 #endif
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e34dccbc4d7..81751f12645 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -203,7 +203,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		icsk->icsk_ca_ops->get_info(sk, ext, skb);
 
 out:
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 errout:
 	nlmsg_cancel(skb, nlh);
@@ -271,7 +272,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	}
 #endif
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
@@ -758,7 +760,8 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 	}
 #endif
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c8034587859..9d78427652d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2290,7 +2290,8 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 	if (err < 0 && err != -ENOENT)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ce112d0f269..f6e43ca5e64 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2390,7 +2390,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index ed9c9a91851..e5f41bd5ec1 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -886,7 +886,8 @@ static int tcp_metrics_dump_info(struct sk_buff *skb,
 	if (tcp_metrics_fill_info(skb, tm) < 0)
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f7c8bbeb27b..8975d9501d5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -489,7 +489,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -619,7 +620,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
 						       cb->nlh->nlmsg_seq,
 						       RTM_NEWNETCONF,
 						       NLM_F_MULTI,
-						       -1) <= 0) {
+						       -1) < 0) {
 				rcu_read_unlock();
 				goto done;
 			}
@@ -635,7 +636,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) <= 0)
+					       -1) < 0)
 			goto done;
 		else
 			h++;
@@ -646,7 +647,7 @@ cont:
 					       NETLINK_CB(cb->skb).portid,
 					       cb->nlh->nlmsg_seq,
 					       RTM_NEWNETCONF, NLM_F_MULTI,
-					       -1) <= 0)
+					       -1) < 0)
 			goto done;
 		else
 			h++;
@@ -4047,7 +4048,8 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0)
 		goto error;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 error:
 	nlmsg_cancel(skb, nlh);
@@ -4076,7 +4078,8 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
@@ -4101,7 +4104,8 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 enum addr_type_t {
@@ -4134,7 +4138,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						cb->nlh->nlmsg_seq,
 						RTM_NEWADDR,
 						NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 		}
@@ -4151,7 +4155,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETMULTICAST,
 						  NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		break;
@@ -4166,7 +4170,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
 						  cb->nlh->nlmsg_seq,
 						  RTM_GETANYCAST,
 						  NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		break;
@@ -4638,7 +4642,8 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
 		goto nla_put_failure;
 
 	nla_nest_end(skb, protoinfo);
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -4670,7 +4675,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 			if (inet6_fill_ifinfo(skb, idev,
 					      NETLINK_CB(cb->skb).portid,
 					      cb->nlh->nlmsg_seq,
-					      RTM_NEWLINK, NLM_F_MULTI) <= 0)
+					      RTM_NEWLINK, NLM_F_MULTI) < 0)
 				goto out;
 cont:
 			idx++;
@@ -4747,7 +4752,8 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
 	ci.valid_time = ntohl(pinfo->valid);
 	if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index fd0dc47f471..e43e79d0a61 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -490,7 +490,8 @@ static int ip6addrlbl_fill(struct sk_buff *skb,
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
@@ -510,7 +511,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 					      cb->nlh->nlmsg_seq,
 					      RTM_NEWADDRLABEL,
 					      NLM_F_MULTI);
-			if (err <= 0)
+			if (err < 0)
 				break;
 		}
 		idx++;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 03c520a4ebe..53775ee7d37 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -277,7 +277,6 @@ static int fib6_dump_node(struct fib6_walker *w)
 			w->leaf = rt;
 			return 1;
 		}
-		WARN_ON(res == 0);
 	}
 	w->leaf = NULL;
 	return 0;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 722669754bb..34b682617f5 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2388,7 +2388,8 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
 	if (err < 0 && err != -ENOENT)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 34dcbb59df7..c60f15775c5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2725,7 +2725,8 @@ static int rt6_fill_node(struct net *net,
 	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 6b16598f31d..b4e923f7795 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -390,7 +390,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	}
 
 out:
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -451,7 +452,7 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
 					cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					tunnel, L2TP_CMD_TUNNEL_GET) <= 0)
+					tunnel, L2TP_CMD_TUNNEL_GET) < 0)
 			goto out;
 
 		ti++;
@@ -752,7 +753,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 		goto nla_put_failure;
 	nla_nest_end(skb, nest);
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -816,7 +818,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					 session, L2TP_CMD_SESSION_GET) <= 0)
+					 session, L2TP_CMD_SESSION_GET) < 0)
 			break;
 
 		si++;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index b8295a430a5..e5575905636 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2887,7 +2887,8 @@ static int ip_vs_genl_dump_service(struct sk_buff *skb,
 	if (ip_vs_genl_fill_service(skb, svc) < 0)
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -3079,7 +3080,8 @@ static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest,
 	if (ip_vs_genl_fill_dest(skb, dest) < 0)
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -3215,7 +3217,8 @@ static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state,
 	if (ip_vs_genl_fill_daemon(skb, state, mcast_ifn, syncid))
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3b3ddb4fb9e..70f697827b9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -427,7 +427,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 	    nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -971,7 +972,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 	if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use)))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -1707,7 +1709,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 	    nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule)))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -2361,7 +2364,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 		goto nla_put_failure;
 	nla_nest_end(skb, desc);
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -3035,7 +3039,8 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 
 	nla_nest_end(skb, nest);
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
@@ -3324,7 +3329,8 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
 	if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)))
 		goto nla_put_failure;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_trim(skb, nlh);
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index c2f2a53a487..179625353ca 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -641,7 +641,8 @@ static int netlbl_cipsov4_listall_cb(struct cipso_v4_doi *doi_def, void *arg)
 	if (ret_val != 0)
 		goto listall_cb_failure;
 
-	return genlmsg_end(cb_arg->skb, data);
+	genlmsg_end(cb_arg->skb, data);
+	return 0;
 
 listall_cb_failure:
 	genlmsg_cancel(cb_arg->skb, data);
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index e66e977ef2f..8b3b789c43c 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -456,7 +456,8 @@ static int netlbl_mgmt_listall_cb(struct netlbl_dom_map *entry, void *arg)
 		goto listall_cb_failure;
 
 	cb_arg->seq++;
-	return genlmsg_end(cb_arg->skb, data);
+	genlmsg_end(cb_arg->skb, data);
+	return 0;
 
 listall_cb_failure:
 	genlmsg_cancel(cb_arg->skb, data);
@@ -620,7 +621,8 @@ static int netlbl_mgmt_protocols_cb(struct sk_buff *skb,
 	if (ret_val != 0)
 		goto protocols_cb_failure;
 
-	return genlmsg_end(skb, data);
+	genlmsg_end(skb, data);
+	return 0;
 
 protocols_cb_failure:
 	genlmsg_cancel(skb, data);
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 78a63c18779..aec7994f78c 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1163,7 +1163,8 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd,
 		goto list_cb_failure;
 
 	cb_arg->seq++;
-	return genlmsg_end(cb_arg->skb, data);
+	genlmsg_end(cb_arg->skb, data);
+	return 0;
 
 list_cb_failure:
 	genlmsg_cancel(cb_arg->skb, data);
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index bb59a7ed085..3ee63a3cff3 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -91,7 +91,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sk_diag_put_rings_cfg(sk, skb))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 2e11061ef88..f52a7d5734c 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -756,7 +756,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq,
 		nla_nest_end(skb, nla_grps);
 	}
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
@@ -796,7 +797,8 @@ static int ctrl_fill_mcgrp_info(struct genl_family *family,
 	nla_nest_end(skb, nest);
 	nla_nest_end(skb, nla_grps);
 
-	return genlmsg_end(skb, hdr);
+	genlmsg_end(skb, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, hdr);
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 44989fc8cdd..be387e6219a 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -102,7 +102,8 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target,
 			goto nla_put_failure;
 	}
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -518,7 +519,8 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev,
 	    nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -908,7 +910,8 @@ static int nfc_genl_send_params(struct sk_buff *msg,
 	    nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux)))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 
@@ -1247,8 +1250,7 @@ static int nfc_genl_send_se(struct sk_buff *msg, struct nfc_dev *dev,
 		    nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type))
 			goto nla_put_failure;
 
-		if (genlmsg_end(msg, hdr) < 0)
-			goto nla_put_failure;
+		genlmsg_end(msg, hdr);
 	}
 
 	return 0;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 8bda3cc1234..f45f1bf4422 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -799,7 +799,8 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 	if (err)
 		goto error;
 
-	return genlmsg_end(skb, ovs_header);
+	genlmsg_end(skb, ovs_header);
+	return 0;
 
 error:
 	genlmsg_cancel(skb, ovs_header);
@@ -1349,7 +1350,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 	if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features))
 		goto nla_put_failure;
 
-	return genlmsg_end(skb, ovs_header);
+	genlmsg_end(skb, ovs_header);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(skb, ovs_header);
@@ -1723,7 +1725,8 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 	if (err == -EMSGSIZE)
 		goto error;
 
-	return genlmsg_end(skb, ovs_header);
+	genlmsg_end(skb, ovs_header);
+	return 0;
 
 nla_put_failure:
 	err = -EMSGSIZE;
diff --git a/net/packet/diag.c b/net/packet/diag.c
index 92f2c7107ee..0ed68f0238b 100644
--- a/net/packet/diag.c
+++ b/net/packet/diag.c
@@ -177,7 +177,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 				     PACKET_DIAG_FILTER))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index b64151ade6b..54d766842c2 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -121,7 +121,8 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr,
 	ifm->ifa_index = dev->ifindex;
 	if (nla_put_u8(skb, IFA_LOCAL, addr))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -190,7 +191,8 @@ static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst,
 	if (nla_put_u8(skb, RTA_DST, dst) ||
 	    nla_put_u32(skb, RTA_OIF, dev->ifindex))
 		goto nla_put_failure;
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 nla_put_failure:
 	nlmsg_cancel(skb, nlh);
@@ -282,9 +284,13 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 		if (addr_idx++ < addr_start_idx)
 			continue;
-		if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid,
-				cb->nlh->nlmsg_seq, RTM_NEWROUTE))
-			goto out;
+		fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid,
+			   cb->nlh->nlmsg_seq, RTM_NEWROUTE);
+		/* fill_route() used to return > 0 (or negative errors) but
+		 * never 0 - ignore the return value and just go out to
+		 * call dumpit again from outside to preserve the behavior
+		 */
+		goto out;
 	}
 
 out:
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 86fa0f3b2ca..ef542fbca9f 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -155,7 +155,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
 	if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown))
 		goto out_nlmsg_trim;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_nlmsg_trim:
 	nlmsg_cancel(skb, nlh);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 380784378df..4ed9039bd5f 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1721,7 +1721,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		break;
 	}
  finish:
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -2404,7 +2405,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 			goto nla_put_failure;
 	}
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -3825,7 +3827,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 		    sinfo->assoc_req_ies))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -4555,7 +4558,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq,
 
 	nla_nest_end(msg, pinfoattr);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -5507,7 +5511,8 @@ static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb,
 	    nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -6577,7 +6582,8 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 
 	nla_nest_end(msg, bss);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  fail_unlock_rcu:
 	rcu_read_unlock();
@@ -6686,7 +6692,8 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 
 	nla_nest_end(msg, infoattr);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -11025,7 +11032,8 @@ static int nl80211_send_scan_msg(struct sk_buff *msg,
 	/* ignore errors and send incomplete event anyway */
 	nl80211_add_scan_req(msg, rdev);
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
@@ -11048,7 +11056,8 @@ nl80211_send_sched_scan_msg(struct sk_buff *msg,
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex))
 		goto nla_put_failure;
 
-	return genlmsg_end(msg, hdr);
+	genlmsg_end(msg, hdr);
+	return 0;
 
  nla_put_failure:
 	genlmsg_cancel(msg, hdr);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 8128594ab37..7de2ed9ec46 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1019,7 +1019,8 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net,
 		return err;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1121,7 +1122,8 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net,
 		return err;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1842,7 +1844,8 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct
 	if (err)
 		goto out_cancel;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_cancel:
 	nlmsg_cancel(skb, nlh);
@@ -2282,7 +2285,8 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m,
 			goto out_cancel;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 
 out_cancel:
 	nlmsg_cancel(skb, nlh);
@@ -2490,7 +2494,8 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct
 	if (err)
 		return err;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
@@ -2712,7 +2717,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
 		return err;
 	}
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
@@ -2827,7 +2833,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
 	}
 	upe->hard = !!hard;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c)
@@ -2986,7 +2993,8 @@ static int build_report(struct sk_buff *skb, u8 proto,
 			return err;
 		}
 	}
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_send_report(struct net *net, u8 proto,
@@ -3031,7 +3039,8 @@ static int build_mapping(struct sk_buff *skb, struct xfrm_state *x,
 	um->old_sport = x->encap->encap_sport;
 	um->reqid = x->props.reqid;
 
-	return nlmsg_end(skb, nlh);
+	nlmsg_end(skb, nlh);
+	return 0;
 }
 
 static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
-- 
cgit v1.2.3-70-g09d2


From 88340160f3ad22401b00f4efcee44f7ec4769b19 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 16 Jan 2015 10:11:00 -0800
Subject: ip_tunnel: Create percpu gro_cell

In the ipip tunnel, the skb->queue_mapping is lost in ipip_rcv().
All skb will be queued to the same cell->napi_skbs.  The
gro_cell_poll is pinned to one core under load.  In production traffic,
we also see severe rx_dropped in the tunl iface and it is probably due to
this limit: skb_queue_len(&cell->napi_skbs) > netdev_max_backlog.

This patch is trying to alloc_percpu(struct gro_cell) and schedule
gro_cell_poll to process the skb in the same core.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gro_cells.h | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/net/gro_cells.h b/include/net/gro_cells.h
index 734d9b5f577..0f712c0bc0b 100644
--- a/include/net/gro_cells.h
+++ b/include/net/gro_cells.h
@@ -8,25 +8,23 @@
 struct gro_cell {
 	struct sk_buff_head	napi_skbs;
 	struct napi_struct	napi;
-} ____cacheline_aligned_in_smp;
+};
 
 struct gro_cells {
-	unsigned int		gro_cells_mask;
-	struct gro_cell		*cells;
+	struct gro_cell __percpu	*cells;
 };
 
 static inline void gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb)
 {
-	struct gro_cell *cell = gcells->cells;
+	struct gro_cell *cell;
 	struct net_device *dev = skb->dev;
 
-	if (!cell || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) {
+	if (!gcells->cells || skb_cloned(skb) || !(dev->features & NETIF_F_GRO)) {
 		netif_rx(skb);
 		return;
 	}
 
-	if (skb_rx_queue_recorded(skb))
-		cell += skb_get_rx_queue(skb) & gcells->gro_cells_mask;
+	cell = this_cpu_ptr(gcells->cells);
 
 	if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) {
 		atomic_long_inc(&dev->rx_dropped);
@@ -72,15 +70,12 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de
 {
 	int i;
 
-	gcells->gro_cells_mask = roundup_pow_of_two(netif_get_num_default_rss_queues()) - 1;
-	gcells->cells = kcalloc(gcells->gro_cells_mask + 1,
-				sizeof(struct gro_cell),
-				GFP_KERNEL);
+	gcells->cells = alloc_percpu(struct gro_cell);
 	if (!gcells->cells)
 		return -ENOMEM;
 
-	for (i = 0; i <= gcells->gro_cells_mask; i++) {
-		struct gro_cell *cell = gcells->cells + i;
+	for_each_possible_cpu(i) {
+		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
 		skb_queue_head_init(&cell->napi_skbs);
 		netif_napi_add(dev, &cell->napi, gro_cell_poll, 64);
@@ -91,16 +86,16 @@ static inline int gro_cells_init(struct gro_cells *gcells, struct net_device *de
 
 static inline void gro_cells_destroy(struct gro_cells *gcells)
 {
-	struct gro_cell *cell = gcells->cells;
 	int i;
 
-	if (!cell)
+	if (!gcells->cells)
 		return;
-	for (i = 0; i <= gcells->gro_cells_mask; i++,cell++) {
+	for_each_possible_cpu(i) {
+		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 		netif_napi_del(&cell->napi);
 		skb_queue_purge(&cell->napi_skbs);
 	}
-	kfree(gcells->cells);
+	free_percpu(gcells->cells);
 	gcells->cells = NULL;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 27c00132852b77b12e625cd6a0ccf43d6bf5795f Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Sun, 18 Jan 2015 10:25:56 +0100
Subject: switchdev: fix typo in inline function definition

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 201120e18e4..205e63698da 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -69,7 +69,7 @@ static inline int unregister_netdev_switch_notifier(struct notifier_block *nb)
 }
 
 static inline int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
-					       struct netdev_switch_notifier_info *info);
+					       struct netdev_switch_notifier_info *info)
 {
 	return NOTIFY_DONE;
 }
-- 
cgit v1.2.3-70-g09d2


From f8c58c1136349fdfa9b605c501f2f911622d3a9a Mon Sep 17 00:00:00 2001
From: Doug Anderson <dianders@chromium.org>
Date: Tue, 2 Dec 2014 15:42:47 -0800
Subject: mmc: dw_mmc: Protect read-modify-write of INTMASK with a lock

We're running into cases where our enabling of the SDIO interrupt in
dw_mmc doesn't actually take effect.  Specifically, adding patch like
this:

 +++ b/drivers/mmc/host/dw_mmc.c
 @@ -1076,6 +1076,9 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb)

      mci_writel(host, INTMASK,
           (int_mask | SDMMC_INT_SDIO(slot->id)));
 +    int_mask = mci_readl(host, INTMASK);
 +    if (!(int_mask & SDMMC_INT_SDIO(slot->id)))
 +      dev_err(&mmc->class_dev, "failed to enable sdio irq\n");
    } else {

...actually triggers the error message.  That's because the
dw_mci_enable_sdio_irq() unsafely does a read-modify-write of the
INTMASK register.

We can't just use the standard host->lock since that lock is not irq
safe and mmc_signal_sdio_irq() (called from interrupt context) calls
dw_mci_enable_sdio_irq().  Add a new irq-safe lock to protect INTMASK.

An alternate solution to this is to punt mmc_signal_sdio_irq() to the
tasklet and then protect INTMASK modifications by the standard host
lock.  This seemed like a bit more of a high-latency change.

Reported-by: Bing Zhao <bzhao@marvell.com>
Signed-off-by: Doug Anderson <dianders@chromium.org>
Reviewed-by: James Hogan <james.hogan@imgtec.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/dw_mmc.c  | 13 +++++++++++++
 include/linux/mmc/dw_mmc.h |  6 ++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index ae10a021765..64ea0427491 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -759,6 +759,7 @@ disable:
 
 static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 {
+	unsigned long irqflags;
 	int sg_len;
 	u32 temp;
 
@@ -795,9 +796,11 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 	mci_writel(host, CTRL, temp);
 
 	/* Disable RX/TX IRQs, let DMA handle it */
+	spin_lock_irqsave(&host->irq_lock, irqflags);
 	temp = mci_readl(host, INTMASK);
 	temp  &= ~(SDMMC_INT_RXDR | SDMMC_INT_TXDR);
 	mci_writel(host, INTMASK, temp);
+	spin_unlock_irqrestore(&host->irq_lock, irqflags);
 
 	host->dma_ops->start(host, sg_len);
 
@@ -806,6 +809,7 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 
 static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 {
+	unsigned long irqflags;
 	u32 temp;
 
 	data->error = -EINPROGRESS;
@@ -834,9 +838,12 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 		host->part_buf_count = 0;
 
 		mci_writel(host, RINTSTS, SDMMC_INT_TXDR | SDMMC_INT_RXDR);
+
+		spin_lock_irqsave(&host->irq_lock, irqflags);
 		temp = mci_readl(host, INTMASK);
 		temp |= SDMMC_INT_TXDR | SDMMC_INT_RXDR;
 		mci_writel(host, INTMASK, temp);
+		spin_unlock_irqrestore(&host->irq_lock, irqflags);
 
 		temp = mci_readl(host, CTRL);
 		temp &= ~SDMMC_CTRL_DMA_ENABLE;
@@ -1284,8 +1291,11 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb)
 {
 	struct dw_mci_slot *slot = mmc_priv(mmc);
 	struct dw_mci *host = slot->host;
+	unsigned long irqflags;
 	u32 int_mask;
 
+	spin_lock_irqsave(&host->irq_lock, irqflags);
+
 	/* Enable/disable Slot Specific SDIO interrupt */
 	int_mask = mci_readl(host, INTMASK);
 	if (enb)
@@ -1293,6 +1303,8 @@ static void dw_mci_enable_sdio_irq(struct mmc_host *mmc, int enb)
 	else
 		int_mask &= ~SDMMC_INT_SDIO(slot->sdio_id);
 	mci_writel(host, INTMASK, int_mask);
+
+	spin_unlock_irqrestore(&host->irq_lock, irqflags);
 }
 
 static int dw_mci_execute_tuning(struct mmc_host *mmc, u32 opcode)
@@ -2661,6 +2673,7 @@ int dw_mci_probe(struct dw_mci *host)
 	host->quirks = host->pdata->quirks;
 
 	spin_lock_init(&host->lock);
+	spin_lock_init(&host->irq_lock);
 	INIT_LIST_HEAD(&host->queue);
 
 	/*
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 42b724e8d50..471fb3116db 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -106,6 +106,11 @@ struct mmc_data;
  * @cur_slot, @mrq and @state. These must always be updated
  * at the same time while holding @lock.
  *
+ * @irq_lock is an irq-safe spinlock protecting the INTMASK register
+ * to allow the interrupt handler to modify it directly.  Held for only long
+ * enough to read-modify-write INTMASK and no other locks are grabbed when
+ * holding this one.
+ *
  * The @mrq field of struct dw_mci_slot is also protected by @lock,
  * and must always be written at the same time as the slot is added to
  * @queue.
@@ -125,6 +130,7 @@ struct mmc_data;
  */
 struct dw_mci {
 	spinlock_t		lock;
+	spinlock_t		irq_lock;
 	void __iomem		*regs;
 
 	struct scatterlist	*sg;
-- 
cgit v1.2.3-70-g09d2


From 61bd8a04b379e4fefbc0b0d06941d3f91071bb8c Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Fri, 12 Dec 2014 08:43:08 +1100
Subject: mmc: omap_hsmmc: remove prepare/complete system suspend support.

The only function of these 'prepare' and 'complete' is to
disable the 'card detect' irq during suspend.

The commit which added this,
commit a48ce884d5819d5df2cf1139ab3c43f8e9e419b3
    mmc: omap_hsmmc: Introduce omap_hsmmc_prepare/complete

justified it by the need to avoid the registration of new devices
during suspend.
However mmc_pm_notify will set ->rescan_disable in the 'prepare'
stage and clear it in the 'complete' stage, so no card detection
will actually happen.
Also the interrupt will be disabled before final suspend as part
of common suspend processing.

So this disabling of the interrupt is unnecessary, and interferes
with a transition to using common code for card-detect management.

Cc: Felipe Balbi <balbi@ti.com>
Cc: Venkatraman S <svenkatr@ti.com>
Cc: Chris Ball <cjb@laptop.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/omap_hsmmc.c          | 50 ----------------------------------
 include/linux/platform_data/mmc-omap.h |  4 ---
 2 files changed, 54 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 7c71dcdcba8..537cba8f1de 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -275,31 +275,6 @@ static int omap_hsmmc_get_cover_state(struct device *dev)
 	return !gpio_get_value_cansleep(mmc->switch_pin);
 }
 
-#ifdef CONFIG_PM
-
-static int omap_hsmmc_suspend_cdirq(struct device *dev)
-{
-	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-
-	disable_irq(host->card_detect_irq);
-	return 0;
-}
-
-static int omap_hsmmc_resume_cdirq(struct device *dev)
-{
-	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-
-	enable_irq(host->card_detect_irq);
-	return 0;
-}
-
-#else
-
-#define omap_hsmmc_suspend_cdirq	NULL
-#define omap_hsmmc_resume_cdirq		NULL
-
-#endif
-
 #ifdef CONFIG_REGULATOR
 
 static int omap_hsmmc_set_power(struct device *dev, int power_on, int vdd)
@@ -2234,8 +2209,6 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 				"Unable to grab MMC CD IRQ\n");
 			goto err_irq_cd;
 		}
-		host->suspend = omap_hsmmc_suspend_cdirq;
-		host->resume = omap_hsmmc_resume_cdirq;
 	}
 
 	omap_hsmmc_disable_irq(host);
@@ -2322,25 +2295,6 @@ static int omap_hsmmc_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM
-static int omap_hsmmc_prepare(struct device *dev)
-{
-	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-
-	if (host->suspend)
-		return host->suspend(dev);
-
-	return 0;
-}
-
-static void omap_hsmmc_complete(struct device *dev)
-{
-	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
-
-	if (host->resume)
-		host->resume(dev);
-
-}
-
 static int omap_hsmmc_suspend(struct device *dev)
 {
 	struct omap_hsmmc_host *host = dev_get_drvdata(dev);
@@ -2398,8 +2352,6 @@ static int omap_hsmmc_resume(struct device *dev)
 }
 
 #else
-#define omap_hsmmc_prepare	NULL
-#define omap_hsmmc_complete	NULL
 #define omap_hsmmc_suspend	NULL
 #define omap_hsmmc_resume	NULL
 #endif
@@ -2484,8 +2436,6 @@ static int omap_hsmmc_runtime_resume(struct device *dev)
 static struct dev_pm_ops omap_hsmmc_dev_pm_ops = {
 	.suspend	= omap_hsmmc_suspend,
 	.resume		= omap_hsmmc_resume,
-	.prepare	= omap_hsmmc_prepare,
-	.complete	= omap_hsmmc_complete,
 	.runtime_suspend = omap_hsmmc_runtime_suspend,
 	.runtime_resume = omap_hsmmc_runtime_resume,
 };
diff --git a/include/linux/platform_data/mmc-omap.h b/include/linux/platform_data/mmc-omap.h
index 5c188f4e9be..92946929140 100644
--- a/include/linux/platform_data/mmc-omap.h
+++ b/include/linux/platform_data/mmc-omap.h
@@ -31,10 +31,6 @@ struct omap_mmc_platform_data {
 	void (*cleanup)(struct device *dev);
 	void (*shutdown)(struct device *dev);
 
-	/* To handle board related suspend/resume functionality for MMC */
-	int (*suspend)(struct device *dev, int slot);
-	int (*resume)(struct device *dev, int slot);
-
 	/* Return context loss count due to PM states changing */
 	int (*get_context_loss_count)(struct device *dev);
 
-- 
cgit v1.2.3-70-g09d2


From eddbc3abc5bf11bdfc92ef84fd97ec4d379b7278 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 18 Dec 2014 15:44:32 +0100
Subject: mmc: slot-gpio: Remove option to explicitly free requested CD/WP
 GPIOs

The slot-gpio uses the devm*_ managed functions. Still it provide APIs
to explicitly free requested CD/WP GPIOs, but these API isn't being
used.

Therefore let's simplify slot-gpio by removing these unused APIs. If it
later turns out we need some of them, we can always consider to restore
the code.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/slot-gpio.c  | 92 ++-----------------------------------------
 include/linux/mmc/slot-gpio.h |  3 --
 2 files changed, 4 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 69bbf2adb32..a428f10747d 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -103,11 +103,7 @@ EXPORT_SYMBOL(mmc_gpio_get_cd);
  * @gpio: gpio number requested
  *
  * As devm_* managed functions are used in mmc_gpio_request_ro(), client
- * drivers do not need to explicitly call mmc_gpio_free_ro() for freeing up,
- * if the requesting and freeing are only needed at probing and unbinding time
- * for once.  However, if client drivers do something special like runtime
- * switching for write-protection, they are responsible for calling
- * mmc_gpio_request_ro() and mmc_gpio_free_ro() as a pair on their own.
+ * drivers do not need to worry about freeing up memory.
  *
  * Returns zero on success, else an error.
  */
@@ -178,11 +174,7 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd_irq);
  * @debounce: debounce time in microseconds
  *
  * As devm_* managed functions are used in mmc_gpio_request_cd(), client
- * drivers do not need to explicitly call mmc_gpio_free_cd() for freeing up,
- * if the requesting and freeing are only needed at probing and unbinding time
- * for once.  However, if client drivers do something special like runtime
- * switching for card-detection, they are responsible for calling
- * mmc_gpio_request_cd() and mmc_gpio_free_cd() as a pair on their own.
+ * drivers do not need to worry about freeing up memory.
  *
  * If GPIO debouncing is desired, set the debounce parameter to a non-zero
  * value. The caller is responsible for ensuring that the GPIO driver associated
@@ -225,55 +217,6 @@ int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio,
 }
 EXPORT_SYMBOL(mmc_gpio_request_cd);
 
-/**
- * mmc_gpio_free_ro - free the write-protection gpio
- * @host: mmc host
- *
- * It's provided only for cases that client drivers need to manually free
- * up the write-protection gpio requested by mmc_gpio_request_ro().
- */
-void mmc_gpio_free_ro(struct mmc_host *host)
-{
-	struct mmc_gpio *ctx = host->slot.handler_priv;
-	int gpio;
-
-	if (!ctx || !ctx->ro_gpio)
-		return;
-
-	gpio = desc_to_gpio(ctx->ro_gpio);
-	ctx->ro_gpio = NULL;
-
-	devm_gpio_free(&host->class_dev, gpio);
-}
-EXPORT_SYMBOL(mmc_gpio_free_ro);
-
-/**
- * mmc_gpio_free_cd - free the card-detection gpio
- * @host: mmc host
- *
- * It's provided only for cases that client drivers need to manually free
- * up the card-detection gpio requested by mmc_gpio_request_cd().
- */
-void mmc_gpio_free_cd(struct mmc_host *host)
-{
-	struct mmc_gpio *ctx = host->slot.handler_priv;
-	int gpio;
-
-	if (!ctx || !ctx->cd_gpio)
-		return;
-
-	if (host->slot.cd_irq >= 0) {
-		devm_free_irq(&host->class_dev, host->slot.cd_irq, host);
-		host->slot.cd_irq = -EINVAL;
-	}
-
-	gpio = desc_to_gpio(ctx->cd_gpio);
-	ctx->cd_gpio = NULL;
-
-	devm_gpio_free(&host->class_dev, gpio);
-}
-EXPORT_SYMBOL(mmc_gpio_free_cd);
-
 /**
  * mmc_gpiod_request_cd - request a gpio descriptor for card-detection
  * @host: mmc host
@@ -285,8 +228,7 @@ EXPORT_SYMBOL(mmc_gpio_free_cd);
  * to NULL to ignore
  *
  * Use this function in place of mmc_gpio_request_cd() to use the GPIO
- * descriptor API.  Note that it is paired with mmc_gpiod_free_cd() not
- * mmc_gpio_free_cd().  Note also that it must be called prior to mmc_add_host()
+ * descriptor API.  Note that it must be called prior to mmc_add_host()
  * otherwise the caller must also call mmc_gpiod_request_cd_irq().
  *
  * Returns zero on success, else an error.
@@ -339,8 +281,7 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd);
  * set to NULL to ignore
  *
  * Use this function in place of mmc_gpio_request_ro() to use the GPIO
- * descriptor API.  Note that it is paired with mmc_gpiod_free_ro() not
- * mmc_gpio_free_ro().
+ * descriptor API.
  *
  * Returns zero on success, else an error.
  */
@@ -380,28 +321,3 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 	return 0;
 }
 EXPORT_SYMBOL(mmc_gpiod_request_ro);
-
-/**
- * mmc_gpiod_free_cd - free the card-detection gpio descriptor
- * @host: mmc host
- *
- * It's provided only for cases that client drivers need to manually free
- * up the card-detection gpio requested by mmc_gpiod_request_cd().
- */
-void mmc_gpiod_free_cd(struct mmc_host *host)
-{
-	struct mmc_gpio *ctx = host->slot.handler_priv;
-
-	if (!ctx || !ctx->cd_gpio)
-		return;
-
-	if (host->slot.cd_irq >= 0) {
-		devm_free_irq(&host->class_dev, host->slot.cd_irq, host);
-		host->slot.cd_irq = -EINVAL;
-	}
-
-	devm_gpiod_put(host->parent, ctx->cd_gpio);
-
-	ctx->cd_gpio = NULL;
-}
-EXPORT_SYMBOL(mmc_gpiod_free_cd);
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index e56fa24c932..4a36d695463 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -15,12 +15,10 @@ struct mmc_host;
 
 int mmc_gpio_get_ro(struct mmc_host *host);
 int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio);
-void mmc_gpio_free_ro(struct mmc_host *host);
 
 int mmc_gpio_get_cd(struct mmc_host *host);
 int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio,
 			unsigned int debounce);
-void mmc_gpio_free_cd(struct mmc_host *host);
 
 int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
@@ -28,7 +26,6 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
 			 unsigned int debounce, bool *gpio_invert);
-void mmc_gpiod_free_cd(struct mmc_host *host);
 void mmc_gpiod_request_cd_irq(struct mmc_host *host);
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From df8aca162e5ff2b20c7a4de3e64e5b96ff838ab0 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 18 Dec 2014 15:44:36 +0100
Subject: mmc: slot-gpio: Rework how to handle allocation of slot-gpio data

By moving the allocation of the slot-gpio data into mmc_alloc_host(),
we can remove the slot-gpio internal calls to mmc_gpio_alloc().

This means mmc_gpio_alloc() has now only one caller left, which
consequence allow us to simplify and remove some of the slot-gpio code.

Additionally, this makes the slot-gpio mutex redundant, so let's remove
it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/host.c      | 20 +++++++-------
 drivers/mmc/core/slot-gpio.c | 62 ++++++++++----------------------------------
 include/linux/mmc/host.h     |  2 --
 3 files changed, 23 insertions(+), 61 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index fcb7f06373c..07636449b4d 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -29,6 +29,7 @@
 
 #include "core.h"
 #include "host.h"
+#include "slot-gpio.h"
 
 #define cls_dev_to_mmc_host(d)	container_of(d, struct mmc_host, class_dev)
 
@@ -38,7 +39,6 @@ static DEFINE_SPINLOCK(mmc_host_lock);
 static void mmc_host_classdev_release(struct device *dev)
 {
 	struct mmc_host *host = cls_dev_to_mmc_host(dev);
-	mutex_destroy(&host->slot.lock);
 	spin_lock(&mmc_host_lock);
 	idr_remove(&mmc_host_idr, host->index);
 	spin_unlock(&mmc_host_lock);
@@ -478,8 +478,10 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 		host->index = err;
 	spin_unlock(&mmc_host_lock);
 	idr_preload_end();
-	if (err < 0)
-		goto free;
+	if (err < 0) {
+		kfree(host);
+		return NULL;
+	}
 
 	dev_set_name(&host->class_dev, "mmc%d", host->index);
 
@@ -488,10 +490,12 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 	host->class_dev.class = &mmc_host_class;
 	device_initialize(&host->class_dev);
 
-	mmc_host_clk_init(host);
+	if (mmc_gpio_alloc(host)) {
+		put_device(&host->class_dev);
+		return NULL;
+	}
 
-	mutex_init(&host->slot.lock);
-	host->slot.cd_irq = -EINVAL;
+	mmc_host_clk_init(host);
 
 	spin_lock_init(&host->lock);
 	init_waitqueue_head(&host->wq);
@@ -512,10 +516,6 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 	host->max_blk_count = PAGE_CACHE_SIZE / 512;
 
 	return host;
-
-free:
-	kfree(host);
-	return NULL;
 }
 
 EXPORT_SYMBOL(mmc_alloc_host);
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index ec918c27e77..1a3edbd4771 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -43,29 +43,17 @@ static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id)
 int mmc_gpio_alloc(struct mmc_host *host)
 {
 	size_t len = strlen(dev_name(host->parent)) + 4;
-	struct mmc_gpio *ctx;
-
-	mutex_lock(&host->slot.lock);
-
-	ctx = host->slot.handler_priv;
-	if (!ctx) {
-		/*
-		 * devm_kzalloc() can be called after device_initialize(), even
-		 * before device_add(), i.e., between mmc_alloc_host() and
-		 * mmc_add_host()
-		 */
-		ctx = devm_kzalloc(host->parent, sizeof(*ctx) + 2 * len,
-				   GFP_KERNEL);
-		if (ctx) {
-			ctx->ro_label = ctx->cd_label + len;
-			snprintf(ctx->cd_label, len, "%s cd", dev_name(host->parent));
-			snprintf(ctx->ro_label, len, "%s ro", dev_name(host->parent));
-			host->slot.handler_priv = ctx;
-		}
+	struct mmc_gpio *ctx = devm_kzalloc(host->parent,
+				sizeof(*ctx) + 2 * len,	GFP_KERNEL);
+
+	if (ctx) {
+		ctx->ro_label = ctx->cd_label + len;
+		snprintf(ctx->cd_label, len, "%s cd", dev_name(host->parent));
+		snprintf(ctx->ro_label, len, "%s ro", dev_name(host->parent));
+		host->slot.handler_priv = ctx;
+		host->slot.cd_irq = -EINVAL;
 	}
 
-	mutex_unlock(&host->slot.lock);
-
 	return ctx ? 0 : -ENOMEM;
 }
 
@@ -111,18 +99,12 @@ EXPORT_SYMBOL(mmc_gpio_get_cd);
  */
 int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio)
 {
-	struct mmc_gpio *ctx;
+	struct mmc_gpio *ctx = host->slot.handler_priv;
 	int ret;
 
 	if (!gpio_is_valid(gpio))
 		return -EINVAL;
 
-	ret = mmc_gpio_alloc(host);
-	if (ret < 0)
-		return ret;
-
-	ctx = host->slot.handler_priv;
-
 	ret = devm_gpio_request_one(host->parent, gpio, GPIOF_DIR_IN,
 				    ctx->ro_label);
 	if (ret < 0)
@@ -187,15 +169,9 @@ EXPORT_SYMBOL(mmc_gpiod_request_cd_irq);
 int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio,
 			unsigned int debounce)
 {
-	struct mmc_gpio *ctx;
+	struct mmc_gpio *ctx = host->slot.handler_priv;
 	int ret;
 
-	ret = mmc_gpio_alloc(host);
-	if (ret < 0)
-		return ret;
-
-	ctx = host->slot.handler_priv;
-
 	ret = devm_gpio_request_one(host->parent, gpio, GPIOF_DIR_IN,
 				    ctx->cd_label);
 	if (ret < 0)
@@ -239,16 +215,10 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
 			 unsigned int debounce, bool *gpio_invert)
 {
-	struct mmc_gpio *ctx;
+	struct mmc_gpio *ctx = host->slot.handler_priv;
 	struct gpio_desc *desc;
 	int ret;
 
-	ret = mmc_gpio_alloc(host);
-	if (ret < 0)
-		return ret;
-
-	ctx = host->slot.handler_priv;
-
 	if (!con_id)
 		con_id = ctx->cd_label;
 
@@ -291,16 +261,10 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
 			 unsigned int debounce, bool *gpio_invert)
 {
-	struct mmc_gpio *ctx;
+	struct mmc_gpio *ctx = host->slot.handler_priv;
 	struct gpio_desc *desc;
 	int ret;
 
-	ret = mmc_gpio_alloc(host);
-	if (ret < 0)
-		return ret;
-
-	ctx = host->slot.handler_priv;
-
 	if (!con_id)
 		con_id = ctx->ro_label;
 
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 9f322706f7c..b6bf718c349 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -166,7 +166,6 @@ struct mmc_async_req {
  * struct mmc_slot - MMC slot functions
  *
  * @cd_irq:		MMC/SD-card slot hotplug detection IRQ or -EINVAL
- * @lock:		protect the @handler_priv pointer
  * @handler_priv:	MMC/SD-card slot context
  *
  * Some MMC/SD host controllers implement slot-functions like card and
@@ -176,7 +175,6 @@ struct mmc_async_req {
  */
 struct mmc_slot {
 	int cd_irq;
-	struct mutex lock;
 	void *handler_priv;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 04cdbbfa73ebac57a30ec2ebebfd7e9342bbdc44 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 1 Dec 2014 16:53:34 +0100
Subject: mmc: core: Make tuning block patterns static

Since previous patches removed the need for the tuning block patterns
to be exported, let's move them close to the mmc_send_tuning() API.

Those are now intended to be used only by the mmc core.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: Jaehoon Chung <jh80.chung@samsung.com>
---
 drivers/mmc/core/mmc.c     | 32 --------------------------------
 drivers/mmc/core/mmc_ops.c | 30 ++++++++++++++++++++++++++++++
 include/linux/mmc/mmc.h    |  5 -----
 3 files changed, 30 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index d854bff037a..0b8ec87fc51 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1155,38 +1155,6 @@ bus_speed:
 	return err;
 }
 
-const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE] = {
-	0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc,
-	0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef,
-	0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb,
-	0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef,
-	0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c,
-	0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee,
-	0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff,
-	0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde,
-};
-EXPORT_SYMBOL(tuning_blk_pattern_4bit);
-
-const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE] = {
-	0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00,
-	0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc,
-	0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff,
-	0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff,
-	0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd,
-	0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb,
-	0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff,
-	0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff,
-	0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00,
-	0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc,
-	0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff,
-	0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee,
-	0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd,
-	0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff,
-	0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff,
-	0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee,
-};
-EXPORT_SYMBOL(tuning_blk_pattern_8bit);
-
 /*
  * Execute tuning sequence to seek the proper bus operating
  * conditions for HS200 and HS400, which sends CMD21 to the device.
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 3b044c5b029..0ea042dc744 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -23,6 +23,36 @@
 
 #define MMC_OPS_TIMEOUT_MS	(10 * 60 * 1000) /* 10 minute timeout */
 
+static const u8 tuning_blk_pattern_4bit[] = {
+	0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc,
+	0xc3, 0x3c, 0xcc, 0xff, 0xfe, 0xff, 0xfe, 0xef,
+	0xff, 0xdf, 0xff, 0xdd, 0xff, 0xfb, 0xff, 0xfb,
+	0xbf, 0xff, 0x7f, 0xff, 0x77, 0xf7, 0xbd, 0xef,
+	0xff, 0xf0, 0xff, 0xf0, 0x0f, 0xfc, 0xcc, 0x3c,
+	0xcc, 0x33, 0xcc, 0xcf, 0xff, 0xef, 0xff, 0xee,
+	0xff, 0xfd, 0xff, 0xfd, 0xdf, 0xff, 0xbf, 0xff,
+	0xbb, 0xff, 0xf7, 0xff, 0xf7, 0x7f, 0x7b, 0xde,
+};
+
+static const u8 tuning_blk_pattern_8bit[] = {
+	0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00, 0x00,
+	0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc, 0xcc,
+	0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff, 0xff,
+	0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee, 0xff,
+	0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd, 0xdd,
+	0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff, 0xbb,
+	0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff, 0xff,
+	0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee, 0xff,
+	0xff, 0xff, 0xff, 0x00, 0xff, 0xff, 0xff, 0x00,
+	0x00, 0xff, 0xff, 0xcc, 0xcc, 0xcc, 0x33, 0xcc,
+	0xcc, 0xcc, 0x33, 0x33, 0xcc, 0xcc, 0xcc, 0xff,
+	0xff, 0xff, 0xee, 0xff, 0xff, 0xff, 0xee, 0xee,
+	0xff, 0xff, 0xff, 0xdd, 0xff, 0xff, 0xff, 0xdd,
+	0xdd, 0xff, 0xff, 0xff, 0xbb, 0xff, 0xff, 0xff,
+	0xbb, 0xbb, 0xff, 0xff, 0xff, 0x77, 0xff, 0xff,
+	0xff, 0x77, 0x77, 0xff, 0x77, 0xbb, 0xdd, 0xee,
+};
+
 static inline int __mmc_send_status(struct mmc_card *card, u32 *status,
 				    bool ignore_crc)
 {
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 49ad7a94363..fb97b5cc91c 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -53,11 +53,6 @@
 #define MMC_SEND_TUNING_BLOCK    19   /* adtc                    R1  */
 #define MMC_SEND_TUNING_BLOCK_HS200	21	/* adtc R1  */
 
-#define MMC_TUNING_BLK_PATTERN_4BIT_SIZE	 64
-#define MMC_TUNING_BLK_PATTERN_8BIT_SIZE	128
-extern const u8 tuning_blk_pattern_4bit[MMC_TUNING_BLK_PATTERN_4BIT_SIZE];
-extern const u8 tuning_blk_pattern_8bit[MMC_TUNING_BLK_PATTERN_8BIT_SIZE];
-
   /* class 3 */
 #define MMC_WRITE_DAT_UNTIL_STOP 20   /* adtc [31:0] data addr   R1  */
 
-- 
cgit v1.2.3-70-g09d2


From 348487cb28e66b032bae1b38424d81bf5b444408 Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@freescale.com>
Date: Tue, 9 Dec 2014 17:04:05 +0800
Subject: mmc: sdhci: use pipeline mmc requests to improve performance

This patch is based on the patches by Per Forlin, Tony Lin and Ryan QIAN.

This patch complete the API 'post_req' and 'pre_req' in sdhci host side,

Test Env:
1. i.MX6Q-SABREAUTO board, CPU @ 996MHz, use ADMA in uSDHC controller.
2. Test command:
		$ echo 1 > /proc/sys/vm/drop_caches
	write to sd card:
		$ dd if=/dev/zero of=/dev/mmcblk0 bs=1M count=2000 conv=fsync
	read the sd card:
		$ dd if=/dev/mmcblk0 of=/dev/null bs=1M count=2000

3. TOSHIBA 16GB SD3.0 card, running at 4 bit, SDR104 @ 198MHZ
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~76.7 MB/s |  ~23.3 MB/s |
	  |------------------------------------------------
	  |without this patch  | ~60.5 MB/s |  ~22.5 MB/s |
	  -------------------------------------------------

4. SanDisk 8GB SD3.0 card, running at 4 bit, DDR50 @ 50MHZ
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~40.5 MB/s |  ~15.6 MB/s |
	  |------------------------------------------------
	  |without this patch  | ~36.1 MB/s |  ~14.1 MB/s |
	  -------------------------------------------------

5. Kingston 8GB SD2.0 card, running at 4 bit, High-speed @ 50MHZ
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~22.7 MB/s |  ~8.2 MB/s  |
	  |------------------------------------------------
	  |without this patch  | ~21.3 MB/s |  ~8.0 MB/s  |
	  -------------------------------------------------

6. About eMMC, Sandisk 8GB eMMC on i.MX6DL-sabresd board, CPU @ 792MHZ,
   eMMC running at 8 bit, DDR52 @ 52MHZ.
	Performance with and without this patch:
      -------------------------------------------------
	  |                    | read speed | write speed |
	  |------------------------------------------------
	  | with this patch    | ~37.3 MB/s |  ~10.5 MB/s |
	  |------------------------------------------------
	  |without this patch  | ~33.4 MB/s |  ~10.5 MB/s |
	  -------------------------------------------------

Signed-off-by: Haibo Chen <haibo.chen@freescale.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 99 +++++++++++++++++++++++++++++++++++++++++------
 include/linux/mmc/sdhci.h |  6 +++
 2 files changed, 93 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 2558d705c92..1aab8a120d0 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -53,6 +53,9 @@ static void sdhci_finish_command(struct sdhci_host *);
 static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode);
 static void sdhci_tuning_timer(unsigned long data);
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable);
+static int sdhci_pre_dma_transfer(struct sdhci_host *host,
+					struct mmc_data *data,
+					struct sdhci_host_next *next);
 
 #ifdef CONFIG_PM
 static int sdhci_runtime_pm_get(struct sdhci_host *host);
@@ -505,9 +508,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		goto fail;
 	BUG_ON(host->align_addr & host->align_mask);
 
-	host->sg_count = dma_map_sg(mmc_dev(host->mmc),
-		data->sg, data->sg_len, direction);
-	if (host->sg_count == 0)
+	host->sg_count = sdhci_pre_dma_transfer(host, data, NULL);
+	if (host->sg_count < 0)
 		goto unmap_align;
 
 	desc = host->adma_table;
@@ -645,8 +647,9 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 		}
 	}
 
-	dma_unmap_sg(mmc_dev(host->mmc), data->sg,
-		data->sg_len, direction);
+	if (!data->host_cookie)
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg,
+			data->sg_len, direction);
 }
 
 static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
@@ -842,11 +845,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 		} else {
 			int sg_cnt;
 
-			sg_cnt = dma_map_sg(mmc_dev(host->mmc),
-					data->sg, data->sg_len,
-					(data->flags & MMC_DATA_READ) ?
-						DMA_FROM_DEVICE :
-						DMA_TO_DEVICE);
+			sg_cnt = sdhci_pre_dma_transfer(host, data, NULL);
 			if (sg_cnt == 0) {
 				/*
 				 * This only happens when someone fed
@@ -959,8 +958,10 @@ static void sdhci_finish_data(struct sdhci_host *host)
 		if (host->flags & SDHCI_USE_ADMA)
 			sdhci_adma_table_post(host, data);
 		else {
-			dma_unmap_sg(mmc_dev(host->mmc), data->sg,
-				data->sg_len, (data->flags & MMC_DATA_READ) ?
+			if (!data->host_cookie)
+				dma_unmap_sg(mmc_dev(host->mmc),
+					data->sg, data->sg_len,
+					(data->flags & MMC_DATA_READ) ?
 					DMA_FROM_DEVICE : DMA_TO_DEVICE);
 		}
 	}
@@ -2125,6 +2126,77 @@ static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable)
 	}
 }
 
+static void sdhci_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
+				int err)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (host->flags & SDHCI_REQ_USE_DMA) {
+		if (data->host_cookie)
+			dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
+					 data->flags & MMC_DATA_WRITE ?
+					 DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		mrq->data->host_cookie = 0;
+	}
+}
+
+static int sdhci_pre_dma_transfer(struct sdhci_host *host,
+				       struct mmc_data *data,
+				       struct sdhci_host_next *next)
+{
+	int sg_count;
+
+	if (!next && data->host_cookie &&
+	    data->host_cookie != host->next_data.cookie) {
+		pr_debug(DRIVER_NAME "[%s] invalid cookie: %d, next-cookie %d\n",
+			__func__, data->host_cookie, host->next_data.cookie);
+		data->host_cookie = 0;
+	}
+
+	/* Check if next job is already prepared */
+	if (next ||
+	    (!next && data->host_cookie != host->next_data.cookie)) {
+		sg_count = dma_map_sg(mmc_dev(host->mmc), data->sg,
+				     data->sg_len,
+				     data->flags & MMC_DATA_WRITE ?
+				     DMA_TO_DEVICE : DMA_FROM_DEVICE);
+
+	} else {
+		sg_count = host->next_data.sg_count;
+		host->next_data.sg_count = 0;
+	}
+
+
+	if (sg_count == 0)
+		return -EINVAL;
+
+	if (next) {
+		next->sg_count = sg_count;
+		data->host_cookie = ++next->cookie < 0 ? 1 : next->cookie;
+	} else
+		host->sg_count = sg_count;
+
+	return sg_count;
+}
+
+static void sdhci_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
+			       bool is_first_req)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	if (mrq->data->host_cookie) {
+		mrq->data->host_cookie = 0;
+		return;
+	}
+
+	if (host->flags & SDHCI_REQ_USE_DMA)
+		if (sdhci_pre_dma_transfer(host,
+					mrq->data,
+					&host->next_data) < 0)
+			mrq->data->host_cookie = 0;
+}
+
 static void sdhci_card_event(struct mmc_host *mmc)
 {
 	struct sdhci_host *host = mmc_priv(mmc);
@@ -2158,6 +2230,8 @@ static void sdhci_card_event(struct mmc_host *mmc)
 
 static const struct mmc_host_ops sdhci_ops = {
 	.request	= sdhci_request,
+	.post_req	= sdhci_post_req,
+	.pre_req	= sdhci_pre_req,
 	.set_ios	= sdhci_set_ios,
 	.get_cd		= sdhci_get_cd,
 	.get_ro		= sdhci_get_ro,
@@ -3015,6 +3089,7 @@ int sdhci_add_host(struct sdhci_host *host)
 		host->max_clk = host->ops->get_max_clock(host);
 	}
 
+	host->next_data.cookie = 1;
 	/*
 	 * In case of Host Controller v3.00, find out whether clock
 	 * multiplier is supported.
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index f767a0de611..cb8b94ff6a2 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -17,6 +17,11 @@
 #include <linux/io.h>
 #include <linux/mmc/host.h>
 
+struct sdhci_host_next {
+	unsigned int	sg_count;
+	s32		cookie;
+};
+
 struct sdhci_host {
 	/* Data set by hardware interface driver */
 	const char *hw_name;	/* Hardware bus name */
@@ -203,6 +208,7 @@ struct sdhci_host {
 #define SDHCI_TUNING_MODE_1	0
 	struct timer_list	tuning_timer;	/* Timer for tuning */
 
+	struct sdhci_host_next	next_data;
 	unsigned long private[0] ____cacheline_aligned;
 };
 #endif /* LINUX_MMC_SDHCI_H */
-- 
cgit v1.2.3-70-g09d2


From 83533ab28380f6957af39a7b322e639e42dbdaf1 Mon Sep 17 00:00:00 2001
From: Johan Rudholm <johan.rudholm@axis.com>
Date: Mon, 12 Jan 2015 15:38:04 +0100
Subject: mmc: core: always check status after reset

Always check if the card is alive after a successful reset. This allows
us to remove mmc_hw_reset_check(), leaving mmc_hw_reset() as the only
card reset interface.

Signed-off-by: Johan Rudholm <johanru@axis.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/card/mmc_test.c | 18 +++++++-----------
 drivers/mmc/core/core.c     | 24 +++++-------------------
 include/linux/mmc/core.h    |  1 -
 3 files changed, 12 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 0a7430f94d2..7dac4695163 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -2342,20 +2342,16 @@ static int mmc_test_hw_reset(struct mmc_test_card *test)
 	struct mmc_host *host = card->host;
 	int err;
 
-	err = mmc_hw_reset_check(host);
+	if (!mmc_card_mmc(card) || !mmc_can_reset(card))
+		return RESULT_UNSUP_CARD;
+
+	err = mmc_hw_reset(host);
 	if (!err)
 		return RESULT_OK;
+	else if (err == -EOPNOTSUPP)
+		return RESULT_UNSUP_HOST;
 
-	if (err == -ENOSYS)
-		return RESULT_FAIL;
-
-	if (err != -EOPNOTSUPP)
-		return err;
-
-	if (!mmc_can_reset(card))
-		return RESULT_UNSUP_CARD;
-
-	return RESULT_UNSUP_HOST;
+	return RESULT_FAIL;
 }
 
 static const struct mmc_test_case mmc_test_cases[] = {
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index d3bfbdfab05..72070f188cc 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2286,9 +2286,10 @@ int mmc_can_reset(struct mmc_card *card)
 }
 EXPORT_SYMBOL(mmc_can_reset);
 
-static int mmc_do_hw_reset(struct mmc_host *host, int check)
+int mmc_hw_reset(struct mmc_host *host)
 {
 	struct mmc_card *card = host->card;
+	u32 status;
 
 	if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->hw_reset)
 		return -EOPNOTSUPP;
@@ -2305,13 +2306,9 @@ static int mmc_do_hw_reset(struct mmc_host *host, int check)
 	host->ops->hw_reset(host);
 
 	/* If the reset has happened, then a status command will fail */
-	if (check) {
-		u32 status;
-
-		if (!mmc_send_status(card, &status)) {
-			mmc_host_clk_release(host);
-			return -ENOSYS;
-		}
+	if (!mmc_send_status(card, &status)) {
+		mmc_host_clk_release(host);
+		return -ENOSYS;
 	}
 
 	/* Set initial state and call mmc_set_ios */
@@ -2321,19 +2318,8 @@ static int mmc_do_hw_reset(struct mmc_host *host, int check)
 
 	return host->bus_ops->power_restore(host);
 }
-
-int mmc_hw_reset(struct mmc_host *host)
-{
-	return mmc_do_hw_reset(host, 0);
-}
 EXPORT_SYMBOL(mmc_hw_reset);
 
-int mmc_hw_reset_check(struct mmc_host *host)
-{
-	return mmc_do_hw_reset(host, 1);
-}
-EXPORT_SYMBOL(mmc_hw_reset_check);
-
 static int mmc_rescan_try_freq(struct mmc_host *host, unsigned freq)
 {
 	host->f_init = freq;
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index cb2b0400d28..160448f920a 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -182,7 +182,6 @@ extern int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen);
 extern int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount,
 			      bool is_rel_write);
 extern int mmc_hw_reset(struct mmc_host *host);
-extern int mmc_hw_reset_check(struct mmc_host *host);
 extern int mmc_can_reset(struct mmc_card *card);
 
 extern void mmc_set_data_timeout(struct mmc_data *, const struct mmc_card *);
-- 
cgit v1.2.3-70-g09d2


From c7ea834d81904b71505093f7ec50d036132cf628 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Tue, 13 Jan 2015 08:23:18 +1300
Subject: mmc: slot-gpio: Allow host driver to provide isr for card-detect
 interrupts

One of the reasons omap_hsmmc doesn't use the slot-gpio library
is that it has some non-standard functionality in the card-detect
interrupt service routine.

To make it possible for omap_hsmmc (and maybe others) to be converted
to use slot-gpio, add 'mmc_gpio_request_cd_isr' which provide an
alternate isr to be register by the slot-gpio code.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/slot-gpio.c  | 18 +++++++++++++++++-
 include/linux/mmc/slot-gpio.h |  2 ++
 2 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 1a3edbd4771..27117ba4707 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -25,6 +25,7 @@ struct mmc_gpio {
 	struct gpio_desc *cd_gpio;
 	bool override_ro_active_level;
 	bool override_cd_active_level;
+	irqreturn_t (*cd_gpio_isr)(int irq, void *dev_id);
 	char *ro_label;
 	char cd_label[0];
 };
@@ -136,8 +137,10 @@ void mmc_gpiod_request_cd_irq(struct mmc_host *host)
 		irq = -EINVAL;
 
 	if (irq >= 0) {
+		if (!ctx->cd_gpio_isr)
+			ctx->cd_gpio_isr = mmc_gpio_cd_irqt;
 		ret = devm_request_threaded_irq(host->parent, irq,
-			NULL, mmc_gpio_cd_irqt,
+			NULL, ctx->cd_gpio_isr,
 			IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 			ctx->cd_label, host);
 		if (ret < 0)
@@ -151,6 +154,19 @@ void mmc_gpiod_request_cd_irq(struct mmc_host *host)
 }
 EXPORT_SYMBOL(mmc_gpiod_request_cd_irq);
 
+/* Register an alternate interrupt service routine for
+ * the card-detect GPIO.
+ */
+void mmc_gpio_set_cd_isr(struct mmc_host *host,
+			 irqreturn_t (*isr)(int irq, void *dev_id))
+{
+	struct mmc_gpio *ctx = host->slot.handler_priv;
+
+	WARN_ON(ctx->cd_gpio_isr);
+	ctx->cd_gpio_isr = isr;
+}
+EXPORT_SYMBOL(mmc_gpio_set_cd_isr);
+
 /**
  * mmc_gpio_request_cd - request a gpio for card-detection
  * @host: mmc host
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index 4a36d695463..3945a8c9d3c 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -26,6 +26,8 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, bool override_active_level,
 			 unsigned int debounce, bool *gpio_invert);
+void mmc_gpio_set_cd_isr(struct mmc_host *host,
+			 irqreturn_t (*isr)(int irq, void *dev_id));
 void mmc_gpiod_request_cd_irq(struct mmc_host *host);
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From cdef511985374dd042a40bb32c1c346c2662c9dc Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Thu, 15 Jan 2015 15:21:19 +0100
Subject: KVM: fix sparse warning in include/trace/events/kvm.h

sparse complains about
include/trace/events/kvm.h:163:1: error: directive in argument list
include/trace/events/kvm.h:167:1: error: directive in argument list
include/trace/events/kvm.h:169:1: error: directive in argument list
and sparse is right. Preprocessing directives in an argument of a
macro are undefined behaviour as of C99 6.10.3p11.

Lets use an indirection to fix this.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/trace/events/kvm.h | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 6edf1f2028c..86b399c66c3 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -146,6 +146,14 @@ TRACE_EVENT(kvm_msi_set_irq,
 
 #if defined(CONFIG_HAVE_KVM_IRQFD)
 
+#ifdef kvm_irqchips
+#define kvm_ack_irq_string "irqchip %s pin %u"
+#define kvm_ack_irq_parm  __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin
+#else
+#define kvm_ack_irq_string "irqchip %d pin %u"
+#define kvm_ack_irq_parm  __entry->irqchip, __entry->pin
+#endif
+
 TRACE_EVENT(kvm_ack_irq,
 	TP_PROTO(unsigned int irqchip, unsigned int pin),
 	TP_ARGS(irqchip, pin),
@@ -160,13 +168,7 @@ TRACE_EVENT(kvm_ack_irq,
 		__entry->pin		= pin;
 	),
 
-#ifdef kvm_irqchips
-	TP_printk("irqchip %s pin %u",
-		  __print_symbolic(__entry->irqchip, kvm_irqchips),
-		 __entry->pin)
-#else
-	TP_printk("irqchip %d pin %u", __entry->irqchip, __entry->pin)
-#endif
+	TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm)
 );
 
 #endif /* defined(CONFIG_HAVE_KVM_IRQFD) */
-- 
cgit v1.2.3-70-g09d2


From 75e8d06d4308436055d1a78a2c02bf6328ba724d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 14 Jan 2015 15:33:57 +0100
Subject: netfilter: nf_tables: validate hooks in NAT expressions

The user can crash the kernel if it uses any of the existing NAT
expressions from the wrong hook, so add some code to validate this
when loading the rule.

This patch introduces nft_chain_validate_hooks() which is based on
an existing function in the bridge version of the reject expression.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        |  2 ++
 net/bridge/netfilter/nft_reject_bridge.c | 29 +++++------------------
 net/netfilter/nf_tables_api.c            | 18 ++++++++++++++
 net/netfilter/nft_masq.c                 | 26 ++++++++++++++-------
 net/netfilter/nft_nat.c                  | 40 ++++++++++++++++++++++++--------
 net/netfilter/nft_redir.c                | 25 +++++++++++++-------
 6 files changed, 90 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3ae969e3acf..9eaaa788458 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -530,6 +530,8 @@ enum nft_chain_type {
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
 				  enum nft_chain_type type);
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+                             unsigned int hook_flags);
 
 struct nft_stats {
 	u64			bytes;
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index b0330aecbf9..3244aead092 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -265,22 +265,12 @@ out:
 	data[NFT_REG_VERDICT].verdict = NF_DROP;
 }
 
-static int nft_reject_bridge_validate_hooks(const struct nft_chain *chain)
+static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
+				      const struct nft_expr *expr,
+				      const struct nft_data **data)
 {
-	struct nft_base_chain *basechain;
-
-	if (chain->flags & NFT_BASE_CHAIN) {
-		basechain = nft_base_chain(chain);
-
-		switch (basechain->ops[0].hooknum) {
-		case NF_BR_PRE_ROUTING:
-		case NF_BR_LOCAL_IN:
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-	}
-	return 0;
+	return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) |
+						    (1 << NF_BR_LOCAL_IN));
 }
 
 static int nft_reject_bridge_init(const struct nft_ctx *ctx,
@@ -290,7 +280,7 @@ static int nft_reject_bridge_init(const struct nft_ctx *ctx,
 	struct nft_reject *priv = nft_expr_priv(expr);
 	int icmp_code, err;
 
-	err = nft_reject_bridge_validate_hooks(ctx->chain);
+	err = nft_reject_bridge_validate(ctx, expr, NULL);
 	if (err < 0)
 		return err;
 
@@ -341,13 +331,6 @@ nla_put_failure:
 	return -1;
 }
 
-static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
-				      const struct nft_expr *expr,
-				      const struct nft_data **data)
-{
-	return nft_reject_bridge_validate_hooks(ctx->chain);
-}
-
 static struct nft_expr_type nft_reject_bridge_type;
 static const struct nft_expr_ops nft_reject_bridge_ops = {
 	.type		= &nft_reject_bridge_type,
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3b3ddb4fb9e..7e686948ddc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3753,6 +3753,24 @@ int nft_chain_validate_dependency(const struct nft_chain *chain,
 }
 EXPORT_SYMBOL_GPL(nft_chain_validate_dependency);
 
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+			     unsigned int hook_flags)
+{
+	struct nft_base_chain *basechain;
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		basechain = nft_base_chain(chain);
+
+		if ((1 << basechain->ops[0].hooknum) & hook_flags)
+			return 0;
+
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_chain_validate_hooks);
+
 /*
  * Loop detection - walk through the ruleset beginning at the destination chain
  * of a new jump until either the source chain is reached (loop) or all
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index d1ffd5eb3a9..9aea747b43e 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -21,6 +21,21 @@ const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
 };
 EXPORT_SYMBOL_GPL(nft_masq_policy);
 
+int nft_masq_validate(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+				        (1 << NF_INET_POST_ROUTING));
+}
+EXPORT_SYMBOL_GPL(nft_masq_validate);
+
 int nft_masq_init(const struct nft_ctx *ctx,
 		  const struct nft_expr *expr,
 		  const struct nlattr * const tb[])
@@ -28,8 +43,8 @@ int nft_masq_init(const struct nft_ctx *ctx,
 	struct nft_masq *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-	if (err < 0)
+	err = nft_masq_validate(ctx, expr, NULL);
+	if (err)
 		return err;
 
 	if (tb[NFTA_MASQ_FLAGS] == NULL)
@@ -60,12 +75,5 @@ nla_put_failure:
 }
 EXPORT_SYMBOL_GPL(nft_masq_dump);
 
-int nft_masq_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		      const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-EXPORT_SYMBOL_GPL(nft_masq_validate);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index aff54fb1c8a..a0837c6c928 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -88,17 +88,40 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
 	[NFTA_NAT_FLAGS]	 = { .type = NLA_U32 },
 };
 
-static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			const struct nlattr * const tb[])
+static int nft_nat_validate(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nft_data **data)
 {
 	struct nft_nat *priv = nft_expr_priv(expr);
-	u32 family;
 	int err;
 
 	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
 	if (err < 0)
 		return err;
 
+	switch (priv->type) {
+	case NFT_NAT_SNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_POST_ROUTING) |
+					       (1 << NF_INET_LOCAL_IN));
+		break;
+	case NFT_NAT_DNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_PRE_ROUTING) |
+					       (1 << NF_INET_LOCAL_OUT));
+		break;
+	}
+
+	return err;
+}
+
+static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_nat *priv = nft_expr_priv(expr);
+	u32 family;
+	int err;
+
 	if (tb[NFTA_NAT_TYPE] == NULL ||
 	    (tb[NFTA_NAT_REG_ADDR_MIN] == NULL &&
 	     tb[NFTA_NAT_REG_PROTO_MIN] == NULL))
@@ -115,6 +138,10 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		return -EINVAL;
 	}
 
+	err = nft_nat_validate(ctx, expr, NULL);
+	if (err < 0)
+		return err;
+
 	if (tb[NFTA_NAT_FAMILY] == NULL)
 		return -EINVAL;
 
@@ -219,13 +246,6 @@ nla_put_failure:
 	return -1;
 }
 
-static int nft_nat_validate(const struct nft_ctx *ctx,
-			    const struct nft_expr *expr,
-			    const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-
 static struct nft_expr_type nft_nat_type;
 static const struct nft_expr_ops nft_nat_ops = {
 	.type           = &nft_nat_type,
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 9e8093f2831..d7e9e93a4e9 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -23,6 +23,22 @@ const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = {
 };
 EXPORT_SYMBOL_GPL(nft_redir_policy);
 
+int nft_redir_validate(const struct nft_ctx *ctx,
+		       const struct nft_expr *expr,
+		       const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+					(1 << NF_INET_PRE_ROUTING) |
+					(1 << NF_INET_LOCAL_OUT));
+}
+EXPORT_SYMBOL_GPL(nft_redir_validate);
+
 int nft_redir_init(const struct nft_ctx *ctx,
 		   const struct nft_expr *expr,
 		   const struct nlattr * const tb[])
@@ -30,7 +46,7 @@ int nft_redir_init(const struct nft_ctx *ctx,
 	struct nft_redir *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	err = nft_redir_validate(ctx, expr, NULL);
 	if (err < 0)
 		return err;
 
@@ -88,12 +104,5 @@ nla_put_failure:
 }
 EXPORT_SYMBOL_GPL(nft_redir_dump);
 
-int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		       const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-EXPORT_SYMBOL_GPL(nft_redir_validate);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
-- 
cgit v1.2.3-70-g09d2


From 85b4545629663486b7f71047ce3b54fa0ad3eb28 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 12 Jan 2015 17:51:14 +0000
Subject: iommu: Consolidate IOVA allocator code

In order to share the IOVA allocator with other architectures, break
the unnecssary dependency on the Intel IOMMU driver and move the
remaining IOVA internals to iova.c

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-iommu.c | 33 ++-------------------------------
 drivers/iommu/iova.c        | 35 +++++++++++++++++++++++++++++++++++
 include/linux/iova.h        |  3 +++
 3 files changed, 40 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 40dfbc0444c..e758d8ed8fb 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -485,7 +485,6 @@ __setup("intel_iommu=", intel_iommu_setup);
 
 static struct kmem_cache *iommu_domain_cache;
 static struct kmem_cache *iommu_devinfo_cache;
-static struct kmem_cache *iommu_iova_cache;
 
 static inline void *alloc_pgtable_page(int node)
 {
@@ -523,16 +522,6 @@ static inline void free_devinfo_mem(void *vaddr)
 	kmem_cache_free(iommu_devinfo_cache, vaddr);
 }
 
-struct iova *alloc_iova_mem(void)
-{
-	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
-}
-
-void free_iova_mem(struct iova *iova)
-{
-	kmem_cache_free(iommu_iova_cache, iova);
-}
-
 static inline int domain_type_is_vm(struct dmar_domain *domain)
 {
 	return domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE;
@@ -3427,23 +3416,6 @@ static inline int iommu_devinfo_cache_init(void)
 	return ret;
 }
 
-static inline int iommu_iova_cache_init(void)
-{
-	int ret = 0;
-
-	iommu_iova_cache = kmem_cache_create("iommu_iova",
-					 sizeof(struct iova),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-					 NULL);
-	if (!iommu_iova_cache) {
-		printk(KERN_ERR "Couldn't create iova cache\n");
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-
 static int __init iommu_init_mempool(void)
 {
 	int ret;
@@ -3461,7 +3433,7 @@ static int __init iommu_init_mempool(void)
 
 	kmem_cache_destroy(iommu_domain_cache);
 domain_error:
-	kmem_cache_destroy(iommu_iova_cache);
+	iommu_iova_cache_destroy();
 
 	return -ENOMEM;
 }
@@ -3470,8 +3442,7 @@ static void __init iommu_exit_mempool(void)
 {
 	kmem_cache_destroy(iommu_devinfo_cache);
 	kmem_cache_destroy(iommu_domain_cache);
-	kmem_cache_destroy(iommu_iova_cache);
-
+	iommu_iova_cache_destroy();
 }
 
 static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index f6b17e6af2f..520b8c8ae0c 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -18,6 +18,41 @@
  */
 
 #include <linux/iova.h>
+#include <linux/slab.h>
+
+static struct kmem_cache *iommu_iova_cache;
+
+int iommu_iova_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_iova_cache = kmem_cache_create("iommu_iova",
+					 sizeof(struct iova),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+					 NULL);
+	if (!iommu_iova_cache) {
+		pr_err("Couldn't create iova cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+void iommu_iova_cache_destroy(void)
+{
+	kmem_cache_destroy(iommu_iova_cache);
+}
+
+struct iova *alloc_iova_mem(void)
+{
+	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
+}
+
+void free_iova_mem(struct iova *iova)
+{
+	kmem_cache_free(iommu_iova_cache, iova);
+}
 
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 19e81d5ccb6..ad0507c61cc 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -39,6 +39,9 @@ static inline unsigned long iova_size(struct iova *iova)
 	return iova->pfn_hi - iova->pfn_lo + 1;
 }
 
+int iommu_iova_cache_init(void);
+void iommu_iova_cache_destroy(void);
+
 struct iova *alloc_iova_mem(void);
 void free_iova_mem(struct iova *iova);
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
-- 
cgit v1.2.3-70-g09d2


From 1b72250076dde4276acecf3a7da722b185703e78 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 12 Jan 2015 17:51:15 +0000
Subject: iommu: Make IOVA domain low limit flexible

To share the IOVA allocator with other architectures, it needs to
accommodate more general aperture restrictions; move the lower limit
from a compile-time constant to a runtime domain property to allow
IOVA domains with different requirements to co-exist.

Also reword the slightly unclear description of alloc_iova since we're
touching it anyway.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-iommu.c |  9 ++++++---
 drivers/iommu/iova.c        | 10 ++++++----
 include/linux/iova.h        |  7 +++----
 3 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index e758d8ed8fb..86f9e82b015 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -71,6 +71,9 @@
 				__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
 #define DOMAIN_MAX_ADDR(gaw)	(((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)
 
+/* IO virtual address start page frame number */
+#define IOVA_START_PFN		(1)
+
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 #define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
 #define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
@@ -1632,7 +1635,7 @@ static int dmar_init_reserved_ranges(void)
 	struct iova *iova;
 	int i;
 
-	init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_list, IOVA_START_PFN, DMA_32BIT_PFN);
 
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
@@ -1690,7 +1693,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	int adjust_width, agaw;
 	unsigned long sagaw;
 
-	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
@@ -4313,7 +4316,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
-	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 520b8c8ae0c..a3dbba8caa1 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -55,11 +55,13 @@ void free_iova_mem(struct iova *iova)
 }
 
 void
-init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
+init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
+	unsigned long pfn_32bit)
 {
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
 	iovad->cached32_node = NULL;
+	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = pfn_32bit;
 }
 
@@ -162,7 +164,7 @@ move_left:
 	if (!curr) {
 		if (size_aligned)
 			pad_size = iova_get_pad_size(size, limit_pfn);
-		if ((IOVA_START_PFN + size + pad_size) > limit_pfn) {
+		if ((iovad->start_pfn + size + pad_size) > limit_pfn) {
 			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 			return -ENOMEM;
 		}
@@ -237,8 +239,8 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova)
  * @size: - size of page frames to allocate
  * @limit_pfn: - max limit address
  * @size_aligned: - set if size_aligned address range is required
- * This function allocates an iova in the range limit_pfn to IOVA_START_PFN
- * looking from limit_pfn instead from IOVA_START_PFN. If the size_aligned
+ * This function allocates an iova in the range iovad->start_pfn to limit_pfn,
+ * searching top-down from limit_pfn to iovad->start_pfn. If the size_aligned
  * flag is set then the allocated address iova->pfn_lo will be naturally
  * aligned on roundup_power_of_two(size).
  */
diff --git a/include/linux/iova.h b/include/linux/iova.h
index ad0507c61cc..591b19626b4 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -16,9 +16,6 @@
 #include <linux/rbtree.h>
 #include <linux/dma-mapping.h>
 
-/* IO virtual address start page frame number */
-#define IOVA_START_PFN		(1)
-
 /* iova structure */
 struct iova {
 	struct rb_node	node;
@@ -31,6 +28,7 @@ struct iova_domain {
 	spinlock_t	iova_rbtree_lock; /* Lock to protect update of rbtree */
 	struct rb_root	rbroot;		/* iova domain rbtree root */
 	struct rb_node	*cached32_node; /* Save last alloced node */
+	unsigned long	start_pfn;	/* Lower limit for this domain */
 	unsigned long	dma_32bit_pfn;
 };
 
@@ -52,7 +50,8 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
 struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
 	unsigned long pfn_hi);
 void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
-void init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit);
+void init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
+	unsigned long pfn_32bit);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
 struct iova *split_and_remove_iova(struct iova_domain *iovad,
-- 
cgit v1.2.3-70-g09d2


From 0fb5fe874c42942e16c450ae05da453e13a1c09e Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 12 Jan 2015 17:51:16 +0000
Subject: iommu: Make IOVA domain page size explicit

Systems may contain heterogeneous IOMMUs supporting differing minimum
page sizes, which may also not be common with the CPU page size.
Thus it is practical to have an explicit notion of IOVA granularity
to simplify handling of mapping and allocation constraints.

As an initial step, move the IOVA page granularity from an implicit
compile-time constant to a per-domain property so we can make use
of it in IOVA domain context at runtime. To keep the abstraction tidy,
extend the little API of inline iova_* helpers to parallel some of the
equivalent PAGE_* macros.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel-iommu.c |  9 ++++++---
 drivers/iommu/iova.c        | 12 ++++++++++--
 include/linux/iova.h        | 35 +++++++++++++++++++++++++++++++++--
 3 files changed, 49 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 86f9e82b015..ae4c1a854e5 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1635,7 +1635,8 @@ static int dmar_init_reserved_ranges(void)
 	struct iova *iova;
 	int i;
 
-	init_iova_domain(&reserved_iova_list, IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
@@ -1693,7 +1694,8 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	int adjust_width, agaw;
 	unsigned long sagaw;
 
-	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
@@ -4316,7 +4318,8 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
-	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index a3dbba8caa1..9dd8208312c 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -55,12 +55,20 @@ void free_iova_mem(struct iova *iova)
 }
 
 void
-init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
-	unsigned long pfn_32bit)
+init_iova_domain(struct iova_domain *iovad, unsigned long granule,
+	unsigned long start_pfn, unsigned long pfn_32bit)
 {
+	/*
+	 * IOVA granularity will normally be equal to the smallest
+	 * supported IOMMU page size; both *must* be capable of
+	 * representing individual CPU pages exactly.
+	 */
+	BUG_ON((granule > PAGE_SIZE) || !is_power_of_2(granule));
+
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
 	iovad->cached32_node = NULL;
+	iovad->granule = granule;
 	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = pfn_32bit;
 }
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 591b19626b4..3920a19d819 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -28,6 +28,7 @@ struct iova_domain {
 	spinlock_t	iova_rbtree_lock; /* Lock to protect update of rbtree */
 	struct rb_root	rbroot;		/* iova domain rbtree root */
 	struct rb_node	*cached32_node; /* Save last alloced node */
+	unsigned long	granule;	/* pfn granularity for this domain */
 	unsigned long	start_pfn;	/* Lower limit for this domain */
 	unsigned long	dma_32bit_pfn;
 };
@@ -37,6 +38,36 @@ static inline unsigned long iova_size(struct iova *iova)
 	return iova->pfn_hi - iova->pfn_lo + 1;
 }
 
+static inline unsigned long iova_shift(struct iova_domain *iovad)
+{
+	return __ffs(iovad->granule);
+}
+
+static inline unsigned long iova_mask(struct iova_domain *iovad)
+{
+	return iovad->granule - 1;
+}
+
+static inline size_t iova_offset(struct iova_domain *iovad, dma_addr_t iova)
+{
+	return iova & iova_mask(iovad);
+}
+
+static inline size_t iova_align(struct iova_domain *iovad, size_t size)
+{
+	return ALIGN(size, iovad->granule);
+}
+
+static inline dma_addr_t iova_dma_addr(struct iova_domain *iovad, struct iova *iova)
+{
+	return (dma_addr_t)iova->pfn_lo << iova_shift(iovad);
+}
+
+static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
+{
+	return iova >> iova_shift(iovad);
+}
+
 int iommu_iova_cache_init(void);
 void iommu_iova_cache_destroy(void);
 
@@ -50,8 +81,8 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
 struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
 	unsigned long pfn_hi);
 void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
-void init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
-	unsigned long pfn_32bit);
+void init_iova_domain(struct iova_domain *iovad, unsigned long granule,
+	unsigned long start_pfn, unsigned long pfn_32bit);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
 struct iova *split_and_remove_iova(struct iova_domain *iovad,
-- 
cgit v1.2.3-70-g09d2


From 72dd299d5039a336493993dcc63413cf31d0e662 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 16 Jan 2015 15:13:02 -0800
Subject: libata: allow sata_sil24 to opt-out of tag ordered submission

Ronny reports: https://bugzilla.kernel.org/show_bug.cgi?id=87101
    "Since commit 8a4aeec8d "libata/ahci: accommodate tag ordered
    controllers" the access to the harddisk on the first SATA-port is
    failing on its first access. The access to the harddisk on the
    second port is working normal.

    When reverting the above commit, access to both harddisks is working
    fine again."

Maintain tag ordered submission as the default, but allow sata_sil24 to
continue with the old behavior.

Cc: <stable@vger.kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Reported-by: Ronny Hegewald <Ronny.Hegewald@online.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/libata-core.c | 5 ++++-
 drivers/ata/sata_sil24.c  | 2 +-
 include/linux/libata.h    | 1 +
 3 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 23c2ae03a7a..d1a05f9bb91 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4771,7 +4771,10 @@ static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 		return NULL;
 
 	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
-		tag = tag < max_queue ? tag : 0;
+		if (ap->flags & ATA_FLAG_LOWTAG)
+			tag = i;
+		else
+			tag = tag < max_queue ? tag : 0;
 
 		/* the last tag is reserved for internal command. */
 		if (tag == ATA_TAG_INTERNAL)
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index d81b20ddb52..ea655949023 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -246,7 +246,7 @@ enum {
 	/* host flags */
 	SIL24_COMMON_FLAGS	= ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
 				  ATA_FLAG_NCQ | ATA_FLAG_ACPI_SATA |
-				  ATA_FLAG_AN | ATA_FLAG_PMP,
+				  ATA_FLAG_AN | ATA_FLAG_PMP | ATA_FLAG_LOWTAG,
 	SIL24_FLAG_PCIX_IRQ_WOC	= (1 << 24), /* IRQ loss errata on PCI-X */
 
 	IRQ_STAT_4PORTS		= 0xf,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index f2b440e44fd..91f705de2c0 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -231,6 +231,7 @@ enum {
 	ATA_FLAG_SW_ACTIVITY	= (1 << 22), /* driver supports sw activity
 					      * led */
 	ATA_FLAG_NO_DIPM	= (1 << 23), /* host not happy with DIPM */
+	ATA_FLAG_LOWTAG		= (1 << 24), /* host wants lowest available tag */
 
 	/* bits 24:31 of ap->flags are reserved for LLD specific flags */
 
-- 
cgit v1.2.3-70-g09d2


From db8614d35bb8fc6d032792c801bd5b38ce860f19 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuahkh@osg.samsung.com>
Date: Fri, 16 Jan 2015 20:53:17 -0700
Subject: iommu: Change trace unmap api to report unmapped size

Currently map and unmap are implemented as events under a
common trace class declaration. The common class forces
trace_unmap() to require a bogus physical address argument
that it doesn't use. Changing unmap to report unmapped size
will provide useful information for debugging. Remove common
map_unmap trace class and change map and unmap into separate
events as opposed to events under the same class to allow for
differences in the reporting information. In addition, map and
unmap are changed to handle size value as size_t instead of int
to match the passed size value and avoid overflow.

Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/iommu.c        |  2 +-
 include/trace/events/iommu.h | 31 ++++++++++++++++++-------------
 2 files changed, 19 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index d4c3db5abf2..3a4fb6274c9 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1134,7 +1134,7 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 		unmapped += unmapped_page;
 	}
 
-	trace_unmap(orig_iova, 0, size);
+	trace_unmap(orig_iova, size, unmapped);
 	return unmapped;
 }
 EXPORT_SYMBOL_GPL(iommu_unmap);
diff --git a/include/trace/events/iommu.h b/include/trace/events/iommu.h
index a8f5c32d174..2c7befb10f1 100644
--- a/include/trace/events/iommu.h
+++ b/include/trace/events/iommu.h
@@ -83,7 +83,7 @@ DEFINE_EVENT(iommu_device_event, detach_device_from_domain,
 	TP_ARGS(dev)
 );
 
-DECLARE_EVENT_CLASS(iommu_map_unmap,
+TRACE_EVENT(map,
 
 	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
 
@@ -92,7 +92,7 @@ DECLARE_EVENT_CLASS(iommu_map_unmap,
 	TP_STRUCT__entry(
 		__field(u64, iova)
 		__field(u64, paddr)
-		__field(int, size)
+		__field(size_t, size)
 	),
 
 	TP_fast_assign(
@@ -101,26 +101,31 @@ DECLARE_EVENT_CLASS(iommu_map_unmap,
 		__entry->size = size;
 	),
 
-	TP_printk("IOMMU: iova=0x%016llx paddr=0x%016llx size=0x%x",
+	TP_printk("IOMMU: iova=0x%016llx paddr=0x%016llx size=%zu",
 			__entry->iova, __entry->paddr, __entry->size
 	)
 );
 
-DEFINE_EVENT(iommu_map_unmap, map,
+TRACE_EVENT(unmap,
 
-	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
-
-	TP_ARGS(iova, paddr, size)
-);
+	TP_PROTO(unsigned long iova, size_t size, size_t unmapped_size),
 
-DEFINE_EVENT_PRINT(iommu_map_unmap, unmap,
+	TP_ARGS(iova, size, unmapped_size),
 
-	TP_PROTO(unsigned long iova, phys_addr_t paddr, size_t size),
+	TP_STRUCT__entry(
+		__field(u64, iova)
+		__field(size_t, size)
+		__field(size_t, unmapped_size)
+	),
 
-	TP_ARGS(iova, paddr, size),
+	TP_fast_assign(
+		__entry->iova = iova;
+		__entry->size = size;
+		__entry->unmapped_size = unmapped_size;
+	),
 
-	TP_printk("IOMMU: iova=0x%016llx size=0x%x",
-			__entry->iova, __entry->size
+	TP_printk("IOMMU: iova=0x%016llx size=%zu unmapped_size=%zu",
+			__entry->iova, __entry->size, __entry->unmapped_size
 	)
 );
 
-- 
cgit v1.2.3-70-g09d2


From c7d7ddee7e24eedde6149eefbcfbfbc7125b9ff0 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@free-electrons.com>
Date: Thu, 15 Jan 2015 15:09:37 +0100
Subject: ata: libahci: Allow using multiple regulators

The current implementation of the libahci allows using multiple PHYs
but not multiple regulators. This patch adds the support of multiple
regulators. Until now it was mandatory to have a PHY under a subnode,
now a port subnode can contain either a regulator or a PHY (or both).

In order to be able to asociate a port with a regulator the port are
now a platform device in the device tree case.

There was only one driver which used directly the regulator field of
the ahci_host_priv structure. To preserve the bisectability the change
in the ahci_imx driver was done in the same patch.

Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/ahci.h             |   2 +-
 drivers/ata/ahci_imx.c         |  14 +--
 drivers/ata/libahci_platform.c | 230 +++++++++++++++++++++++++++++------------
 include/linux/ahci_platform.h  |   2 +
 4 files changed, 173 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 40f0e34f17a..275358ae0b3 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -333,7 +333,7 @@ struct ahci_host_priv {
 	u32			em_msg_type;	/* EM message type */
 	bool			got_runtime_pm; /* Did we do pm_runtime_get? */
 	struct clk		*clks[AHCI_MAX_CLKS]; /* Optional */
-	struct regulator	*target_pwr;	/* Optional */
+	struct regulator	**target_pwrs;	/* Optional */
 	/*
 	 * If platform uses PHYs. There is a 1:1 relation between the port number and
 	 * the PHY position in this array.
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index 35d51c59a37..41632e57d46 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -221,11 +221,9 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv)
 	if (imxpriv->no_device)
 		return 0;
 
-	if (hpriv->target_pwr) {
-		ret = regulator_enable(hpriv->target_pwr);
-		if (ret)
-			return ret;
-	}
+	ret = ahci_platform_enable_regulators(hpriv);
+	if (ret)
+		return ret;
 
 	ret = clk_prepare_enable(imxpriv->sata_ref_clk);
 	if (ret < 0)
@@ -270,8 +268,7 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv)
 disable_clk:
 	clk_disable_unprepare(imxpriv->sata_ref_clk);
 disable_regulator:
-	if (hpriv->target_pwr)
-		regulator_disable(hpriv->target_pwr);
+	ahci_platform_disable_regulators(hpriv);
 
 	return ret;
 }
@@ -291,8 +288,7 @@ static void imx_sata_disable(struct ahci_host_priv *hpriv)
 
 	clk_disable_unprepare(imxpriv->sata_ref_clk);
 
-	if (hpriv->target_pwr)
-		regulator_disable(hpriv->target_pwr);
+	ahci_platform_disable_regulators(hpriv);
 }
 
 static void ahci_imx_error_handler(struct ata_port *ap)
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index a147aaadca8..73a086664ee 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -24,6 +24,7 @@
 #include <linux/ahci_platform.h>
 #include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
+#include <linux/of_platform.h>
 #include "ahci.h"
 
 static void ahci_host_stop(struct ata_host *host);
@@ -137,6 +138,59 @@ void ahci_platform_disable_clks(struct ahci_host_priv *hpriv)
 }
 EXPORT_SYMBOL_GPL(ahci_platform_disable_clks);
 
+/**
+ * ahci_platform_enable_regulators - Enable regulators
+ * @hpriv: host private area to store config values
+ *
+ * This function enables all the regulators found in
+ * hpriv->target_pwrs, if any.  If a regulator fails to be enabled, it
+ * disables all the regulators already enabled in reverse order and
+ * returns an error.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv)
+{
+	int rc, i;
+
+	for (i = 0; i < hpriv->nports; i++) {
+		if (!hpriv->target_pwrs[i])
+			continue;
+
+		rc = regulator_enable(hpriv->target_pwrs[i]);
+		if (rc)
+			goto disable_target_pwrs;
+	}
+
+	return 0;
+
+disable_target_pwrs:
+	while (--i >= 0)
+		if (hpriv->target_pwrs[i])
+			regulator_disable(hpriv->target_pwrs[i]);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators);
+
+/**
+ * ahci_platform_disable_regulators - Disable regulators
+ * @hpriv: host private area to store config values
+ *
+ * This function disables all regulators found in hpriv->target_pwrs.
+ */
+void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv)
+{
+	int i;
+
+	for (i = 0; i < hpriv->nports; i++) {
+		if (!hpriv->target_pwrs[i])
+			continue;
+		regulator_disable(hpriv->target_pwrs[i]);
+	}
+}
+EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators);
 /**
  * ahci_platform_enable_resources - Enable platform resources
  * @hpriv: host private area to store config values
@@ -157,11 +211,9 @@ int ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
 {
 	int rc;
 
-	if (hpriv->target_pwr) {
-		rc = regulator_enable(hpriv->target_pwr);
-		if (rc)
-			return rc;
-	}
+	rc = ahci_platform_enable_regulators(hpriv);
+	if (rc)
+		return rc;
 
 	rc = ahci_platform_enable_clks(hpriv);
 	if (rc)
@@ -177,8 +229,8 @@ disable_clks:
 	ahci_platform_disable_clks(hpriv);
 
 disable_regulator:
-	if (hpriv->target_pwr)
-		regulator_disable(hpriv->target_pwr);
+	ahci_platform_disable_regulators(hpriv);
+
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_platform_enable_resources);
@@ -199,8 +251,7 @@ void ahci_platform_disable_resources(struct ahci_host_priv *hpriv)
 
 	ahci_platform_disable_clks(hpriv);
 
-	if (hpriv->target_pwr)
-		regulator_disable(hpriv->target_pwr);
+	ahci_platform_disable_regulators(hpriv);
 }
 EXPORT_SYMBOL_GPL(ahci_platform_disable_resources);
 
@@ -216,6 +267,68 @@ static void ahci_platform_put_resources(struct device *dev, void *res)
 
 	for (c = 0; c < AHCI_MAX_CLKS && hpriv->clks[c]; c++)
 		clk_put(hpriv->clks[c]);
+	/*
+	 * The regulators are tied to child node device and not to the
+	 * SATA device itself. So we can't use devm for automatically
+	 * releasing them. We have to do it manually here.
+	 */
+	for (c = 0; c < hpriv->nports; c++)
+		if (hpriv->target_pwrs && hpriv->target_pwrs[c])
+			regulator_put(hpriv->target_pwrs[c]);
+
+}
+
+static int ahci_platform_get_phy(struct ahci_host_priv *hpriv, u32 port,
+				struct device *dev, struct device_node *node)
+{
+	int rc;
+
+	hpriv->phys[port] = devm_of_phy_get(dev, node, NULL);
+
+	if (!IS_ERR(hpriv->phys[port]))
+		return 0;
+
+	rc = PTR_ERR(hpriv->phys[port]);
+	switch (rc) {
+	case -ENOSYS:
+		/* No PHY support. Check if PHY is required. */
+		if (of_find_property(node, "phys", NULL)) {
+			dev_err(dev,
+				"couldn't get PHY in node %s: ENOSYS\n",
+				node->name);
+			break;
+		}
+	case -ENODEV:
+		/* continue normally */
+		hpriv->phys[port] = NULL;
+		rc = 0;
+		break;
+
+	default:
+		dev_err(dev,
+			"couldn't get PHY in node %s: %d\n",
+			node->name, rc);
+
+		break;
+	}
+
+	return rc;
+}
+
+static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port,
+				struct device *dev)
+{
+	struct regulator *target_pwr;
+	int rc = 0;
+
+	target_pwr = regulator_get_optional(dev, "target");
+
+	if (!IS_ERR(target_pwr))
+		hpriv->target_pwrs[port] = target_pwr;
+	else
+		rc = PTR_ERR(target_pwr);
+
+	return rc;
 }
 
 /**
@@ -240,7 +353,7 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 	struct ahci_host_priv *hpriv;
 	struct clk *clk;
 	struct device_node *child;
-	int i, enabled_ports = 0, rc = -ENOMEM;
+	int i, sz, enabled_ports = 0, rc = -ENOMEM, child_nodes;
 	u32 mask_port_map = 0;
 
 	if (!devres_open_group(dev, NULL, GFP_KERNEL))
@@ -261,14 +374,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 		goto err_out;
 	}
 
-	hpriv->target_pwr = devm_regulator_get_optional(dev, "target");
-	if (IS_ERR(hpriv->target_pwr)) {
-		rc = PTR_ERR(hpriv->target_pwr);
-		if (rc == -EPROBE_DEFER)
-			goto err_out;
-		hpriv->target_pwr = NULL;
-	}
-
 	for (i = 0; i < AHCI_MAX_CLKS; i++) {
 		/*
 		 * For now we must use clk_get(dev, NULL) for the first clock,
@@ -290,19 +395,33 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 		hpriv->clks[i] = clk;
 	}
 
-	hpriv->nports = of_get_child_count(dev->of_node);
+	hpriv->nports = child_nodes = of_get_child_count(dev->of_node);
 
-	if (hpriv->nports) {
-		hpriv->phys = devm_kzalloc(dev,
-					   hpriv->nports * sizeof(*hpriv->phys),
-					   GFP_KERNEL);
-		if (!hpriv->phys) {
-			rc = -ENOMEM;
-			goto err_out;
-		}
+	/*
+	 * If no sub-node was found, we still need to set nports to
+	 * one in order to be able to use the
+	 * ahci_platform_[en|dis]able_[phys|regulators] functions.
+	 */
+	if (!child_nodes)
+		hpriv->nports = 1;
 
+	sz = hpriv->nports * sizeof(*hpriv->phys);
+	hpriv->phys = devm_kzalloc(dev, sz, GFP_KERNEL);
+	if (!hpriv->phys) {
+		rc = -ENOMEM;
+		goto err_out;
+	}
+	sz = hpriv->nports * sizeof(*hpriv->target_pwrs);
+	hpriv->target_pwrs = devm_kzalloc(dev, sz, GFP_KERNEL);
+	if (!hpriv->target_pwrs) {
+		rc = -ENOMEM;
+		goto err_out;
+	}
+
+	if (child_nodes) {
 		for_each_child_of_node(dev->of_node, child) {
 			u32 port;
+			struct platform_device *port_dev;
 
 			if (!of_device_is_available(child))
 				continue;
@@ -316,18 +435,23 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 				dev_warn(dev, "invalid port number %d\n", port);
 				continue;
 			}
-
 			mask_port_map |= BIT(port);
 
-			hpriv->phys[port] = devm_of_phy_get(dev, child, NULL);
-			if (IS_ERR(hpriv->phys[port])) {
-				rc = PTR_ERR(hpriv->phys[port]);
-				dev_err(dev,
-					"couldn't get PHY in node %s: %d\n",
-					child->name, rc);
-				goto err_out;
+			of_platform_device_create(child, NULL, NULL);
+
+			port_dev = of_find_device_by_node(child);
+
+			if (port_dev) {
+				rc = ahci_platform_get_regulator(hpriv, port,
+								&port_dev->dev);
+				if (rc == -EPROBE_DEFER)
+					goto err_out;
 			}
 
+			rc = ahci_platform_get_phy(hpriv, port, dev, child);
+			if (rc)
+				goto err_out;
+
 			enabled_ports++;
 		}
 		if (!enabled_ports) {
@@ -343,38 +467,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 		 * If no sub-node was found, keep this for device tree
 		 * compatibility
 		 */
-		struct phy *phy = devm_phy_get(dev, "sata-phy");
-		if (!IS_ERR(phy)) {
-			hpriv->phys = devm_kzalloc(dev, sizeof(*hpriv->phys),
-						   GFP_KERNEL);
-			if (!hpriv->phys) {
-				rc = -ENOMEM;
-				goto err_out;
-			}
-
-			hpriv->phys[0] = phy;
-			hpriv->nports = 1;
-		} else {
-			rc = PTR_ERR(phy);
-			switch (rc) {
-				case -ENOSYS:
-					/* No PHY support. Check if PHY is required. */
-					if (of_find_property(dev->of_node, "phys", NULL)) {
-						dev_err(dev, "couldn't get sata-phy: ENOSYS\n");
-						goto err_out;
-					}
-				case -ENODEV:
-					/* continue normally */
-					hpriv->phys = NULL;
-					break;
-
-				default:
-					goto err_out;
+		rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node);
+		if (rc)
+			goto err_out;
 
-			}
-		}
+		rc = ahci_platform_get_regulator(hpriv, 0, dev);
+		if (rc == -EPROBE_DEFER)
+			goto err_out;
 	}
-
 	pm_runtime_enable(dev);
 	pm_runtime_get_sync(dev);
 	hpriv->got_runtime_pm = true;
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index 642d6ae4030..f65b3380917 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -24,6 +24,8 @@ struct platform_device;
 
 int ahci_platform_enable_clks(struct ahci_host_priv *hpriv);
 void ahci_platform_disable_clks(struct ahci_host_priv *hpriv);
+int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv);
+void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv);
 int ahci_platform_enable_resources(struct ahci_host_priv *hpriv);
 void ahci_platform_disable_resources(struct ahci_host_priv *hpriv);
 struct ahci_host_priv *ahci_platform_get_resources(
-- 
cgit v1.2.3-70-g09d2


From 54c523127bcca986c6f9b04c7b56a949ea011899 Mon Sep 17 00:00:00 2001
From: Matt Wagantall <mattw@codeaurora.org>
Date: Mon, 15 Dec 2014 23:47:23 +0000
Subject: iopoll: Introduce memory-mapped IO polling macros

It is sometimes necessary to poll a memory-mapped register until its value
satisfies some condition. Introduce a family of convenience macros that do
this. Tight-looping, sleeping, and timing out can all be accomplished using
these macros.

Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Robert Elliott <elliott@hp.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Matt Wagantall <mattw@codeaurora.org>
Signed-off-by: Mitchel Humpherys <mitchelh@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/linux/iopoll.h | 144 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 144 insertions(+)
 create mode 100644 include/linux/iopoll.h

(limited to 'include')

diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
new file mode 100644
index 00000000000..1c30014ed17
--- /dev/null
+++ b/include/linux/iopoll.h
@@ -0,0 +1,144 @@
+/*
+ * Copyright (c) 2012-2014 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_IOPOLL_H
+#define _LINUX_IOPOLL_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/hrtimer.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+
+/**
+ * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs
+ * @op: accessor function (takes @addr as its only argument)
+ * @addr: Address to poll
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0
+ *            tight-loops).  Should be less than ~20ms since usleep_range
+ *            is used (see Documentation/timers/timers-howto.txt).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ *
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @addr is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ */
+#define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us)	\
+({ \
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+	might_sleep_if(sleep_us); \
+	for (;;) { \
+		(val) = op(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+			(val) = op(addr); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range((sleep_us >> 2) + 1, sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+/**
+ * readx_poll_timeout_atomic - Periodically poll an address until a condition is met or a timeout occurs
+ * @op: accessor function (takes @addr as its only argument)
+ * @addr: Address to poll
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @delay_us: Time to udelay between reads in us (0 tight-loops).  Should
+ *            be less than ~10us since udelay is used (see
+ *            Documentation/timers/timers-howto.txt).
+ * @timeout_us: Timeout in us, 0 means never timeout
+ *
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @addr is stored in @val.
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ */
+#define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \
+({ \
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+	for (;;) { \
+		(val) = op(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+			(val) = op(addr); \
+			break; \
+		} \
+		if (delay_us) \
+			udelay(delay_us);	\
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+
+#define readb_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readb, addr, val, cond, delay_us, timeout_us)
+
+#define readb_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readb, addr, val, cond, delay_us, timeout_us)
+
+#define readw_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readw, addr, val, cond, delay_us, timeout_us)
+
+#define readw_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readw, addr, val, cond, delay_us, timeout_us)
+
+#define readl_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readl, addr, val, cond, delay_us, timeout_us)
+
+#define readl_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readl, addr, val, cond, delay_us, timeout_us)
+
+#define readq_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readq, addr, val, cond, delay_us, timeout_us)
+
+#define readq_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readq, addr, val, cond, delay_us, timeout_us)
+
+#define readb_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readb_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readb_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readb_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readw_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readw_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readw_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readw_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readl_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readl_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readl_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readl_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readq_relaxed_poll_timeout(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout(readq_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#define readq_relaxed_poll_timeout_atomic(addr, val, cond, delay_us, timeout_us) \
+	readx_poll_timeout_atomic(readq_relaxed, addr, val, cond, delay_us, timeout_us)
+
+#endif /* _LINUX_IOPOLL_H */
-- 
cgit v1.2.3-70-g09d2


From 0c7aecd4bde4b7302cd41986d3a29e4f0b0ed218 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 15 Jan 2015 15:11:15 +0100
Subject: netns: add rtnl cmd to add and get peer netns ids

With this patch, a user can define an id for a peer netns by providing a FD or a
PID. These ids are local to the netns where it is added (ie valid only into this
netns).

The main function (ie the one exported to other module), peernet2id(), allows to
get the id of a peer netns. If no id has been assigned by the user, this
function allocates one.

These ids will be used in netlink messages to point to a peer netns, for example
in case of a x-netns interface.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                        |   1 +
 include/net/net_namespace.h        |   4 +
 include/uapi/linux/Kbuild          |   1 +
 include/uapi/linux/net_namespace.h |  23 ++++
 include/uapi/linux/rtnetlink.h     |   5 +
 net/core/net_namespace.c           | 211 +++++++++++++++++++++++++++++++++++++
 6 files changed, 245 insertions(+)
 create mode 100644 include/uapi/linux/net_namespace.h

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 9de90057263..9b91d9f0257 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6578,6 +6578,7 @@ F:	include/linux/netdevice.h
 F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/netdevice.h
+F:	include/uapi/linux/net_namespace.h
 F:	tools/net/
 F:	tools/testing/selftests/net/
 F:	lib/random32.c
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 2e8756b8c77..36faf4990c4 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -60,6 +60,7 @@ struct net {
 	struct list_head	exit_list;	/* Use only net_mutex */
 
 	struct user_namespace   *user_ns;	/* Owning user namespace */
+	struct idr		netns_ids;
 
 	struct ns_common	ns;
 
@@ -290,6 +291,9 @@ static inline struct net *read_pnet(struct net * const *pnet)
 #define __net_initconst	__initconst
 #endif
 
+int peernet2id(struct net *net, struct net *peer);
+struct net *get_net_ns_by_id(struct net *net, int id);
+
 struct pernet_operations {
 	struct list_head list;
 	int (*init)(struct net *net);
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 00b100023c4..14b7b6e44c7 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -283,6 +283,7 @@ header-y += net.h
 header-y += netlink_diag.h
 header-y += netlink.h
 header-y += netrom.h
+header-y += net_namespace.h
 header-y += net_tstamp.h
 header-y += nfc.h
 header-y += nfs2.h
diff --git a/include/uapi/linux/net_namespace.h b/include/uapi/linux/net_namespace.h
new file mode 100644
index 00000000000..778cd2c3ebf
--- /dev/null
+++ b/include/uapi/linux/net_namespace.h
@@ -0,0 +1,23 @@
+/* Copyright (c) 2015 6WIND S.A.
+ * Author: Nicolas Dichtel <nicolas.dichtel@6wind.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+#ifndef _UAPI_LINUX_NET_NAMESPACE_H_
+#define _UAPI_LINUX_NET_NAMESPACE_H_
+
+/* Attributes of RTM_NEWNSID/RTM_GETNSID messages */
+enum {
+	NETNSA_NONE,
+#define NETNSA_NSID_NOT_ASSIGNED -1
+	NETNSA_NSID,
+	NETNSA_PID,
+	NETNSA_FD,
+	__NETNSA_MAX,
+};
+
+#define NETNSA_MAX		(__NETNSA_MAX - 1)
+
+#endif /* _UAPI_LINUX_NET_NAMESPACE_H_ */
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index a1d18593f41..5cc5d66bf51 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -132,6 +132,11 @@ enum {
 	RTM_GETMDB = 86,
 #define RTM_GETMDB RTM_GETMDB
 
+	RTM_NEWNSID = 88,
+#define RTM_NEWNSID RTM_NEWNSID
+	RTM_GETNSID = 90,
+#define RTM_GETNSID RTM_GETNSID
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ce780c722e4..9d1a4cac83b 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -15,6 +15,10 @@
 #include <linux/file.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/net_namespace.h>
+#include <linux/rtnetlink.h>
+#include <net/sock.h>
+#include <net/netlink.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -144,6 +148,77 @@ static void ops_free_list(const struct pernet_operations *ops,
 	}
 }
 
+static int alloc_netid(struct net *net, struct net *peer, int reqid)
+{
+	int min = 0, max = 0;
+
+	ASSERT_RTNL();
+
+	if (reqid >= 0) {
+		min = reqid;
+		max = reqid + 1;
+	}
+
+	return idr_alloc(&net->netns_ids, peer, min, max, GFP_KERNEL);
+}
+
+/* This function is used by idr_for_each(). If net is equal to peer, the
+ * function returns the id so that idr_for_each() stops. Because we cannot
+ * returns the id 0 (idr_for_each() will not stop), we return the magic value
+ * NET_ID_ZERO (-1) for it.
+ */
+#define NET_ID_ZERO -1
+static int net_eq_idr(int id, void *net, void *peer)
+{
+	if (net_eq(net, peer))
+		return id ? : NET_ID_ZERO;
+	return 0;
+}
+
+static int __peernet2id(struct net *net, struct net *peer, bool alloc)
+{
+	int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
+
+	ASSERT_RTNL();
+
+	/* Magic value for id 0. */
+	if (id == NET_ID_ZERO)
+		return 0;
+	if (id > 0)
+		return id;
+
+	if (alloc)
+		return alloc_netid(net, peer, -1);
+
+	return -ENOENT;
+}
+
+/* This function returns the id of a peer netns. If no id is assigned, one will
+ * be allocated and returned.
+ */
+int peernet2id(struct net *net, struct net *peer)
+{
+	int id = __peernet2id(net, peer, true);
+
+	return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
+}
+
+struct net *get_net_ns_by_id(struct net *net, int id)
+{
+	struct net *peer;
+
+	if (id < 0)
+		return NULL;
+
+	rcu_read_lock();
+	peer = idr_find(&net->netns_ids, id);
+	if (peer)
+		get_net(peer);
+	rcu_read_unlock();
+
+	return peer;
+}
+
 /*
  * setup_net runs the initializers for the network namespace object.
  */
@@ -158,6 +233,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	atomic_set(&net->passive, 1);
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
+	idr_init(&net->netns_ids);
 
 #ifdef NETNS_REFCNT_DEBUG
 	atomic_set(&net->use_count, 0);
@@ -288,6 +364,14 @@ static void cleanup_net(struct work_struct *work)
 	list_for_each_entry(net, &net_kill_list, cleanup_list) {
 		list_del_rcu(&net->list);
 		list_add_tail(&net->exit_list, &net_exit_list);
+		for_each_net(tmp) {
+			int id = __peernet2id(tmp, net, false);
+
+			if (id >= 0)
+				idr_remove(&tmp->netns_ids, id);
+		}
+		idr_destroy(&net->netns_ids);
+
 	}
 	rtnl_unlock();
 
@@ -402,6 +486,130 @@ static struct pernet_operations __net_initdata net_ns_ops = {
 	.exit = net_ns_net_exit,
 };
 
+static struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = {
+	[NETNSA_NONE]		= { .type = NLA_UNSPEC },
+	[NETNSA_NSID]		= { .type = NLA_S32 },
+	[NETNSA_PID]		= { .type = NLA_U32 },
+	[NETNSA_FD]		= { .type = NLA_U32 },
+};
+
+static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[NETNSA_MAX + 1];
+	struct net *peer;
+	int nsid, err;
+
+	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+			  rtnl_net_policy);
+	if (err < 0)
+		return err;
+	if (!tb[NETNSA_NSID])
+		return -EINVAL;
+	nsid = nla_get_s32(tb[NETNSA_NSID]);
+
+	if (tb[NETNSA_PID])
+		peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID]));
+	else if (tb[NETNSA_FD])
+		peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
+	else
+		return -EINVAL;
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	if (__peernet2id(net, peer, false) >= 0) {
+		err = -EEXIST;
+		goto out;
+	}
+
+	err = alloc_netid(net, peer, nsid);
+	if (err > 0)
+		err = 0;
+out:
+	put_net(peer);
+	return err;
+}
+
+static int rtnl_net_get_size(void)
+{
+	return NLMSG_ALIGN(sizeof(struct rtgenmsg))
+	       + nla_total_size(sizeof(s32)) /* NETNSA_NSID */
+	       ;
+}
+
+static int rtnl_net_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
+			 int cmd, struct net *net, struct net *peer)
+{
+	struct nlmsghdr *nlh;
+	struct rtgenmsg *rth;
+	int id;
+
+	ASSERT_RTNL();
+
+	nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rth), flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	rth = nlmsg_data(nlh);
+	rth->rtgen_family = AF_UNSPEC;
+
+	id = __peernet2id(net, peer, false);
+	if  (id < 0)
+		id = NETNSA_NSID_NOT_ASSIGNED;
+	if (nla_put_s32(skb, NETNSA_NSID, id))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+	return 0;
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tb[NETNSA_MAX + 1];
+	struct sk_buff *msg;
+	int err = -ENOBUFS;
+	struct net *peer;
+
+	err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX,
+			  rtnl_net_policy);
+	if (err < 0)
+		return err;
+	if (tb[NETNSA_PID])
+		peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID]));
+	else if (tb[NETNSA_FD])
+		peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD]));
+	else
+		return -EINVAL;
+
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
+	if (!msg) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = rtnl_net_fill(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0,
+			    RTM_GETNSID, net, peer);
+	if (err < 0)
+		goto err_out;
+
+	err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid);
+	goto out;
+
+err_out:
+	nlmsg_free(msg);
+out:
+	put_net(peer);
+	return err;
+}
+
 static int __init net_ns_init(void)
 {
 	struct net_generic *ng;
@@ -435,6 +643,9 @@ static int __init net_ns_init(void)
 
 	register_pernet_subsys(&net_ns_ops);
 
+	rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, NULL, NULL);
+
 	return 0;
 }
 
-- 
cgit v1.2.3-70-g09d2


From d37512a277dfb2cef8a578e25a3246f61399a55a Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 15 Jan 2015 15:11:16 +0100
Subject: rtnl: add link netns id to interface messages

This patch adds a new attribute (IFLA_LINK_NETNSID) which contains the 'link'
netns id when this netns is different from the netns where the interface
stands (for example for x-net interfaces like ip tunnels).
With this attribute, it's possible to interpret correctly all advertised
information (like IFLA_LINK, etc.).

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rtnetlink.h      |  2 ++
 include/uapi/linux/if_link.h |  1 +
 net/core/rtnetlink.c         | 13 +++++++++++++
 3 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index e21b9f9653c..6c6d5393fc3 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -46,6 +46,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
  *			    to create when creating a new device.
  *	@get_num_rx_queues: Function to determine number of receive queues
  *			    to create when creating a new device.
+ *	@get_link_net: Function to get the i/o netns of the device
  */
 struct rtnl_link_ops {
 	struct list_head	list;
@@ -93,6 +94,7 @@ struct rtnl_link_ops {
 	int			(*fill_slave_info)(struct sk_buff *skb,
 						   const struct net_device *dev,
 						   const struct net_device *slave_dev);
+	struct net		*(*get_link_net)(const struct net_device *dev);
 };
 
 int __rtnl_link_register(struct rtnl_link_ops *ops);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 2a8380edbb7..0deee3eeddb 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -146,6 +146,7 @@ enum {
 	IFLA_PHYS_PORT_ID,
 	IFLA_CARRIER_CHANGES,
 	IFLA_PHYS_SWITCH_ID,
+	IFLA_LINK_NETNSID,
 	__IFLA_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 47b39f3e867..bd6370f0cb3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -875,6 +875,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
+	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
@@ -1169,6 +1170,18 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			goto nla_put_failure;
 	}
 
+	if (dev->rtnl_link_ops &&
+	    dev->rtnl_link_ops->get_link_net) {
+		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
+
+		if (!net_eq(dev_net(dev), link_net)) {
+			int id = peernet2id(dev_net(dev), link_net);
+
+			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
+				goto nla_put_failure;
+		}
+	}
+
 	if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC)))
 		goto nla_put_failure;
 
-- 
cgit v1.2.3-70-g09d2


From 1728d4fabd1bc9965728de25dda0b694b8da6450 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Thu, 15 Jan 2015 15:11:17 +0100
Subject: tunnels: advertise link netns via netlink

Implement rtnl_link_ops->get_link_net() callback so that IFLA_LINK_NETNSID is
added to rtnetlink messages.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c      | 8 ++++++++
 include/net/ip6_tunnel.h | 1 +
 include/net/ip_tunnels.h | 1 +
 net/ipv4/ip_gre.c        | 2 ++
 net/ipv4/ip_tunnel.c     | 8 ++++++++
 net/ipv4/ip_vti.c        | 1 +
 net/ipv4/ipip.c          | 1 +
 net/ipv6/ip6_gre.c       | 1 +
 net/ipv6/ip6_tunnel.c    | 9 +++++++++
 net/ipv6/ip6_vti.c       | 1 +
 net/ipv6/sit.c           | 1 +
 11 files changed, 34 insertions(+)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index c5f79e7513a..0346eaa6d23 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2923,6 +2923,13 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static struct net *vxlan_get_link_net(const struct net_device *dev)
+{
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+
+	return vxlan->net;
+}
+
 static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
 	.kind		= "vxlan",
 	.maxtype	= IFLA_VXLAN_MAX,
@@ -2934,6 +2941,7 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
 	.dellink	= vxlan_dellink,
 	.get_size	= vxlan_get_size,
 	.fill_info	= vxlan_fill_info,
+	.get_link_net	= vxlan_get_link_net,
 };
 
 static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn,
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 9326c41c2d7..76c091b53da 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -70,6 +70,7 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
 __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw);
 __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
 			     const struct in6_addr *raddr);
+struct net *ip6_tnl_get_link_net(const struct net_device *dev);
 
 static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 {
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index ce4db3cc564..2c47061a695 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -141,6 +141,7 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_init(struct net_device *dev);
 void ip_tunnel_uninit(struct net_device *dev);
 void  ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
+struct net *ip_tunnel_get_link_net(const struct net_device *dev);
 int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 		       struct rtnl_link_ops *ops, char *devname);
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 942576e27df..6e7727f2739 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -829,6 +829,7 @@ static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
 	.fill_info	= ipgre_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
@@ -843,6 +844,7 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
 	.fill_info	= ipgre_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static int __net_init ipgre_tap_init_net(struct net *net)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index d3e44793672..2cd08280c77 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -972,6 +972,14 @@ void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_dellink);
 
+struct net *ip_tunnel_get_link_net(const struct net_device *dev)
+{
+	struct ip_tunnel *tunnel = netdev_priv(dev);
+
+	return tunnel->net;
+}
+EXPORT_SYMBOL(ip_tunnel_get_link_net);
+
 int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 				  struct rtnl_link_ops *ops, char *devname)
 {
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1a7e979e80b..94efe148181 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -531,6 +531,7 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = {
 	.dellink        = ip_tunnel_dellink,
 	.get_size	= vti_get_size,
 	.fill_info	= vti_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static int __init vti_init(void)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 40403114f00..b58d6689874 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -498,6 +498,7 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly = {
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipip_get_size,
 	.fill_info	= ipip_fill_info,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct xfrm_tunnel ipip_handler __read_mostly = {
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 13cda4c6313..9306a5ff914 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1662,6 +1662,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
 	.dellink	= ip6gre_dellink,
 	.get_size	= ip6gre_get_size,
 	.fill_info	= ip6gre_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 92b3da57198..266a264ec21 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1760,6 +1760,14 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+struct net *ip6_tnl_get_link_net(const struct net_device *dev)
+{
+	struct ip6_tnl *tunnel = netdev_priv(dev);
+
+	return tunnel->net;
+}
+EXPORT_SYMBOL(ip6_tnl_get_link_net);
+
 static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_LINK]		= { .type = NLA_U32 },
 	[IFLA_IPTUN_LOCAL]		= { .len = sizeof(struct in6_addr) },
@@ -1783,6 +1791,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = {
 	.dellink	= ip6_tnl_dellink,
 	.get_size	= ip6_tnl_get_size,
 	.fill_info	= ip6_tnl_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ace10d0b3aa..5fb9e212eca 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -1016,6 +1016,7 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = {
 	.changelink	= vti6_changelink,
 	.get_size	= vti6_get_size,
 	.fill_info	= vti6_fill_info,
+	.get_link_net	= ip6_tnl_get_link_net,
 };
 
 static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 213546bd6d5..3cc197c72b5 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1763,6 +1763,7 @@ static struct rtnl_link_ops sit_link_ops __read_mostly = {
 	.get_size	= ipip6_get_size,
 	.fill_info	= ipip6_fill_info,
 	.dellink	= ipip6_dellink,
+	.get_link_net	= ip_tunnel_get_link_net,
 };
 
 static struct xfrm_tunnel sit_handler __read_mostly = {
-- 
cgit v1.2.3-70-g09d2


From 22a5dc0e5e3e8fef804230cd73ed7b0afd4c7bae Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Sun, 18 Jan 2015 16:35:14 -0500
Subject: net: sched: Introduce connmark action

This tc action allows you to retrieve the connection tracking mark
This action has been used heavily by openwrt for a few years now.

There are known limitations currently:

doesn't work for initial packets, since we only query the ct table.
  Fine given use case is for returning packets

no implicit defrag.
  frags should be rare so fix later..

won't work for more complex tasks, e.g. lookup of other extensions
  since we have no means to store results

we still have a 2nd lookup later on via normal conntrack path.
This shouldn't break anything though since skb->nfct isn't altered.

V2:
remove unnecessary braces (Jiri)
change the action identifier to 14 (Jiri)
Fix some stylistic issues caught by checkpatch
V3:
Move module params to bottom (Cong)
Get rid of tcf_hashinfo_init and friends and conform to newer API (Cong)

Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_connmark.h        |  14 +++
 include/uapi/linux/tc_act/tc_connmark.h |  22 ++++
 net/sched/Kconfig                       |  11 ++
 net/sched/Makefile                      |   1 +
 net/sched/act_connmark.c                | 192 ++++++++++++++++++++++++++++++++
 5 files changed, 240 insertions(+)
 create mode 100644 include/net/tc_act/tc_connmark.h
 create mode 100644 include/uapi/linux/tc_act/tc_connmark.h
 create mode 100644 net/sched/act_connmark.c

(limited to 'include')

diff --git a/include/net/tc_act/tc_connmark.h b/include/net/tc_act/tc_connmark.h
new file mode 100644
index 00000000000..5c1104c2e24
--- /dev/null
+++ b/include/net/tc_act/tc_connmark.h
@@ -0,0 +1,14 @@
+#ifndef __NET_TC_CONNMARK_H
+#define __NET_TC_CONNMARK_H
+
+#include <net/act_api.h>
+
+struct tcf_connmark_info {
+	struct tcf_common common;
+	u16 zone;
+};
+
+#define to_connmark(a) \
+	container_of(a->priv, struct tcf_connmark_info, common)
+
+#endif /* __NET_TC_CONNMARK_H */
diff --git a/include/uapi/linux/tc_act/tc_connmark.h b/include/uapi/linux/tc_act/tc_connmark.h
new file mode 100644
index 00000000000..994b0971bce
--- /dev/null
+++ b/include/uapi/linux/tc_act/tc_connmark.h
@@ -0,0 +1,22 @@
+#ifndef __UAPI_TC_CONNMARK_H
+#define __UAPI_TC_CONNMARK_H
+
+#include <linux/types.h>
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_CONNMARK 14
+
+struct tc_connmark {
+	tc_gen;
+	__u16 zone;
+};
+
+enum {
+	TCA_CONNMARK_UNSPEC,
+	TCA_CONNMARK_PARMS,
+	TCA_CONNMARK_TM,
+	__TCA_CONNMARK_MAX
+};
+#define TCA_CONNMARK_MAX (__TCA_CONNMARK_MAX - 1)
+
+#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 46694355158..475e35e261e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -710,6 +710,17 @@ config NET_ACT_BPF
 	  To compile this code as a module, choose M here: the
 	  module will be called act_bpf.
 
+config NET_ACT_CONNMARK
+        tristate "Netfilter Connection Mark Retriever"
+        depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES
+        ---help---
+	  Say Y here to allow retrieving of conn mark
+
+	  If unsure, say N.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called act_connmark.
+
 config NET_CLS_IND
 	bool "Incoming device classification"
 	depends on NET_CLS_U32 || NET_CLS_FW
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 7ca2b4e7631..7ca7f4c1b8c 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_NET_ACT_SKBEDIT)	+= act_skbedit.o
 obj-$(CONFIG_NET_ACT_CSUM)	+= act_csum.o
 obj-$(CONFIG_NET_ACT_VLAN)	+= act_vlan.o
 obj-$(CONFIG_NET_ACT_BPF)	+= act_bpf.o
+obj-$(CONFIG_NET_ACT_CONNMARK)	+= act_connmark.o
 obj-$(CONFIG_NET_SCH_FIFO)	+= sch_fifo.o
 obj-$(CONFIG_NET_SCH_CBQ)	+= sch_cbq.o
 obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
new file mode 100644
index 00000000000..8e472518f9f
--- /dev/null
+++ b/net/sched/act_connmark.c
@@ -0,0 +1,192 @@
+/*
+ * net/sched/act_connmark.c  netfilter connmark retriever action
+ * skb mark is over-written
+ *
+ * Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+*/
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/pkt_cls.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <net/act_api.h>
+#include <uapi/linux/tc_act/tc_connmark.h>
+#include <net/tc_act/tc_connmark.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+
+#define CONNMARK_TAB_MASK     3
+
+static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
+			struct tcf_result *res)
+{
+	const struct nf_conntrack_tuple_hash *thash;
+	struct nf_conntrack_tuple tuple;
+	enum ip_conntrack_info ctinfo;
+	struct tcf_connmark_info *ca = a->priv;
+	struct nf_conn *c;
+	int proto;
+
+	spin_lock(&ca->tcf_lock);
+	ca->tcf_tm.lastuse = jiffies;
+	bstats_update(&ca->tcf_bstats, skb);
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		if (skb->len < sizeof(struct iphdr))
+			goto out;
+
+		proto = NFPROTO_IPV4;
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		if (skb->len < sizeof(struct ipv6hdr))
+			goto out;
+
+		proto = NFPROTO_IPV6;
+	} else {
+		goto out;
+	}
+
+	c = nf_ct_get(skb, &ctinfo);
+	if (c) {
+		skb->mark = c->mark;
+		/* using overlimits stats to count how many packets marked */
+		ca->tcf_qstats.overlimits++;
+		nf_ct_put(c);
+		goto out;
+	}
+
+	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
+			       proto, &tuple))
+		goto out;
+
+	thash = nf_conntrack_find_get(dev_net(skb->dev), ca->zone, &tuple);
+	if (!thash)
+		goto out;
+
+	c = nf_ct_tuplehash_to_ctrack(thash);
+	/* using overlimits stats to count how many packets marked */
+	ca->tcf_qstats.overlimits++;
+	skb->mark = c->mark;
+	nf_ct_put(c);
+
+out:
+	skb->nfct = NULL;
+	spin_unlock(&ca->tcf_lock);
+	return ca->tcf_action;
+}
+
+static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
+	[TCA_CONNMARK_PARMS] = { .len = sizeof(struct tc_connmark) },
+};
+
+static int tcf_connmark_init(struct net *net, struct nlattr *nla,
+			     struct nlattr *est, struct tc_action *a,
+			     int ovr, int bind)
+{
+	struct nlattr *tb[TCA_CONNMARK_MAX + 1];
+	struct tcf_connmark_info *ci;
+	struct tc_connmark *parm;
+	int ret = 0;
+
+	if (!nla)
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy);
+	if (ret < 0)
+		return ret;
+
+	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
+
+	if (!tcf_hash_check(parm->index, a, bind)) {
+		ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), bind);
+		if (ret)
+			return ret;
+
+		ci = to_connmark(a);
+		ci->tcf_action = parm->action;
+		ci->zone = parm->zone;
+
+		tcf_hash_insert(a);
+		ret = ACT_P_CREATED;
+	} else {
+		ci = to_connmark(a);
+		if (bind)
+			return 0;
+		tcf_hash_release(a, bind);
+		if (!ovr)
+			return -EEXIST;
+		/* replacing action and zone */
+		ci->tcf_action = parm->action;
+		ci->zone = parm->zone;
+	}
+
+	return ret;
+}
+
+static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
+				    int bind, int ref)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tcf_connmark_info *ci = a->priv;
+
+	struct tc_connmark opt = {
+		.index   = ci->tcf_index,
+		.refcnt  = ci->tcf_refcnt - ref,
+		.bindcnt = ci->tcf_bindcnt - bind,
+		.action  = ci->tcf_action,
+		.zone   = ci->zone,
+	};
+	struct tcf_t t;
+
+	if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	t.install = jiffies_to_clock_t(jiffies - ci->tcf_tm.install);
+	t.lastuse = jiffies_to_clock_t(jiffies - ci->tcf_tm.lastuse);
+	t.expires = jiffies_to_clock_t(ci->tcf_tm.expires);
+	if (nla_put(skb, TCA_CONNMARK_TM, sizeof(t), &t))
+		goto nla_put_failure;
+
+	return skb->len;
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
+static struct tc_action_ops act_connmark_ops = {
+	.kind		=	"connmark",
+	.type		=	TCA_ACT_CONNMARK,
+	.owner		=	THIS_MODULE,
+	.act		=	tcf_connmark,
+	.dump		=	tcf_connmark_dump,
+	.init		=	tcf_connmark_init,
+};
+
+static int __init connmark_init_module(void)
+{
+	return tcf_register_action(&act_connmark_ops, CONNMARK_TAB_MASK);
+}
+
+static void __exit connmark_cleanup_module(void)
+{
+	tcf_unregister_action(&act_connmark_ops);
+}
+
+module_init(connmark_init_module);
+module_exit(connmark_cleanup_module);
+MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
+MODULE_DESCRIPTION("Connection tracking mark restoring");
+MODULE_LICENSE("GPL");
+
-- 
cgit v1.2.3-70-g09d2


From d453cded05ee219b77815ea194dc36efa5398bca Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Tue, 20 Jan 2015 09:07:04 +1030
Subject: module_arch_freeing_init(): new hook for archs before
 module->module_init freed.

Archs have been abusing module_free() to clean up their arch-specific
allocations.  Since module_free() is also (ab)used by BPF and trace code,
let's keep it to simple allocations, and provide a hook called before
that.

This means that avr32, ia64, parisc and s390 no longer need to implement
their own module_free() at all.  avr32 doesn't need module_finalize()
either.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: Helge Deller <deller@gmx.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-parisc@vger.kernel.org
Cc: linux-s390@vger.kernel.org
---
 arch/avr32/kernel/module.c   | 13 +------------
 arch/ia64/kernel/module.c    |  6 ++----
 arch/parisc/kernel/module.c  |  6 +-----
 arch/s390/kernel/module.c    | 10 +++-------
 arch/tile/kernel/module.c    |  2 +-
 include/linux/moduleloader.h |  2 ++
 kernel/module.c              |  7 +++++++
 7 files changed, 17 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c
index 2c941290802..164efa009e5 100644
--- a/arch/avr32/kernel/module.c
+++ b/arch/avr32/kernel/module.c
@@ -19,12 +19,10 @@
 #include <linux/moduleloader.h>
 #include <linux/vmalloc.h>
 
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
 	vfree(mod->arch.syminfo);
 	mod->arch.syminfo = NULL;
-
-	vfree(module_region);
 }
 
 static inline int check_rela(Elf32_Rela *rela, struct module *module,
@@ -291,12 +289,3 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
 
 	return ret;
 }
-
-int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
-		    struct module *module)
-{
-	vfree(module->arch.syminfo);
-	module->arch.syminfo = NULL;
-
-	return 0;
-}
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index 24603be24c1..29754aae517 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -305,14 +305,12 @@ plt_target (struct plt_entry *plt)
 #endif /* !USE_BRL */
 
 void
-module_free (struct module *mod, void *module_region)
+module_arch_freeing_init (struct module *mod)
 {
-	if (mod && mod->arch.init_unw_table &&
-	    module_region == mod->module_init) {
+	if (mod->arch.init_unw_table) {
 		unw_remove_unwind_table(mod->arch.init_unw_table);
 		mod->arch.init_unw_table = NULL;
 	}
-	vfree(module_region);
 }
 
 /* Have we already seen one of these relocations? */
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index 50dfafc3f2c..5822e8e200e 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -298,14 +298,10 @@ static inline unsigned long count_stubs(const Elf_Rela *rela, unsigned long n)
 }
 #endif
 
-
-/* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
 	kfree(mod->arch.section);
 	mod->arch.section = NULL;
-
-	vfree(module_region);
 }
 
 /* Additional bytes needed in front of individual sections */
diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c
index b89b59158b9..409d152585b 100644
--- a/arch/s390/kernel/module.c
+++ b/arch/s390/kernel/module.c
@@ -55,14 +55,10 @@ void *module_alloc(unsigned long size)
 }
 #endif
 
-/* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_arch_freeing_init(struct module *mod)
 {
-	if (mod) {
-		vfree(mod->arch.syminfo);
-		mod->arch.syminfo = NULL;
-	}
-	vfree(module_region);
+	vfree(mod->arch.syminfo);
+	mod->arch.syminfo = NULL;
 }
 
 static void check_rela(Elf_Rela *rela, struct module *me)
diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c
index 96447c9160a..62a597e810d 100644
--- a/arch/tile/kernel/module.c
+++ b/arch/tile/kernel/module.c
@@ -83,7 +83,7 @@ void module_free(struct module *mod, void *module_region)
 		     0, 0, 0, NULL, NULL, 0);
 
 	/*
-	 * FIXME: If module_region == mod->module_init, trim exception
+	 * FIXME: Add module_arch_freeing_init to trim exception
 	 * table entries.
 	 */
 }
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 7eeb9bbfb81..054eac85309 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -82,4 +82,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 /* Any cleanup needed when module leaves. */
 void module_arch_cleanup(struct module *mod);
 
+/* Any cleanup before freeing mod->module_init */
+void module_arch_freeing_init(struct module *mod);
 #endif
diff --git a/kernel/module.c b/kernel/module.c
index 3965511ae13..68be0b1f9e7 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1804,6 +1804,10 @@ void __weak module_arch_cleanup(struct module *mod)
 {
 }
 
+void __weak module_arch_freeing_init(struct module *mod)
+{
+}
+
 /* Free a module, remove from lists, etc. */
 static void free_module(struct module *mod)
 {
@@ -1841,6 +1845,7 @@ static void free_module(struct module *mod)
 
 	/* This may be NULL, but that's OK */
 	unset_module_init_ro_nx(mod);
+	module_arch_freeing_init(mod);
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
 	percpu_modfree(mod);
@@ -2930,6 +2935,7 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 static void module_deallocate(struct module *mod, struct load_info *info)
 {
 	percpu_modfree(mod);
+	module_arch_freeing_init(mod);
 	module_free(mod, mod->module_init);
 	module_free(mod, mod->module_core);
 }
@@ -3055,6 +3061,7 @@ static int do_init_module(struct module *mod)
 	mod->strtab = mod->core_strtab;
 #endif
 	unset_module_init_ro_nx(mod);
+	module_arch_freeing_init(mod);
 	module_free(mod, mod->module_init);
 	mod->module_init = NULL;
 	mod->init_size = 0;
-- 
cgit v1.2.3-70-g09d2


From be1f221c0445a4157d177197c236f888d3581914 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Tue, 20 Jan 2015 09:07:05 +1030
Subject: module: remove mod arg from module_free, rename module_memfree().

Nothing needs the module pointer any more, and the next patch will
call it from RCU, where the module itself might no longer exist.
Removing the arg is the safest approach.

This just codifies the use of the module_alloc/module_free pattern
which ftrace and bpf use.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Mikael Starvik <starvik@axis.com>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Ley Foon Tan <lftan@altera.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: x86@kernel.org
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: linux-cris-kernel@axis.com
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: nios2-dev@lists.rocketboards.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: sparclinux@vger.kernel.org
Cc: netdev@vger.kernel.org
---
 arch/cris/kernel/module.c       |  2 +-
 arch/mips/net/bpf_jit.c         |  2 +-
 arch/nios2/kernel/module.c      |  2 +-
 arch/powerpc/net/bpf_jit_comp.c |  2 +-
 arch/sparc/net/bpf_jit_comp.c   |  4 ++--
 arch/tile/kernel/module.c       |  2 +-
 arch/x86/kernel/ftrace.c        |  2 +-
 include/linux/moduleloader.h    |  2 +-
 kernel/bpf/core.c               |  2 +-
 kernel/kprobes.c                |  2 +-
 kernel/module.c                 | 14 +++++++-------
 11 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/cris/kernel/module.c b/arch/cris/kernel/module.c
index 51123f985eb..af04cb6b6dc 100644
--- a/arch/cris/kernel/module.c
+++ b/arch/cris/kernel/module.c
@@ -36,7 +36,7 @@ void *module_alloc(unsigned long size)
 }
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	kfree(module_region);
 }
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 9fd6834a217..5d6139390bf 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -1388,7 +1388,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/nios2/kernel/module.c b/arch/nios2/kernel/module.c
index cc924a38f22..e2e3f13f98d 100644
--- a/arch/nios2/kernel/module.c
+++ b/arch/nios2/kernel/module.c
@@ -36,7 +36,7 @@ void *module_alloc(unsigned long size)
 }
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	kfree(module_region);
 }
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 1ca125b9c22..d1916b577f2 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -699,7 +699,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index f33e7c7a3bf..7931eeeb649 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -776,7 +776,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 				if (unlikely(proglen + ilen > oldproglen)) {
 					pr_err("bpb_jit_compile fatal error\n");
 					kfree(addrs);
-					module_free(NULL, image);
+					module_memfree(image);
 					return;
 				}
 				memcpy(image + proglen, temp, ilen);
@@ -822,7 +822,7 @@ out:
 void bpf_jit_free(struct bpf_prog *fp)
 {
 	if (fp->jited)
-		module_free(NULL, fp->bpf_func);
+		module_memfree(fp->bpf_func);
 
 	bpf_prog_unlock_free(fp);
 }
diff --git a/arch/tile/kernel/module.c b/arch/tile/kernel/module.c
index 62a597e810d..2305084c9b9 100644
--- a/arch/tile/kernel/module.c
+++ b/arch/tile/kernel/module.c
@@ -74,7 +74,7 @@ error:
 
 
 /* Free memory returned from module_alloc */
-void module_free(struct module *mod, void *module_region)
+void module_memfree(void *module_region)
 {
 	vfree(module_region);
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 2142376dc8c..8b7b0a51e74 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size)
 }
 static inline void tramp_free(void *tramp)
 {
-	module_free(NULL, tramp);
+	module_memfree(tramp);
 }
 #else
 /* Trampolines can only be created if modules are supported */
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 054eac85309..f7556261fe3 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -26,7 +26,7 @@ unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section);
 void *module_alloc(unsigned long size);
 
 /* Free memory returned from module_alloc. */
-void module_free(struct module *mod, void *module_region);
+void module_memfree(void *module_region);
 
 /*
  * Apply the given relocation to the (simplified) ELF.  Return -error
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6594e457a2..a64e7a207d2 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -163,7 +163,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 
 void bpf_jit_binary_free(struct bpf_binary_header *hdr)
 {
-	module_free(NULL, hdr);
+	module_memfree(hdr);
 }
 #endif /* CONFIG_BPF_JIT */
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 06f58309fed..ee619929cf9 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -127,7 +127,7 @@ static void *alloc_insn_page(void)
 
 static void free_insn_page(void *page)
 {
-	module_free(NULL, page);
+	module_memfree(page);
 }
 
 struct kprobe_insn_cache kprobe_insn_slots = {
diff --git a/kernel/module.c b/kernel/module.c
index 68be0b1f9e7..1f85fd5c89d 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1795,7 +1795,7 @@ static void unset_module_core_ro_nx(struct module *mod) { }
 static void unset_module_init_ro_nx(struct module *mod) { }
 #endif
 
-void __weak module_free(struct module *mod, void *module_region)
+void __weak module_memfree(void *module_region)
 {
 	vfree(module_region);
 }
@@ -1846,7 +1846,7 @@ static void free_module(struct module *mod)
 	/* This may be NULL, but that's OK */
 	unset_module_init_ro_nx(mod);
 	module_arch_freeing_init(mod);
-	module_free(mod, mod->module_init);
+	module_memfree(mod->module_init);
 	kfree(mod->args);
 	percpu_modfree(mod);
 
@@ -1855,7 +1855,7 @@ static void free_module(struct module *mod)
 
 	/* Finally, free the core (containing the module structure) */
 	unset_module_core_ro_nx(mod);
-	module_free(mod, mod->module_core);
+	module_memfree(mod->module_core);
 
 #ifdef CONFIG_MPU
 	update_protections(current->mm);
@@ -2790,7 +2790,7 @@ static int move_module(struct module *mod, struct load_info *info)
 		 */
 		kmemleak_ignore(ptr);
 		if (!ptr) {
-			module_free(mod, mod->module_core);
+			module_memfree(mod->module_core);
 			return -ENOMEM;
 		}
 		memset(ptr, 0, mod->init_size);
@@ -2936,8 +2936,8 @@ static void module_deallocate(struct module *mod, struct load_info *info)
 {
 	percpu_modfree(mod);
 	module_arch_freeing_init(mod);
-	module_free(mod, mod->module_init);
-	module_free(mod, mod->module_core);
+	module_memfree(mod->module_init);
+	module_memfree(mod->module_core);
 }
 
 int __weak module_finalize(const Elf_Ehdr *hdr,
@@ -3062,7 +3062,7 @@ static int do_init_module(struct module *mod)
 #endif
 	unset_module_init_ro_nx(mod);
 	module_arch_freeing_init(mod);
-	module_free(mod, mod->module_init);
+	module_memfree(mod->module_init);
 	mod->module_init = NULL;
 	mod->init_size = 0;
 	mod->init_ro_size = 0;
-- 
cgit v1.2.3-70-g09d2


From 67d0d04a762db4bd610fd628ad683b5d7dc905e7 Mon Sep 17 00:00:00 2001
From: Vincent Yang <vincent.yang.fujitsu@gmail.com>
Date: Tue, 20 Jan 2015 16:05:16 +0800
Subject: mmc: sdhci: add a quirk for tuning work around

This patch defines a quirk for tuning work
around for some sdhci host controller. It sets
both SDHCI_CTRL_EXEC_TUNING and SDHCI_CTRL_TUNED_CLK
for tuning.
It is a preparation and will be used by Fujitsu
SDHCI controller f_sdh30 driver.

Signed-off-by: Vincent Yang <Vincent.Yang@tw.fujitsu.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 2 ++
 include/linux/mmc/sdhci.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 3e4fe967d7e..a3ecd20e551 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1961,6 +1961,8 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 
 	ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
 	ctrl |= SDHCI_CTRL_EXEC_TUNING;
+	if (host->quirks2 & SDHCI_QUIRK2_TUNING_WORK_AROUND)
+		ctrl |= SDHCI_CTRL_TUNED_CLK;
 	sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
 
 	/*
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index cb8b94ff6a2..933b897ca09 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -111,6 +111,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD	(1<<10)
 /* Capability register bit-63 indicates HS400 support */
 #define SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400		(1<<11)
+/* forced tuned clock */
+#define SDHCI_QUIRK2_TUNING_WORK_AROUND			(1<<12)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
-- 
cgit v1.2.3-70-g09d2


From d3fc5d71ac4dfd28a66689cfd1eea84c4dba8bde Mon Sep 17 00:00:00 2001
From: Vincent Yang <vincent.yang.fujitsu@gmail.com>
Date: Tue, 20 Jan 2015 16:05:17 +0800
Subject: mmc: sdhci: add a quirk for single block transactions

This patch defines a quirk to disable the block count
for single block transactions.
It is a preparation and will be used by Fujitsu
SDHCI controller f_sdh30 driver.

Signed-off-by: Vincent Yang <Vincent.Yang@tw.fujitsu.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.c  | 8 +++++---
 include/linux/mmc/sdhci.h | 2 ++
 2 files changed, 7 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index a3ecd20e551..c9881ca131d 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -904,7 +904,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
 static void sdhci_set_transfer_mode(struct sdhci_host *host,
 	struct mmc_command *cmd)
 {
-	u16 mode;
+	u16 mode = 0;
 	struct mmc_data *data = cmd->data;
 
 	if (data == NULL) {
@@ -922,9 +922,11 @@ static void sdhci_set_transfer_mode(struct sdhci_host *host,
 
 	WARN_ON(!host->data);
 
-	mode = SDHCI_TRNS_BLK_CNT_EN;
+	if (!(host->quirks2 & SDHCI_QUIRK2_SUPPORT_SINGLE))
+		mode = SDHCI_TRNS_BLK_CNT_EN;
+
 	if (mmc_op_multi(cmd->opcode) || data->blocks > 1) {
-		mode |= SDHCI_TRNS_MULTI;
+		mode = SDHCI_TRNS_BLK_CNT_EN | SDHCI_TRNS_MULTI;
 		/*
 		 * If we are sending CMD23, CMD12 never gets sent
 		 * on successful completion (so no Auto-CMD12).
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 933b897ca09..c3e3db19673 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -113,6 +113,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400		(1<<11)
 /* forced tuned clock */
 #define SDHCI_QUIRK2_TUNING_WORK_AROUND			(1<<12)
+/* disable the block count for single block transactions */
+#define SDHCI_QUIRK2_SUPPORT_SINGLE			(1<<13)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
-- 
cgit v1.2.3-70-g09d2


From 94b110aff8679b14f46fd6653ea87b42fe1555be Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:57:22 +0000
Subject: mmc: tmio: add tmio_mmc_host_alloc/free()

Current tmio_mmc driver is using tmio_mmc_data for driver/platform
specific data/callback, and it is needed for tmio_mmc_host_probe()
function. Because of this style, include/linux/mfd/tmio.h header has
tmio driver/framework specific data which is not needed from platform.

This patch adds new tmio_mmc_host_alloc/free() as cleanup preparation.
tmio driver specific data/callback will be implemented in tmio_mmc_host,
and platform specific data/callback will be implemented in tmio_mmc_data
in this cleanup.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 14 +++++++++---
 drivers/mmc/host/tmio_mmc.c       | 10 +++++++--
 drivers/mmc/host/tmio_mmc.h       |  5 +++--
 drivers/mmc/host/tmio_mmc_pio.c   | 45 +++++++++++++++++++++++++--------------
 include/linux/mfd/tmio.h          |  1 -
 5 files changed, 51 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 00c8ebdf8ec..cf062c4d87a 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -113,7 +113,7 @@ static int sh_mobile_sdhi_wait_idle(struct tmio_mmc_host *host)
 		udelay(1);
 
 	if (!timeout) {
-		dev_warn(host->pdata->dev, "timeout waiting for SD bus idle\n");
+		dev_warn(&host->pdev->dev, "timeout waiting for SD bus idle\n");
 		return -EBUSY;
 	}
 
@@ -207,6 +207,12 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		goto eclkget;
 	}
 
+	host = tmio_mmc_host_alloc(pdev);
+	if (!host) {
+		ret = -ENOMEM;
+		goto eprobe;
+	}
+
 	mmc_data->clk_enable = sh_mobile_sdhi_clk_enable;
 	mmc_data->clk_disable = sh_mobile_sdhi_clk_disable;
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
@@ -274,9 +280,9 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	/* SD control register space size is 0x100, 0x200 for bus_shift=1 */
 	mmc_data->bus_shift = resource_size(res) >> 9;
 
-	ret = tmio_mmc_host_probe(&host, pdev, mmc_data);
+	ret = tmio_mmc_host_probe(host, mmc_data);
 	if (ret < 0)
-		goto eprobe;
+		goto efree;
 
 	/*
 	 * FIXME:
@@ -351,6 +357,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 
 eirq:
 	tmio_mmc_host_remove(host);
+efree:
+	tmio_mmc_host_free(host);
 eprobe:
 eclkget:
 	if (p && p->cleanup)
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index 2ca0afaab79..a7c2e459187 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -92,10 +92,14 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 	pdata->bus_shift = resource_size(res) >> 10;
 	pdata->flags |= TMIO_MMC_HAVE_HIGH_REG;
 
-	ret = tmio_mmc_host_probe(&host, pdev, pdata);
-	if (ret)
+	host = tmio_mmc_host_alloc(pdev);
+	if (!host)
 		goto cell_disable;
 
+	ret = tmio_mmc_host_probe(host, pdata);
+	if (ret)
+		goto host_free;
+
 	ret = request_irq(irq, tmio_mmc_irq, IRQF_TRIGGER_FALLING,
 				dev_name(&pdev->dev), host);
 	if (ret)
@@ -108,6 +112,8 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 
 host_remove:
 	tmio_mmc_host_remove(host);
+host_free:
+	tmio_mmc_host_free(host);
 cell_disable:
 	if (cell->disable)
 		cell->disable(pdev);
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index a34ecbe1c1a..60d6747f0df 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -85,8 +85,9 @@ struct tmio_mmc_host {
 	bool			sdio_irq_enabled;
 };
 
-int tmio_mmc_host_probe(struct tmio_mmc_host **host,
-			struct platform_device *pdev,
+struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev);
+void tmio_mmc_host_free(struct tmio_mmc_host *host);
+int tmio_mmc_host_probe(struct tmio_mmc_host *host,
 			struct tmio_mmc_data *pdata);
 void tmio_mmc_host_remove(struct tmio_mmc_host *host);
 void tmio_mmc_do_data_irq(struct tmio_mmc_host *host);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 250bf8c9f99..396be0e95a9 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -1054,12 +1054,37 @@ static void tmio_mmc_of_parse(struct platform_device *pdev,
 		pdata->flags |= TMIO_MMC_WRPROTECT_DISABLE;
 }
 
-int tmio_mmc_host_probe(struct tmio_mmc_host **host,
-				  struct platform_device *pdev,
-				  struct tmio_mmc_data *pdata)
+struct tmio_mmc_host*
+tmio_mmc_host_alloc(struct platform_device *pdev)
 {
-	struct tmio_mmc_host *_host;
+	struct tmio_mmc_host *host;
 	struct mmc_host *mmc;
+
+	mmc = mmc_alloc_host(sizeof(struct tmio_mmc_host), &pdev->dev);
+	if (!mmc)
+		return NULL;
+
+	host = mmc_priv(mmc);
+	host->mmc = mmc;
+	host->pdev = pdev;
+
+	return host;
+}
+EXPORT_SYMBOL(tmio_mmc_host_alloc);
+
+void tmio_mmc_host_free(struct tmio_mmc_host *host)
+{
+	mmc_free_host(host->mmc);
+
+	host->mmc = NULL;
+}
+EXPORT_SYMBOL(tmio_mmc_host_free);
+
+int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
+			struct tmio_mmc_data *pdata)
+{
+	struct platform_device *pdev = _host->pdev;
+	struct mmc_host *mmc = _host->mmc;
 	struct resource *res_ctl;
 	int ret;
 	u32 irq_mask = TMIO_MASK_CMD;
@@ -1073,19 +1098,11 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host,
 	if (!res_ctl)
 		return -EINVAL;
 
-	mmc = mmc_alloc_host(sizeof(struct tmio_mmc_host), &pdev->dev);
-	if (!mmc)
-		return -ENOMEM;
-
 	ret = mmc_of_parse(mmc);
 	if (ret < 0)
 		goto host_free;
 
-	pdata->dev = &pdev->dev;
-	_host = mmc_priv(mmc);
 	_host->pdata = pdata;
-	_host->mmc = mmc;
-	_host->pdev = pdev;
 	platform_set_drvdata(pdev, mmc);
 
 	_host->set_pwr = pdata->set_pwr;
@@ -1192,12 +1209,9 @@ int tmio_mmc_host_probe(struct tmio_mmc_host **host,
 		mmc_gpiod_request_cd_irq(mmc);
 	}
 
-	*host = _host;
-
 	return 0;
 
 host_free:
-	mmc_free_host(mmc);
 
 	return ret;
 }
@@ -1222,7 +1236,6 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 	pm_runtime_disable(&pdev->dev);
 
 	iounmap(host->ctl);
-	mmc_free_host(mmc);
 }
 EXPORT_SYMBOL(tmio_mmc_host_remove);
 
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 57388171610..c7d9af042d0 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -135,7 +135,6 @@ struct tmio_mmc_data {
 	unsigned long			bus_shift;
 	u32				ocr_mask;	/* available voltages */
 	struct tmio_mmc_dma		*dma;
-	struct device			*dev;
 	unsigned int			cd_gpio;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
-- 
cgit v1.2.3-70-g09d2


From 7ecc09bab1e856e6730a4dd8a3bc1c28bb6ab3be Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:57:33 +0000
Subject: mmc: tmio: tmio_mmc_host has .dma

Current .dma is implemented under tmio_mmc_data.
It goes to tmio_mmc_host by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c |  4 ++--
 drivers/mmc/host/tmio_mmc.h       | 11 +++++++++++
 drivers/mmc/host/tmio_mmc_dma.c   | 24 +++++++++++-------------
 include/linux/mfd/tmio.h          | 11 -----------
 4 files changed, 24 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index cf062c4d87a..288e78d2c7a 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -213,6 +213,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		goto eprobe;
 	}
 
+	host->dma		= dma_priv;
+
 	mmc_data->clk_enable = sh_mobile_sdhi_clk_enable;
 	mmc_data->clk_disable = sh_mobile_sdhi_clk_disable;
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
@@ -241,8 +243,6 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	dma_priv->alignment_shift = 1; /* 2-byte alignment */
 	dma_priv->filter = shdma_chan_filter;
 
-	mmc_data->dma = dma_priv;
-
 	/*
 	 * All SDHI blocks support 2-byte and larger block sizes in 4-bit
 	 * bus width mode.
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 60d6747f0df..49a2559ff48 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -40,6 +40,16 @@
 
 struct tmio_mmc_data;
 
+struct tmio_mmc_dma {
+	void *chan_priv_tx;
+	void *chan_priv_rx;
+	int slave_id_tx;
+	int slave_id_rx;
+	int alignment_shift;
+	dma_addr_t dma_rx_offset;
+	bool (*filter)(struct dma_chan *chan, void *arg);
+};
+
 struct tmio_mmc_host {
 	void __iomem *ctl;
 	struct mmc_command      *cmd;
@@ -59,6 +69,7 @@ struct tmio_mmc_host {
 
 	struct platform_device *pdev;
 	struct tmio_mmc_data *pdata;
+	struct tmio_mmc_dma	*dma;
 
 	/* DMA support */
 	bool			force_pio;
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index 7d077388b9e..6c214d60bbb 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -49,11 +49,10 @@ static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host)
 	struct scatterlist *sg = host->sg_ptr, *sg_tmp;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_rx;
-	struct tmio_mmc_data *pdata = host->pdata;
 	dma_cookie_t cookie;
 	int ret, i;
 	bool aligned = true, multiple = true;
-	unsigned int align = (1 << pdata->dma->alignment_shift) - 1;
+	unsigned int align = (1 << host->dma->alignment_shift) - 1;
 
 	for_each_sg(sg, sg_tmp, host->sg_len, i) {
 		if (sg_tmp->offset & align)
@@ -126,11 +125,10 @@ static void tmio_mmc_start_dma_tx(struct tmio_mmc_host *host)
 	struct scatterlist *sg = host->sg_ptr, *sg_tmp;
 	struct dma_async_tx_descriptor *desc = NULL;
 	struct dma_chan *chan = host->chan_tx;
-	struct tmio_mmc_data *pdata = host->pdata;
 	dma_cookie_t cookie;
 	int ret, i;
 	bool aligned = true, multiple = true;
-	unsigned int align = (1 << pdata->dma->alignment_shift) - 1;
+	unsigned int align = (1 << host->dma->alignment_shift) - 1;
 
 	for_each_sg(sg, sg_tmp, host->sg_len, i) {
 		if (sg_tmp->offset & align)
@@ -262,8 +260,8 @@ out:
 void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdata)
 {
 	/* We can only either use DMA for both Tx and Rx or not use it at all */
-	if (!pdata->dma || (!host->pdev->dev.of_node &&
-		(!pdata->dma->chan_priv_tx || !pdata->dma->chan_priv_rx)))
+	if (!host->dma || (!host->pdev->dev.of_node &&
+		(!host->dma->chan_priv_tx || !host->dma->chan_priv_rx)))
 		return;
 
 	if (!host->chan_tx && !host->chan_rx) {
@@ -280,7 +278,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		dma_cap_set(DMA_SLAVE, mask);
 
 		host->chan_tx = dma_request_slave_channel_compat(mask,
-					pdata->dma->filter, pdata->dma->chan_priv_tx,
+					host->dma->filter, host->dma->chan_priv_tx,
 					&host->pdev->dev, "tx");
 		dev_dbg(&host->pdev->dev, "%s: TX: got channel %p\n", __func__,
 			host->chan_tx);
@@ -288,8 +286,8 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		if (!host->chan_tx)
 			return;
 
-		if (pdata->dma->chan_priv_tx)
-			cfg.slave_id = pdata->dma->slave_id_tx;
+		if (host->dma->chan_priv_tx)
+			cfg.slave_id = host->dma->slave_id_tx;
 		cfg.direction = DMA_MEM_TO_DEV;
 		cfg.dst_addr = res->start + (CTL_SD_DATA_PORT << host->pdata->bus_shift);
 		cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
@@ -299,7 +297,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 			goto ecfgtx;
 
 		host->chan_rx = dma_request_slave_channel_compat(mask,
-					pdata->dma->filter, pdata->dma->chan_priv_rx,
+					host->dma->filter, host->dma->chan_priv_rx,
 					&host->pdev->dev, "rx");
 		dev_dbg(&host->pdev->dev, "%s: RX: got channel %p\n", __func__,
 			host->chan_rx);
@@ -307,10 +305,10 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		if (!host->chan_rx)
 			goto ereqrx;
 
-		if (pdata->dma->chan_priv_rx)
-			cfg.slave_id = pdata->dma->slave_id_rx;
+		if (host->dma->chan_priv_rx)
+			cfg.slave_id = host->dma->slave_id_rx;
 		cfg.direction = DMA_DEV_TO_MEM;
-		cfg.src_addr = cfg.dst_addr + pdata->dma->dma_rx_offset;
+		cfg.src_addr = cfg.dst_addr + host->dma->dma_rx_offset;
 		cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		cfg.dst_addr = 0;
 		ret = dmaengine_slave_config(host->chan_rx, &cfg);
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index c7d9af042d0..8d708c7cf68 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -112,16 +112,6 @@ void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state);
 
 struct dma_chan;
 
-struct tmio_mmc_dma {
-	void *chan_priv_tx;
-	void *chan_priv_rx;
-	int slave_id_tx;
-	int slave_id_rx;
-	int alignment_shift;
-	dma_addr_t dma_rx_offset;
-	bool (*filter)(struct dma_chan *chan, void *arg);
-};
-
 struct tmio_mmc_host;
 
 /*
@@ -134,7 +124,6 @@ struct tmio_mmc_data {
 	unsigned long			flags;
 	unsigned long			bus_shift;
 	u32				ocr_mask;	/* available voltages */
-	struct tmio_mmc_dma		*dma;
 	unsigned int			cd_gpio;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
-- 
cgit v1.2.3-70-g09d2


From dfe9a229e0a66b6a00439cea2885ad3b5d3e0840 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:57:42 +0000
Subject: mmc: tmio: tmio_mmc_host has .write16_hook

Current .write16_hook is implemented under tmio_mmc_data.
It goes to tmio_mmc_host by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 2 +-
 drivers/mmc/host/tmio_mmc.h       | 4 +++-
 drivers/mmc/host/tmio_mmc_pio.c   | 2 +-
 include/linux/mfd/tmio.h          | 3 ---
 4 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 288e78d2c7a..77ff0620912 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -214,11 +214,11 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	}
 
 	host->dma		= dma_priv;
+	host->write16_hook	= sh_mobile_sdhi_write16_hook;
 
 	mmc_data->clk_enable = sh_mobile_sdhi_clk_enable;
 	mmc_data->clk_disable = sh_mobile_sdhi_clk_disable;
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
-	mmc_data->write16_hook = sh_mobile_sdhi_write16_hook;
 	mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk;
 	if (p) {
 		mmc_data->flags = p->tmio_flags;
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 49a2559ff48..3fa96b11f76 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -94,6 +94,8 @@ struct tmio_mmc_host {
 	struct mutex		ios_lock;	/* protect set_ios() context */
 	bool			native_hotplug;
 	bool			sdio_irq_enabled;
+
+	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
 };
 
 struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev);
@@ -183,7 +185,7 @@ static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val
 	/* If there is a hook and it returns non-zero then there
 	 * is an error and the write should be skipped
 	 */
-	if (host->pdata->write16_hook && host->pdata->write16_hook(host, addr))
+	if (host->write16_hook && host->write16_hook(host, addr))
 		return;
 	writew(val, host->ctl + (addr << host->pdata->bus_shift));
 }
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 396be0e95a9..58f4e47aac8 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -1092,7 +1092,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	tmio_mmc_of_parse(pdev, pdata);
 
 	if (!(pdata->flags & TMIO_MMC_HAS_IDLE_WAIT))
-		pdata->write16_hook = NULL;
+		_host->write16_hook = NULL;
 
 	res_ctl = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res_ctl)
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 8d708c7cf68..0872ca1e5dc 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -112,8 +112,6 @@ void tmio_core_mmc_clk_div(void __iomem *cnf, int shift, int state);
 
 struct dma_chan;
 
-struct tmio_mmc_host;
-
 /*
  * data for the MMC controller
  */
@@ -127,7 +125,6 @@ struct tmio_mmc_data {
 	unsigned int			cd_gpio;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
-	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
 	/* clock management callbacks */
 	int (*clk_enable)(struct platform_device *pdev, unsigned int *f);
 	void (*clk_disable)(struct platform_device *pdev);
-- 
cgit v1.2.3-70-g09d2


From 4fe2ec57a15f98c232536cf04e7c139d830955d4 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:57:52 +0000
Subject: mmc: tmio: tmio_mmc_host has .clk_enable

Current .clk_enable is implemented under tmio_mmc_data.
It goes to tmio_mmc_host by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 2 +-
 drivers/mmc/host/tmio_mmc.h       | 1 +
 drivers/mmc/host/tmio_mmc_pio.c   | 5 ++---
 include/linux/mfd/tmio.h          | 1 -
 4 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 77ff0620912..87af77dd660 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -215,8 +215,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 
 	host->dma		= dma_priv;
 	host->write16_hook	= sh_mobile_sdhi_write16_hook;
+	host->clk_enable	= sh_mobile_sdhi_clk_enable;
 
-	mmc_data->clk_enable = sh_mobile_sdhi_clk_enable;
 	mmc_data->clk_disable = sh_mobile_sdhi_clk_disable;
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
 	mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk;
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 3fa96b11f76..5cd298665b9 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -96,6 +96,7 @@ struct tmio_mmc_host {
 	bool			sdio_irq_enabled;
 
 	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
+	int (*clk_enable)(struct platform_device *pdev, unsigned int *f);
 };
 
 struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 58f4e47aac8..38bcf0ca31c 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -835,13 +835,12 @@ fail:
 static int tmio_mmc_clk_update(struct tmio_mmc_host *host)
 {
 	struct mmc_host *mmc = host->mmc;
-	struct tmio_mmc_data *pdata = host->pdata;
 	int ret;
 
-	if (!pdata->clk_enable)
+	if (!host->clk_enable)
 		return -ENOTSUPP;
 
-	ret = pdata->clk_enable(host->pdev, &mmc->f_max);
+	ret = host->clk_enable(host->pdev, &mmc->f_max);
 	if (!ret)
 		mmc->f_min = mmc->f_max / 512;
 
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 0872ca1e5dc..472587a02a4 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -126,7 +126,6 @@ struct tmio_mmc_data {
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
 	/* clock management callbacks */
-	int (*clk_enable)(struct platform_device *pdev, unsigned int *f);
 	void (*clk_disable)(struct platform_device *pdev);
 	int (*multi_io_quirk)(struct mmc_card *card,
 			      unsigned int direction, int blk_size);
-- 
cgit v1.2.3-70-g09d2


From 00452c11ea0e4e5822edf0ac46853933860d0f53 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:58:01 +0000
Subject: mmc: tmio: tmio_mmc_host has .clk_disable

Current .clk_disable is implemented under tmio_mmc_data.
It goes to tmio_mmc_host by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 2 +-
 drivers/mmc/host/tmio_mmc.h       | 1 +
 drivers/mmc/host/tmio_mmc_pio.c   | 4 ++--
 include/linux/mfd/tmio.h          | 3 +--
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 87af77dd660..5e02a6a302e 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -216,8 +216,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	host->dma		= dma_priv;
 	host->write16_hook	= sh_mobile_sdhi_write16_hook;
 	host->clk_enable	= sh_mobile_sdhi_clk_enable;
+	host->clk_disable	= sh_mobile_sdhi_clk_disable;
 
-	mmc_data->clk_disable = sh_mobile_sdhi_clk_disable;
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
 	mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk;
 	if (p) {
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 5cd298665b9..28234ec5caa 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -97,6 +97,7 @@ struct tmio_mmc_host {
 
 	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
 	int (*clk_enable)(struct platform_device *pdev, unsigned int *f);
+	void (*clk_disable)(struct platform_device *pdev);
 };
 
 struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 38bcf0ca31c..e33eb8ee5eb 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -1249,8 +1249,8 @@ int tmio_mmc_host_runtime_suspend(struct device *dev)
 	if (host->clk_cache)
 		tmio_mmc_clk_stop(host);
 
-	if (host->pdata->clk_disable)
-		host->pdata->clk_disable(host->pdev);
+	if (host->clk_disable)
+		host->clk_disable(host->pdev);
 
 	return 0;
 }
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 472587a02a4..a3f78da70af 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -125,8 +125,7 @@ struct tmio_mmc_data {
 	unsigned int			cd_gpio;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
-	/* clock management callbacks */
-	void (*clk_disable)(struct platform_device *pdev);
+
 	int (*multi_io_quirk)(struct mmc_card *card,
 			      unsigned int direction, int blk_size);
 };
-- 
cgit v1.2.3-70-g09d2


From 85c02ddd591e5252eb1cbe8743a839638d7415fd Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:58:10 +0000
Subject: mmc: tmio: tmio_mmc_host has .multi_io_quirk

Current .multi_io_quirk is implemented under tmio_mmc_data.
It goes to tmio_mmc_host by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 2 +-
 drivers/mmc/host/tmio_mmc.h       | 2 ++
 drivers/mmc/host/tmio_mmc_pio.c   | 5 ++---
 include/linux/mfd/tmio.h          | 3 ---
 4 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 5e02a6a302e..c92efe59284 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -217,9 +217,9 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	host->write16_hook	= sh_mobile_sdhi_write16_hook;
 	host->clk_enable	= sh_mobile_sdhi_clk_enable;
 	host->clk_disable	= sh_mobile_sdhi_clk_disable;
+	host->multi_io_quirk	= sh_mobile_sdhi_multi_io_quirk;
 
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
-	mmc_data->multi_io_quirk = sh_mobile_sdhi_multi_io_quirk;
 	if (p) {
 		mmc_data->flags = p->tmio_flags;
 		mmc_data->ocr_mask = p->tmio_ocr_mask;
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 28234ec5caa..263256c897e 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -98,6 +98,8 @@ struct tmio_mmc_host {
 	int (*write16_hook)(struct tmio_mmc_host *host, int addr);
 	int (*clk_enable)(struct platform_device *pdev, unsigned int *f);
 	void (*clk_disable)(struct platform_device *pdev);
+	int (*multi_io_quirk)(struct mmc_card *card,
+			      unsigned int direction, int blk_size);
 };
 
 struct tmio_mmc_host *tmio_mmc_host_alloc(struct platform_device *pdev);
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index e33eb8ee5eb..a31c3573d38 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -1004,10 +1004,9 @@ static int tmio_multi_io_quirk(struct mmc_card *card,
 			       unsigned int direction, int blk_size)
 {
 	struct tmio_mmc_host *host = mmc_priv(card->host);
-	struct tmio_mmc_data *pdata = host->pdata;
 
-	if (pdata->multi_io_quirk)
-		return pdata->multi_io_quirk(card, direction, blk_size);
+	if (host->multi_io_quirk)
+		return host->multi_io_quirk(card, direction, blk_size);
 
 	return blk_size;
 }
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index a3f78da70af..3edaa17d1cc 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -125,9 +125,6 @@ struct tmio_mmc_data {
 	unsigned int			cd_gpio;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
-
-	int (*multi_io_quirk)(struct mmc_card *card,
-			      unsigned int direction, int blk_size);
 };
 
 /*
-- 
cgit v1.2.3-70-g09d2


From 7445bf9e6f4e5d7755e22c7c9b06f4ae0d6160c6 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:58:20 +0000
Subject: mmc: tmio: tmio_mmc_host has .bus_shift

Current .bus_shift is implemented under tmio_mmc_data.
It goes to tmio_mmc_host by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c |  5 ++---
 drivers/mmc/host/tmio_mmc.c       |  5 +++--
 drivers/mmc/host/tmio_mmc.h       | 17 +++++++++--------
 drivers/mmc/host/tmio_mmc_dma.c   |  2 +-
 include/linux/mfd/tmio.h          |  1 -
 5 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index c92efe59284..0db2a0a0376 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -218,6 +218,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	host->clk_enable	= sh_mobile_sdhi_clk_enable;
 	host->clk_disable	= sh_mobile_sdhi_clk_disable;
 	host->multi_io_quirk	= sh_mobile_sdhi_multi_io_quirk;
+	/* SD control register space size is 0x100, 0x200 for bus_shift=1 */
+	host->bus_shift		= resource_size(res) >> 9;
 
 	mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED;
 	if (p) {
@@ -277,9 +279,6 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		dma_priv->dma_rx_offset = of_data->dma_rx_offset;
 	}
 
-	/* SD control register space size is 0x100, 0x200 for bus_shift=1 */
-	mmc_data->bus_shift = resource_size(res) >> 9;
-
 	ret = tmio_mmc_host_probe(host, mmc_data);
 	if (ret < 0)
 		goto efree;
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index a7c2e459187..f746df49389 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -88,14 +88,15 @@ static int tmio_mmc_probe(struct platform_device *pdev)
 	if (!res)
 		return -EINVAL;
 
-	/* SD control register space size is 0x200, 0x400 for bus_shift=1 */
-	pdata->bus_shift = resource_size(res) >> 10;
 	pdata->flags |= TMIO_MMC_HAVE_HIGH_REG;
 
 	host = tmio_mmc_host_alloc(pdev);
 	if (!host)
 		goto cell_disable;
 
+	/* SD control register space size is 0x200, 0x400 for bus_shift=1 */
+	host->bus_shift = resource_size(res) >> 10;
+
 	ret = tmio_mmc_host_probe(host, pdata);
 	if (ret)
 		goto host_free;
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 263256c897e..a5d30bfa7e6 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -66,6 +66,7 @@ struct tmio_mmc_host {
 	struct scatterlist      *sg_orig;
 	unsigned int            sg_len;
 	unsigned int            sg_off;
+	unsigned long		bus_shift;
 
 	struct platform_device *pdev;
 	struct tmio_mmc_data *pdata;
@@ -169,19 +170,19 @@ int tmio_mmc_host_runtime_resume(struct device *dev);
 
 static inline u16 sd_ctrl_read16(struct tmio_mmc_host *host, int addr)
 {
-	return readw(host->ctl + (addr << host->pdata->bus_shift));
+	return readw(host->ctl + (addr << host->bus_shift));
 }
 
 static inline void sd_ctrl_read16_rep(struct tmio_mmc_host *host, int addr,
 		u16 *buf, int count)
 {
-	readsw(host->ctl + (addr << host->pdata->bus_shift), buf, count);
+	readsw(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
 static inline u32 sd_ctrl_read32(struct tmio_mmc_host *host, int addr)
 {
-	return readw(host->ctl + (addr << host->pdata->bus_shift)) |
-	       readw(host->ctl + ((addr + 2) << host->pdata->bus_shift)) << 16;
+	return readw(host->ctl + (addr << host->bus_shift)) |
+	       readw(host->ctl + ((addr + 2) << host->bus_shift)) << 16;
 }
 
 static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val)
@@ -191,19 +192,19 @@ static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val
 	 */
 	if (host->write16_hook && host->write16_hook(host, addr))
 		return;
-	writew(val, host->ctl + (addr << host->pdata->bus_shift));
+	writew(val, host->ctl + (addr << host->bus_shift));
 }
 
 static inline void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr,
 		u16 *buf, int count)
 {
-	writesw(host->ctl + (addr << host->pdata->bus_shift), buf, count);
+	writesw(host->ctl + (addr << host->bus_shift), buf, count);
 }
 
 static inline void sd_ctrl_write32(struct tmio_mmc_host *host, int addr, u32 val)
 {
-	writew(val, host->ctl + (addr << host->pdata->bus_shift));
-	writew(val >> 16, host->ctl + ((addr + 2) << host->pdata->bus_shift));
+	writew(val, host->ctl + (addr << host->bus_shift));
+	writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift));
 }
 
 
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index 6c214d60bbb..ee0131eb078 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -289,7 +289,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		if (host->dma->chan_priv_tx)
 			cfg.slave_id = host->dma->slave_id_tx;
 		cfg.direction = DMA_MEM_TO_DEV;
-		cfg.dst_addr = res->start + (CTL_SD_DATA_PORT << host->pdata->bus_shift);
+		cfg.dst_addr = res->start + (CTL_SD_DATA_PORT << host->bus_shift);
 		cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		cfg.src_addr = 0;
 		ret = dmaengine_slave_config(host->chan_tx, &cfg);
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 3edaa17d1cc..7a5c2794831 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -120,7 +120,6 @@ struct tmio_mmc_data {
 	unsigned long			capabilities;
 	unsigned long			capabilities2;
 	unsigned long			flags;
-	unsigned long			bus_shift;
 	u32				ocr_mask;	/* available voltages */
 	unsigned int			cd_gpio;
 	void (*set_pwr)(struct platform_device *host, int state);
-- 
cgit v1.2.3-70-g09d2


From e471df0bcaa137f1bbe7c5f75db6ce7566caa292 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:58:46 +0000
Subject: mmc: tmio: tmio_mmc_data has .alignment_shift

Current .alignment_shift is implemented under tmio_mmc_dma.
It goes to tmio_mmc_data by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 4 ++--
 drivers/mmc/host/tmio_mmc.h       | 1 -
 drivers/mmc/host/tmio_mmc_dma.c   | 4 ++--
 include/linux/mfd/tmio.h          | 1 +
 4 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 0db2a0a0376..782d8cf942a 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -241,10 +241,10 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 			dma_priv->slave_id_rx = p->dma_slave_rx;
 		}
 	}
-
-	dma_priv->alignment_shift = 1; /* 2-byte alignment */
 	dma_priv->filter = shdma_chan_filter;
 
+	mmc_data->alignment_shift = 1; /* 2-byte alignment */
+
 	/*
 	 * All SDHI blocks support 2-byte and larger block sizes in 4-bit
 	 * bus width mode.
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index a5d30bfa7e6..9482abceeb9 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -45,7 +45,6 @@ struct tmio_mmc_dma {
 	void *chan_priv_rx;
 	int slave_id_tx;
 	int slave_id_rx;
-	int alignment_shift;
 	dma_addr_t dma_rx_offset;
 	bool (*filter)(struct dma_chan *chan, void *arg);
 };
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index ee0131eb078..d2b02de2f37 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -52,7 +52,7 @@ static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host)
 	dma_cookie_t cookie;
 	int ret, i;
 	bool aligned = true, multiple = true;
-	unsigned int align = (1 << host->dma->alignment_shift) - 1;
+	unsigned int align = (1 << host->pdata->alignment_shift) - 1;
 
 	for_each_sg(sg, sg_tmp, host->sg_len, i) {
 		if (sg_tmp->offset & align)
@@ -128,7 +128,7 @@ static void tmio_mmc_start_dma_tx(struct tmio_mmc_host *host)
 	dma_cookie_t cookie;
 	int ret, i;
 	bool aligned = true, multiple = true;
-	unsigned int align = (1 << host->dma->alignment_shift) - 1;
+	unsigned int align = (1 << host->pdata->alignment_shift) - 1;
 
 	for_each_sg(sg, sg_tmp, host->sg_len, i) {
 		if (sg_tmp->offset & align)
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 7a5c2794831..28a12d10e50 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -122,6 +122,7 @@ struct tmio_mmc_data {
 	unsigned long			flags;
 	u32				ocr_mask;	/* available voltages */
 	unsigned int			cd_gpio;
+	int				alignment_shift;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
 };
-- 
cgit v1.2.3-70-g09d2


From 8b4c8f32da91681c0dcd321c9e3cd14f866c5517 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:58:56 +0000
Subject: mmc: tmio: tmio_mmc_data has .dma_rx_offset

Current .dma_rx_offset is implemented under tmio_mmc_dma.
It goes to tmio_mmc_data by this patch.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 2 +-
 drivers/mmc/host/tmio_mmc.h       | 1 -
 drivers/mmc/host/tmio_mmc_dma.c   | 2 +-
 include/linux/mfd/tmio.h          | 1 +
 4 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 782d8cf942a..c06e93b7799 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -276,7 +276,7 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		mmc_data->flags |= of_data->tmio_flags;
 		mmc_data->capabilities |= of_data->capabilities;
 		mmc_data->capabilities2 |= of_data->capabilities2;
-		dma_priv->dma_rx_offset = of_data->dma_rx_offset;
+		mmc_data->dma_rx_offset = of_data->dma_rx_offset;
 	}
 
 	ret = tmio_mmc_host_probe(host, mmc_data);
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 9482abceeb9..c9a84695cff 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -45,7 +45,6 @@ struct tmio_mmc_dma {
 	void *chan_priv_rx;
 	int slave_id_tx;
 	int slave_id_rx;
-	dma_addr_t dma_rx_offset;
 	bool (*filter)(struct dma_chan *chan, void *arg);
 };
 
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index d2b02de2f37..634b2700cb7 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -308,7 +308,7 @@ void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdat
 		if (host->dma->chan_priv_rx)
 			cfg.slave_id = host->dma->slave_id_rx;
 		cfg.direction = DMA_DEV_TO_MEM;
-		cfg.src_addr = cfg.dst_addr + host->dma->dma_rx_offset;
+		cfg.src_addr = cfg.dst_addr + host->pdata->dma_rx_offset;
 		cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		cfg.dst_addr = 0;
 		ret = dmaengine_slave_config(host->chan_rx, &cfg);
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 28a12d10e50..807ecfb162d 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -123,6 +123,7 @@ struct tmio_mmc_data {
 	u32				ocr_mask;	/* available voltages */
 	unsigned int			cd_gpio;
 	int				alignment_shift;
+	dma_addr_t			dma_rx_offset;
 	void (*set_pwr)(struct platform_device *host, int state);
 	void (*set_clk_div)(struct platform_device *host, int state);
 };
-- 
cgit v1.2.3-70-g09d2


From 010f4aa758f437647799b1fd677a5e2cf31714e9 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 04:59:24 +0000
Subject: mmc: sh_mobile_sdhi: remove .init/.cleanup

No one is using .init/.cleanup callback function.
Let's remove these.
sdhi_ops and .cd_wakeup are also removed

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c  | 26 +-------------------------
 include/linux/mmc/sh_mobile_sdhi.h | 15 ---------------
 2 files changed, 1 insertion(+), 40 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index c06e93b7799..48a3be804cc 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -156,15 +156,6 @@ static int sh_mobile_sdhi_multi_io_quirk(struct mmc_card *card,
 	return blk_size;
 }
 
-static void sh_mobile_sdhi_cd_wakeup(const struct platform_device *pdev)
-{
-	mmc_detect_change(platform_get_drvdata(pdev), msecs_to_jiffies(100));
-}
-
-static const struct sh_mobile_sdhi_ops sdhi_ops = {
-	.cd_wakeup = sh_mobile_sdhi_cd_wakeup,
-};
-
 static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
@@ -192,19 +183,11 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	mmc_data = &priv->mmc_data;
 	dma_priv = &priv->dma_priv;
 
-	if (p) {
-		if (p->init) {
-			ret = p->init(pdev, &sdhi_ops);
-			if (ret)
-				return ret;
-		}
-	}
-
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(priv->clk)) {
 		ret = PTR_ERR(priv->clk);
 		dev_err(&pdev->dev, "cannot get clock: %d\n", ret);
-		goto eclkget;
+		goto eprobe;
 	}
 
 	host = tmio_mmc_host_alloc(pdev);
@@ -359,9 +342,6 @@ eirq:
 efree:
 	tmio_mmc_host_free(host);
 eprobe:
-eclkget:
-	if (p && p->cleanup)
-		p->cleanup(pdev);
 	return ret;
 }
 
@@ -369,13 +349,9 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev)
 {
 	struct mmc_host *mmc = platform_get_drvdata(pdev);
 	struct tmio_mmc_host *host = mmc_priv(mmc);
-	struct sh_mobile_sdhi_info *p = pdev->dev.platform_data;
 
 	tmio_mmc_host_remove(host);
 
-	if (p && p->cleanup)
-		p->cleanup(pdev);
-
 	return 0;
 }
 
diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h
index 68927ae5084..da77e5e2041 100644
--- a/include/linux/mmc/sh_mobile_sdhi.h
+++ b/include/linux/mmc/sh_mobile_sdhi.h
@@ -3,20 +3,10 @@
 
 #include <linux/types.h>
 
-struct platform_device;
-
 #define SH_MOBILE_SDHI_IRQ_CARD_DETECT	"card_detect"
 #define SH_MOBILE_SDHI_IRQ_SDCARD	"sdcard"
 #define SH_MOBILE_SDHI_IRQ_SDIO		"sdio"
 
-/**
- * struct sh_mobile_sdhi_ops - SDHI driver callbacks
- * @cd_wakeup:		trigger a card-detection run
- */
-struct sh_mobile_sdhi_ops {
-	void (*cd_wakeup)(const struct platform_device *pdev);
-};
-
 struct sh_mobile_sdhi_info {
 	int dma_slave_tx;
 	int dma_slave_rx;
@@ -25,11 +15,6 @@ struct sh_mobile_sdhi_info {
 	unsigned long tmio_caps2;
 	u32 tmio_ocr_mask;	/* available MMC voltages */
 	unsigned int cd_gpio;
-
-	/* callbacks for board specific setup code */
-	int (*init)(struct platform_device *pdev,
-		    const struct sh_mobile_sdhi_ops *ops);
-	void (*cleanup)(struct platform_device *pdev);
 };
 
 #endif /* LINUX_MMC_SH_MOBILE_SDHI_H */
-- 
cgit v1.2.3-70-g09d2


From de122cb1745313f331dc7c7923b484343d455e64 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 13 Jan 2015 05:00:39 +0000
Subject: mmc: tmio: remove TMIO_MMC_HAVE_CTL_DMA_REG flag

tmio_mmc_host has .enable_dma callback now.
We don't need TMIO_MMC_HAVE_CTL_DMA_REG anymore.
Let's remove it

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mobile_sdhi.c | 5 -----
 drivers/mmc/host/tmio_mmc_dma.c   | 3 ---
 include/linux/mfd/tmio.h          | 5 -----
 3 files changed, 13 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index 7dbcb577f59..6906a905cd5 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -291,11 +291,6 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	 */
 	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_QUIRK;
 
-	/*
-	 * All SDHI have DMA control register
-	 */
-	mmc_data->flags |= TMIO_MMC_HAVE_CTL_DMA_REG;
-
 	if (of_id && of_id->data) {
 		const struct sh_mobile_sdhi_of_data *of_data = of_id->data;
 		mmc_data->flags |= of_data->tmio_flags;
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index aa5f4b6e790..331bb618e39 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -28,9 +28,6 @@ void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable)
 	if (!host->chan_tx || !host->chan_rx)
 		return;
 
-	if (host->pdata->flags & TMIO_MMC_HAVE_CTL_DMA_REG)
-		sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0);
-
 	if (host->dma->enable)
 		host->dma->enable(host, enable);
 }
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index 807ecfb162d..605812820e4 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -95,11 +95,6 @@
  */
 #define TMIO_MMC_SDIO_STATUS_QUIRK	(1 << 8)
 
-/*
- * Some controllers have DMA enable/disable register
- */
-#define TMIO_MMC_HAVE_CTL_DMA_REG	(1 << 9)
-
 /*
  * Some controllers allows to set SDx actual clock
  */
-- 
cgit v1.2.3-70-g09d2


From 1dfb4a0d7615811ec4a61b0a7631c8ddc0baf335 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 13 Jan 2015 08:00:29 +0100
Subject: gpio: stmpe: enforce device tree only mode

Require that device tree be used with STMPE (all platforms use this)
and enforce OF_GPIO, then delete the platform data.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig      |  1 +
 drivers/gpio/gpio-stmpe.c | 23 +++--------------------
 include/linux/mfd/stmpe.h | 16 ----------------
 3 files changed, 4 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 4187fcbc88f..22b46567b3b 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -644,6 +644,7 @@ config GPIO_SX150X
 config GPIO_STMPE
 	bool "STMPE GPIOs"
 	depends on MFD_STMPE
+	depends on OF_GPIO
 	select GPIOLIB_IRQCHIP
 	help
 	  This enables support for the GPIOs found on the STMPE I/O
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 85c5b197429..dabfb99ddde 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -30,7 +30,7 @@ struct stmpe_gpio {
 	struct stmpe *stmpe;
 	struct device *dev;
 	struct mutex irq_lock;
-	unsigned norequest_mask;
+	u32 norequest_mask;
 	/* Caches of interrupt control registers for bus_lock */
 	u8 regs[CACHE_NR_REGS][CACHE_NR_BANKS];
 	u8 oldregs[CACHE_NR_REGS][CACHE_NR_BANKS];
@@ -340,13 +340,10 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 {
 	struct stmpe *stmpe = dev_get_drvdata(pdev->dev.parent);
 	struct device_node *np = pdev->dev.of_node;
-	struct stmpe_gpio_platform_data *pdata;
 	struct stmpe_gpio *stmpe_gpio;
 	int ret;
 	int irq = 0;
 
-	pdata = stmpe->pdata->gpio;
-
 	irq = platform_get_irq(pdev, 0);
 
 	stmpe_gpio = kzalloc(sizeof(struct stmpe_gpio), GFP_KERNEL);
@@ -360,19 +357,14 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 	stmpe_gpio->chip = template_chip;
 	stmpe_gpio->chip.ngpio = stmpe->num_gpios;
 	stmpe_gpio->chip.dev = &pdev->dev;
-#ifdef CONFIG_OF
 	stmpe_gpio->chip.of_node = np;
-#endif
 	stmpe_gpio->chip.base = -1;
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS))
                 stmpe_gpio->chip.dbg_show = stmpe_dbg_show;
 
-	if (pdata)
-		stmpe_gpio->norequest_mask = pdata->norequest_mask;
-	else if (np)
-		of_property_read_u32(np, "st,norequest-mask",
-				&stmpe_gpio->norequest_mask);
+	of_property_read_u32(np, "st,norequest-mask",
+			&stmpe_gpio->norequest_mask);
 
 	if (irq < 0)
 		dev_info(&pdev->dev,
@@ -414,9 +406,6 @@ static int stmpe_gpio_probe(struct platform_device *pdev)
 					     NULL);
 	}
 
-	if (pdata && pdata->setup)
-		pdata->setup(stmpe, stmpe_gpio->chip.base);
-
 	platform_set_drvdata(pdev, stmpe_gpio);
 
 	return 0;
@@ -433,15 +422,9 @@ static int stmpe_gpio_remove(struct platform_device *pdev)
 {
 	struct stmpe_gpio *stmpe_gpio = platform_get_drvdata(pdev);
 	struct stmpe *stmpe = stmpe_gpio->stmpe;
-	struct stmpe_gpio_platform_data *pdata = stmpe->pdata->gpio;
-
-	if (pdata && pdata->remove)
-		pdata->remove(stmpe, stmpe_gpio->chip.base);
 
 	gpiochip_remove(&stmpe_gpio->chip);
-
 	stmpe_disable(stmpe, STMPE_BLOCK_GPIO);
-
 	kfree(stmpe_gpio);
 
 	return 0;
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index f742b6717d5..c9d86902730 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -117,20 +117,6 @@ extern int stmpe_disable(struct stmpe *stmpe, unsigned int blocks);
 
 #define STMPE_GPIO_NOREQ_811_TOUCH	(0xf0)
 
-/**
- * struct stmpe_gpio_platform_data - STMPE GPIO platform data
- * @norequest_mask: bitmask specifying which GPIOs should _not_ be
- *		    requestable due to different usage (e.g. touch, keypad)
- *		    STMPE_GPIO_NOREQ_* macros can be used here.
- * @setup: board specific setup callback.
- * @remove: board specific remove callback
- */
-struct stmpe_gpio_platform_data {
-	unsigned norequest_mask;
-	void (*setup)(struct stmpe *stmpe, unsigned gpio_base);
-	void (*remove)(struct stmpe *stmpe, unsigned gpio_base);
-};
-
 /**
  * struct stmpe_ts_platform_data - stmpe811 touch screen controller platform
  * data
@@ -182,7 +168,6 @@ struct stmpe_ts_platform_data {
  * @irq_over_gpio: true if gpio is used to get irq
  * @irq_gpio: gpio number over which irq will be requested (significant only if
  *	      irq_over_gpio is true)
- * @gpio: GPIO-specific platform data
  * @ts: touchscreen-specific platform data
  */
 struct stmpe_platform_data {
@@ -194,7 +179,6 @@ struct stmpe_platform_data {
 	int irq_gpio;
 	int autosleep_timeout;
 
-	struct stmpe_gpio_platform_data *gpio;
 	struct stmpe_ts_platform_data *ts;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 7d7d731d1f0f27d2e470d4bc6112aca5ff30476f Mon Sep 17 00:00:00 2001
From: Jeremiah Mahler <jmmahler@gmail.com>
Date: Fri, 5 Dec 2014 06:56:50 -0800
Subject: msdos_fs.h: fix 'fields' in comment

Signed-off-by: Jeremiah Mahler <jmmahler@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/uapi/linux/msdos_fs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h
index e284ff919d6..e956704f5fb 100644
--- a/include/uapi/linux/msdos_fs.h
+++ b/include/uapi/linux/msdos_fs.h
@@ -134,7 +134,7 @@ struct fat_boot_sector {
 			__u8	vol_id[4];	/* volume ID */
 			__u8	vol_label[11];	/* volume label */
 			__u8	fs_type[8];		/* file system type */
-			/* other fiealds are not added here */
+			/* other fields are not added here */
 		} fat16;
 
 		struct {
@@ -157,7 +157,7 @@ struct fat_boot_sector {
 			__u8	vol_id[4];	/* volume ID */
 			__u8	vol_label[11];	/* volume label */
 			__u8	fs_type[8];		/* file system type */
-			/* other fiealds are not added here */
+			/* other fields are not added here */
 		} fat32;
 	};
 };
-- 
cgit v1.2.3-70-g09d2


From 4b6eade76ad19183464b739e9af1efacdb1bbda8 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Tue, 20 Jan 2015 11:00:53 +0100
Subject: mfd: max77693: Add defines for MAX77693 charger driver

Prepare for adding support for Maxim 77693 charger by adding necessary
new defines.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Sebastian Reichel <sre@kernel.org>
---
 include/linux/mfd/max77693-private.h | 108 +++++++++++++++++++++++++++++++++++
 1 file changed, 108 insertions(+)

(limited to 'include')

diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 08dae01258b..955dd990bea 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -143,10 +143,118 @@ enum max77693_pmic_reg {
 #define FLASH_INT_FLED1_SHORT	BIT(3)
 #define FLASH_INT_OVER_CURRENT	BIT(4)
 
+/* Fast charge timer in in hours */
+#define DEFAULT_FAST_CHARGE_TIMER		4
+/* microamps */
+#define DEFAULT_TOP_OFF_THRESHOLD_CURRENT	150000
+/* minutes */
+#define DEFAULT_TOP_OFF_TIMER			30
+/* microvolts */
+#define DEFAULT_CONSTANT_VOLT			4200000
+/* microvolts */
+#define DEFAULT_MIN_SYSTEM_VOLT			3600000
+/* celsius */
+#define DEFAULT_THERMAL_REGULATION_TEMP		100
+/* microamps */
+#define DEFAULT_BATTERY_OVERCURRENT		3500000
+/* microvolts */
+#define DEFAULT_CHARGER_INPUT_THRESHOLD_VOLT	4300000
+
+/* MAX77693_CHG_REG_CHG_INT_OK register */
+#define CHG_INT_OK_BYP_SHIFT		0
+#define CHG_INT_OK_BAT_SHIFT		3
+#define CHG_INT_OK_CHG_SHIFT		4
+#define CHG_INT_OK_CHGIN_SHIFT		6
+#define CHG_INT_OK_DETBAT_SHIFT		7
+#define CHG_INT_OK_BYP_MASK		BIT(CHG_INT_OK_BYP_SHIFT)
+#define CHG_INT_OK_BAT_MASK		BIT(CHG_INT_OK_BAT_SHIFT)
+#define CHG_INT_OK_CHG_MASK		BIT(CHG_INT_OK_CHG_SHIFT)
+#define CHG_INT_OK_CHGIN_MASK		BIT(CHG_INT_OK_CHGIN_SHIFT)
+#define CHG_INT_OK_DETBAT_MASK		BIT(CHG_INT_OK_DETBAT_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_DETAILS_00 register */
+#define CHG_DETAILS_00_CHGIN_SHIFT	5
+#define CHG_DETAILS_00_CHGIN_MASK	(0x3 << CHG_DETAILS_00_CHGIN_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_DETAILS_01 register */
+#define CHG_DETAILS_01_CHG_SHIFT	0
+#define CHG_DETAILS_01_BAT_SHIFT	4
+#define CHG_DETAILS_01_TREG_SHIFT	7
+#define CHG_DETAILS_01_CHG_MASK		(0xf << CHG_DETAILS_01_CHG_SHIFT)
+#define CHG_DETAILS_01_BAT_MASK		(0x7 << CHG_DETAILS_01_BAT_SHIFT)
+#define CHG_DETAILS_01_TREG_MASK	BIT(7)
+
+/* MAX77693_CHG_REG_CHG_DETAILS_01/CHG field */
+enum max77693_charger_charging_state {
+	MAX77693_CHARGING_PREQUALIFICATION	= 0x0,
+	MAX77693_CHARGING_FAST_CONST_CURRENT,
+	MAX77693_CHARGING_FAST_CONST_VOLTAGE,
+	MAX77693_CHARGING_TOP_OFF,
+	MAX77693_CHARGING_DONE,
+	MAX77693_CHARGING_HIGH_TEMP,
+	MAX77693_CHARGING_TIMER_EXPIRED,
+	MAX77693_CHARGING_THERMISTOR_SUSPEND,
+	MAX77693_CHARGING_OFF,
+	MAX77693_CHARGING_RESERVED,
+	MAX77693_CHARGING_OVER_TEMP,
+	MAX77693_CHARGING_WATCHDOG_EXPIRED,
+};
+
+/* MAX77693_CHG_REG_CHG_DETAILS_01/BAT field */
+enum max77693_charger_battery_state {
+	MAX77693_BATTERY_NOBAT			= 0x0,
+	/* Dead-battery or low-battery prequalification */
+	MAX77693_BATTERY_PREQUALIFICATION,
+	MAX77693_BATTERY_TIMER_EXPIRED,
+	MAX77693_BATTERY_GOOD,
+	MAX77693_BATTERY_LOWVOLTAGE,
+	MAX77693_BATTERY_OVERVOLTAGE,
+	MAX77693_BATTERY_OVERCURRENT,
+	MAX77693_BATTERY_RESERVED,
+};
+
+/* MAX77693_CHG_REG_CHG_DETAILS_02 register */
+#define CHG_DETAILS_02_BYP_SHIFT	0
+#define CHG_DETAILS_02_BYP_MASK		(0xf << CHG_DETAILS_02_BYP_SHIFT)
+
 /* MAX77693 CHG_CNFG_00 register */
 #define CHG_CNFG_00_CHG_MASK		0x1
 #define CHG_CNFG_00_BUCK_MASK		0x4
 
+/* MAX77693_CHG_REG_CHG_CNFG_01 register */
+#define CHG_CNFG_01_FCHGTIME_SHIFT	0
+#define CHG_CNFG_01_CHGRSTRT_SHIFT	4
+#define CHG_CNFG_01_PQEN_SHIFT		7
+#define CHG_CNFG_01_FCHGTIME_MASK	(0x7 << CHG_CNFG_01_FCHGTIME_SHIFT)
+#define CHG_CNFG_01_CHGRSTRT_MASK	(0x3 << CHG_CNFG_01_CHGRSTRT_SHIFT)
+#define CHG_CNFG_01_PQEN_MAKS		BIT(CHG_CNFG_01_PQEN_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_03 register */
+#define CHG_CNFG_03_TOITH_SHIFT		0
+#define CHG_CNFG_03_TOTIME_SHIFT	3
+#define CHG_CNFG_03_TOITH_MASK		(0x7 << CHG_CNFG_03_TOITH_SHIFT)
+#define CHG_CNFG_03_TOTIME_MASK		(0x7 << CHG_CNFG_03_TOTIME_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_04 register */
+#define CHG_CNFG_04_CHGCVPRM_SHIFT	0
+#define CHG_CNFG_04_MINVSYS_SHIFT	5
+#define CHG_CNFG_04_CHGCVPRM_MASK	(0x1f << CHG_CNFG_04_CHGCVPRM_SHIFT)
+#define CHG_CNFG_04_MINVSYS_MASK	(0x7 << CHG_CNFG_04_MINVSYS_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_06 register */
+#define CHG_CNFG_06_CHGPROT_SHIFT	2
+#define CHG_CNFG_06_CHGPROT_MASK	(0x3 << CHG_CNFG_06_CHGPROT_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_07 register */
+#define CHG_CNFG_07_REGTEMP_SHIFT	5
+#define CHG_CNFG_07_REGTEMP_MASK	(0x3 << CHG_CNFG_07_REGTEMP_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_12 register */
+#define CHG_CNFG_12_B2SOVRC_SHIFT	0
+#define CHG_CNFG_12_VCHGINREG_SHIFT	3
+#define CHG_CNFG_12_B2SOVRC_MASK	(0x7 << CHG_CNFG_12_B2SOVRC_SHIFT)
+#define CHG_CNFG_12_VCHGINREG_MASK	(0x3 << CHG_CNFG_12_VCHGINREG_SHIFT)
+
 /* MAX77693 CHG_CNFG_09 Register */
 #define CHG_CNFG_09_CHGIN_ILIM_MASK	0x7F
 
-- 
cgit v1.2.3-70-g09d2


From 2fded7f44b8fcf79e274c3f0cfbd0298f95308f3 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 23 Dec 2014 16:39:54 -0500
Subject: audit: remove vestiges of vers_ops

Should have been removed with commit 18900909 ("audit: remove the old
depricated kernel interface").

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <pmoore@redhat.com>
---
 include/linux/audit.h | 1 -
 kernel/auditfilter.c  | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 93331929d64..b481779a8de 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -46,7 +46,6 @@ struct audit_tree;
 struct sk_buff;
 
 struct audit_krule {
-	int			vers_ops;
 	u32			pflags;
 	u32			flags;
 	u32			listnr;
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 103586e239a..81c94d739e3 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -425,7 +425,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		goto exit_nofree;
 
 	bufp = data->buf;
-	entry->rule.vers_ops = 2;
 	for (i = 0; i < data->field_count; i++) {
 		struct audit_field *f = &entry->rule.fields[i];
 
@@ -758,7 +757,6 @@ struct audit_entry *audit_dupe_rule(struct audit_krule *old)
 		return ERR_PTR(-ENOMEM);
 
 	new = &entry->rule;
-	new->vers_ops = old->vers_ops;
 	new->flags = old->flags;
 	new->pflags = old->pflags;
 	new->listnr = old->listnr;
-- 
cgit v1.2.3-70-g09d2


From 6a806cbc1525e6f95e22173d9f54a7b75a2bb973 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 18 Jan 2015 16:11:29 +0100
Subject: scsi: annotate sdev_prefix_printk and scmd_printk as printf-like

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Bottomley <JBottomley@Parallels.com>
Reviewed-by: Ewan D. Milne <emilne@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
---
 include/scsi/scsi_device.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index d1aad4d0433..2e0281ee719 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -237,14 +237,15 @@ struct scsi_dh_data {
  * like scmd_printk, but the device name is passed in
  * as a string pointer
  */
-extern int sdev_prefix_printk(const char *, const struct scsi_device *,
-			      const char *, const char *, ...);
+__printf(4, 5) int
+sdev_prefix_printk(const char *, const struct scsi_device *, const char *,
+		const char *, ...);
 
 #define sdev_printk(l, sdev, fmt, a...)				\
 	sdev_prefix_printk(l, sdev, NULL, fmt, ##a)
 
-extern int scmd_printk(const char *, const struct scsi_cmnd *,
-		       const char *, ...);
+__printf(3, 4) int
+scmd_printk(const char *, const struct scsi_cmnd *, const char *, ...);
 
 #define scmd_dbg(scmd, fmt, a...)					   \
 	do {								   \
-- 
cgit v1.2.3-70-g09d2


From 39e794bff718188cfb9ace2032cbe4fd86048dc6 Mon Sep 17 00:00:00 2001
From: Yaniv Gardi <ygardi@codeaurora.org>
Date: Thu, 15 Jan 2015 16:32:36 +0200
Subject: phy: qcom-ufs: add support for 20nm phy

This change adds a support for a 20nm qcom-ufs phy that is required in
platforms that use ufs-qcom controller.

Signed-off-by: Yaniv Gardi <ygardi@codeaurora.org>
Reviewed-by: Dov Levenglick <dovl@codeaurora.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/phy/Makefile                |   1 +
 drivers/phy/phy-qcom-ufs-i.h        |  43 +++++-
 drivers/phy/phy-qcom-ufs-qmp-20nm.c | 257 ++++++++++++++++++++++++++++++++++++
 drivers/phy/phy-qcom-ufs-qmp-20nm.h | 235 +++++++++++++++++++++++++++++++++
 include/linux/phy/phy-qcom-ufs.h    |  59 +++++++++
 5 files changed, 594 insertions(+), 1 deletion(-)
 create mode 100644 drivers/phy/phy-qcom-ufs-qmp-20nm.c
 create mode 100644 drivers/phy/phy-qcom-ufs-qmp-20nm.h
 create mode 100644 include/linux/phy/phy-qcom-ufs.h

(limited to 'include')

diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index 335965d3a9b..781b2fa46d0 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -35,3 +35,4 @@ obj-$(CONFIG_PHY_XGENE)			+= phy-xgene.o
 obj-$(CONFIG_PHY_STIH407_USB)		+= phy-stih407-usb.o
 obj-$(CONFIG_PHY_STIH41X_USB)		+= phy-stih41x-usb.o
 obj-$(CONFIG_PHY_QCOM_UFS) 	+= phy-qcom-ufs.o
+obj-$(CONFIG_PHY_QCOM_UFS) 	+= phy-qcom-ufs-qmp-20nm.o
diff --git a/drivers/phy/phy-qcom-ufs-i.h b/drivers/phy/phy-qcom-ufs-i.h
index dac200f4d63..591a39175e8 100644
--- a/drivers/phy/phy-qcom-ufs-i.h
+++ b/drivers/phy/phy-qcom-ufs-i.h
@@ -15,15 +15,56 @@
 #ifndef UFS_QCOM_PHY_I_H_
 #define UFS_QCOM_PHY_I_H_
 
+#include <linux/module.h>
 #include <linux/clk.h>
+#include <linux/regulator/consumer.h>
 #include <linux/slab.h>
-#include <linux/phy/phy.h>
+#include <linux/phy/phy-qcom-ufs.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/delay.h>
 
+#define readl_poll_timeout(addr, val, cond, sleep_us, timeout_us) \
+({ \
+	ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+	might_sleep_if(timeout_us); \
+	for (;;) { \
+		(val) = readl(addr); \
+		if (cond) \
+			break; \
+		if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+			(val) = readl(addr); \
+			break; \
+		} \
+		if (sleep_us) \
+			usleep_range(DIV_ROUND_UP(sleep_us, 4), sleep_us); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+#define UFS_QCOM_PHY_CAL_ENTRY(reg, val)	\
+	{				\
+		.reg_offset = reg,	\
+		.cfg_value = val,	\
+	}
+
 #define UFS_QCOM_PHY_NAME_LEN	30
 
+enum {
+	MASK_SERDES_START       = 0x1,
+	MASK_PCS_READY          = 0x1,
+};
+
+enum {
+	OFFSET_SERDES_START     = 0x0,
+};
+
+struct ufs_qcom_phy_stored_attributes {
+	u32 att;
+	u32 value;
+};
+
+
 struct ufs_qcom_phy_calibration {
 	u32 reg_offset;
 	u32 cfg_value;
diff --git a/drivers/phy/phy-qcom-ufs-qmp-20nm.c b/drivers/phy/phy-qcom-ufs-qmp-20nm.c
new file mode 100644
index 00000000000..8332f96b2c4
--- /dev/null
+++ b/drivers/phy/phy-qcom-ufs-qmp-20nm.c
@@ -0,0 +1,257 @@
+/*
+ * Copyright (c) 2013-2015, Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include "phy-qcom-ufs-qmp-20nm.h"
+
+#define UFS_PHY_NAME "ufs_phy_qmp_20nm"
+
+static
+int ufs_qcom_phy_qmp_20nm_phy_calibrate(struct ufs_qcom_phy *ufs_qcom_phy,
+					bool is_rate_B)
+{
+	struct ufs_qcom_phy_calibration *tbl_A, *tbl_B;
+	int tbl_size_A, tbl_size_B;
+	u8 major = ufs_qcom_phy->host_ctrl_rev_major;
+	u16 minor = ufs_qcom_phy->host_ctrl_rev_minor;
+	u16 step = ufs_qcom_phy->host_ctrl_rev_step;
+	int err;
+
+	if ((major == 0x1) && (minor == 0x002) && (step == 0x0000)) {
+		tbl_size_A = ARRAY_SIZE(phy_cal_table_rate_A_1_2_0);
+		tbl_A = phy_cal_table_rate_A_1_2_0;
+	} else if ((major == 0x1) && (minor == 0x003) && (step == 0x0000)) {
+		tbl_size_A = ARRAY_SIZE(phy_cal_table_rate_A_1_3_0);
+		tbl_A = phy_cal_table_rate_A_1_3_0;
+	} else {
+		dev_err(ufs_qcom_phy->dev, "%s: Unknown UFS-PHY version, no calibration values\n",
+			__func__);
+		err = -ENODEV;
+		goto out;
+	}
+
+	tbl_size_B = ARRAY_SIZE(phy_cal_table_rate_B);
+	tbl_B = phy_cal_table_rate_B;
+
+	err = ufs_qcom_phy_calibrate(ufs_qcom_phy, tbl_A, tbl_size_A,
+						tbl_B, tbl_size_B, is_rate_B);
+
+	if (err)
+		dev_err(ufs_qcom_phy->dev, "%s: ufs_qcom_phy_calibrate() failed %d\n",
+			__func__, err);
+
+out:
+	return err;
+}
+
+static
+void ufs_qcom_phy_qmp_20nm_advertise_quirks(struct ufs_qcom_phy *phy_common)
+{
+	phy_common->quirks =
+		UFS_QCOM_PHY_QUIRK_HIBERN8_EXIT_AFTER_PHY_PWR_COLLAPSE;
+}
+
+static int ufs_qcom_phy_qmp_20nm_init(struct phy *generic_phy)
+{
+	struct ufs_qcom_phy_qmp_20nm *phy = phy_get_drvdata(generic_phy);
+	struct ufs_qcom_phy *phy_common = &phy->common_cfg;
+	int err = 0;
+
+	err = ufs_qcom_phy_init_clks(generic_phy, phy_common);
+	if (err) {
+		dev_err(phy_common->dev, "%s: ufs_qcom_phy_init_clks() failed %d\n",
+			__func__, err);
+		goto out;
+	}
+
+	err = ufs_qcom_phy_init_vregulators(generic_phy, phy_common);
+	if (err) {
+		dev_err(phy_common->dev, "%s: ufs_qcom_phy_init_vregulators() failed %d\n",
+			__func__, err);
+		goto out;
+	}
+
+	ufs_qcom_phy_qmp_20nm_advertise_quirks(phy_common);
+
+out:
+	return err;
+}
+
+static
+void ufs_qcom_phy_qmp_20nm_power_control(struct ufs_qcom_phy *phy, bool val)
+{
+	bool hibern8_exit_after_pwr_collapse = phy->quirks &
+		UFS_QCOM_PHY_QUIRK_HIBERN8_EXIT_AFTER_PHY_PWR_COLLAPSE;
+
+	if (val) {
+		writel_relaxed(0x1, phy->mmio + UFS_PHY_POWER_DOWN_CONTROL);
+		/*
+		 * Before any transactions involving PHY, ensure PHY knows
+		 * that it's analog rail is powered ON.
+		 */
+		mb();
+
+		if (hibern8_exit_after_pwr_collapse) {
+			/*
+			 * Give atleast 1us delay after restoring PHY analog
+			 * power.
+			 */
+			usleep_range(1, 2);
+			writel_relaxed(0x0A, phy->mmio +
+				       QSERDES_COM_SYSCLK_EN_SEL_TXBAND);
+			writel_relaxed(0x08, phy->mmio +
+				       QSERDES_COM_SYSCLK_EN_SEL_TXBAND);
+			/*
+			 * Make sure workaround is deactivated before proceeding
+			 * with normal PHY operations.
+			 */
+			mb();
+		}
+	} else {
+		if (hibern8_exit_after_pwr_collapse) {
+			writel_relaxed(0x0A, phy->mmio +
+				       QSERDES_COM_SYSCLK_EN_SEL_TXBAND);
+			writel_relaxed(0x02, phy->mmio +
+				       QSERDES_COM_SYSCLK_EN_SEL_TXBAND);
+			/*
+			 * Make sure that above workaround is activated before
+			 * PHY analog power collapse.
+			 */
+			mb();
+		}
+
+		writel_relaxed(0x0, phy->mmio + UFS_PHY_POWER_DOWN_CONTROL);
+		/*
+		 * ensure that PHY knows its PHY analog rail is going
+		 * to be powered down
+		 */
+		mb();
+	}
+}
+
+static
+void ufs_qcom_phy_qmp_20nm_set_tx_lane_enable(struct ufs_qcom_phy *phy, u32 val)
+{
+	writel_relaxed(val & UFS_PHY_TX_LANE_ENABLE_MASK,
+			phy->mmio + UFS_PHY_TX_LANE_ENABLE);
+	mb();
+}
+
+static inline void ufs_qcom_phy_qmp_20nm_start_serdes(struct ufs_qcom_phy *phy)
+{
+	u32 tmp;
+
+	tmp = readl_relaxed(phy->mmio + UFS_PHY_PHY_START);
+	tmp &= ~MASK_SERDES_START;
+	tmp |= (1 << OFFSET_SERDES_START);
+	writel_relaxed(tmp, phy->mmio + UFS_PHY_PHY_START);
+	mb();
+}
+
+static int ufs_qcom_phy_qmp_20nm_is_pcs_ready(struct ufs_qcom_phy *phy_common)
+{
+	int err = 0;
+	u32 val;
+
+	err = readl_poll_timeout(phy_common->mmio + UFS_PHY_PCS_READY_STATUS,
+			val, (val & MASK_PCS_READY), 10, 1000000);
+	if (err)
+		dev_err(phy_common->dev, "%s: poll for pcs failed err = %d\n",
+			__func__, err);
+	return err;
+}
+
+static struct phy_ops ufs_qcom_phy_qmp_20nm_phy_ops = {
+	.init		= ufs_qcom_phy_qmp_20nm_init,
+	.exit		= ufs_qcom_phy_exit,
+	.power_on	= ufs_qcom_phy_power_on,
+	.power_off	= ufs_qcom_phy_power_off,
+	.owner		= THIS_MODULE,
+};
+
+static struct ufs_qcom_phy_specific_ops phy_20nm_ops = {
+	.calibrate_phy		= ufs_qcom_phy_qmp_20nm_phy_calibrate,
+	.start_serdes		= ufs_qcom_phy_qmp_20nm_start_serdes,
+	.is_physical_coding_sublayer_ready = ufs_qcom_phy_qmp_20nm_is_pcs_ready,
+	.set_tx_lane_enable	= ufs_qcom_phy_qmp_20nm_set_tx_lane_enable,
+	.power_control		= ufs_qcom_phy_qmp_20nm_power_control,
+};
+
+static int ufs_qcom_phy_qmp_20nm_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct phy *generic_phy;
+	struct ufs_qcom_phy_qmp_20nm *phy;
+	int err = 0;
+
+	phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL);
+	if (!phy) {
+		dev_err(dev, "%s: failed to allocate phy\n", __func__);
+		err = -ENOMEM;
+		goto out;
+	}
+
+	generic_phy = ufs_qcom_phy_generic_probe(pdev, &phy->common_cfg,
+				&ufs_qcom_phy_qmp_20nm_phy_ops, &phy_20nm_ops);
+
+	if (!generic_phy) {
+		dev_err(dev, "%s: ufs_qcom_phy_generic_probe() failed\n",
+			__func__);
+		err = -EIO;
+		goto out;
+	}
+
+	phy_set_drvdata(generic_phy, phy);
+
+	strlcpy(phy->common_cfg.name, UFS_PHY_NAME,
+			sizeof(phy->common_cfg.name));
+
+out:
+	return err;
+}
+
+static int ufs_qcom_phy_qmp_20nm_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct phy *generic_phy = to_phy(dev);
+	struct ufs_qcom_phy *ufs_qcom_phy = get_ufs_qcom_phy(generic_phy);
+	int err = 0;
+
+	err = ufs_qcom_phy_remove(generic_phy, ufs_qcom_phy);
+	if (err)
+		dev_err(dev, "%s: ufs_qcom_phy_remove failed = %d\n",
+			__func__, err);
+
+	return err;
+}
+
+static const struct of_device_id ufs_qcom_phy_qmp_20nm_of_match[] = {
+	{.compatible = "qcom,ufs-phy-qmp-20nm"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, ufs_qcom_phy_qmp_20nm_of_match);
+
+static struct platform_driver ufs_qcom_phy_qmp_20nm_driver = {
+	.probe = ufs_qcom_phy_qmp_20nm_probe,
+	.remove = ufs_qcom_phy_qmp_20nm_remove,
+	.driver = {
+		.of_match_table = ufs_qcom_phy_qmp_20nm_of_match,
+		.name = "ufs_qcom_phy_qmp_20nm",
+		.owner = THIS_MODULE,
+	},
+};
+
+module_platform_driver(ufs_qcom_phy_qmp_20nm_driver);
+
+MODULE_DESCRIPTION("Universal Flash Storage (UFS) QCOM PHY QMP 20nm");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/phy-qcom-ufs-qmp-20nm.h b/drivers/phy/phy-qcom-ufs-qmp-20nm.h
new file mode 100644
index 00000000000..4f3076bb3d7
--- /dev/null
+++ b/drivers/phy/phy-qcom-ufs-qmp-20nm.h
@@ -0,0 +1,235 @@
+/*
+ * Copyright (c) 2013-2015, Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef UFS_QCOM_PHY_QMP_20NM_H_
+#define UFS_QCOM_PHY_QMP_20NM_H_
+
+#include "phy-qcom-ufs-i.h"
+
+/* QCOM UFS PHY control registers */
+
+#define COM_OFF(x)     (0x000 + x)
+#define PHY_OFF(x)     (0xC00 + x)
+#define TX_OFF(n, x)   (0x400 + (0x400 * n) + x)
+#define RX_OFF(n, x)   (0x600 + (0x400 * n) + x)
+
+/* UFS PHY PLL block registers */
+#define QSERDES_COM_SYS_CLK_CTRL		COM_OFF(0x0)
+#define QSERDES_COM_PLL_VCOTAIL_EN		COM_OFF(0x04)
+#define QSERDES_COM_PLL_CNTRL			COM_OFF(0x14)
+#define QSERDES_COM_PLL_IP_SETI			COM_OFF(0x24)
+#define QSERDES_COM_CORE_CLK_IN_SYNC_SEL	COM_OFF(0x28)
+#define QSERDES_COM_BIAS_EN_CLKBUFLR_EN		COM_OFF(0x30)
+#define QSERDES_COM_PLL_CP_SETI			COM_OFF(0x34)
+#define QSERDES_COM_PLL_IP_SETP			COM_OFF(0x38)
+#define QSERDES_COM_PLL_CP_SETP			COM_OFF(0x3C)
+#define QSERDES_COM_SYSCLK_EN_SEL_TXBAND	COM_OFF(0x48)
+#define QSERDES_COM_RESETSM_CNTRL		COM_OFF(0x4C)
+#define QSERDES_COM_RESETSM_CNTRL2		COM_OFF(0x50)
+#define QSERDES_COM_PLLLOCK_CMP1		COM_OFF(0x90)
+#define QSERDES_COM_PLLLOCK_CMP2		COM_OFF(0x94)
+#define QSERDES_COM_PLLLOCK_CMP3		COM_OFF(0x98)
+#define QSERDES_COM_PLLLOCK_CMP_EN		COM_OFF(0x9C)
+#define QSERDES_COM_BGTC			COM_OFF(0xA0)
+#define QSERDES_COM_DEC_START1			COM_OFF(0xAC)
+#define QSERDES_COM_PLL_AMP_OS			COM_OFF(0xB0)
+#define QSERDES_COM_RES_CODE_UP_OFFSET		COM_OFF(0xD8)
+#define QSERDES_COM_RES_CODE_DN_OFFSET		COM_OFF(0xDC)
+#define QSERDES_COM_DIV_FRAC_START1		COM_OFF(0x100)
+#define QSERDES_COM_DIV_FRAC_START2		COM_OFF(0x104)
+#define QSERDES_COM_DIV_FRAC_START3		COM_OFF(0x108)
+#define QSERDES_COM_DEC_START2			COM_OFF(0x10C)
+#define QSERDES_COM_PLL_RXTXEPCLK_EN		COM_OFF(0x110)
+#define QSERDES_COM_PLL_CRCTRL			COM_OFF(0x114)
+#define QSERDES_COM_PLL_CLKEPDIV		COM_OFF(0x118)
+
+/* TX LANE n (0, 1) registers */
+#define QSERDES_TX_EMP_POST1_LVL(n)		TX_OFF(n, 0x08)
+#define QSERDES_TX_DRV_LVL(n)			TX_OFF(n, 0x0C)
+#define QSERDES_TX_LANE_MODE(n)			TX_OFF(n, 0x54)
+
+/* RX LANE n (0, 1) registers */
+#define QSERDES_RX_CDR_CONTROL1(n)		RX_OFF(n, 0x0)
+#define QSERDES_RX_CDR_CONTROL_HALF(n)		RX_OFF(n, 0x8)
+#define QSERDES_RX_RX_EQ_GAIN1_LSB(n)		RX_OFF(n, 0xA8)
+#define QSERDES_RX_RX_EQ_GAIN1_MSB(n)		RX_OFF(n, 0xAC)
+#define QSERDES_RX_RX_EQ_GAIN2_LSB(n)		RX_OFF(n, 0xB0)
+#define QSERDES_RX_RX_EQ_GAIN2_MSB(n)		RX_OFF(n, 0xB4)
+#define QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(n)	RX_OFF(n, 0xBC)
+#define QSERDES_RX_CDR_CONTROL_QUARTER(n)	RX_OFF(n, 0xC)
+#define QSERDES_RX_SIGDET_CNTRL(n)		RX_OFF(n, 0x100)
+
+/* UFS PHY registers */
+#define UFS_PHY_PHY_START			PHY_OFF(0x00)
+#define UFS_PHY_POWER_DOWN_CONTROL		PHY_OFF(0x4)
+#define UFS_PHY_TX_LANE_ENABLE			PHY_OFF(0x44)
+#define UFS_PHY_PWM_G1_CLK_DIVIDER		PHY_OFF(0x08)
+#define UFS_PHY_PWM_G2_CLK_DIVIDER		PHY_OFF(0x0C)
+#define UFS_PHY_PWM_G3_CLK_DIVIDER		PHY_OFF(0x10)
+#define UFS_PHY_PWM_G4_CLK_DIVIDER		PHY_OFF(0x14)
+#define UFS_PHY_CORECLK_PWM_G1_CLK_DIVIDER	PHY_OFF(0x34)
+#define UFS_PHY_CORECLK_PWM_G2_CLK_DIVIDER	PHY_OFF(0x38)
+#define UFS_PHY_CORECLK_PWM_G3_CLK_DIVIDER	PHY_OFF(0x3C)
+#define UFS_PHY_CORECLK_PWM_G4_CLK_DIVIDER	PHY_OFF(0x40)
+#define UFS_PHY_OMC_STATUS_RDVAL		PHY_OFF(0x68)
+#define UFS_PHY_LINE_RESET_TIME			PHY_OFF(0x28)
+#define UFS_PHY_LINE_RESET_GRANULARITY		PHY_OFF(0x2C)
+#define UFS_PHY_TSYNC_RSYNC_CNTL		PHY_OFF(0x48)
+#define UFS_PHY_PLL_CNTL			PHY_OFF(0x50)
+#define UFS_PHY_TX_LARGE_AMP_DRV_LVL		PHY_OFF(0x54)
+#define UFS_PHY_TX_SMALL_AMP_DRV_LVL		PHY_OFF(0x5C)
+#define UFS_PHY_TX_LARGE_AMP_POST_EMP_LVL	PHY_OFF(0x58)
+#define UFS_PHY_TX_SMALL_AMP_POST_EMP_LVL	PHY_OFF(0x60)
+#define UFS_PHY_CFG_CHANGE_CNT_VAL		PHY_OFF(0x64)
+#define UFS_PHY_RX_SYNC_WAIT_TIME		PHY_OFF(0x6C)
+#define UFS_PHY_TX_MIN_SLEEP_NOCONFIG_TIME_CAPABILITY	PHY_OFF(0xB4)
+#define UFS_PHY_RX_MIN_SLEEP_NOCONFIG_TIME_CAPABILITY	PHY_OFF(0xE0)
+#define UFS_PHY_TX_MIN_STALL_NOCONFIG_TIME_CAPABILITY	PHY_OFF(0xB8)
+#define UFS_PHY_RX_MIN_STALL_NOCONFIG_TIME_CAPABILITY	PHY_OFF(0xE4)
+#define UFS_PHY_TX_MIN_SAVE_CONFIG_TIME_CAPABILITY	PHY_OFF(0xBC)
+#define UFS_PHY_RX_MIN_SAVE_CONFIG_TIME_CAPABILITY	PHY_OFF(0xE8)
+#define UFS_PHY_RX_PWM_BURST_CLOSURE_LENGTH_CAPABILITY	PHY_OFF(0xFC)
+#define UFS_PHY_RX_MIN_ACTIVATETIME_CAPABILITY		PHY_OFF(0x100)
+#define UFS_PHY_RX_SIGDET_CTRL3				PHY_OFF(0x14c)
+#define UFS_PHY_RMMI_ATTR_CTRL			PHY_OFF(0x160)
+#define UFS_PHY_RMMI_RX_CFGUPDT_L1	(1 << 7)
+#define UFS_PHY_RMMI_TX_CFGUPDT_L1	(1 << 6)
+#define UFS_PHY_RMMI_CFGWR_L1		(1 << 5)
+#define UFS_PHY_RMMI_CFGRD_L1		(1 << 4)
+#define UFS_PHY_RMMI_RX_CFGUPDT_L0	(1 << 3)
+#define UFS_PHY_RMMI_TX_CFGUPDT_L0	(1 << 2)
+#define UFS_PHY_RMMI_CFGWR_L0		(1 << 1)
+#define UFS_PHY_RMMI_CFGRD_L0		(1 << 0)
+#define UFS_PHY_RMMI_ATTRID			PHY_OFF(0x164)
+#define UFS_PHY_RMMI_ATTRWRVAL			PHY_OFF(0x168)
+#define UFS_PHY_RMMI_ATTRRDVAL_L0_STATUS	PHY_OFF(0x16C)
+#define UFS_PHY_RMMI_ATTRRDVAL_L1_STATUS	PHY_OFF(0x170)
+#define UFS_PHY_PCS_READY_STATUS		PHY_OFF(0x174)
+
+#define UFS_PHY_TX_LANE_ENABLE_MASK		0x3
+
+/*
+ * This structure represents the 20nm specific phy.
+ * common_cfg MUST remain the first field in this structure
+ * in case extra fields are added. This way, when calling
+ * get_ufs_qcom_phy() of generic phy, we can extract the
+ * common phy structure (struct ufs_qcom_phy) out of it
+ * regardless of the relevant specific phy.
+ */
+struct ufs_qcom_phy_qmp_20nm {
+	struct ufs_qcom_phy common_cfg;
+};
+
+static struct ufs_qcom_phy_calibration phy_cal_table_rate_A_1_2_0[] = {
+	UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_POWER_DOWN_CONTROL, 0x01),
+	UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_RX_SIGDET_CTRL3, 0x0D),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_VCOTAIL_EN, 0xe1),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CRCTRL, 0xcc),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_SYSCLK_EN_SEL_TXBAND, 0x08),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CLKEPDIV, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_RXTXEPCLK_EN, 0x10),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START1, 0x82),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START2, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START1, 0x80),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START2, 0x80),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START3, 0x40),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP1, 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP2, 0x19),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP3, 0x00),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP_EN, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL, 0x90),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL2, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(0), 0xf2),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(0), 0x0c),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(0), 0x12),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(1), 0xf2),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(1), 0x0c),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(1), 0x12),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(0), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(0), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(0), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(0), 0x00),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(1), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(1), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(1), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(1), 0x00),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETI, 0x3f),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETP, 0x1b),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETP, 0x0f),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETI, 0x01),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_EMP_POST1_LVL(0), 0x2F),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_DRV_LVL(0), 0x20),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_EMP_POST1_LVL(1), 0x2F),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_DRV_LVL(1), 0x20),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(0), 0x68),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(1), 0x68),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(1), 0xdc),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(0), 0xdc),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x3),
+};
+
+static struct ufs_qcom_phy_calibration phy_cal_table_rate_A_1_3_0[] = {
+	UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_POWER_DOWN_CONTROL, 0x01),
+	UFS_QCOM_PHY_CAL_ENTRY(UFS_PHY_RX_SIGDET_CTRL3, 0x0D),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_VCOTAIL_EN, 0xe1),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CRCTRL, 0xcc),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_SYSCLK_EN_SEL_TXBAND, 0x08),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CLKEPDIV, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_RXTXEPCLK_EN, 0x10),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START1, 0x82),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START2, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START1, 0x80),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START2, 0x80),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DIV_FRAC_START3, 0x40),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP1, 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP2, 0x19),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP3, 0x00),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP_EN, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL, 0x90),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RESETSM_CNTRL2, 0x03),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(0), 0xf2),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(0), 0x0c),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(0), 0x12),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL1(1), 0xf2),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_HALF(1), 0x0c),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_CDR_CONTROL_QUARTER(1), 0x12),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(0), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(0), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(0), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(0), 0x00),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_LSB(1), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN1_MSB(1), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_LSB(1), 0xff),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQ_GAIN2_MSB(1), 0x00),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETI, 0x2b),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETP, 0x38),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CP_SETP, 0x3c),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RES_CODE_UP_OFFSET, 0x02),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_RES_CODE_DN_OFFSET, 0x02),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_IP_SETI, 0x01),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLL_CNTRL, 0x40),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(0), 0x68),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_TX_LANE_MODE(1), 0x68),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(1), 0xdc),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2(0), 0xdc),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x3),
+};
+
+static struct ufs_qcom_phy_calibration phy_cal_table_rate_B[] = {
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_DEC_START1, 0x98),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP1, 0x65),
+	UFS_QCOM_PHY_CAL_ENTRY(QSERDES_COM_PLLLOCK_CMP2, 0x1e),
+};
+
+#endif
diff --git a/include/linux/phy/phy-qcom-ufs.h b/include/linux/phy/phy-qcom-ufs.h
new file mode 100644
index 00000000000..9d18e9f948e
--- /dev/null
+++ b/include/linux/phy/phy-qcom-ufs.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2013-2015, Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef PHY_QCOM_UFS_H_
+#define PHY_QCOM_UFS_H_
+
+#include "phy.h"
+
+/**
+ * ufs_qcom_phy_enable_ref_clk() - Enable the phy
+ * ref clock.
+ * @phy: reference to a generic phy
+ *
+ * returns 0 for success, and non-zero for error.
+ */
+int ufs_qcom_phy_enable_ref_clk(struct phy *phy);
+
+/**
+ * ufs_qcom_phy_disable_ref_clk() - Disable the phy
+ * ref clock.
+ * @phy: reference to a generic phy.
+ */
+void ufs_qcom_phy_disable_ref_clk(struct phy *phy);
+
+/**
+ * ufs_qcom_phy_enable_dev_ref_clk() - Enable the device
+ * ref clock.
+ * @phy: reference to a generic phy.
+ */
+void ufs_qcom_phy_enable_dev_ref_clk(struct phy *phy);
+
+/**
+ * ufs_qcom_phy_disable_dev_ref_clk() - Disable the device
+ * ref clock.
+ * @phy: reference to a generic phy.
+ */
+void ufs_qcom_phy_disable_dev_ref_clk(struct phy *phy);
+
+int ufs_qcom_phy_enable_iface_clk(struct phy *phy);
+void ufs_qcom_phy_disable_iface_clk(struct phy *phy);
+int ufs_qcom_phy_start_serdes(struct phy *phy);
+int ufs_qcom_phy_set_tx_lane_enable(struct phy *phy, u32 tx_lanes);
+int ufs_qcom_phy_calibrate_phy(struct phy *phy, bool is_rate_B);
+int ufs_qcom_phy_is_pcs_ready(struct phy *phy);
+void ufs_qcom_phy_save_controller_version(struct phy *phy,
+			u8 major, u16 minor, u16 step);
+
+#endif /* PHY_QCOM_UFS_H_ */
-- 
cgit v1.2.3-70-g09d2


From 3c33f5b99d688deafd21d4a770303691c7c3a320 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 20 Jan 2015 09:26:19 -0600
Subject: livepatch: support for repatching a function

Add support for patching a function multiple times.  If multiple patches
affect a function, the function in the most recently enabled patch
"wins".  This enables a cumulative patch upgrade path, where each patch
is a superset of previous patches.

This requires restructuring the data a little bit.  With the current
design, where each klp_func struct has its own ftrace_ops, we'd have to
unregister the old ops and then register the new ops, because
FTRACE_OPS_FL_IPMODIFY prevents us from having two ops registered for
the same function at the same time.  That would leave a regression
window where the function isn't patched at all (not good for a patch
upgrade path).

This patch replaces the per-klp_func ftrace_ops with a global klp_ops
list, with one ftrace_ops per original function.  A single ftrace_ops is
shared between all klp_funcs which have the same old_addr.  This allows
the switch between function versions to happen instantaneously by
updating the klp_ops struct's func_stack list.  The winner is the
klp_func at the top of the func_stack (front of the list).

[ jkosina@suse.cz: turn WARN_ON() into WARN_ON_ONCE() in ftrace handler to
  avoid storm in pathological cases ]

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/livepatch.h |   4 +-
 kernel/livepatch/core.c   | 170 ++++++++++++++++++++++++++++++++--------------
 2 files changed, 121 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index 950bc615842..f14c6fb262b 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -40,8 +40,8 @@ enum klp_state {
  * @old_addr:	a hint conveying at what address the old function
  *		can be found (optional, vmlinux patches only)
  * @kobj:	kobject for sysfs resources
- * @fops:	ftrace operations structure
  * @state:	tracks function-level patch application state
+ * @stack_node:	list node for klp_ops func_stack list
  */
 struct klp_func {
 	/* external */
@@ -59,8 +59,8 @@ struct klp_func {
 
 	/* internal */
 	struct kobject kobj;
-	struct ftrace_ops *fops;
 	enum klp_state state;
+	struct list_head stack_node;
 };
 
 /**
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 2401e7f955d..bc05d390ce8 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -29,17 +29,53 @@
 #include <linux/kallsyms.h>
 #include <linux/livepatch.h>
 
-/*
- * The klp_mutex protects the klp_patches list and state transitions of any
- * structure reachable from the patches list.  References to any structure must
- * be obtained under mutex protection.
+/**
+ * struct klp_ops - structure for tracking registered ftrace ops structs
+ *
+ * A single ftrace_ops is shared between all enabled replacement functions
+ * (klp_func structs) which have the same old_addr.  This allows the switch
+ * between function versions to happen instantaneously by updating the klp_ops
+ * struct's func_stack list.  The winner is the klp_func at the top of the
+ * func_stack (front of the list).
+ *
+ * @node:	node for the global klp_ops list
+ * @func_stack:	list head for the stack of klp_func's (active func is on top)
+ * @fops:	registered ftrace ops struct
  */
+struct klp_ops {
+	struct list_head node;
+	struct list_head func_stack;
+	struct ftrace_ops fops;
+};
 
+/*
+ * The klp_mutex protects the global lists and state transitions of any
+ * structure reachable from them.  References to any structure must be obtained
+ * under mutex protection (except in klp_ftrace_handler(), which uses RCU to
+ * ensure it gets consistent data).
+ */
 static DEFINE_MUTEX(klp_mutex);
+
 static LIST_HEAD(klp_patches);
+static LIST_HEAD(klp_ops);
 
 static struct kobject *klp_root_kobj;
 
+static struct klp_ops *klp_find_ops(unsigned long old_addr)
+{
+	struct klp_ops *ops;
+	struct klp_func *func;
+
+	list_for_each_entry(ops, &klp_ops, node) {
+		func = list_first_entry(&ops->func_stack, struct klp_func,
+					stack_node);
+		if (func->old_addr == old_addr)
+			return ops;
+	}
+
+	return NULL;
+}
+
 static bool klp_is_module(struct klp_object *obj)
 {
 	return obj->name;
@@ -267,16 +303,28 @@ static int klp_write_object_relocations(struct module *pmod,
 
 static void notrace klp_ftrace_handler(unsigned long ip,
 				       unsigned long parent_ip,
-				       struct ftrace_ops *ops,
+				       struct ftrace_ops *fops,
 				       struct pt_regs *regs)
 {
-	struct klp_func *func = ops->private;
+	struct klp_ops *ops;
+	struct klp_func *func;
+
+	ops = container_of(fops, struct klp_ops, fops);
+
+	rcu_read_lock();
+	func = list_first_or_null_rcu(&ops->func_stack, struct klp_func,
+				      stack_node);
+	rcu_read_unlock();
+
+	if (WARN_ON_ONCE(!func))
+		return;
 
 	klp_arch_set_pc(regs, (unsigned long)func->new_func);
 }
 
 static int klp_disable_func(struct klp_func *func)
 {
+	struct klp_ops *ops;
 	int ret;
 
 	if (WARN_ON(func->state != KLP_ENABLED))
@@ -285,16 +333,28 @@ static int klp_disable_func(struct klp_func *func)
 	if (WARN_ON(!func->old_addr))
 		return -EINVAL;
 
-	ret = unregister_ftrace_function(func->fops);
-	if (ret) {
-		pr_err("failed to unregister ftrace handler for function '%s' (%d)\n",
-		       func->old_name, ret);
-		return ret;
-	}
+	ops = klp_find_ops(func->old_addr);
+	if (WARN_ON(!ops))
+		return -EINVAL;
 
-	ret = ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0);
-	if (ret)
-		pr_warn("function unregister succeeded but failed to clear the filter\n");
+	if (list_is_singular(&ops->func_stack)) {
+		ret = unregister_ftrace_function(&ops->fops);
+		if (ret) {
+			pr_err("failed to unregister ftrace handler for function '%s' (%d)\n",
+			       func->old_name, ret);
+			return ret;
+		}
+
+		ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0);
+		if (ret)
+			pr_warn("function unregister succeeded but failed to clear the filter\n");
+
+		list_del_rcu(&func->stack_node);
+		list_del(&ops->node);
+		kfree(ops);
+	} else {
+		list_del_rcu(&func->stack_node);
+	}
 
 	func->state = KLP_DISABLED;
 
@@ -303,6 +363,7 @@ static int klp_disable_func(struct klp_func *func)
 
 static int klp_enable_func(struct klp_func *func)
 {
+	struct klp_ops *ops;
 	int ret;
 
 	if (WARN_ON(!func->old_addr))
@@ -311,22 +372,50 @@ static int klp_enable_func(struct klp_func *func)
 	if (WARN_ON(func->state != KLP_DISABLED))
 		return -EINVAL;
 
-	ret = ftrace_set_filter_ip(func->fops, func->old_addr, 0, 0);
-	if (ret) {
-		pr_err("failed to set ftrace filter for function '%s' (%d)\n",
-		       func->old_name, ret);
-		return ret;
-	}
+	ops = klp_find_ops(func->old_addr);
+	if (!ops) {
+		ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+		if (!ops)
+			return -ENOMEM;
+
+		ops->fops.func = klp_ftrace_handler;
+		ops->fops.flags = FTRACE_OPS_FL_SAVE_REGS |
+				  FTRACE_OPS_FL_DYNAMIC |
+				  FTRACE_OPS_FL_IPMODIFY;
+
+		list_add(&ops->node, &klp_ops);
+
+		INIT_LIST_HEAD(&ops->func_stack);
+		list_add_rcu(&func->stack_node, &ops->func_stack);
+
+		ret = ftrace_set_filter_ip(&ops->fops, func->old_addr, 0, 0);
+		if (ret) {
+			pr_err("failed to set ftrace filter for function '%s' (%d)\n",
+			       func->old_name, ret);
+			goto err;
+		}
+
+		ret = register_ftrace_function(&ops->fops);
+		if (ret) {
+			pr_err("failed to register ftrace handler for function '%s' (%d)\n",
+			       func->old_name, ret);
+			ftrace_set_filter_ip(&ops->fops, func->old_addr, 1, 0);
+			goto err;
+		}
+
 
-	ret = register_ftrace_function(func->fops);
-	if (ret) {
-		pr_err("failed to register ftrace handler for function '%s' (%d)\n",
-		       func->old_name, ret);
-		ftrace_set_filter_ip(func->fops, func->old_addr, 1, 0);
 	} else {
-		func->state = KLP_ENABLED;
+		list_add_rcu(&func->stack_node, &ops->func_stack);
 	}
 
+	func->state = KLP_ENABLED;
+
+	return ret;
+
+err:
+	list_del_rcu(&func->stack_node);
+	list_del(&ops->node);
+	kfree(ops);
 	return ret;
 }
 
@@ -582,10 +671,6 @@ static struct kobj_type klp_ktype_patch = {
 
 static void klp_kobj_release_func(struct kobject *kobj)
 {
-	struct klp_func *func;
-
-	func = container_of(kobj, struct klp_func, kobj);
-	kfree(func->fops);
 }
 
 static struct kobj_type klp_ktype_func = {
@@ -642,28 +727,11 @@ static void klp_free_patch(struct klp_patch *patch)
 
 static int klp_init_func(struct klp_object *obj, struct klp_func *func)
 {
-	struct ftrace_ops *ops;
-	int ret;
-
-	ops = kzalloc(sizeof(*ops), GFP_KERNEL);
-	if (!ops)
-		return -ENOMEM;
-
-	ops->private = func;
-	ops->func = klp_ftrace_handler;
-	ops->flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_DYNAMIC |
-		     FTRACE_OPS_FL_IPMODIFY;
-	func->fops = ops;
+	INIT_LIST_HEAD(&func->stack_node);
 	func->state = KLP_DISABLED;
 
-	ret = kobject_init_and_add(&func->kobj, &klp_ktype_func,
-				   obj->kobj, func->old_name);
-	if (ret) {
-		kfree(func->fops);
-		return ret;
-	}
-
-	return 0;
+	return kobject_init_and_add(&func->kobj, &klp_ktype_func,
+				    obj->kobj, func->old_name);
 }
 
 /* parts of the initialization that is done only when the object is loaded */
-- 
cgit v1.2.3-70-g09d2


From 97b713ba3ebaa6c8d84c2c720f5468a7c6a6eb4e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 14 Jan 2015 10:42:31 +0100
Subject: fs: kill BDI_CAP_SWAP_BACKED

This bdi flag isn't too useful - we can determine that a vma is backed by
either swap or shmem trivially in the caller.

This also allows removing the backing_dev_info instaces for swap and shmem
in favor of noop_backing_dev_info.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/backing-dev.h | 13 -------------
 mm/madvise.c                | 17 ++++++++++-------
 mm/shmem.c                  | 25 +++++++------------------
 mm/swap.c                   |  2 --
 mm/swap_state.c             |  7 +------
 5 files changed, 18 insertions(+), 46 deletions(-)

(limited to 'include')

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5da6012b7a1..e936cea856d 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -238,8 +238,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_WRITE_MAP:      Can be mapped for writing
  * BDI_CAP_EXEC_MAP:       Can be mapped for execution
  *
- * BDI_CAP_SWAP_BACKED:    Count shmem/tmpfs objects as swap-backed.
- *
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
@@ -250,7 +248,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_WRITE_MAP	0x00000020
 #define BDI_CAP_EXEC_MAP	0x00000040
 #define BDI_CAP_NO_ACCT_WB	0x00000080
-#define BDI_CAP_SWAP_BACKED	0x00000100
 #define BDI_CAP_STABLE_WRITES	0x00000200
 #define BDI_CAP_STRICTLIMIT	0x00000400
 
@@ -329,11 +326,6 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
 				      BDI_CAP_NO_WRITEBACK));
 }
 
-static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
-{
-	return bdi->capabilities & BDI_CAP_SWAP_BACKED;
-}
-
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -344,11 +336,6 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping)
 	return bdi_cap_account_dirty(mapping->backing_dev_info);
 }
 
-static inline bool mapping_cap_swap_backed(struct address_space *mapping)
-{
-	return bdi_cap_swap_backed(mapping->backing_dev_info);
-}
-
 static inline int bdi_sched_wait(void *word)
 {
 	schedule();
diff --git a/mm/madvise.c b/mm/madvise.c
index a271adc9328..1383a8916bc 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -222,19 +222,22 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	struct file *file = vma->vm_file;
 
 #ifdef CONFIG_SWAP
-	if (!file || mapping_cap_swap_backed(file->f_mapping)) {
+	if (!file) {
 		*prev = vma;
-		if (!file)
-			force_swapin_readahead(vma, start, end);
-		else
-			force_shm_swapin_readahead(vma, start, end,
-						file->f_mapping);
+		force_swapin_readahead(vma, start, end);
 		return 0;
 	}
-#endif
 
+	if (shmem_mapping(file->f_mapping)) {
+		*prev = vma;
+		force_shm_swapin_readahead(vma, start, end,
+					file->f_mapping);
+		return 0;
+	}
+#else
 	if (!file)
 		return -EBADF;
+#endif
 
 	if (file->f_mapping->a_ops->get_xip_mem) {
 		/* no bad return value, but ignore advice */
diff --git a/mm/shmem.c b/mm/shmem.c
index 73ba1df7c8b..1b77eaf589f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -191,11 +191,6 @@ static const struct inode_operations shmem_dir_inode_operations;
 static const struct inode_operations shmem_special_inode_operations;
 static const struct vm_operations_struct shmem_vm_ops;
 
-static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-};
-
 static LIST_HEAD(shmem_swaplist);
 static DEFINE_MUTEX(shmem_swaplist_mutex);
 
@@ -765,11 +760,11 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		goto redirty;
 
 	/*
-	 * shmem_backing_dev_info's capabilities prevent regular writeback or
-	 * sync from ever calling shmem_writepage; but a stacking filesystem
-	 * might use ->writepage of its underlying filesystem, in which case
-	 * tmpfs should write out to swap only in response to memory pressure,
-	 * and not for the writeback threads or sync.
+	 * Our capabilities prevent regular writeback or sync from ever calling
+	 * shmem_writepage; but a stacking filesystem might use ->writepage of
+	 * its underlying filesystem, in which case tmpfs should write out to
+	 * swap only in response to memory pressure, and not for the writeback
+	 * threads or sync.
 	 */
 	if (!wbc->for_reclaim) {
 		WARN_ON_ONCE(1);	/* Still happens? Tell us about it! */
@@ -1415,7 +1410,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_blocks = 0;
-		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
+		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_generation = get_seconds();
 		info = SHMEM_I(inode);
@@ -1461,7 +1456,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 
 bool shmem_mapping(struct address_space *mapping)
 {
-	return mapping->backing_dev_info == &shmem_backing_dev_info;
+	return mapping->host->i_sb->s_op == &shmem_ops;
 }
 
 #ifdef CONFIG_TMPFS
@@ -3226,10 +3221,6 @@ int __init shmem_init(void)
 	if (shmem_inode_cachep)
 		return 0;
 
-	error = bdi_init(&shmem_backing_dev_info);
-	if (error)
-		goto out4;
-
 	error = shmem_init_inodecache();
 	if (error)
 		goto out3;
@@ -3253,8 +3244,6 @@ out1:
 out2:
 	shmem_destroy_inodecache();
 out3:
-	bdi_destroy(&shmem_backing_dev_info);
-out4:
 	shm_mnt = ERR_PTR(error);
 	return error;
 }
diff --git a/mm/swap.c b/mm/swap.c
index 8a12b33936b..4e0109a2f37 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1138,8 +1138,6 @@ void __init swap_setup(void)
 #ifdef CONFIG_SWAP
 	int i;
 
-	if (bdi_init(swapper_spaces[0].backing_dev_info))
-		panic("Failed to init swap bdi");
 	for (i = 0; i < MAX_SWAPFILES; i++) {
 		spin_lock_init(&swapper_spaces[i].tree_lock);
 		INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 9711342987a..1c137b69ecd 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -32,17 +32,12 @@ static const struct address_space_operations swap_aops = {
 #endif
 };
 
-static struct backing_dev_info swap_backing_dev_info = {
-	.name		= "swap",
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
-};
-
 struct address_space swapper_spaces[MAX_SWAPFILES] = {
 	[0 ... MAX_SWAPFILES - 1] = {
 		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
 		.i_mmap_writable = ATOMIC_INIT(0),
 		.a_ops		= &swap_aops,
-		.backing_dev_info = &swap_backing_dev_info,
+		.backing_dev_info = &noop_backing_dev_info,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From b4caecd48005fbed3949dde6c1cb233142fd69e9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 14 Jan 2015 10:42:32 +0100
Subject: fs: introduce f_op->mmap_capabilities for nommu mmap support

Since "BDI: Provide backing device capability information [try #3]" the
backing_dev_info structure also provides flags for the kind of mmap
operation available in a nommu environment, which is entirely unrelated
to it's original purpose.

Introduce a new nommu-only file operation to provide this information to
the nommu mmap code instead.  Splitting this from the backing_dev_info
structure allows to remove lots of backing_dev_info instance that aren't
otherwise needed, and entirely gets rid of the concept of providing a
backing_dev_info for a character device.  It also removes the need for
the mtd_inodefs filesystem.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Tejun Heo <tj@kernel.org>
Acked-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 Documentation/nommu-mmap.txt                    |  8 +--
 block/blk-core.c                                |  2 +-
 drivers/char/mem.c                              | 64 ++++++++++----------
 drivers/mtd/mtdchar.c                           | 72 ++++------------------
 drivers/mtd/mtdconcat.c                         | 10 ----
 drivers/mtd/mtdcore.c                           | 80 +++++++------------------
 drivers/mtd/mtdpart.c                           |  1 -
 drivers/staging/lustre/lustre/llite/llite_lib.c |  2 +-
 fs/9p/v9fs.c                                    |  2 +-
 fs/afs/volume.c                                 |  2 +-
 fs/aio.c                                        | 14 +----
 fs/btrfs/disk-io.c                              |  3 +-
 fs/char_dev.c                                   | 24 --------
 fs/cifs/connect.c                               |  2 +-
 fs/coda/inode.c                                 |  2 +-
 fs/configfs/configfs_internal.h                 |  2 -
 fs/configfs/inode.c                             | 18 +-----
 fs/configfs/mount.c                             | 11 +---
 fs/ecryptfs/main.c                              |  2 +-
 fs/exofs/super.c                                |  2 +-
 fs/ncpfs/inode.c                                |  2 +-
 fs/ramfs/file-nommu.c                           |  7 +++
 fs/ramfs/inode.c                                | 22 +------
 fs/romfs/mmap-nommu.c                           | 10 ++++
 fs/ubifs/super.c                                |  2 +-
 include/linux/backing-dev.h                     | 33 ++--------
 include/linux/cdev.h                            |  2 -
 include/linux/fs.h                              | 23 +++++++
 include/linux/mtd/mtd.h                         |  2 +
 mm/backing-dev.c                                |  7 +--
 mm/nommu.c                                      | 69 ++++++++++-----------
 security/security.c                             | 13 ++--
 32 files changed, 169 insertions(+), 346 deletions(-)

(limited to 'include')

diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt
index 8e1ddec2c78..ae57b9ea0d4 100644
--- a/Documentation/nommu-mmap.txt
+++ b/Documentation/nommu-mmap.txt
@@ -43,12 +43,12 @@ and it's also much more restricted in the latter case:
            even if this was created by another process.
 
          - If possible, the file mapping will be directly on the backing device
-           if the backing device has the BDI_CAP_MAP_DIRECT capability and
+           if the backing device has the NOMMU_MAP_DIRECT capability and
            appropriate mapping protection capabilities. Ramfs, romfs, cramfs
            and mtd might all permit this.
 
 	 - If the backing device device can't or won't permit direct sharing,
-           but does have the BDI_CAP_MAP_COPY capability, then a copy of the
+           but does have the NOMMU_MAP_COPY capability, then a copy of the
            appropriate bit of the file will be read into a contiguous bit of
            memory and any extraneous space beyond the EOF will be cleared
 
@@ -220,7 +220,7 @@ directly (can't be copied).
 
 The file->f_op->mmap() operation will be called to actually inaugurate the
 mapping. It can be rejected at that point. Returning the ENOSYS error will
-cause the mapping to be copied instead if BDI_CAP_MAP_COPY is specified.
+cause the mapping to be copied instead if NOMMU_MAP_COPY is specified.
 
 The vm_ops->close() routine will be invoked when the last mapping on a chardev
 is removed. An existing mapping will be shared, partially or not, if possible
@@ -232,7 +232,7 @@ want to handle it, despite the fact it's got an operation. For instance, it
 might try directing the call to a secondary driver which turns out not to
 implement it. Such is the case for the framebuffer driver which attempts to
 direct the call to the device-specific driver. Under such circumstances, the
-mapping request will be rejected if BDI_CAP_MAP_COPY is not specified, and a
+mapping request will be rejected if NOMMU_MAP_COPY is not specified, and a
 copy mapped otherwise.
 
 IMPORTANT NOTE:
diff --git a/block/blk-core.c b/block/blk-core.c
index 3ad405571dc..928aac29bcc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -607,7 +607,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.state = 0;
-	q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+	q->backing_dev_info.capabilities = 0;
 	q->backing_dev_info.name = "block";
 	q->node = node_id;
 
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 4c58333b425..9a6b63783a9 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -287,13 +287,24 @@ static unsigned long get_unmapped_area_mem(struct file *file,
 	return pgoff << PAGE_SHIFT;
 }
 
+/* permit direct mmap, for read, write or exec */
+static unsigned memory_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_DIRECT |
+		NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
+static unsigned zero_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_COPY;
+}
+
 /* can't do an in-place private mapping if there's no MMU */
 static inline int private_mapping_ok(struct vm_area_struct *vma)
 {
 	return vma->vm_flags & VM_MAYSHARE;
 }
 #else
-#define get_unmapped_area_mem	NULL
 
 static inline int private_mapping_ok(struct vm_area_struct *vma)
 {
@@ -721,7 +732,10 @@ static const struct file_operations mem_fops = {
 	.write		= write_mem,
 	.mmap		= mmap_mem,
 	.open		= open_mem,
+#ifndef CONFIG_MMU
 	.get_unmapped_area = get_unmapped_area_mem,
+	.mmap_capabilities = memory_mmap_capabilities,
+#endif
 };
 
 #ifdef CONFIG_DEVKMEM
@@ -731,7 +745,10 @@ static const struct file_operations kmem_fops = {
 	.write		= write_kmem,
 	.mmap		= mmap_kmem,
 	.open		= open_kmem,
+#ifndef CONFIG_MMU
 	.get_unmapped_area = get_unmapped_area_mem,
+	.mmap_capabilities = memory_mmap_capabilities,
+#endif
 };
 #endif
 
@@ -760,16 +777,9 @@ static const struct file_operations zero_fops = {
 	.read_iter	= read_iter_zero,
 	.aio_write	= aio_write_zero,
 	.mmap		= mmap_zero,
-};
-
-/*
- * capabilities for /dev/zero
- * - permits private mappings, "copies" are taken of the source of zeros
- * - no writeback happens
- */
-static struct backing_dev_info zero_bdi = {
-	.name		= "char/mem",
-	.capabilities	= BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK,
+#ifndef CONFIG_MMU
+	.mmap_capabilities = zero_mmap_capabilities,
+#endif
 };
 
 static const struct file_operations full_fops = {
@@ -783,22 +793,22 @@ static const struct memdev {
 	const char *name;
 	umode_t mode;
 	const struct file_operations *fops;
-	struct backing_dev_info *dev_info;
+	fmode_t fmode;
 } devlist[] = {
-	 [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
+	 [1] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET },
 #ifdef CONFIG_DEVKMEM
-	 [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
+	 [2] = { "kmem", 0, &kmem_fops, FMODE_UNSIGNED_OFFSET },
 #endif
-	 [3] = { "null", 0666, &null_fops, NULL },
+	 [3] = { "null", 0666, &null_fops, 0 },
 #ifdef CONFIG_DEVPORT
-	 [4] = { "port", 0, &port_fops, NULL },
+	 [4] = { "port", 0, &port_fops, 0 },
 #endif
-	 [5] = { "zero", 0666, &zero_fops, &zero_bdi },
-	 [7] = { "full", 0666, &full_fops, NULL },
-	 [8] = { "random", 0666, &random_fops, NULL },
-	 [9] = { "urandom", 0666, &urandom_fops, NULL },
+	 [5] = { "zero", 0666, &zero_fops, 0 },
+	 [7] = { "full", 0666, &full_fops, 0 },
+	 [8] = { "random", 0666, &random_fops, 0 },
+	 [9] = { "urandom", 0666, &urandom_fops, 0 },
 #ifdef CONFIG_PRINTK
-	[11] = { "kmsg", 0644, &kmsg_fops, NULL },
+	[11] = { "kmsg", 0644, &kmsg_fops, 0 },
 #endif
 };
 
@@ -816,12 +826,7 @@ static int memory_open(struct inode *inode, struct file *filp)
 		return -ENXIO;
 
 	filp->f_op = dev->fops;
-	if (dev->dev_info)
-		filp->f_mapping->backing_dev_info = dev->dev_info;
-
-	/* Is /dev/mem or /dev/kmem ? */
-	if (dev->dev_info == &directly_mappable_cdev_bdi)
-		filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+	filp->f_mode |= dev->fmode;
 
 	if (dev->fops->open)
 		return dev->fops->open(inode, filp);
@@ -846,11 +851,6 @@ static struct class *mem_class;
 static int __init chr_dev_init(void)
 {
 	int minor;
-	int err;
-
-	err = bdi_init(&zero_bdi);
-	if (err)
-		return err;
 
 	if (register_chrdev(MEM_MAJOR, "mem", &memory_fops))
 		printk("unable to get major %d for memory devs\n", MEM_MAJOR);
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 53563955931..55fa27ecf4e 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -49,7 +49,6 @@ static DEFINE_MUTEX(mtd_mutex);
  */
 struct mtd_file_info {
 	struct mtd_info *mtd;
-	struct inode *ino;
 	enum mtd_file_modes mode;
 };
 
@@ -59,10 +58,6 @@ static loff_t mtdchar_lseek(struct file *file, loff_t offset, int orig)
 	return fixed_size_llseek(file, offset, orig, mfi->mtd->size);
 }
 
-static int count;
-static struct vfsmount *mnt;
-static struct file_system_type mtd_inodefs_type;
-
 static int mtdchar_open(struct inode *inode, struct file *file)
 {
 	int minor = iminor(inode);
@@ -70,7 +65,6 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 	int ret = 0;
 	struct mtd_info *mtd;
 	struct mtd_file_info *mfi;
-	struct inode *mtd_ino;
 
 	pr_debug("MTD_open\n");
 
@@ -78,10 +72,6 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 	if ((file->f_mode & FMODE_WRITE) && (minor & 1))
 		return -EACCES;
 
-	ret = simple_pin_fs(&mtd_inodefs_type, &mnt, &count);
-	if (ret)
-		return ret;
-
 	mutex_lock(&mtd_mutex);
 	mtd = get_mtd_device(NULL, devnum);
 
@@ -95,43 +85,26 @@ static int mtdchar_open(struct inode *inode, struct file *file)
 		goto out1;
 	}
 
-	mtd_ino = iget_locked(mnt->mnt_sb, devnum);
-	if (!mtd_ino) {
-		ret = -ENOMEM;
-		goto out1;
-	}
-	if (mtd_ino->i_state & I_NEW) {
-		mtd_ino->i_private = mtd;
-		mtd_ino->i_mode = S_IFCHR;
-		mtd_ino->i_data.backing_dev_info = mtd->backing_dev_info;
-		unlock_new_inode(mtd_ino);
-	}
-	file->f_mapping = mtd_ino->i_mapping;
-
 	/* You can't open it RW if it's not a writeable device */
 	if ((file->f_mode & FMODE_WRITE) && !(mtd->flags & MTD_WRITEABLE)) {
 		ret = -EACCES;
-		goto out2;
+		goto out1;
 	}
 
 	mfi = kzalloc(sizeof(*mfi), GFP_KERNEL);
 	if (!mfi) {
 		ret = -ENOMEM;
-		goto out2;
+		goto out1;
 	}
-	mfi->ino = mtd_ino;
 	mfi->mtd = mtd;
 	file->private_data = mfi;
 	mutex_unlock(&mtd_mutex);
 	return 0;
 
-out2:
-	iput(mtd_ino);
 out1:
 	put_mtd_device(mtd);
 out:
 	mutex_unlock(&mtd_mutex);
-	simple_release_fs(&mnt, &count);
 	return ret;
 } /* mtdchar_open */
 
@@ -148,12 +121,9 @@ static int mtdchar_close(struct inode *inode, struct file *file)
 	if ((file->f_mode & FMODE_WRITE))
 		mtd_sync(mtd);
 
-	iput(mfi->ino);
-
 	put_mtd_device(mtd);
 	file->private_data = NULL;
 	kfree(mfi);
-	simple_release_fs(&mnt, &count);
 
 	return 0;
 } /* mtdchar_close */
@@ -1117,6 +1087,13 @@ static unsigned long mtdchar_get_unmapped_area(struct file *file,
 	ret = mtd_get_unmapped_area(mtd, len, offset, flags);
 	return ret == -EOPNOTSUPP ? -ENODEV : ret;
 }
+
+static unsigned mtdchar_mmap_capabilities(struct file *file)
+{
+	struct mtd_file_info *mfi = file->private_data;
+
+	return mtd_mmap_capabilities(mfi->mtd);
+}
 #endif
 
 /*
@@ -1160,27 +1137,10 @@ static const struct file_operations mtd_fops = {
 	.mmap		= mtdchar_mmap,
 #ifndef CONFIG_MMU
 	.get_unmapped_area = mtdchar_get_unmapped_area,
+	.mmap_capabilities = mtdchar_mmap_capabilities,
 #endif
 };
 
-static const struct super_operations mtd_ops = {
-	.drop_inode = generic_delete_inode,
-	.statfs = simple_statfs,
-};
-
-static struct dentry *mtd_inodefs_mount(struct file_system_type *fs_type,
-				int flags, const char *dev_name, void *data)
-{
-	return mount_pseudo(fs_type, "mtd_inode:", &mtd_ops, NULL, MTD_INODE_FS_MAGIC);
-}
-
-static struct file_system_type mtd_inodefs_type = {
-       .name = "mtd_inodefs",
-       .mount = mtd_inodefs_mount,
-       .kill_sb = kill_anon_super,
-};
-MODULE_ALIAS_FS("mtd_inodefs");
-
 int __init init_mtdchar(void)
 {
 	int ret;
@@ -1193,23 +1153,11 @@ int __init init_mtdchar(void)
 		return ret;
 	}
 
-	ret = register_filesystem(&mtd_inodefs_type);
-	if (ret) {
-		pr_err("Can't register mtd_inodefs filesystem, error %d\n",
-		       ret);
-		goto err_unregister_chdev;
-	}
-
-	return ret;
-
-err_unregister_chdev:
-	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 	return ret;
 }
 
 void __exit cleanup_mtdchar(void)
 {
-	unregister_filesystem(&mtd_inodefs_type);
 	__unregister_chrdev(MTD_CHAR_MAJOR, 0, 1 << MINORBITS, "mtd");
 }
 
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index b9000563b9f..eacc3aac732 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -732,8 +732,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 
 	concat->mtd.ecc_stats.badblocks = subdev[0]->ecc_stats.badblocks;
 
-	concat->mtd.backing_dev_info = subdev[0]->backing_dev_info;
-
 	concat->subdev[0] = subdev[0];
 
 	for (i = 1; i < num_devs; i++) {
@@ -761,14 +759,6 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 				    subdev[i]->flags & MTD_WRITEABLE;
 		}
 
-		/* only permit direct mapping if the BDIs are all the same
-		 * - copy-mapping is still permitted
-		 */
-		if (concat->mtd.backing_dev_info !=
-		    subdev[i]->backing_dev_info)
-			concat->mtd.backing_dev_info =
-				&default_backing_dev_info;
-
 		concat->mtd.size += subdev[i]->size;
 		concat->mtd.ecc_stats.badblocks +=
 			subdev[i]->ecc_stats.badblocks;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 4c611871d7e..ff38a1df22f 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -43,33 +43,7 @@
 
 #include "mtdcore.h"
 
-/*
- * backing device capabilities for non-mappable devices (such as NAND flash)
- * - permits private mappings, copies are taken of the data
- */
-static struct backing_dev_info mtd_bdi_unmappable = {
-	.capabilities	= BDI_CAP_MAP_COPY,
-};
-
-/*
- * backing device capabilities for R/O mappable devices (such as ROM)
- * - permits private mappings, copies are taken of the data
- * - permits non-writable shared mappings
- */
-static struct backing_dev_info mtd_bdi_ro_mappable = {
-	.capabilities	= (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT |
-			   BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP),
-};
-
-/*
- * backing device capabilities for writable mappable devices (such as RAM)
- * - permits private mappings, copies are taken of the data
- * - permits non-writable shared mappings
- */
-static struct backing_dev_info mtd_bdi_rw_mappable = {
-	.capabilities	= (BDI_CAP_MAP_COPY | BDI_CAP_MAP_DIRECT |
-			   BDI_CAP_EXEC_MAP | BDI_CAP_READ_MAP |
-			   BDI_CAP_WRITE_MAP),
+static struct backing_dev_info mtd_bdi = {
 };
 
 static int mtd_cls_suspend(struct device *dev, pm_message_t state);
@@ -365,6 +339,22 @@ static struct device_type mtd_devtype = {
 	.release	= mtd_release,
 };
 
+#ifndef CONFIG_MMU
+unsigned mtd_mmap_capabilities(struct mtd_info *mtd)
+{
+	switch (mtd->type) {
+	case MTD_RAM:
+		return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
+			NOMMU_MAP_READ | NOMMU_MAP_WRITE;
+	case MTD_ROM:
+		return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC |
+			NOMMU_MAP_READ;
+	default:
+		return NOMMU_MAP_COPY;
+	}
+}
+#endif
+
 /**
  *	add_mtd_device - register an MTD device
  *	@mtd: pointer to new MTD device info structure
@@ -380,19 +370,7 @@ int add_mtd_device(struct mtd_info *mtd)
 	struct mtd_notifier *not;
 	int i, error;
 
-	if (!mtd->backing_dev_info) {
-		switch (mtd->type) {
-		case MTD_RAM:
-			mtd->backing_dev_info = &mtd_bdi_rw_mappable;
-			break;
-		case MTD_ROM:
-			mtd->backing_dev_info = &mtd_bdi_ro_mappable;
-			break;
-		default:
-			mtd->backing_dev_info = &mtd_bdi_unmappable;
-			break;
-		}
-	}
+	mtd->backing_dev_info = &mtd_bdi;
 
 	BUG_ON(mtd->writesize == 0);
 	mutex_lock(&mtd_table_mutex);
@@ -1237,17 +1215,9 @@ static int __init init_mtd(void)
 	if (ret)
 		goto err_reg;
 
-	ret = mtd_bdi_init(&mtd_bdi_unmappable, "mtd-unmap");
-	if (ret)
-		goto err_bdi1;
-
-	ret = mtd_bdi_init(&mtd_bdi_ro_mappable, "mtd-romap");
-	if (ret)
-		goto err_bdi2;
-
-	ret = mtd_bdi_init(&mtd_bdi_rw_mappable, "mtd-rwmap");
+	ret = mtd_bdi_init(&mtd_bdi, "mtd");
 	if (ret)
-		goto err_bdi3;
+		goto err_bdi;
 
 	proc_mtd = proc_create("mtd", 0, NULL, &mtd_proc_ops);
 
@@ -1260,11 +1230,7 @@ static int __init init_mtd(void)
 out_procfs:
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
-err_bdi3:
-	bdi_destroy(&mtd_bdi_ro_mappable);
-err_bdi2:
-	bdi_destroy(&mtd_bdi_unmappable);
-err_bdi1:
+err_bdi:
 	class_unregister(&mtd_class);
 err_reg:
 	pr_err("Error registering mtd class or bdi: %d\n", ret);
@@ -1277,9 +1243,7 @@ static void __exit cleanup_mtd(void)
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
 	class_unregister(&mtd_class);
-	bdi_destroy(&mtd_bdi_unmappable);
-	bdi_destroy(&mtd_bdi_ro_mappable);
-	bdi_destroy(&mtd_bdi_rw_mappable);
+	bdi_destroy(&mtd_bdi);
 }
 
 module_init(init_mtd);
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index a3e3a7d074d..e779de315ad 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -378,7 +378,6 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 
 	slave->mtd.name = name;
 	slave->mtd.owner = master->owner;
-	slave->mtd.backing_dev_info = master->backing_dev_info;
 
 	/* NOTE:  we don't arrange MTDs as a tree; it'd be error-prone
 	 * to have the same data be in two different partitions.
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index a3367bfb145..d5b149c5542 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -987,7 +987,7 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
 	if (err)
 		goto out_free;
 	lsi->lsi_flags |= LSI_BDI_INITIALIZED;
-	lsi->lsi_bdi.capabilities = BDI_CAP_MAP_COPY;
+	lsi->lsi_bdi.capabilities = 0;
 	err = ll_bdi_register(&lsi->lsi_bdi);
 	if (err)
 		goto out_free;
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 6894b085f0e..620d9348953 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -335,7 +335,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	}
 	init_rwsem(&v9ses->rename_sem);
 
-	rc = bdi_setup_and_register(&v9ses->bdi, "9p", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
 	if (rc) {
 		kfree(v9ses->aname);
 		kfree(v9ses->uname);
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 2b607257820..d142a2449e6 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -106,7 +106,7 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 	volume->cell		= params->cell;
 	volume->vid		= vlocation->vldb.vid[params->type];
 
-	ret = bdi_setup_and_register(&volume->bdi, "afs", BDI_CAP_MAP_COPY);
+	ret = bdi_setup_and_register(&volume->bdi, "afs");
 	if (ret)
 		goto error_bdi;
 
diff --git a/fs/aio.c b/fs/aio.c
index 1b7893ecc29..6f13d3fab07 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -165,15 +165,6 @@ static struct vfsmount *aio_mnt;
 static const struct file_operations aio_ring_fops;
 static const struct address_space_operations aio_ctx_aops;
 
-/* Backing dev info for aio fs.
- * -no dirty page accounting or writeback happens
- */
-static struct backing_dev_info aio_fs_backing_dev_info = {
-	.name           = "aiofs",
-	.state          = 0,
-	.capabilities   = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_COPY,
-};
-
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
 	struct qstr this = QSTR_INIT("[aio]", 5);
@@ -185,7 +176,7 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
 	inode->i_mapping->private_data = ctx;
-	inode->i_mapping->backing_dev_info = &aio_fs_backing_dev_info;
+	inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
@@ -230,9 +221,6 @@ static int __init aio_setup(void)
 	if (IS_ERR(aio_mnt))
 		panic("Failed to create aio fs mount.");
 
-	if (bdi_init(&aio_fs_backing_dev_info))
-		panic("Failed to init aio fs backing dev info.");
-
 	kiocb_cachep = KMEM_CACHE(kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 	kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8c63419a7f7..afc4092989c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1715,8 +1715,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 {
 	int err;
 
-	bdi->capabilities = BDI_CAP_MAP_COPY;
-	err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY);
+	err = bdi_setup_and_register(bdi, "btrfs");
 	if (err)
 		return err;
 
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 67b2007f10f..ea06a3d0364 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -24,27 +24,6 @@
 
 #include "internal.h"
 
-/*
- * capabilities for /dev/mem, /dev/kmem and similar directly mappable character
- * devices
- * - permits shared-mmap for read, write and/or exec
- * - does not permit private mmap in NOMMU mode (can't do COW)
- * - no readahead or I/O queue unplugging required
- */
-struct backing_dev_info directly_mappable_cdev_bdi = {
-	.name = "char",
-	.capabilities	= (
-#ifdef CONFIG_MMU
-		/* permit private copies of the data to be taken */
-		BDI_CAP_MAP_COPY |
-#endif
-		/* permit direct mmap, for read, write or exec */
-		BDI_CAP_MAP_DIRECT |
-		BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP |
-		/* no writeback happens */
-		BDI_CAP_NO_ACCT_AND_WRITEBACK),
-};
-
 static struct kobj_map *cdev_map;
 
 static DEFINE_MUTEX(chrdevs_lock);
@@ -575,8 +554,6 @@ static struct kobject *base_probe(dev_t dev, int *part, void *data)
 void __init chrdev_init(void)
 {
 	cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
-	if (bdi_init(&directly_mappable_cdev_bdi))
-		panic("Failed to init directly mappable cdev bdi");
 }
 
 
@@ -590,4 +567,3 @@ EXPORT_SYMBOL(cdev_del);
 EXPORT_SYMBOL(cdev_add);
 EXPORT_SYMBOL(__register_chrdev);
 EXPORT_SYMBOL(__unregister_chrdev);
-EXPORT_SYMBOL(directly_mappable_cdev_bdi);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2a772da16b8..d3aa999ab78 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3446,7 +3446,7 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 	int referral_walks_count = 0;
 #endif
 
-	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs");
 	if (rc)
 		return rc;
 
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index b945410bfcd..82ec68b5920 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -183,7 +183,7 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 		goto unlock_out;
 	}
 
-	error = bdi_setup_and_register(&vc->bdi, "coda", BDI_CAP_MAP_COPY);
+	error = bdi_setup_and_register(&vc->bdi, "coda");
 	if (error)
 		goto unlock_out;
 
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
index bd4a3c16709..a315677e44d 100644
--- a/fs/configfs/configfs_internal.h
+++ b/fs/configfs/configfs_internal.h
@@ -70,8 +70,6 @@ extern int configfs_is_root(struct config_item *item);
 
 extern struct inode * configfs_new_inode(umode_t mode, struct configfs_dirent *, struct super_block *);
 extern int configfs_create(struct dentry *, umode_t mode, int (*init)(struct inode *));
-extern int configfs_inode_init(void);
-extern void configfs_inode_exit(void);
 
 extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
 extern int configfs_make_dirent(struct configfs_dirent *,
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 5946ad98053..0ad6b4d6de0 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -50,12 +50,6 @@ static const struct address_space_operations configfs_aops = {
 	.write_end	= simple_write_end,
 };
 
-static struct backing_dev_info configfs_backing_dev_info = {
-	.name		= "configfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
 static const struct inode_operations configfs_inode_operations ={
 	.setattr	= configfs_setattr,
 };
@@ -137,7 +131,7 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode->i_mapping->a_ops = &configfs_aops;
-		inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
+		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		inode->i_op = &configfs_inode_operations;
 
 		if (sd->s_iattr) {
@@ -283,13 +277,3 @@ void configfs_hash_and_remove(struct dentry * dir, const char * name)
 	}
 	mutex_unlock(&dir->d_inode->i_mutex);
 }
-
-int __init configfs_inode_init(void)
-{
-	return bdi_init(&configfs_backing_dev_info);
-}
-
-void configfs_inode_exit(void)
-{
-	bdi_destroy(&configfs_backing_dev_info);
-}
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index f6c28583339..da94e41bdbf 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -145,19 +145,13 @@ static int __init configfs_init(void)
 	if (!config_kobj)
 		goto out2;
 
-	err = configfs_inode_init();
-	if (err)
-		goto out3;
-
 	err = register_filesystem(&configfs_fs_type);
 	if (err)
-		goto out4;
+		goto out3;
 
 	return 0;
-out4:
-	pr_err("Unable to register filesystem!\n");
-	configfs_inode_exit();
 out3:
+	pr_err("Unable to register filesystem!\n");
 	kobject_put(config_kobj);
 out2:
 	kmem_cache_destroy(configfs_dir_cachep);
@@ -172,7 +166,6 @@ static void __exit configfs_exit(void)
 	kobject_put(config_kobj);
 	kmem_cache_destroy(configfs_dir_cachep);
 	configfs_dir_cachep = NULL;
-	configfs_inode_exit();
 }
 
 MODULE_AUTHOR("Oracle");
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index d9eb84bda55..1895d60f412 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -520,7 +520,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
+	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs");
 	if (rc)
 		goto out1;
 
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 95965503afc..fcc2e565f54 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -836,7 +836,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
-	ret = bdi_setup_and_register(&sbi->bdi, "exofs", BDI_CAP_MAP_COPY);
+	ret = bdi_setup_and_register(&sbi->bdi, "exofs");
 	if (ret) {
 		EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
 		dput(sb->s_root);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index e31e589369a..a699a3fc62c 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -560,7 +560,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	server = NCP_SBP(sb);
 	memset(server, 0, sizeof(*server));
 
-	error = bdi_setup_and_register(&server->bdi, "ncpfs", BDI_CAP_MAP_COPY);
+	error = bdi_setup_and_register(&server->bdi, "ncpfs");
 	if (error)
 		goto out_fput;
 
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index bbafbde3471..f6ab41b3961 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -34,7 +34,14 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
 						   unsigned long flags);
 static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
 
+static unsigned ramfs_mmap_capabilities(struct file *file)
+{
+	return NOMMU_MAP_DIRECT | NOMMU_MAP_COPY | NOMMU_MAP_READ |
+		NOMMU_MAP_WRITE | NOMMU_MAP_EXEC;
+}
+
 const struct file_operations ramfs_file_operations = {
+	.mmap_capabilities	= ramfs_mmap_capabilities,
 	.mmap			= ramfs_nommu_mmap,
 	.get_unmapped_area	= ramfs_nommu_get_unmapped_area,
 	.read			= new_sync_read,
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index d365b1c4eb3..ad4d712002f 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -50,14 +50,6 @@ static const struct address_space_operations ramfs_aops = {
 	.set_page_dirty	= __set_page_dirty_no_writeback,
 };
 
-static struct backing_dev_info ramfs_backing_dev_info = {
-	.name		= "ramfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK |
-			  BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
-			  BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP,
-};
-
 struct inode *ramfs_get_inode(struct super_block *sb,
 				const struct inode *dir, umode_t mode, dev_t dev)
 {
@@ -67,7 +59,7 @@ struct inode *ramfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_mapping->a_ops = &ramfs_aops;
-		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
+		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
 		mapping_set_unevictable(inode->i_mapping);
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -267,19 +259,9 @@ static struct file_system_type ramfs_fs_type = {
 int __init init_ramfs_fs(void)
 {
 	static unsigned long once;
-	int err;
 
 	if (test_and_set_bit(0, &once))
 		return 0;
-
-	err = bdi_init(&ramfs_backing_dev_info);
-	if (err)
-		return err;
-
-	err = register_filesystem(&ramfs_fs_type);
-	if (err)
-		bdi_destroy(&ramfs_backing_dev_info);
-
-	return err;
+	return register_filesystem(&ramfs_fs_type);
 }
 fs_initcall(init_ramfs_fs);
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index ea06c755486..7da9e215395 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -70,6 +70,15 @@ static int romfs_mmap(struct file *file, struct vm_area_struct *vma)
 	return vma->vm_flags & (VM_SHARED | VM_MAYSHARE) ? 0 : -ENOSYS;
 }
 
+static unsigned romfs_mmap_capabilities(struct file *file)
+{
+	struct mtd_info *mtd = file_inode(file)->i_sb->s_mtd;
+
+	if (!mtd)
+		return NOMMU_MAP_COPY;
+	return mtd_mmap_capabilities(mtd);
+}
+
 const struct file_operations romfs_ro_fops = {
 	.llseek			= generic_file_llseek,
 	.read			= new_sync_read,
@@ -77,4 +86,5 @@ const struct file_operations romfs_ro_fops = {
 	.splice_read		= generic_file_splice_read,
 	.mmap			= romfs_mmap,
 	.get_unmapped_area	= romfs_get_unmapped_area,
+	.mmap_capabilities	= romfs_mmap_capabilities,
 };
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 106bf20629c..ed93dc6ae24 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2017,7 +2017,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
 	 */
 	c->bdi.name = "ubifs",
-	c->bdi.capabilities = BDI_CAP_MAP_COPY;
+	c->bdi.capabilities = 0;
 	err  = bdi_init(&c->bdi);
 	if (err)
 		goto out_close;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index e936cea856d..478f95d92d7 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -114,7 +114,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
-int __must_check bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
+int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
 void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 			enum wb_reason reason);
 void bdi_start_background_writeback(struct backing_dev_info *bdi);
@@ -228,42 +228,17 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_NO_ACCT_DIRTY:  Dirty pages shouldn't contribute to accounting
  * BDI_CAP_NO_WRITEBACK:   Don't write pages back
  * BDI_CAP_NO_ACCT_WB:     Don't automatically account writeback pages
- *
- * These flags let !MMU mmap() govern direct device mapping vs immediate
- * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
- *
- * BDI_CAP_MAP_COPY:       Copy can be mapped (MAP_PRIVATE)
- * BDI_CAP_MAP_DIRECT:     Can be mapped directly (MAP_SHARED)
- * BDI_CAP_READ_MAP:       Can be mapped for reading
- * BDI_CAP_WRITE_MAP:      Can be mapped for writing
- * BDI_CAP_EXEC_MAP:       Can be mapped for execution
- *
  * BDI_CAP_STRICTLIMIT:    Keep number of dirty pages below bdi threshold.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
-#define BDI_CAP_MAP_COPY	0x00000004
-#define BDI_CAP_MAP_DIRECT	0x00000008
-#define BDI_CAP_READ_MAP	0x00000010
-#define BDI_CAP_WRITE_MAP	0x00000020
-#define BDI_CAP_EXEC_MAP	0x00000040
-#define BDI_CAP_NO_ACCT_WB	0x00000080
-#define BDI_CAP_STABLE_WRITES	0x00000200
-#define BDI_CAP_STRICTLIMIT	0x00000400
-
-#define BDI_CAP_VMFLAGS \
-	(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
+#define BDI_CAP_NO_ACCT_WB	0x00000004
+#define BDI_CAP_STABLE_WRITES	0x00000008
+#define BDI_CAP_STRICTLIMIT	0x00000010
 
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
 	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
 
-#if defined(VM_MAYREAD) && \
-	(BDI_CAP_READ_MAP != VM_MAYREAD || \
-	 BDI_CAP_WRITE_MAP != VM_MAYWRITE || \
-	 BDI_CAP_EXEC_MAP != VM_MAYEXEC)
-#error please change backing_dev_info::capabilities flags
-#endif
-
 extern struct backing_dev_info default_backing_dev_info;
 extern struct backing_dev_info noop_backing_dev_info;
 
diff --git a/include/linux/cdev.h b/include/linux/cdev.h
index fb4591977b0..f8763615a5f 100644
--- a/include/linux/cdev.h
+++ b/include/linux/cdev.h
@@ -30,6 +30,4 @@ void cdev_del(struct cdev *);
 
 void cd_forget(struct inode *);
 
-extern struct backing_dev_info directly_mappable_cdev_bdi;
-
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42efe13077b..1dada399aa2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1502,6 +1502,26 @@ struct block_device_operations;
 #define HAVE_COMPAT_IOCTL 1
 #define HAVE_UNLOCKED_IOCTL 1
 
+/*
+ * These flags let !MMU mmap() govern direct device mapping vs immediate
+ * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
+ *
+ * NOMMU_MAP_COPY:	Copy can be mapped (MAP_PRIVATE)
+ * NOMMU_MAP_DIRECT:	Can be mapped directly (MAP_SHARED)
+ * NOMMU_MAP_READ:	Can be mapped for reading
+ * NOMMU_MAP_WRITE:	Can be mapped for writing
+ * NOMMU_MAP_EXEC:	Can be mapped for execution
+ */
+#define NOMMU_MAP_COPY		0x00000001
+#define NOMMU_MAP_DIRECT	0x00000008
+#define NOMMU_MAP_READ		VM_MAYREAD
+#define NOMMU_MAP_WRITE		VM_MAYWRITE
+#define NOMMU_MAP_EXEC		VM_MAYEXEC
+
+#define NOMMU_VMFLAGS \
+	(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
+
+
 struct iov_iter;
 
 struct file_operations {
@@ -1536,6 +1556,9 @@ struct file_operations {
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	void (*show_fdinfo)(struct seq_file *m, struct file *f);
+#ifndef CONFIG_MMU
+	unsigned (*mmap_capabilities)(struct file *);
+#endif
 };
 
 struct inode_operations {
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 031ff3a9a0b..3301c4c289d 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -408,4 +408,6 @@ static inline int mtd_is_bitflip_or_eccerr(int err) {
 	return mtd_is_bitflip(err) || mtd_is_eccerr(err);
 }
 
+unsigned mtd_mmap_capabilities(struct mtd_info *mtd);
+
 #endif /* __MTD_MTD_H__ */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 0ae0df55000..16c68958aed 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -17,8 +17,6 @@ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 struct backing_dev_info default_backing_dev_info = {
 	.name		= "default",
 	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
-	.state		= 0,
-	.capabilities	= BDI_CAP_MAP_COPY,
 };
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
@@ -513,13 +511,12 @@ EXPORT_SYMBOL(bdi_destroy);
  * For use from filesystems to quickly init and register a bdi associated
  * with dirty writeback
  */
-int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
-			   unsigned int cap)
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
 {
 	int err;
 
 	bdi->name = name;
-	bdi->capabilities = cap;
+	bdi->capabilities = 0;
 	err = bdi_init(bdi);
 	if (err)
 		return err;
diff --git a/mm/nommu.c b/mm/nommu.c
index b51eadf6d95..13af96f35a4 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -946,9 +946,6 @@ static int validate_mmap_request(struct file *file,
 		return -EOVERFLOW;
 
 	if (file) {
-		/* validate file mapping requests */
-		struct address_space *mapping;
-
 		/* files must support mmap */
 		if (!file->f_op->mmap)
 			return -ENODEV;
@@ -957,28 +954,22 @@ static int validate_mmap_request(struct file *file,
 		 * - we support chardevs that provide their own "memory"
 		 * - we support files/blockdevs that are memory backed
 		 */
-		mapping = file->f_mapping;
-		if (!mapping)
-			mapping = file_inode(file)->i_mapping;
-
-		capabilities = 0;
-		if (mapping && mapping->backing_dev_info)
-			capabilities = mapping->backing_dev_info->capabilities;
-
-		if (!capabilities) {
+		if (file->f_op->mmap_capabilities) {
+			capabilities = file->f_op->mmap_capabilities(file);
+		} else {
 			/* no explicit capabilities set, so assume some
 			 * defaults */
 			switch (file_inode(file)->i_mode & S_IFMT) {
 			case S_IFREG:
 			case S_IFBLK:
-				capabilities = BDI_CAP_MAP_COPY;
+				capabilities = NOMMU_MAP_COPY;
 				break;
 
 			case S_IFCHR:
 				capabilities =
-					BDI_CAP_MAP_DIRECT |
-					BDI_CAP_READ_MAP |
-					BDI_CAP_WRITE_MAP;
+					NOMMU_MAP_DIRECT |
+					NOMMU_MAP_READ |
+					NOMMU_MAP_WRITE;
 				break;
 
 			default:
@@ -989,9 +980,9 @@ static int validate_mmap_request(struct file *file,
 		/* eliminate any capabilities that we can't support on this
 		 * device */
 		if (!file->f_op->get_unmapped_area)
-			capabilities &= ~BDI_CAP_MAP_DIRECT;
+			capabilities &= ~NOMMU_MAP_DIRECT;
 		if (!file->f_op->read)
-			capabilities &= ~BDI_CAP_MAP_COPY;
+			capabilities &= ~NOMMU_MAP_COPY;
 
 		/* The file shall have been opened with read permission. */
 		if (!(file->f_mode & FMODE_READ))
@@ -1010,29 +1001,29 @@ static int validate_mmap_request(struct file *file,
 			if (locks_verify_locked(file))
 				return -EAGAIN;
 
-			if (!(capabilities & BDI_CAP_MAP_DIRECT))
+			if (!(capabilities & NOMMU_MAP_DIRECT))
 				return -ENODEV;
 
 			/* we mustn't privatise shared mappings */
-			capabilities &= ~BDI_CAP_MAP_COPY;
+			capabilities &= ~NOMMU_MAP_COPY;
 		} else {
 			/* we're going to read the file into private memory we
 			 * allocate */
-			if (!(capabilities & BDI_CAP_MAP_COPY))
+			if (!(capabilities & NOMMU_MAP_COPY))
 				return -ENODEV;
 
 			/* we don't permit a private writable mapping to be
 			 * shared with the backing device */
 			if (prot & PROT_WRITE)
-				capabilities &= ~BDI_CAP_MAP_DIRECT;
+				capabilities &= ~NOMMU_MAP_DIRECT;
 		}
 
-		if (capabilities & BDI_CAP_MAP_DIRECT) {
-			if (((prot & PROT_READ)  && !(capabilities & BDI_CAP_READ_MAP))  ||
-			    ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
-			    ((prot & PROT_EXEC)  && !(capabilities & BDI_CAP_EXEC_MAP))
+		if (capabilities & NOMMU_MAP_DIRECT) {
+			if (((prot & PROT_READ)  && !(capabilities & NOMMU_MAP_READ))  ||
+			    ((prot & PROT_WRITE) && !(capabilities & NOMMU_MAP_WRITE)) ||
+			    ((prot & PROT_EXEC)  && !(capabilities & NOMMU_MAP_EXEC))
 			    ) {
-				capabilities &= ~BDI_CAP_MAP_DIRECT;
+				capabilities &= ~NOMMU_MAP_DIRECT;
 				if (flags & MAP_SHARED) {
 					printk(KERN_WARNING
 					       "MAP_SHARED not completely supported on !MMU\n");
@@ -1049,21 +1040,21 @@ static int validate_mmap_request(struct file *file,
 		} else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
 			/* handle implication of PROT_EXEC by PROT_READ */
 			if (current->personality & READ_IMPLIES_EXEC) {
-				if (capabilities & BDI_CAP_EXEC_MAP)
+				if (capabilities & NOMMU_MAP_EXEC)
 					prot |= PROT_EXEC;
 			}
 		} else if ((prot & PROT_READ) &&
 			 (prot & PROT_EXEC) &&
-			 !(capabilities & BDI_CAP_EXEC_MAP)
+			 !(capabilities & NOMMU_MAP_EXEC)
 			 ) {
 			/* backing file is not executable, try to copy */
-			capabilities &= ~BDI_CAP_MAP_DIRECT;
+			capabilities &= ~NOMMU_MAP_DIRECT;
 		}
 	} else {
 		/* anonymous mappings are always memory backed and can be
 		 * privately mapped
 		 */
-		capabilities = BDI_CAP_MAP_COPY;
+		capabilities = NOMMU_MAP_COPY;
 
 		/* handle PROT_EXEC implication by PROT_READ */
 		if ((prot & PROT_READ) &&
@@ -1095,7 +1086,7 @@ static unsigned long determine_vm_flags(struct file *file,
 	vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags);
 	/* vm_flags |= mm->def_flags; */
 
-	if (!(capabilities & BDI_CAP_MAP_DIRECT)) {
+	if (!(capabilities & NOMMU_MAP_DIRECT)) {
 		/* attempt to share read-only copies of mapped file chunks */
 		vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
 		if (file && !(prot & PROT_WRITE))
@@ -1104,7 +1095,7 @@ static unsigned long determine_vm_flags(struct file *file,
 		/* overlay a shareable mapping on the backing device or inode
 		 * if possible - used for chardevs, ramfs/tmpfs/shmfs and
 		 * romfs/cramfs */
-		vm_flags |= VM_MAYSHARE | (capabilities & BDI_CAP_VMFLAGS);
+		vm_flags |= VM_MAYSHARE | (capabilities & NOMMU_VMFLAGS);
 		if (flags & MAP_SHARED)
 			vm_flags |= VM_SHARED;
 	}
@@ -1157,7 +1148,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 	 * shared mappings on devices or memory
 	 * - VM_MAYSHARE will be set if it may attempt to share
 	 */
-	if (capabilities & BDI_CAP_MAP_DIRECT) {
+	if (capabilities & NOMMU_MAP_DIRECT) {
 		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
 		if (ret == 0) {
 			/* shouldn't return success if we're not sharing */
@@ -1346,7 +1337,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 			if ((pregion->vm_pgoff != pgoff || rpglen != pglen) &&
 			    !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) {
 				/* new mapping is not a subset of the region */
-				if (!(capabilities & BDI_CAP_MAP_DIRECT))
+				if (!(capabilities & NOMMU_MAP_DIRECT))
 					goto sharing_violation;
 				continue;
 			}
@@ -1385,7 +1376,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 		 * - this is the hook for quasi-memory character devices to
 		 *   tell us the location of a shared mapping
 		 */
-		if (capabilities & BDI_CAP_MAP_DIRECT) {
+		if (capabilities & NOMMU_MAP_DIRECT) {
 			addr = file->f_op->get_unmapped_area(file, addr, len,
 							     pgoff, flags);
 			if (IS_ERR_VALUE(addr)) {
@@ -1397,10 +1388,10 @@ unsigned long do_mmap_pgoff(struct file *file,
 				 * the mapping so we'll have to attempt to copy
 				 * it */
 				ret = -ENODEV;
-				if (!(capabilities & BDI_CAP_MAP_COPY))
+				if (!(capabilities & NOMMU_MAP_COPY))
 					goto error_just_free;
 
-				capabilities &= ~BDI_CAP_MAP_DIRECT;
+				capabilities &= ~NOMMU_MAP_DIRECT;
 			} else {
 				vma->vm_start = region->vm_start = addr;
 				vma->vm_end = region->vm_end = addr + len;
@@ -1411,7 +1402,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 	vma->vm_region = region;
 
 	/* set up the mapping
-	 * - the region is filled in if BDI_CAP_MAP_DIRECT is still set
+	 * - the region is filled in if NOMMU_MAP_DIRECT is still set
 	 */
 	if (file && vma->vm_flags & VM_SHARED)
 		ret = do_mmap_shared_file(vma);
diff --git a/security/security.c b/security/security.c
index 18b35c63fc0..a0442b20f00 100644
--- a/security/security.c
+++ b/security/security.c
@@ -726,16 +726,15 @@ static inline unsigned long mmap_prot(struct file *file, unsigned long prot)
 		return prot | PROT_EXEC;
 	/*
 	 * ditto if it's not on noexec mount, except that on !MMU we need
-	 * BDI_CAP_EXEC_MMAP (== VM_MAYEXEC) in this case
+	 * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case
 	 */
 	if (!(file->f_path.mnt->mnt_flags & MNT_NOEXEC)) {
 #ifndef CONFIG_MMU
-		unsigned long caps = 0;
-		struct address_space *mapping = file->f_mapping;
-		if (mapping && mapping->backing_dev_info)
-			caps = mapping->backing_dev_info->capabilities;
-		if (!(caps & BDI_CAP_EXEC_MAP))
-			return prot;
+		if (file->f_op->mmap_capabilities) {
+			unsigned caps = file->f_op->mmap_capabilities(file);
+			if (!(caps & NOMMU_MAP_EXEC))
+				return prot;
+		}
 #endif
 		return prot | PROT_EXEC;
 	}
-- 
cgit v1.2.3-70-g09d2


From de1414a654e66b81b5348dbc5259ecf2fb61655e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 14 Jan 2015 10:42:36 +0100
Subject: fs: export inode_to_bdi and use it in favor of
 mapping->backing_dev_info

Now that we got rid of the bdi abuse on character devices we can always use
sb->s_bdi to get at the backing_dev_info for a file, except for the block
device special case.  Export inode_to_bdi and replace uses of
mapping->backing_dev_info with it to prepare for the removal of
mapping->backing_dev_info.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 fs/btrfs/file.c                  |  2 +-
 fs/ceph/file.c                   |  2 +-
 fs/ext2/ialloc.c                 |  2 +-
 fs/ext4/super.c                  |  2 +-
 fs/fs-writeback.c                |  3 ++-
 fs/fuse/file.c                   | 10 +++++-----
 fs/gfs2/aops.c                   |  2 +-
 fs/gfs2/super.c                  |  2 +-
 fs/nfs/filelayout/filelayout.c   |  2 +-
 fs/nfs/write.c                   |  6 +++---
 fs/ntfs/file.c                   |  3 ++-
 fs/ocfs2/file.c                  |  2 +-
 fs/xfs/xfs_file.c                |  2 +-
 include/linux/backing-dev.h      |  6 ++++--
 include/trace/events/writeback.h |  6 +++---
 mm/fadvise.c                     |  4 ++--
 mm/filemap.c                     |  4 ++--
 mm/filemap_xip.c                 |  3 ++-
 mm/page-writeback.c              | 29 +++++++++++++----------------
 mm/readahead.c                   |  4 ++--
 mm/truncate.c                    |  2 +-
 mm/vmscan.c                      |  4 ++--
 22 files changed, 52 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e4090259569..835c04a874f 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1746,7 +1746,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 
 	mutex_lock(&inode->i_mutex);
 
-	current->backing_dev_info = inode->i_mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err) {
 		mutex_unlock(&inode->i_mutex);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ce74b394b49..905986dd4c3 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -945,7 +945,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = file->f_mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 7d66fb0e4cc..6c14bb8322f 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -170,7 +170,7 @@ static void ext2_preread_inode(struct inode *inode)
 	struct ext2_group_desc * gdp;
 	struct backing_dev_info *bdi;
 
-	bdi = inode->i_mapping->backing_dev_info;
+	bdi = inode_to_bdi(inode);
 	if (bdi_read_congested(bdi))
 		return;
 	if (bdi_write_congested(bdi))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 74c5f53595f..ad88e601a6c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -334,7 +334,7 @@ static void save_error_info(struct super_block *sb, const char *func,
 static int block_device_ejected(struct super_block *sb)
 {
 	struct inode *bd_inode = sb->s_bdev->bd_inode;
-	struct backing_dev_info *bdi = bd_inode->i_mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(bd_inode);
 
 	return bdi->dev == NULL;
 }
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e8116a44cc2..a20b1145f4d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -66,7 +66,7 @@ int writeback_in_progress(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(writeback_in_progress);
 
-static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
+struct backing_dev_info *inode_to_bdi(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 #ifdef CONFIG_BLOCK
@@ -75,6 +75,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 #endif
 	return sb->s_bdi;
 }
+EXPORT_SYMBOL_GPL(inode_to_bdi);
 
 static inline struct inode *wb_inode(struct list_head *head)
 {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 760b2c55219..19d80b82d34 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1159,7 +1159,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
@@ -1464,7 +1464,7 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct inode *inode = req->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
-	struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
 	int i;
 
 	list_del(&req->writepages_entry);
@@ -1658,7 +1658,7 @@ static int fuse_writepage_locked(struct page *page)
 	req->end = fuse_writepage_end;
 	req->inode = inode;
 
-	inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
+	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	spin_lock(&fc->lock);
@@ -1768,7 +1768,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req,
 
 	if (old_req->num_pages == 1 && (old_req->state == FUSE_REQ_INIT ||
 					old_req->state == FUSE_REQ_PENDING)) {
-		struct backing_dev_info *bdi = page->mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(page->mapping->host);
 
 		copy_highpage(old_req->pages[0], page);
 		spin_unlock(&fc->lock);
@@ -1872,7 +1872,7 @@ static int fuse_writepages_fill(struct page *page,
 	req->page_descs[req->num_pages].offset = 0;
 	req->page_descs[req->num_pages].length = PAGE_SIZE;
 
-	inc_bdi_stat(page->mapping->backing_dev_info, BDI_WRITEBACK);
+	inc_bdi_stat(inode_to_bdi(inode), BDI_WRITEBACK);
 	inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
 
 	err = 0;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 805b37fed63..4ad4f94edeb 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -289,7 +289,7 @@ continue_unlock:
 		if (!clear_page_dirty_for_io(page))
 			goto continue_unlock;
 
-		trace_wbc_writepage(wbc, mapping->backing_dev_info);
+		trace_wbc_writepage(wbc, inode_to_bdi(inode));
 
 		ret = __gfs2_jdata_writepage(page, wbc);
 		if (unlikely(ret)) {
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 5b327f837de..1666382b198 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -743,7 +743,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
-	struct backing_dev_info *bdi = metamapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(metamapping->host);
 	int ret = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 7afb52f6a25..51aa889611c 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -1081,7 +1081,7 @@ mds_commit:
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+		inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index af3af685a9e..298abcc5281 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -786,7 +786,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 	spin_unlock(cinfo->lock);
 	if (!cinfo->dreq) {
 		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+		inc_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
 			     BDI_RECLAIMABLE);
 		__mark_inode_dirty(req->wb_context->dentry->d_inode,
 				   I_DIRTY_DATASYNC);
@@ -853,7 +853,7 @@ static void
 nfs_clear_page_commit(struct page *page)
 {
 	dec_zone_page_state(page, NR_UNSTABLE_NFS);
-	dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE);
+	dec_bdi_stat(inode_to_bdi(page_file_mapping(page)->host), BDI_RECLAIMABLE);
 }
 
 /* Called holding inode (/cinfo) lock */
@@ -1564,7 +1564,7 @@ void nfs_retry_commit(struct list_head *page_list,
 		nfs_mark_request_commit(req, lseg, cinfo);
 		if (!cinfo->dreq) {
 			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,
+			dec_bdi_stat(inode_to_bdi(page_file_mapping(req->wb_page)->host),
 				     BDI_RECLAIMABLE);
 		}
 		nfs_unlock_and_release_request(req);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 643faa44f22..1da9b2d184d 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -19,6 +19,7 @@
  * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include <linux/gfp.h>
 #include <linux/pagemap.h>
@@ -2091,7 +2092,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
 	count = iov_length(iov, nr_segs);
 	pos = *ppos;
 	/* We can write back this queue in page reclaim. */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	written = 0;
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 3950693dd0f..abe7d98d617 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2363,7 +2363,7 @@ relock:
 			goto out_dio;
 		}
 	} else {
-		current->backing_dev_info = file->f_mapping->backing_dev_info;
+		current->backing_dev_info = inode_to_bdi(inode);
 		written = generic_perform_write(file, from, *ppos);
 		if (likely(written >= 0))
 			iocb->ki_pos = *ppos + written;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 13e974e6a88..5684ac3e7d1 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -699,7 +699,7 @@ xfs_file_buffered_aio_write(
 
 	iov_iter_truncate(from, count);
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 478f95d92d7..ed59dee03a7 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -106,6 +106,8 @@ struct backing_dev_info {
 #endif
 };
 
+struct backing_dev_info *inode_to_bdi(struct inode *inode);
+
 int __must_check bdi_init(struct backing_dev_info *bdi);
 void bdi_destroy(struct backing_dev_info *bdi);
 
@@ -303,12 +305,12 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
 
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
-	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
+	return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host));
 }
 
 static inline bool mapping_cap_account_dirty(struct address_space *mapping)
 {
-	return bdi_cap_account_dirty(mapping->backing_dev_info);
+	return bdi_cap_account_dirty(inode_to_bdi(mapping->host));
 }
 
 static inline int bdi_sched_wait(void *word)
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index cee02d65ab3..74f5207bd09 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -47,7 +47,7 @@ TRACE_EVENT(writeback_dirty_page,
 
 	TP_fast_assign(
 		strncpy(__entry->name,
-			mapping ? dev_name(mapping->backing_dev_info->dev) : "(unknown)", 32);
+			mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", 32);
 		__entry->ino = mapping ? mapping->host->i_ino : 0;
 		__entry->index = page->index;
 	),
@@ -72,7 +72,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 	),
 
 	TP_fast_assign(
-		struct backing_dev_info *bdi = inode->i_mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(inode);
 
 		/* may be called for files on pseudo FSes w/ unregistered bdi */
 		strncpy(__entry->name,
@@ -116,7 +116,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 
 	TP_fast_assign(
 		strncpy(__entry->name,
-			dev_name(inode->i_mapping->backing_dev_info->dev), 32);
+			dev_name(inode_to_bdi(inode)->dev), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->sync_mode	= wbc->sync_mode;
 	),
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 2ad7adf4f0a..fac23ecf8d7 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -73,7 +73,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 	else
 		endbyte--;		/* inclusive */
 
-	bdi = mapping->backing_dev_info;
+	bdi = inode_to_bdi(mapping->host);
 
 	switch (advice) {
 	case POSIX_FADV_NORMAL:
@@ -113,7 +113,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 	case POSIX_FADV_NOREUSE:
 		break;
 	case POSIX_FADV_DONTNEED:
-		if (!bdi_write_congested(mapping->backing_dev_info))
+		if (!bdi_write_congested(bdi))
 			__filemap_fdatawrite_range(mapping, offset, endbyte,
 						   WB_SYNC_NONE);
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 673e4581a2e..5d7c23c26f8 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -211,7 +211,7 @@ void __delete_from_page_cache(struct page *page, void *shadow)
 	 */
 	if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
 		dec_zone_page_state(page, NR_FILE_DIRTY);
-		dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+		dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE);
 	}
 }
 
@@ -2565,7 +2565,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	size_t		count = iov_iter_count(from);
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
 		goto out;
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 0d105aeff82..26897fbfbe1 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/backing-dev.h>
 #include <linux/pagemap.h>
 #include <linux/export.h>
 #include <linux/uio.h>
@@ -410,7 +411,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len,
 	count = len;
 
 	/* We can write back this queue in page reclaim */
-	current->backing_dev_info = mapping->backing_dev_info;
+	current->backing_dev_info = inode_to_bdi(inode);
 
 	ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
 	if (ret)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6f4335238e3..d4cbb4bd7d1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1351,7 +1351,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 	unsigned long task_ratelimit;
 	unsigned long dirty_ratelimit;
 	unsigned long pos_ratio;
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT;
 	unsigned long start_time = jiffies;
 
@@ -1574,7 +1574,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
  */
 void balance_dirty_pages_ratelimited(struct address_space *mapping)
 {
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
+	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	int ratelimit;
 	int *p;
 
@@ -1929,7 +1929,7 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			trace_wbc_writepage(wbc, mapping->backing_dev_info);
+			trace_wbc_writepage(wbc, inode_to_bdi(mapping->host));
 			ret = (*writepage)(page, wbc, data);
 			if (unlikely(ret)) {
 				if (ret == AOP_WRITEPAGE_ACTIVATE) {
@@ -2094,10 +2094,12 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 	trace_writeback_dirty_page(page, mapping);
 
 	if (mapping_cap_account_dirty(mapping)) {
+		struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
+
 		__inc_zone_page_state(page, NR_FILE_DIRTY);
 		__inc_zone_page_state(page, NR_DIRTIED);
-		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
-		__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+		__inc_bdi_stat(bdi, BDI_RECLAIMABLE);
+		__inc_bdi_stat(bdi, BDI_DIRTIED);
 		task_io_account_write(PAGE_CACHE_SIZE);
 		current->nr_dirtied++;
 		this_cpu_inc(bdp_ratelimits);
@@ -2156,7 +2158,7 @@ void account_page_redirty(struct page *page)
 	if (mapping && mapping_cap_account_dirty(mapping)) {
 		current->nr_dirtied--;
 		dec_zone_page_state(page, NR_DIRTIED);
-		dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+		dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED);
 	}
 }
 EXPORT_SYMBOL(account_page_redirty);
@@ -2295,7 +2297,7 @@ int clear_page_dirty_for_io(struct page *page)
 		 */
 		if (TestClearPageDirty(page)) {
 			dec_zone_page_state(page, NR_FILE_DIRTY);
-			dec_bdi_stat(mapping->backing_dev_info,
+			dec_bdi_stat(inode_to_bdi(mapping->host),
 					BDI_RECLAIMABLE);
 			return 1;
 		}
@@ -2315,7 +2317,7 @@ int test_clear_page_writeback(struct page *page)
 
 	memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
 	if (mapping) {
-		struct backing_dev_info *bdi = mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 		unsigned long flags;
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
@@ -2352,7 +2354,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 
 	memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
 	if (mapping) {
-		struct backing_dev_info *bdi = mapping->backing_dev_info;
+		struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 		unsigned long flags;
 
 		spin_lock_irqsave(&mapping->tree_lock, flags);
@@ -2406,12 +2408,7 @@ EXPORT_SYMBOL(mapping_tagged);
  */
 void wait_for_stable_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
-
-	if (!bdi_cap_stable_pages_required(bdi))
-		return;
-
-	wait_on_page_writeback(page);
+	if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host)))
+		wait_on_page_writeback(page);
 }
 EXPORT_SYMBOL_GPL(wait_for_stable_page);
diff --git a/mm/readahead.c b/mm/readahead.c
index 17b9172ec37..935675844b2 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -27,7 +27,7 @@
 void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
 {
-	ra->ra_pages = mapping->backing_dev_info->ra_pages;
+	ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages;
 	ra->prev_pos = -1;
 }
 EXPORT_SYMBOL_GPL(file_ra_state_init);
@@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping,
 	/*
 	 * Defer asynchronous read-ahead on IO congestion.
 	 */
-	if (bdi_read_congested(mapping->backing_dev_info))
+	if (bdi_read_congested(inode_to_bdi(mapping->host)))
 		return;
 
 	/* do read-ahead */
diff --git a/mm/truncate.c b/mm/truncate.c
index f1e4d605236..ddec5a5966d 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -112,7 +112,7 @@ void cancel_dirty_page(struct page *page, unsigned int account_size)
 		struct address_space *mapping = page->mapping;
 		if (mapping && mapping_cap_account_dirty(mapping)) {
 			dec_zone_page_state(page, NR_FILE_DIRTY);
-			dec_bdi_stat(mapping->backing_dev_info,
+			dec_bdi_stat(inode_to_bdi(mapping->host),
 					BDI_RECLAIMABLE);
 			if (account_size)
 				task_io_account_cancelled_write(account_size);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ab2505c3ef5..e00a16393f2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -497,7 +497,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 	}
 	if (mapping->a_ops->writepage == NULL)
 		return PAGE_ACTIVATE;
-	if (!may_write_to_queue(mapping->backing_dev_info, sc))
+	if (!may_write_to_queue(inode_to_bdi(mapping->host), sc))
 		return PAGE_KEEP;
 
 	if (clear_page_dirty_for_io(page)) {
@@ -876,7 +876,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 */
 		mapping = page_mapping(page);
 		if (((dirty || writeback) && mapping &&
-		     bdi_write_congested(mapping->backing_dev_info)) ||
+		     bdi_write_congested(inode_to_bdi(mapping->host))) ||
 		    (writeback && PageReclaim(page)))
 			nr_congested++;
 
-- 
cgit v1.2.3-70-g09d2


From b83ae6d421435c6204150300f1c25bfbd39cd62b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 14 Jan 2015 10:42:37 +0100
Subject: fs: remove mapping->backing_dev_info

Now that we never use the backing_dev_info pointer in struct address_space
we can simply remove it and save 4 to 8 bytes in every inode.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 drivers/char/raw.c     |  4 +---
 fs/aio.c               |  1 -
 fs/block_dev.c         | 26 +-------------------------
 fs/btrfs/disk-io.c     |  1 -
 fs/btrfs/inode.c       |  6 ------
 fs/ceph/inode.c        |  2 --
 fs/cifs/inode.c        |  2 --
 fs/configfs/inode.c    |  1 -
 fs/ecryptfs/inode.c    |  1 -
 fs/exofs/inode.c       |  2 --
 fs/fuse/inode.c        |  1 -
 fs/gfs2/glock.c        |  1 -
 fs/gfs2/ops_fstype.c   |  1 -
 fs/hugetlbfs/inode.c   |  1 -
 fs/inode.c             | 13 -------------
 fs/kernfs/inode.c      |  1 -
 fs/ncpfs/inode.c       |  1 -
 fs/nfs/inode.c         |  1 -
 fs/nilfs2/gcinode.c    |  1 -
 fs/nilfs2/mdt.c        |  6 ++----
 fs/nilfs2/page.c       |  4 +---
 fs/nilfs2/page.h       |  3 +--
 fs/nilfs2/super.c      |  2 +-
 fs/ocfs2/dlmfs/dlmfs.c |  2 --
 fs/ramfs/inode.c       |  1 -
 fs/romfs/super.c       |  3 ---
 fs/ubifs/dir.c         |  2 --
 fs/ubifs/super.c       |  3 ---
 include/linux/fs.h     |  3 +--
 mm/backing-dev.c       |  1 -
 mm/shmem.c             |  1 -
 mm/swap_state.c        |  1 -
 32 files changed, 8 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index a24891b9754..6e29bf2db53 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -104,11 +104,9 @@ static int raw_release(struct inode *inode, struct file *filp)
 
 	mutex_lock(&raw_mutex);
 	bdev = raw_devices[minor].binding;
-	if (--raw_devices[minor].inuse == 0) {
+	if (--raw_devices[minor].inuse == 0)
 		/* Here  inode->i_mapping == bdev->bd_inode->i_mapping  */
 		inode->i_mapping = &inode->i_data;
-		inode->i_mapping->backing_dev_info = &default_backing_dev_info;
-	}
 	mutex_unlock(&raw_mutex);
 
 	blkdev_put(bdev, filp->f_mode | FMODE_EXCL);
diff --git a/fs/aio.c b/fs/aio.c
index 6f13d3fab07..3bf8b1d250c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -176,7 +176,6 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 
 	inode->i_mapping->a_ops = &aio_ctx_aops;
 	inode->i_mapping->private_data = ctx;
-	inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
 	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 026ca7b8431..a9f92794d7a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -60,19 +60,6 @@ static void bdev_write_inode(struct inode *inode)
 	spin_unlock(&inode->i_lock);
 }
 
-/*
- * Move the inode from its current bdi to a new bdi.  Make sure the inode
- * is clean before moving so that it doesn't linger on the old bdi.
- */
-static void bdev_inode_switch_bdi(struct inode *inode,
-			struct backing_dev_info *dst)
-{
-	spin_lock(&inode->i_lock);
-	WARN_ON_ONCE(inode->i_state & I_DIRTY);
-	inode->i_data.backing_dev_info = dst;
-	spin_unlock(&inode->i_lock);
-}
-
 /* Kill _all_ buffers and pagecache , dirty or not.. */
 void kill_bdev(struct block_device *bdev)
 {
@@ -589,7 +576,6 @@ struct block_device *bdget(dev_t dev)
 		inode->i_bdev = bdev;
 		inode->i_data.a_ops = &def_blk_aops;
 		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
-		inode->i_data.backing_dev_info = &default_backing_dev_info;
 		spin_lock(&bdev_lock);
 		list_add(&bdev->bd_list, &all_bdevs);
 		spin_unlock(&bdev_lock);
@@ -1150,8 +1136,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
 		if (!partno) {
-			struct backing_dev_info *bdi;
-
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!bdev->bd_part)
@@ -1177,11 +1161,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				}
 			}
 
-			if (!ret) {
+			if (!ret)
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
-				bdi = blk_get_backing_dev_info(bdev);
-				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
-			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1208,8 +1189,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (ret)
 				goto out_clear;
 			bdev->bd_contains = whole;
-			bdev_inode_switch_bdi(bdev->bd_inode,
-				whole->bd_inode->i_data.backing_dev_info);
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
 			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
@@ -1249,7 +1228,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_queue = NULL;
-	bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
@@ -1474,8 +1452,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		 * dirty data before.
 		 */
 		bdev_write_inode(bdev->bd_inode);
-		bdev_inode_switch_bdi(bdev->bd_inode,
-					&default_backing_dev_info);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index afc4092989c..1ec872e3a92 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2318,7 +2318,6 @@ int open_ctree(struct super_block *sb,
 	 */
 	fs_info->btree_inode->i_size = OFFSET_MAX;
 	fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
-	fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
 
 	RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
 	extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8bf326affb9..54bcf639d1c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3608,7 +3608,6 @@ cache_acl:
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_mapping->a_ops = &btrfs_aops;
-		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 		BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 		inode->i_fop = &btrfs_file_operations;
 		inode->i_op = &btrfs_file_inode_operations;
@@ -3623,7 +3622,6 @@ cache_acl:
 	case S_IFLNK:
 		inode->i_op = &btrfs_symlink_inode_operations;
 		inode->i_mapping->a_ops = &btrfs_symlink_aops;
-		inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 		break;
 	default:
 		inode->i_op = &btrfs_special_inode_operations;
@@ -6088,7 +6086,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
@@ -9203,7 +9200,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	inode->i_fop = &btrfs_file_operations;
 	inode->i_op = &btrfs_file_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
@@ -9247,7 +9243,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 
 	inode->i_op = &btrfs_symlink_inode_operations;
 	inode->i_mapping->a_ops = &btrfs_symlink_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	inode_set_bytes(inode, name_len);
 	btrfs_i_size_write(inode, name_len);
 	err = btrfs_update_inode(trans, root, inode);
@@ -9459,7 +9454,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_op = &btrfs_file_inode_operations;
 
 	inode->i_mapping->a_ops = &btrfs_aops;
-	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
 	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index f61a74115be..6b517360515 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -783,8 +783,6 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
 	}
 
 	inode->i_mapping->a_ops = &ceph_aops;
-	inode->i_mapping->backing_dev_info =
-		&ceph_sb_to_client(inode->i_sb)->backing_dev_info;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFIFO:
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 0c3ce464cae..2d4f37235ed 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -937,8 +937,6 @@ retry_iget5_locked:
 			inode->i_flags |= S_NOATIME | S_NOCMTIME;
 		if (inode->i_state & I_NEW) {
 			inode->i_ino = hash;
-			if (S_ISREG(inode->i_mode))
-				inode->i_data.backing_dev_info = sb->s_bdi;
 #ifdef CONFIG_CIFS_FSCACHE
 			/* initialize per-inode cache cookie pointer */
 			CIFS_I(inode)->fscache = NULL;
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 0ad6b4d6de0..65af8614715 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -131,7 +131,6 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd,
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode->i_mapping->a_ops = &configfs_aops;
-		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		inode->i_op = &configfs_inode_operations;
 
 		if (sd->s_iattr) {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1686dc2da9f..34b36a50405 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -67,7 +67,6 @@ static int ecryptfs_inode_set(struct inode *inode, void *opaque)
 	inode->i_ino = lower_inode->i_ino;
 	inode->i_version++;
 	inode->i_mapping->a_ops = &ecryptfs_aops;
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	if (S_ISLNK(inode->i_mode))
 		inode->i_op = &ecryptfs_symlink_iops;
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index f1d3d4eb8c4..6fc91df99ff 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1214,7 +1214,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
 		memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
 	}
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &exofs_file_inode_operations;
 		inode->i_fop = &exofs_file_operations;
@@ -1314,7 +1313,6 @@ struct inode *exofs_new_inode(struct inode *dir, umode_t mode)
 
 	set_obj_2bcreated(oi);
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	inode_init_owner(inode, dir, mode);
 	inode->i_ino = sbi->s_nextid++;
 	inode->i_blkbits = EXOFS_BLKSHIFT;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f38256e4476..e8799c11424 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -308,7 +308,6 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid,
 		if (!fc->writeback_cache || !S_ISREG(attr->mode))
 			inode->i_flags |= S_NOCMTIME;
 		inode->i_generation = generation;
-		inode->i_data.backing_dev_info = &fc->bdi;
 		fuse_init_inode(inode, attr);
 		unlock_new_inode(inode);
 	} else if ((inode->i_mode ^ attr->mode) & S_IFMT) {
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a23524aa3ea..08ea717981f 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -775,7 +775,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_NOFS);
 		mapping->private_data = NULL;
-		mapping->backing_dev_info = s->s_bdi;
 		mapping->writeback_index = 0;
 	}
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 8633ad328ee..efc8e254787 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -112,7 +112,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = sb->s_bdi;
 	mapping->writeback_index = 0;
 
 	spin_lock_init(&sdp->sd_log_lock);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index de7c95c7d84..c274aca8e8d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -492,7 +492,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
-		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_mapping->private_data = resv_map;
 		info = HUGETLBFS_I(inode);
diff --git a/fs/inode.c b/fs/inode.c
index aa149e7262a..e4e8caa7464 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -170,20 +170,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	atomic_set(&mapping->i_mmap_writable, 0);
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = &default_backing_dev_info;
 	mapping->writeback_index = 0;
-
-	/*
-	 * If the block_device provides a backing_dev_info for client
-	 * inodes then use that.  Otherwise the inode share the bdev's
-	 * backing_dev_info.
-	 */
-	if (sb->s_bdev) {
-		struct backing_dev_info *bdi;
-
-		bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
-		mapping->backing_dev_info = bdi;
-	}
 	inode->i_private = NULL;
 	inode->i_mapping = mapping;
 	INIT_HLIST_HEAD(&inode->i_dentry);	/* buggered by rcu freeing */
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 06f06887b2d..9000874a945 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -286,7 +286,6 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
 	kernfs_get(kn);
 	inode->i_private = kn;
 	inode->i_mapping->a_ops = &kernfs_aops;
-	inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 	inode->i_op = &kernfs_iops;
 
 	set_default_inode_attr(inode, kn->mode);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index a699a3fc62c..01a9e16e978 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -267,7 +267,6 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 	if (inode) {
 		atomic_set(&NCP_FINFO(inode)->opened, info->opened);
 
-		inode->i_mapping->backing_dev_info = sb->s_bdi;
 		inode->i_ino = info->ino;
 		ncp_set_attr(inode, info);
 		if (S_ISREG(inode->i_mode)) {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 4bffe637ea3..24aac72420f 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -387,7 +387,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		if (S_ISREG(inode->i_mode)) {
 			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
-			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
 			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 57ceaf33d17..748ca238915 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -172,7 +172,6 @@ int nilfs_init_gcinode(struct inode *inode)
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 	inode->i_mapping->a_ops = &empty_aops;
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	ii->i_flags = 0;
 	nilfs_bmap_init_gc(ii->i_bmap);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index c4dcd1db57e..892cf5ffdb8 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -429,7 +429,6 @@ int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz)
 
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, gfp_mask);
-	inode->i_mapping->backing_dev_info = inode->i_sb->s_bdi;
 
 	inode->i_op = &def_mdt_iops;
 	inode->i_fop = &def_mdt_fops;
@@ -457,13 +456,12 @@ int nilfs_mdt_setup_shadow_map(struct inode *inode,
 			       struct nilfs_shadow_map *shadow)
 {
 	struct nilfs_mdt_info *mi = NILFS_MDT(inode);
-	struct backing_dev_info *bdi = inode->i_sb->s_bdi;
 
 	INIT_LIST_HEAD(&shadow->frozen_buffers);
 	address_space_init_once(&shadow->frozen_data);
-	nilfs_mapping_init(&shadow->frozen_data, inode, bdi);
+	nilfs_mapping_init(&shadow->frozen_data, inode);
 	address_space_init_once(&shadow->frozen_btnodes);
-	nilfs_mapping_init(&shadow->frozen_btnodes, inode, bdi);
+	nilfs_mapping_init(&shadow->frozen_btnodes, inode);
 	mi->mi_shadow = shadow;
 	return 0;
 }
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index da276640f77..700ecbcca55 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -461,14 +461,12 @@ unsigned nilfs_page_count_clean_buffers(struct page *page,
 	return nc;
 }
 
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
-			struct backing_dev_info *bdi)
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode)
 {
 	mapping->host = inode;
 	mapping->flags = 0;
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
 	mapping->private_data = NULL;
-	mapping->backing_dev_info = bdi;
 	mapping->a_ops = &empty_aops;
 }
 
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index ef30c5c2426..a43b8287d01 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -57,8 +57,7 @@ int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
 void nilfs_copy_back_pages(struct address_space *, struct address_space *);
 void nilfs_clear_dirty_page(struct page *, bool);
 void nilfs_clear_dirty_pages(struct address_space *, bool);
-void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
-			struct backing_dev_info *bdi);
+void nilfs_mapping_init(struct address_space *mapping, struct inode *inode);
 unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
 unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
 					    sector_t start_blk,
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 3d4bbac36be..5bc2a1cf73c 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -166,7 +166,7 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
 	ii->i_state = 0;
 	ii->i_cno = 0;
 	ii->vfs_inode.i_version = 1;
-	nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode, sb->s_bdi);
+	nilfs_mapping_init(&ii->i_btnode_cache, &ii->vfs_inode);
 	return &ii->vfs_inode;
 }
 
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 6000d3029b2..061ba6a91bf 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -398,7 +398,6 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 	if (inode) {
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, NULL, mode);
-		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inc_nlink(inode);
 
@@ -422,7 +421,6 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
 
 	inode->i_ino = get_next_ino();
 	inode_init_owner(inode, parent, mode);
-	inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 
 	ip = DLMFS_I(inode);
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index ad4d712002f..889d558b4e0 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -59,7 +59,6 @@ struct inode *ramfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_mapping->a_ops = &ramfs_aops;
-		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
 		mapping_set_unevictable(inode->i_mapping);
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index e98dd88197d..268733cda39 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -355,9 +355,6 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos)
 	case ROMFH_REG:
 		i->i_fop = &romfs_ro_fops;
 		i->i_data.a_ops = &romfs_aops;
-		if (i->i_sb->s_mtd)
-			i->i_data.backing_dev_info =
-				i->i_sb->s_mtd->backing_dev_info;
 		if (nextfh & ROMFH_EXEC)
 			mode |= S_IXUGO;
 		break;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index ea41649e4ca..c49b1981ac9 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -108,8 +108,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir,
 	inode->i_mtime = inode->i_atime = inode->i_ctime =
 			 ubifs_current_time(inode);
 	inode->i_mapping->nrpages = 0;
-	/* Disable readahead */
-	inode->i_mapping->backing_dev_info = &c->bdi;
 
 	switch (mode & S_IFMT) {
 	case S_IFREG:
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index ed93dc6ae24..6197154f36c 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -156,9 +156,6 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum)
 	if (err)
 		goto out_invalid;
 
-	/* Disable read-ahead */
-	inode->i_mapping->backing_dev_info = &c->bdi;
-
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_mapping->a_ops = &ubifs_file_address_operations;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1dada399aa2..65d02de342e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -34,6 +34,7 @@
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
 
+struct backing_dev_info;
 struct export_operations;
 struct hd_geometry;
 struct iovec;
@@ -394,7 +395,6 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct page *page, void *fsdata);
 
-struct backing_dev_info;
 struct address_space {
 	struct inode		*host;		/* owner: inode, block_device */
 	struct radix_tree_root	page_tree;	/* radix tree of all pages */
@@ -409,7 +409,6 @@ struct address_space {
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
 	unsigned long		flags;		/* error bits/gfp mask */
-	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
 	spinlock_t		private_lock;	/* for use by the address_space */
 	struct list_head	private_list;	/* ditto */
 	void			*private_data;	/* ditto */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 16c68958aed..52e0c765244 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -24,7 +24,6 @@ struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
-EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 1b77eaf589f..4c61d3d5bfb 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1410,7 +1410,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_blocks = 0;
-		inode->i_mapping->backing_dev_info = &noop_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_generation = get_seconds();
 		info = SHMEM_I(inode);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 1c137b69ecd..405923f7733 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -37,7 +37,6 @@ struct address_space swapper_spaces[MAX_SWAPFILES] = {
 		.page_tree	= RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
 		.i_mmap_writable = ATOMIC_INIT(0),
 		.a_ops		= &swap_aops,
-		.backing_dev_info = &noop_backing_dev_info,
 	}
 };
 
-- 
cgit v1.2.3-70-g09d2


From df0ce26cb4ee8bc233d50213b97213532aff0a3c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 14 Jan 2015 10:42:41 +0100
Subject: fs: remove default_backing_dev_info

Now that default_backing_dev_info is not used for writeback purposes we can
git rid of it easily:

 - instead of using it's name for tracing unregistered bdi we just use
   "unknown"
 - btrfs and ceph can just assign the default read ahead window themselves
   like several other filesystems already do.
 - we can assign noop_backing_dev_info as the default one in alloc_super.
   All filesystems already either assigned their own or
   noop_backing_dev_info.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 fs/btrfs/disk-io.c               | 2 +-
 fs/ceph/super.c                  | 2 +-
 fs/super.c                       | 8 ++------
 include/linux/backing-dev.h      | 1 -
 include/trace/events/writeback.h | 6 ++----
 mm/backing-dev.c                 | 9 ---------
 6 files changed, 6 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1ec872e3a92..1afb18226da 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1719,7 +1719,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 	if (err)
 		return err;
 
-	bdi->ra_pages	= default_backing_dev_info.ra_pages;
+	bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
 	bdi->congested_fn	= btrfs_congested_fn;
 	bdi->congested_data	= info;
 	return 0;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index e350cc1611e..5ae62587a71 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -899,7 +899,7 @@ static int ceph_register_bdi(struct super_block *sb,
 			>> PAGE_SHIFT;
 	else
 		fsc->backing_dev_info.ra_pages =
-			default_backing_dev_info.ra_pages;
+			VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
 
 	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
 			   atomic_long_inc_return(&bdi_seq));
diff --git a/fs/super.c b/fs/super.c
index eae088f6aaa..3b4dadafdd6 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -185,8 +185,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	}
 	init_waitqueue_head(&s->s_writers.wait);
 	init_waitqueue_head(&s->s_writers.wait_unfrozen);
+	s->s_bdi = &noop_backing_dev_info;
 	s->s_flags = flags;
-	s->s_bdi = &default_backing_dev_info;
 	INIT_HLIST_NODE(&s->s_instances);
 	INIT_HLIST_BL_HEAD(&s->s_anon);
 	INIT_LIST_HEAD(&s->s_inodes);
@@ -863,10 +863,7 @@ EXPORT_SYMBOL(free_anon_bdev);
 
 int set_anon_super(struct super_block *s, void *data)
 {
-	int error = get_anon_bdev(&s->s_dev);
-	if (!error)
-		s->s_bdi = &noop_backing_dev_info;
-	return error;
+	return get_anon_bdev(&s->s_dev);
 }
 
 EXPORT_SYMBOL(set_anon_super);
@@ -1111,7 +1108,6 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
 	sb = root->d_sb;
 	BUG_ON(!sb);
 	WARN_ON(!sb->s_bdi);
-	WARN_ON(sb->s_bdi == &default_backing_dev_info);
 	sb->s_flags |= MS_BORN;
 
 	error = security_sb_kern_mount(sb, flags, secdata);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index ed59dee03a7..d94077fea1f 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -241,7 +241,6 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \
 	(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
 
-extern struct backing_dev_info default_backing_dev_info;
 extern struct backing_dev_info noop_backing_dev_info;
 
 int writeback_in_progress(struct backing_dev_info *bdi);
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 74f5207bd09..0e931090541 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -156,10 +156,8 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(int, reason)
 	),
 	TP_fast_assign(
-		struct device *dev = bdi->dev;
-		if (!dev)
-			dev = default_backing_dev_info.dev;
-		strncpy(__entry->name, dev_name(dev), 32);
+		strncpy(__entry->name,
+			bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
 		__entry->nr_pages = work->nr_pages;
 		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
 		__entry->sync_mode = work->sync_mode;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1725adb242e..7690ec77c72 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -14,12 +14,6 @@
 
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-struct backing_dev_info default_backing_dev_info = {
-	.name		= "default",
-	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
-};
-EXPORT_SYMBOL_GPL(default_backing_dev_info);
-
 struct backing_dev_info noop_backing_dev_info = {
 	.name		= "noop",
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
@@ -250,9 +244,6 @@ static int __init default_bdi_init(void)
 	if (!bdi_wq)
 		return -ENOMEM;
 
-	err = bdi_init(&default_backing_dev_info);
-	if (!err)
-		bdi_register(&default_backing_dev_info, NULL, "default");
 	err = bdi_init(&noop_backing_dev_info);
 
 	return err;
-- 
cgit v1.2.3-70-g09d2


From 85cdf36e11557dc367c1361e4b7bb2c4619cae91 Mon Sep 17 00:00:00 2001
From: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Date: Thu, 1 Jan 2015 18:04:52 +0100
Subject: power: ab8500_fg.c: Remove unused function

Remove the function ab8500_fg_reinit() that is not used anywhere.

This was partially found by using a static code analysis program called cppcheck.

Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sebastian Reichel <sre@kernel.org>
---
 drivers/power/ab8500_fg.c            | 14 --------------
 include/linux/mfd/abx500/ab8500-bm.h |  1 -
 2 files changed, 15 deletions(-)

(limited to 'include')

diff --git a/drivers/power/ab8500_fg.c b/drivers/power/ab8500_fg.c
index 69b80bcaa9e..c908658aa31 100644
--- a/drivers/power/ab8500_fg.c
+++ b/drivers/power/ab8500_fg.c
@@ -2435,20 +2435,6 @@ static void ab8500_fg_reinit_work(struct work_struct *work)
 	}
 }
 
-/**
- * ab8500_fg_reinit() - forces FG algorithm to reinitialize with current values
- *
- * This function can be used to force the FG algorithm to recalculate a new
- * voltage based battery capacity.
- */
-void ab8500_fg_reinit(void)
-{
-	struct ab8500_fg *di = ab8500_fg_get();
-	/* User won't be notified if a null pointer returned. */
-	if (di != NULL)
-		queue_delayed_work(di->fg_wq, &di->fg_reinit_work, 0);
-}
-
 /* Exposure to the sysfs interface */
 
 struct ab8500_fg_sysfs_entry {
diff --git a/include/linux/mfd/abx500/ab8500-bm.h b/include/linux/mfd/abx500/ab8500-bm.h
index cc892a8d8d6..12a5b396921 100644
--- a/include/linux/mfd/abx500/ab8500-bm.h
+++ b/include/linux/mfd/abx500/ab8500-bm.h
@@ -461,7 +461,6 @@ struct ab8500_fg;
 #ifdef CONFIG_AB8500_BM
 extern struct abx500_bm_data ab8500_bm_data;
 
-void ab8500_fg_reinit(void);
 void ab8500_charger_usb_state_changed(u8 bm_usb_state, u16 mA);
 struct ab8500_btemp *ab8500_btemp_get(void);
 int ab8500_btemp_get_batctrl_temp(struct ab8500_btemp *btemp);
-- 
cgit v1.2.3-70-g09d2


From 9c45101e88b2bf2ce36b8833fcfa784a9149aa74 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 19 Nov 2014 09:21:58 +0100
Subject: quota: Cleanup flags definitions

Currently all quota flags were defined just in kernel-private headers.
Export flags readable / writeable from userspace to userspace via
include/uapi/linux/quota.h.

Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/dquot.c           |  2 +-
 include/linux/dqblk_v1.h   |  3 ---
 include/linux/quota.h      | 14 ++++++++------
 include/uapi/linux/quota.h | 14 +++++++++++++-
 4 files changed, 22 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 8f0acef3d18..f8be368b908 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1248,7 +1248,7 @@ static int ignore_hardlimit(struct dquot *dquot)
 
 	return capable(CAP_SYS_RESOURCE) &&
 	       (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD ||
-		!(info->dqi_flags & V1_DQF_RSQUASH));
+		!(info->dqi_flags & DQF_ROOT_SQUASH));
 }
 
 /* needs dq_data_lock */
diff --git a/include/linux/dqblk_v1.h b/include/linux/dqblk_v1.h
index 3713a7232dd..c0d4d1e2a45 100644
--- a/include/linux/dqblk_v1.h
+++ b/include/linux/dqblk_v1.h
@@ -5,9 +5,6 @@
 #ifndef _LINUX_DQBLK_V1_H
 #define _LINUX_DQBLK_V1_H
 
-/* Root squash turned on */
-#define V1_DQF_RSQUASH 1
-
 /* Numbers of blocks needed for updates */
 #define V1_INIT_ALLOC 1
 #define V1_INIT_REWRITE 1
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 50978b781a1..0c42113607c 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -223,12 +223,14 @@ struct mem_dqinfo {
 
 struct super_block;
 
-#define DQF_MASK 0xffff		/* Mask for format specific flags */
-#define DQF_GETINFO_MASK 0x1ffff	/* Mask for flags passed to userspace */
-#define DQF_SETINFO_MASK 0xffff		/* Mask for flags modifiable from userspace */
-#define DQF_SYS_FILE_B		16
-#define DQF_SYS_FILE (1 << DQF_SYS_FILE_B)	/* Quota file stored as system file */
-#define DQF_INFO_DIRTY_B	31
+/* Mask for flags passed to userspace */
+#define DQF_GETINFO_MASK (DQF_ROOT_SQUASH | DQF_SYS_FILE)
+/* Mask for flags modifiable from userspace */
+#define DQF_SETINFO_MASK DQF_ROOT_SQUASH
+
+enum {
+	DQF_INFO_DIRTY_B = DQF_PRIVATE,
+};
 #define DQF_INFO_DIRTY (1 << DQF_INFO_DIRTY_B)	/* Is info dirty? */
 
 extern void mark_info_dirty(struct super_block *sb, int type);
diff --git a/include/uapi/linux/quota.h b/include/uapi/linux/quota.h
index 3b6cfbeb086..1f49b8341c9 100644
--- a/include/uapi/linux/quota.h
+++ b/include/uapi/linux/quota.h
@@ -126,10 +126,22 @@ struct if_dqblk {
 #define IIF_FLAGS	4
 #define IIF_ALL		(IIF_BGRACE | IIF_IGRACE | IIF_FLAGS)
 
+enum {
+	DQF_ROOT_SQUASH_B = 0,
+	DQF_SYS_FILE_B = 16,
+	/* Kernel internal flags invisible to userspace */
+	DQF_PRIVATE
+};
+
+/* Root squash enabled (for v1 quota format) */
+#define DQF_ROOT_SQUASH	(1 << DQF_ROOT_SQUASH_B)
+/* Quota stored in a system file */
+#define DQF_SYS_FILE	(1 << DQF_SYS_FILE_B)
+
 struct if_dqinfo {
 	__u64 dqi_bgrace;
 	__u64 dqi_igrace;
-	__u32 dqi_flags;
+	__u32 dqi_flags;	/* DFQ_* */
 	__u32 dqi_valid;
 };
 
-- 
cgit v1.2.3-70-g09d2


From c1155c64e603378dccfc21ee0612cf60dd11725b Mon Sep 17 00:00:00 2001
From: Jonghwa Lee <jonghwa3.lee@samsung.com>
Date: Fri, 19 Dec 2014 17:55:13 +0900
Subject: power: charger-manager: Use alarmtimer for battery monitoring in
 suspend.

To guerantee proper charing and managing batteries even in suspend,
charger-manager has used rtc device with rtc framework interface.
However, it is better to use alarmtimer for cleaner and more appropriate
operation.
This patch makes driver to use alarmtimer for polling work in suspend and
removes all deprecated codes related with using rtc interface.

Signed-off-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
Signed-off-by: Sebastian Reichel <sre@kernel.org>
---
 drivers/power/Kconfig                 |   2 +-
 drivers/power/charger-manager.c       | 289 ++++++++++------------------------
 include/linux/power/charger-manager.h |  32 +---
 3 files changed, 84 insertions(+), 239 deletions(-)

(limited to 'include')

diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index e2569a53850..a79f16afb58 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -315,7 +315,7 @@ config CHARGER_GPIO
 
 config CHARGER_MANAGER
 	bool "Battery charger manager for multiple chargers"
-	depends on REGULATOR && RTC_CLASS
+	depends on REGULATOR
 	select EXTCON
 	help
           Say Y to enable charger-manager support, which allows multiple
diff --git a/drivers/power/charger-manager.c b/drivers/power/charger-manager.c
index 649052e1f2d..14b0d85318e 100644
--- a/drivers/power/charger-manager.c
+++ b/drivers/power/charger-manager.c
@@ -69,16 +69,10 @@ static LIST_HEAD(cm_list);
 static DEFINE_MUTEX(cm_list_mtx);
 
 /* About in-suspend (suspend-again) monitoring */
-static struct rtc_device *rtc_dev;
-/*
- * Backup RTC alarm
- * Save the wakeup alarm before entering suspend-to-RAM
- */
-static struct rtc_wkalrm rtc_wkalarm_save;
-/* Backup RTC alarm time in terms of seconds since 01-01-1970 00:00:00 */
-static unsigned long rtc_wkalarm_save_time;
+static struct alarm *cm_timer;
+
 static bool cm_suspended;
-static bool cm_rtc_set;
+static bool cm_timer_set;
 static unsigned long cm_suspend_duration_ms;
 
 /* About normal (not suspended) monitoring */
@@ -87,9 +81,6 @@ static unsigned long next_polling; /* Next appointed polling time */
 static struct workqueue_struct *cm_wq; /* init at driver add */
 static struct delayed_work cm_monitor_work; /* init at driver add */
 
-/* Global charger-manager description */
-static struct charger_global_desc *g_desc; /* init with setup_charger_manager */
-
 /**
  * is_batt_present - See if the battery presents in place.
  * @cm: the Charger Manager representing the battery.
@@ -1047,10 +1038,13 @@ static bool cm_setup_timer(void)
 {
 	struct charger_manager *cm;
 	unsigned int wakeup_ms = UINT_MAX;
-	bool ret = false;
+	int timer_req = 0;
 
-	mutex_lock(&cm_list_mtx);
+	if (time_after(next_polling, jiffies))
+		CM_MIN_VALID(wakeup_ms,
+			jiffies_to_msecs(next_polling - jiffies));
 
+	mutex_lock(&cm_list_mtx);
 	list_for_each_entry(cm, &cm_list, entry) {
 		unsigned int fbchk_ms = 0;
 
@@ -1070,162 +1064,38 @@ static bool cm_setup_timer(void)
 		/* Skip if polling is not required for this CM */
 		if (!is_polling_required(cm) && !cm->emergency_stop)
 			continue;
+		timer_req++;
 		if (cm->desc->polling_interval_ms == 0)
 			continue;
 		CM_MIN_VALID(wakeup_ms, cm->desc->polling_interval_ms);
 	}
-
 	mutex_unlock(&cm_list_mtx);
 
-	if (wakeup_ms < UINT_MAX && wakeup_ms > 0) {
-		pr_info("Charger Manager wakeup timer: %u ms\n", wakeup_ms);
-		if (rtc_dev) {
-			struct rtc_wkalrm tmp;
-			unsigned long time, now;
-			unsigned long add = DIV_ROUND_UP(wakeup_ms, 1000);
-
-			/*
-			 * Set alarm with the polling interval (wakeup_ms)
-			 * except when rtc_wkalarm_save comes first.
-			 * However, the alarm time should be NOW +
-			 * CM_RTC_SMALL or later.
-			 */
-			tmp.enabled = 1;
-			rtc_read_time(rtc_dev, &tmp.time);
-			rtc_tm_to_time(&tmp.time, &now);
-			if (add < CM_RTC_SMALL)
-				add = CM_RTC_SMALL;
-			time = now + add;
+	if (timer_req && cm_timer) {
+		ktime_t now, add;
 
-			ret = true;
+		/*
+		 * Set alarm with the polling interval (wakeup_ms)
+		 * The alarm time should be NOW + CM_RTC_SMALL or later.
+		 */
+		if (wakeup_ms == UINT_MAX ||
+			wakeup_ms < CM_RTC_SMALL * MSEC_PER_SEC)
+			wakeup_ms = 2 * CM_RTC_SMALL * MSEC_PER_SEC;
 
-			if (rtc_wkalarm_save.enabled &&
-			    rtc_wkalarm_save_time &&
-			    rtc_wkalarm_save_time < time) {
-				if (rtc_wkalarm_save_time < now + CM_RTC_SMALL)
-					time = now + CM_RTC_SMALL;
-				else
-					time = rtc_wkalarm_save_time;
+		pr_info("Charger Manager wakeup timer: %u ms\n", wakeup_ms);
 
-				/* The timer is not appointed by CM */
-				ret = false;
-			}
+		now = ktime_get_boottime();
+		add = ktime_set(wakeup_ms / MSEC_PER_SEC,
+				(wakeup_ms % MSEC_PER_SEC) * NSEC_PER_MSEC);
+		alarm_start(cm_timer, ktime_add(now, add));
 
-			pr_info("Waking up after %lu secs\n", time - now);
+		cm_suspend_duration_ms = wakeup_ms;
 
-			rtc_time_to_tm(time, &tmp.time);
-			rtc_set_alarm(rtc_dev, &tmp);
-			cm_suspend_duration_ms += wakeup_ms;
-			return ret;
-		}
+		return true;
 	}
-
-	if (rtc_dev)
-		rtc_set_alarm(rtc_dev, &rtc_wkalarm_save);
 	return false;
 }
 
-static void _cm_fbchk_in_suspend(struct charger_manager *cm)
-{
-	unsigned long jiffy_now = jiffies;
-
-	if (!cm->fullbatt_vchk_jiffies_at)
-		return;
-
-	if (g_desc && g_desc->assume_timer_stops_in_suspend)
-		jiffy_now += msecs_to_jiffies(cm_suspend_duration_ms);
-
-	/* Execute now if it's going to be executed not too long after */
-	jiffy_now += CM_JIFFIES_SMALL;
-
-	if (time_after_eq(jiffy_now, cm->fullbatt_vchk_jiffies_at))
-		fullbatt_vchk(&cm->fullbatt_vchk_work.work);
-}
-
-/**
- * cm_suspend_again - Determine whether suspend again or not
- *
- * Returns true if the system should be suspended again
- * Returns false if the system should be woken up
- */
-bool cm_suspend_again(void)
-{
-	struct charger_manager *cm;
-	bool ret = false;
-
-	if (!g_desc || !g_desc->rtc_only_wakeup || !g_desc->rtc_only_wakeup() ||
-	    !cm_rtc_set)
-		return false;
-
-	if (cm_monitor())
-		goto out;
-
-	ret = true;
-	mutex_lock(&cm_list_mtx);
-	list_for_each_entry(cm, &cm_list, entry) {
-		_cm_fbchk_in_suspend(cm);
-
-		if (cm->status_save_ext_pwr_inserted != is_ext_pwr_online(cm) ||
-		    cm->status_save_batt != is_batt_present(cm)) {
-			ret = false;
-			break;
-		}
-	}
-	mutex_unlock(&cm_list_mtx);
-
-	cm_rtc_set = cm_setup_timer();
-out:
-	/* It's about the time when the non-CM appointed timer goes off */
-	if (rtc_wkalarm_save.enabled) {
-		unsigned long now;
-		struct rtc_time tmp;
-
-		rtc_read_time(rtc_dev, &tmp);
-		rtc_tm_to_time(&tmp, &now);
-
-		if (rtc_wkalarm_save_time &&
-		    now + CM_RTC_SMALL >= rtc_wkalarm_save_time)
-			return false;
-	}
-	return ret;
-}
-EXPORT_SYMBOL_GPL(cm_suspend_again);
-
-/**
- * setup_charger_manager - initialize charger_global_desc data
- * @gd: pointer to instance of charger_global_desc
- */
-int setup_charger_manager(struct charger_global_desc *gd)
-{
-	if (!gd)
-		return -EINVAL;
-
-	if (rtc_dev)
-		rtc_class_close(rtc_dev);
-	rtc_dev = NULL;
-	g_desc = NULL;
-
-	if (!gd->rtc_only_wakeup) {
-		pr_err("The callback rtc_only_wakeup is not given\n");
-		return -EINVAL;
-	}
-
-	if (gd->rtc_name) {
-		rtc_dev = rtc_class_open(gd->rtc_name);
-		if (IS_ERR_OR_NULL(rtc_dev)) {
-			rtc_dev = NULL;
-			/* Retry at probe. RTC may be not registered yet */
-		}
-	} else {
-		pr_warn("No wakeup timer is given for charger manager.  "
-			"In-suspend monitoring won't work.\n");
-	}
-
-	g_desc = gd;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(setup_charger_manager);
-
 /**
  * charger_extcon_work - enable/diable charger according to the state
  *			of charger cable
@@ -1719,6 +1589,12 @@ static inline struct charger_desc *cm_get_drv_data(struct platform_device *pdev)
 	return dev_get_platdata(&pdev->dev);
 }
 
+static enum alarmtimer_restart cm_timer_func(struct alarm *alarm, ktime_t now)
+{
+	cm_timer_set = false;
+	return ALARMTIMER_NORESTART;
+}
+
 static int charger_manager_probe(struct platform_device *pdev)
 {
 	struct charger_desc *desc = cm_get_drv_data(pdev);
@@ -1728,16 +1604,6 @@ static int charger_manager_probe(struct platform_device *pdev)
 	union power_supply_propval val;
 	struct power_supply *fuel_gauge;
 
-	if (g_desc && !rtc_dev && g_desc->rtc_name) {
-		rtc_dev = rtc_class_open(g_desc->rtc_name);
-		if (IS_ERR_OR_NULL(rtc_dev)) {
-			rtc_dev = NULL;
-			dev_err(&pdev->dev, "Cannot get RTC %s\n",
-				g_desc->rtc_name);
-			return -ENODEV;
-		}
-	}
-
 	if (IS_ERR(desc)) {
 		dev_err(&pdev->dev, "No platform data (desc) found\n");
 		return -ENODEV;
@@ -1752,6 +1618,12 @@ static int charger_manager_probe(struct platform_device *pdev)
 	cm->dev = &pdev->dev;
 	cm->desc = desc;
 
+	/* Initialize alarm timer */
+	if (alarmtimer_get_rtcdev()) {
+		cm_timer = devm_kzalloc(cm->dev, sizeof(*cm_timer), GFP_KERNEL);
+		alarm_init(cm_timer, ALARM_BOOTTIME, cm_timer_func);
+	}
+
 	/*
 	 * The following two do not need to be errors.
 	 * Users may intentionally ignore those two features.
@@ -1993,38 +1865,41 @@ static int cm_suspend_noirq(struct device *dev)
 	return ret;
 }
 
+static bool cm_need_to_awake(void)
+{
+	struct charger_manager *cm;
+
+	if (cm_timer)
+		return false;
+
+	mutex_lock(&cm_list_mtx);
+	list_for_each_entry(cm, &cm_list, entry) {
+		if (is_charging(cm)) {
+			mutex_unlock(&cm_list_mtx);
+			return true;
+		}
+	}
+	mutex_unlock(&cm_list_mtx);
+
+	return false;
+}
+
 static int cm_suspend_prepare(struct device *dev)
 {
 	struct charger_manager *cm = dev_get_drvdata(dev);
 
-	if (!cm_suspended) {
-		if (rtc_dev) {
-			struct rtc_time tmp;
-			unsigned long now;
-
-			rtc_read_alarm(rtc_dev, &rtc_wkalarm_save);
-			rtc_read_time(rtc_dev, &tmp);
+	if (cm_need_to_awake())
+		return -EBUSY;
 
-			if (rtc_wkalarm_save.enabled) {
-				rtc_tm_to_time(&rtc_wkalarm_save.time,
-					       &rtc_wkalarm_save_time);
-				rtc_tm_to_time(&tmp, &now);
-				if (now > rtc_wkalarm_save_time)
-					rtc_wkalarm_save_time = 0;
-			} else {
-				rtc_wkalarm_save_time = 0;
-			}
-		}
+	if (!cm_suspended)
 		cm_suspended = true;
-	}
 
-	cancel_delayed_work(&cm->fullbatt_vchk_work);
-	cm->status_save_ext_pwr_inserted = is_ext_pwr_online(cm);
-	cm->status_save_batt = is_batt_present(cm);
+	cm_timer_set = cm_setup_timer();
 
-	if (!cm_rtc_set) {
-		cm_suspend_duration_ms = 0;
-		cm_rtc_set = cm_setup_timer();
+	if (cm_timer_set) {
+		cancel_work_sync(&setup_polling);
+		cancel_delayed_work_sync(&cm_monitor_work);
+		cancel_delayed_work(&cm->fullbatt_vchk_work);
 	}
 
 	return 0;
@@ -2034,18 +1909,21 @@ static void cm_suspend_complete(struct device *dev)
 {
 	struct charger_manager *cm = dev_get_drvdata(dev);
 
-	if (cm_suspended) {
-		if (rtc_dev) {
-			struct rtc_wkalrm tmp;
-
-			rtc_read_alarm(rtc_dev, &tmp);
-			rtc_wkalarm_save.pending = tmp.pending;
-			rtc_set_alarm(rtc_dev, &rtc_wkalarm_save);
-		}
+	if (cm_suspended)
 		cm_suspended = false;
-		cm_rtc_set = false;
+
+	if (cm_timer_set) {
+		ktime_t remain;
+
+		alarm_cancel(cm_timer);
+		cm_timer_set = false;
+		remain = alarm_expires_remaining(cm_timer);
+		cm_suspend_duration_ms -= ktime_to_ms(remain);
+		schedule_work(&setup_polling);
 	}
 
+	_cm_monitor(cm);
+
 	/* Re-enqueue delayed work (fullbatt_vchk_work) */
 	if (cm->fullbatt_vchk_jiffies_at) {
 		unsigned long delay = 0;
@@ -2060,21 +1938,18 @@ static void cm_suspend_complete(struct device *dev)
 		}
 
 		/*
-		 * Account for cm_suspend_duration_ms if
-		 * assume_timer_stops_in_suspend is active
+		 * Account for cm_suspend_duration_ms with assuming that
+		 * timer stops in suspend.
 		 */
-		if (g_desc && g_desc->assume_timer_stops_in_suspend) {
-			if (delay > cm_suspend_duration_ms)
-				delay -= cm_suspend_duration_ms;
-			else
-				delay = 0;
-		}
+		if (delay > cm_suspend_duration_ms)
+			delay -= cm_suspend_duration_ms;
+		else
+			delay = 0;
 
 		queue_delayed_work(cm_wq, &cm->fullbatt_vchk_work,
 				   msecs_to_jiffies(delay));
 	}
 	device_set_wakeup_capable(cm->dev, false);
-	uevent_notify(cm, NULL);
 }
 
 static const struct dev_pm_ops charger_manager_pm = {
diff --git a/include/linux/power/charger-manager.h b/include/linux/power/charger-manager.h
index e97fc656a05..416ebeb6ee1 100644
--- a/include/linux/power/charger-manager.h
+++ b/include/linux/power/charger-manager.h
@@ -17,6 +17,7 @@
 
 #include <linux/power_supply.h>
 #include <linux/extcon.h>
+#include <linux/alarmtimer.h>
 
 enum data_source {
 	CM_BATTERY_PRESENT,
@@ -44,29 +45,6 @@ enum cm_event_types {
 	CM_EVENT_OTHERS,
 };
 
-/**
- * struct charger_global_desc
- * @rtc_name: the name of RTC used to wake up the system from suspend.
- * @rtc_only_wakeup:
- *	If the system is woken up by waekup-sources other than the RTC or
- *	callbacks, Charger Manager should recognize with
- *	rtc_only_wakeup() returning false.
- *	If the RTC given to CM is the only wakeup reason,
- *	rtc_only_wakeup should return true.
- * @assume_timer_stops_in_suspend:
- *	Assume that the jiffy timer stops in suspend-to-RAM.
- *	When enabled, CM does not rely on jiffies value in
- *	suspend_again and assumes that jiffies value does not
- *	change during suspend.
- */
-struct charger_global_desc {
-	char *rtc_name;
-
-	bool (*rtc_only_wakeup)(void);
-
-	bool assume_timer_stops_in_suspend;
-};
-
 /**
  * struct charger_cable
  * @extcon_name: the name of extcon device.
@@ -266,22 +244,14 @@ struct charger_manager {
 	char psy_name_buf[PSY_NAME_MAX + 1];
 	struct power_supply charger_psy;
 
-	bool status_save_ext_pwr_inserted;
-	bool status_save_batt;
-
 	u64 charging_start_time;
 	u64 charging_end_time;
 };
 
 #ifdef CONFIG_CHARGER_MANAGER
-extern int setup_charger_manager(struct charger_global_desc *gd);
-extern bool cm_suspend_again(void);
 extern void cm_notify_event(struct power_supply *psy,
 				enum cm_event_types type, char *msg);
 #else
-static inline int setup_charger_manager(struct charger_global_desc *gd)
-{ return 0; }
-static inline bool cm_suspend_again(void) { return false; }
 static inline void cm_notify_event(struct power_supply *psy,
 				enum cm_event_types type, char *msg) { }
 #endif
-- 
cgit v1.2.3-70-g09d2


From d5db139ab3764640e0882a1746e7b9fdee33fd87 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Thu, 22 Jan 2015 11:13:14 +1030
Subject: module: make module_refcount() a signed integer.

James Bottomley points out that it will be -1 during unload.  It's
only used for diagnostics, so let's not hide that as it could be a
clue as to what's gone wrong.

Cc: Jason Wessel <jason.wessel@windriver.com>
Acked-and-documention-added-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Reviewed-by: Masami Hiramatsu <maasami.hiramatsu.pt@hitachi.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/module.h      |  2 +-
 kernel/debug/kdb/kdb_main.c |  2 +-
 kernel/module.c             | 17 +++++++++++++----
 3 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index ebfb0e153c6..b653d7c0a05 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -444,7 +444,7 @@ extern void __module_put_and_exit(struct module *mod, long code)
 #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code)
 
 #ifdef CONFIG_MODULE_UNLOAD
-unsigned long module_refcount(struct module *mod);
+int module_refcount(struct module *mod);
 void __symbol_put(const char *symbol);
 #define symbol_put(x) __symbol_put(VMLINUX_SYMBOL_STR(x))
 void symbol_put_addr(void *addr);
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 379650b984f..2934889f2cc 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -1979,7 +1979,7 @@ static int kdb_lsmod(int argc, const char **argv)
 		kdb_printf("%-20s%8u  0x%p ", mod->name,
 			   mod->core_size, (void *)mod);
 #ifdef CONFIG_MODULE_UNLOAD
-		kdb_printf("%4ld ", module_refcount(mod));
+		kdb_printf("%4d ", module_refcount(mod));
 #endif
 		if (mod->state == MODULE_STATE_GOING)
 			kdb_printf(" (Unloading)");
diff --git a/kernel/module.c b/kernel/module.c
index ed4ec9c30bd..d856e96a3cc 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -772,9 +772,18 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 	return 0;
 }
 
-unsigned long module_refcount(struct module *mod)
+/**
+ * module_refcount - return the refcount or -1 if unloading
+ *
+ * @mod:	the module we're checking
+ *
+ * Returns:
+ *	-1 if the module is in the process of unloading
+ *	otherwise the number of references in the kernel to the module
+ */
+int module_refcount(struct module *mod)
 {
-	return (unsigned long)atomic_read(&mod->refcnt) - MODULE_REF_BASE;
+	return atomic_read(&mod->refcnt) - MODULE_REF_BASE;
 }
 EXPORT_SYMBOL(module_refcount);
 
@@ -856,7 +865,7 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod)
 	struct module_use *use;
 	int printed_something = 0;
 
-	seq_printf(m, " %lu ", module_refcount(mod));
+	seq_printf(m, " %i ", module_refcount(mod));
 
 	/*
 	 * Always include a trailing , so userspace can differentiate
@@ -908,7 +917,7 @@ EXPORT_SYMBOL_GPL(symbol_put_addr);
 static ssize_t show_refcnt(struct module_attribute *mattr,
 			   struct module_kobject *mk, char *buffer)
 {
-	return sprintf(buffer, "%lu\n", module_refcount(mk->mod));
+	return sprintf(buffer, "%i\n", module_refcount(mk->mod));
 }
 
 static struct module_attribute modinfo_refcnt =
-- 
cgit v1.2.3-70-g09d2


From 8116bf4cb62d337c953cfa5369ef4cf83e73140c Mon Sep 17 00:00:00 2001
From: Jeff Layton <jeff.layton@primarydata.com>
Date: Wed, 21 Jan 2015 20:44:01 -0500
Subject: locks: update comments that refer to inode->i_flock

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
 fs/locks.c         |  2 +-
 include/linux/fs.h | 19 ++++++++++---------
 2 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index 2fc36b3772a..4d0d41163a5 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2212,7 +2212,7 @@ again:
 	 */
 	/*
 	 * we need that spin_lock here - it prevents reordering between
-	 * update of inode->i_flock and check for it done in close().
+	 * update of i_flctx->flc_posix and check for it done in close().
 	 * rcu_read_lock() wouldn't do.
 	 */
 	spin_lock(&current->files->file_lock);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f87cb2f0310..ddd2fa7cefd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -925,12 +925,11 @@ int locks_in_grace(struct net *);
  * FIXME: should we create a separate "struct lock_request" to help distinguish
  * these two uses?
  *
- * The i_flock list is ordered by:
+ * The varous i_flctx lists are ordered by:
  *
- * 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX
- * 2) lock owner
- * 3) lock range start
- * 4) lock range end
+ * 1) lock owner
+ * 2) lock range start
+ * 3) lock range end
  *
  * Obviously, the last two criteria only matter for POSIX locks.
  */
@@ -1992,8 +1991,9 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 {
 	/*
 	 * Since this check is lockless, we must ensure that any refcounts
-	 * taken are done before checking inode->i_flock. Otherwise, we could
-	 * end up racing with tasks trying to set a new lease on this file.
+	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
+	 * could end up racing with tasks trying to set a new lease on this
+	 * file.
 	 */
 	smp_mb();
 	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
@@ -2005,8 +2005,9 @@ static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
 	/*
 	 * Since this check is lockless, we must ensure that any refcounts
-	 * taken are done before checking inode->i_flock. Otherwise, we could
-	 * end up racing with tasks trying to set a new lease on this file.
+	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
+	 * could end up racing with tasks trying to set a new lease on this
+	 * file.
 	 */
 	smp_mb();
 	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
-- 
cgit v1.2.3-70-g09d2


From 30b8b0066cafef274fc92462578ee346211ce7cb Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 15 Jan 2015 21:22:39 +0000
Subject: init: Get rid of x86isms

The UP local API support can be set up from an early initcall. No need
for horrible hackery in the init code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Link: http://lkml.kernel.org/r/20150115211703.827943883@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig            |  4 ++++
 arch/x86/kernel/apic/apic.c |  7 +++++++
 include/linux/smp.h         |  7 +++++++
 init/main.c                 | 13 -------------
 4 files changed, 18 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba397bde794..ffcc3ca5862 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -855,6 +855,10 @@ config SCHED_MC
 
 source "kernel/Kconfig.preempt"
 
+config UP_LATE_INIT
+       def_bool y
+       depends on X86_UP_APIC
+
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors"
 	depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index c681e9ba9e4..19f1bc714ee 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2267,6 +2267,13 @@ int __init APIC_init_uniprocessor(void)
 	return 0;
 }
 
+#ifdef CONFIG_UP_LATE_INIT
+void __init up_late_init(void)
+{
+	APIC_init_uniprocessor();
+}
+#endif
+
 /*
  * Power management
  */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 93dff5fff52..be91db2a701 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -151,6 +151,13 @@ smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
 static inline void kick_all_cpus_sync(void) {  }
 static inline void wake_up_all_idle_cpus(void) {  }
 
+#ifdef CONFIG_UP_LATE_INIT
+extern void __init up_late_init(void);
+static inline void smp_init(void) { up_late_init(); }
+#else
+static inline void smp_init(void) { }
+#endif
+
 #endif /* !SMP */
 
 /*
diff --git a/init/main.c b/init/main.c
index 61b993767db..179ada15d08 100644
--- a/init/main.c
+++ b/init/main.c
@@ -87,10 +87,6 @@
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
 
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/smp.h>
-#endif
-
 static int kernel_init(void *);
 
 extern void init_IRQ(void);
@@ -351,15 +347,6 @@ __setup("rdinit=", rdinit_setup);
 
 #ifndef CONFIG_SMP
 static const unsigned int setup_max_cpus = NR_CPUS;
-#ifdef CONFIG_X86_LOCAL_APIC
-static void __init smp_init(void)
-{
-	APIC_init_uniprocessor();
-}
-#else
-#define smp_init()	do { } while (0)
-#endif
-
 static inline void setup_nr_cpu_ids(void) { }
 static inline void smp_prepare_cpus(unsigned int maxcpus) { }
 #endif
-- 
cgit v1.2.3-70-g09d2


From 1f94a94f67e1083e19fb7b436dd7ca7a4ba03f2b Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Fri, 9 Jan 2015 20:34:39 -0600
Subject: PCI: Add generic config accessors

Many PCI controllers' configuration space accesses are memory-mapped and
vary only in address calculation and access checks.  There are 2 main
access methods: a decoded address space such as ECAM or a single address
and data register similar to x86.  This implementation can support both
cases as well as be used in cases that need additional pre- or post-access
handling.

Add a new pci_ops member, map_bus, which can do access checks and any
necessary setup.  It returns the address to use for the configuration space
access.  The access types supported are 32-bit only accesses or correct
byte, word, or dword sized accesses.

Tested-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
---
 drivers/pci/access.c | 87 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h  | 11 +++++++
 2 files changed, 98 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 49dd766852b..d9b64a17599 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -67,6 +67,93 @@ EXPORT_SYMBOL(pci_bus_write_config_byte);
 EXPORT_SYMBOL(pci_bus_write_config_word);
 EXPORT_SYMBOL(pci_bus_write_config_dword);
 
+int pci_generic_config_read(struct pci_bus *bus, unsigned int devfn,
+			    int where, int size, u32 *val)
+{
+	void __iomem *addr;
+
+	addr = bus->ops->map_bus(bus, devfn, where);
+	if (!addr) {
+		*val = ~0;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	if (size == 1)
+		*val = readb(addr);
+	else if (size == 2)
+		*val = readw(addr);
+	else
+		*val = readl(addr);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+EXPORT_SYMBOL_GPL(pci_generic_config_read);
+
+int pci_generic_config_write(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 val)
+{
+	void __iomem *addr;
+
+	addr = bus->ops->map_bus(bus, devfn, where);
+	if (!addr)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (size == 1)
+		writeb(val, addr);
+	else if (size == 2)
+		writew(val, addr);
+	else
+		writel(val, addr);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+EXPORT_SYMBOL_GPL(pci_generic_config_write);
+
+int pci_generic_config_read32(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 *val)
+{
+	void __iomem *addr;
+
+	addr = bus->ops->map_bus(bus, devfn, where & ~0x3);
+	if (!addr) {
+		*val = ~0;
+		return PCIBIOS_DEVICE_NOT_FOUND;
+	}
+
+	*val = readl(addr);
+
+	if (size <= 2)
+		*val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+EXPORT_SYMBOL_GPL(pci_generic_config_read32);
+
+int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn,
+			       int where, int size, u32 val)
+{
+	void __iomem *addr;
+	u32 mask, tmp;
+
+	addr = bus->ops->map_bus(bus, devfn, where & ~0x3);
+	if (!addr)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (size == 4) {
+		writel(val, addr);
+		return PCIBIOS_SUCCESSFUL;
+	} else {
+		mask = ~(((1 << (size * 8)) - 1) << ((where & 0x3) * 8));
+	}
+
+	tmp = readl(addr) & mask;
+	tmp |= val << ((where & 0x3) * 8);
+	writel(tmp, addr);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+EXPORT_SYMBOL_GPL(pci_generic_config_write32);
+
 /**
  * pci_bus_set_ops - Set raw operations of pci bus
  * @bus:	pci bus struct
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 360a966a97a..e7fd5190018 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -560,6 +560,7 @@ static inline int pcibios_err_to_errno(int err)
 /* Low-level architecture-dependent routines */
 
 struct pci_ops {
+	void __iomem *(*map_bus)(struct pci_bus *bus, unsigned int devfn, int where);
 	int (*read)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val);
 	int (*write)(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val);
 };
@@ -857,6 +858,16 @@ int pci_bus_write_config_word(struct pci_bus *bus, unsigned int devfn,
 			      int where, u16 val);
 int pci_bus_write_config_dword(struct pci_bus *bus, unsigned int devfn,
 			       int where, u32 val);
+
+int pci_generic_config_read(struct pci_bus *bus, unsigned int devfn,
+			    int where, int size, u32 *val);
+int pci_generic_config_write(struct pci_bus *bus, unsigned int devfn,
+			    int where, int size, u32 val);
+int pci_generic_config_read32(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 *val);
+int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn,
+			       int where, int size, u32 val);
+
 struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops);
 
 static inline int pci_read_config_byte(const struct pci_dev *dev, int where, u8 *val)
-- 
cgit v1.2.3-70-g09d2


From fa7e1fbcb52cc9efab394526a566d80fb31529bb Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 22 Jan 2015 18:44:19 +0100
Subject: mac80211: allow drivers to control software crypto

Some drivers unfortunately cannot support software crypto, but
mac80211 currently assumes that they do.

This has the issue that if the hardware enabling fails for some
reason, the software fallback is used, which won't work. This
clearly isn't desirable, the error should be reported and the
key setting refused.

Support this in mac80211 by allowing drivers to set a new HW
flag IEEE80211_HW_SW_CRYPTO_CONTROL, in which case mac80211 will
only allow software fallback if the set_key() method returns 1.
The driver will also need to advertise supported cipher suites
so that mac80211 doesn't advertise any (future) software ciphers
that the driver can't actually do.

While at it, to make it easier to support this, refactor the
ieee80211_init_cipher_suites() code.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 12 ++++++++++
 net/mac80211/key.c     | 10 +++++---
 net/mac80211/main.c    | 65 ++++++++++++++++++++++++++++++--------------------
 3 files changed, 58 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 275ee56152a..33b87c50a4c 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1634,6 +1634,12 @@ struct ieee80211_tx_control {
  *	be created.  It is expected user-space will create vifs as
  *	desired (and thus have them named as desired).
  *
+ * @IEEE80211_HW_SW_CRYPTO_CONTROL: The driver wants to control which of the
+ *	crypto algorithms can be done in software - so don't automatically
+ *	try to fall back to it if hardware crypto fails, but do so only if
+ *	the driver returns 1. This also forces the driver to advertise its
+ *	supported cipher suites.
+ *
  * @IEEE80211_HW_QUEUE_CONTROL: The driver wants to control per-interface
  *	queue mapping in order to use different queues (not just one per AC)
  *	for different virtual interfaces. See the doc section on HW queue
@@ -1681,6 +1687,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_MFP_CAPABLE			= 1<<13,
 	IEEE80211_HW_WANT_MONITOR_VIF			= 1<<14,
 	IEEE80211_HW_NO_AUTO_VIF			= 1<<15,
+	IEEE80211_HW_SW_CRYPTO_CONTROL			= 1<<16,
 	/* free slots */
 	IEEE80211_HW_REPORTS_TX_ACK_STATUS		= 1<<18,
 	IEEE80211_HW_CONNECTION_MONITOR			= 1<<19,
@@ -1955,6 +1962,11 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
  * added; if you return 0 then hw_key_idx must be assigned to the
  * hardware key index, you are free to use the full u8 range.
  *
+ * Note that in the case that the @IEEE80211_HW_SW_CRYPTO_CONTROL flag is
+ * set, mac80211 will not automatically fall back to software crypto if
+ * enabling hardware crypto failed. The set_key() call may also return the
+ * value 1 to permit this specific key/algorithm to be done in software.
+ *
  * When the cmd is %DISABLE_KEY then it must succeed.
  *
  * Note that it is permissible to not decrypt a frame even if a key
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index f8d9f0ee59b..5167c53aa15 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -90,7 +90,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct sta_info *sta;
-	int ret;
+	int ret = -EOPNOTSUPP;
 
 	might_sleep();
 
@@ -150,7 +150,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 		return 0;
 	}
 
-	if (ret != -ENOSPC && ret != -EOPNOTSUPP)
+	if (ret != -ENOSPC && ret != -EOPNOTSUPP && ret != 1)
 		sdata_err(sdata,
 			  "failed to set key (%d, %pM) to hardware (%d)\n",
 			  key->conf.keyidx,
@@ -163,7 +163,11 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_TKIP:
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
-		/* all of these we can do in software */
+		/* all of these we can do in software - if driver can */
+		if (ret == 1)
+			return 0;
+		if (key->local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL)
+			return -EINVAL;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 46264cb6604..ea6b82ac4f0 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -658,7 +658,6 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 	bool have_wep = !(IS_ERR(local->wep_tx_tfm) ||
 			  IS_ERR(local->wep_rx_tfm));
 	bool have_mfp = local->hw.flags & IEEE80211_HW_MFP_CAPABLE;
-	const struct ieee80211_cipher_scheme *cs = local->hw.cipher_schemes;
 	int n_suites = 0, r = 0, w = 0;
 	u32 *suites;
 	static const u32 cipher_suites[] = {
@@ -672,12 +671,38 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		WLAN_CIPHER_SUITE_AES_CMAC
 	};
 
-	/* Driver specifies the ciphers, we have nothing to do... */
-	if (local->hw.wiphy->cipher_suites && have_wep)
-		return 0;
+	if (local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL ||
+	    local->hw.wiphy->cipher_suites) {
+		/* If the driver advertises, or doesn't support SW crypto,
+		 * we only need to remove WEP if necessary.
+		 */
+		if (have_wep)
+			return 0;
+
+		/* well if it has _no_ ciphers ... fine */
+		if (!local->hw.wiphy->n_cipher_suites)
+			return 0;
+
+		/* Driver provides cipher suites, but we need to exclude WEP */
+		suites = kmemdup(local->hw.wiphy->cipher_suites,
+				 sizeof(u32) * local->hw.wiphy->n_cipher_suites,
+				 GFP_KERNEL);
+		if (!suites)
+			return -ENOMEM;
 
-	/* Set up cipher suites if driver relies on mac80211 cipher defs */
-	if (!local->hw.wiphy->cipher_suites && !cs) {
+		for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) {
+			u32 suite = local->hw.wiphy->cipher_suites[r];
+
+			if (suite == WLAN_CIPHER_SUITE_WEP40 ||
+			    suite == WLAN_CIPHER_SUITE_WEP104)
+				continue;
+			suites[w++] = suite;
+		}
+	} else if (!local->hw.cipher_schemes) {
+		/* If the driver doesn't have cipher schemes, there's nothing
+		 * else to do other than assign the (software supported and
+		 * perhaps offloaded) cipher suites.
+		 */
 		local->hw.wiphy->cipher_suites = cipher_suites;
 		local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
 
@@ -689,12 +714,16 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 			local->hw.wiphy->n_cipher_suites -= 2;
 		}
 
+		/* not dynamically allocated, so just return */
 		return 0;
-	}
+	} else {
+		const struct ieee80211_cipher_scheme *cs;
 
-	if (!local->hw.wiphy->cipher_suites) {
-		/*
-		 * Driver specifies cipher schemes only
+		cs = local->hw.cipher_schemes;
+
+		/* Driver specifies cipher schemes only (but not cipher suites
+		 * including the schemes)
+		 *
 		 * We start counting ciphers defined by schemes, TKIP and CCMP
 		 */
 		n_suites = local->hw.n_cipher_schemes + 2;
@@ -724,22 +753,6 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 
 		for (r = 0; r < local->hw.n_cipher_schemes; r++)
 			suites[w++] = cs[r].cipher;
-	} else {
-		/* Driver provides cipher suites, but we need to exclude WEP */
-		suites = kmemdup(local->hw.wiphy->cipher_suites,
-				 sizeof(u32) * local->hw.wiphy->n_cipher_suites,
-				 GFP_KERNEL);
-		if (!suites)
-			return -ENOMEM;
-
-		for (r = 0; r < local->hw.wiphy->n_cipher_suites; r++) {
-			u32 suite = local->hw.wiphy->cipher_suites[r];
-
-			if (suite == WLAN_CIPHER_SUITE_WEP40 ||
-			    suite == WLAN_CIPHER_SUITE_WEP104)
-				continue;
-			suites[w++] = suite;
-		}
 	}
 
 	local->hw.wiphy->cipher_suites = suites;
-- 
cgit v1.2.3-70-g09d2


From 4b681c82d2f9bef121c912ffcaac89a004af3f2c Mon Sep 17 00:00:00 2001
From: Vadim Kochan <vadim4j@gmail.com>
Date: Mon, 12 Jan 2015 16:34:05 +0200
Subject: nl80211: Allow set network namespace by fd

Added new NL80211_ATTR_NETNS_FD which allows to
set namespace via nl80211 by fd.

Signed-off-by: Vadim Kochan <vadim4j@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h |  2 ++
 net/core/net_namespace.c     |  1 +
 net/wireless/nl80211.c       | 16 +++++++++++-----
 3 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f52797a9081..f68532b015d 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2098,6 +2098,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_SURVEY_RADIO_STATS,
 
+	NL80211_ATTR_NETNS_FD,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7f155175bba..5d5ee8f3e4f 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -361,6 +361,7 @@ struct net *get_net_ns_by_fd(int fd)
 	return ERR_PTR(-EINVAL);
 }
 #endif
+EXPORT_SYMBOL_GPL(get_net_ns_by_fd);
 
 struct net *get_net_ns_by_pid(pid_t pid)
 {
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c5661c5ad8f..c64100ec79e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -397,6 +397,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 },
 	[NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN },
 	[NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG },
+	[NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 },
 };
 
 /* policy for the key attributes */
@@ -7762,14 +7763,19 @@ static int nl80211_wiphy_netns(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net *net;
 	int err;
-	u32 pid;
 
-	if (!info->attrs[NL80211_ATTR_PID])
-		return -EINVAL;
+	if (info->attrs[NL80211_ATTR_PID]) {
+		u32 pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]);
+
+		net = get_net_ns_by_pid(pid);
+	} else if (info->attrs[NL80211_ATTR_NETNS_FD]) {
+		u32 fd = nla_get_u32(info->attrs[NL80211_ATTR_NETNS_FD]);
 
-	pid = nla_get_u32(info->attrs[NL80211_ATTR_PID]);
+		net = get_net_ns_by_fd(fd);
+	} else {
+		return -EINVAL;
+	}
 
-	net = get_net_ns_by_pid(pid);
 	if (IS_ERR(net))
 		return PTR_ERR(net);
 
-- 
cgit v1.2.3-70-g09d2


From db82d8a966ded064bd4cf0e1fcca13442f50d0ae Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
Date: Wed, 14 Jan 2015 12:55:08 +0100
Subject: mac80211: enable TPC through mac80211 stack

Control per packet Transmit Power Control (TPC) in lower drivers
according to TX power settings configured by the user. In particular TPC is
enabled if value passed in enum nl80211_tx_power_setting is
NL80211_TX_POWER_LIMITED (allow using less than specified from userspace),
whereas TPC is disabled if nl80211_tx_power_setting is set to
NL80211_TX_POWER_FIXED (use value configured from userspace)

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  7 +++++++
 net/mac80211/cfg.c         | 19 ++++++++++++++++---
 net/mac80211/chan.c        |  4 ++--
 net/mac80211/ieee80211_i.h |  3 ++-
 net/mac80211/iface.c       |  5 +++--
 5 files changed, 30 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 33b87c50a4c..866073e27ea 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -376,6 +376,12 @@ enum ieee80211_rssi_event {
  * @ssid_len: Length of SSID given in @ssid.
  * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode.
  * @txpower: TX power in dBm
+ * @txpower_type: TX power adjustment used to control per packet Transmit
+ *	Power Control (TPC) in lower driver for the current vif. In particular
+ *	TPC is enabled if value passed in %txpower_type is
+ *	NL80211_TX_POWER_LIMITED (allow using less than specified from
+ *	userspace), whereas TPC is disabled if %txpower_type is set to
+ *	NL80211_TX_POWER_FIXED (use value configured from userspace)
  * @p2p_noa_attr: P2P NoA attribute for P2P powersave
  */
 struct ieee80211_bss_conf {
@@ -411,6 +417,7 @@ struct ieee80211_bss_conf {
 	size_t ssid_len;
 	bool hidden_ssid;
 	int txpower;
+	enum nl80211_tx_power_setting txpower_type;
 	struct ieee80211_p2p_noa_attr p2p_noa_attr;
 };
 
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ff090ef1ea2..a777114d663 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2110,6 +2110,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct ieee80211_sub_if_data *sdata;
+	enum nl80211_tx_power_setting txp_type = type;
+	bool update_txp_type = false;
 
 	if (wdev) {
 		sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
@@ -2117,6 +2119,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 		switch (type) {
 		case NL80211_TX_POWER_AUTOMATIC:
 			sdata->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
+			txp_type = NL80211_TX_POWER_LIMITED;
 			break;
 		case NL80211_TX_POWER_LIMITED:
 		case NL80211_TX_POWER_FIXED:
@@ -2126,7 +2129,12 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 			break;
 		}
 
-		ieee80211_recalc_txpower(sdata);
+		if (txp_type != sdata->vif.bss_conf.txpower_type) {
+			update_txp_type = true;
+			sdata->vif.bss_conf.txpower_type = txp_type;
+		}
+
+		ieee80211_recalc_txpower(sdata, update_txp_type);
 
 		return 0;
 	}
@@ -2134,6 +2142,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 	switch (type) {
 	case NL80211_TX_POWER_AUTOMATIC:
 		local->user_power_level = IEEE80211_UNSET_POWER_LEVEL;
+		txp_type = NL80211_TX_POWER_LIMITED;
 		break;
 	case NL80211_TX_POWER_LIMITED:
 	case NL80211_TX_POWER_FIXED:
@@ -2144,10 +2153,14 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
 	}
 
 	mutex_lock(&local->iflist_mtx);
-	list_for_each_entry(sdata, &local->interfaces, list)
+	list_for_each_entry(sdata, &local->interfaces, list) {
 		sdata->user_power_level = local->user_power_level;
+		if (txp_type != sdata->vif.bss_conf.txpower_type)
+			update_txp_type = true;
+		sdata->vif.bss_conf.txpower_type = txp_type;
+	}
 	list_for_each_entry(sdata, &local->interfaces, list)
-		ieee80211_recalc_txpower(sdata);
+		ieee80211_recalc_txpower(sdata, update_txp_type);
 	mutex_unlock(&local->iflist_mtx);
 
 	return 0;
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 35b11e11e0c..ff0d2db09df 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -655,7 +655,7 @@ out:
 	}
 
 	if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) {
-		ieee80211_recalc_txpower(sdata);
+		ieee80211_recalc_txpower(sdata, false);
 		ieee80211_recalc_chanctx_min_def(local, new_ctx);
 	}
 
@@ -1387,7 +1387,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local)
 				ieee80211_bss_info_change_notify(sdata,
 								 changed);
 
-			ieee80211_recalc_txpower(sdata);
+			ieee80211_recalc_txpower(sdata, false);
 		}
 
 		ieee80211_recalc_chanctx_chantype(local, ctx);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 156ea79e015..6e1b184183f 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1621,7 +1621,8 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local);
 void ieee80211_del_virtual_monitor(struct ieee80211_local *local);
 
 bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
-void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
+void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
+			      bool update_bss);
 
 static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
 {
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 677422e11e0..4371c123a95 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -73,9 +73,10 @@ bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
 	return false;
 }
 
-void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata)
+void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
+			      bool update_bss)
 {
-	if (__ieee80211_recalc_txpower(sdata))
+	if (__ieee80211_recalc_txpower(sdata) || update_bss)
 		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 9c74893441d3cf4b258a82b19cbf6bfd2ed6e549 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <luciano.coelho@intel.com>
Date: Fri, 16 Jan 2015 16:04:09 +0200
Subject: nl80211: add an attribute to allow delaying the first scheduled scan
 cycle

The userspace may want to delay the the first scheduled scan or
net-detect cycle.  Add an optional attribute to the scheduled scan
configuration to pass the delay to be (optionally) used by the driver.

Signed-off-by: Luciano Coelho <luciano.coelho@intel.com>
[add the attribute to the policy to validate it]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  5 +++++
 include/uapi/linux/nl80211.h | 20 ++++++++++++++------
 net/wireless/nl80211.c       |  5 +++++
 3 files changed, 24 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 7b44ba0a763..64e09e1e809 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1493,6 +1493,10 @@ struct cfg80211_match_set {
  * @rcu_head: RCU callback used to free the struct
  * @owner_nlportid: netlink portid of owner (if this should is a request
  *	owned by a particular socket)
+ * @delay: delay in seconds to use before starting the first scan
+ *	cycle.  The driver may ignore this parameter and start
+ *	immediately (or at any other time), if this feature is not
+ *	supported.
  */
 struct cfg80211_sched_scan_request {
 	struct cfg80211_ssid *ssids;
@@ -1506,6 +1510,7 @@ struct cfg80211_sched_scan_request {
 	struct cfg80211_match_set *match_sets;
 	int n_match_sets;
 	s32 min_rssi_thold;
+	u32 delay;
 
 	u8 mac_addr[ETH_ALEN] __aligned(2);
 	u8 mac_addr_mask[ETH_ALEN] __aligned(2);
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f68532b015d..1cbc3aae425 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -324,7 +324,9 @@
  *	if passed, define which channels should be scanned; if not
  *	passed, all channels allowed for the current regulatory domain
  *	are used.  Extra IEs can also be passed from the userspace by
- *	using the %NL80211_ATTR_IE attribute.
+ *	using the %NL80211_ATTR_IE attribute.  The first cycle of the
+ *	scheduled scan can be delayed by %NL80211_ATTR_SCHED_SCAN_DELAY
+ *	is supplied.
  * @NL80211_CMD_STOP_SCHED_SCAN: stop a scheduled scan. Returns -ENOENT if
  *	scheduled scan is not running. The caller may assume that as soon
  *	as the call returns, it is safe to start a new scheduled scan again.
@@ -1735,6 +1737,9 @@ enum nl80211_commands {
  *	should be contained in the result as the sum of the respective counters
  *	over all channels.
  *
+ * @NL80211_ATTR_SCHED_SCAN_DELAY: delay before a scheduled scan (or a
+ *	WoWLAN net-detect scan) is started, u32 in seconds.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -2100,6 +2105,8 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_NETNS_FD,
 
+	NL80211_ATTR_SCHED_SCAN_DELAY,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -3743,11 +3750,12 @@ struct nl80211_pattern_support {
  * @NL80211_WOWLAN_TRIG_NET_DETECT: wake up when a configured network
  *	is detected.  This is a nested attribute that contains the
  *	same attributes used with @NL80211_CMD_START_SCHED_SCAN.  It
- *	specifies how the scan is performed (e.g. the interval and the
- *	channels to scan) as well as the scan results that will
- *	trigger a wake (i.e. the matchsets).  This attribute is also
- *	sent in a response to @NL80211_CMD_GET_WIPHY, indicating the
- *	number of match sets supported by the driver (u32).
+ *	specifies how the scan is performed (e.g. the interval, the
+ *	channels to scan and the initial delay) as well as the scan
+ *	results that will trigger a wake (i.e. the matchsets).  This
+ *	attribute is also sent in a response to
+ *	@NL80211_CMD_GET_WIPHY, indicating the number of match sets
+ *	supported by the driver (u32).
  * @NL80211_WOWLAN_TRIG_NET_DETECT_RESULTS: nested attribute
  *	containing an array with information about what triggered the
  *	wake up.  If no elements are present in the array, it means
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c64100ec79e..4542e8683be 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -398,6 +398,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_MAC_MASK] = { .len = ETH_ALEN },
 	[NL80211_ATTR_WIPHY_SELF_MANAGED_REG] = { .type = NLA_FLAG },
 	[NL80211_ATTR_NETNS_FD] = { .type = NLA_U32 },
+	[NL80211_ATTR_SCHED_SCAN_DELAY] = { .type = NLA_U32 },
 };
 
 /* policy for the key attributes */
@@ -6205,6 +6206,10 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 		}
 	}
 
+	if (attrs[NL80211_ATTR_SCHED_SCAN_DELAY])
+		request->delay =
+			nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_DELAY]);
+
 	request->interval = interval;
 	request->scan_start = jiffies;
 
-- 
cgit v1.2.3-70-g09d2


From 41fbf3b39d5eca01527338b4d0ee15ee1ae1023c Mon Sep 17 00:00:00 2001
From: Chunyan Zhang <zhang.chunyan@linaro.org>
Date: Wed, 17 Dec 2014 13:11:35 +0800
Subject: ktime.h: Introduce ktime_ms_delta

This patch adds a reusable time difference function which returns the
difference in millisecond, as often used in some driver code, e.g.
mtd/test, media/rc, etc.

Signed-off-by: Chunyan Zhang <zhang.chunyan@linaro.org>
Acked-by: Arnd Bergmann <arnd@linaro.org>
Cc: zhang.lyra@gmail.com
Cc: davem@davemloft.net
Cc: john.stultz@linaro.org
Cc: dborkman@redhat.com
Link: http://lkml.kernel.org/r/1418793095-18780-1-git-send-email-zhang.chunyan@linaro.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/ktime.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index c9d645ad98f..891ea92a68b 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -186,6 +186,11 @@ static inline s64 ktime_us_delta(const ktime_t later, const ktime_t earlier)
        return ktime_to_us(ktime_sub(later, earlier));
 }
 
+static inline s64 ktime_ms_delta(const ktime_t later, const ktime_t earlier)
+{
+	return ktime_to_ms(ktime_sub(later, earlier));
+}
+
 static inline ktime_t ktime_add_us(const ktime_t kt, const u64 usec)
 {
 	return ktime_add_ns(kt, usec * NSEC_PER_USEC);
-- 
cgit v1.2.3-70-g09d2


From 9bc7491906b4113b4c5ae442157c7dfc4e10cd14 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 20 Jan 2015 21:24:10 +0100
Subject: hrtimer: Prevent stale expiry time in hrtimer_interrupt()

hrtimer_interrupt() has the following subtle issue:

hrtimer_interrupt()
  lock(cpu_base);
  expires_next = KTIME_MAX;

  expire_timers(CLOCK_MONOTONIC);
  expires = get_next_timer(CLOCK_MONOTONIC);
  if (expires < expires_next)
    expires_next = expires;

  expire_timers(CLOCK_REALTIME);
    unlock(cpu_base);
    wakeup()
    hrtimer_start(CLOCK_MONOTONIC, newtimer);
    lock(cpu_base();
  expires = get_next_timer(CLOCK_REALTIME);
  if (expires < expires_next)
    expires_next = expires;

So because we already evaluated the next expiring timer of
CLOCK_MONOTONIC we ignore that the expiry time of newtimer might be
earlier than the overall next expiry time in hrtimer_interrupt().

To solve this, remove the caching of the next expiry value from
hrtimer_interrupt() and reevaluate all active clock bases for the next
expiry value. To avoid another code duplication, create a shared
evaluation function and use it for hrtimer_get_next_event(),
hrtimer_force_reprogram() and hrtimer_interrupt().

There is another subtlety in this mechanism:

While hrtimer_interrupt() is running, we want to avoid to touch the
hardware device because we will reprogram it anyway at the end of
hrtimer_interrupt(). This works nicely for hrtimers which get rearmed
via the HRTIMER_RESTART mechanism, because we drop out when the
callback on that CPU is running. But that fails, if a new timer gets
enqueued like in the example above.

This has another implication: While hrtimer_interrupt() is running we
refuse remote enqueueing of timers - see hrtimer_interrupt() and
hrtimer_check_target().

hrtimer_interrupt() tries to prevent this by setting cpu_base->expires
to KTIME_MAX, but that fails if a new timer gets queued.

Prevent both the hardware access and the remote enqueue
explicitely. We can loosen the restriction on the remote enqueue now
due to reevaluation of the next expiry value, but that needs a
seperate patch.

Folded in a fix from Vignesh Radhakrishnan.

Reported-and-tested-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Based-on-patch-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: vigneshr@codeaurora.org
Cc: john.stultz@linaro.org
Cc: viresh.kumar@linaro.org
Cc: fweisbec@gmail.com
Cc: cl@linux.com
Cc: stuart.w.hayes@gmail.com
Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1501202049190.5526@nanos
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/hrtimer.h |   2 +
 kernel/time/hrtimer.c   | 108 ++++++++++++++++++++++--------------------------
 2 files changed, 52 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index a036d058a24..05f6df1fdf5 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -170,6 +170,7 @@ enum  hrtimer_base_type {
  * @clock_was_set:	Indicates that clock was set from irq context.
  * @expires_next:	absolute time of the next event which was scheduled
  *			via clock_set_next_event()
+ * @in_hrtirq:		hrtimer_interrupt() is currently executing
  * @hres_active:	State of high resolution mode
  * @hang_detected:	The last hrtimer interrupt detected a hang
  * @nr_events:		Total number of hrtimer interrupt events
@@ -185,6 +186,7 @@ struct hrtimer_cpu_base {
 	unsigned int			clock_was_set;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t				expires_next;
+	int				in_hrtirq;
 	int				hres_active;
 	int				hang_detected;
 	unsigned long			nr_events;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 37e50aadd47..b663653a5d5 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -440,6 +440,37 @@ static inline void debug_deactivate(struct hrtimer *timer)
 	trace_hrtimer_cancel(timer);
 }
 
+#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
+ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base)
+{
+	struct hrtimer_clock_base *base = cpu_base->clock_base;
+	ktime_t expires, expires_next = { .tv64 = KTIME_MAX };
+	int i;
+
+	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
+		struct timerqueue_node *next;
+		struct hrtimer *timer;
+
+		next = timerqueue_getnext(&base->active);
+		if (!next)
+			continue;
+
+		timer = container_of(next, struct hrtimer, node);
+		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
+		if (expires.tv64 < expires_next.tv64)
+			expires_next = expires;
+	}
+	/*
+	 * clock_was_set() might have changed base->offset of any of
+	 * the clock bases so the result might be negative. Fix it up
+	 * to prevent a false positive in clockevents_program_event().
+	 */
+	if (expires_next.tv64 < 0)
+		expires_next.tv64 = 0;
+	return expires_next;
+}
+#endif
+
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -488,32 +519,7 @@ static inline int hrtimer_hres_active(void)
 static void
 hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 {
-	int i;
-	struct hrtimer_clock_base *base = cpu_base->clock_base;
-	ktime_t expires, expires_next;
-
-	expires_next.tv64 = KTIME_MAX;
-
-	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
-		struct hrtimer *timer;
-		struct timerqueue_node *next;
-
-		next = timerqueue_getnext(&base->active);
-		if (!next)
-			continue;
-		timer = container_of(next, struct hrtimer, node);
-
-		expires = ktime_sub(hrtimer_get_expires(timer), base->offset);
-		/*
-		 * clock_was_set() has changed base->offset so the
-		 * result might be negative. Fix it up to prevent a
-		 * false positive in clockevents_program_event()
-		 */
-		if (expires.tv64 < 0)
-			expires.tv64 = 0;
-		if (expires.tv64 < expires_next.tv64)
-			expires_next = expires;
-	}
+	ktime_t expires_next = __hrtimer_get_next_event(cpu_base);
 
 	if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64)
 		return;
@@ -586,6 +592,15 @@ static int hrtimer_reprogram(struct hrtimer *timer,
 	if (expires.tv64 >= cpu_base->expires_next.tv64)
 		return 0;
 
+	/*
+	 * When the target cpu of the timer is currently executing
+	 * hrtimer_interrupt(), then we do not touch the clock event
+	 * device. hrtimer_interrupt() will reevaluate all clock bases
+	 * before reprogramming the device.
+	 */
+	if (cpu_base->in_hrtirq)
+		return 0;
+
 	/*
 	 * If a hang was detected in the last timer interrupt then we
 	 * do not schedule a timer which is earlier than the expiry
@@ -1104,29 +1119,14 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining);
 ktime_t hrtimer_get_next_event(void)
 {
 	struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases);
-	struct hrtimer_clock_base *base = cpu_base->clock_base;
-	ktime_t delta, mindelta = { .tv64 = KTIME_MAX };
+	ktime_t mindelta = { .tv64 = KTIME_MAX };
 	unsigned long flags;
-	int i;
 
 	raw_spin_lock_irqsave(&cpu_base->lock, flags);
 
-	if (!hrtimer_hres_active()) {
-		for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) {
-			struct hrtimer *timer;
-			struct timerqueue_node *next;
-
-			next = timerqueue_getnext(&base->active);
-			if (!next)
-				continue;
-
-			timer = container_of(next, struct hrtimer, node);
-			delta.tv64 = hrtimer_get_expires_tv64(timer);
-			delta = ktime_sub(delta, base->get_time());
-			if (delta.tv64 < mindelta.tv64)
-				mindelta.tv64 = delta.tv64;
-		}
-	}
+	if (!hrtimer_hres_active())
+		mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base),
+				     ktime_get());
 
 	raw_spin_unlock_irqrestore(&cpu_base->lock, flags);
 
@@ -1253,7 +1253,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	raw_spin_lock(&cpu_base->lock);
 	entry_time = now = hrtimer_update_base(cpu_base);
 retry:
-	expires_next.tv64 = KTIME_MAX;
+	cpu_base->in_hrtirq = 1;
 	/*
 	 * We set expires_next to KTIME_MAX here with cpu_base->lock
 	 * held to prevent that a timer is enqueued in our queue via
@@ -1291,28 +1291,20 @@ retry:
 			 * are right-of a not yet expired timer, because that
 			 * timer will have to trigger a wakeup anyway.
 			 */
-
-			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
-				ktime_t expires;
-
-				expires = ktime_sub(hrtimer_get_expires(timer),
-						    base->offset);
-				if (expires.tv64 < 0)
-					expires.tv64 = KTIME_MAX;
-				if (expires.tv64 < expires_next.tv64)
-					expires_next = expires;
+			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer))
 				break;
-			}
 
 			__run_hrtimer(timer, &basenow);
 		}
 	}
-
+	/* Reevaluate the clock bases for the next expiry */
+	expires_next = __hrtimer_get_next_event(cpu_base);
 	/*
 	 * Store the new expiry value so the migration code can verify
 	 * against it.
 	 */
 	cpu_base->expires_next = expires_next;
+	cpu_base->in_hrtirq = 0;
 	raw_spin_unlock(&cpu_base->lock);
 
 	/* Reprogramming necessary ? */
-- 
cgit v1.2.3-70-g09d2


From 3c5199143bc4b35f472c5c2534026d74821e2044 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jeff.layton@primarydata.com>
Date: Thu, 22 Jan 2015 08:19:32 -0500
Subject: sunrpc/lockd: fix references to the BKL

The BKL is completely out of the picture in the lockd and sunrpc code
these days. Update the antiquated comments that refer to it.

Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/lockd/svclock.c         | 4 ++--
 include/linux/sunrpc/svc.h | 2 +-
 net/sunrpc/svc.c           | 4 ++--
 net/sunrpc/svc_xprt.c      | 3 +--
 4 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 56598742dde..5581e020644 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -57,8 +57,8 @@ static DEFINE_SPINLOCK(nlm_blocked_lock);
 static const char *nlmdbg_cookie2a(const struct nlm_cookie *cookie)
 {
 	/*
-	 * We can get away with a static buffer because we're only
-	 * called with BKL held.
+	 * We can get away with a static buffer because this is only called
+	 * from lockd, which is single-threaded.
 	 */
 	static char buf[2*NLM_MAXCOOKIELEN+1];
 	unsigned int i, len = sizeof(buf);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 6f22cfeef5e..fae6fb947fc 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -110,7 +110,7 @@ struct svc_serv {
  * We use sv_nrthreads as a reference count.  svc_destroy() drops
  * this refcount, so we need to bump it up around operations that
  * change the number of threads.  Horrible, but there it is.
- * Should be called with the BKL held.
+ * Should be called with the "service mutex" held.
  */
 static inline void svc_get(struct svc_serv *serv)
 {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 91eaef1844c..78974e4d9ad 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -768,8 +768,8 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
 /*
- * Called from a server thread as it's exiting. Caller must hold the BKL or
- * the "service mutex", whichever is appropriate for the service.
+ * Called from a server thread as it's exiting. Caller must hold the "service
+ * mutex" for the service.
  */
 void
 svc_exit_thread(struct svc_rqst *rqstp)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c69358b3cf7..163ac45c363 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -42,7 +42,7 @@ static LIST_HEAD(svc_xprt_class_list);
  *	svc_pool->sp_lock protects most of the fields of that pool.
  *	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
  *	when both need to be taken (rare), svc_serv->sv_lock is first.
- *	BKL protects svc_serv->sv_nrthread.
+ *	The "service mutex" protects svc_serv->sv_nrthread.
  *	svc_sock->sk_lock protects the svc_sock->sk_deferred list
  *             and the ->sk_info_authunix cache.
  *
@@ -67,7 +67,6 @@ static LIST_HEAD(svc_xprt_class_list);
  *		  that no other thread will be using the transport or will
  *		  try to set XPT_DEAD.
  */
-
 int svc_reg_xprt_class(struct svc_xprt_class *xcl)
 {
 	struct svc_xprt_class *cl;
-- 
cgit v1.2.3-70-g09d2


From a1443f5a273713d4bfda360e45aa6e1d14fe7324 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 23 Jan 2015 15:42:46 +0200
Subject: Bluetooth: Convert Set SC to use HCI Request

This patch converts the Set Secure Connection HCI handling to use a HCI
request instead of using a hard-coded callback in hci_event.c. This e.g.
ensures that we don't clear the flags incorrectly if something goes
wrong with the power up process (not related to a mgmt Set SC command).

The code can also be simplified a bit since only one pending Set SC
command is allowed, i.e. mgmt_pending_foreach usage is not needed.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_event.c        |  4 +-
 net/bluetooth/mgmt.c             | 92 +++++++++++++++++++++-------------------
 3 files changed, 50 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 7777124bff5..0f5e59f1e3c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1369,7 +1369,6 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr,
 void mgmt_auth_failed(struct hci_conn *conn, u8 status);
 void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
 void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
-void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status);
 void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 				    u8 status);
 void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a58845e9892..e2b81adc232 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -525,9 +525,7 @@ static void hci_cc_write_sc_support(struct hci_dev *hdev, struct sk_buff *skb)
 			hdev->features[1][0] &= ~LMP_HOST_SC;
 	}
 
-	if (test_bit(HCI_MGMT, &hdev->dev_flags))
-		mgmt_sc_enable_complete(hdev, sent->support, status);
-	else if (!status) {
+	if (!test_bit(HCI_MGMT, &hdev->dev_flags) && !status) {
 		if (sent->support)
 			set_bit(HCI_SC_ENABLED, &hdev->dev_flags);
 		else
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 862a005d9db..25e40e82b9a 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4741,11 +4741,57 @@ unlock:
 	return err;
 }
 
+static void sc_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
+{
+	struct pending_cmd *cmd;
+	struct mgmt_mode *cp;
+
+	BT_DBG("%s status %u", hdev->name, status);
+
+	hci_dev_lock(hdev);
+
+	cmd = mgmt_pending_find(MGMT_OP_SET_SECURE_CONN, hdev);
+	if (!cmd)
+		goto unlock;
+
+	if (status) {
+		cmd_status(cmd->sk, cmd->index, cmd->opcode,
+			   mgmt_status(status));
+		goto remove;
+	}
+
+	cp = cmd->param;
+
+	switch (cp->val) {
+	case 0x00:
+		clear_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+		clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+		break;
+	case 0x01:
+		set_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+		clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
+		break;
+	case 0x02:
+		set_bit(HCI_SC_ENABLED, &hdev->dev_flags);
+		set_bit(HCI_SC_ONLY, &hdev->dev_flags);
+		break;
+	}
+
+	send_settings_rsp(cmd->sk, MGMT_OP_SET_SECURE_CONN, hdev);
+	new_settings(hdev, cmd->sk);
+
+remove:
+	mgmt_pending_remove(cmd);
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static int set_secure_conn(struct sock *sk, struct hci_dev *hdev,
 			   void *data, u16 len)
 {
 	struct mgmt_mode *cp = data;
 	struct pending_cmd *cmd;
+	struct hci_request req;
 	u8 val;
 	int err;
 
@@ -4814,17 +4860,14 @@ static int set_secure_conn(struct sock *sk, struct hci_dev *hdev,
 		goto failed;
 	}
 
-	err = hci_send_cmd(hdev, HCI_OP_WRITE_SC_SUPPORT, 1, &val);
+	hci_req_init(&req, hdev);
+	hci_req_add(&req, HCI_OP_WRITE_SC_SUPPORT, 1, &val);
+	err = hci_req_run(&req, sc_enable_complete);
 	if (err < 0) {
 		mgmt_pending_remove(cmd);
 		goto failed;
 	}
 
-	if (cp->val == 0x02)
-		set_bit(HCI_SC_ONLY, &hdev->dev_flags);
-	else
-		clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
-
 failed:
 	hci_dev_unlock(hdev);
 	return err;
@@ -7001,43 +7044,6 @@ void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
 	hci_req_run(&req, NULL);
 }
 
-void mgmt_sc_enable_complete(struct hci_dev *hdev, u8 enable, u8 status)
-{
-	struct cmd_lookup match = { NULL, hdev };
-	bool changed = false;
-
-	if (status) {
-		u8 mgmt_err = mgmt_status(status);
-
-		if (enable) {
-			if (test_and_clear_bit(HCI_SC_ENABLED,
-					       &hdev->dev_flags))
-				new_settings(hdev, NULL);
-			clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
-		}
-
-		mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev,
-				     cmd_status_rsp, &mgmt_err);
-		return;
-	}
-
-	if (enable) {
-		changed = !test_and_set_bit(HCI_SC_ENABLED, &hdev->dev_flags);
-	} else {
-		changed = test_and_clear_bit(HCI_SC_ENABLED, &hdev->dev_flags);
-		clear_bit(HCI_SC_ONLY, &hdev->dev_flags);
-	}
-
-	mgmt_pending_foreach(MGMT_OP_SET_SECURE_CONN, hdev,
-			     settings_rsp, &match);
-
-	if (changed)
-		new_settings(hdev, match.sk);
-
-	if (match.sk)
-		sock_put(match.sk);
-}
-
 static void sk_lookup(struct pending_cmd *cmd, void *data)
 {
 	struct cmd_lookup *match = data;
-- 
cgit v1.2.3-70-g09d2


From c5ed1df781cb544d4e4d189bb5b6ec7336d8888c Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Mon, 19 Jan 2015 08:30:30 +0100
Subject: bcma: use standard bus scanning during early register
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Starting with kernel 3.19-rc1 early registration of bcma on MIPS is done
a bit later, with memory allocator available. This allows us to simplify
code by using standard bus scanning method.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/bcma/bcma_private.h   |  7 +----
 drivers/bcma/host_soc.c       |  2 +-
 drivers/bcma/main.c           | 33 +++++++----------------
 drivers/bcma/scan.c           | 62 +++----------------------------------------
 include/linux/bcma/bcma_soc.h |  2 --
 5 files changed, 15 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index 59422b5fa46..3f314c98d08 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -28,9 +28,7 @@ void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core);
 void bcma_init_bus(struct bcma_bus *bus);
 int bcma_bus_register(struct bcma_bus *bus);
 void bcma_bus_unregister(struct bcma_bus *bus);
-int __init bcma_bus_early_register(struct bcma_bus *bus,
-				   struct bcma_device *core_cc,
-				   struct bcma_device *core_mips);
+int __init bcma_bus_early_register(struct bcma_bus *bus);
 #ifdef CONFIG_PM
 int bcma_bus_suspend(struct bcma_bus *bus);
 int bcma_bus_resume(struct bcma_bus *bus);
@@ -39,9 +37,6 @@ int bcma_bus_resume(struct bcma_bus *bus);
 /* scan.c */
 void bcma_detect_chip(struct bcma_bus *bus);
 int bcma_bus_scan(struct bcma_bus *bus);
-int __init bcma_bus_scan_early(struct bcma_bus *bus,
-			       struct bcma_device_id *match,
-			       struct bcma_device *core);
 
 /* sprom.c */
 int bcma_sprom_get(struct bcma_bus *bus);
diff --git a/drivers/bcma/host_soc.c b/drivers/bcma/host_soc.c
index 335cbcfd945..2dce3478932 100644
--- a/drivers/bcma/host_soc.c
+++ b/drivers/bcma/host_soc.c
@@ -193,7 +193,7 @@ int __init bcma_host_soc_init(struct bcma_soc *soc)
 	int err;
 
 	/* Scan bus and initialize it */
-	err = bcma_bus_early_register(bus, &soc->core_cc, &soc->core_mips);
+	err = bcma_bus_early_register(bus);
 	if (err)
 		iounmap(bus->mmio);
 
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index c166d444fef..c3c5e0a2d5b 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -489,35 +489,20 @@ void bcma_bus_unregister(struct bcma_bus *bus)
 	kfree(cores[0]);
 }
 
-int __init bcma_bus_early_register(struct bcma_bus *bus,
-				   struct bcma_device *core_cc,
-				   struct bcma_device *core_mips)
+/*
+ * This is a special version of bus registration function designed for SoCs.
+ * It scans bus and performs basic initialization of main cores only.
+ * Please note it requires memory allocation, however it won't try to sleep.
+ */
+int __init bcma_bus_early_register(struct bcma_bus *bus)
 {
 	int err;
 	struct bcma_device *core;
-	struct bcma_device_id match;
-
-	match.manuf = BCMA_MANUF_BCM;
-	match.id = bcma_cc_core_id(bus);
-	match.class = BCMA_CL_SIM;
-	match.rev = BCMA_ANY_REV;
-
-	/* Scan for chip common core */
-	err = bcma_bus_scan_early(bus, &match, core_cc);
-	if (err) {
-		bcma_err(bus, "Failed to scan for common core: %d\n", err);
-		return -1;
-	}
-
-	match.manuf = BCMA_MANUF_MIPS;
-	match.id = BCMA_CORE_MIPS_74K;
-	match.class = BCMA_CL_SIM;
-	match.rev = BCMA_ANY_REV;
 
-	/* Scan for mips core */
-	err = bcma_bus_scan_early(bus, &match, core_mips);
+	/* Scan for devices (cores) */
+	err = bcma_bus_scan(bus);
 	if (err) {
-		bcma_err(bus, "Failed to scan for mips core: %d\n", err);
+		bcma_err(bus, "Failed to scan bus: %d\n", err);
 		return -1;
 	}
 
diff --git a/drivers/bcma/scan.c b/drivers/bcma/scan.c
index 5328ee5b4df..df806b9c549 100644
--- a/drivers/bcma/scan.c
+++ b/drivers/bcma/scan.c
@@ -461,6 +461,10 @@ int bcma_bus_scan(struct bcma_bus *bus)
 
 	int err, core_num = 0;
 
+	/* Skip if bus was already scanned (e.g. during early register) */
+	if (bus->nr_cores)
+		return 0;
+
 	erombase = bcma_scan_read32(bus, 0, BCMA_CC_EROM);
 	if (bus->hosttype == BCMA_HOSTTYPE_SOC) {
 		eromptr = ioremap_nocache(erombase, BCMA_CORE_SIZE);
@@ -519,61 +523,3 @@ out:
 
 	return err;
 }
-
-int __init bcma_bus_scan_early(struct bcma_bus *bus,
-			       struct bcma_device_id *match,
-			       struct bcma_device *core)
-{
-	u32 erombase;
-	u32 __iomem *eromptr, *eromend;
-
-	int err = -ENODEV;
-	int core_num = 0;
-
-	erombase = bcma_scan_read32(bus, 0, BCMA_CC_EROM);
-	if (bus->hosttype == BCMA_HOSTTYPE_SOC) {
-		eromptr = ioremap_nocache(erombase, BCMA_CORE_SIZE);
-		if (!eromptr)
-			return -ENOMEM;
-	} else {
-		eromptr = bus->mmio;
-	}
-
-	eromend = eromptr + BCMA_CORE_SIZE / sizeof(u32);
-
-	bcma_scan_switch_core(bus, erombase);
-
-	while (eromptr < eromend) {
-		memset(core, 0, sizeof(*core));
-		INIT_LIST_HEAD(&core->list);
-		core->bus = bus;
-
-		err = bcma_get_next_core(bus, &eromptr, match, core_num, core);
-		if (err == -ENODEV) {
-			core_num++;
-			continue;
-		} else if (err == -ENXIO)
-			continue;
-		else if (err == -ESPIPE)
-			break;
-		else if (err < 0)
-			goto out;
-
-		core->core_index = core_num++;
-		bus->nr_cores++;
-		bcma_info(bus, "Core %d found: %s (manuf 0x%03X, id 0x%03X, rev 0x%02X, class 0x%X)\n",
-			  core->core_index, bcma_device_name(&core->id),
-			  core->id.manuf, core->id.id, core->id.rev,
-			  core->id.class);
-
-		list_add_tail(&core->list, &bus->cores);
-		err = 0;
-		break;
-	}
-
-out:
-	if (bus->hosttype == BCMA_HOSTTYPE_SOC)
-		iounmap(eromptr);
-
-	return err;
-}
diff --git a/include/linux/bcma/bcma_soc.h b/include/linux/bcma/bcma_soc.h
index f24d245f839..1b5fc0c3b1b 100644
--- a/include/linux/bcma/bcma_soc.h
+++ b/include/linux/bcma/bcma_soc.h
@@ -5,8 +5,6 @@
 
 struct bcma_soc {
 	struct bcma_bus bus;
-	struct bcma_device core_cc;
-	struct bcma_device core_mips;
 };
 
 int __init bcma_host_soc_register(struct bcma_soc *soc);
-- 
cgit v1.2.3-70-g09d2


From a9aaf2915ee265735c28b764551d084e61a694e0 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 13 Jan 2015 11:34:00 +0530
Subject: cpufreq: stats: get rid of per-cpu cpufreq_stats_table

All CPUs sharing a cpufreq policy share stats too. For this reason,
add a stats pointer to struct cpufreq_policy and drop per-CPU variable
cpufreq_stats_table used for accessing cpufreq stats so as to reduce
code complexity.

Reviewed-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq_stats.c | 62 +++++++++++++++++++----------------------
 include/linux/cpufreq.h         |  3 ++
 2 files changed, 32 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 6c234f54860..3792b2e2f4a 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -31,8 +31,6 @@ struct cpufreq_stats {
 #endif
 };
 
-static DEFINE_PER_CPU(struct cpufreq_stats *, cpufreq_stats_table);
-
 static int cpufreq_stats_update(struct cpufreq_stats *stat)
 {
 	unsigned long long cur_time = get_jiffies_64();
@@ -48,20 +46,15 @@ static int cpufreq_stats_update(struct cpufreq_stats *stat)
 
 static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf)
 {
-	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu);
-	if (!stat)
-		return 0;
-	return sprintf(buf, "%d\n",
-			per_cpu(cpufreq_stats_table, stat->cpu)->total_trans);
+	return sprintf(buf, "%d\n", policy->stats->total_trans);
 }
 
 static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 {
+	struct cpufreq_stats *stat = policy->stats;
 	ssize_t len = 0;
 	int i;
-	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu);
-	if (!stat)
-		return 0;
+
 	cpufreq_stats_update(stat);
 	for (i = 0; i < stat->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stat->freq_table[i],
@@ -74,12 +67,10 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 {
+	struct cpufreq_stats *stat = policy->stats;
 	ssize_t len = 0;
 	int i, j;
 
-	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu);
-	if (!stat)
-		return 0;
 	cpufreq_stats_update(stat);
 	len += snprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
 	len += snprintf(buf + len, PAGE_SIZE - len, "         : ");
@@ -145,8 +136,9 @@ static int freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq)
 
 static void __cpufreq_stats_free_table(struct cpufreq_policy *policy)
 {
-	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, policy->cpu);
+	struct cpufreq_stats *stat = policy->stats;
 
+	/* Already freed */
 	if (!stat)
 		return;
 
@@ -155,7 +147,7 @@ static void __cpufreq_stats_free_table(struct cpufreq_policy *policy)
 	sysfs_remove_group(&policy->kobj, &stats_attr_group);
 	kfree(stat->time_in_state);
 	kfree(stat);
-	per_cpu(cpufreq_stats_table, policy->cpu) = NULL;
+	policy->stats = NULL;
 }
 
 static void cpufreq_stats_free_table(unsigned int cpu)
@@ -184,7 +176,7 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 		return 0;
 
 	/* stats already initialized */
-	if (per_cpu(cpufreq_stats_table, cpu))
+	if (policy->stats)
 		return -EEXIST;
 
 	stat = kzalloc(sizeof(*stat), GFP_KERNEL);
@@ -196,7 +188,7 @@ static int __cpufreq_stats_create_table(struct cpufreq_policy *policy)
 		goto error_out;
 
 	stat->cpu = cpu;
-	per_cpu(cpufreq_stats_table, cpu) = stat;
+	policy->stats = stat;
 
 	cpufreq_for_each_valid_entry(pos, table)
 		count++;
@@ -231,7 +223,7 @@ error_alloc:
 	sysfs_remove_group(&policy->kobj, &stats_attr_group);
 error_out:
 	kfree(stat);
-	per_cpu(cpufreq_stats_table, cpu) = NULL;
+	policy->stats = NULL;
 	return ret;
 }
 
@@ -254,15 +246,7 @@ static void cpufreq_stats_create_table(unsigned int cpu)
 
 static void cpufreq_stats_update_policy_cpu(struct cpufreq_policy *policy)
 {
-	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table,
-			policy->last_cpu);
-
-	pr_debug("Updating stats_table for new_cpu %u from last_cpu %u\n",
-			policy->cpu, policy->last_cpu);
-	per_cpu(cpufreq_stats_table, policy->cpu) = per_cpu(cpufreq_stats_table,
-			policy->last_cpu);
-	per_cpu(cpufreq_stats_table, policy->last_cpu) = NULL;
-	stat->cpu = policy->cpu;
+	policy->stats->cpu = policy->cpu;
 }
 
 static int cpufreq_stat_notifier_policy(struct notifier_block *nb,
@@ -288,27 +272,36 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb,
 		unsigned long val, void *data)
 {
 	struct cpufreq_freqs *freq = data;
+	struct cpufreq_policy *policy = cpufreq_cpu_get(freq->cpu);
 	struct cpufreq_stats *stat;
 	int old_index, new_index;
 
-	if (val != CPUFREQ_POSTCHANGE)
+	if (!policy) {
+		pr_err("%s: No policy found\n", __func__);
 		return 0;
+	}
 
-	stat = per_cpu(cpufreq_stats_table, freq->cpu);
-	if (!stat)
-		return 0;
+	if (val != CPUFREQ_POSTCHANGE)
+		goto put_policy;
+
+	if (!policy->stats) {
+		pr_debug("%s: No stats found\n", __func__);
+		goto put_policy;
+	}
+
+	stat = policy->stats;
 
 	old_index = stat->last_index;
 	new_index = freq_table_get_index(stat, freq->new);
 
 	/* We can't do stat->time_in_state[-1]= .. */
 	if (old_index == -1 || new_index == -1)
-		return 0;
+		goto put_policy;
 
 	cpufreq_stats_update(stat);
 
 	if (old_index == new_index)
-		return 0;
+		goto put_policy;
 
 	spin_lock(&cpufreq_stats_lock);
 	stat->last_index = new_index;
@@ -317,6 +310,9 @@ static int cpufreq_stat_notifier_trans(struct notifier_block *nb,
 #endif
 	stat->total_trans++;
 	spin_unlock(&cpufreq_stats_lock);
+
+put_policy:
+	cpufreq_cpu_put(policy);
 	return 0;
 }
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 4d078cebafd..60b7b496565 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -113,6 +113,9 @@ struct cpufreq_policy {
 	wait_queue_head_t	transition_wait;
 	struct task_struct	*transition_task; /* Task which is doing the transition */
 
+	/* cpufreq-stats */
+	struct cpufreq_stats	*stats;
+
 	/* For cpufreq driver's internal use */
 	void			*driver_data;
 };
-- 
cgit v1.2.3-70-g09d2


From 7c418ff099110d987846c8c670479a3b90ed1dcb Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 6 Jan 2015 21:09:08 +0530
Subject: cpufreq: Remove (now) unused 'last_cpu' from struct cpufreq_policy

'last_cpu' was used only from cpufreq-stats and isn't used anymore. Get rid of
it.

Reviewed-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 3 ---
 include/linux/cpufreq.h   | 2 --
 2 files changed, 5 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 70b568a253e..60ef37d569c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1086,10 +1086,7 @@ static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu,
 	}
 
 	down_write(&policy->rwsem);
-
-	policy->last_cpu = policy->cpu;
 	policy->cpu = cpu;
-
 	up_write(&policy->rwsem);
 
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 60b7b496565..7e1a389b4e9 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -66,8 +66,6 @@ struct cpufreq_policy {
 	unsigned int		shared_type; /* ACPI: ANY or ALL affected CPUs
 						should set cpufreq */
 	unsigned int		cpu;    /* cpu nr of CPU managing this policy */
-	unsigned int		last_cpu; /* cpu nr of previous CPU that managed
-					   * this policy */
 	struct clk		*clk;
 	struct cpufreq_cpuinfo	cpuinfo;/* see above */
 
-- 
cgit v1.2.3-70-g09d2


From d9f354460db8b58a8395936d323b4ca6e8428b9d Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 6 Jan 2015 21:09:10 +0530
Subject: cpufreq: remove CPUFREQ_UPDATE_POLICY_CPU notifications

CPUFREQ_UPDATE_POLICY_CPU notifications were used only from cpufreq-stats which
doesn't use it anymore. Remove them.

This also decrements values of other notification macros defined after
CPUFREQ_UPDATE_POLICY_CPU by 1 to remove gaps. Hopefully all users are using
macro's instead of direct numbers and so they wouldn't break as macro values are
changed now.

Reviewed-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 3 ---
 include/linux/cpufreq.h   | 5 ++---
 2 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 60ef37d569c..ca69f42b8e1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1089,9 +1089,6 @@ static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu,
 	policy->cpu = cpu;
 	up_write(&policy->rwsem);
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_UPDATE_POLICY_CPU, policy);
-
 	return 0;
 }
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 7e1a389b4e9..2ee4888c1f4 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -368,9 +368,8 @@ static inline void cpufreq_resume(void) {}
 #define CPUFREQ_INCOMPATIBLE		(1)
 #define CPUFREQ_NOTIFY			(2)
 #define CPUFREQ_START			(3)
-#define CPUFREQ_UPDATE_POLICY_CPU	(4)
-#define CPUFREQ_CREATE_POLICY		(5)
-#define CPUFREQ_REMOVE_POLICY		(6)
+#define CPUFREQ_CREATE_POLICY		(4)
+#define CPUFREQ_REMOVE_POLICY		(5)
 
 #ifdef CONFIG_CPU_FREQ
 int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
-- 
cgit v1.2.3-70-g09d2


From 382548a62ade2c003c77a1055b6eb2a47ce30084 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 20 Jan 2015 11:33:09 +0100
Subject: PM / Domains: Remove pm_genpd_dev_need_restore() API

There are currently no users of this API, let's remove it.

Additionally, if such feature would be needed future wise, a better
option is likely use pm_runtime_set_active|suspended() in some form.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 20 --------------------
 include/linux/pm_domain.h   |  2 --
 2 files changed, 22 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 0d8780c04a5..c5280f2b798 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1558,26 +1558,6 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	return ret;
 }
 
-/**
- * pm_genpd_dev_need_restore - Set/unset the device's "need restore" flag.
- * @dev: Device to set/unset the flag for.
- * @val: The new value of the device's "need restore" flag.
- */
-void pm_genpd_dev_need_restore(struct device *dev, bool val)
-{
-	struct pm_subsys_data *psd;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->power.lock, flags);
-
-	psd = dev_to_psd(dev);
-	if (psd && psd->domain_data)
-		to_gpd_data(psd->domain_data)->need_restore = val ? 1 : 0;
-
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-}
-EXPORT_SYMBOL_GPL(pm_genpd_dev_need_restore);
-
 /**
  * pm_genpd_add_subdomain - Add a subdomain to an I/O PM domain.
  * @genpd: Master PM domain to add the subdomain to.
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index a9edab2c787..ed607760fc2 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -140,7 +140,6 @@ extern int __pm_genpd_name_add_device(const char *domain_name,
 
 extern int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 				  struct device *dev);
-extern void pm_genpd_dev_need_restore(struct device *dev, bool val);
 extern int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 				  struct generic_pm_domain *new_subdomain);
 extern int pm_genpd_add_subdomain_names(const char *master_name,
@@ -187,7 +186,6 @@ static inline int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 {
 	return -ENOSYS;
 }
-static inline void pm_genpd_dev_need_restore(struct device *dev, bool val) {}
 static inline int pm_genpd_add_subdomain(struct generic_pm_domain *genpd,
 					 struct generic_pm_domain *new_sd)
 {
-- 
cgit v1.2.3-70-g09d2


From 8b618628b2bf83512fc8df5e8672619d65adfdfb Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Wed, 3 Dec 2014 14:43:06 -0500
Subject: ktime: Optimize ktime_divns for constant divisors

At least on ARM, do_div() is optimized to turn constant divisors into
an inline multiplication by the reciprocal value at compile time.
However this optimization is missed entirely whenever ktime_divns() is
used and the slow out-of-line division code is used all the time.

Let ktime_divns() use do_div() inline whenever the divisor is constant
and small enough.  This will make things like ktime_to_us() and
ktime_to_ms() much faster.

Cc: Arnd Bergmann <arnd.bergmann@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Nicolas Pitre <nico@linaro.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/ktime.h | 12 +++++++++++-
 kernel/time/hrtimer.c |  4 ++--
 2 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index c9d645ad98f..411dd8bfe53 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -166,7 +166,17 @@ static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2)
 }
 
 #if BITS_PER_LONG < 64
-extern u64 ktime_divns(const ktime_t kt, s64 div);
+extern u64 __ktime_divns(const ktime_t kt, s64 div);
+static inline u64 ktime_divns(const ktime_t kt, s64 div)
+{
+	if (__builtin_constant_p(div) && !(div >> 32)) {
+		u64 ns = kt.tv64;
+		do_div(ns, div);
+		return ns;
+	} else {
+		return __ktime_divns(kt, div);
+	}
+}
 #else /* BITS_PER_LONG < 64 */
 # define ktime_divns(kt, div)		(u64)((kt).tv64 / (div))
 #endif
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 37e50aadd47..890535c41c2 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -266,7 +266,7 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags)
 /*
  * Divide a ktime value by a nanosecond value
  */
-u64 ktime_divns(const ktime_t kt, s64 div)
+u64 __ktime_divns(const ktime_t kt, s64 div)
 {
 	u64 dclc;
 	int sft = 0;
@@ -282,7 +282,7 @@ u64 ktime_divns(const ktime_t kt, s64 div)
 
 	return dclc;
 }
-EXPORT_SYMBOL_GPL(ktime_divns);
+EXPORT_SYMBOL_GPL(__ktime_divns);
 #endif /* BITS_PER_LONG >= 64 */
 
 /*
-- 
cgit v1.2.3-70-g09d2


From d08c0cdd26d48751c15aa2b4479a410594fee9ac Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 8 Dec 2014 12:00:09 -0800
Subject: time: Expose getboottime64 for in-kernel uses

Adds a timespec64 based getboottime64() implementation
that can be used as we convert internal users of
getboottime away from using timespecs.

Cc: pang.xunlei <pang.xunlei@linaro.org>
Cc: Arnd Bergmann <arnd.bergmann@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h | 16 ++++++++++++++--
 kernel/time/timekeeping.c   | 12 ++++++------
 2 files changed, 20 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 9b63d13ba82..91480137aa3 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -33,6 +33,7 @@ extern time64_t ktime_get_real_seconds(void);
 
 extern int __getnstimeofday64(struct timespec64 *tv);
 extern void getnstimeofday64(struct timespec64 *tv);
+extern void getboottime64(struct timespec64 *ts);
 
 #if BITS_PER_LONG == 64
 /**
@@ -72,6 +73,11 @@ static inline struct timespec get_monotonic_coarse(void)
 {
 	return get_monotonic_coarse64();
 }
+
+static inline void getboottime(struct timespec *ts)
+{
+	return getboottime64(ts);
+}
 #else
 /**
  * Deprecated. Use do_settimeofday64().
@@ -129,9 +135,15 @@ static inline struct timespec get_monotonic_coarse(void)
 {
 	return timespec64_to_timespec(get_monotonic_coarse64());
 }
-#endif
 
-extern void getboottime(struct timespec *ts);
+static inline void getboottime(struct timespec *ts)
+{
+	struct timespec64 ts64;
+
+	getboottime64(&ts64);
+	*ts = timespec64_to_timespec(ts64);
+}
+#endif
 
 #define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
 #define ktime_get_real_ts64(ts)	getnstimeofday64(ts)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6a931852082..b124af25980 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1659,24 +1659,24 @@ out:
 }
 
 /**
- * getboottime - Return the real time of system boot.
- * @ts:		pointer to the timespec to be set
+ * getboottime64 - Return the real time of system boot.
+ * @ts:		pointer to the timespec64 to be set
  *
- * Returns the wall-time of boot in a timespec.
+ * Returns the wall-time of boot in a timespec64.
  *
  * This is based on the wall_to_monotonic offset and the total suspend
  * time. Calls to settimeofday will affect the value returned (which
  * basically means that however wrong your real time clock is at boot time,
  * you get the right time here).
  */
-void getboottime(struct timespec *ts)
+void getboottime64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot);
 
-	*ts = ktime_to_timespec(t);
+	*ts = ktime_to_timespec64(t);
 }
-EXPORT_SYMBOL_GPL(getboottime);
+EXPORT_SYMBOL_GPL(getboottime64);
 
 unsigned long get_seconds(void)
 {
-- 
cgit v1.2.3-70-g09d2


From 2e0c78ee5ba4d777ecf22c8f40cc968b4308ca88 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 18 Dec 2014 18:04:34 -0800
Subject: time: Expose get_monotonic_boottime64 for in-kernel use

As part of the 2038 conversion process, add a
get_monotonic_boottime64 accessor so we can depracate
get_monotonic_boottime.

Cc: pang.xunlei <pang.xunlei@linaro.org>
Cc: Arnd Bergmann <arnd.bergmann@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 91480137aa3..3eaae475427 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -229,6 +229,11 @@ static inline void get_monotonic_boottime(struct timespec *ts)
 	*ts = ktime_to_timespec(ktime_get_boottime());
 }
 
+static inline void get_monotonic_boottime64(struct timespec64 *ts)
+{
+	*ts = ktime_to_timespec64(ktime_get_boottime());
+}
+
 static inline void timekeeping_clocktai(struct timespec *ts)
 {
 	*ts = ktime_to_timespec(ktime_get_clocktai());
-- 
cgit v1.2.3-70-g09d2


From 9a4a445e30f0b601ca2d9433274047cbf48ebf9e Mon Sep 17 00:00:00 2001
From: Xunlei Pang <pang.xunlei@linaro.org>
Date: Thu, 22 Jan 2015 02:31:55 +0000
Subject: rtc: Convert rtc_set_ntp_time() to use timespec64

rtc_set_ntp_time() uses timespec which is y2038-unsafe,
so modify to use timespec64 which is y2038-safe, then
replace rtc_time_to_tm() with rtc_time64_to_tm().

Also adjust all its call sites(only NTP uses it) accordingly.

Cc: pang.xunlei <pang.xunlei@linaro.org>
Cc: Arnd Bergmann <arnd.bergmann@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 drivers/rtc/systohc.c | 6 +++---
 include/linux/rtc.h   | 2 +-
 kernel/time/ntp.c     | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/rtc/systohc.c b/drivers/rtc/systohc.c
index bf3e242ccc5..eb71872d036 100644
--- a/drivers/rtc/systohc.c
+++ b/drivers/rtc/systohc.c
@@ -20,16 +20,16 @@
  *
  * If temporary failure is indicated the caller should try again 'soon'
  */
-int rtc_set_ntp_time(struct timespec now)
+int rtc_set_ntp_time(struct timespec64 now)
 {
 	struct rtc_device *rtc;
 	struct rtc_time tm;
 	int err = -ENODEV;
 
 	if (now.tv_nsec < (NSEC_PER_SEC >> 1))
-		rtc_time_to_tm(now.tv_sec, &tm);
+		rtc_time64_to_tm(now.tv_sec, &tm);
 	else
-		rtc_time_to_tm(now.tv_sec + 1, &tm);
+		rtc_time64_to_tm(now.tv_sec + 1, &tm);
 
 	rtc = rtc_class_open(CONFIG_RTC_HCTOSYS_DEVICE);
 	if (rtc) {
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 6d6be09a2fe..dcad7ee0d74 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -161,7 +161,7 @@ extern void devm_rtc_device_unregister(struct device *dev,
 extern int rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm);
 extern int rtc_set_mmss(struct rtc_device *rtc, unsigned long secs);
-extern int rtc_set_ntp_time(struct timespec now);
+extern int rtc_set_ntp_time(struct timespec64 now);
 int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm);
 extern int rtc_read_alarm(struct rtc_device *rtc,
 			struct rtc_wkalrm *alrm);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 87a346fd6d6..183dfe2191c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -488,13 +488,13 @@ static void sync_cmos_clock(struct work_struct *work)
 
 	getnstimeofday64(&now);
 	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec * 5) {
-		struct timespec adjust = timespec64_to_timespec(now);
+		struct timespec64 adjust = now;
 
 		fail = -ENODEV;
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
 #ifdef CONFIG_GENERIC_CMOS_UPDATE
-		fail = update_persistent_clock(adjust);
+		fail = update_persistent_clock(timespec64_to_timespec(adjust));
 #endif
 #ifdef CONFIG_RTC_SYSTOHC
 		if (fail == -ENODEV)
-- 
cgit v1.2.3-70-g09d2


From 193523bf937309d57c6dd7839bcf34d7a029dbee Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Tue, 20 Jan 2015 15:15:47 +0100
Subject: vxlan: advertise netns of vxlan dev in fdb msg

Netlink FDB messages are sent in the link netns. The header of these messages
contains the ifindex (ndm_ifindex) of the netdevice, but this ifindex is
unusable in case of x-netns vxlan.
I named the new attribute NDA_NDM_IFINDEX_NETNSID, to avoid confusion with
NDA_IFINDEX.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c            | 5 +++++
 include/uapi/linux/neighbour.h | 1 +
 net/core/net_namespace.c       | 1 +
 3 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 0346eaa6d23..19d3664ab9d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -339,6 +339,11 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	ndm->ndm_flags = fdb->flags;
 	ndm->ndm_type = RTN_UNICAST;
 
+	if (!net_eq(dev_net(vxlan->dev), vxlan->net) &&
+	    nla_put_s32(skb, NDA_NDM_IFINDEX_NETNSID,
+			peernet2id(vxlan->net, dev_net(vxlan->dev))))
+		goto nla_put_failure;
+
 	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
 		goto nla_put_failure;
 
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index f3d77f9f1e0..38f236853cc 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -25,6 +25,7 @@ enum {
 	NDA_VNI,
 	NDA_IFINDEX,
 	NDA_MASTER,
+	NDA_NDM_IFINDEX_NETNSID,
 	__NDA_MAX
 };
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 9d1a4cac83b..b7bde551ef7 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -202,6 +202,7 @@ int peernet2id(struct net *net, struct net *peer)
 
 	return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED;
 }
+EXPORT_SYMBOL(peernet2id);
 
 struct net *get_net_ns_by_id(struct net *net, int id)
 {
-- 
cgit v1.2.3-70-g09d2


From d998f8efa47221405ceae129aa93fa6d4ac8510d Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 20 Jan 2015 11:23:04 -0800
Subject: udp: Do not require sock in udp_tunnel_xmit_skb

The UDP tunnel transmit functions udp_tunnel_xmit_skb and
udp_tunnel6_xmit_skb include a socket argument. The socket being
passed to the functions (from VXLAN) is a UDP created for receive
side. The only thing that the socket is used for in the transmit
functions is to get the setting for checksum (enabled or zero).
This patch removes the argument and and adds a nocheck argument
for checksum setting. This eliminates the unnecessary dependency
on a UDP socket for UDP tunnel transmit.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c       | 10 ++++++----
 include/net/udp_tunnel.h  | 16 ++++++++--------
 net/ipv4/geneve.c         |  5 +++--
 net/ipv4/udp_tunnel.c     | 12 ++++++------
 net/ipv6/ip6_udp_tunnel.c | 12 ++++++------
 5 files changed, 29 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 19d3664ab9d..a288ceab502 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1769,8 +1769,9 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
-	udp_tunnel6_xmit_skb(vs->sock, dst, skb, dev, saddr, daddr, prio,
-			     ttl, src_port, dst_port);
+	udp_tunnel6_xmit_skb(dst, skb, dev, saddr, daddr, prio,
+			     ttl, src_port, dst_port,
+			     udp_get_no_check6_tx(vs->sock->sk));
 	return 0;
 err:
 	dst_release(dst);
@@ -1848,8 +1849,9 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
-	return udp_tunnel_xmit_skb(vs->sock, rt, skb, src, dst, tos,
-				   ttl, df, src_port, dst_port, xnet);
+	return udp_tunnel_xmit_skb(rt, skb, src, dst, tos,
+				   ttl, df, src_port, dst_port, xnet,
+				   vs->sock->sk->sk_no_check_tx);
 }
 EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
 
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 2a50a70ef58..1a20d33d56b 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -77,17 +77,17 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 			   struct udp_tunnel_sock_cfg *sock_cfg);
 
 /* Transmit the skb using UDP encapsulation. */
-int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
-			struct sk_buff *skb, __be32 src, __be32 dst,
-			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
-			__be16 dst_port, bool xnet);
+int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb,
+			__be32 src, __be32 dst, __u8 tos, __u8 ttl,
+			__be16 df, __be16 src_port, __be16 dst_port,
+			bool xnet, bool nocheck);
 
 #if IS_ENABLED(CONFIG_IPV6)
-int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
-			 struct sk_buff *skb, struct net_device *dev,
-			 struct in6_addr *saddr, struct in6_addr *daddr,
+int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
+			 struct net_device *dev, struct in6_addr *saddr,
+			 struct in6_addr *daddr,
 			 __u8 prio, __u8 ttl, __be16 src_port,
-			 __be16 dst_port);
+			 __be16 dst_port, bool nocheck);
 #endif
 
 void udp_tunnel_sock_release(struct socket *sock);
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 9568594ca2f..93e51199e44 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -136,8 +136,9 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
-	return udp_tunnel_xmit_skb(gs->sock, rt, skb, src, dst,
-				   tos, ttl, df, src_port, dst_port, xnet);
+	return udp_tunnel_xmit_skb(rt, skb, src, dst,
+				   tos, ttl, df, src_port, dst_port, xnet,
+				   gs->sock->sk->sk_no_check_tx);
 }
 EXPORT_SYMBOL_GPL(geneve_xmit_skb);
 
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 9996e63ed30..c83b3548505 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -75,10 +75,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 
-int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
-			struct sk_buff *skb, __be32 src, __be32 dst,
-			__u8 tos, __u8 ttl, __be16 df, __be16 src_port,
-			__be16 dst_port, bool xnet)
+int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb,
+			__be32 src, __be32 dst, __u8 tos, __u8 ttl,
+			__be16 df, __be16 src_port, __be16 dst_port,
+			bool xnet, bool nocheck)
 {
 	struct udphdr *uh;
 
@@ -90,9 +90,9 @@ int udp_tunnel_xmit_skb(struct socket *sock, struct rtable *rt,
 	uh->source = src_port;
 	uh->len = htons(skb->len);
 
-	udp_set_csum(sock->sk->sk_no_check_tx, skb, src, dst, skb->len);
+	udp_set_csum(nocheck, skb, src, dst, skb->len);
 
-	return iptunnel_xmit(sock->sk, rt, skb, src, dst, IPPROTO_UDP,
+	return iptunnel_xmit(skb->sk, rt, skb, src, dst, IPPROTO_UDP,
 			     tos, ttl, df, xnet);
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index 8db6c98fe21..32d9b268e7d 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -62,14 +62,14 @@ error:
 }
 EXPORT_SYMBOL_GPL(udp_sock_create6);
 
-int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
-			 struct sk_buff *skb, struct net_device *dev,
-			 struct in6_addr *saddr, struct in6_addr *daddr,
-			 __u8 prio, __u8 ttl, __be16 src_port, __be16 dst_port)
+int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
+			 struct net_device *dev, struct in6_addr *saddr,
+			 struct in6_addr *daddr,
+			 __u8 prio, __u8 ttl, __be16 src_port,
+			 __be16 dst_port, bool nocheck)
 {
 	struct udphdr *uh;
 	struct ipv6hdr *ip6h;
-	struct sock *sk = sock->sk;
 
 	__skb_push(skb, sizeof(*uh));
 	skb_reset_transport_header(skb);
@@ -85,7 +85,7 @@ int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
 			    | IPSKB_REROUTED);
 	skb_dst_set(skb, dst);
 
-	udp6_set_csum(udp_get_no_check6_tx(sk), skb, saddr, daddr, skb->len);
+	udp6_set_csum(nocheck, skb, saddr, daddr, skb->len);
 
 	__skb_push(skb, sizeof(*ip6h));
 	skb_reset_network_header(skb);
-- 
cgit v1.2.3-70-g09d2


From af33c1adae1e095e90d14fe35501256ebb07aabf Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Tue, 20 Jan 2015 11:23:05 -0800
Subject: vxlan: Eliminate dependency on UDP socket in transmit path

In the vxlan transmit path there is no need to reference the socket
for a tunnel which is needed for the receive side. We do, however,
need the vxlan_dev flags. This patch eliminate references
to the socket in the transmit path, and changes VXLAN_F_UNSHAREABLE
to be VXLAN_F_RCV_FLAGS. This mask is used to store the flags
applicable to receive (GBP, CSUM6_RX, and REMCSUM_RX) in the
vxlan_sock flags.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c           | 60 ++++++++++++++++++++-----------------------
 include/net/vxlan.h           | 13 ++++++----
 net/openvswitch/vport-vxlan.c |  6 ++---
 3 files changed, 38 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a288ceab502..87736e65cd1 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -270,12 +270,13 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
 					  __be16 port, u32 flags)
 {
 	struct vxlan_sock *vs;
-	u32 match_flags = flags & VXLAN_F_UNSHAREABLE;
+
+	flags &= VXLAN_F_RCV_FLAGS;
 
 	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
 		if (inet_sk(vs->sock->sk)->inet_sport == port &&
 		    inet_sk(vs->sock->sk)->sk.sk_family == family &&
-		    (vs->flags & VXLAN_F_UNSHAREABLE) == match_flags)
+		    vs->flags == flags)
 			return vs;
 	}
 	return NULL;
@@ -1674,7 +1675,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
 	return false;
 }
 
-static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, struct vxlan_sock *vs,
+static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags,
 				struct vxlan_metadata *md)
 {
 	struct vxlanhdr_gbp *gbp;
@@ -1692,21 +1693,20 @@ static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, struct vxlan_sock *vs,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int vxlan6_xmit_skb(struct vxlan_sock *vs,
-			   struct dst_entry *dst, struct sk_buff *skb,
+static int vxlan6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
 			   struct net_device *dev, struct in6_addr *saddr,
 			   struct in6_addr *daddr, __u8 prio, __u8 ttl,
 			   __be16 src_port, __be16 dst_port,
-			   struct vxlan_metadata *md, bool xnet)
+			   struct vxlan_metadata *md, bool xnet, u32 vxflags)
 {
 	struct vxlanhdr *vxh;
 	int min_headroom;
 	int err;
-	bool udp_sum = !udp_get_no_check6_tx(vs->sock->sk);
+	bool udp_sum = !(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX);
 	int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 	u16 hdrlen = sizeof(struct vxlanhdr);
 
-	if ((vs->flags & VXLAN_F_REMCSUM_TX) &&
+	if ((vxflags & VXLAN_F_REMCSUM_TX) &&
 	    skb->ip_summed == CHECKSUM_PARTIAL) {
 		int csum_start = skb_checksum_start_offset(skb);
 
@@ -1764,14 +1764,14 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 		}
 	}
 
-	if (vs->flags & VXLAN_F_GBP)
-		vxlan_build_gbp_hdr(vxh, vs, md);
+	if (vxflags & VXLAN_F_GBP)
+		vxlan_build_gbp_hdr(vxh, vxflags, md);
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
 	udp_tunnel6_xmit_skb(dst, skb, dev, saddr, daddr, prio,
 			     ttl, src_port, dst_port,
-			     udp_get_no_check6_tx(vs->sock->sk));
+			     !!(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX));
 	return 0;
 err:
 	dst_release(dst);
@@ -1779,20 +1779,19 @@ err:
 }
 #endif
 
-int vxlan_xmit_skb(struct vxlan_sock *vs,
-		   struct rtable *rt, struct sk_buff *skb,
+int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
 		   __be16 src_port, __be16 dst_port,
-		   struct vxlan_metadata *md, bool xnet)
+		   struct vxlan_metadata *md, bool xnet, u32 vxflags)
 {
 	struct vxlanhdr *vxh;
 	int min_headroom;
 	int err;
-	bool udp_sum = !vs->sock->sk->sk_no_check_tx;
+	bool udp_sum = !!(vxflags & VXLAN_F_UDP_CSUM);
 	int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
 	u16 hdrlen = sizeof(struct vxlanhdr);
 
-	if ((vs->flags & VXLAN_F_REMCSUM_TX) &&
+	if ((vxflags & VXLAN_F_REMCSUM_TX) &&
 	    skb->ip_summed == CHECKSUM_PARTIAL) {
 		int csum_start = skb_checksum_start_offset(skb);
 
@@ -1844,14 +1843,14 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 		}
 	}
 
-	if (vs->flags & VXLAN_F_GBP)
-		vxlan_build_gbp_hdr(vxh, vs, md);
+	if (vxflags & VXLAN_F_GBP)
+		vxlan_build_gbp_hdr(vxh, vxflags, md);
 
 	skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
 	return udp_tunnel_xmit_skb(rt, skb, src, dst, tos,
 				   ttl, df, src_port, dst_port, xnet,
-				   vs->sock->sk->sk_no_check_tx);
+				   !(vxflags & VXLAN_F_UDP_CSUM));
 }
 EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
 
@@ -1983,10 +1982,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		md.vni = htonl(vni << 8);
 		md.gbp = skb->mark;
 
-		err = vxlan_xmit_skb(vxlan->vn_sock, rt, skb,
-				     fl4.saddr, dst->sin.sin_addr.s_addr,
-				     tos, ttl, df, src_port, dst_port, &md,
-				     !net_eq(vxlan->net, dev_net(vxlan->dev)));
+		err = vxlan_xmit_skb(rt, skb, fl4.saddr,
+				     dst->sin.sin_addr.s_addr, tos, ttl, df,
+				     src_port, dst_port, &md,
+				     !net_eq(vxlan->net, dev_net(vxlan->dev)),
+				     vxlan->flags);
 		if (err < 0) {
 			/* skb is already freed. */
 			skb = NULL;
@@ -2042,10 +2042,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		md.vni = htonl(vni << 8);
 		md.gbp = skb->mark;
 
-		err = vxlan6_xmit_skb(vxlan->vn_sock, ndst, skb,
-				      dev, &fl6.saddr, &fl6.daddr, 0, ttl,
-				      src_port, dst_port, &md,
-				      !net_eq(vxlan->net, dev_net(vxlan->dev)));
+		err = vxlan6_xmit_skb(ndst, skb, dev, &fl6.saddr, &fl6.daddr,
+				      0, ttl, src_port, dst_port, &md,
+				      !net_eq(vxlan->net, dev_net(vxlan->dev)),
+				      vxlan->flags);
 #endif
 	}
 
@@ -2517,15 +2517,11 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 
 	if (ipv6) {
 		udp_conf.family = AF_INET6;
-		udp_conf.use_udp6_tx_checksums =
-		    !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
 		udp_conf.use_udp6_rx_checksums =
 		    !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
 	} else {
 		udp_conf.family = AF_INET;
 		udp_conf.local_ip.s_addr = INADDR_ANY;
-		udp_conf.use_udp_checksums =
-		    !!(flags & VXLAN_F_UDP_CSUM);
 	}
 
 	udp_conf.local_udp_port = port;
@@ -2569,7 +2565,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	atomic_set(&vs->refcnt, 1);
 	vs->rcv = rcv;
 	vs->data = data;
-	vs->flags = flags;
+	vs->flags = (flags & VXLAN_F_RCV_FLAGS);
 
 	/* Initialize the vxlan udp offloads structure */
 	vs->udp_offloads.port = port;
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 7be8c342fc9..2927d624448 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -129,8 +129,12 @@ struct vxlan_sock {
 #define VXLAN_F_REMCSUM_RX		0x400
 #define VXLAN_F_GBP			0x800
 
-/* These flags must match in order for a socket to be shareable */
-#define VXLAN_F_UNSHAREABLE		VXLAN_F_GBP
+/* Flags that are used in the receive patch. These flags must match in
+ * order for a socket to be shareable
+ */
+#define VXLAN_F_RCV_FLAGS		(VXLAN_F_GBP |			\
+					 VXLAN_F_UDP_ZERO_CSUM6_RX |	\
+					 VXLAN_F_REMCSUM_RX)
 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,
@@ -138,11 +142,10 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 
 void vxlan_sock_release(struct vxlan_sock *vs);
 
-int vxlan_xmit_skb(struct vxlan_sock *vs,
-		   struct rtable *rt, struct sk_buff *skb,
+int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
 		   __be16 src_port, __be16 dst_port, struct vxlan_metadata *md,
-		   bool xnet);
+		   bool xnet, u32 vxflags);
 
 static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
 						     netdev_features_t features)
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 8a2d54cba9b..3cc983bf444 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -252,12 +252,10 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
 	md.gbp = vxlan_ext_gbp(skb);
 
-	err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
-			     fl.saddr, tun_key->ipv4_dst,
+	err = vxlan_xmit_skb(rt, skb, fl.saddr, tun_key->ipv4_dst,
 			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
 			     src_port, dst_port,
-			     &md,
-			     false);
+			     &md, false, vxlan_port->exts);
 	if (err < 0)
 		ip_rt_put(rt);
 	return err;
-- 
cgit v1.2.3-70-g09d2


From 872bf2fb69d90e3619befee842fc26db39d8e475 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 25 Jan 2015 16:59:35 +0200
Subject: net/mlx4_core: Maintain a persistent memory for mlx4 device

Maintain a persistent memory that should survive reset flow/PCI error.
This comes as a preparation for coming series to support above flows.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/alias_GUID.c            |   2 +-
 drivers/infiniband/hw/mlx4/mad.c                   |   3 +-
 drivers/infiniband/hw/mlx4/main.c                  |  17 ++--
 drivers/infiniband/hw/mlx4/mr.c                    |   6 +-
 drivers/infiniband/hw/mlx4/sysfs.c                 |   6 +-
 drivers/net/ethernet/mellanox/mlx4/alloc.c         |  15 +--
 drivers/net/ethernet/mellanox/mlx4/catas.c         |  13 +--
 drivers/net/ethernet/mellanox/mlx4/cmd.c           |  46 +++++----
 drivers/net/ethernet/mellanox/mlx4/en_cq.c         |   4 +-
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c    |   2 +-
 drivers/net/ethernet/mellanox/mlx4/en_main.c       |   4 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c     |   2 +-
 drivers/net/ethernet/mellanox/mlx4/en_rx.c         |   4 +-
 drivers/net/ethernet/mellanox/mlx4/en_tx.c         |   4 +-
 drivers/net/ethernet/mellanox/mlx4/eq.c            |  42 ++++----
 drivers/net/ethernet/mellanox/mlx4/icm.c           |  11 ++-
 drivers/net/ethernet/mellanox/mlx4/main.c          | 106 +++++++++++++--------
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |   9 +-
 drivers/net/ethernet/mellanox/mlx4/mr.c            |   8 +-
 drivers/net/ethernet/mellanox/mlx4/pd.c            |   6 +-
 drivers/net/ethernet/mellanox/mlx4/port.c          |  17 ++--
 drivers/net/ethernet/mellanox/mlx4/reset.c         |  23 +++--
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |  36 ++++---
 include/linux/mlx4/device.h                        |  11 ++-
 24 files changed, 234 insertions(+), 163 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index 0eb141c4141..a31e031afd8 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -154,7 +154,7 @@ void mlx4_ib_notify_slaves_on_guid_change(struct mlx4_ib_dev *dev,
 			continue;
 
 		slave_id = (block_num * NUM_ALIAS_GUID_IN_REC) + i ;
-		if (slave_id >= dev->dev->num_vfs + 1)
+		if (slave_id >= dev->dev->persist->num_vfs + 1)
 			return;
 		tmp_cur_ag = *(__be64 *)&p_data[i * GUID_REC_SIZE];
 		form_cache_ag = get_cached_alias_guid(dev, port_num,
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 82a7dd87089..c7619716c31 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -1951,7 +1951,8 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev,
 	ctx->ib_dev = &dev->ib_dev;
 
 	for (i = 0;
-	     i < min(dev->dev->caps.sqp_demux, (u16)(dev->dev->num_vfs + 1));
+	     i < min(dev->dev->caps.sqp_demux,
+	     (u16)(dev->dev->persist->num_vfs + 1));
 	     i++) {
 		struct mlx4_active_ports actv_ports =
 			mlx4_get_active_ports(dev->dev, i);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 57ecc5b204f..b4fa6f65880 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -198,7 +198,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 
 	props->vendor_id	   = be32_to_cpup((__be32 *) (out_mad->data + 36)) &
 		0xffffff;
-	props->vendor_part_id	   = dev->dev->pdev->device;
+	props->vendor_part_id	   = dev->dev->persist->pdev->device;
 	props->hw_ver		   = be32_to_cpup((__be32 *) (out_mad->data + 32));
 	memcpy(&props->sys_image_guid, out_mad->data +	4, 8);
 
@@ -1375,7 +1375,7 @@ static ssize_t show_hca(struct device *device, struct device_attribute *attr,
 {
 	struct mlx4_ib_dev *dev =
 		container_of(device, struct mlx4_ib_dev, ib_dev.dev);
-	return sprintf(buf, "MT%d\n", dev->dev->pdev->device);
+	return sprintf(buf, "MT%d\n", dev->dev->persist->pdev->device);
 }
 
 static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
@@ -1937,7 +1937,8 @@ static void init_pkeys(struct mlx4_ib_dev *ibdev)
 	int i;
 
 	if (mlx4_is_master(ibdev->dev)) {
-		for (slave = 0; slave <= ibdev->dev->num_vfs; ++slave) {
+		for (slave = 0; slave <= ibdev->dev->persist->num_vfs;
+		     ++slave) {
 			for (port = 1; port <= ibdev->dev->caps.num_ports; ++port) {
 				for (i = 0;
 				     i < ibdev->dev->phys_caps.pkey_phys_table_len[port];
@@ -1994,7 +1995,7 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) {
 		for (j = 0; j < eq_per_port; j++) {
 			snprintf(name, sizeof(name), "mlx4-ib-%d-%d@%s",
-				 i, j, dev->pdev->bus->name);
+				 i, j, dev->persist->pdev->bus->name);
 			/* Set IRQ for specific name (per ring) */
 			if (mlx4_assign_eq(dev, name, NULL,
 					   &ibdev->eq_table[eq])) {
@@ -2058,7 +2059,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	ibdev = (struct mlx4_ib_dev *) ib_alloc_device(sizeof *ibdev);
 	if (!ibdev) {
-		dev_err(&dev->pdev->dev, "Device struct alloc failed\n");
+		dev_err(&dev->persist->pdev->dev,
+			"Device struct alloc failed\n");
 		return NULL;
 	}
 
@@ -2085,7 +2087,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->num_ports		= num_ports;
 	ibdev->ib_dev.phys_port_cnt     = ibdev->num_ports;
 	ibdev->ib_dev.num_comp_vectors	= dev->caps.num_comp_vectors;
-	ibdev->ib_dev.dma_device	= &dev->pdev->dev;
+	ibdev->ib_dev.dma_device	= &dev->persist->pdev->dev;
 
 	if (dev->caps.userspace_caps)
 		ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION;
@@ -2236,7 +2238,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 				sizeof(long),
 				GFP_KERNEL);
 		if (!ibdev->ib_uc_qpns_bitmap) {
-			dev_err(&dev->pdev->dev, "bit map alloc failed\n");
+			dev_err(&dev->persist->pdev->dev,
+				"bit map alloc failed\n");
 			goto err_steer_qp_release;
 		}
 
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index c36ccbd9a64..e0d271782d0 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -401,7 +401,8 @@ struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device
 	if (!mfrpl->ibfrpl.page_list)
 		goto err_free;
 
-	mfrpl->mapped_page_list = dma_alloc_coherent(&dev->dev->pdev->dev,
+	mfrpl->mapped_page_list = dma_alloc_coherent(&dev->dev->persist->
+						     pdev->dev,
 						     size, &mfrpl->map,
 						     GFP_KERNEL);
 	if (!mfrpl->mapped_page_list)
@@ -423,7 +424,8 @@ void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
 	struct mlx4_ib_fast_reg_page_list *mfrpl = to_mfrpl(page_list);
 	int size = page_list->max_page_list_len * sizeof (u64);
 
-	dma_free_coherent(&dev->dev->pdev->dev, size, mfrpl->mapped_page_list,
+	dma_free_coherent(&dev->dev->persist->pdev->dev, size,
+			  mfrpl->mapped_page_list,
 			  mfrpl->map);
 	kfree(mfrpl->ibfrpl.page_list);
 	kfree(mfrpl);
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index cb4c66e723b..d10c2b8a5da 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -375,7 +375,7 @@ static void get_name(struct mlx4_ib_dev *dev, char *name, int i, int max)
 	char base_name[9];
 
 	/* pci_name format is: bus:dev:func -> xxxx:yy:zz.n */
-	strlcpy(name, pci_name(dev->dev->pdev), max);
+	strlcpy(name, pci_name(dev->dev->persist->pdev), max);
 	strncpy(base_name, name, 8); /*till xxxx:yy:*/
 	base_name[8] = '\0';
 	/* with no ARI only 3 last bits are used so when the fn is higher than 8
@@ -792,7 +792,7 @@ static int register_pkey_tree(struct mlx4_ib_dev *device)
 	if (!mlx4_is_master(device->dev))
 		return 0;
 
-	for (i = 0; i <= device->dev->num_vfs; ++i)
+	for (i = 0; i <= device->dev->persist->num_vfs; ++i)
 		register_one_pkey_tree(device, i);
 
 	return 0;
@@ -807,7 +807,7 @@ static void unregister_pkey_tree(struct mlx4_ib_dev *device)
 	if (!mlx4_is_master(device->dev))
 		return;
 
-	for (slave = device->dev->num_vfs; slave >= 0; --slave) {
+	for (slave = device->dev->persist->num_vfs; slave >= 0; --slave) {
 		list_for_each_entry_safe(p, t,
 					 &device->pkeys.pkey_port_list[slave],
 					 entry) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index 963dd7e6d54..a716c26e0d9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -592,7 +592,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		buf->nbufs        = 1;
 		buf->npages       = 1;
 		buf->page_shift   = get_order(size) + PAGE_SHIFT;
-		buf->direct.buf   = dma_alloc_coherent(&dev->pdev->dev,
+		buf->direct.buf   = dma_alloc_coherent(&dev->persist->pdev->dev,
 						       size, &t, gfp);
 		if (!buf->direct.buf)
 			return -ENOMEM;
@@ -619,7 +619,8 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 
 		for (i = 0; i < buf->nbufs; ++i) {
 			buf->page_list[i].buf =
-				dma_alloc_coherent(&dev->pdev->dev, PAGE_SIZE,
+				dma_alloc_coherent(&dev->persist->pdev->dev,
+						   PAGE_SIZE,
 						   &t, gfp);
 			if (!buf->page_list[i].buf)
 				goto err_free;
@@ -657,7 +658,8 @@ void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf)
 	int i;
 
 	if (buf->nbufs == 1)
-		dma_free_coherent(&dev->pdev->dev, size, buf->direct.buf,
+		dma_free_coherent(&dev->persist->pdev->dev, size,
+				  buf->direct.buf,
 				  buf->direct.map);
 	else {
 		if (BITS_PER_LONG == 64 && buf->direct.buf)
@@ -665,7 +667,8 @@ void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf)
 
 		for (i = 0; i < buf->nbufs; ++i)
 			if (buf->page_list[i].buf)
-				dma_free_coherent(&dev->pdev->dev, PAGE_SIZE,
+				dma_free_coherent(&dev->persist->pdev->dev,
+						  PAGE_SIZE,
 						  buf->page_list[i].buf,
 						  buf->page_list[i].map);
 		kfree(buf->page_list);
@@ -738,7 +741,7 @@ int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, gfp_t gfp
 		if (!mlx4_alloc_db_from_pgdir(pgdir, db, order))
 			goto out;
 
-	pgdir = mlx4_alloc_db_pgdir(&(dev->pdev->dev), gfp);
+	pgdir = mlx4_alloc_db_pgdir(&dev->persist->pdev->dev, gfp);
 	if (!pgdir) {
 		ret = -ENOMEM;
 		goto out;
@@ -775,7 +778,7 @@ void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db)
 	set_bit(i, db->u.pgdir->bits[o]);
 
 	if (bitmap_full(db->u.pgdir->order1, MLX4_DB_PER_PAGE / 2)) {
-		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+		dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE,
 				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
 		list_del(&db->u.pgdir->list);
 		kfree(db->u.pgdir);
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 9c656fe4983..1a102c9bac9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -70,7 +70,7 @@ static void poll_catas(unsigned long dev_ptr)
 
 	if (readl(priv->catas_err.map)) {
 		/* If the device is off-line, we cannot try to recover it */
-		if (pci_channel_offline(dev->pdev))
+		if (pci_channel_offline(dev->persist->pdev))
 			mod_timer(&priv->catas_err.timer,
 				  round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
 		else {
@@ -94,6 +94,7 @@ static void catas_reset(struct work_struct *work)
 {
 	struct mlx4_priv *priv, *tmppriv;
 	struct mlx4_dev *dev;
+	struct mlx4_dev_persistent *persist;
 
 	LIST_HEAD(tlist);
 	int ret;
@@ -103,20 +104,20 @@ static void catas_reset(struct work_struct *work)
 	spin_unlock_irq(&catas_lock);
 
 	list_for_each_entry_safe(priv, tmppriv, &tlist, catas_err.list) {
-		struct pci_dev *pdev = priv->dev.pdev;
+		struct pci_dev *pdev = priv->dev.persist->pdev;
 
 		/* If the device is off-line, we cannot reset it */
 		if (pci_channel_offline(pdev))
 			continue;
 
-		ret = mlx4_restart_one(priv->dev.pdev);
+		ret = mlx4_restart_one(priv->dev.persist->pdev);
 		/* 'priv' now is not valid */
 		if (ret)
 			pr_err("mlx4 %s: Reset failed (%d)\n",
 			       pci_name(pdev), ret);
 		else {
-			dev  = pci_get_drvdata(pdev);
-			mlx4_dbg(dev, "Reset succeeded\n");
+			persist  = pci_get_drvdata(pdev);
+			mlx4_dbg(persist->dev, "Reset succeeded\n");
 		}
 	}
 }
@@ -134,7 +135,7 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 	init_timer(&priv->catas_err.timer);
 	priv->catas_err.map = NULL;
 
-	addr = pci_resource_start(dev->pdev, priv->fw.catas_bar) +
+	addr = pci_resource_start(dev->persist->pdev, priv->fw.catas_bar) +
 		priv->fw.catas_offset;
 
 	priv->catas_err.map = ioremap(addr, priv->fw.catas_size * 4);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 5c93d1451c4..7cd90e6a427 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -307,7 +307,7 @@ static int cmd_pending(struct mlx4_dev *dev)
 {
 	u32 status;
 
-	if (pci_channel_offline(dev->pdev))
+	if (pci_channel_offline(dev->persist->pdev))
 		return -EIO;
 
 	status = readl(mlx4_priv(dev)->cmd.hcr + HCR_STATUS_OFFSET);
@@ -328,7 +328,7 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 
 	mutex_lock(&cmd->hcr_mutex);
 
-	if (pci_channel_offline(dev->pdev)) {
+	if (pci_channel_offline(dev->persist->pdev)) {
 		/*
 		 * Device is going through error recovery
 		 * and cannot accept commands.
@@ -342,7 +342,7 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 		end += msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS);
 
 	while (cmd_pending(dev)) {
-		if (pci_channel_offline(dev->pdev)) {
+		if (pci_channel_offline(dev->persist->pdev)) {
 			/*
 			 * Device is going through error recovery
 			 * and cannot accept commands.
@@ -464,7 +464,7 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 
 	down(&priv->cmd.poll_sem);
 
-	if (pci_channel_offline(dev->pdev)) {
+	if (pci_channel_offline(dev->persist->pdev)) {
 		/*
 		 * Device is going through error recovery
 		 * and cannot accept commands.
@@ -487,7 +487,7 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 
 	end = msecs_to_jiffies(timeout) + jiffies;
 	while (cmd_pending(dev) && time_before(jiffies, end)) {
-		if (pci_channel_offline(dev->pdev)) {
+		if (pci_channel_offline(dev->persist->pdev)) {
 			/*
 			 * Device is going through error recovery
 			 * and cannot accept commands.
@@ -612,7 +612,7 @@ int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	       int out_is_imm, u32 in_modifier, u8 op_modifier,
 	       u16 op, unsigned long timeout, int native)
 {
-	if (pci_channel_offline(dev->pdev))
+	if (pci_channel_offline(dev->persist->pdev))
 		return -EIO;
 
 	if (!mlx4_is_mfunc(dev) || (native && mlx4_is_master(dev))) {
@@ -1997,11 +1997,12 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 
 	if (mlx4_is_master(dev))
 		priv->mfunc.comm =
-		ioremap(pci_resource_start(dev->pdev, priv->fw.comm_bar) +
+		ioremap(pci_resource_start(dev->persist->pdev,
+					   priv->fw.comm_bar) +
 			priv->fw.comm_base, MLX4_COMM_PAGESIZE);
 	else
 		priv->mfunc.comm =
-		ioremap(pci_resource_start(dev->pdev, 2) +
+		ioremap(pci_resource_start(dev->persist->pdev, 2) +
 			MLX4_SLAVE_COMM_BASE, MLX4_COMM_PAGESIZE);
 	if (!priv->mfunc.comm) {
 		mlx4_err(dev, "Couldn't map communication vector\n");
@@ -2107,9 +2108,9 @@ err_comm_admin:
 err_comm:
 	iounmap(priv->mfunc.comm);
 err_vhcr:
-	dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
-					     priv->mfunc.vhcr,
-					     priv->mfunc.vhcr_dma);
+	dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE,
+			  priv->mfunc.vhcr,
+			  priv->mfunc.vhcr_dma);
 	priv->mfunc.vhcr = NULL;
 	return -ENOMEM;
 }
@@ -2130,8 +2131,8 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 	}
 
 	if (!mlx4_is_slave(dev) && !priv->cmd.hcr) {
-		priv->cmd.hcr = ioremap(pci_resource_start(dev->pdev, 0) +
-					MLX4_HCR_BASE, MLX4_HCR_SIZE);
+		priv->cmd.hcr = ioremap(pci_resource_start(dev->persist->pdev,
+					0) + MLX4_HCR_BASE, MLX4_HCR_SIZE);
 		if (!priv->cmd.hcr) {
 			mlx4_err(dev, "Couldn't map command register\n");
 			goto err;
@@ -2140,7 +2141,8 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 	}
 
 	if (mlx4_is_mfunc(dev) && !priv->mfunc.vhcr) {
-		priv->mfunc.vhcr = dma_alloc_coherent(&(dev->pdev->dev), PAGE_SIZE,
+		priv->mfunc.vhcr = dma_alloc_coherent(&dev->persist->pdev->dev,
+						      PAGE_SIZE,
 						      &priv->mfunc.vhcr_dma,
 						      GFP_KERNEL);
 		if (!priv->mfunc.vhcr)
@@ -2150,7 +2152,8 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 	}
 
 	if (!priv->cmd.pool) {
-		priv->cmd.pool = pci_pool_create("mlx4_cmd", dev->pdev,
+		priv->cmd.pool = pci_pool_create("mlx4_cmd",
+						 dev->persist->pdev,
 						 MLX4_MAILBOX_SIZE,
 						 MLX4_MAILBOX_SIZE, 0);
 		if (!priv->cmd.pool)
@@ -2202,7 +2205,7 @@ void mlx4_cmd_cleanup(struct mlx4_dev *dev, int cleanup_mask)
 	}
 	if (mlx4_is_mfunc(dev) && priv->mfunc.vhcr &&
 	    (cleanup_mask & MLX4_CMD_CLEANUP_VHCR)) {
-		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+		dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE,
 				  priv->mfunc.vhcr, priv->mfunc.vhcr_dma);
 		priv->mfunc.vhcr = NULL;
 	}
@@ -2306,8 +2309,9 @@ u32 mlx4_comm_get_version(void)
 
 static int mlx4_get_slave_indx(struct mlx4_dev *dev, int vf)
 {
-	if ((vf < 0) || (vf >= dev->num_vfs)) {
-		mlx4_err(dev, "Bad vf number:%d (number of activated vf: %d)\n", vf, dev->num_vfs);
+	if ((vf < 0) || (vf >= dev->persist->num_vfs)) {
+		mlx4_err(dev, "Bad vf number:%d (number of activated vf: %d)\n",
+			 vf, dev->persist->num_vfs);
 		return -EINVAL;
 	}
 
@@ -2316,7 +2320,7 @@ static int mlx4_get_slave_indx(struct mlx4_dev *dev, int vf)
 
 int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave)
 {
-	if (slave < 1 || slave > dev->num_vfs) {
+	if (slave < 1 || slave > dev->persist->num_vfs) {
 		mlx4_err(dev,
 			 "Bad slave number:%d (number of activated slaves: %lu)\n",
 			 slave, dev->num_slaves);
@@ -2388,7 +2392,7 @@ struct mlx4_slaves_pport mlx4_phys_to_slaves_pport(struct mlx4_dev *dev,
 	if (port <= 0 || port > dev->caps.num_ports)
 		return slaves_pport;
 
-	for (i = 0; i < dev->num_vfs + 1; i++) {
+	for (i = 0; i < dev->persist->num_vfs + 1; i++) {
 		struct mlx4_active_ports actv_ports =
 			mlx4_get_active_ports(dev, i);
 		if (test_bit(port - 1, actv_ports.ports))
@@ -2408,7 +2412,7 @@ struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv(
 
 	bitmap_zero(slaves_pport.slaves, MLX4_MFUNC_MAX);
 
-	for (i = 0; i < dev->num_vfs + 1; i++) {
+	for (i = 0; i < dev->persist->num_vfs + 1; i++) {
 		struct mlx4_active_ports actv_ports =
 			mlx4_get_active_ports(dev, i);
 		if (bitmap_equal(crit_ports->ports, actv_ports.ports,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 82322b1c841..22da4d0d0f0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -70,10 +70,10 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	/* Allocate HW buffers on provided NUMA node.
 	 * dev->numa_node is used in mtt range allocation flow.
 	 */
-	set_dev_node(&mdev->dev->pdev->dev, node);
+	set_dev_node(&mdev->dev->persist->pdev->dev, node);
 	err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
 				cq->buf_size, 2 * PAGE_SIZE);
-	set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
+	set_dev_node(&mdev->dev->persist->pdev->dev, mdev->dev->numa_node);
 	if (err)
 		goto err_cq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 90e0f045a6b..569eda9e83d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -92,7 +92,7 @@ mlx4_en_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 		(u16) (mdev->dev->caps.fw_ver >> 32),
 		(u16) ((mdev->dev->caps.fw_ver >> 16) & 0xffff),
 		(u16) (mdev->dev->caps.fw_ver & 0xffff));
-	strlcpy(drvinfo->bus_info, pci_name(mdev->dev->pdev),
+	strlcpy(drvinfo->bus_info, pci_name(mdev->dev->persist->pdev),
 		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = 0;
 	drvinfo->regdump_len = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 9f16f754137..c643d2bbb7b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -241,8 +241,8 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	spin_lock_init(&mdev->uar_lock);
 
 	mdev->dev = dev;
-	mdev->dma_device = &(dev->pdev->dev);
-	mdev->pdev = dev->pdev;
+	mdev->dma_device = &dev->persist->pdev->dev;
+	mdev->pdev = dev->persist->pdev;
 	mdev->device_up = false;
 
 	mdev->LSO_support = !!(dev->caps.flags & (1 << 15));
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index d0d6dc1b8e4..43a3f9822f7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2457,7 +2457,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	netif_set_real_num_tx_queues(dev, prof->tx_ring_num);
 	netif_set_real_num_rx_queues(dev, prof->rx_ring_num);
 
-	SET_NETDEV_DEV(dev, &mdev->dev->pdev->dev);
+	SET_NETDEV_DEV(dev, &mdev->dev->persist->pdev->dev);
 	dev->dev_port = port - 1;
 
 	/*
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index a0474eb94aa..2ba5d368edc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -387,10 +387,10 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 		 ring->rx_info, tmp);
 
 	/* Allocate HW buffers on provided NUMA node */
-	set_dev_node(&mdev->dev->pdev->dev, node);
+	set_dev_node(&mdev->dev->persist->pdev->dev, node);
 	err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres,
 				 ring->buf_size, 2 * PAGE_SIZE);
-	set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
+	set_dev_node(&mdev->dev->persist->pdev->dev, mdev->dev->numa_node);
 	if (err)
 		goto err_info;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 359bb1286eb..55f9f5c5344 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -91,10 +91,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	ring->buf_size = ALIGN(size * ring->stride, MLX4_EN_PAGE_SIZE);
 
 	/* Allocate HW buffers on provided NUMA node */
-	set_dev_node(&mdev->dev->pdev->dev, node);
+	set_dev_node(&mdev->dev->persist->pdev->dev, node);
 	err = mlx4_alloc_hwq_res(mdev->dev, &ring->wqres, ring->buf_size,
 				 2 * PAGE_SIZE);
-	set_dev_node(&mdev->dev->pdev->dev, mdev->dev->numa_node);
+	set_dev_node(&mdev->dev->persist->pdev->dev, mdev->dev->numa_node);
 	if (err) {
 		en_err(priv, "Failed allocating hwq resources\n");
 		goto err_bounce;
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 3d275fbaf0e..7538c9ce98a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -237,7 +237,7 @@ int mlx4_gen_guid_change_eqe(struct mlx4_dev *dev, int slave, u8 port)
 	struct mlx4_eqe eqe;
 
 	/*don't send if we don't have the that slave */
-	if (dev->num_vfs < slave)
+	if (dev->persist->num_vfs < slave)
 		return 0;
 	memset(&eqe, 0, sizeof eqe);
 
@@ -255,7 +255,7 @@ int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port,
 	struct mlx4_eqe eqe;
 
 	/*don't send if we don't have the that slave */
-	if (dev->num_vfs < slave)
+	if (dev->persist->num_vfs < slave)
 		return 0;
 	memset(&eqe, 0, sizeof eqe);
 
@@ -310,7 +310,7 @@ static void set_all_slave_state(struct mlx4_dev *dev, u8 port, int event)
 	struct mlx4_slaves_pport slaves_pport = mlx4_phys_to_slaves_pport(dev,
 									  port);
 
-	for (i = 0; i < dev->num_vfs + 1; i++)
+	for (i = 0; i < dev->persist->num_vfs + 1; i++)
 		if (test_bit(i, slaves_pport.slaves))
 			set_and_calc_slave_port_state(dev, i, port,
 						      event, &gen_event);
@@ -560,7 +560,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				mlx4_priv(dev)->sense.do_sense_port[port] = 1;
 				if (!mlx4_is_master(dev))
 					break;
-				for (i = 0; i < dev->num_vfs + 1; i++) {
+				for (i = 0; i < dev->persist->num_vfs + 1;
+				     i++) {
 					if (!test_bit(i, slaves_port.slaves))
 						continue;
 					if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) {
@@ -596,7 +597,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				if (!mlx4_is_master(dev))
 					break;
 				if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
-					for (i = 0; i < dev->num_vfs + 1; i++) {
+					for (i = 0;
+					     i < dev->persist->num_vfs + 1;
+					     i++) {
 						if (!test_bit(i, slaves_port.slaves))
 							continue;
 						if (i == mlx4_master_func_num(dev))
@@ -865,7 +868,7 @@ static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 	if (!priv->eq_table.uar_map[index]) {
 		priv->eq_table.uar_map[index] =
-			ioremap(pci_resource_start(dev->pdev, 2) +
+			ioremap(pci_resource_start(dev->persist->pdev, 2) +
 				((eq->eqn / 4) << PAGE_SHIFT),
 				PAGE_SIZE);
 		if (!priv->eq_table.uar_map[index]) {
@@ -928,8 +931,10 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent,
 	eq_context = mailbox->buf;
 
 	for (i = 0; i < npages; ++i) {
-		eq->page_list[i].buf = dma_alloc_coherent(&dev->pdev->dev,
-							  PAGE_SIZE, &t, GFP_KERNEL);
+		eq->page_list[i].buf = dma_alloc_coherent(&dev->persist->
+							  pdev->dev,
+							  PAGE_SIZE, &t,
+							  GFP_KERNEL);
 		if (!eq->page_list[i].buf)
 			goto err_out_free_pages;
 
@@ -995,7 +1000,7 @@ err_out_free_eq:
 err_out_free_pages:
 	for (i = 0; i < npages; ++i)
 		if (eq->page_list[i].buf)
-			dma_free_coherent(&dev->pdev->dev, PAGE_SIZE,
+			dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE,
 					  eq->page_list[i].buf,
 					  eq->page_list[i].map);
 
@@ -1044,9 +1049,9 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 
 	mlx4_mtt_cleanup(dev, &eq->mtt);
 	for (i = 0; i < npages; ++i)
-		dma_free_coherent(&dev->pdev->dev, PAGE_SIZE,
-				    eq->page_list[i].buf,
-				    eq->page_list[i].map);
+		dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE,
+				  eq->page_list[i].buf,
+				  eq->page_list[i].map);
 
 	kfree(eq->page_list);
 	mlx4_bitmap_free(&priv->eq_table.bitmap, eq->eqn, MLX4_USE_RR);
@@ -1060,7 +1065,7 @@ static void mlx4_free_irqs(struct mlx4_dev *dev)
 	int	i, vec;
 
 	if (eq_table->have_irq)
-		free_irq(dev->pdev->irq, dev);
+		free_irq(dev->persist->pdev->irq, dev);
 
 	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
 		if (eq_table->eq[i].have_irq) {
@@ -1089,7 +1094,8 @@ static int mlx4_map_clr_int(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	priv->clr_base = ioremap(pci_resource_start(dev->pdev, priv->fw.clr_int_bar) +
+	priv->clr_base = ioremap(pci_resource_start(dev->persist->pdev,
+				 priv->fw.clr_int_bar) +
 				 priv->fw.clr_int_base, MLX4_CLR_INT_SIZE);
 	if (!priv->clr_base) {
 		mlx4_err(dev, "Couldn't map interrupt clear register, aborting\n");
@@ -1212,13 +1218,13 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 					 i * MLX4_IRQNAME_SIZE,
 					 MLX4_IRQNAME_SIZE,
 					 "mlx4-comp-%d@pci:%s", i,
-					 pci_name(dev->pdev));
+					 pci_name(dev->persist->pdev));
 			} else {
 				snprintf(priv->eq_table.irq_names +
 					 i * MLX4_IRQNAME_SIZE,
 					 MLX4_IRQNAME_SIZE,
 					 "mlx4-async@pci:%s",
-					 pci_name(dev->pdev));
+					 pci_name(dev->persist->pdev));
 			}
 
 			eq_name = priv->eq_table.irq_names +
@@ -1235,8 +1241,8 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 		snprintf(priv->eq_table.irq_names,
 			 MLX4_IRQNAME_SIZE,
 			 DRV_NAME "@pci:%s",
-			 pci_name(dev->pdev));
-		err = request_irq(dev->pdev->irq, mlx4_interrupt,
+			 pci_name(dev->persist->pdev));
+		err = request_irq(dev->persist->pdev->irq, mlx4_interrupt,
 				  IRQF_SHARED, priv->eq_table.irq_names, dev);
 		if (err)
 			goto err_out_async;
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 97c9b1db1d2..2a9dd460a95 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -56,7 +56,7 @@ static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chu
 	int i;
 
 	if (chunk->nsg > 0)
-		pci_unmap_sg(dev->pdev, chunk->mem, chunk->npages,
+		pci_unmap_sg(dev->persist->pdev, chunk->mem, chunk->npages,
 			     PCI_DMA_BIDIRECTIONAL);
 
 	for (i = 0; i < chunk->npages; ++i)
@@ -69,7 +69,8 @@ static void mlx4_free_icm_coherent(struct mlx4_dev *dev, struct mlx4_icm_chunk *
 	int i;
 
 	for (i = 0; i < chunk->npages; ++i)
-		dma_free_coherent(&dev->pdev->dev, chunk->mem[i].length,
+		dma_free_coherent(&dev->persist->pdev->dev,
+				  chunk->mem[i].length,
 				  lowmem_page_address(sg_page(&chunk->mem[i])),
 				  sg_dma_address(&chunk->mem[i]));
 }
@@ -173,7 +174,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 			--cur_order;
 
 		if (coherent)
-			ret = mlx4_alloc_icm_coherent(&dev->pdev->dev,
+			ret = mlx4_alloc_icm_coherent(&dev->persist->pdev->dev,
 						      &chunk->mem[chunk->npages],
 						      cur_order, gfp_mask);
 		else
@@ -193,7 +194,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 		if (coherent)
 			++chunk->nsg;
 		else if (chunk->npages == MLX4_ICM_CHUNK_LEN) {
-			chunk->nsg = pci_map_sg(dev->pdev, chunk->mem,
+			chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
 						chunk->npages,
 						PCI_DMA_BIDIRECTIONAL);
 
@@ -208,7 +209,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 	}
 
 	if (!coherent && chunk) {
-		chunk->nsg = pci_map_sg(dev->pdev, chunk->mem,
+		chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
 					chunk->npages,
 					PCI_DMA_BIDIRECTIONAL);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 03e9eb0dc76..abcee61f8a4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -318,10 +318,11 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		return -ENODEV;
 	}
 
-	if (dev_cap->uar_size > pci_resource_len(dev->pdev, 2)) {
+	if (dev_cap->uar_size > pci_resource_len(dev->persist->pdev, 2)) {
 		mlx4_err(dev, "HCA reported UAR size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n",
 			 dev_cap->uar_size,
-			 (unsigned long long) pci_resource_len(dev->pdev, 2));
+			 (unsigned long long)
+			 pci_resource_len(dev->persist->pdev, 2));
 		return -ENODEV;
 	}
 
@@ -541,8 +542,10 @@ static int mlx4_get_pcie_dev_link_caps(struct mlx4_dev *dev,
 	*speed = PCI_SPEED_UNKNOWN;
 	*width = PCIE_LNK_WIDTH_UNKNOWN;
 
-	err1 = pcie_capability_read_dword(dev->pdev, PCI_EXP_LNKCAP, &lnkcap1);
-	err2 = pcie_capability_read_dword(dev->pdev, PCI_EXP_LNKCAP2, &lnkcap2);
+	err1 = pcie_capability_read_dword(dev->persist->pdev, PCI_EXP_LNKCAP,
+					  &lnkcap1);
+	err2 = pcie_capability_read_dword(dev->persist->pdev, PCI_EXP_LNKCAP2,
+					  &lnkcap2);
 	if (!err2 && lnkcap2) { /* PCIe r3.0-compliant */
 		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
 			*speed = PCIE_SPEED_8_0GT;
@@ -587,7 +590,7 @@ static void mlx4_check_pcie_caps(struct mlx4_dev *dev)
 		return;
 	}
 
-	err = pcie_get_minimum_link(dev->pdev, &speed, &width);
+	err = pcie_get_minimum_link(dev->persist->pdev, &speed, &width);
 	if (err || speed == PCI_SPEED_UNKNOWN ||
 	    width == PCIE_LNK_WIDTH_UNKNOWN) {
 		mlx4_warn(dev,
@@ -837,10 +840,12 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 
 	if (dev->caps.uar_page_size * (dev->caps.num_uars -
 				       dev->caps.reserved_uars) >
-				       pci_resource_len(dev->pdev, 2)) {
+				       pci_resource_len(dev->persist->pdev,
+							2)) {
 		mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n",
 			 dev->caps.uar_page_size * dev->caps.num_uars,
-			 (unsigned long long) pci_resource_len(dev->pdev, 2));
+			 (unsigned long long)
+			 pci_resource_len(dev->persist->pdev, 2));
 		goto err_mem;
 	}
 
@@ -1492,9 +1497,9 @@ static int map_bf_area(struct mlx4_dev *dev)
 	if (!dev->caps.bf_reg_size)
 		return -ENXIO;
 
-	bf_start = pci_resource_start(dev->pdev, 2) +
+	bf_start = pci_resource_start(dev->persist->pdev, 2) +
 			(dev->caps.num_uars << PAGE_SHIFT);
-	bf_len = pci_resource_len(dev->pdev, 2) -
+	bf_len = pci_resource_len(dev->persist->pdev, 2) -
 			(dev->caps.num_uars << PAGE_SHIFT);
 	priv->bf_mapping = io_mapping_create_wc(bf_start, bf_len);
 	if (!priv->bf_mapping)
@@ -1536,7 +1541,8 @@ static int map_internal_clock(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	priv->clock_mapping =
-		ioremap(pci_resource_start(dev->pdev, priv->fw.clock_bar) +
+		ioremap(pci_resource_start(dev->persist->pdev,
+					   priv->fw.clock_bar) +
 			priv->fw.clock_offset, MLX4_CLOCK_SIZE);
 
 	if (!priv->clock_mapping)
@@ -1705,7 +1711,8 @@ static void choose_steering_mode(struct mlx4_dev *dev,
 	if (mlx4_log_num_mgm_entry_size <= 0 &&
 	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
 	    (!mlx4_is_mfunc(dev) ||
-	     (dev_cap->fs_max_num_qp_per_entry >= (dev->num_vfs + 1))) &&
+	     (dev_cap->fs_max_num_qp_per_entry >=
+	     (dev->persist->num_vfs + 1))) &&
 	    choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry) >=
 		MLX4_MIN_MGM_LOG_ENTRY_SIZE) {
 		dev->oper_log_mgm_entry_size =
@@ -2288,7 +2295,8 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 		for (i = 0; i < nreq; ++i)
 			entries[i].entry = i;
 
-		nreq = pci_enable_msix_range(dev->pdev, entries, 2, nreq);
+		nreq = pci_enable_msix_range(dev->persist->pdev, entries, 2,
+					     nreq);
 
 		if (nreq < 0) {
 			kfree(entries);
@@ -2316,7 +2324,7 @@ no_msi:
 	dev->caps.comp_pool	   = 0;
 
 	for (i = 0; i < 2; ++i)
-		priv->eq_table.eq[i].irq = dev->pdev->irq;
+		priv->eq_table.eq[i].irq = dev->persist->pdev->irq;
 }
 
 static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
@@ -2344,7 +2352,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 	info->port_attr.show      = show_port_type;
 	sysfs_attr_init(&info->port_attr.attr);
 
-	err = device_create_file(&dev->pdev->dev, &info->port_attr);
+	err = device_create_file(&dev->persist->pdev->dev, &info->port_attr);
 	if (err) {
 		mlx4_err(dev, "Failed to create file for port %d\n", port);
 		info->port = -1;
@@ -2361,10 +2369,12 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 	info->port_mtu_attr.show      = show_port_ib_mtu;
 	sysfs_attr_init(&info->port_mtu_attr.attr);
 
-	err = device_create_file(&dev->pdev->dev, &info->port_mtu_attr);
+	err = device_create_file(&dev->persist->pdev->dev,
+				 &info->port_mtu_attr);
 	if (err) {
 		mlx4_err(dev, "Failed to create mtu file for port %d\n", port);
-		device_remove_file(&info->dev->pdev->dev, &info->port_attr);
+		device_remove_file(&info->dev->persist->pdev->dev,
+				   &info->port_attr);
 		info->port = -1;
 	}
 
@@ -2376,8 +2386,9 @@ static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
 	if (info->port < 0)
 		return;
 
-	device_remove_file(&info->dev->pdev->dev, &info->port_attr);
-	device_remove_file(&info->dev->pdev->dev, &info->port_mtu_attr);
+	device_remove_file(&info->dev->persist->pdev->dev, &info->port_attr);
+	device_remove_file(&info->dev->persist->pdev->dev,
+			   &info->port_mtu_attr);
 }
 
 static int mlx4_init_steering(struct mlx4_dev *dev)
@@ -2444,10 +2455,11 @@ static int mlx4_get_ownership(struct mlx4_dev *dev)
 	void __iomem *owner;
 	u32 ret;
 
-	if (pci_channel_offline(dev->pdev))
+	if (pci_channel_offline(dev->persist->pdev))
 		return -EIO;
 
-	owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
+	owner = ioremap(pci_resource_start(dev->persist->pdev, 0) +
+			MLX4_OWNER_BASE,
 			MLX4_OWNER_SIZE);
 	if (!owner) {
 		mlx4_err(dev, "Failed to obtain ownership bit\n");
@@ -2463,10 +2475,11 @@ static void mlx4_free_ownership(struct mlx4_dev *dev)
 {
 	void __iomem *owner;
 
-	if (pci_channel_offline(dev->pdev))
+	if (pci_channel_offline(dev->persist->pdev))
 		return;
 
-	owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
+	owner = ioremap(pci_resource_start(dev->persist->pdev, 0) +
+			MLX4_OWNER_BASE,
 			MLX4_OWNER_SIZE);
 	if (!owner) {
 		mlx4_err(dev, "Failed to obtain ownership bit\n");
@@ -2514,13 +2527,13 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
 		dev_flags |= MLX4_FLAG_SRIOV |
 			MLX4_FLAG_MASTER;
 		dev_flags &= ~MLX4_FLAG_SLAVE;
-		dev->num_vfs = total_vfs;
+		dev->persist->num_vfs = total_vfs;
 	}
 	return dev_flags;
 
 disable_sriov:
 	atomic_dec(&pf_loading);
-	dev->num_vfs = 0;
+	dev->persist->num_vfs = 0;
 	kfree(dev->dev_vfs);
 	return dev_flags & ~MLX4_FLAG_MASTER;
 }
@@ -2607,7 +2620,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 			existing_vfs = pci_num_vf(pdev);
 			if (existing_vfs)
 				dev->flags |= MLX4_FLAG_SRIOV;
-			dev->num_vfs = total_vfs;
+			dev->persist->num_vfs = total_vfs;
 		}
 	}
 
@@ -2771,12 +2784,14 @@ slave_start:
 				 dev->caps.num_ports);
 			goto err_close;
 		}
-		memcpy(dev->nvfs, nvfs, sizeof(dev->nvfs));
+		memcpy(dev->persist->nvfs, nvfs, sizeof(dev->persist->nvfs));
 
-		for (i = 0; i < sizeof(dev->nvfs)/sizeof(dev->nvfs[0]); i++) {
+		for (i = 0;
+		     i < sizeof(dev->persist->nvfs)/
+		     sizeof(dev->persist->nvfs[0]); i++) {
 			unsigned j;
 
-			for (j = 0; j < dev->nvfs[i]; ++sum, ++j) {
+			for (j = 0; j < dev->persist->nvfs[i]; ++sum, ++j) {
 				dev->dev_vfs[sum].min_port = i < 2 ? i + 1 : 1;
 				dev->dev_vfs[sum].n_ports = i < 2 ? 1 :
 					dev->caps.num_ports;
@@ -2846,7 +2861,7 @@ slave_start:
 
 	priv->removed = 0;
 
-	if (mlx4_is_master(dev) && dev->num_vfs)
+	if (mlx4_is_master(dev) && dev->persist->num_vfs)
 		atomic_dec(&pf_loading);
 
 	kfree(dev_cap);
@@ -2908,7 +2923,7 @@ err_sriov:
 	if (dev->flags & MLX4_FLAG_SRIOV && !existing_vfs)
 		pci_disable_sriov(pdev);
 
-	if (mlx4_is_master(dev) && dev->num_vfs)
+	if (mlx4_is_master(dev) && dev->persist->num_vfs)
 		atomic_dec(&pf_loading);
 
 	kfree(priv->dev.dev_vfs);
@@ -3076,20 +3091,28 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	dev       = &priv->dev;
-	dev->pdev = pdev;
-	pci_set_drvdata(pdev, dev);
+	dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL);
+	if (!dev->persist) {
+		kfree(priv);
+		return -ENOMEM;
+	}
+	dev->persist->pdev = pdev;
+	dev->persist->dev = dev;
+	pci_set_drvdata(pdev, dev->persist);
 	priv->pci_dev_data = id->driver_data;
 
 	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
-	if (ret)
+	if (ret) {
+		kfree(dev->persist);
 		kfree(priv);
-
+	}
 	return ret;
 }
 
 static void mlx4_unload_one(struct pci_dev *pdev)
 {
-	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
+	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
+	struct mlx4_dev  *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int               pci_dev_data;
 	int p;
@@ -3155,7 +3178,7 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 		mlx4_warn(dev, "Disabling SR-IOV\n");
 		pci_disable_sriov(pdev);
 		dev->flags &= ~MLX4_FLAG_SRIOV;
-		dev->num_vfs = 0;
+		dev->persist->num_vfs = 0;
 	}
 
 	if (!mlx4_is_slave(dev))
@@ -3175,26 +3198,29 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 
 static void mlx4_remove_one(struct pci_dev *pdev)
 {
-	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
+	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
+	struct mlx4_dev  *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	mlx4_unload_one(pdev);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+	kfree(dev->persist);
 	kfree(priv);
 	pci_set_drvdata(pdev, NULL);
 }
 
 int mlx4_restart_one(struct pci_dev *pdev)
 {
-	struct mlx4_dev	 *dev  = pci_get_drvdata(pdev);
+	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
+	struct mlx4_dev	 *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0};
 	int pci_dev_data, err, total_vfs;
 
 	pci_dev_data = priv->pci_dev_data;
-	total_vfs = dev->num_vfs;
-	memcpy(nvfs, dev->nvfs, sizeof(dev->nvfs));
+	total_vfs = dev->persist->num_vfs;
+	memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));
 
 	mlx4_unload_one(pdev);
 	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index bdd4eea2247..faa37ab75a9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -221,16 +221,17 @@ extern int mlx4_debug_level;
 #define mlx4_dbg(mdev, format, ...)					\
 do {									\
 	if (mlx4_debug_level)						\
-		dev_printk(KERN_DEBUG, &(mdev)->pdev->dev, format,	\
+		dev_printk(KERN_DEBUG,					\
+			   &(mdev)->persist->pdev->dev, format,		\
 			   ##__VA_ARGS__);				\
 } while (0)
 
 #define mlx4_err(mdev, format, ...)					\
-	dev_err(&(mdev)->pdev->dev, format, ##__VA_ARGS__)
+	dev_err(&(mdev)->persist->pdev->dev, format, ##__VA_ARGS__)
 #define mlx4_info(mdev, format, ...)					\
-	dev_info(&(mdev)->pdev->dev, format, ##__VA_ARGS__)
+	dev_info(&(mdev)->persist->pdev->dev, format, ##__VA_ARGS__)
 #define mlx4_warn(mdev, format, ...)					\
-	dev_warn(&(mdev)->pdev->dev, format, ##__VA_ARGS__)
+	dev_warn(&(mdev)->persist->pdev->dev, format, ##__VA_ARGS__)
 
 extern int mlx4_log_num_mgm_entry_size;
 extern int log_mtts_per_seg;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 7094a9c70fd..8dbdf1d2935 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -708,13 +708,13 @@ static int mlx4_write_mtt_chunk(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 	if (!mtts)
 		return -ENOMEM;
 
-	dma_sync_single_for_cpu(&dev->pdev->dev, dma_handle,
+	dma_sync_single_for_cpu(&dev->persist->pdev->dev, dma_handle,
 				npages * sizeof (u64), DMA_TO_DEVICE);
 
 	for (i = 0; i < npages; ++i)
 		mtts[i] = cpu_to_be64(page_list[i] | MLX4_MTT_FLAG_PRESENT);
 
-	dma_sync_single_for_device(&dev->pdev->dev, dma_handle,
+	dma_sync_single_for_device(&dev->persist->pdev->dev, dma_handle,
 				   npages * sizeof (u64), DMA_TO_DEVICE);
 
 	return 0;
@@ -1020,13 +1020,13 @@ int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list
 	/* Make sure MPT status is visible before writing MTT entries */
 	wmb();
 
-	dma_sync_single_for_cpu(&dev->pdev->dev, fmr->dma_handle,
+	dma_sync_single_for_cpu(&dev->persist->pdev->dev, fmr->dma_handle,
 				npages * sizeof(u64), DMA_TO_DEVICE);
 
 	for (i = 0; i < npages; ++i)
 		fmr->mtts[i] = cpu_to_be64(page_list[i] | MLX4_MTT_FLAG_PRESENT);
 
-	dma_sync_single_for_device(&dev->pdev->dev, fmr->dma_handle,
+	dma_sync_single_for_device(&dev->persist->pdev->dev, fmr->dma_handle,
 				   npages * sizeof(u64), DMA_TO_DEVICE);
 
 	fmr->mpt->key    = cpu_to_be32(key);
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 74216071201..a42b4c0a9ed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -151,11 +151,13 @@ int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar)
 		return -ENOMEM;
 
 	if (mlx4_is_slave(dev))
-		offset = uar->index % ((int) pci_resource_len(dev->pdev, 2) /
+		offset = uar->index % ((int)pci_resource_len(dev->persist->pdev,
+							     2) /
 				       dev->caps.uar_page_size);
 	else
 		offset = uar->index;
-	uar->pfn = (pci_resource_start(dev->pdev, 2) >> PAGE_SHIFT) + offset;
+	uar->pfn = (pci_resource_start(dev->persist->pdev, 2) >> PAGE_SHIFT)
+		    + offset;
 	uar->map = NULL;
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 30eb1ead0fe..9f268f05290 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -553,9 +553,9 @@ int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port)
 		slaves_pport_actv = mlx4_phys_to_slaves_pport_actv(
 				    dev, &exclusive_ports);
 		slave_gid -= bitmap_weight(slaves_pport_actv.slaves,
-					   dev->num_vfs + 1);
+					   dev->persist->num_vfs + 1);
 	}
-	vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+	vfs = bitmap_weight(slaves_pport.slaves, dev->persist->num_vfs + 1) - 1;
 	if (slave_gid <= ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) % vfs))
 		return ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / vfs) + 1;
 	return (MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / vfs;
@@ -590,10 +590,10 @@ int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port)
 		slaves_pport_actv = mlx4_phys_to_slaves_pport_actv(
 				    dev, &exclusive_ports);
 		slave_gid -= bitmap_weight(slaves_pport_actv.slaves,
-					   dev->num_vfs + 1);
+					   dev->persist->num_vfs + 1);
 	}
 	gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
-	vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+	vfs = bitmap_weight(slaves_pport.slaves, dev->persist->num_vfs + 1) - 1;
 	if (slave_gid <= gids % vfs)
 		return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave_gid - 1);
 
@@ -644,7 +644,7 @@ void mlx4_reset_roce_gids(struct mlx4_dev *dev, int slave)
 	int num_eth_ports, err;
 	int i;
 
-	if (slave < 0 || slave > dev->num_vfs)
+	if (slave < 0 || slave > dev->persist->num_vfs)
 		return;
 
 	actv_ports = mlx4_get_active_ports(dev, slave);
@@ -1214,7 +1214,8 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
 		return -EINVAL;
 
 	slaves_pport = mlx4_phys_to_slaves_pport(dev, port);
-	num_vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+	num_vfs = bitmap_weight(slaves_pport.slaves,
+				dev->persist->num_vfs + 1) - 1;
 
 	for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
 		if (!memcmp(priv->port[port].gid_table.roce_gids[i].raw, gid,
@@ -1258,7 +1259,7 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
 							dev, &exclusive_ports);
 				num_vfs_before += bitmap_weight(
 						slaves_pport_actv.slaves,
-						dev->num_vfs + 1);
+						dev->persist->num_vfs + 1);
 			}
 
 			/* candidate_slave_gid isn't necessarily the correct slave, but
@@ -1288,7 +1289,7 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
 						dev, &exclusive_ports);
 				slave_gid += bitmap_weight(
 						slaves_pport_actv.slaves,
-						dev->num_vfs + 1);
+						dev->persist->num_vfs + 1);
 			}
 		}
 		*slave_id = slave_gid;
diff --git a/drivers/net/ethernet/mellanox/mlx4/reset.c b/drivers/net/ethernet/mellanox/mlx4/reset.c
index ea1c6d09214..0076d88587c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/reset.c
+++ b/drivers/net/ethernet/mellanox/mlx4/reset.c
@@ -76,19 +76,21 @@ int mlx4_reset(struct mlx4_dev *dev)
 		goto out;
 	}
 
-	pcie_cap = pci_pcie_cap(dev->pdev);
+	pcie_cap = pci_pcie_cap(dev->persist->pdev);
 
 	for (i = 0; i < 64; ++i) {
 		if (i == 22 || i == 23)
 			continue;
-		if (pci_read_config_dword(dev->pdev, i * 4, hca_header + i)) {
+		if (pci_read_config_dword(dev->persist->pdev, i * 4,
+					  hca_header + i)) {
 			err = -ENODEV;
 			mlx4_err(dev, "Couldn't save HCA PCI header, aborting\n");
 			goto out;
 		}
 	}
 
-	reset = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_RESET_BASE,
+	reset = ioremap(pci_resource_start(dev->persist->pdev, 0) +
+			MLX4_RESET_BASE,
 			MLX4_RESET_SIZE);
 	if (!reset) {
 		err = -ENOMEM;
@@ -122,8 +124,8 @@ int mlx4_reset(struct mlx4_dev *dev)
 
 	end = jiffies + MLX4_RESET_TIMEOUT_JIFFIES;
 	do {
-		if (!pci_read_config_word(dev->pdev, PCI_VENDOR_ID, &vendor) &&
-		    vendor != 0xffff)
+		if (!pci_read_config_word(dev->persist->pdev, PCI_VENDOR_ID,
+					  &vendor) && vendor != 0xffff)
 			break;
 
 		msleep(1);
@@ -138,14 +140,16 @@ int mlx4_reset(struct mlx4_dev *dev)
 	/* Now restore the PCI headers */
 	if (pcie_cap) {
 		devctl = hca_header[(pcie_cap + PCI_EXP_DEVCTL) / 4];
-		if (pcie_capability_write_word(dev->pdev, PCI_EXP_DEVCTL,
+		if (pcie_capability_write_word(dev->persist->pdev,
+					       PCI_EXP_DEVCTL,
 					       devctl)) {
 			err = -ENODEV;
 			mlx4_err(dev, "Couldn't restore HCA PCI Express Device Control register, aborting\n");
 			goto out;
 		}
 		linkctl = hca_header[(pcie_cap + PCI_EXP_LNKCTL) / 4];
-		if (pcie_capability_write_word(dev->pdev, PCI_EXP_LNKCTL,
+		if (pcie_capability_write_word(dev->persist->pdev,
+					       PCI_EXP_LNKCTL,
 					       linkctl)) {
 			err = -ENODEV;
 			mlx4_err(dev, "Couldn't restore HCA PCI Express Link control register, aborting\n");
@@ -157,7 +161,8 @@ int mlx4_reset(struct mlx4_dev *dev)
 		if (i * 4 == PCI_COMMAND)
 			continue;
 
-		if (pci_write_config_dword(dev->pdev, i * 4, hca_header[i])) {
+		if (pci_write_config_dword(dev->persist->pdev, i * 4,
+					   hca_header[i])) {
 			err = -ENODEV;
 			mlx4_err(dev, "Couldn't restore HCA reg %x, aborting\n",
 				 i);
@@ -165,7 +170,7 @@ int mlx4_reset(struct mlx4_dev *dev)
 		}
 	}
 
-	if (pci_write_config_dword(dev->pdev, PCI_COMMAND,
+	if (pci_write_config_dword(dev->persist->pdev, PCI_COMMAND,
 				   hca_header[PCI_COMMAND / 4])) {
 		err = -ENODEV;
 		mlx4_err(dev, "Couldn't restore HCA COMMAND, aborting\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 4efbd1eca61..3e93879bccc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -309,12 +309,13 @@ static inline int mlx4_grant_resource(struct mlx4_dev *dev, int slave,
 	int allocated, free, reserved, guaranteed, from_free;
 	int from_rsvd;
 
-	if (slave > dev->num_vfs)
+	if (slave > dev->persist->num_vfs)
 		return -EINVAL;
 
 	spin_lock(&res_alloc->alloc_lock);
 	allocated = (port > 0) ?
-		res_alloc->allocated[(port - 1) * (dev->num_vfs + 1) + slave] :
+		res_alloc->allocated[(port - 1) *
+		(dev->persist->num_vfs + 1) + slave] :
 		res_alloc->allocated[slave];
 	free = (port > 0) ? res_alloc->res_port_free[port - 1] :
 		res_alloc->res_free;
@@ -352,7 +353,8 @@ static inline int mlx4_grant_resource(struct mlx4_dev *dev, int slave,
 	if (!err) {
 		/* grant the request */
 		if (port > 0) {
-			res_alloc->allocated[(port - 1) * (dev->num_vfs + 1) + slave] += count;
+			res_alloc->allocated[(port - 1) *
+			(dev->persist->num_vfs + 1) + slave] += count;
 			res_alloc->res_port_free[port - 1] -= count;
 			res_alloc->res_port_rsvd[port - 1] -= from_rsvd;
 		} else {
@@ -376,13 +378,14 @@ static inline void mlx4_release_resource(struct mlx4_dev *dev, int slave,
 		&priv->mfunc.master.res_tracker.res_alloc[res_type];
 	int allocated, guaranteed, from_rsvd;
 
-	if (slave > dev->num_vfs)
+	if (slave > dev->persist->num_vfs)
 		return;
 
 	spin_lock(&res_alloc->alloc_lock);
 
 	allocated = (port > 0) ?
-		res_alloc->allocated[(port - 1) * (dev->num_vfs + 1) + slave] :
+		res_alloc->allocated[(port - 1) *
+		(dev->persist->num_vfs + 1) + slave] :
 		res_alloc->allocated[slave];
 	guaranteed = res_alloc->guaranteed[slave];
 
@@ -397,7 +400,8 @@ static inline void mlx4_release_resource(struct mlx4_dev *dev, int slave,
 	}
 
 	if (port > 0) {
-		res_alloc->allocated[(port - 1) * (dev->num_vfs + 1) + slave] -= count;
+		res_alloc->allocated[(port - 1) *
+		(dev->persist->num_vfs + 1) + slave] -= count;
 		res_alloc->res_port_free[port - 1] += count;
 		res_alloc->res_port_rsvd[port - 1] += from_rsvd;
 	} else {
@@ -415,7 +419,8 @@ static inline void initialize_res_quotas(struct mlx4_dev *dev,
 					 enum mlx4_resource res_type,
 					 int vf, int num_instances)
 {
-	res_alloc->guaranteed[vf] = num_instances / (2 * (dev->num_vfs + 1));
+	res_alloc->guaranteed[vf] = num_instances /
+				    (2 * (dev->persist->num_vfs + 1));
 	res_alloc->quota[vf] = (num_instances / 2) + res_alloc->guaranteed[vf];
 	if (vf == mlx4_master_func_num(dev)) {
 		res_alloc->res_free = num_instances;
@@ -486,21 +491,26 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 	for (i = 0; i < MLX4_NUM_OF_RESOURCE_TYPE; i++) {
 		struct resource_allocator *res_alloc =
 			&priv->mfunc.master.res_tracker.res_alloc[i];
-		res_alloc->quota = kmalloc((dev->num_vfs + 1) * sizeof(int), GFP_KERNEL);
-		res_alloc->guaranteed = kmalloc((dev->num_vfs + 1) * sizeof(int), GFP_KERNEL);
+		res_alloc->quota = kmalloc((dev->persist->num_vfs + 1) *
+					   sizeof(int), GFP_KERNEL);
+		res_alloc->guaranteed = kmalloc((dev->persist->num_vfs + 1) *
+						sizeof(int), GFP_KERNEL);
 		if (i == RES_MAC || i == RES_VLAN)
 			res_alloc->allocated = kzalloc(MLX4_MAX_PORTS *
-						       (dev->num_vfs + 1) * sizeof(int),
-							GFP_KERNEL);
+						       (dev->persist->num_vfs
+						       + 1) *
+						       sizeof(int), GFP_KERNEL);
 		else
-			res_alloc->allocated = kzalloc((dev->num_vfs + 1) * sizeof(int), GFP_KERNEL);
+			res_alloc->allocated = kzalloc((dev->persist->
+							num_vfs + 1) *
+						       sizeof(int), GFP_KERNEL);
 
 		if (!res_alloc->quota || !res_alloc->guaranteed ||
 		    !res_alloc->allocated)
 			goto no_mem_err;
 
 		spin_lock_init(&res_alloc->alloc_lock);
-		for (t = 0; t < dev->num_vfs + 1; t++) {
+		for (t = 0; t < dev->persist->num_vfs + 1; t++) {
 			struct mlx4_active_ports actv_ports =
 				mlx4_get_active_ports(dev, t);
 			switch (i) {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f1e41b33462..1069ce65e8b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -744,8 +744,15 @@ struct mlx4_vf_dev {
 	u8			n_ports;
 };
 
-struct mlx4_dev {
+struct mlx4_dev_persistent {
 	struct pci_dev	       *pdev;
+	struct mlx4_dev	       *dev;
+	int                     nvfs[MLX4_MAX_PORTS + 1];
+	int			num_vfs;
+};
+
+struct mlx4_dev {
+	struct mlx4_dev_persistent *persist;
 	unsigned long		flags;
 	unsigned long		num_slaves;
 	struct mlx4_caps	caps;
@@ -754,13 +761,11 @@ struct mlx4_dev {
 	struct radix_tree_root	qp_table_tree;
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
-	int			num_vfs;
 	int			numa_node;
 	int			oper_log_mgm_entry_size;
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
 	struct mlx4_vf_dev     *dev_vfs;
-	int                     nvfs[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_eqe {
-- 
cgit v1.2.3-70-g09d2


From dd0eefe3abbf47442db296bf68f27eb2860c1cdf Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 25 Jan 2015 16:59:36 +0200
Subject: net/mlx4_core: Set device configuration data to be persistent across
 reset

When an HCA enters an internal error state, this is detected by the driver.
The driver then should reset the HCA and restart the software stack.

Keep ports information and some SRIOV configuration in a persistent area
to have it valid across reset.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 45 +++++++++++++++++++++++++++++--
 include/linux/mlx4/device.h               |  2 ++
 2 files changed, 45 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index abcee61f8a4..2c5a555dff8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3109,18 +3109,34 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ret;
 }
 
+static void mlx4_clean_dev(struct mlx4_dev *dev)
+{
+	struct mlx4_dev_persistent *persist = dev->persist;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	memset(priv, 0, sizeof(*priv));
+	priv->dev.persist = persist;
+}
+
 static void mlx4_unload_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
 	struct mlx4_dev  *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int               pci_dev_data;
-	int p;
+	int p, i;
 	int active_vfs = 0;
 
 	if (priv->removed)
 		return;
 
+	/* saving current ports type for further use */
+	for (i = 0; i < dev->caps.num_ports; i++) {
+		dev->persist->curr_port_type[i] = dev->caps.port_type[i + 1];
+		dev->persist->curr_port_poss_type[i] = dev->caps.
+						       possible_type[i + 1];
+	}
+
 	pci_dev_data = priv->pci_dev_data;
 
 	/* Disabling SR-IOV is not allowed while there are active vf's */
@@ -3191,7 +3207,7 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 	kfree(dev->caps.qp1_proxy);
 	kfree(dev->dev_vfs);
 
-	memset(priv, 0, sizeof(*priv));
+	mlx4_clean_dev(dev);
 	priv->pci_dev_data = pci_dev_data;
 	priv->removed = 1;
 }
@@ -3210,6 +3226,25 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, NULL);
 }
 
+static int restore_current_port_types(struct mlx4_dev *dev,
+				      enum mlx4_port_type *types,
+				      enum mlx4_port_type *poss_types)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int err, i;
+
+	mlx4_stop_sense(dev);
+
+	mutex_lock(&priv->port_mutex);
+	for (i = 0; i < dev->caps.num_ports; i++)
+		dev->caps.possible_type[i + 1] = poss_types[i];
+	err = mlx4_change_port_types(dev, types);
+	mlx4_start_sense(dev);
+	mutex_unlock(&priv->port_mutex);
+
+	return err;
+}
+
 int mlx4_restart_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
@@ -3230,6 +3265,12 @@ int mlx4_restart_one(struct pci_dev *pdev)
 		return err;
 	}
 
+	err = restore_current_port_types(dev, dev->persist->curr_port_type,
+					 dev->persist->curr_port_poss_type);
+	if (err)
+		mlx4_err(dev, "could not restore original port types (%d)\n",
+			 err);
+
 	return err;
 }
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 1069ce65e8b..8c3837ac1a2 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -749,6 +749,8 @@ struct mlx4_dev_persistent {
 	struct mlx4_dev	       *dev;
 	int                     nvfs[MLX4_MAX_PORTS + 1];
 	int			num_vfs;
+	enum mlx4_port_type curr_port_type[MLX4_MAX_PORTS + 1];
+	enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_dev {
-- 
cgit v1.2.3-70-g09d2


From ad9a0bf08ffbf32b8f292c3bb78ca0f24bb8f6b2 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 25 Jan 2015 16:59:37 +0200
Subject: net/mlx4_core: Refactor the catas flow to work per device

Using a WQ per device instead of a single global WQ, this allows
independent reset handling per device even when SRIOV is used.

This comes as a pre-patch for supporting chip reset
for both native and SRIOV.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/catas.c | 75 ++++++++++++++----------------
 drivers/net/ethernet/mellanox/mlx4/main.c  | 12 ++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h  |  3 +-
 include/linux/mlx4/device.h                |  2 +
 4 files changed, 48 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 1a102c9bac9..5bb9aa6e281 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -40,10 +40,7 @@ enum {
 	MLX4_CATAS_POLL_INTERVAL	= 5 * HZ,
 };
 
-static DEFINE_SPINLOCK(catas_lock);
 
-static LIST_HEAD(catas_list);
-static struct work_struct catas_work;
 
 static int internal_err_reset = 1;
 module_param(internal_err_reset, int, 0644);
@@ -77,13 +74,9 @@ static void poll_catas(unsigned long dev_ptr)
 			dump_err_buf(dev);
 			mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
 
-			if (internal_err_reset) {
-				spin_lock(&catas_lock);
-				list_add(&priv->catas_err.list, &catas_list);
-				spin_unlock(&catas_lock);
-
-				queue_work(mlx4_wq, &catas_work);
-			}
+			if (internal_err_reset)
+				queue_work(dev->persist->catas_wq,
+					   &dev->persist->catas_work);
 		}
 	} else
 		mod_timer(&priv->catas_err.timer,
@@ -92,34 +85,23 @@ static void poll_catas(unsigned long dev_ptr)
 
 static void catas_reset(struct work_struct *work)
 {
-	struct mlx4_priv *priv, *tmppriv;
-	struct mlx4_dev *dev;
-	struct mlx4_dev_persistent *persist;
-
-	LIST_HEAD(tlist);
+	struct mlx4_dev_persistent *persist =
+		container_of(work, struct mlx4_dev_persistent,
+			     catas_work);
+	struct pci_dev *pdev = persist->pdev;
 	int ret;
 
-	spin_lock_irq(&catas_lock);
-	list_splice_init(&catas_list, &tlist);
-	spin_unlock_irq(&catas_lock);
-
-	list_for_each_entry_safe(priv, tmppriv, &tlist, catas_err.list) {
-		struct pci_dev *pdev = priv->dev.persist->pdev;
-
-		/* If the device is off-line, we cannot reset it */
-		if (pci_channel_offline(pdev))
-			continue;
+	/* If the device is off-line, we cannot reset it */
+	if (pci_channel_offline(pdev))
+		return;
 
-		ret = mlx4_restart_one(priv->dev.persist->pdev);
-		/* 'priv' now is not valid */
-		if (ret)
-			pr_err("mlx4 %s: Reset failed (%d)\n",
-			       pci_name(pdev), ret);
-		else {
-			persist  = pci_get_drvdata(pdev);
-			mlx4_dbg(persist->dev, "Reset succeeded\n");
-		}
-	}
+	ret = mlx4_restart_one(pdev);
+	/* 'priv' now is not valid */
+	if (ret)
+		pr_err("mlx4 %s: Reset failed (%d)\n",
+		       pci_name(pdev), ret);
+	else
+		mlx4_dbg(persist->dev, "Reset succeeded\n");
 }
 
 void mlx4_start_catas_poll(struct mlx4_dev *dev)
@@ -158,15 +140,26 @@ void mlx4_stop_catas_poll(struct mlx4_dev *dev)
 
 	del_timer_sync(&priv->catas_err.timer);
 
-	if (priv->catas_err.map)
+	if (priv->catas_err.map) {
 		iounmap(priv->catas_err.map);
+		priv->catas_err.map = NULL;
+	}
+}
 
-	spin_lock_irq(&catas_lock);
-	list_del(&priv->catas_err.list);
-	spin_unlock_irq(&catas_lock);
+int  mlx4_catas_init(struct mlx4_dev *dev)
+{
+	INIT_WORK(&dev->persist->catas_work, catas_reset);
+	dev->persist->catas_wq = create_singlethread_workqueue("mlx4_health");
+	if (!dev->persist->catas_wq)
+		return -ENOMEM;
+
+	return 0;
 }
 
-void  __init mlx4_catas_init(void)
+void mlx4_catas_end(struct mlx4_dev *dev)
 {
-	INIT_WORK(&catas_work, catas_reset);
+	if (dev->persist->catas_wq) {
+		destroy_workqueue(dev->persist->catas_wq);
+		dev->persist->catas_wq = NULL;
+	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 2c5a555dff8..a61694cc147 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3064,11 +3064,19 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 		}
 	}
 
-	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv);
+	err = mlx4_catas_init(&priv->dev);
 	if (err)
 		goto err_release_regions;
+
+	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv);
+	if (err)
+		goto err_catas;
+
 	return 0;
 
+err_catas:
+	mlx4_catas_end(&priv->dev);
+
 err_release_regions:
 	pci_release_regions(pdev);
 
@@ -3219,6 +3227,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	mlx4_unload_one(pdev);
+	mlx4_catas_end(dev);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 	kfree(dev->persist);
@@ -3403,7 +3412,6 @@ static int __init mlx4_init(void)
 	if (mlx4_verify_params())
 		return -EINVAL;
 
-	mlx4_catas_init();
 
 	mlx4_wq = create_singlethread_workqueue("mlx4");
 	if (!mlx4_wq)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index faa37ab75a9..d41af84f965 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -995,7 +995,8 @@ void __mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn);
 
 void mlx4_start_catas_poll(struct mlx4_dev *dev);
 void mlx4_stop_catas_poll(struct mlx4_dev *dev);
-void mlx4_catas_init(void);
+int mlx4_catas_init(struct mlx4_dev *dev);
+void mlx4_catas_end(struct mlx4_dev *dev);
 int mlx4_restart_one(struct pci_dev *pdev);
 int mlx4_register_device(struct mlx4_dev *dev);
 void mlx4_unregister_device(struct mlx4_dev *dev);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 8c3837ac1a2..da425d2f370 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -751,6 +751,8 @@ struct mlx4_dev_persistent {
 	int			num_vfs;
 	enum mlx4_port_type curr_port_type[MLX4_MAX_PORTS + 1];
 	enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1];
+	struct work_struct      catas_work;
+	struct workqueue_struct *catas_wq;
 };
 
 struct mlx4_dev {
-- 
cgit v1.2.3-70-g09d2


From f6bc11e42646e661e699a5593cbd1e9dba7191d0 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 25 Jan 2015 16:59:38 +0200
Subject: net/mlx4_core: Enhance the catas flow to support device reset

This includes:

- resetting the chip when a fatal error is detected (the current code
  does not do this).

- exposing the ability to enter error state from outside the catas code
  by calling its functionality. (E.g. FW Command timeout, AER error).

- managing a persistent device state. This is needed to sync between
  reset flow cases.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/catas.c | 122 ++++++++++++++++++++++-------
 drivers/net/ethernet/mellanox/mlx4/main.c  |   6 ++
 drivers/net/ethernet/mellanox/mlx4/mlx4.h  |   2 +-
 include/linux/mlx4/device.h                |   7 ++
 4 files changed, 108 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 5bb9aa6e281..588d6b5e121 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -48,6 +48,83 @@ MODULE_PARM_DESC(internal_err_reset,
 		 "Reset device on internal errors if non-zero"
 		 " (default 1, in SRIOV mode default is 0)");
 
+static int read_vendor_id(struct mlx4_dev *dev)
+{
+	u16 vendor_id = 0;
+	int ret;
+
+	ret = pci_read_config_word(dev->persist->pdev, 0, &vendor_id);
+	if (ret) {
+		mlx4_err(dev, "Failed to read vendor ID, ret=%d\n", ret);
+		return ret;
+	}
+
+	if (vendor_id == 0xffff) {
+		mlx4_err(dev, "PCI can't be accessed to read vendor id\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int mlx4_reset_master(struct mlx4_dev *dev)
+{
+	int err = 0;
+
+	if (!pci_channel_offline(dev->persist->pdev)) {
+		err = read_vendor_id(dev);
+		/* If PCI can't be accessed to read vendor ID we assume that its
+		 * link was disabled and chip was already reset.
+		 */
+		if (err)
+			return 0;
+
+		err = mlx4_reset(dev);
+		if (err)
+			mlx4_err(dev, "Fail to reset HCA\n");
+	}
+
+	return err;
+}
+
+void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
+{
+	int err;
+	struct mlx4_dev *dev;
+
+	if (!internal_err_reset)
+		return;
+
+	mutex_lock(&persist->device_state_mutex);
+	if (persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)
+		goto out;
+
+	dev = persist->dev;
+	mlx4_err(dev, "device is going to be reset\n");
+	err = mlx4_reset_master(dev);
+	BUG_ON(err != 0);
+
+	dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR;
+	mlx4_err(dev, "device was reset successfully\n");
+	mutex_unlock(&persist->device_state_mutex);
+
+	/* At that step HW was already reset, now notify clients */
+	mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
+	return;
+
+out:
+	mutex_unlock(&persist->device_state_mutex);
+}
+
+static void mlx4_handle_error_state(struct mlx4_dev_persistent *persist)
+{
+	int err = 0;
+
+	mlx4_enter_error_state(persist);
+	err = mlx4_restart_one(persist->pdev);
+	mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n", err);
+}
+
 static void dump_err_buf(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -66,21 +143,22 @@ static void poll_catas(unsigned long dev_ptr)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	if (readl(priv->catas_err.map)) {
-		/* If the device is off-line, we cannot try to recover it */
-		if (pci_channel_offline(dev->persist->pdev))
-			mod_timer(&priv->catas_err.timer,
-				  round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
-		else {
-			dump_err_buf(dev);
-			mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
-
-			if (internal_err_reset)
-				queue_work(dev->persist->catas_wq,
-					   &dev->persist->catas_work);
-		}
-	} else
-		mod_timer(&priv->catas_err.timer,
-			  round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
+		dump_err_buf(dev);
+		goto internal_err;
+	}
+
+	if (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
+		mlx4_warn(dev, "Internal error mark was detected on device\n");
+		goto internal_err;
+	}
+
+	mod_timer(&priv->catas_err.timer,
+		  round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
+	return;
+
+internal_err:
+	if (internal_err_reset)
+		queue_work(dev->persist->catas_wq, &dev->persist->catas_work);
 }
 
 static void catas_reset(struct work_struct *work)
@@ -88,20 +166,8 @@ static void catas_reset(struct work_struct *work)
 	struct mlx4_dev_persistent *persist =
 		container_of(work, struct mlx4_dev_persistent,
 			     catas_work);
-	struct pci_dev *pdev = persist->pdev;
-	int ret;
-
-	/* If the device is off-line, we cannot reset it */
-	if (pci_channel_offline(pdev))
-		return;
 
-	ret = mlx4_restart_one(pdev);
-	/* 'priv' now is not valid */
-	if (ret)
-		pr_err("mlx4 %s: Reset failed (%d)\n",
-		       pci_name(pdev), ret);
-	else
-		mlx4_dbg(persist->dev, "Reset succeeded\n");
+	mlx4_handle_error_state(persist);
 }
 
 void mlx4_start_catas_poll(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index a61694cc147..dc2d910fcc8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2624,6 +2624,11 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 		}
 	}
 
+	/* on load remove any previous indication of internal error,
+	 * device is up.
+	 */
+	dev->persist->state = MLX4_DEVICE_STATE_UP;
+
 slave_start:
 	err = mlx4_cmd_init(dev);
 	if (err) {
@@ -3108,6 +3113,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev->persist->dev = dev;
 	pci_set_drvdata(pdev, dev->persist);
 	priv->pci_dev_data = id->driver_data;
+	mutex_init(&dev->persist->device_state_mutex);
 
 	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
 	if (ret) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index d41af84f965..aa1ecbc5a60 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1178,7 +1178,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type);
 
 void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
 
-void mlx4_handle_catas_err(struct mlx4_dev *dev);
+void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
 
 int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
 		    enum mlx4_port_type *type);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index da425d2f370..7d5d317cb7a 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -411,6 +411,11 @@ enum {
 	MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK	= 1 << 4,
 };
 
+enum {
+	MLX4_DEVICE_STATE_UP			= 1 << 0,
+	MLX4_DEVICE_STATE_INTERNAL_ERROR	= 1 << 1,
+};
+
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
 			     MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK)
 
@@ -753,6 +758,8 @@ struct mlx4_dev_persistent {
 	enum mlx4_port_type curr_port_poss_type[MLX4_MAX_PORTS + 1];
 	struct work_struct      catas_work;
 	struct workqueue_struct *catas_wq;
+	struct mutex	device_state_mutex; /* protect HW state */
+	u8		state;
 };
 
 struct mlx4_dev {
-- 
cgit v1.2.3-70-g09d2


From f5aef5aa35063f2b45c3605871cd525d0cb7fb7a Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 25 Jan 2015 16:59:39 +0200
Subject: net/mlx4_core: Activate reset flow upon fatal command cases

We activate reset flow upon command fatal errors, when the device enters an
erroneous state, and must be reset.

The cases below are assumed to be fatal: FW command timed-out, an error from FW
on closing commands, pci is offline when posting/pending a command.

In those cases we place the device into an error state: chip is reset, pending
commands are awakened and completed immediately. Subsequent commands will
return immediately.

The return code in the above cases will depend on the command. Commands which
free and close resources will return success (because the chip was reset, so
callers may safely free their kernel resources). Other commands will return -EIO.

Since the device's state was marked as error, the catas poller will
detect this and restart the device's software stack (as is done when a FW
internal error is directly detected). The device state is protected by a
persistent mutex lives on its mlx4_dev, as such no need any more for the
hcr_mutex which is removed.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/catas.c |  11 +-
 drivers/net/ethernet/mellanox/mlx4/cmd.c   | 163 +++++++++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlx4/mcg.c   |   3 +
 drivers/net/ethernet/mellanox/mlx4/mlx4.h  |   2 +-
 include/linux/mlx4/cmd.h                   |   1 +
 5 files changed, 153 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 588d6b5e121..63f14ffcc90 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -42,8 +42,8 @@ enum {
 
 
 
-static int internal_err_reset = 1;
-module_param(internal_err_reset, int, 0644);
+int mlx4_internal_err_reset = 1;
+module_param_named(internal_err_reset, mlx4_internal_err_reset,  int, 0644);
 MODULE_PARM_DESC(internal_err_reset,
 		 "Reset device on internal errors if non-zero"
 		 " (default 1, in SRIOV mode default is 0)");
@@ -92,7 +92,7 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 	int err;
 	struct mlx4_dev *dev;
 
-	if (!internal_err_reset)
+	if (!mlx4_internal_err_reset)
 		return;
 
 	mutex_lock(&persist->device_state_mutex);
@@ -110,6 +110,7 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 
 	/* At that step HW was already reset, now notify clients */
 	mlx4_dispatch_event(dev, MLX4_DEV_EVENT_CATASTROPHIC_ERROR, 0);
+	mlx4_cmd_wake_completions(dev);
 	return;
 
 out:
@@ -157,7 +158,7 @@ static void poll_catas(unsigned long dev_ptr)
 	return;
 
 internal_err:
-	if (internal_err_reset)
+	if (mlx4_internal_err_reset)
 		queue_work(dev->persist->catas_wq, &dev->persist->catas_work);
 }
 
@@ -177,7 +178,7 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 
 	/*If we are in SRIOV the default of the module param must be 0*/
 	if (mlx4_is_mfunc(dev))
-		internal_err_reset = 0;
+		mlx4_internal_err_reset = 0;
 
 	INIT_LIST_HEAD(&priv->catas_err.list);
 	init_timer(&priv->catas_err.timer);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 7cd90e6a427..3895b2b5fc9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -182,6 +182,72 @@ static u8 mlx4_errno_to_status(int errno)
 	}
 }
 
+static int mlx4_internal_err_ret_value(struct mlx4_dev *dev, u16 op,
+				       u8 op_modifier)
+{
+	switch (op) {
+	case MLX4_CMD_UNMAP_ICM:
+	case MLX4_CMD_UNMAP_ICM_AUX:
+	case MLX4_CMD_UNMAP_FA:
+	case MLX4_CMD_2RST_QP:
+	case MLX4_CMD_HW2SW_EQ:
+	case MLX4_CMD_HW2SW_CQ:
+	case MLX4_CMD_HW2SW_SRQ:
+	case MLX4_CMD_HW2SW_MPT:
+	case MLX4_CMD_CLOSE_HCA:
+	case MLX4_QP_FLOW_STEERING_DETACH:
+	case MLX4_CMD_FREE_RES:
+	case MLX4_CMD_CLOSE_PORT:
+		return CMD_STAT_OK;
+
+	case MLX4_CMD_QP_ATTACH:
+		/* On Detach case return success */
+		if (op_modifier == 0)
+			return CMD_STAT_OK;
+		return mlx4_status_to_errno(CMD_STAT_INTERNAL_ERR);
+
+	default:
+		return mlx4_status_to_errno(CMD_STAT_INTERNAL_ERR);
+	}
+}
+
+static int mlx4_closing_cmd_fatal_error(u16 op, u8 fw_status)
+{
+	/* Any error during the closing commands below is considered fatal */
+	if (op == MLX4_CMD_CLOSE_HCA ||
+	    op == MLX4_CMD_HW2SW_EQ ||
+	    op == MLX4_CMD_HW2SW_CQ ||
+	    op == MLX4_CMD_2RST_QP ||
+	    op == MLX4_CMD_HW2SW_SRQ ||
+	    op == MLX4_CMD_SYNC_TPT ||
+	    op == MLX4_CMD_UNMAP_ICM ||
+	    op == MLX4_CMD_UNMAP_ICM_AUX ||
+	    op == MLX4_CMD_UNMAP_FA)
+		return 1;
+	/* Error on MLX4_CMD_HW2SW_MPT is fatal except when fw status equals
+	  * CMD_STAT_REG_BOUND.
+	  * This status indicates that memory region has memory windows bound to it
+	  * which may result from invalid user space usage and is not fatal.
+	  */
+	if (op == MLX4_CMD_HW2SW_MPT && fw_status != CMD_STAT_REG_BOUND)
+		return 1;
+	return 0;
+}
+
+static int mlx4_cmd_reset_flow(struct mlx4_dev *dev, u16 op, u8 op_modifier,
+			       int err)
+{
+	/* Only if reset flow is really active return code is based on
+	  * command, otherwise current error code is returned.
+	  */
+	if (mlx4_internal_err_reset) {
+		mlx4_enter_error_state(dev->persist);
+		err = mlx4_internal_err_ret_value(dev, op, op_modifier);
+	}
+
+	return err;
+}
+
 static int comm_pending(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -258,7 +324,7 @@ static int mlx4_comm_cmd_wait(struct mlx4_dev *dev, u8 op,
 	cmd->free_head = context->next;
 	spin_unlock(&cmd->context_lock);
 
-	init_completion(&context->done);
+	reinit_completion(&context->done);
 
 	mlx4_comm_cmd_post(dev, op, param);
 
@@ -323,17 +389,21 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 {
 	struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
 	u32 __iomem *hcr = cmd->hcr;
-	int ret = -EAGAIN;
+	int ret = -EIO;
 	unsigned long end;
 
-	mutex_lock(&cmd->hcr_mutex);
-
-	if (pci_channel_offline(dev->persist->pdev)) {
+	mutex_lock(&dev->persist->device_state_mutex);
+	/* To avoid writing to unknown addresses after the device state was
+	  * changed to internal error and the chip was reset,
+	  * check the INTERNAL_ERROR flag which is updated under
+	  * device_state_mutex lock.
+	  */
+	if (pci_channel_offline(dev->persist->pdev) ||
+	    (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)) {
 		/*
 		 * Device is going through error recovery
 		 * and cannot accept commands.
 		 */
-		ret = -EIO;
 		goto out;
 	}
 
@@ -347,7 +417,6 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 			 * Device is going through error recovery
 			 * and cannot accept commands.
 			 */
-			ret = -EIO;
 			goto out;
 		}
 
@@ -391,7 +460,11 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 	ret = 0;
 
 out:
-	mutex_unlock(&cmd->hcr_mutex);
+	if (ret)
+		mlx4_warn(dev, "Could not post command 0x%x: ret=%d, in_param=0x%llx, in_mod=0x%x, op_mod=0x%x\n",
+			  op, ret, in_param, in_modifier, op_modifier);
+	mutex_unlock(&dev->persist->device_state_mutex);
+
 	return ret;
 }
 
@@ -464,12 +537,12 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 
 	down(&priv->cmd.poll_sem);
 
-	if (pci_channel_offline(dev->persist->pdev)) {
+	if (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
 		/*
 		 * Device is going through error recovery
 		 * and cannot accept commands.
 		 */
-		err = -EIO;
+		err = mlx4_internal_err_ret_value(dev, op, op_modifier);
 		goto out;
 	}
 
@@ -483,7 +556,7 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	err = mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
 			    in_modifier, op_modifier, op, CMD_POLL_TOKEN, 0);
 	if (err)
-		goto out;
+		goto out_reset;
 
 	end = msecs_to_jiffies(timeout) + jiffies;
 	while (cmd_pending(dev) && time_before(jiffies, end)) {
@@ -493,6 +566,11 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 			 * and cannot accept commands.
 			 */
 			err = -EIO;
+			goto out_reset;
+		}
+
+		if (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
+			err = mlx4_internal_err_ret_value(dev, op, op_modifier);
 			goto out;
 		}
 
@@ -502,8 +580,8 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	if (cmd_pending(dev)) {
 		mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
 			  op);
-		err = -ETIMEDOUT;
-		goto out;
+		err = -EIO;
+		goto out_reset;
 	}
 
 	if (out_is_imm)
@@ -515,10 +593,17 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	stat = be32_to_cpu((__force __be32)
 			   __raw_readl(hcr + HCR_STATUS_OFFSET)) >> 24;
 	err = mlx4_status_to_errno(stat);
-	if (err)
+	if (err) {
 		mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
 			 op, stat);
+		if (mlx4_closing_cmd_fatal_error(op, stat))
+			goto out_reset;
+		goto out;
+	}
 
+out_reset:
+	if (err)
+		err = mlx4_cmd_reset_flow(dev, op, op_modifier, err);
 out:
 	up(&priv->cmd.poll_sem);
 	return err;
@@ -565,17 +650,19 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 		goto out;
 	}
 
-	init_completion(&context->done);
+	reinit_completion(&context->done);
 
-	mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
-		      in_modifier, op_modifier, op, context->token, 1);
+	err = mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
+			    in_modifier, op_modifier, op, context->token, 1);
+	if (err)
+		goto out_reset;
 
 	if (!wait_for_completion_timeout(&context->done,
 					 msecs_to_jiffies(timeout))) {
 		mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
 			  op);
-		err = -EBUSY;
-		goto out;
+		err = -EIO;
+		goto out_reset;
 	}
 
 	err = context->result;
@@ -592,12 +679,20 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 		else
 			mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
 				 op, context->fw_status);
+		if (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)
+			err = mlx4_internal_err_ret_value(dev, op, op_modifier);
+		else if (mlx4_closing_cmd_fatal_error(op, context->fw_status))
+			goto out_reset;
+
 		goto out;
 	}
 
 	if (out_is_imm)
 		*out_param = context->out_param;
 
+out_reset:
+	if (err)
+		err = mlx4_cmd_reset_flow(dev, op, op_modifier, err);
 out:
 	spin_lock(&cmd->context_lock);
 	context->next = cmd->free_head;
@@ -613,9 +708,12 @@ int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	       u16 op, unsigned long timeout, int native)
 {
 	if (pci_channel_offline(dev->persist->pdev))
-		return -EIO;
+		return mlx4_cmd_reset_flow(dev, op, op_modifier, -EIO);
 
 	if (!mlx4_is_mfunc(dev) || (native && mlx4_is_master(dev))) {
+		if (dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)
+			return mlx4_internal_err_ret_value(dev, op,
+							  op_modifier);
 		if (mlx4_priv(dev)->cmd.use_events)
 			return mlx4_cmd_wait(dev, in_param, out_param,
 					     out_is_imm, in_modifier,
@@ -2121,7 +2219,6 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 	int flags = 0;
 
 	if (!priv->cmd.initialized) {
-		mutex_init(&priv->cmd.hcr_mutex);
 		mutex_init(&priv->cmd.slave_cmd_mutex);
 		sema_init(&priv->cmd.poll_sem, 1);
 		priv->cmd.use_events = 0;
@@ -2232,6 +2329,11 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	for (i = 0; i < priv->cmd.max_cmds; ++i) {
 		priv->cmd.context[i].token = i;
 		priv->cmd.context[i].next  = i + 1;
+		/* To support fatal error flow, initialize all
+		 * cmd contexts to allow simulating completions
+		 * with complete() at any time.
+		 */
+		init_completion(&priv->cmd.context[i].done);
 	}
 
 	priv->cmd.context[priv->cmd.max_cmds - 1].next = -1;
@@ -2329,6 +2431,25 @@ int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave)
 	return slave - 1;
 }
 
+void mlx4_cmd_wake_completions(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cmd_context *context;
+	int i;
+
+	spin_lock(&priv->cmd.context_lock);
+	if (priv->cmd.context) {
+		for (i = 0; i < priv->cmd.max_cmds; ++i) {
+			context = &priv->cmd.context[i];
+			context->fw_status = CMD_STAT_INTERNAL_ERR;
+			context->result    =
+				mlx4_status_to_errno(CMD_STAT_INTERNAL_ERR);
+			complete(&context->done);
+		}
+	}
+	spin_unlock(&priv->cmd.context_lock);
+}
+
 struct mlx4_active_ports mlx4_get_active_ports(struct mlx4_dev *dev, int slave)
 {
 	struct mlx4_active_ports actv_ports;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index a3867e7ef88..d22d9283d2c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1318,6 +1318,9 @@ out:
 	mutex_unlock(&priv->mcg_table.mutex);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
+	if (err && dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)
+		/* In case device is under an error, return success as a closing command */
+		err = 0;
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index aa1ecbc5a60..5c772ea4473 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -235,6 +235,7 @@ do {									\
 
 extern int mlx4_log_num_mgm_entry_size;
 extern int log_mtts_per_seg;
+extern int mlx4_internal_err_reset;
 
 #define MLX4_MAX_NUM_SLAVES	(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF)
 #define ALL_SLAVES 0xff
@@ -607,7 +608,6 @@ struct mlx4_mgm {
 struct mlx4_cmd {
 	struct pci_pool	       *pool;
 	void __iomem	       *hcr;
-	struct mutex		hcr_mutex;
 	struct mutex		slave_cmd_mutex;
 	struct semaphore	poll_sem;
 	struct semaphore	event_sem;
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 64d25941b32..e7543844cc7 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -279,6 +279,7 @@ int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_in
 int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state);
 int mlx4_config_dev_retrieval(struct mlx4_dev *dev,
 			      struct mlx4_config_dev_params *params);
+void mlx4_cmd_wake_completions(struct mlx4_dev *dev);
 /*
  * mlx4_get_slave_default_vlan -
  * return true if VST ( default vlan)
-- 
cgit v1.2.3-70-g09d2


From c69453e294c9f16da977b68e658a8028b854c209 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 25 Jan 2015 16:59:40 +0200
Subject: net/mlx4_core: Manage interface state for Reset flow cases

We need to manage interface state to sync between reset flow and some other
relative cases such as remove_one. This has to be done to prevent certain
races. For example in case software stack is down as a result of unload call,
the remove_one should skip the unload phase.

Implement the remove_one case, handling AER and other cases comes next.

The interface can be up/down, upon remove_one, the state will include an extra
bit indicating that the device is cleaned-up, forcing other tasks to finish
before the final cleanup.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/catas.c | 13 +++++++++++--
 drivers/net/ethernet/mellanox/mlx4/intf.c  |  2 ++
 drivers/net/ethernet/mellanox/mlx4/main.c  | 13 ++++++++++++-
 include/linux/mlx4/device.h                |  7 +++++++
 4 files changed, 32 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 63f14ffcc90..3fcf3cfaedf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -122,8 +122,14 @@ static void mlx4_handle_error_state(struct mlx4_dev_persistent *persist)
 	int err = 0;
 
 	mlx4_enter_error_state(persist);
-	err = mlx4_restart_one(persist->pdev);
-	mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n", err);
+	mutex_lock(&persist->interface_state_mutex);
+	if (persist->interface_state & MLX4_INTERFACE_STATE_UP &&
+	    !(persist->interface_state & MLX4_INTERFACE_STATE_DELETION)) {
+		err = mlx4_restart_one(persist->pdev);
+		mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n",
+			  err);
+	}
+	mutex_unlock(&persist->interface_state_mutex);
 }
 
 static void dump_err_buf(struct mlx4_dev *dev)
@@ -211,6 +217,9 @@ void mlx4_stop_catas_poll(struct mlx4_dev *dev)
 		iounmap(priv->catas_err.map);
 		priv->catas_err.map = NULL;
 	}
+
+	if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION)
+		flush_workqueue(dev->persist->catas_wq);
 }
 
 int  mlx4_catas_init(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 116895ac8b3..fba0b96a6f2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -138,6 +138,7 @@ int mlx4_register_device(struct mlx4_dev *dev)
 
 	mutex_lock(&intf_mutex);
 
+	dev->persist->interface_state |= MLX4_INTERFACE_STATE_UP;
 	list_add_tail(&priv->dev_list, &dev_list);
 	list_for_each_entry(intf, &intf_list, list)
 		mlx4_add_device(intf, priv);
@@ -162,6 +163,7 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 		mlx4_remove_device(intf, priv);
 
 	list_del(&priv->dev_list);
+	dev->persist->interface_state &= ~MLX4_INTERFACE_STATE_UP;
 
 	mutex_unlock(&intf_mutex);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index dc2d910fcc8..d59cae5da3f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3114,6 +3114,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_set_drvdata(pdev, dev->persist);
 	priv->pci_dev_data = id->driver_data;
 	mutex_init(&dev->persist->device_state_mutex);
+	mutex_init(&dev->persist->interface_state_mutex);
 
 	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
 	if (ret) {
@@ -3232,7 +3233,17 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct mlx4_dev  *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
-	mlx4_unload_one(pdev);
+	mutex_lock(&persist->interface_state_mutex);
+	persist->interface_state |= MLX4_INTERFACE_STATE_DELETION;
+	mutex_unlock(&persist->interface_state_mutex);
+
+	/* device marked to be under deletion running now without the lock
+	 * letting other tasks to be terminated
+	 */
+	if (persist->interface_state & MLX4_INTERFACE_STATE_UP)
+		mlx4_unload_one(pdev);
+	else
+		mlx4_info(dev, "%s: interface is down\n", __func__);
 	mlx4_catas_end(dev);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 7d5d317cb7a..33f9ca71925 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -416,6 +416,11 @@ enum {
 	MLX4_DEVICE_STATE_INTERNAL_ERROR	= 1 << 1,
 };
 
+enum {
+	MLX4_INTERFACE_STATE_UP		= 1 << 0,
+	MLX4_INTERFACE_STATE_DELETION	= 1 << 1,
+};
+
 #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
 			     MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK)
 
@@ -760,6 +765,8 @@ struct mlx4_dev_persistent {
 	struct workqueue_struct *catas_wq;
 	struct mutex	device_state_mutex; /* protect HW state */
 	u8		state;
+	struct mutex	interface_state_mutex; /* protect SW state */
+	u8	interface_state;
 };
 
 struct mlx4_dev {
-- 
cgit v1.2.3-70-g09d2


From 55ad359225b2232b9b8f04a0dfa169bd3a7d86d2 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 25 Jan 2015 16:59:42 +0200
Subject: net/mlx4_core: Enable device recovery flow with SRIOV

In SRIOV, both the PF and the VF may attempt device recovery whenever they
assume that the device is not functioning.  When the PF driver resets the
device, the VF should detect this and attempt to reinitialize itself.

The VF must be able to reset itself under all circumstances, even
if the PF is not responsive.

The VF shall reset itself in the following cases:

1. Commands are not processed within reasonable time over the communication channel.
This is done considering device state and the correct return code based on
the command as was done in the native mode, done in the next patch.

2. The VF driver receives an internal error event reported by the PF on the
communication channel. This occurs when the PF driver resets the device or
when VF is out of sync with the PF.

Add 'VF reset' capability, which allows the VF to reinitialize itself even when the
PF is not responsive.

As PF and VF may run their reset flow simulantanisly, there are several cases
that are handled:
- Prevent freeing VF resources upon FLR, when PF is in its unloading stage.
- Prevent PF getting VF commands before it has finished initializing its resources.
- Upon VF startup, check that comm-channel is online before sending
  commands to the PF and getting timed-out.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/catas.c | 120 +++++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlx4/cmd.c   |  77 ++++++++++++----
 drivers/net/ethernet/mellanox/mlx4/eq.c    |  10 ++-
 drivers/net/ethernet/mellanox/mlx4/intf.c  |   6 +-
 drivers/net/ethernet/mellanox/mlx4/main.c  | 135 +++++++++++++++++++++++------
 drivers/net/ethernet/mellanox/mlx4/mlx4.h  |   7 +-
 include/linux/mlx4/cmd.h                   |   2 +
 include/linux/mlx4/device.h                |   5 ++
 8 files changed, 292 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 3fcf3cfaedf..715de8affcc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -45,8 +45,7 @@ enum {
 int mlx4_internal_err_reset = 1;
 module_param_named(internal_err_reset, mlx4_internal_err_reset,  int, 0644);
 MODULE_PARM_DESC(internal_err_reset,
-		 "Reset device on internal errors if non-zero"
-		 " (default 1, in SRIOV mode default is 0)");
+		 "Reset device on internal errors if non-zero (default 1)");
 
 static int read_vendor_id(struct mlx4_dev *dev)
 {
@@ -71,6 +70,9 @@ static int mlx4_reset_master(struct mlx4_dev *dev)
 {
 	int err = 0;
 
+	if (mlx4_is_master(dev))
+		mlx4_report_internal_err_comm_event(dev);
+
 	if (!pci_channel_offline(dev->persist->pdev)) {
 		err = read_vendor_id(dev);
 		/* If PCI can't be accessed to read vendor ID we assume that its
@@ -87,6 +89,81 @@ static int mlx4_reset_master(struct mlx4_dev *dev)
 	return err;
 }
 
+static int mlx4_reset_slave(struct mlx4_dev *dev)
+{
+#define COM_CHAN_RST_REQ_OFFSET 0x10
+#define COM_CHAN_RST_ACK_OFFSET 0x08
+
+	u32 comm_flags;
+	u32 rst_req;
+	u32 rst_ack;
+	unsigned long end;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (pci_channel_offline(dev->persist->pdev))
+		return 0;
+
+	comm_flags = swab32(readl((__iomem char *)priv->mfunc.comm +
+				  MLX4_COMM_CHAN_FLAGS));
+	if (comm_flags == 0xffffffff) {
+		mlx4_err(dev, "VF reset is not needed\n");
+		return 0;
+	}
+
+	if (!(dev->caps.vf_caps & MLX4_VF_CAP_FLAG_RESET)) {
+		mlx4_err(dev, "VF reset is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	rst_req = (comm_flags & (u32)(1 << COM_CHAN_RST_REQ_OFFSET)) >>
+		COM_CHAN_RST_REQ_OFFSET;
+	rst_ack = (comm_flags & (u32)(1 << COM_CHAN_RST_ACK_OFFSET)) >>
+		COM_CHAN_RST_ACK_OFFSET;
+	if (rst_req != rst_ack) {
+		mlx4_err(dev, "Communication channel isn't sync, fail to send reset\n");
+		return -EIO;
+	}
+
+	rst_req ^= 1;
+	mlx4_warn(dev, "VF is sending reset request to Firmware\n");
+	comm_flags = rst_req << COM_CHAN_RST_REQ_OFFSET;
+	__raw_writel((__force u32)cpu_to_be32(comm_flags),
+		     (__iomem char *)priv->mfunc.comm + MLX4_COMM_CHAN_FLAGS);
+	/* Make sure that our comm channel write doesn't
+	 * get mixed in with writes from another CPU.
+	 */
+	mmiowb();
+
+	end = msecs_to_jiffies(MLX4_COMM_TIME) + jiffies;
+	while (time_before(jiffies, end)) {
+		comm_flags = swab32(readl((__iomem char *)priv->mfunc.comm +
+					  MLX4_COMM_CHAN_FLAGS));
+		rst_ack = (comm_flags & (u32)(1 << COM_CHAN_RST_ACK_OFFSET)) >>
+			COM_CHAN_RST_ACK_OFFSET;
+
+		/* Reading rst_req again since the communication channel can
+		 * be reset at any time by the PF and all its bits will be
+		 * set to zero.
+		 */
+		rst_req = (comm_flags & (u32)(1 << COM_CHAN_RST_REQ_OFFSET)) >>
+			COM_CHAN_RST_REQ_OFFSET;
+
+		if (rst_ack == rst_req) {
+			mlx4_warn(dev, "VF Reset succeed\n");
+			return 0;
+		}
+		cond_resched();
+	}
+	mlx4_err(dev, "Fail to send reset over the communication channel\n");
+	return -ETIMEDOUT;
+}
+
+static int mlx4_comm_internal_err(u32 slave_read)
+{
+	return (u32)COMM_CHAN_EVENT_INTERNAL_ERR ==
+		(slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0;
+}
+
 void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 {
 	int err;
@@ -101,7 +178,10 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 
 	dev = persist->dev;
 	mlx4_err(dev, "device is going to be reset\n");
-	err = mlx4_reset_master(dev);
+	if (mlx4_is_slave(dev))
+		err = mlx4_reset_slave(dev);
+	else
+		err = mlx4_reset_master(dev);
 	BUG_ON(err != 0);
 
 	dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR;
@@ -148,8 +228,15 @@ static void poll_catas(unsigned long dev_ptr)
 {
 	struct mlx4_dev *dev = (struct mlx4_dev *) dev_ptr;
 	struct mlx4_priv *priv = mlx4_priv(dev);
-
-	if (readl(priv->catas_err.map)) {
+	u32 slave_read;
+
+	if (mlx4_is_slave(dev)) {
+		slave_read = swab32(readl(&priv->mfunc.comm->slave_read));
+		if (mlx4_comm_internal_err(slave_read)) {
+			mlx4_warn(dev, "Internal error detected on the communication channel\n");
+			goto internal_err;
+		}
+	} else if (readl(priv->catas_err.map)) {
 		dump_err_buf(dev);
 		goto internal_err;
 	}
@@ -182,22 +269,21 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	phys_addr_t addr;
 
-	/*If we are in SRIOV the default of the module param must be 0*/
-	if (mlx4_is_mfunc(dev))
-		mlx4_internal_err_reset = 0;
-
 	INIT_LIST_HEAD(&priv->catas_err.list);
 	init_timer(&priv->catas_err.timer);
 	priv->catas_err.map = NULL;
 
-	addr = pci_resource_start(dev->persist->pdev, priv->fw.catas_bar) +
-		priv->fw.catas_offset;
-
-	priv->catas_err.map = ioremap(addr, priv->fw.catas_size * 4);
-	if (!priv->catas_err.map) {
-		mlx4_warn(dev, "Failed to map internal error buffer at 0x%llx\n",
-			  (unsigned long long) addr);
-		return;
+	if (!mlx4_is_slave(dev)) {
+		addr = pci_resource_start(dev->persist->pdev,
+					  priv->fw.catas_bar) +
+					  priv->fw.catas_offset;
+
+		priv->catas_err.map = ioremap(addr, priv->fw.catas_size * 4);
+		if (!priv->catas_err.map) {
+			mlx4_warn(dev, "Failed to map internal error buffer at 0x%llx\n",
+				  (unsigned long long)addr);
+			return;
+		}
 	}
 
 	priv->catas_err.timer.data     = (unsigned long) dev;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 3895b2b5fc9..7652eed4bbc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -42,6 +42,7 @@
 #include <linux/mlx4/device.h>
 #include <linux/semaphore.h>
 #include <rdma/ib_smi.h>
+#include <linux/delay.h>
 
 #include <asm/io.h>
 
@@ -729,7 +730,7 @@ int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 EXPORT_SYMBOL_GPL(__mlx4_cmd);
 
 
-static int mlx4_ARM_COMM_CHANNEL(struct mlx4_dev *dev)
+int mlx4_ARM_COMM_CHANNEL(struct mlx4_dev *dev)
 {
 	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_ARM_COMM_CHANNEL,
 			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
@@ -1945,8 +1946,11 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 		break;
 	case MLX4_COMM_CMD_VHCR_POST:
 		if ((slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_EN) &&
-		    (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_POST))
+		    (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_POST)) {
+			mlx4_warn(dev, "slave:%d is out of sync, cmd=0x%x, last command=0x%x, reset is needed\n",
+				  slave, cmd, slave_state[slave].last_cmd);
 			goto reset_slave;
+		}
 
 		mutex_lock(&priv->cmd.slave_cmd_mutex);
 		if (mlx4_master_process_vhcr(dev, slave, NULL)) {
@@ -1980,7 +1984,18 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 
 reset_slave:
 	/* cleanup any slave resources */
-	mlx4_delete_all_resources_for_slave(dev, slave);
+	if (dev->persist->interface_state & MLX4_INTERFACE_STATE_UP)
+		mlx4_delete_all_resources_for_slave(dev, slave);
+
+	if (cmd != MLX4_COMM_CMD_RESET) {
+		mlx4_warn(dev, "Turn on internal error to force reset, slave=%d, cmd=0x%x\n",
+			  slave, cmd);
+		/* Turn on internal error letting slave reset itself immeditaly,
+		 * otherwise it might take till timeout on command is passed
+		 */
+		reply |= ((u32)COMM_CHAN_EVENT_INTERNAL_ERR);
+	}
+
 	spin_lock_irqsave(&priv->mfunc.master.slave_state_lock, flags);
 	if (!slave_state[slave].is_slave_going_down)
 		slave_state[slave].last_cmd = MLX4_COMM_CMD_RESET;
@@ -2056,17 +2071,28 @@ void mlx4_master_comm_channel(struct work_struct *work)
 static int sync_toggles(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int wr_toggle;
-	int rd_toggle;
+	u32 wr_toggle;
+	u32 rd_toggle;
 	unsigned long end;
 
-	wr_toggle = swab32(readl(&priv->mfunc.comm->slave_write)) >> 31;
-	end = jiffies + msecs_to_jiffies(5000);
+	wr_toggle = swab32(readl(&priv->mfunc.comm->slave_write));
+	if (wr_toggle == 0xffffffff)
+		end = jiffies + msecs_to_jiffies(30000);
+	else
+		end = jiffies + msecs_to_jiffies(5000);
 
 	while (time_before(jiffies, end)) {
-		rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read)) >> 31;
-		if (rd_toggle == wr_toggle) {
-			priv->cmd.comm_toggle = rd_toggle;
+		rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read));
+		if (wr_toggle == 0xffffffff || rd_toggle == 0xffffffff) {
+			/* PCI might be offline */
+			msleep(100);
+			wr_toggle = swab32(readl(&priv->mfunc.comm->
+					   slave_write));
+			continue;
+		}
+
+		if (rd_toggle >> 31 == wr_toggle >> 31) {
+			priv->cmd.comm_toggle = rd_toggle >> 31;
 			return 0;
 		}
 
@@ -2172,13 +2198,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 		if (mlx4_init_resource_tracker(dev))
 			goto err_thread;
 
-		err = mlx4_ARM_COMM_CHANNEL(dev);
-		if (err) {
-			mlx4_err(dev, " Failed to arm comm channel eq: %x\n",
-				 err);
-			goto err_resource;
-		}
-
 	} else {
 		err = sync_toggles(dev);
 		if (err) {
@@ -2188,8 +2207,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 	}
 	return 0;
 
-err_resource:
-	mlx4_free_resource_tracker(dev, RES_TR_FREE_ALL);
 err_thread:
 	flush_workqueue(priv->mfunc.master.comm_wq);
 	destroy_workqueue(priv->mfunc.master.comm_wq);
@@ -2266,6 +2283,27 @@ err:
 	return -ENOMEM;
 }
 
+void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int slave;
+	u32 slave_read;
+
+	/* Report an internal error event to all
+	 * communication channels.
+	 */
+	for (slave = 0; slave < dev->num_slaves; slave++) {
+		slave_read = swab32(readl(&priv->mfunc.comm[slave].slave_read));
+		slave_read |= (u32)COMM_CHAN_EVENT_INTERNAL_ERR;
+		__raw_writel((__force u32)cpu_to_be32(slave_read),
+			     &priv->mfunc.comm[slave].slave_read);
+		/* Make sure that our comm channel write doesn't
+		 * get mixed in with writes from another CPU.
+		 */
+		mmiowb();
+	}
+}
+
 void mlx4_multi_func_cleanup(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2281,6 +2319,7 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev)
 		kfree(priv->mfunc.master.slave_state);
 		kfree(priv->mfunc.master.vf_admin);
 		kfree(priv->mfunc.master.vf_oper);
+		dev->num_slaves = 0;
 	}
 
 	iounmap(priv->mfunc.comm);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 7538c9ce98a..2f2e6067426 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -429,8 +429,14 @@ void mlx4_master_handle_slave_flr(struct work_struct *work)
 		if (MLX4_COMM_CMD_FLR == slave_state[i].last_cmd) {
 			mlx4_dbg(dev, "mlx4_handle_slave_flr: clean slave: %d\n",
 				 i);
-
-			mlx4_delete_all_resources_for_slave(dev, i);
+			/* In case of 'Reset flow' FLR can be generated for
+			 * a slave before mlx4_load_one is done.
+			 * make sure interface is up before trying to delete
+			 * slave resources which weren't allocated yet.
+			 */
+			if (dev->persist->interface_state &
+			    MLX4_INTERFACE_STATE_UP)
+				mlx4_delete_all_resources_for_slave(dev, i);
 			/*return the slave to running mode*/
 			spin_lock_irqsave(&priv->mfunc.master.slave_state_lock, flags);
 			slave_state[i].last_cmd = MLX4_COMM_CMD_RESET;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index fba0b96a6f2..68d2bad325d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -144,8 +144,7 @@ int mlx4_register_device(struct mlx4_dev *dev)
 		mlx4_add_device(intf, priv);
 
 	mutex_unlock(&intf_mutex);
-	if (!mlx4_is_slave(dev))
-		mlx4_start_catas_poll(dev);
+	mlx4_start_catas_poll(dev);
 
 	return 0;
 }
@@ -155,8 +154,7 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_interface *intf;
 
-	if (!mlx4_is_slave(dev))
-		mlx4_stop_catas_poll(dev);
+	mlx4_stop_catas_poll(dev);
 	mutex_lock(&intf_mutex);
 
 	list_for_each_entry(intf, &intf_list, list)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6bb0fca137c..1baf1f1e286 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -108,6 +108,8 @@ MODULE_PARM_DESC(enable_64b_cqe_eqe,
 					 MLX4_FUNC_CAP_EQE_CQE_STRIDE | \
 					 MLX4_FUNC_CAP_DMFS_A0_STATIC)
 
+#define RESET_PERSIST_MASK_FLAGS	(MLX4_FLAG_SRIOV)
+
 static char mlx4_version[] =
 	DRV_NAME ": Mellanox ConnectX core driver v"
 	DRV_VERSION " (" DRV_RELDATE ")\n";
@@ -1579,6 +1581,50 @@ static void mlx4_close_fw(struct mlx4_dev *dev)
 	}
 }
 
+static int mlx4_comm_check_offline(struct mlx4_dev *dev)
+{
+#define COMM_CHAN_OFFLINE_OFFSET 0x09
+
+	u32 comm_flags;
+	u32 offline_bit;
+	unsigned long end;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	end = msecs_to_jiffies(MLX4_COMM_OFFLINE_TIME_OUT) + jiffies;
+	while (time_before(jiffies, end)) {
+		comm_flags = swab32(readl((__iomem char *)priv->mfunc.comm +
+					  MLX4_COMM_CHAN_FLAGS));
+		offline_bit = (comm_flags &
+			       (u32)(1 << COMM_CHAN_OFFLINE_OFFSET));
+		if (!offline_bit)
+			return 0;
+		/* There are cases as part of AER/Reset flow that PF needs
+		 * around 100 msec to load. We therefore sleep for 100 msec
+		 * to allow other tasks to make use of that CPU during this
+		 * time interval.
+		 */
+		msleep(100);
+	}
+	mlx4_err(dev, "Communication channel is offline.\n");
+	return -EIO;
+}
+
+static void mlx4_reset_vf_support(struct mlx4_dev *dev)
+{
+#define COMM_CHAN_RST_OFFSET 0x1e
+
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	u32 comm_rst;
+	u32 comm_caps;
+
+	comm_caps = swab32(readl((__iomem char *)priv->mfunc.comm +
+				 MLX4_COMM_CHAN_CAPS));
+	comm_rst = (comm_caps & (u32)(1 << COMM_CHAN_RST_OFFSET));
+
+	if (comm_rst)
+		dev->caps.vf_caps |= MLX4_VF_CAP_FLAG_RESET;
+}
+
 static int mlx4_init_slave(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1594,6 +1640,12 @@ static int mlx4_init_slave(struct mlx4_dev *dev)
 
 	mutex_lock(&priv->cmd.slave_cmd_mutex);
 	priv->cmd.max_cmds = 1;
+	if (mlx4_comm_check_offline(dev)) {
+		mlx4_err(dev, "PF is not responsive, skipping initialization\n");
+		goto err_offline;
+	}
+
+	mlx4_reset_vf_support(dev);
 	mlx4_warn(dev, "Sending reset\n");
 	ret_from_reset = mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0,
 				       MLX4_COMM_TIME);
@@ -1637,6 +1689,7 @@ static int mlx4_init_slave(struct mlx4_dev *dev)
 
 err:
 	mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, 0);
+err_offline:
 	mutex_unlock(&priv->cmd.slave_cmd_mutex);
 	return -EIO;
 }
@@ -2494,11 +2547,19 @@ static void mlx4_free_ownership(struct mlx4_dev *dev)
 				  !!((flags) & MLX4_FLAG_MASTER))
 
 static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
-			     u8 total_vfs, int existing_vfs)
+			     u8 total_vfs, int existing_vfs, int reset_flow)
 {
 	u64 dev_flags = dev->flags;
 	int err = 0;
 
+	if (reset_flow) {
+		dev->dev_vfs = kcalloc(total_vfs, sizeof(*dev->dev_vfs),
+				       GFP_KERNEL);
+		if (!dev->dev_vfs)
+			goto free_mem;
+		return dev_flags;
+	}
+
 	atomic_inc(&pf_loading);
 	if (dev->flags &  MLX4_FLAG_SRIOV) {
 		if (existing_vfs != total_vfs) {
@@ -2533,6 +2594,7 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
 
 disable_sriov:
 	atomic_dec(&pf_loading);
+free_mem:
 	dev->persist->num_vfs = 0;
 	kfree(dev->dev_vfs);
 	return dev_flags & ~MLX4_FLAG_MASTER;
@@ -2557,7 +2619,8 @@ static int mlx4_check_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap
 }
 
 static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
-			 int total_vfs, int *nvfs, struct mlx4_priv *priv)
+			 int total_vfs, int *nvfs, struct mlx4_priv *priv,
+			 int reset_flow)
 {
 	struct mlx4_dev *dev;
 	unsigned sum = 0;
@@ -2679,8 +2742,10 @@ slave_start:
 				goto err_fw;
 
 			if (!(dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS)) {
-				u64 dev_flags = mlx4_enable_sriov(dev, pdev, total_vfs,
-								  existing_vfs);
+				u64 dev_flags = mlx4_enable_sriov(dev, pdev,
+								  total_vfs,
+								  existing_vfs,
+								  reset_flow);
 
 				mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);
 				dev->flags = dev_flags;
@@ -2722,7 +2787,7 @@ slave_start:
 			if (dev->flags & MLX4_FLAG_SRIOV) {
 				if (!existing_vfs)
 					pci_disable_sriov(pdev);
-				if (mlx4_is_master(dev))
+				if (mlx4_is_master(dev) && !reset_flow)
 					atomic_dec(&pf_loading);
 				dev->flags &= ~MLX4_FLAG_SRIOV;
 			}
@@ -2736,7 +2801,8 @@ slave_start:
 	}
 
 	if (mlx4_is_master(dev) && (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS)) {
-		u64 dev_flags = mlx4_enable_sriov(dev, pdev, total_vfs, existing_vfs);
+		u64 dev_flags = mlx4_enable_sriov(dev, pdev, total_vfs,
+						  existing_vfs, reset_flow);
 
 		if ((dev->flags ^ dev_flags) & (MLX4_FLAG_MASTER | MLX4_FLAG_SLAVE)) {
 			mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_VHCR);
@@ -2848,6 +2914,17 @@ slave_start:
 		goto err_steer;
 
 	mlx4_init_quotas(dev);
+	/* When PF resources are ready arm its comm channel to enable
+	 * getting commands
+	 */
+	if (mlx4_is_master(dev)) {
+		err = mlx4_ARM_COMM_CHANNEL(dev);
+		if (err) {
+			mlx4_err(dev, " Failed to arm comm channel eq: %x\n",
+				 err);
+			goto err_steer;
+		}
+	}
 
 	for (port = 1; port <= dev->caps.num_ports; port++) {
 		err = mlx4_init_port_info(dev, port);
@@ -2866,7 +2943,7 @@ slave_start:
 
 	priv->removed = 0;
 
-	if (mlx4_is_master(dev) && dev->persist->num_vfs)
+	if (mlx4_is_master(dev) && dev->persist->num_vfs && !reset_flow)
 		atomic_dec(&pf_loading);
 
 	kfree(dev_cap);
@@ -2925,10 +3002,12 @@ err_cmd:
 	mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL);
 
 err_sriov:
-	if (dev->flags & MLX4_FLAG_SRIOV && !existing_vfs)
+	if (dev->flags & MLX4_FLAG_SRIOV && !existing_vfs) {
 		pci_disable_sriov(pdev);
+		dev->flags &= ~MLX4_FLAG_SRIOV;
+	}
 
-	if (mlx4_is_master(dev) && dev->persist->num_vfs)
+	if (mlx4_is_master(dev) && dev->persist->num_vfs && !reset_flow)
 		atomic_dec(&pf_loading);
 
 	kfree(priv->dev.dev_vfs);
@@ -3073,7 +3152,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 	if (err)
 		goto err_release_regions;
 
-	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv);
+	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0);
 	if (err)
 		goto err_catas;
 
@@ -3131,9 +3210,11 @@ static void mlx4_clean_dev(struct mlx4_dev *dev)
 {
 	struct mlx4_dev_persistent *persist = dev->persist;
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	unsigned long	flags = (dev->flags & RESET_PERSIST_MASK_FLAGS);
 
 	memset(priv, 0, sizeof(*priv));
 	priv->dev.persist = persist;
+	priv->dev.flags = flags;
 }
 
 static void mlx4_unload_one(struct pci_dev *pdev)
@@ -3143,7 +3224,6 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int               pci_dev_data;
 	int p, i;
-	int active_vfs = 0;
 
 	if (priv->removed)
 		return;
@@ -3157,14 +3237,6 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 
 	pci_dev_data = priv->pci_dev_data;
 
-	/* Disabling SR-IOV is not allowed while there are active vf's */
-	if (mlx4_is_master(dev)) {
-		active_vfs = mlx4_how_many_lives_vf(dev);
-		if (active_vfs) {
-			pr_warn("Removing PF when there are active VF's !!\n");
-			pr_warn("Will not disable SR-IOV.\n");
-		}
-	}
 	mlx4_stop_sense(dev);
 	mlx4_unregister_device(dev);
 
@@ -3208,12 +3280,6 @@ static void mlx4_unload_one(struct pci_dev *pdev)
 
 	if (dev->flags & MLX4_FLAG_MSI_X)
 		pci_disable_msix(pdev);
-	if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
-		mlx4_warn(dev, "Disabling SR-IOV\n");
-		pci_disable_sriov(pdev);
-		dev->flags &= ~MLX4_FLAG_SRIOV;
-		dev->persist->num_vfs = 0;
-	}
 
 	if (!mlx4_is_slave(dev))
 		mlx4_free_ownership(dev);
@@ -3235,11 +3301,21 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
 	struct mlx4_dev  *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	int active_vfs = 0;
 
 	mutex_lock(&persist->interface_state_mutex);
 	persist->interface_state |= MLX4_INTERFACE_STATE_DELETION;
 	mutex_unlock(&persist->interface_state_mutex);
 
+	/* Disabling SR-IOV is not allowed while there are active vf's */
+	if (mlx4_is_master(dev) && dev->flags & MLX4_FLAG_SRIOV) {
+		active_vfs = mlx4_how_many_lives_vf(dev);
+		if (active_vfs) {
+			pr_warn("Removing PF when there are active VF's !!\n");
+			pr_warn("Will not disable SR-IOV.\n");
+		}
+	}
+
 	/* device marked to be under deletion running now without the lock
 	 * letting other tasks to be terminated
 	 */
@@ -3248,6 +3324,11 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	else
 		mlx4_info(dev, "%s: interface is down\n", __func__);
 	mlx4_catas_end(dev);
+	if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
+		mlx4_warn(dev, "Disabling SR-IOV\n");
+		pci_disable_sriov(pdev);
+	}
+
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 	kfree(dev->persist);
@@ -3287,7 +3368,7 @@ int mlx4_restart_one(struct pci_dev *pdev)
 	memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));
 
 	mlx4_unload_one(pdev);
-	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv);
+	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 1);
 	if (err) {
 		mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n",
 			 __func__, pci_name(pdev), err);
@@ -3397,7 +3478,7 @@ static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 	mutex_lock(&persist->interface_state_mutex);
 	if (!(persist->interface_state & MLX4_INTERFACE_STATE_UP)) {
 		ret = mlx4_load_one(pdev, priv->pci_dev_data, total_vfs, nvfs,
-				    priv);
+				    priv, 1);
 		if (ret) {
 			mlx4_err(dev, "%s: mlx4_load_one failed, ret=%d\n",
 				 __func__,  ret);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 5c772ea4473..2a15b8248e7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -85,7 +85,9 @@ enum {
 	MLX4_CLR_INT_SIZE	= 0x00008,
 	MLX4_SLAVE_COMM_BASE	= 0x0,
 	MLX4_COMM_PAGESIZE	= 0x1000,
-	MLX4_CLOCK_SIZE		= 0x00008
+	MLX4_CLOCK_SIZE		= 0x00008,
+	MLX4_COMM_CHAN_CAPS	= 0x8,
+	MLX4_COMM_CHAN_FLAGS	= 0xc
 };
 
 enum {
@@ -120,6 +122,8 @@ enum mlx4_mpt_state {
 };
 
 #define MLX4_COMM_TIME		10000
+#define MLX4_COMM_OFFLINE_TIME_OUT 30000
+
 enum {
 	MLX4_COMM_CMD_RESET,
 	MLX4_COMM_CMD_VHCR0,
@@ -1162,6 +1166,7 @@ enum {
 int mlx4_cmd_init(struct mlx4_dev *dev);
 void mlx4_cmd_cleanup(struct mlx4_dev *dev, int cleanup_mask);
 int mlx4_multi_func_init(struct mlx4_dev *dev);
+int mlx4_ARM_COMM_CHANNEL(struct mlx4_dev *dev);
 void mlx4_multi_func_cleanup(struct mlx4_dev *dev);
 void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param);
 int mlx4_cmd_use_events(struct mlx4_dev *dev);
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index e7543844cc7..c989442ffc6 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -280,6 +280,7 @@ int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_stat
 int mlx4_config_dev_retrieval(struct mlx4_dev *dev,
 			      struct mlx4_config_dev_params *params);
 void mlx4_cmd_wake_completions(struct mlx4_dev *dev);
+void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev);
 /*
  * mlx4_get_slave_default_vlan -
  * return true if VST ( default vlan)
@@ -289,5 +290,6 @@ bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave,
 				 u16 *vlan, u8 *qos);
 
 #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8)
+#define COMM_CHAN_EVENT_INTERNAL_ERR (1 << 17)
 
 #endif /* MLX4_CMD_H */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 33f9ca71925..5ef54e145e4 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -208,6 +208,10 @@ enum {
 	MLX4_QUERY_FUNC_FLAGS_A0_RES_QP		= 1LL << 1
 };
 
+enum {
+	MLX4_VF_CAP_FLAG_RESET			= 1 << 0
+};
+
 /* bit enums for an 8-bit flags field indicating special use
  * QPs which require special handling in qp_reserve_range.
  * Currently, this only includes QPs used by the ETH interface,
@@ -545,6 +549,7 @@ struct mlx4_caps {
 	u8			alloc_res_qp_mask;
 	u32			dmfs_high_rate_qpn_base;
 	u32			dmfs_high_rate_qpn_range;
+	u32			vf_caps;
 };
 
 struct mlx4_buf_list {
-- 
cgit v1.2.3-70-g09d2


From c2943f14534bdc4230f4da6dcd4ea03c5d8c8162 Mon Sep 17 00:00:00 2001
From: Harout Hedeshian <harouth@codeaurora.org>
Date: Tue, 20 Jan 2015 10:06:05 -0700
Subject: net: ipv6: Add sysctl entry to disable MTU updates from RA

The kernel forcefully applies MTU values received in router
advertisements provided the new MTU is less than the current. This
behavior is undesirable when the user space is managing the MTU. Instead
a sysctl flag 'accept_ra_mtu' is introduced such that the user space
can control whether or not RA provided MTU updates should be applied. The
default behavior is unchanged; user space must explicitly set this flag
to 0 for RA MTUs to be ignored.

Signed-off-by: Harout Hedeshian <harouth@codeaurora.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  7 +++++++
 include/linux/ipv6.h                   |  1 +
 include/uapi/linux/ipv6.h              |  1 +
 net/ipv6/addrconf.c                    | 10 ++++++++++
 net/ipv6/ndisc.c                       |  2 +-
 5 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 85b02217910..a5e4c813f17 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1287,6 +1287,13 @@ accept_ra_rtr_pref - BOOLEAN
 	Functional default: enabled if accept_ra is enabled.
 			    disabled if accept_ra is disabled.
 
+accept_ra_mtu - BOOLEAN
+	Apply the MTU value specified in RA option 5 (RFC4861). If
+	disabled, the MTU specified in the RA will be ignored.
+
+	Functional default: enabled if accept_ra is enabled.
+			    disabled if accept_ra is disabled.
+
 accept_redirects - BOOLEAN
 	Accept Redirects.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index c694e7baa62..2805062c013 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -52,6 +52,7 @@ struct ipv6_devconf {
 	__s32		force_tllao;
 	__s32           ndisc_notify;
 	__s32		suppress_frag_ndisc;
+	__s32		accept_ra_mtu;
 	void		*sysctl;
 };
 
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index 73cb02dc306..437a6a4b125 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -169,6 +169,7 @@ enum {
 	DEVCONF_SUPPRESS_FRAG_NDISC,
 	DEVCONF_ACCEPT_RA_FROM_LOCAL,
 	DEVCONF_USE_OPTIMISTIC,
+	DEVCONF_ACCEPT_RA_MTU,
 	DEVCONF_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d6b4f5d0801..7dcc065e216 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -201,6 +201,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.disable_ipv6		= 0,
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
+	.accept_ra_mtu		= 1,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -238,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.disable_ipv6		= 0,
 	.accept_dad		= 1,
 	.suppress_frag_ndisc	= 1,
+	.accept_ra_mtu		= 1,
 };
 
 /* Check if a valid qdisc is available */
@@ -4380,6 +4382,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify;
 	array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
 	array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local;
+	array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -5258,6 +5261,13 @@ static struct addrconf_sysctl_table
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
+		{
+			.procname	= "accept_ra_mtu",
+			.data		= &ipv6_devconf.accept_ra_mtu,
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
+			.proc_handler	= proc_dointvec,
+		},
 		{
 			/* sentinel */
 		}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 682866777d5..8a9d7c19e24 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1348,7 +1348,7 @@ skip_routeinfo:
 		}
 	}
 
-	if (ndopts.nd_opts_mtu) {
+	if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) {
 		__be32 n;
 		u32 mtu;
 
-- 
cgit v1.2.3-70-g09d2


From 607954b084d4ad5e6a2e0f795de7803d9c6ae37f Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Wed, 21 Jan 2015 11:12:13 +0000
Subject: rhashtable: fix rht_for_each_entry_safe() endless loop

"next" is not updated, causing an endless loop for buckets with more than
one element.

Fixes: 88d6ed15acff ("rhashtable: Convert bucket iterators to take table and index")
Signed-off-by: Patrick McHardy <kaber@trash.net>
Acked-by: Thomas Graf <tgraf@suug.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index a2562ed53ea..e0337844358 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -260,7 +260,9 @@ void rhashtable_destroy(struct rhashtable *ht);
 	     next = !rht_is_a_nulls(pos) ?				    \
 		       rht_dereference_bucket(pos->next, tbl, hash) : NULL; \
 	     (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member);	    \
-	     pos = next)
+	     pos = next,						    \
+	     next = !rht_is_a_nulls(pos) ?				    \
+		       rht_dereference_bucket(pos->next, tbl, hash) : NULL)
 
 /**
  * rht_for_each_rcu_continue - continue iterating over rcu hash chain
-- 
cgit v1.2.3-70-g09d2


From 6ac730951104a437bf828683bcf9ba66336c4fa7 Mon Sep 17 00:00:00 2001
From: Beniamino Galvani <b.galvani@gmail.com>
Date: Sat, 17 Jan 2015 19:15:14 +0100
Subject: pinctrl: add driver for Amlogic Meson SoCs

This is a driver for the pinmux and GPIO controller available in
Amlogic Meson SoCs. It currently supports only Meson8, however the
common code should be generic enough to work also for other SoCs after
having defined the proper set of functions and groups.

GPIO interrupts are not supported at the moment due to lack of
documentation.

Signed-off-by: Beniamino Galvani <b.galvani@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig                |    8 +
 drivers/pinctrl/Makefile               |    1 +
 drivers/pinctrl/meson/Makefile         |    2 +
 drivers/pinctrl/meson/pinctrl-meson.c  |  761 ++++++++++++++++++++++
 drivers/pinctrl/meson/pinctrl-meson.h  |  209 ++++++
 drivers/pinctrl/meson/pinctrl-meson8.c | 1089 ++++++++++++++++++++++++++++++++
 include/dt-bindings/gpio/meson8-gpio.h |  157 +++++
 7 files changed, 2227 insertions(+)
 create mode 100644 drivers/pinctrl/meson/Makefile
 create mode 100644 drivers/pinctrl/meson/pinctrl-meson.c
 create mode 100644 drivers/pinctrl/meson/pinctrl-meson.h
 create mode 100644 drivers/pinctrl/meson/pinctrl-meson8.c
 create mode 100644 include/dt-bindings/gpio/meson8-gpio.h

(limited to 'include')

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index e738cca15a2..ee9f44ad7f0 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -96,6 +96,14 @@ config PINCTRL_FALCON
 	depends on SOC_FALCON
 	depends on PINCTRL_LANTIQ
 
+config PINCTRL_MESON
+	bool
+	select PINMUX
+	select PINCONF
+	select GENERIC_PINCONF
+	select OF_GPIO
+	select REGMAP_MMIO
+
 config PINCTRL_ROCKCHIP
 	bool
 	select PINMUX
diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile
index 6c28bd62361..0475206dd60 100644
--- a/drivers/pinctrl/Makefile
+++ b/drivers/pinctrl/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_PINCTRL_AT91)	+= pinctrl-at91.o
 obj-$(CONFIG_PINCTRL_BCM2835)	+= pinctrl-bcm2835.o
 obj-$(CONFIG_PINCTRL_BCM281XX)	+= pinctrl-bcm281xx.o
 obj-$(CONFIG_PINCTRL_FALCON)	+= pinctrl-falcon.o
+obj-$(CONFIG_PINCTRL_MESON)	+= meson/
 obj-$(CONFIG_PINCTRL_PALMAS)	+= pinctrl-palmas.o
 obj-$(CONFIG_PINCTRL_ROCKCHIP)	+= pinctrl-rockchip.o
 obj-$(CONFIG_PINCTRL_SINGLE)	+= pinctrl-single.o
diff --git a/drivers/pinctrl/meson/Makefile b/drivers/pinctrl/meson/Makefile
new file mode 100644
index 00000000000..eafc216067a
--- /dev/null
+++ b/drivers/pinctrl/meson/Makefile
@@ -0,0 +1,2 @@
+obj-y	+= pinctrl-meson8.o
+obj-y	+= pinctrl-meson.o
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
new file mode 100644
index 00000000000..a2bf49ce16e
--- /dev/null
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -0,0 +1,761 @@
+/*
+ * Pin controller and GPIO driver for Amlogic Meson SoCs
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * The available pins are organized in banks (A,B,C,D,E,X,Y,Z,AO,
+ * BOOT,CARD for meson6 and X,Y,DV,H,Z,AO,BOOT,CARD for meson8) and
+ * each bank has a variable number of pins.
+ *
+ * The AO bank is special because it belongs to the Always-On power
+ * domain which can't be powered off; the bank also uses a set of
+ * registers different from the other banks.
+ *
+ * For each of the two power domains (regular and always-on) there are
+ * 4 different register ranges that control the following properties
+ * of the pins:
+ *  1) pin muxing
+ *  2) pull enable/disable
+ *  3) pull up/down
+ *  4) GPIO direction, output value, input value
+ *
+ * In some cases the register ranges for pull enable and pull
+ * direction are the same and thus there are only 3 register ranges.
+ *
+ * Every pinmux group can be enabled by a specific bit in the first
+ * register range of the domain; when all groups for a given pin are
+ * disabled the pin acts as a GPIO.
+ *
+ * For the pull and GPIO configuration every bank uses a contiguous
+ * set of bits in the register sets described above; the same register
+ * can be shared by more banks with different offsets.
+ *
+ * In addition to this there are some registers shared between all
+ * banks that control the IRQ functionality. This feature is not
+ * supported at the moment by the driver.
+ */
+
+#include <linux/device.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/pinctrl/pinmux.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/seq_file.h>
+
+#include "../core.h"
+#include "../pinctrl-utils.h"
+#include "pinctrl-meson.h"
+
+/**
+ * meson_get_bank() - find the bank containing a given pin
+ *
+ * @domain:	the domain containing the pin
+ * @pin:	the pin number
+ * @bank:	the found bank
+ *
+ * Return:	0 on success, a negative value on error
+ */
+static int meson_get_bank(struct meson_domain *domain, unsigned int pin,
+			  struct meson_bank **bank)
+{
+	int i;
+
+	for (i = 0; i < domain->data->num_banks; i++) {
+		if (pin >= domain->data->banks[i].first &&
+		    pin <= domain->data->banks[i].last) {
+			*bank = &domain->data->banks[i];
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * meson_get_domain_and_bank() - find domain and bank containing a given pin
+ *
+ * @pc:		Meson pin controller device
+ * @pin:	the pin number
+ * @domain:	the found domain
+ * @bank:	the found bank
+ *
+ * Return:	0 on success, a negative value on error
+ */
+static int meson_get_domain_and_bank(struct meson_pinctrl *pc, unsigned int pin,
+				     struct meson_domain **domain,
+				     struct meson_bank **bank)
+{
+	struct meson_domain *d;
+	int i;
+
+	for (i = 0; i < pc->data->num_domains; i++) {
+		d = &pc->domains[i];
+		if (pin >= d->data->pin_base &&
+		    pin < d->data->pin_base + d->data->num_pins) {
+			*domain = d;
+			return meson_get_bank(d, pin, bank);
+		}
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * meson_calc_reg_and_bit() - calculate register and bit for a pin
+ *
+ * @bank:	the bank containing the pin
+ * @pin:	the pin number
+ * @reg_type:	the type of register needed (pull-enable, pull, etc...)
+ * @reg:	the computed register offset
+ * @bit:	the computed bit
+ */
+static void meson_calc_reg_and_bit(struct meson_bank *bank, unsigned int pin,
+				   enum meson_reg_type reg_type,
+				   unsigned int *reg, unsigned int *bit)
+{
+	struct meson_reg_desc *desc = &bank->regs[reg_type];
+
+	*reg = desc->reg * 4;
+	*bit = desc->bit + pin - bank->first;
+}
+
+static int meson_get_groups_count(struct pinctrl_dev *pcdev)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+
+	return pc->data->num_groups;
+}
+
+static const char *meson_get_group_name(struct pinctrl_dev *pcdev,
+					unsigned selector)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+
+	return pc->data->groups[selector].name;
+}
+
+static int meson_get_group_pins(struct pinctrl_dev *pcdev, unsigned selector,
+				const unsigned **pins, unsigned *num_pins)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+
+	*pins = pc->data->groups[selector].pins;
+	*num_pins = pc->data->groups[selector].num_pins;
+
+	return 0;
+}
+
+static void meson_pin_dbg_show(struct pinctrl_dev *pcdev, struct seq_file *s,
+			       unsigned offset)
+{
+	seq_printf(s, " %s", dev_name(pcdev->dev));
+}
+
+static const struct pinctrl_ops meson_pctrl_ops = {
+	.get_groups_count	= meson_get_groups_count,
+	.get_group_name		= meson_get_group_name,
+	.get_group_pins		= meson_get_group_pins,
+	.dt_node_to_map		= pinconf_generic_dt_node_to_map_all,
+	.dt_free_map		= pinctrl_utils_dt_free_map,
+	.pin_dbg_show		= meson_pin_dbg_show,
+};
+
+/**
+ * meson_pmx_disable_other_groups() - disable other groups using a given pin
+ *
+ * @pc:		meson pin controller device
+ * @pin:	number of the pin
+ * @sel_group:	index of the selected group, or -1 if none
+ *
+ * The function disables all pinmux groups using a pin except the
+ * selected one. If @sel_group is -1 all groups are disabled, leaving
+ * the pin in GPIO mode.
+ */
+static void meson_pmx_disable_other_groups(struct meson_pinctrl *pc,
+					   unsigned int pin, int sel_group)
+{
+	struct meson_pmx_group *group;
+	struct meson_domain *domain;
+	int i, j;
+
+	for (i = 0; i < pc->data->num_groups; i++) {
+		group = &pc->data->groups[i];
+		if (group->is_gpio || i == sel_group)
+			continue;
+
+		for (j = 0; j < group->num_pins; j++) {
+			if (group->pins[j] == pin) {
+				/* We have found a group using the pin */
+				domain = &pc->domains[group->domain];
+				regmap_update_bits(domain->reg_mux,
+						   group->reg * 4,
+						   BIT(group->bit), 0);
+			}
+		}
+	}
+}
+
+static int meson_pmx_set_mux(struct pinctrl_dev *pcdev, unsigned func_num,
+			     unsigned group_num)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+	struct meson_pmx_func *func = &pc->data->funcs[func_num];
+	struct meson_pmx_group *group = &pc->data->groups[group_num];
+	struct meson_domain *domain = &pc->domains[group->domain];
+	int i, ret = 0;
+
+	dev_dbg(pc->dev, "enable function %s, group %s\n", func->name,
+		group->name);
+
+	/*
+	 * Disable groups using the same pin.
+	 * The selected group is not disabled to avoid glitches.
+	 */
+	for (i = 0; i < group->num_pins; i++)
+		meson_pmx_disable_other_groups(pc, group->pins[i], group_num);
+
+	/* Function 0 (GPIO) doesn't need any additional setting */
+	if (func_num)
+		ret = regmap_update_bits(domain->reg_mux, group->reg * 4,
+					 BIT(group->bit), BIT(group->bit));
+
+	return ret;
+}
+
+static int meson_pmx_request_gpio(struct pinctrl_dev *pcdev,
+				  struct pinctrl_gpio_range *range,
+				  unsigned offset)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+
+	meson_pmx_disable_other_groups(pc, range->pin_base + offset, -1);
+
+	return 0;
+}
+
+static int meson_pmx_get_funcs_count(struct pinctrl_dev *pcdev)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+
+	return pc->data->num_funcs;
+}
+
+static const char *meson_pmx_get_func_name(struct pinctrl_dev *pcdev,
+					   unsigned selector)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+
+	return pc->data->funcs[selector].name;
+}
+
+static int meson_pmx_get_groups(struct pinctrl_dev *pcdev, unsigned selector,
+				const char * const **groups,
+				unsigned * const num_groups)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+
+	*groups = pc->data->funcs[selector].groups;
+	*num_groups = pc->data->funcs[selector].num_groups;
+
+	return 0;
+}
+
+static const struct pinmux_ops meson_pmx_ops = {
+	.set_mux = meson_pmx_set_mux,
+	.get_functions_count = meson_pmx_get_funcs_count,
+	.get_function_name = meson_pmx_get_func_name,
+	.get_function_groups = meson_pmx_get_groups,
+	.gpio_request_enable = meson_pmx_request_gpio,
+};
+
+static int meson_pinconf_set(struct pinctrl_dev *pcdev, unsigned int pin,
+			     unsigned long *configs, unsigned num_configs)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+	struct meson_domain *domain;
+	struct meson_bank *bank;
+	enum pin_config_param param;
+	unsigned int reg, bit;
+	int i, ret;
+	u16 arg;
+
+	ret = meson_get_domain_and_bank(pc, pin, &domain, &bank);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num_configs; i++) {
+		param = pinconf_to_config_param(configs[i]);
+		arg = pinconf_to_config_argument(configs[i]);
+
+		switch (param) {
+		case PIN_CONFIG_BIAS_DISABLE:
+			dev_dbg(pc->dev, "pin %u: disable bias\n", pin);
+
+			meson_calc_reg_and_bit(bank, pin, REG_PULL, &reg, &bit);
+			ret = regmap_update_bits(domain->reg_pull, reg,
+						 BIT(bit), 0);
+			if (ret)
+				return ret;
+			break;
+		case PIN_CONFIG_BIAS_PULL_UP:
+			dev_dbg(pc->dev, "pin %u: enable pull-up\n", pin);
+
+			meson_calc_reg_and_bit(bank, pin, REG_PULLEN,
+					       &reg, &bit);
+			ret = regmap_update_bits(domain->reg_pullen, reg,
+						 BIT(bit), BIT(bit));
+			if (ret)
+				return ret;
+
+			meson_calc_reg_and_bit(bank, pin, REG_PULL, &reg, &bit);
+			ret = regmap_update_bits(domain->reg_pull, reg,
+						 BIT(bit), BIT(bit));
+			if (ret)
+				return ret;
+			break;
+		case PIN_CONFIG_BIAS_PULL_DOWN:
+			dev_dbg(pc->dev, "pin %u: enable pull-down\n", pin);
+
+			meson_calc_reg_and_bit(bank, pin, REG_PULLEN,
+					       &reg, &bit);
+			ret = regmap_update_bits(domain->reg_pullen, reg,
+						 BIT(bit), BIT(bit));
+			if (ret)
+				return ret;
+
+			meson_calc_reg_and_bit(bank, pin, REG_PULL, &reg, &bit);
+			ret = regmap_update_bits(domain->reg_pull, reg,
+						 BIT(bit), 0);
+			if (ret)
+				return ret;
+			break;
+		default:
+			return -ENOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int meson_pinconf_get_pull(struct meson_pinctrl *pc, unsigned int pin)
+{
+	struct meson_domain *domain;
+	struct meson_bank *bank;
+	unsigned int reg, bit, val;
+	int ret, conf;
+
+	ret = meson_get_domain_and_bank(pc, pin, &domain, &bank);
+	if (ret)
+		return ret;
+
+	meson_calc_reg_and_bit(bank, pin, REG_PULLEN, &reg, &bit);
+
+	ret = regmap_read(domain->reg_pullen, reg, &val);
+	if (ret)
+		return ret;
+
+	if (!(val & BIT(bit))) {
+		conf = PIN_CONFIG_BIAS_DISABLE;
+	} else {
+		meson_calc_reg_and_bit(bank, pin, REG_PULL, &reg, &bit);
+
+		ret = regmap_read(domain->reg_pull, reg, &val);
+		if (ret)
+			return ret;
+
+		if (val & BIT(bit))
+			conf = PIN_CONFIG_BIAS_PULL_UP;
+		else
+			conf = PIN_CONFIG_BIAS_PULL_DOWN;
+	}
+
+	return conf;
+}
+
+static int meson_pinconf_get(struct pinctrl_dev *pcdev, unsigned int pin,
+			     unsigned long *config)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+	enum pin_config_param param = pinconf_to_config_param(*config);
+	u16 arg;
+
+	switch (param) {
+	case PIN_CONFIG_BIAS_DISABLE:
+	case PIN_CONFIG_BIAS_PULL_DOWN:
+	case PIN_CONFIG_BIAS_PULL_UP:
+		if (meson_pinconf_get_pull(pc, pin) == param)
+			arg = 1;
+		else
+			return -EINVAL;
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	*config = pinconf_to_config_packed(param, arg);
+	dev_dbg(pc->dev, "pinconf for pin %u is %lu\n", pin, *config);
+
+	return 0;
+}
+
+static int meson_pinconf_group_set(struct pinctrl_dev *pcdev,
+				   unsigned int num_group,
+				   unsigned long *configs, unsigned num_configs)
+{
+	struct meson_pinctrl *pc = pinctrl_dev_get_drvdata(pcdev);
+	struct meson_pmx_group *group = &pc->data->groups[num_group];
+	int i;
+
+	dev_dbg(pc->dev, "set pinconf for group %s\n", group->name);
+
+	for (i = 0; i < group->num_pins; i++) {
+		meson_pinconf_set(pcdev, group->pins[i], configs,
+				  num_configs);
+	}
+
+	return 0;
+}
+
+static int meson_pinconf_group_get(struct pinctrl_dev *pcdev,
+				   unsigned int group, unsigned long *config)
+{
+	return -ENOSYS;
+}
+
+static const struct pinconf_ops meson_pinconf_ops = {
+	.pin_config_get		= meson_pinconf_get,
+	.pin_config_set		= meson_pinconf_set,
+	.pin_config_group_get	= meson_pinconf_group_get,
+	.pin_config_group_set	= meson_pinconf_group_set,
+	.is_generic		= true,
+};
+
+static inline struct meson_domain *to_meson_domain(struct gpio_chip *chip)
+{
+	return container_of(chip, struct meson_domain, chip);
+}
+
+static int meson_gpio_request(struct gpio_chip *chip, unsigned gpio)
+{
+	return pinctrl_request_gpio(chip->base + gpio);
+}
+
+static void meson_gpio_free(struct gpio_chip *chip, unsigned gpio)
+{
+	struct meson_domain *domain = to_meson_domain(chip);
+
+	pinctrl_free_gpio(domain->data->pin_base + gpio);
+}
+
+static int meson_gpio_direction_input(struct gpio_chip *chip, unsigned gpio)
+{
+	struct meson_domain *domain = to_meson_domain(chip);
+	unsigned int reg, bit, pin;
+	struct meson_bank *bank;
+	int ret;
+
+	pin = domain->data->pin_base + gpio;
+	ret = meson_get_bank(domain, pin, &bank);
+	if (ret)
+		return ret;
+
+	meson_calc_reg_and_bit(bank, pin, REG_DIR, &reg, &bit);
+
+	return regmap_update_bits(domain->reg_gpio, reg, BIT(bit), BIT(bit));
+}
+
+static int meson_gpio_direction_output(struct gpio_chip *chip, unsigned gpio,
+				       int value)
+{
+	struct meson_domain *domain = to_meson_domain(chip);
+	unsigned int reg, bit, pin;
+	struct meson_bank *bank;
+	int ret;
+
+	pin = domain->data->pin_base + gpio;
+	ret = meson_get_bank(domain, pin, &bank);
+	if (ret)
+		return ret;
+
+	meson_calc_reg_and_bit(bank, pin, REG_DIR, &reg, &bit);
+	ret = regmap_update_bits(domain->reg_gpio, reg, BIT(bit), 0);
+	if (ret)
+		return ret;
+
+	meson_calc_reg_and_bit(bank, pin, REG_OUT, &reg, &bit);
+	return regmap_update_bits(domain->reg_gpio, reg, BIT(bit),
+				  value ? BIT(bit) : 0);
+}
+
+static void meson_gpio_set(struct gpio_chip *chip, unsigned gpio, int value)
+{
+	struct meson_domain *domain = to_meson_domain(chip);
+	unsigned int reg, bit, pin;
+	struct meson_bank *bank;
+	int ret;
+
+	pin = domain->data->pin_base + gpio;
+	ret = meson_get_bank(domain, pin, &bank);
+	if (ret)
+		return;
+
+	meson_calc_reg_and_bit(bank, pin, REG_OUT, &reg, &bit);
+	regmap_update_bits(domain->reg_gpio, reg, BIT(bit),
+			   value ? BIT(bit) : 0);
+}
+
+static int meson_gpio_get(struct gpio_chip *chip, unsigned gpio)
+{
+	struct meson_domain *domain = to_meson_domain(chip);
+	unsigned int reg, bit, val, pin;
+	struct meson_bank *bank;
+	int ret;
+
+	pin = domain->data->pin_base + gpio;
+	ret = meson_get_bank(domain, pin, &bank);
+	if (ret)
+		return ret;
+
+	meson_calc_reg_and_bit(bank, pin, REG_IN, &reg, &bit);
+	regmap_read(domain->reg_gpio, reg, &val);
+
+	return !!(val & BIT(bit));
+}
+
+static const struct of_device_id meson_pinctrl_dt_match[] = {
+	{
+		.compatible = "amlogic,meson8-pinctrl",
+		.data = &meson8_pinctrl_data,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, meson_pinctrl_dt_match);
+
+static int meson_gpiolib_register(struct meson_pinctrl *pc)
+{
+	struct meson_domain *domain;
+	int i, ret;
+
+	for (i = 0; i < pc->data->num_domains; i++) {
+		domain = &pc->domains[i];
+
+		domain->chip.label = domain->data->name;
+		domain->chip.dev = pc->dev;
+		domain->chip.request = meson_gpio_request;
+		domain->chip.free = meson_gpio_free;
+		domain->chip.direction_input = meson_gpio_direction_input;
+		domain->chip.direction_output = meson_gpio_direction_output;
+		domain->chip.get = meson_gpio_get;
+		domain->chip.set = meson_gpio_set;
+		domain->chip.base = -1;
+		domain->chip.ngpio = domain->data->num_pins;
+		domain->chip.can_sleep = false;
+		domain->chip.of_node = domain->of_node;
+		domain->chip.of_gpio_n_cells = 2;
+
+		ret = gpiochip_add(&domain->chip);
+		if (ret) {
+			dev_err(pc->dev, "can't add gpio chip %s\n",
+				domain->data->name);
+			goto fail;
+		}
+
+		ret = gpiochip_add_pin_range(&domain->chip, dev_name(pc->dev),
+					     0, domain->data->pin_base,
+					     domain->chip.ngpio);
+		if (ret) {
+			dev_err(pc->dev, "can't add pin range\n");
+			goto fail;
+		}
+	}
+
+	return 0;
+fail:
+	for (i--; i >= 0; i--)
+		gpiochip_remove(&pc->domains[i].chip);
+
+	return ret;
+}
+
+static struct meson_domain_data *meson_get_domain_data(struct meson_pinctrl *pc,
+						       struct device_node *np)
+{
+	int i;
+
+	for (i = 0; i < pc->data->num_domains; i++) {
+		if (!strcmp(np->name, pc->data->domain_data[i].name))
+			return &pc->data->domain_data[i];
+	}
+
+	return NULL;
+}
+
+static struct regmap_config meson_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
+static struct regmap *meson_map_resource(struct meson_pinctrl *pc,
+					 struct device_node *node, char *name)
+{
+	struct resource res;
+	void __iomem *base;
+	int i;
+
+	i = of_property_match_string(node, "reg-names", name);
+	if (of_address_to_resource(node, i, &res))
+		return ERR_PTR(-ENOENT);
+
+	base = devm_ioremap_resource(pc->dev, &res);
+	if (IS_ERR(base))
+		return ERR_CAST(base);
+
+	meson_regmap_config.max_register = resource_size(&res) - 4;
+	meson_regmap_config.name = devm_kasprintf(pc->dev, GFP_KERNEL,
+						  "%s-%s", node->name,
+						  name);
+	if (!meson_regmap_config.name)
+		return ERR_PTR(-ENOMEM);
+
+	return devm_regmap_init_mmio(pc->dev, base, &meson_regmap_config);
+}
+
+static int meson_pinctrl_parse_dt(struct meson_pinctrl *pc,
+				  struct device_node *node)
+{
+	struct device_node *np;
+	struct meson_domain *domain;
+	int i = 0, num_domains = 0;
+
+	for_each_child_of_node(node, np) {
+		if (!of_find_property(np, "gpio-controller", NULL))
+			continue;
+		num_domains++;
+	}
+
+	if (num_domains != pc->data->num_domains) {
+		dev_err(pc->dev, "wrong number of subnodes\n");
+		return -EINVAL;
+	}
+
+	pc->domains = devm_kzalloc(pc->dev, num_domains *
+				   sizeof(struct meson_domain), GFP_KERNEL);
+	if (!pc->domains)
+		return -ENOMEM;
+
+	for_each_child_of_node(node, np) {
+		if (!of_find_property(np, "gpio-controller", NULL))
+			continue;
+
+		domain = &pc->domains[i];
+
+		domain->data = meson_get_domain_data(pc, np);
+		if (!domain->data) {
+			dev_err(pc->dev, "domain data not found for node %s\n",
+				np->name);
+			return -ENODEV;
+		}
+
+		domain->of_node = np;
+
+		domain->reg_mux = meson_map_resource(pc, np, "mux");
+		if (IS_ERR(domain->reg_mux)) {
+			dev_err(pc->dev, "mux registers not found\n");
+			return PTR_ERR(domain->reg_mux);
+		}
+
+		domain->reg_pull = meson_map_resource(pc, np, "pull");
+		if (IS_ERR(domain->reg_pull)) {
+			dev_err(pc->dev, "pull registers not found\n");
+			return PTR_ERR(domain->reg_pull);
+		}
+
+		domain->reg_pullen = meson_map_resource(pc, np, "pull-enable");
+		/* Use pull region if pull-enable one is not present */
+		if (IS_ERR(domain->reg_pullen))
+			domain->reg_pullen = domain->reg_pull;
+
+		domain->reg_gpio = meson_map_resource(pc, np, "gpio");
+		if (IS_ERR(domain->reg_gpio)) {
+			dev_err(pc->dev, "gpio registers not found\n");
+			return PTR_ERR(domain->reg_gpio);
+		}
+
+		i++;
+	}
+
+	return 0;
+}
+
+static int meson_pinctrl_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+	struct meson_pinctrl *pc;
+	int ret;
+
+	pc = devm_kzalloc(dev, sizeof(struct meson_pinctrl), GFP_KERNEL);
+	if (!pc)
+		return -ENOMEM;
+
+	pc->dev = dev;
+	match = of_match_node(meson_pinctrl_dt_match, pdev->dev.of_node);
+	pc->data = (struct meson_pinctrl_data *)match->data;
+
+	ret = meson_pinctrl_parse_dt(pc, pdev->dev.of_node);
+	if (ret)
+		return ret;
+
+	pc->desc.name		= "pinctrl-meson";
+	pc->desc.owner		= THIS_MODULE;
+	pc->desc.pctlops	= &meson_pctrl_ops;
+	pc->desc.pmxops		= &meson_pmx_ops;
+	pc->desc.confops	= &meson_pinconf_ops;
+	pc->desc.pins		= pc->data->pins;
+	pc->desc.npins		= pc->data->num_pins;
+
+	pc->pcdev = pinctrl_register(&pc->desc, pc->dev, pc);
+	if (!pc->pcdev) {
+		dev_err(pc->dev, "can't register pinctrl device");
+		return -EINVAL;
+	}
+
+	ret = meson_gpiolib_register(pc);
+	if (ret) {
+		pinctrl_unregister(pc->pcdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static struct platform_driver meson_pinctrl_driver = {
+	.probe		= meson_pinctrl_probe,
+	.driver = {
+		.name	= "meson-pinctrl",
+		.of_match_table = meson_pinctrl_dt_match,
+	},
+};
+module_platform_driver(meson_pinctrl_driver);
+
+MODULE_AUTHOR("Beniamino Galvani <b.galvani@gmail.com>");
+MODULE_DESCRIPTION("Amlogic Meson pinctrl driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/meson/pinctrl-meson.h b/drivers/pinctrl/meson/pinctrl-meson.h
new file mode 100644
index 00000000000..bfea8adc795
--- /dev/null
+++ b/drivers/pinctrl/meson/pinctrl-meson.h
@@ -0,0 +1,209 @@
+/*
+ * Pin controller and GPIO driver for Amlogic Meson SoCs
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/gpio.h>
+#include <linux/pinctrl/pinctrl.h>
+#include <linux/regmap.h>
+#include <linux/types.h>
+
+/**
+ * struct meson_pmx_group - a pinmux group
+ *
+ * @name:	group name
+ * @pins:	pins in the group
+ * @num_pins:	number of pins in the group
+ * @is_gpio:	whether the group is a single GPIO group
+ * @reg:	register offset for the group in the domain mux registers
+ * @bit		bit index enabling the group
+ * @domain:	index of the domain this group belongs to
+ */
+struct meson_pmx_group {
+	const char *name;
+	const unsigned int *pins;
+	unsigned int num_pins;
+	bool is_gpio;
+	unsigned int reg;
+	unsigned int bit;
+	unsigned int domain;
+};
+
+/**
+ * struct meson_pmx_func - a pinmux function
+ *
+ * @name:	function name
+ * @groups:	groups in the function
+ * @num_groups:	number of groups in the function
+ */
+struct meson_pmx_func {
+	const char *name;
+	const char * const *groups;
+	unsigned int num_groups;
+};
+
+/**
+ * struct meson_reg_desc - a register descriptor
+ *
+ * @reg:	register offset in the regmap
+ * @bit:	bit index in register
+ *
+ * The structure describes the information needed to control pull,
+ * pull-enable, direction, etc. for a single pin
+ */
+struct meson_reg_desc {
+	unsigned int reg;
+	unsigned int bit;
+};
+
+/**
+ * enum meson_reg_type - type of registers encoded in @meson_reg_desc
+ */
+enum meson_reg_type {
+	REG_PULLEN,
+	REG_PULL,
+	REG_DIR,
+	REG_OUT,
+	REG_IN,
+	NUM_REG,
+};
+
+/**
+ * struct meson bank
+ *
+ * @name:	bank name
+ * @first:	first pin of the bank
+ * @last:	last pin of the bank
+ * @regs:	array of register descriptors
+ *
+ * A bank represents a set of pins controlled by a contiguous set of
+ * bits in the domain registers. The structure specifies which bits in
+ * the regmap control the different functionalities. Each member of
+ * the @regs array refers to the first pin of the bank.
+ */
+struct meson_bank {
+	const char *name;
+	unsigned int first;
+	unsigned int last;
+	struct meson_reg_desc regs[NUM_REG];
+};
+
+/**
+ * struct meson_domain_data - domain platform data
+ *
+ * @name:	name of the domain
+ * @banks:	set of banks belonging to the domain
+ * @num_banks:	number of banks in the domain
+ */
+struct meson_domain_data {
+	const char *name;
+	struct meson_bank *banks;
+	unsigned int num_banks;
+	unsigned int pin_base;
+	unsigned int num_pins;
+};
+
+/**
+ * struct meson_domain
+ *
+ * @reg_mux:	registers for mux settings
+ * @reg_pullen:	registers for pull-enable settings
+ * @reg_pull:	registers for pull settings
+ * @reg_gpio:	registers for gpio settings
+ * @chip:	gpio chip associated with the domain
+ * @data;	platform data for the domain
+ * @node:	device tree node for the domain
+ *
+ * A domain represents a set of banks controlled by the same set of
+ * registers.
+ */
+struct meson_domain {
+	struct regmap *reg_mux;
+	struct regmap *reg_pullen;
+	struct regmap *reg_pull;
+	struct regmap *reg_gpio;
+
+	struct gpio_chip chip;
+	struct meson_domain_data *data;
+	struct device_node *of_node;
+};
+
+struct meson_pinctrl_data {
+	const struct pinctrl_pin_desc *pins;
+	struct meson_pmx_group *groups;
+	struct meson_pmx_func *funcs;
+	struct meson_domain_data *domain_data;
+	unsigned int num_pins;
+	unsigned int num_groups;
+	unsigned int num_funcs;
+	unsigned int num_domains;
+};
+
+struct meson_pinctrl {
+	struct device *dev;
+	struct pinctrl_dev *pcdev;
+	struct pinctrl_desc desc;
+	struct meson_pinctrl_data *data;
+	struct meson_domain *domains;
+};
+
+#define GROUP(grp, r, b)						\
+	{								\
+		.name = #grp,						\
+		.pins = grp ## _pins,					\
+		.num_pins = ARRAY_SIZE(grp ## _pins),			\
+		.reg = r,						\
+		.bit = b,						\
+		.domain = 0,						\
+	 }
+
+#define GPIO_GROUP(gpio)						\
+	{								\
+		.name = #gpio,						\
+		.pins = (const unsigned int[]){ PIN_ ## gpio},		\
+		.num_pins = 1,						\
+		.is_gpio = true,					\
+	 }
+
+#define GROUP_AO(grp, r, b)						\
+	{								\
+		.name = #grp,						\
+		.pins = grp ## _pins,					\
+		.num_pins = ARRAY_SIZE(grp ## _pins),			\
+		.reg = r,						\
+		.bit = b,						\
+		.domain = 1,						\
+	 }
+
+#define FUNCTION(fn)							\
+	{								\
+		.name = #fn,						\
+		.groups = fn ## _groups,				\
+		.num_groups = ARRAY_SIZE(fn ## _groups),		\
+	}
+
+#define BANK(n, f, l, per, peb, pr, pb, dr, db, or, ob, ir, ib)		\
+	{								\
+		.name	= n,						\
+		.first	= f,						\
+		.last	= l,						\
+		.regs	= {						\
+			[REG_PULLEN]	= { per, peb },			\
+			[REG_PULL]	= { pr, pb },			\
+			[REG_DIR]	= { dr, db },			\
+			[REG_OUT]	= { or, ob },			\
+			[REG_IN]	= { ir, ib },			\
+		},							\
+	 }
+
+#define MESON_PIN(x) PINCTRL_PIN(PIN_ ## x, #x)
+
+extern struct meson_pinctrl_data meson8_pinctrl_data;
diff --git a/drivers/pinctrl/meson/pinctrl-meson8.c b/drivers/pinctrl/meson/pinctrl-meson8.c
new file mode 100644
index 00000000000..f8aa3a28176
--- /dev/null
+++ b/drivers/pinctrl/meson/pinctrl-meson8.c
@@ -0,0 +1,1089 @@
+/*
+ * Pin controller and GPIO driver for Amlogic Meson8.
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <dt-bindings/gpio/meson8-gpio.h>
+#include "pinctrl-meson.h"
+
+#define AO_OFFSET	120
+
+#define PIN_GPIOX_0	GPIOX_0
+#define PIN_GPIOX_1	GPIOX_1
+#define PIN_GPIOX_2	GPIOX_2
+#define PIN_GPIOX_3	GPIOX_3
+#define PIN_GPIOX_4	GPIOX_4
+#define PIN_GPIOX_5	GPIOX_5
+#define PIN_GPIOX_6	GPIOX_6
+#define PIN_GPIOX_7	GPIOX_7
+#define PIN_GPIOX_8	GPIOX_8
+#define PIN_GPIOX_9	GPIOX_9
+#define PIN_GPIOX_10	GPIOX_10
+#define PIN_GPIOX_11	GPIOX_11
+#define PIN_GPIOX_12	GPIOX_12
+#define PIN_GPIOX_13	GPIOX_13
+#define PIN_GPIOX_14	GPIOX_14
+#define PIN_GPIOX_15	GPIOX_15
+#define PIN_GPIOX_16	GPIOX_16
+#define PIN_GPIOX_17	GPIOX_17
+#define PIN_GPIOX_18	GPIOX_18
+#define PIN_GPIOX_19	GPIOX_19
+#define PIN_GPIOX_20	GPIOX_20
+#define PIN_GPIOX_21	GPIOX_21
+#define PIN_GPIOY_0	GPIOY_0
+#define PIN_GPIOY_1	GPIOY_1
+#define PIN_GPIOY_2	GPIOY_2
+#define PIN_GPIOY_3	GPIOY_3
+#define PIN_GPIOY_4	GPIOY_4
+#define PIN_GPIOY_5	GPIOY_5
+#define PIN_GPIOY_6	GPIOY_6
+#define PIN_GPIOY_7	GPIOY_7
+#define PIN_GPIOY_8	GPIOY_8
+#define PIN_GPIOY_9	GPIOY_9
+#define PIN_GPIOY_10	GPIOY_10
+#define PIN_GPIOY_11	GPIOY_11
+#define PIN_GPIOY_12	GPIOY_12
+#define PIN_GPIOY_13	GPIOY_13
+#define PIN_GPIOY_14	GPIOY_14
+#define PIN_GPIOY_15	GPIOY_15
+#define PIN_GPIOY_16	GPIOY_16
+#define PIN_GPIODV_0	GPIODV_0
+#define PIN_GPIODV_1	GPIODV_1
+#define PIN_GPIODV_2	GPIODV_2
+#define PIN_GPIODV_3	GPIODV_3
+#define PIN_GPIODV_4	GPIODV_4
+#define PIN_GPIODV_5	GPIODV_5
+#define PIN_GPIODV_6	GPIODV_6
+#define PIN_GPIODV_7	GPIODV_7
+#define PIN_GPIODV_8	GPIODV_8
+#define PIN_GPIODV_9	GPIODV_9
+#define PIN_GPIODV_10	GPIODV_10
+#define PIN_GPIODV_11	GPIODV_11
+#define PIN_GPIODV_12	GPIODV_12
+#define PIN_GPIODV_13	GPIODV_13
+#define PIN_GPIODV_14	GPIODV_14
+#define PIN_GPIODV_15	GPIODV_15
+#define PIN_GPIODV_16	GPIODV_16
+#define PIN_GPIODV_17	GPIODV_17
+#define PIN_GPIODV_18	GPIODV_18
+#define PIN_GPIODV_19	GPIODV_19
+#define PIN_GPIODV_20	GPIODV_20
+#define PIN_GPIODV_21	GPIODV_21
+#define PIN_GPIODV_22	GPIODV_22
+#define PIN_GPIODV_23	GPIODV_23
+#define PIN_GPIODV_24	GPIODV_24
+#define PIN_GPIODV_25	GPIODV_25
+#define PIN_GPIODV_26	GPIODV_26
+#define PIN_GPIODV_27	GPIODV_27
+#define PIN_GPIODV_28	GPIODV_28
+#define PIN_GPIODV_29	GPIODV_29
+#define PIN_GPIOH_0	GPIOH_0
+#define PIN_GPIOH_1	GPIOH_1
+#define PIN_GPIOH_2	GPIOH_2
+#define PIN_GPIOH_3	GPIOH_3
+#define PIN_GPIOH_4	GPIOH_4
+#define PIN_GPIOH_5	GPIOH_5
+#define PIN_GPIOH_6	GPIOH_6
+#define PIN_GPIOH_7	GPIOH_7
+#define PIN_GPIOH_8	GPIOH_8
+#define PIN_GPIOH_9	GPIOH_9
+#define PIN_GPIOZ_0	GPIOZ_0
+#define PIN_GPIOZ_1	GPIOZ_1
+#define PIN_GPIOZ_2	GPIOZ_2
+#define PIN_GPIOZ_3	GPIOZ_3
+#define PIN_GPIOZ_4	GPIOZ_4
+#define PIN_GPIOZ_5	GPIOZ_5
+#define PIN_GPIOZ_6	GPIOZ_6
+#define PIN_GPIOZ_7	GPIOZ_7
+#define PIN_GPIOZ_8	GPIOZ_8
+#define PIN_GPIOZ_9	GPIOZ_9
+#define PIN_GPIOZ_10	GPIOZ_10
+#define PIN_GPIOZ_11	GPIOZ_11
+#define PIN_GPIOZ_12	GPIOZ_12
+#define PIN_GPIOZ_13	GPIOZ_13
+#define PIN_GPIOZ_14	GPIOZ_14
+#define PIN_CARD_0	CARD_0
+#define PIN_CARD_1	CARD_1
+#define PIN_CARD_2	CARD_2
+#define PIN_CARD_3	CARD_3
+#define PIN_CARD_4	CARD_4
+#define PIN_CARD_5	CARD_5
+#define PIN_CARD_6	CARD_6
+#define PIN_BOOT_0	BOOT_0
+#define PIN_BOOT_1	BOOT_1
+#define PIN_BOOT_2	BOOT_2
+#define PIN_BOOT_3	BOOT_3
+#define PIN_BOOT_4	BOOT_4
+#define PIN_BOOT_5	BOOT_5
+#define PIN_BOOT_6	BOOT_6
+#define PIN_BOOT_7	BOOT_7
+#define PIN_BOOT_8	BOOT_8
+#define PIN_BOOT_9	BOOT_9
+#define PIN_BOOT_10	BOOT_10
+#define PIN_BOOT_11	BOOT_11
+#define PIN_BOOT_12	BOOT_12
+#define PIN_BOOT_13	BOOT_13
+#define PIN_BOOT_14	BOOT_14
+#define PIN_BOOT_15	BOOT_15
+#define PIN_BOOT_16	BOOT_16
+#define PIN_BOOT_17	BOOT_17
+#define PIN_BOOT_18	BOOT_18
+
+#define PIN_GPIOAO_0	(AO_OFFSET + GPIOAO_0)
+#define PIN_GPIOAO_1	(AO_OFFSET + GPIOAO_1)
+#define PIN_GPIOAO_2	(AO_OFFSET + GPIOAO_2)
+#define PIN_GPIOAO_3	(AO_OFFSET + GPIOAO_3)
+#define PIN_GPIOAO_4	(AO_OFFSET + GPIOAO_4)
+#define PIN_GPIOAO_5	(AO_OFFSET + GPIOAO_5)
+#define PIN_GPIOAO_6	(AO_OFFSET + GPIOAO_6)
+#define PIN_GPIOAO_7	(AO_OFFSET + GPIOAO_7)
+#define PIN_GPIOAO_8	(AO_OFFSET + GPIOAO_8)
+#define PIN_GPIOAO_9	(AO_OFFSET + GPIOAO_9)
+#define PIN_GPIOAO_10	(AO_OFFSET + GPIOAO_10)
+#define PIN_GPIOAO_11	(AO_OFFSET + GPIOAO_11)
+#define PIN_GPIOAO_12	(AO_OFFSET + GPIOAO_12)
+#define PIN_GPIOAO_13	(AO_OFFSET + GPIOAO_13)
+#define PIN_GPIO_BSD_EN	(AO_OFFSET + GPIO_BSD_EN)
+#define PIN_GPIO_TEST_N	(AO_OFFSET + GPIO_TEST_N)
+
+static const struct pinctrl_pin_desc meson8_pins[] = {
+	MESON_PIN(GPIOX_0),
+	MESON_PIN(GPIOX_1),
+	MESON_PIN(GPIOX_2),
+	MESON_PIN(GPIOX_3),
+	MESON_PIN(GPIOX_4),
+	MESON_PIN(GPIOX_5),
+	MESON_PIN(GPIOX_6),
+	MESON_PIN(GPIOX_7),
+	MESON_PIN(GPIOX_8),
+	MESON_PIN(GPIOX_9),
+	MESON_PIN(GPIOX_10),
+	MESON_PIN(GPIOX_11),
+	MESON_PIN(GPIOX_12),
+	MESON_PIN(GPIOX_13),
+	MESON_PIN(GPIOX_14),
+	MESON_PIN(GPIOX_15),
+	MESON_PIN(GPIOX_16),
+	MESON_PIN(GPIOX_17),
+	MESON_PIN(GPIOX_18),
+	MESON_PIN(GPIOX_19),
+	MESON_PIN(GPIOX_20),
+	MESON_PIN(GPIOX_21),
+	MESON_PIN(GPIOY_0),
+	MESON_PIN(GPIOY_1),
+	MESON_PIN(GPIOY_2),
+	MESON_PIN(GPIOY_3),
+	MESON_PIN(GPIOY_4),
+	MESON_PIN(GPIOY_5),
+	MESON_PIN(GPIOY_6),
+	MESON_PIN(GPIOY_7),
+	MESON_PIN(GPIOY_8),
+	MESON_PIN(GPIOY_9),
+	MESON_PIN(GPIOY_10),
+	MESON_PIN(GPIOY_11),
+	MESON_PIN(GPIOY_12),
+	MESON_PIN(GPIOY_13),
+	MESON_PIN(GPIOY_14),
+	MESON_PIN(GPIOY_15),
+	MESON_PIN(GPIOY_16),
+	MESON_PIN(GPIODV_0),
+	MESON_PIN(GPIODV_1),
+	MESON_PIN(GPIODV_2),
+	MESON_PIN(GPIODV_3),
+	MESON_PIN(GPIODV_4),
+	MESON_PIN(GPIODV_5),
+	MESON_PIN(GPIODV_6),
+	MESON_PIN(GPIODV_7),
+	MESON_PIN(GPIODV_8),
+	MESON_PIN(GPIODV_9),
+	MESON_PIN(GPIODV_10),
+	MESON_PIN(GPIODV_11),
+	MESON_PIN(GPIODV_12),
+	MESON_PIN(GPIODV_13),
+	MESON_PIN(GPIODV_14),
+	MESON_PIN(GPIODV_15),
+	MESON_PIN(GPIODV_16),
+	MESON_PIN(GPIODV_17),
+	MESON_PIN(GPIODV_18),
+	MESON_PIN(GPIODV_19),
+	MESON_PIN(GPIODV_20),
+	MESON_PIN(GPIODV_21),
+	MESON_PIN(GPIODV_22),
+	MESON_PIN(GPIODV_23),
+	MESON_PIN(GPIODV_24),
+	MESON_PIN(GPIODV_25),
+	MESON_PIN(GPIODV_26),
+	MESON_PIN(GPIODV_27),
+	MESON_PIN(GPIODV_28),
+	MESON_PIN(GPIODV_29),
+	MESON_PIN(GPIOH_0),
+	MESON_PIN(GPIOH_1),
+	MESON_PIN(GPIOH_2),
+	MESON_PIN(GPIOH_3),
+	MESON_PIN(GPIOH_4),
+	MESON_PIN(GPIOH_5),
+	MESON_PIN(GPIOH_6),
+	MESON_PIN(GPIOH_7),
+	MESON_PIN(GPIOH_8),
+	MESON_PIN(GPIOH_9),
+	MESON_PIN(GPIOZ_0),
+	MESON_PIN(GPIOZ_1),
+	MESON_PIN(GPIOZ_2),
+	MESON_PIN(GPIOZ_3),
+	MESON_PIN(GPIOZ_4),
+	MESON_PIN(GPIOZ_5),
+	MESON_PIN(GPIOZ_6),
+	MESON_PIN(GPIOZ_7),
+	MESON_PIN(GPIOZ_8),
+	MESON_PIN(GPIOZ_9),
+	MESON_PIN(GPIOZ_10),
+	MESON_PIN(GPIOZ_11),
+	MESON_PIN(GPIOZ_12),
+	MESON_PIN(GPIOZ_13),
+	MESON_PIN(GPIOZ_14),
+	MESON_PIN(CARD_0),
+	MESON_PIN(CARD_1),
+	MESON_PIN(CARD_2),
+	MESON_PIN(CARD_3),
+	MESON_PIN(CARD_4),
+	MESON_PIN(CARD_5),
+	MESON_PIN(CARD_6),
+	MESON_PIN(BOOT_0),
+	MESON_PIN(BOOT_1),
+	MESON_PIN(BOOT_2),
+	MESON_PIN(BOOT_3),
+	MESON_PIN(BOOT_4),
+	MESON_PIN(BOOT_5),
+	MESON_PIN(BOOT_6),
+	MESON_PIN(BOOT_7),
+	MESON_PIN(BOOT_8),
+	MESON_PIN(BOOT_9),
+	MESON_PIN(BOOT_10),
+	MESON_PIN(BOOT_11),
+	MESON_PIN(BOOT_12),
+	MESON_PIN(BOOT_13),
+	MESON_PIN(BOOT_14),
+	MESON_PIN(BOOT_15),
+	MESON_PIN(BOOT_16),
+	MESON_PIN(BOOT_17),
+	MESON_PIN(BOOT_18),
+	MESON_PIN(GPIOAO_0),
+	MESON_PIN(GPIOAO_1),
+	MESON_PIN(GPIOAO_2),
+	MESON_PIN(GPIOAO_3),
+	MESON_PIN(GPIOAO_4),
+	MESON_PIN(GPIOAO_5),
+	MESON_PIN(GPIOAO_6),
+	MESON_PIN(GPIOAO_7),
+	MESON_PIN(GPIOAO_8),
+	MESON_PIN(GPIOAO_9),
+	MESON_PIN(GPIOAO_10),
+	MESON_PIN(GPIOAO_11),
+	MESON_PIN(GPIOAO_12),
+	MESON_PIN(GPIOAO_13),
+	MESON_PIN(GPIO_BSD_EN),
+	MESON_PIN(GPIO_TEST_N),
+};
+
+/* bank X */
+static const unsigned int sd_d0_a_pins[] = { PIN_GPIOX_0 };
+static const unsigned int sd_d1_a_pins[] = { PIN_GPIOX_1 };
+static const unsigned int sd_d2_a_pins[] = { PIN_GPIOX_2 };
+static const unsigned int sd_d3_a_pins[] = { PIN_GPIOX_3 };
+static const unsigned int sd_clk_a_pins[] = { PIN_GPIOX_8 };
+static const unsigned int sd_cmd_a_pins[] = { PIN_GPIOX_9 };
+
+static const unsigned int sdxc_d0_a_pins[] = { PIN_GPIOX_0 };
+static const unsigned int sdxc_d13_a_pins[] = { PIN_GPIOX_1, PIN_GPIOX_2,
+						PIN_GPIOX_3 };
+static const unsigned int sdxc_d47_a_pins[] = { PIN_GPIOX_4, PIN_GPIOX_5,
+						PIN_GPIOX_6, PIN_GPIOX_7 };
+static const unsigned int sdxc_clk_a_pins[] = { PIN_GPIOX_8 };
+static const unsigned int sdxc_cmd_a_pins[] = { PIN_GPIOX_9 };
+
+static const unsigned int pcm_out_a_pins[] = { PIN_GPIOX_4 };
+static const unsigned int pcm_in_a_pins[] = { PIN_GPIOX_5 };
+static const unsigned int pcm_fs_a_pins[] = { PIN_GPIOX_6 };
+static const unsigned int pcm_clk_a_pins[] = { PIN_GPIOX_7 };
+
+static const unsigned int uart_tx_a0_pins[] = { PIN_GPIOX_4 };
+static const unsigned int uart_rx_a0_pins[] = { PIN_GPIOX_5 };
+static const unsigned int uart_cts_a0_pins[] = { PIN_GPIOX_6 };
+static const unsigned int uart_rts_a0_pins[] = { PIN_GPIOX_7 };
+
+static const unsigned int uart_tx_a1_pins[] = { PIN_GPIOX_12 };
+static const unsigned int uart_rx_a1_pins[] = { PIN_GPIOX_13 };
+static const unsigned int uart_cts_a1_pins[] = { PIN_GPIOX_14 };
+static const unsigned int uart_rts_a1_pins[] = { PIN_GPIOX_15 };
+
+static const unsigned int uart_tx_b0_pins[] = { PIN_GPIOX_16 };
+static const unsigned int uart_rx_b0_pins[] = { PIN_GPIOX_17 };
+static const unsigned int uart_cts_b0_pins[] = { PIN_GPIOX_18 };
+static const unsigned int uart_rts_b0_pins[] = { PIN_GPIOX_19 };
+
+static const unsigned int iso7816_det_pins[] = { PIN_GPIOX_16 };
+static const unsigned int iso7816_reset_pins[] = { PIN_GPIOX_17 };
+static const unsigned int iso7816_clk_pins[] = { PIN_GPIOX_18 };
+static const unsigned int iso7816_data_pins[] = { PIN_GPIOX_19 };
+
+static const unsigned int i2c_sda_d0_pins[] = { PIN_GPIOX_16 };
+static const unsigned int i2c_sck_d0_pins[] = { PIN_GPIOX_17 };
+
+static const unsigned int xtal_32k_out_pins[] = { PIN_GPIOX_10 };
+static const unsigned int xtal_24m_out_pins[] = { PIN_GPIOX_11 };
+
+/* bank Y */
+static const unsigned int uart_tx_c_pins[] = { PIN_GPIOY_0 };
+static const unsigned int uart_rx_c_pins[] = { PIN_GPIOY_1 };
+static const unsigned int uart_cts_c_pins[] = { PIN_GPIOY_2 };
+static const unsigned int uart_rts_c_pins[] = { PIN_GPIOY_3 };
+
+static const unsigned int pcm_out_b_pins[] = { PIN_GPIOY_4 };
+static const unsigned int pcm_in_b_pins[] = { PIN_GPIOY_5 };
+static const unsigned int pcm_fs_b_pins[] = { PIN_GPIOY_6 };
+static const unsigned int pcm_clk_b_pins[] = { PIN_GPIOY_7 };
+
+static const unsigned int i2c_sda_c0_pins[] = { PIN_GPIOY_0 };
+static const unsigned int i2c_sck_c0_pins[] = { PIN_GPIOY_1 };
+
+/* bank DV */
+static const unsigned int dvin_rgb_pins[] = { PIN_GPIODV_0, PIN_GPIODV_1,
+					      PIN_GPIODV_2, PIN_GPIODV_3,
+					      PIN_GPIODV_4, PIN_GPIODV_5,
+					      PIN_GPIODV_6, PIN_GPIODV_7,
+					      PIN_GPIODV_8, PIN_GPIODV_9,
+					      PIN_GPIODV_10, PIN_GPIODV_11,
+					      PIN_GPIODV_12, PIN_GPIODV_13,
+					      PIN_GPIODV_14, PIN_GPIODV_15,
+					      PIN_GPIODV_16, PIN_GPIODV_17,
+					      PIN_GPIODV_18, PIN_GPIODV_19,
+					      PIN_GPIODV_20, PIN_GPIODV_21,
+					      PIN_GPIODV_22, PIN_GPIODV_23 };
+static const unsigned int dvin_vs_pins[] = { PIN_GPIODV_24 };
+static const unsigned int dvin_hs_pins[] = { PIN_GPIODV_25 };
+static const unsigned int dvin_clk_pins[] = { PIN_GPIODV_26 };
+static const unsigned int dvin_de_pins[] = { PIN_GPIODV_27 };
+
+static const unsigned int enc_0_pins[] = { PIN_GPIODV_0 };
+static const unsigned int enc_1_pins[] = { PIN_GPIODV_1 };
+static const unsigned int enc_2_pins[] = { PIN_GPIODV_2 };
+static const unsigned int enc_3_pins[] = { PIN_GPIODV_3 };
+static const unsigned int enc_4_pins[] = { PIN_GPIODV_4 };
+static const unsigned int enc_5_pins[] = { PIN_GPIODV_5 };
+static const unsigned int enc_6_pins[] = { PIN_GPIODV_6 };
+static const unsigned int enc_7_pins[] = { PIN_GPIODV_7 };
+static const unsigned int enc_8_pins[] = { PIN_GPIODV_8 };
+static const unsigned int enc_9_pins[] = { PIN_GPIODV_9 };
+static const unsigned int enc_10_pins[] = { PIN_GPIODV_10 };
+static const unsigned int enc_11_pins[] = { PIN_GPIODV_11 };
+static const unsigned int enc_12_pins[] = { PIN_GPIODV_12 };
+static const unsigned int enc_13_pins[] = { PIN_GPIODV_13 };
+static const unsigned int enc_14_pins[] = { PIN_GPIODV_14 };
+static const unsigned int enc_15_pins[] = { PIN_GPIODV_15 };
+static const unsigned int enc_16_pins[] = { PIN_GPIODV_16 };
+static const unsigned int enc_17_pins[] = { PIN_GPIODV_17 };
+
+static const unsigned int uart_tx_b1_pins[] = { PIN_GPIODV_24 };
+static const unsigned int uart_rx_b1_pins[] = { PIN_GPIODV_25 };
+static const unsigned int uart_cts_b1_pins[] = { PIN_GPIODV_26 };
+static const unsigned int uart_rts_b1_pins[] = { PIN_GPIODV_27 };
+
+static const unsigned int vga_vs_pins[] = { PIN_GPIODV_24 };
+static const unsigned int vga_hs_pins[] = { PIN_GPIODV_25 };
+
+/* bank H */
+static const unsigned int hdmi_hpd_pins[] = { PIN_GPIOH_0 };
+static const unsigned int hdmi_sda_pins[] = { PIN_GPIOH_1 };
+static const unsigned int hdmi_scl_pins[] = { PIN_GPIOH_2 };
+static const unsigned int hdmi_cec_pins[] = { PIN_GPIOH_3 };
+
+static const unsigned int spi_ss0_0_pins[] = { PIN_GPIOH_3 };
+static const unsigned int spi_miso_0_pins[] = { PIN_GPIOH_4 };
+static const unsigned int spi_mosi_0_pins[] = { PIN_GPIOH_5 };
+static const unsigned int spi_sclk_0_pins[] = { PIN_GPIOH_6 };
+
+static const unsigned int i2c_sda_d1_pins[] = { PIN_GPIOH_7 };
+static const unsigned int i2c_sck_d1_pins[] = { PIN_GPIOH_8 };
+
+/* bank Z */
+static const unsigned int spi_ss0_1_pins[] = { PIN_GPIOZ_9 };
+static const unsigned int spi_ss1_1_pins[] = { PIN_GPIOZ_10 };
+static const unsigned int spi_sclk_1_pins[] = { PIN_GPIOZ_11 };
+static const unsigned int spi_mosi_1_pins[] = { PIN_GPIOZ_12 };
+static const unsigned int spi_miso_1_pins[] = { PIN_GPIOZ_13 };
+static const unsigned int spi_ss2_1_pins[] = { PIN_GPIOZ_14 };
+
+static const unsigned int eth_tx_clk_50m_pins[] = { PIN_GPIOZ_4 };
+static const unsigned int eth_tx_en_pins[] = { PIN_GPIOZ_5 };
+static const unsigned int eth_txd1_pins[] = { PIN_GPIOZ_6 };
+static const unsigned int eth_txd0_pins[] = { PIN_GPIOZ_7 };
+static const unsigned int eth_rx_clk_in_pins[] = { PIN_GPIOZ_8 };
+static const unsigned int eth_rx_dv_pins[] = { PIN_GPIOZ_9 };
+static const unsigned int eth_rxd1_pins[] = { PIN_GPIOZ_10 };
+static const unsigned int eth_rxd0_pins[] = { PIN_GPIOZ_11 };
+static const unsigned int eth_mdio_pins[] = { PIN_GPIOZ_12 };
+static const unsigned int eth_mdc_pins[] = { PIN_GPIOZ_13 };
+
+static const unsigned int i2c_sda_a0_pins[] = { PIN_GPIOZ_0 };
+static const unsigned int i2c_sck_a0_pins[] = { PIN_GPIOZ_1 };
+
+static const unsigned int i2c_sda_b_pins[] = { PIN_GPIOZ_2 };
+static const unsigned int i2c_sck_b_pins[] = { PIN_GPIOZ_3 };
+
+static const unsigned int i2c_sda_c1_pins[] = { PIN_GPIOZ_4 };
+static const unsigned int i2c_sck_c1_pins[] = { PIN_GPIOZ_5 };
+
+static const unsigned int i2c_sda_a1_pins[] = { PIN_GPIOZ_0 };
+static const unsigned int i2c_sck_a1_pins[] = { PIN_GPIOZ_1 };
+
+static const unsigned int i2c_sda_a2_pins[] = { PIN_GPIOZ_0 };
+static const unsigned int i2c_sck_a2_pins[] = { PIN_GPIOZ_1 };
+
+/* bank BOOT */
+static const unsigned int sd_d0_c_pins[] = { PIN_BOOT_0 };
+static const unsigned int sd_d1_c_pins[] = { PIN_BOOT_1 };
+static const unsigned int sd_d2_c_pins[] = { PIN_BOOT_2 };
+static const unsigned int sd_d3_c_pins[] = { PIN_BOOT_3 };
+static const unsigned int sd_cmd_c_pins[] = { PIN_BOOT_16 };
+static const unsigned int sd_clk_c_pins[] = { PIN_BOOT_17 };
+
+static const unsigned int sdxc_d0_c_pins[] = { PIN_BOOT_0};
+static const unsigned int sdxc_d13_c_pins[] = { PIN_BOOT_1, PIN_BOOT_2,
+						PIN_BOOT_3 };
+static const unsigned int sdxc_d47_c_pins[] = { PIN_BOOT_4, PIN_BOOT_5,
+						PIN_BOOT_6, PIN_BOOT_7 };
+static const unsigned int sdxc_cmd_c_pins[] = { PIN_BOOT_16 };
+static const unsigned int sdxc_clk_c_pins[] = { PIN_BOOT_17 };
+
+static const unsigned int nand_io_pins[] = { PIN_BOOT_0, PIN_BOOT_1,
+					     PIN_BOOT_2, PIN_BOOT_3,
+					     PIN_BOOT_4, PIN_BOOT_5,
+					     PIN_BOOT_6, PIN_BOOT_7 };
+static const unsigned int nand_io_ce0_pins[] = { PIN_BOOT_8 };
+static const unsigned int nand_io_ce1_pins[] = { PIN_BOOT_9 };
+static const unsigned int nand_io_rb0_pins[] = { PIN_BOOT_10 };
+static const unsigned int nand_ale_pins[] = { PIN_BOOT_11 };
+static const unsigned int nand_cle_pins[] = { PIN_BOOT_12 };
+static const unsigned int nand_wen_clk_pins[] = { PIN_BOOT_13 };
+static const unsigned int nand_ren_clk_pins[] = { PIN_BOOT_14 };
+static const unsigned int nand_dqs_pins[] = { PIN_BOOT_15 };
+static const unsigned int nand_ce2_pins[] = { PIN_BOOT_16 };
+static const unsigned int nand_ce3_pins[] = { PIN_BOOT_17 };
+
+static const unsigned int nor_d_pins[] = { PIN_BOOT_11 };
+static const unsigned int nor_q_pins[] = { PIN_BOOT_12 };
+static const unsigned int nor_c_pins[] = { PIN_BOOT_13 };
+static const unsigned int nor_cs_pins[] = { PIN_BOOT_18 };
+
+/* bank CARD */
+static const unsigned int sd_d1_b_pins[] = { PIN_CARD_0 };
+static const unsigned int sd_d0_b_pins[] = { PIN_CARD_1 };
+static const unsigned int sd_clk_b_pins[] = { PIN_CARD_2 };
+static const unsigned int sd_cmd_b_pins[] = { PIN_CARD_3 };
+static const unsigned int sd_d3_b_pins[] = { PIN_CARD_4 };
+static const unsigned int sd_d2_b_pins[] = { PIN_CARD_5 };
+
+static const unsigned int sdxc_d13_b_pins[] = { PIN_CARD_0, PIN_CARD_4,
+						PIN_CARD_5 };
+static const unsigned int sdxc_d0_b_pins[] = { PIN_CARD_1 };
+static const unsigned int sdxc_clk_b_pins[] = { PIN_CARD_2 };
+static const unsigned int sdxc_cmd_b_pins[] = { PIN_CARD_3 };
+
+/* bank AO */
+static const unsigned int uart_tx_ao_a_pins[] = { PIN_GPIOAO_0 };
+static const unsigned int uart_rx_ao_a_pins[] = { PIN_GPIOAO_1 };
+static const unsigned int uart_cts_ao_a_pins[] = { PIN_GPIOAO_2 };
+static const unsigned int uart_rts_ao_a_pins[] = { PIN_GPIOAO_3 };
+
+static const unsigned int remote_input_pins[] = { PIN_GPIOAO_7 };
+
+static const unsigned int i2c_slave_sck_ao_pins[] = { PIN_GPIOAO_4 };
+static const unsigned int i2c_slave_sda_ao_pins[] = { PIN_GPIOAO_5 };
+
+static const unsigned int uart_tx_ao_b0_pins[] = { PIN_GPIOAO_0 };
+static const unsigned int uart_rx_ao_b0_pins[] = { PIN_GPIOAO_1 };
+
+static const unsigned int uart_tx_ao_b1_pins[] = { PIN_GPIOAO_4 };
+static const unsigned int uart_rx_ao_b1_pins[] = { PIN_GPIOAO_5 };
+
+static const unsigned int i2c_mst_sck_ao_pins[] = { PIN_GPIOAO_4 };
+static const unsigned int i2c_mst_sda_ao_pins[] = { PIN_GPIOAO_5 };
+
+static struct meson_pmx_group meson8_groups[] = {
+	GPIO_GROUP(GPIOX_0),
+	GPIO_GROUP(GPIOX_1),
+	GPIO_GROUP(GPIOX_2),
+	GPIO_GROUP(GPIOX_3),
+	GPIO_GROUP(GPIOX_4),
+	GPIO_GROUP(GPIOX_5),
+	GPIO_GROUP(GPIOX_6),
+	GPIO_GROUP(GPIOX_7),
+	GPIO_GROUP(GPIOX_8),
+	GPIO_GROUP(GPIOX_9),
+	GPIO_GROUP(GPIOX_10),
+	GPIO_GROUP(GPIOX_11),
+	GPIO_GROUP(GPIOX_12),
+	GPIO_GROUP(GPIOX_13),
+	GPIO_GROUP(GPIOX_14),
+	GPIO_GROUP(GPIOX_15),
+	GPIO_GROUP(GPIOX_16),
+	GPIO_GROUP(GPIOX_17),
+	GPIO_GROUP(GPIOX_18),
+	GPIO_GROUP(GPIOX_19),
+	GPIO_GROUP(GPIOX_20),
+	GPIO_GROUP(GPIOX_21),
+	GPIO_GROUP(GPIOY_0),
+	GPIO_GROUP(GPIOY_1),
+	GPIO_GROUP(GPIOY_2),
+	GPIO_GROUP(GPIOY_3),
+	GPIO_GROUP(GPIOY_4),
+	GPIO_GROUP(GPIOY_5),
+	GPIO_GROUP(GPIOY_6),
+	GPIO_GROUP(GPIOY_7),
+	GPIO_GROUP(GPIOY_8),
+	GPIO_GROUP(GPIOY_9),
+	GPIO_GROUP(GPIOY_10),
+	GPIO_GROUP(GPIOY_11),
+	GPIO_GROUP(GPIOY_12),
+	GPIO_GROUP(GPIOY_13),
+	GPIO_GROUP(GPIOY_14),
+	GPIO_GROUP(GPIOY_15),
+	GPIO_GROUP(GPIOY_16),
+	GPIO_GROUP(GPIODV_0),
+	GPIO_GROUP(GPIODV_1),
+	GPIO_GROUP(GPIODV_2),
+	GPIO_GROUP(GPIODV_3),
+	GPIO_GROUP(GPIODV_4),
+	GPIO_GROUP(GPIODV_5),
+	GPIO_GROUP(GPIODV_6),
+	GPIO_GROUP(GPIODV_7),
+	GPIO_GROUP(GPIODV_8),
+	GPIO_GROUP(GPIODV_9),
+	GPIO_GROUP(GPIODV_10),
+	GPIO_GROUP(GPIODV_11),
+	GPIO_GROUP(GPIODV_12),
+	GPIO_GROUP(GPIODV_13),
+	GPIO_GROUP(GPIODV_14),
+	GPIO_GROUP(GPIODV_15),
+	GPIO_GROUP(GPIODV_16),
+	GPIO_GROUP(GPIODV_17),
+	GPIO_GROUP(GPIODV_18),
+	GPIO_GROUP(GPIODV_19),
+	GPIO_GROUP(GPIODV_20),
+	GPIO_GROUP(GPIODV_21),
+	GPIO_GROUP(GPIODV_22),
+	GPIO_GROUP(GPIODV_23),
+	GPIO_GROUP(GPIODV_24),
+	GPIO_GROUP(GPIODV_25),
+	GPIO_GROUP(GPIODV_26),
+	GPIO_GROUP(GPIODV_27),
+	GPIO_GROUP(GPIODV_28),
+	GPIO_GROUP(GPIODV_29),
+	GPIO_GROUP(GPIOH_0),
+	GPIO_GROUP(GPIOH_1),
+	GPIO_GROUP(GPIOH_2),
+	GPIO_GROUP(GPIOH_3),
+	GPIO_GROUP(GPIOH_4),
+	GPIO_GROUP(GPIOH_5),
+	GPIO_GROUP(GPIOH_6),
+	GPIO_GROUP(GPIOH_7),
+	GPIO_GROUP(GPIOH_8),
+	GPIO_GROUP(GPIOH_9),
+	GPIO_GROUP(GPIOZ_0),
+	GPIO_GROUP(GPIOZ_1),
+	GPIO_GROUP(GPIOZ_2),
+	GPIO_GROUP(GPIOZ_3),
+	GPIO_GROUP(GPIOZ_4),
+	GPIO_GROUP(GPIOZ_5),
+	GPIO_GROUP(GPIOZ_6),
+	GPIO_GROUP(GPIOZ_7),
+	GPIO_GROUP(GPIOZ_8),
+	GPIO_GROUP(GPIOZ_9),
+	GPIO_GROUP(GPIOZ_10),
+	GPIO_GROUP(GPIOZ_11),
+	GPIO_GROUP(GPIOZ_12),
+	GPIO_GROUP(GPIOZ_13),
+	GPIO_GROUP(GPIOZ_14),
+	GPIO_GROUP(GPIOAO_0),
+	GPIO_GROUP(GPIOAO_1),
+	GPIO_GROUP(GPIOAO_2),
+	GPIO_GROUP(GPIOAO_3),
+	GPIO_GROUP(GPIOAO_4),
+	GPIO_GROUP(GPIOAO_5),
+	GPIO_GROUP(GPIOAO_6),
+	GPIO_GROUP(GPIOAO_7),
+	GPIO_GROUP(GPIOAO_8),
+	GPIO_GROUP(GPIOAO_9),
+	GPIO_GROUP(GPIOAO_10),
+	GPIO_GROUP(GPIOAO_11),
+	GPIO_GROUP(GPIOAO_12),
+	GPIO_GROUP(GPIOAO_13),
+	GPIO_GROUP(GPIO_BSD_EN),
+	GPIO_GROUP(GPIO_TEST_N),
+
+	/* bank X */
+	GROUP(sd_d0_a,		8,	5),
+	GROUP(sd_d1_a,		8,	4),
+	GROUP(sd_d2_a,		8,	3),
+	GROUP(sd_d3_a,		8,	2),
+	GROUP(sd_clk_a,		8,	1),
+	GROUP(sd_cmd_a,		8,	0),
+
+	GROUP(sdxc_d0_a,	5,	14),
+	GROUP(sdxc_d13_a,	5,	13),
+	GROUP(sdxc_d47_a,	5,	12),
+	GROUP(sdxc_clk_a,	5,	11),
+	GROUP(sdxc_cmd_a,	5,	10),
+
+	GROUP(pcm_out_a,	3,	30),
+	GROUP(pcm_in_a,		3,	29),
+	GROUP(pcm_fs_a,		3,	28),
+	GROUP(pcm_clk_a,	3,	27),
+
+	GROUP(uart_tx_a0,	4,	17),
+	GROUP(uart_rx_a0,	4,	16),
+	GROUP(uart_cts_a0,	4,	15),
+	GROUP(uart_rts_a0,	4,	14),
+
+	GROUP(uart_tx_a1,	4,	13),
+	GROUP(uart_rx_a1,	4,	12),
+	GROUP(uart_cts_a1,	4,	11),
+	GROUP(uart_rts_a1,	4,	10),
+
+	GROUP(uart_tx_b0,	4,	9),
+	GROUP(uart_rx_b0,	4,	8),
+	GROUP(uart_cts_b0,	4,	7),
+	GROUP(uart_rts_b0,	4,	6),
+
+	GROUP(iso7816_det,	4,	21),
+	GROUP(iso7816_reset,	4,	20),
+	GROUP(iso7816_clk,	4,	19),
+	GROUP(iso7816_data,	4,	18),
+
+	GROUP(i2c_sda_d0,	4,	5),
+	GROUP(i2c_sck_d0,	4,	4),
+
+	GROUP(xtal_32k_out,	3,	22),
+	GROUP(xtal_24m_out,	3,	23),
+
+	/* bank Y */
+	GROUP(uart_tx_c,	1,	19),
+	GROUP(uart_rx_c,	1,	18),
+	GROUP(uart_cts_c,	1,	17),
+	GROUP(uart_rts_c,	1,	16),
+
+	GROUP(pcm_out_b,	4,	25),
+	GROUP(pcm_in_b,		4,	24),
+	GROUP(pcm_fs_b,		4,	23),
+	GROUP(pcm_clk_b,	4,	22),
+
+	GROUP(i2c_sda_c0,	1,	15),
+	GROUP(i2c_sck_c0,	1,	14),
+
+	/* bank DV */
+	GROUP(dvin_rgb,		0,	6),
+	GROUP(dvin_vs,		0,	9),
+	GROUP(dvin_hs,		0,	8),
+	GROUP(dvin_clk,		0,	7),
+	GROUP(dvin_de,		0,	10),
+
+	GROUP(enc_0,		7,	0),
+	GROUP(enc_1,		7,	1),
+	GROUP(enc_2,		7,	2),
+	GROUP(enc_3,		7,	3),
+	GROUP(enc_4,		7,	4),
+	GROUP(enc_5,		7,	5),
+	GROUP(enc_6,		7,	6),
+	GROUP(enc_7,		7,	7),
+	GROUP(enc_8,		7,	8),
+	GROUP(enc_9,		7,	9),
+	GROUP(enc_10,		7,	10),
+	GROUP(enc_11,		7,	11),
+	GROUP(enc_12,		7,	12),
+	GROUP(enc_13,		7,	13),
+	GROUP(enc_14,		7,	14),
+	GROUP(enc_15,		7,	15),
+	GROUP(enc_16,		7,	16),
+	GROUP(enc_17,		7,	17),
+
+	GROUP(uart_tx_b1,	6,	23),
+	GROUP(uart_rx_b1,	6,	22),
+	GROUP(uart_cts_b1,	6,	21),
+	GROUP(uart_rts_b1,	6,	20),
+
+	GROUP(vga_vs,		0,	21),
+	GROUP(vga_hs,		0,	20),
+
+	/* bank H */
+	GROUP(hdmi_hpd,		1,	26),
+	GROUP(hdmi_sda,		1,	25),
+	GROUP(hdmi_scl,		1,	24),
+	GROUP(hdmi_cec,		1,	23),
+
+	GROUP(spi_ss0_0,	9,	13),
+	GROUP(spi_miso_0,	9,	12),
+	GROUP(spi_mosi_0,	9,	11),
+	GROUP(spi_sclk_0,	9,	10),
+
+	GROUP(i2c_sda_d1,	4,	3),
+	GROUP(i2c_sck_d1,	4,	2),
+
+	/* bank Z */
+	GROUP(spi_ss0_1,	8,	16),
+	GROUP(spi_ss1_1,	8,	12),
+	GROUP(spi_sclk_1,	8,	15),
+	GROUP(spi_mosi_1,	8,	14),
+	GROUP(spi_miso_1,	8,	13),
+	GROUP(spi_ss2_1,	8,	17),
+
+	GROUP(eth_tx_clk_50m,	6,	15),
+	GROUP(eth_tx_en,	6,	14),
+	GROUP(eth_txd1,		6,	13),
+	GROUP(eth_txd0,		6,	12),
+	GROUP(eth_rx_clk_in,	6,	10),
+	GROUP(eth_rx_dv,	6,	11),
+	GROUP(eth_rxd1,		6,	8),
+	GROUP(eth_rxd0,		6,	7),
+	GROUP(eth_mdio,		6,	6),
+	GROUP(eth_mdc,		6,	5),
+
+	GROUP(i2c_sda_a0,	5,	31),
+	GROUP(i2c_sck_a0,	5,	30),
+
+	GROUP(i2c_sda_b,	5,	27),
+	GROUP(i2c_sck_b,	5,	26),
+
+	GROUP(i2c_sda_c1,	5,	25),
+	GROUP(i2c_sck_c1,	5,	24),
+
+	GROUP(i2c_sda_a1,	5,	9),
+	GROUP(i2c_sck_a1,	5,	8),
+
+	GROUP(i2c_sda_a2,	5,	7),
+	GROUP(i2c_sck_a2,	5,	6),
+
+	/* bank BOOT */
+	GROUP(sd_d0_c,		6,	29),
+	GROUP(sd_d1_c,		6,	28),
+	GROUP(sd_d2_c,		6,	27),
+	GROUP(sd_d3_c,		6,	26),
+	GROUP(sd_cmd_c,		6,	25),
+	GROUP(sd_clk_c,		6,	24),
+
+	GROUP(sdxc_d0_c,	4,	30),
+	GROUP(sdxc_d13_c,	4,	29),
+	GROUP(sdxc_d47_c,	4,	28),
+	GROUP(sdxc_cmd_c,	4,	27),
+	GROUP(sdxc_clk_c,	4,	26),
+
+	GROUP(nand_io,		2,	26),
+	GROUP(nand_io_ce0,	2,	25),
+	GROUP(nand_io_ce1,	2,	24),
+	GROUP(nand_io_rb0,	2,	17),
+	GROUP(nand_ale,		2,	21),
+	GROUP(nand_cle,		2,	20),
+	GROUP(nand_wen_clk,	2,	19),
+	GROUP(nand_ren_clk,	2,	18),
+	GROUP(nand_dqs,		2,	27),
+	GROUP(nand_ce2,		2,	23),
+	GROUP(nand_ce3,		2,	22),
+
+	GROUP(nor_d,		5,	1),
+	GROUP(nor_q,		5,	3),
+	GROUP(nor_c,		5,	2),
+	GROUP(nor_cs,		5,	0),
+
+	/* bank CARD */
+	GROUP(sd_d1_b,		2,	14),
+	GROUP(sd_d0_b,		2,	15),
+	GROUP(sd_clk_b,		2,	11),
+	GROUP(sd_cmd_b,		2,	10),
+	GROUP(sd_d3_b,		2,	12),
+	GROUP(sd_d2_b,		2,	13),
+
+	GROUP(sdxc_d13_b,	2,	6),
+	GROUP(sdxc_d0_b,	2,	7),
+	GROUP(sdxc_clk_b,	2,	5),
+	GROUP(sdxc_cmd_b,	2,	4),
+
+	/* bank AO */
+	GROUP_AO(uart_tx_ao_a,		0,	12),
+	GROUP_AO(uart_rx_ao_a,		0,	11),
+	GROUP_AO(uart_cts_ao_a,		0,	10),
+	GROUP_AO(uart_rts_ao_a,		0,	9),
+
+	GROUP_AO(remote_input,		0,	0),
+
+	GROUP_AO(i2c_slave_sck_ao,	0,	2),
+	GROUP_AO(i2c_slave_sda_ao,	0,	1),
+
+	GROUP_AO(uart_tx_ao_b0,		0,	26),
+	GROUP_AO(uart_rx_ao_b0,		0,	25),
+
+	GROUP_AO(uart_tx_ao_b1,		0,	24),
+	GROUP_AO(uart_rx_ao_b1,		0,	23),
+
+	GROUP_AO(i2c_mst_sck_ao,	0,	6),
+	GROUP_AO(i2c_mst_sda_ao,	0,	5),
+};
+
+static const char * const gpio_groups[] = {
+	"GPIOX_0", "GPIOX_1", "GPIOX_2", "GPIOX_3", "GPIOX_4",
+	"GPIOX_5", "GPIOX_6", "GPIOX_7", "GPIOX_8", "GPIOX_9",
+	"GPIOX_10", "GPIOX_11", "GPIOX_12", "GPIOX_13", "GPIOX_14",
+	"GPIOX_15", "GPIOX_16", "GPIOX_17", "GPIOX_18", "GPIOX_19",
+	"GPIOX_20", "GPIOX_21",
+
+	"GPIOY_0", "GPIOY_1", "GPIOY_2", "GPIOY_3", "GPIOY_4",
+	"GPIOY_5", "GPIOY_6", "GPIOY_7", "GPIOY_8", "GPIOY_9",
+	"GPIOY_10", "GPIOY_11", "GPIOY_12", "GPIOY_13", "GPIOY_14",
+	"GPIOY_15", "GPIOY_16",
+
+	"GPIODV_0", "GPIODV_1", "GPIODV_2", "GPIODV_3", "GPIODV_4",
+	"GPIODV_5", "GPIODV_6", "GPIODV_7", "GPIODV_8", "GPIODV_9",
+	"GPIODV_10", "GPIODV_11", "GPIODV_12", "GPIODV_13", "GPIODV_14",
+	"GPIODV_15", "GPIODV_16", "GPIODV_17", "GPIODV_18", "GPIODV_19",
+	"GPIODV_20", "GPIODV_21", "GPIODV_22", "GPIODV_23", "GPIODV_24",
+	"GPIODV_25", "GPIODV_26", "GPIODV_27", "GPIODV_28", "GPIODV_29",
+
+	"GPIOH_0", "GPIOH_1", "GPIOH_2", "GPIOH_3", "GPIOH_4",
+	"GPIOH_5", "GPIOH_6", "GPIOH_7", "GPIOH_8", "GPIOH_9",
+
+	"GPIOZ_0", "GPIOZ_1", "GPIOZ_2", "GPIOZ_3", "GPIOZ_4",
+	"GPIOZ_5", "GPIOZ_6", "GPIOZ_7", "GPIOZ_8", "GPIOZ_9",
+	"GPIOZ_10", "GPIOZ_11", "GPIOZ_12", "GPIOZ_13", "GPIOZ_14",
+
+	"CARD_0", "CARD_1", "CARD_2", "CARD_3", "CARD_4",
+	"CARD_5", "CARD_6",
+
+	"BOOT_0", "BOOT_1", "BOOT_2", "BOOT_3", "BOOT_4",
+	"BOOT_5", "BOOT_6", "BOOT_7", "BOOT_8", "BOOT_9",
+	"BOOT_10", "BOOT_11", "BOOT_12", "BOOT_13", "BOOT_14",
+	"BOOT_15", "BOOT_16", "BOOT_17", "BOOT_18",
+
+	"GPIOAO_0", "GPIOAO_1", "GPIOAO_2", "GPIOAO_3",
+	"GPIOAO_4", "GPIOAO_5", "GPIOAO_6", "GPIOAO_7",
+	"GPIOAO_8", "GPIOAO_9", "GPIOAO_10", "GPIOAO_11",
+	"GPIOAO_12", "GPIOAO_13", "GPIO_BSD_EN", "GPIO_TEST_N"
+};
+
+static const char * const sd_a_groups[] = {
+	"sd_d0_a", "sd_d1_a", "sd_d2_a", "sd_d3_a", "sd_clk_a", "sd_cmd_a"
+};
+
+static const char * const sdxc_a_groups[] = {
+	"sdxc_d0_a", "sdxc_d13_a", "sdxc_d47_a", "sdxc_clk_a", "sdxc_cmd_a"
+};
+
+static const char * const pcm_a_groups[] = {
+	"pcm_out_a", "pcm_in_a", "pcm_fs_a", "pcm_clk_a"
+};
+
+static const char * const uart_a_groups[] = {
+	"uart_tx_a0", "uart_rx_a0", "uart_cts_a0", "uart_rts_a0",
+	"uart_tx_a1", "uart_rx_a1", "uart_cts_a1", "uart_rts_a1"
+};
+
+static const char * const uart_b_groups[] = {
+	"uart_tx_b0", "uart_rx_b0", "uart_cts_b0", "uart_rts_b0",
+	"uart_tx_b1", "uart_rx_b1", "uart_cts_b1", "uart_rts_b1"
+};
+
+static const char * const iso7816_groups[] = {
+	"iso7816_det", "iso7816_reset", "iso7816_clk", "iso7816_data"
+};
+
+static const char * const i2c_d_groups[] = {
+	"i2c_sda_d0", "i2c_sck_d0", "i2c_sda_d1", "i2c_sck_d1"
+};
+
+static const char * const xtal_groups[] = {
+	"xtal_32k_out", "xtal_24m_out"
+};
+
+static const char * const uart_c_groups[] = {
+	"uart_tx_c", "uart_rx_c", "uart_cts_c", "uart_rts_c"
+};
+
+static const char * const pcm_b_groups[] = {
+	"pcm_out_b", "pcm_in_b", "pcm_fs_b", "pcm_clk_b"
+};
+
+static const char * const i2c_c_groups[] = {
+	"i2c_sda_c0", "i2c_sck_c0", "i2c_sda_c1", "i2c_sck_c1"
+};
+
+static const char * const dvin_groups[] = {
+	"dvin_rgb", "dvin_vs", "dvin_hs", "dvin_clk", "dvin_de"
+};
+
+static const char * const enc_groups[] = {
+	"enc_0", "enc_1", "enc_2", "enc_3", "enc_4", "enc_5",
+	"enc_6", "enc_7", "enc_8", "enc_9", "enc_10", "enc_11",
+	"enc_12", "enc_13", "enc_14", "enc_15", "enc_16", "enc_17"
+};
+
+static const char * const vga_groups[] = {
+	"vga_vs", "vga_hs"
+};
+
+static const char * const hdmi_groups[] = {
+	"hdmi_hpd", "hdmi_sda", "hdmi_scl", "hdmi_cec"
+};
+
+static const char * const spi_groups[] = {
+	"spi_ss0_0", "spi_miso_0", "spi_mosi_0", "spi_sclk_0",
+	"spi_ss0_1", "spi_ss1_1", "spi_sclk_1", "spi_mosi_1",
+	"spi_miso_1", "spi_ss2_1"
+};
+
+static const char * const ethernet_groups[] = {
+	"eth_tx_clk_50m", "eth_tx_en", "eth_txd1",
+	"eth_txd0", "eth_rx_clk_in", "eth_rx_dv",
+	"eth_rxd1", "eth_rxd0", "eth_mdio", "eth_mdc"
+};
+
+static const char * const i2c_a_groups[] = {
+	"i2c_sda_a0", "i2c_sck_a0", "i2c_sda_a1", "i2c_sck_a1",
+	"i2c_sda_a2", "i2c_sck_a2"
+};
+
+static const char * const i2c_b_groups[] = {
+	"i2c_sda_b", "i2c_sck_b"
+};
+
+static const char * const sd_c_groups[] = {
+	"sd_d0_c", "sd_d1_c", "sd_d2_c", "sd_d3_c",
+	"sd_cmd_c", "sd_clk_c"
+};
+
+static const char * const sdxc_c_groups[] = {
+	"sdxc_d0_c", "sdxc_d13_c", "sdxc_d47_c", "sdxc_cmd_c",
+	"sdxc_clk_c"
+};
+
+static const char * const nand_groups[] = {
+	"nand_io", "nand_io_ce0", "nand_io_ce1",
+	"nand_io_rb0", "nand_ale", "nand_cle",
+	"nand_wen_clk", "nand_ren_clk", "nand_dqs",
+	"nand_ce2", "nand_ce3"
+};
+
+static const char * const nor_groups[] = {
+	"nor_d", "nor_q", "nor_c", "nor_cs"
+};
+
+static const char * const sd_b_groups[] = {
+	"sd_d1_b", "sd_d0_b", "sd_clk_b", "sd_cmd_b",
+	"sd_d3_b", "sd_d2_b"
+};
+
+static const char * const sdxc_b_groups[] = {
+	"sdxc_d13_b", "sdxc_d0_b", "sdxc_clk_b", "sdxc_cmd_b"
+};
+
+static const char * const uart_ao_groups[] = {
+	"uart_tx_ao_a", "uart_rx_ao_a", "uart_cts_ao_a", "uart_rts_ao_a"
+};
+
+static const char * const remote_groups[] = {
+	"remote_input"
+};
+
+static const char * const i2c_slave_ao_groups[] = {
+	"i2c_slave_sck_ao", "i2c_slave_sda_ao"
+};
+
+static const char * const uart_ao_b_groups[] = {
+	"uart_tx_ao_b0", "uart_rx_ao_b0", "uart_tx_ao_b1", "uart_rx_ao_b1"
+};
+
+static const char * const i2c_mst_ao_groups[] = {
+	"i2c_mst_sck_ao", "i2c_mst_sda_ao"
+};
+
+static struct meson_pmx_func meson8_functions[] = {
+	FUNCTION(gpio),
+	FUNCTION(sd_a),
+	FUNCTION(sdxc_a),
+	FUNCTION(pcm_a),
+	FUNCTION(uart_a),
+	FUNCTION(uart_b),
+	FUNCTION(iso7816),
+	FUNCTION(i2c_d),
+	FUNCTION(xtal),
+	FUNCTION(uart_c),
+	FUNCTION(pcm_b),
+	FUNCTION(i2c_c),
+	FUNCTION(dvin),
+	FUNCTION(enc),
+	FUNCTION(vga),
+	FUNCTION(hdmi),
+	FUNCTION(spi),
+	FUNCTION(ethernet),
+	FUNCTION(i2c_a),
+	FUNCTION(i2c_b),
+	FUNCTION(sd_c),
+	FUNCTION(sdxc_c),
+	FUNCTION(nand),
+	FUNCTION(nor),
+	FUNCTION(sd_b),
+	FUNCTION(sdxc_b),
+	FUNCTION(uart_ao),
+	FUNCTION(remote),
+	FUNCTION(i2c_slave_ao),
+	FUNCTION(uart_ao_b),
+	FUNCTION(i2c_mst_ao),
+};
+
+static struct meson_bank meson8_banks[] = {
+	/*   name    first         last             pullen  pull     dir     out     in  */
+	BANK("X",    PIN_GPIOX_0,  PIN_GPIOX_21,    4,  0,  4,  0,  0,  0,  1,  0,  2,  0),
+	BANK("Y",    PIN_GPIOY_0,  PIN_GPIOY_16,    3,  0,  3,  0,  3,  0,  4,  0,  5,  0),
+	BANK("DV",   PIN_GPIODV_0, PIN_GPIODV_29,   0,  0,  0,  0,  7,  0,  8,  0,  9,  0),
+	BANK("H",    PIN_GPIOH_0,  PIN_GPIOH_9,     1, 16,  1, 16,  9, 19, 10, 19, 11, 19),
+	BANK("Z",    PIN_GPIOZ_0,  PIN_GPIOZ_14,    1,  0,  1,  0,  3, 17,  4, 17,  5, 17),
+	BANK("CARD", PIN_CARD_0,   PIN_CARD_6,      2, 20,  2, 20,  0, 22,  1, 22,  2, 22),
+	BANK("BOOT", PIN_BOOT_0,   PIN_BOOT_18,     2,  0,  2,  0,  9,  0, 10,  0, 11,  0),
+};
+
+static struct meson_bank meson8_ao_banks[] = {
+	/*   name    first         last             pullen  pull     dir     out     in  */
+	BANK("AO",   PIN_GPIOAO_0, PIN_GPIO_TEST_N, 0,  0,  0, 16,  0,  0,  0, 16,  1,  0),
+};
+
+static struct meson_domain_data meson8_domain_data[] = {
+	{
+		.name		= "banks",
+		.banks		= meson8_banks,
+		.num_banks	= ARRAY_SIZE(meson8_banks),
+		.pin_base	= 0,
+		.num_pins	= 120,
+	},
+	{
+		.name		= "ao-bank",
+		.banks		= meson8_ao_banks,
+		.num_banks	= ARRAY_SIZE(meson8_ao_banks),
+		.pin_base	= 120,
+		.num_pins	= 16,
+	},
+};
+
+struct meson_pinctrl_data meson8_pinctrl_data = {
+	.pins		= meson8_pins,
+	.groups		= meson8_groups,
+	.funcs		= meson8_functions,
+	.domain_data	= meson8_domain_data,
+	.num_pins	= ARRAY_SIZE(meson8_pins),
+	.num_groups	= ARRAY_SIZE(meson8_groups),
+	.num_funcs	= ARRAY_SIZE(meson8_functions),
+	.num_domains	= ARRAY_SIZE(meson8_domain_data),
+};
diff --git a/include/dt-bindings/gpio/meson8-gpio.h b/include/dt-bindings/gpio/meson8-gpio.h
new file mode 100644
index 00000000000..fdaeb5cbf5e
--- /dev/null
+++ b/include/dt-bindings/gpio/meson8-gpio.h
@@ -0,0 +1,157 @@
+/*
+ * GPIO definitions for Amlogic Meson8 SoCs
+ *
+ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DT_BINDINGS_MESON8_GPIO_H
+#define _DT_BINDINGS_MESON8_GPIO_H
+
+/* First GPIO chip */
+#define GPIOX_0		0
+#define GPIOX_1		1
+#define GPIOX_2		2
+#define GPIOX_3		3
+#define GPIOX_4		4
+#define GPIOX_5		5
+#define GPIOX_6		6
+#define GPIOX_7		7
+#define GPIOX_8		8
+#define GPIOX_9		9
+#define GPIOX_10	10
+#define GPIOX_11	11
+#define GPIOX_12	12
+#define GPIOX_13	13
+#define GPIOX_14	14
+#define GPIOX_15	15
+#define GPIOX_16	16
+#define GPIOX_17	17
+#define GPIOX_18	18
+#define GPIOX_19	19
+#define GPIOX_20	20
+#define GPIOX_21	21
+#define GPIOY_0		22
+#define GPIOY_1		23
+#define GPIOY_2		24
+#define GPIOY_3		25
+#define GPIOY_4		26
+#define GPIOY_5		27
+#define GPIOY_6		28
+#define GPIOY_7		29
+#define GPIOY_8		30
+#define GPIOY_9		31
+#define GPIOY_10	32
+#define GPIOY_11	33
+#define GPIOY_12	34
+#define GPIOY_13	35
+#define GPIOY_14	36
+#define GPIOY_15	37
+#define GPIOY_16	38
+#define GPIODV_0	39
+#define GPIODV_1	40
+#define GPIODV_2	41
+#define GPIODV_3	42
+#define GPIODV_4	43
+#define GPIODV_5	44
+#define GPIODV_6	45
+#define GPIODV_7	46
+#define GPIODV_8	47
+#define GPIODV_9	48
+#define GPIODV_10	49
+#define GPIODV_11	50
+#define GPIODV_12	51
+#define GPIODV_13	52
+#define GPIODV_14	53
+#define GPIODV_15	54
+#define GPIODV_16	55
+#define GPIODV_17	56
+#define GPIODV_18	57
+#define GPIODV_19	58
+#define GPIODV_20	59
+#define GPIODV_21	60
+#define GPIODV_22	61
+#define GPIODV_23	62
+#define GPIODV_24	63
+#define GPIODV_25	64
+#define GPIODV_26	65
+#define GPIODV_27	66
+#define GPIODV_28	67
+#define GPIODV_29	68
+#define GPIOH_0		69
+#define GPIOH_1		70
+#define GPIOH_2		71
+#define GPIOH_3		72
+#define GPIOH_4		73
+#define GPIOH_5		74
+#define GPIOH_6		75
+#define GPIOH_7		76
+#define GPIOH_8		77
+#define GPIOH_9		78
+#define GPIOZ_0		79
+#define GPIOZ_1		80
+#define GPIOZ_2		81
+#define GPIOZ_3		82
+#define GPIOZ_4		83
+#define GPIOZ_5		84
+#define GPIOZ_6		85
+#define GPIOZ_7		86
+#define GPIOZ_8		87
+#define GPIOZ_9		88
+#define GPIOZ_10	89
+#define GPIOZ_11	90
+#define GPIOZ_12	91
+#define GPIOZ_13	92
+#define GPIOZ_14	93
+#define CARD_0		94
+#define CARD_1		95
+#define CARD_2		96
+#define CARD_3		97
+#define CARD_4		98
+#define CARD_5		99
+#define CARD_6		100
+#define BOOT_0		101
+#define BOOT_1		102
+#define BOOT_2		103
+#define BOOT_3		104
+#define BOOT_4		105
+#define BOOT_5		106
+#define BOOT_6		107
+#define BOOT_7		108
+#define BOOT_8		109
+#define BOOT_9		110
+#define BOOT_10		111
+#define BOOT_11		112
+#define BOOT_12		113
+#define BOOT_13		114
+#define BOOT_14		115
+#define BOOT_15		116
+#define BOOT_16		117
+#define BOOT_17		118
+#define BOOT_18		119
+
+/* Second GPIO chip */
+#define GPIOAO_0	0
+#define GPIOAO_1	1
+#define GPIOAO_2	2
+#define GPIOAO_3	3
+#define GPIOAO_4	4
+#define GPIOAO_5	5
+#define GPIOAO_6	6
+#define GPIOAO_7	7
+#define GPIOAO_8	8
+#define GPIOAO_9	9
+#define GPIOAO_10	10
+#define GPIOAO_11	11
+#define GPIOAO_12	12
+#define GPIOAO_13	13
+#define GPIO_BSD_EN	14
+#define GPIO_TEST_N	15
+
+#endif /* _DT_BINDINGS_MESON8_GPIO_H */
-- 
cgit v1.2.3-70-g09d2


From 1f2fb110259afef478d65051c149ed04bd94c655 Mon Sep 17 00:00:00 2001
From: Clemens Ladisch <clemens@ladisch.de>
Date: Sun, 25 Jan 2015 14:35:58 +0100
Subject: ALSA: seq: remove unused symbols

Signed-off-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/seq_kernel.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/seq_kernel.h b/include/sound/seq_kernel.h
index eea5400fe37..ab8ddd9328a 100644
--- a/include/sound/seq_kernel.h
+++ b/include/sound/seq_kernel.h
@@ -27,9 +27,6 @@
 typedef struct snd_seq_real_time snd_seq_real_time_t;
 typedef union snd_seq_timestamp snd_seq_timestamp_t;
 
-/* maximum number of events dequeued per schedule interval */
-#define SNDRV_SEQ_MAX_DEQUEUE		50
-
 /* maximum number of queues */
 #define SNDRV_SEQ_MAX_QUEUES		8
 
@@ -42,9 +39,6 @@ typedef union snd_seq_timestamp snd_seq_timestamp_t;
 /* max number of events in memory pool */
 #define SNDRV_SEQ_MAX_EVENTS		2000
 
-/* default number of events in memory chunk */
-#define SNDRV_SEQ_DEFAULT_CHUNK_EVENTS	64
-
 /* default number of events in memory pool */
 #define SNDRV_SEQ_DEFAULT_EVENTS	500
 
-- 
cgit v1.2.3-70-g09d2


From a55bdf1ec5945050bfce9c3b2c3d8b70e8fd01a1 Mon Sep 17 00:00:00 2001
From: Clemens Ladisch <clemens@ladisch.de>
Date: Sun, 25 Jan 2015 14:36:27 +0100
Subject: ALSA: seq: remove unused callback_all field

Signed-off-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/seq_kernel.h     | 1 -
 sound/core/seq/seq_clientmgr.c | 1 -
 sound/core/seq/seq_ports.c     | 7 ++-----
 sound/core/seq/seq_ports.h     | 1 -
 4 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/sound/seq_kernel.h b/include/sound/seq_kernel.h
index ab8ddd9328a..f1c8e94524b 100644
--- a/include/sound/seq_kernel.h
+++ b/include/sound/seq_kernel.h
@@ -64,7 +64,6 @@ struct snd_seq_port_callback {
 	int (*unuse)(void *private_data, struct snd_seq_port_subscribe *info);
 	int (*event_input)(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop);
 	void (*private_free)(void *private_data);
-	unsigned int callback_all;	/* call subscribe callbacks at each connection/disconnection */
 	/*...*/
 };
 
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 808918ad293..29182f56bfb 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1279,7 +1279,6 @@ static int snd_seq_ioctl_create_port(struct snd_seq_client *client,
 				port->owner = callback->owner;
 			port->private_data = callback->private_data;
 			port->private_free = callback->private_free;
-			port->callback_all = callback->callback_all;
 			port->event_input = callback->event_input;
 			port->c_src.open = callback->subscribe;
 			port->c_src.close = callback->unsubscribe;
diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c
index 52b279b7b03..46ff593f618 100644
--- a/sound/core/seq/seq_ports.c
+++ b/sound/core/seq/seq_ports.c
@@ -411,9 +411,6 @@ int snd_seq_get_port_info(struct snd_seq_client_port * port,
  * invoked.
  * This feature is useful if these callbacks are associated with
  * initialization or termination of devices (see seq_midi.c).
- *
- * If callback_all option is set, the callback function is invoked
- * at each connection/disconnection. 
  */
 
 static int subscribe_port(struct snd_seq_client *client,
@@ -427,7 +424,7 @@ static int subscribe_port(struct snd_seq_client *client,
 	if (!try_module_get(port->owner))
 		return -EFAULT;
 	grp->count++;
-	if (grp->open && (port->callback_all || grp->count == 1)) {
+	if (grp->open && grp->count == 1) {
 		err = grp->open(port->private_data, info);
 		if (err < 0) {
 			module_put(port->owner);
@@ -452,7 +449,7 @@ static int unsubscribe_port(struct snd_seq_client *client,
 	if (! grp->count)
 		return -EINVAL;
 	grp->count--;
-	if (grp->close && (port->callback_all || grp->count == 0))
+	if (grp->close && grp->count == 0)
 		err = grp->close(port->private_data, info);
 	if (send_ack && client->type == USER_CLIENT)
 		snd_seq_client_notify_subscription(port->addr.client, port->addr.port,
diff --git a/sound/core/seq/seq_ports.h b/sound/core/seq/seq_ports.h
index 9d7117118ba..26bd71f36c4 100644
--- a/sound/core/seq/seq_ports.h
+++ b/sound/core/seq/seq_ports.h
@@ -73,7 +73,6 @@ struct snd_seq_client_port {
 			   int atomic, int hop);
 	void (*private_free)(void *private_data);
 	void *private_data;
-	unsigned int callback_all : 1;
 	unsigned int closing : 1;
 	unsigned int timestamping: 1;
 	unsigned int time_real: 1;
-- 
cgit v1.2.3-70-g09d2


From 1001fb810b1295d0600c0c6bdcb17889460470a5 Mon Sep 17 00:00:00 2001
From: Clemens Ladisch <clemens@ladisch.de>
Date: Sun, 25 Jan 2015 14:36:46 +0100
Subject: ALSA: seq: increase the maximum number of queues

Queues are used both for scheduling playback events and for assigning
timestamps to recorded events, so it is easy to need quite a lot of
them, especially on a multi-user system.  Additionally, the actual
queue objects are allocated dynamically, so it does not really make
sense to have a low limit.  Increase it to something still sane.

Signed-off-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/seq_kernel.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/seq_kernel.h b/include/sound/seq_kernel.h
index f1c8e94524b..18a2ac58b88 100644
--- a/include/sound/seq_kernel.h
+++ b/include/sound/seq_kernel.h
@@ -28,7 +28,7 @@ typedef struct snd_seq_real_time snd_seq_real_time_t;
 typedef union snd_seq_timestamp snd_seq_timestamp_t;
 
 /* maximum number of queues */
-#define SNDRV_SEQ_MAX_QUEUES		8
+#define SNDRV_SEQ_MAX_QUEUES		32
 
 /* max number of concurrent clients */
 #define SNDRV_SEQ_MAX_CLIENTS 		192
-- 
cgit v1.2.3-70-g09d2


From e044d8f92f79db167bb7f9dfd0f317e3238d82d1 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Mon, 26 Jan 2015 16:58:48 +0800
Subject: ACPI: Introduce acpi_unload_parent_table() usages in Linux kernel

ACPICA has implemented acpi_unload_parent_table() which can exactly replace
the acpi_get_id()/acpi_unload_table_id() implemented in Linux kernel.  The
acpi_unload_parent_table() has been unit tested in ACPICA simulation
environment.

This patch can also help to reduce the source code differences between
Linux and ACPICA.

Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Octavian Purdila <octavian.purdila@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/nsxfobj.c     | 44 -------------------------------------
 drivers/acpi/acpica/tbxface.c     | 46 ---------------------------------------
 drivers/pci/hotplug/sgi_hotplug.c | 13 ++++++-----
 include/acpi/acpixf.h             |  6 -----
 4 files changed, 7 insertions(+), 102 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c
index dae9401be7a..51a83298c18 100644
--- a/drivers/acpi/acpica/nsxfobj.c
+++ b/drivers/acpi/acpica/nsxfobj.c
@@ -51,50 +51,6 @@
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsxfobj")
 
-/*******************************************************************************
- *
- * FUNCTION:    acpi_get_id
- *
- * PARAMETERS:  Handle          - Handle of object whose id is desired
- *              ret_id          - Where the id will be placed
- *
- * RETURN:      Status
- *
- * DESCRIPTION: This routine returns the owner id associated with a handle
- *
- ******************************************************************************/
-acpi_status acpi_get_id(acpi_handle handle, acpi_owner_id * ret_id)
-{
-	struct acpi_namespace_node *node;
-	acpi_status status;
-
-	/* Parameter Validation */
-
-	if (!ret_id) {
-		return (AE_BAD_PARAMETER);
-	}
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
-	if (ACPI_FAILURE(status)) {
-		return (status);
-	}
-
-	/* Convert and validate the handle */
-
-	node = acpi_ns_validate_handle(handle);
-	if (!node) {
-		(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
-		return (AE_BAD_PARAMETER);
-	}
-
-	*ret_id = node->owner_id;
-
-	status = acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
-	return (status);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_get_id)
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_get_type
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 9520ae19bb3..0f9dd80b1cd 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -263,52 +263,6 @@ acpi_get_table_header(char *signature,
 
 ACPI_EXPORT_SYMBOL(acpi_get_table_header)
 
-/*******************************************************************************
- *
- * FUNCTION:    acpi_unload_table_id
- *
- * PARAMETERS:  id            - Owner ID of the table to be removed.
- *
- * RETURN:      Status
- *
- * DESCRIPTION: This routine is used to force the unload of a table (by id)
- *
- ******************************************************************************/
-acpi_status acpi_unload_table_id(acpi_owner_id id)
-{
-	int i;
-	acpi_status status = AE_NOT_EXIST;
-
-	ACPI_FUNCTION_TRACE(acpi_unload_table_id);
-
-	status = acpi_ut_acquire_mutex(ACPI_MTX_INTERPRETER);
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
-
-	/* Find table in the global table list */
-	for (i = 0; i < acpi_gbl_root_table_list.current_table_count; ++i) {
-		if (id != acpi_gbl_root_table_list.tables[i].owner_id) {
-			continue;
-		}
-		/*
-		 * Delete all namespace objects owned by this table. Note that these
-		 * objects can appear anywhere in the namespace by virtue of the AML
-		 * "Scope" operator. Thus, we need to track ownership by an ID, not
-		 * simply a position within the hierarchy
-		 */
-		acpi_tb_delete_namespace_by_owner(i);
-		status = acpi_tb_release_owner_id(i);
-		acpi_tb_set_table_loaded_flag(i, FALSE);
-		break;
-	}
-
-	(void)acpi_ut_release_mutex(ACPI_MTX_INTERPRETER);
-	return_ACPI_STATUS(status);
-}
-
-ACPI_EXPORT_SYMBOL(acpi_unload_table_id)
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_get_table_with_size
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index bada2099987..c32fb786d48 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -475,7 +475,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
 	struct slot *slot = bss_hotplug_slot->private;
 	struct pci_dev *dev, *temp;
 	int rc;
-	acpi_owner_id ssdt_id = 0;
+	acpi_handle ssdt_hdl = NULL;
 
 	/* Acquire update access to the bus */
 	mutex_lock(&sn_hotplug_mutex);
@@ -522,7 +522,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
 			if (ACPI_SUCCESS(ret) &&
 			    (adr>>16) == (slot->device_num + 1)) {
 				/* retain the owner id */
-				acpi_get_id(chandle, &ssdt_id);
+				ssdt_hdl = chandle;
 
 				ret = acpi_bus_get_device(chandle,
 							  &device);
@@ -547,12 +547,13 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
 	pci_unlock_rescan_remove();
 
 	/* Remove the SSDT for the slot from the ACPI namespace */
-	if (SN_ACPI_BASE_SUPPORT() && ssdt_id) {
+	if (SN_ACPI_BASE_SUPPORT() && ssdt_hdl) {
 		acpi_status ret;
-		ret = acpi_unload_table_id(ssdt_id);
+		ret = acpi_unload_parent_table(ssdt_hdl);
 		if (ACPI_FAILURE(ret)) {
-			printk(KERN_ERR "%s: acpi_unload_table_id failed (0x%x) for id %d\n",
-			       __func__, ret, ssdt_id);
+			acpi_handle_err(ssdt_hdl,
+					"%s: acpi_unload_parent_table failed (0x%x)\n",
+					__func__, ret);
 			/* try to continue on */
 		}
 	}
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 5ba78464c1b..5dd21bc18ce 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -890,12 +890,6 @@ ACPI_APP_DEPENDENT_RETURN_VOID(ACPI_PRINTF_LIKE(1)
  */
 ACPI_GLOBAL(u8, acpi_gbl_permanent_mmap);
 
-ACPI_EXTERNAL_RETURN_STATUS(acpi_status
-			    acpi_get_id(acpi_handle object,
-					acpi_owner_id * out_type))
-
-ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_unload_table_id(acpi_owner_id id))
-
 ACPI_EXTERNAL_RETURN_STATUS(acpi_status
 			    acpi_get_table_with_size(acpi_string signature,
 						     u32 instance,
-- 
cgit v1.2.3-70-g09d2


From a45de93eb10ae44446aec2c73d722562ab46092a Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Mon, 26 Jan 2015 16:58:56 +0800
Subject: ACPICA: Resources: Provide common part for struct
 acpi_resource_address structures.

struct acpi_resource_address and struct acpi_resource_extended_address64 share substracts
just at different offsets. To unify the parsing functions, OSPMs like Linux
need a new ACPI_ADDRESS64_ATTRIBUTE as their substructs, so they can
extract the shared data.

This patch also synchronizes the structure changes to the Linux kernel.
The usages are searched by matching the following keywords:
1. acpi_resource_address
2. acpi_resource_extended_address
3. ACPI_RESOURCE_TYPE_ADDRESS
4. ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS
And we found and fixed the usages in the following files:
 arch/ia64/kernel/acpi-ext.c
 arch/ia64/pci/pci.c
 arch/x86/pci/acpi.c
 arch/x86/pci/mmconfig-shared.c
 drivers/xen/xen-acpi-memhotplug.c
 drivers/acpi/acpi_memhotplug.c
 drivers/acpi/pci_root.c
 drivers/acpi/resource.c
 drivers/char/hpet.c
 drivers/pnp/pnpacpi/rsparser.c
 drivers/hv/vmbus_drv.c

Build tests are passed with defconfig/allnoconfig/allyesconfig and
defconfig+CONFIG_ACPI=n.

Original-by: Thomas Gleixner <tglx@linutronix.de>
Original-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/ia64/kernel/acpi-ext.c       |  6 ++--
 arch/ia64/pci/pci.c               | 14 +++++-----
 arch/x86/pci/acpi.c               | 26 ++++++++---------
 arch/x86/pci/mmconfig-shared.c    |  6 ++--
 drivers/acpi/acpi_memhotplug.c    |  8 +++---
 drivers/acpi/acpica/rsaddr.c      |  9 +++---
 drivers/acpi/acpica/rsdumpinfo.c  | 59 ++++++++++++++++++++-------------------
 drivers/acpi/acpica/rsxface.c     | 10 +++----
 drivers/acpi/pci_root.c           |  6 ++--
 drivers/acpi/resource.c           | 24 ++++++++--------
 drivers/char/hpet.c               |  4 +--
 drivers/hv/vmbus_drv.c            |  4 +--
 drivers/pnp/pnpacpi/rsparser.c    | 16 +++++------
 drivers/xen/xen-acpi-memhotplug.c |  8 +++---
 include/acpi/acrestyp.h           | 40 +++++++++++++++-----------
 15 files changed, 125 insertions(+), 115 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/acpi-ext.c b/arch/ia64/kernel/acpi-ext.c
index 8b9318d311a..bd09bf74f18 100644
--- a/arch/ia64/kernel/acpi-ext.c
+++ b/arch/ia64/kernel/acpi-ext.c
@@ -69,10 +69,10 @@ static acpi_status find_csr_space(struct acpi_resource *resource, void *data)
 	status = acpi_resource_to_address64(resource, &addr);
 	if (ACPI_SUCCESS(status) &&
 	    addr.resource_type == ACPI_MEMORY_RANGE &&
-	    addr.address_length &&
+	    addr.address.address_length &&
 	    addr.producer_consumer == ACPI_CONSUMER) {
-		space->base = addr.minimum;
-		space->length = addr.address_length;
+		space->base = addr.address.minimum;
+		space->length = addr.address.address_length;
 		return AE_CTRL_TERMINATE;
 	}
 	return AE_OK;		/* keep looking */
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 291a582777c..46920aaa7e9 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -188,12 +188,12 @@ static u64 add_io_space(struct pci_root_info *info,
 
 	name = (char *)(iospace + 1);
 
-	min = addr->minimum;
-	max = min + addr->address_length - 1;
+	min = addr->address.minimum;
+	max = min + addr->address.address_length - 1;
 	if (addr->info.io.translation_type == ACPI_SPARSE_TRANSLATION)
 		sparse = 1;
 
-	space_nr = new_space(addr->translation_offset, sparse);
+	space_nr = new_space(addr->address.translation_offset, sparse);
 	if (space_nr == ~0)
 		goto free_resource;
 
@@ -247,7 +247,7 @@ static acpi_status resource_to_window(struct acpi_resource *resource,
 	if (ACPI_SUCCESS(status) &&
 	    (addr->resource_type == ACPI_MEMORY_RANGE ||
 	     addr->resource_type == ACPI_IO_RANGE) &&
-	    addr->address_length &&
+	    addr->address.address_length &&
 	    addr->producer_consumer == ACPI_PRODUCER)
 		return AE_OK;
 
@@ -284,7 +284,7 @@ static acpi_status add_window(struct acpi_resource *res, void *data)
 	if (addr.resource_type == ACPI_MEMORY_RANGE) {
 		flags = IORESOURCE_MEM;
 		root = &iomem_resource;
-		offset = addr.translation_offset;
+		offset = addr.address.translation_offset;
 	} else if (addr.resource_type == ACPI_IO_RANGE) {
 		flags = IORESOURCE_IO;
 		root = &ioport_resource;
@@ -297,8 +297,8 @@ static acpi_status add_window(struct acpi_resource *res, void *data)
 	resource = &info->res[info->res_num];
 	resource->name = info->name;
 	resource->flags = flags;
-	resource->start = addr.minimum + offset;
-	resource->end = resource->start + addr.address_length - 1;
+	resource->start = addr.address.minimum + offset;
+	resource->end = resource->start + addr.address.address_length - 1;
 	info->res_offset[info->res_num] = offset;
 
 	if (insert_resource(root, resource)) {
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index cfd1b132b8e..bb98afd0591 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -231,23 +231,23 @@ static acpi_status resource_to_addr(struct acpi_resource *resource,
 	case ACPI_RESOURCE_TYPE_MEMORY24:
 		memory24 = &resource->data.memory24;
 		addr->resource_type = ACPI_MEMORY_RANGE;
-		addr->minimum = memory24->minimum;
-		addr->address_length = memory24->address_length;
-		addr->maximum = addr->minimum + addr->address_length - 1;
+		addr->address.minimum = memory24->minimum;
+		addr->address.address_length = memory24->address_length;
+		addr->address.maximum = addr->address.minimum + addr->address.address_length - 1;
 		return AE_OK;
 	case ACPI_RESOURCE_TYPE_MEMORY32:
 		memory32 = &resource->data.memory32;
 		addr->resource_type = ACPI_MEMORY_RANGE;
-		addr->minimum = memory32->minimum;
-		addr->address_length = memory32->address_length;
-		addr->maximum = addr->minimum + addr->address_length - 1;
+		addr->address.minimum = memory32->minimum;
+		addr->address.address_length = memory32->address_length;
+		addr->address.maximum = addr->address.minimum + addr->address.address_length - 1;
 		return AE_OK;
 	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
 		fixed_memory32 = &resource->data.fixed_memory32;
 		addr->resource_type = ACPI_MEMORY_RANGE;
-		addr->minimum = fixed_memory32->address;
-		addr->address_length = fixed_memory32->address_length;
-		addr->maximum = addr->minimum + addr->address_length - 1;
+		addr->address.minimum = fixed_memory32->address;
+		addr->address.address_length = fixed_memory32->address_length;
+		addr->address.maximum = addr->address.minimum + addr->address.address_length - 1;
 		return AE_OK;
 	case ACPI_RESOURCE_TYPE_ADDRESS16:
 	case ACPI_RESOURCE_TYPE_ADDRESS32:
@@ -256,7 +256,7 @@ static acpi_status resource_to_addr(struct acpi_resource *resource,
 		if (ACPI_SUCCESS(status) &&
 		    (addr->resource_type == ACPI_MEMORY_RANGE ||
 		    addr->resource_type == ACPI_IO_RANGE) &&
-		    addr->address_length > 0) {
+		    addr->address.address_length > 0) {
 			return AE_OK;
 		}
 		break;
@@ -298,8 +298,8 @@ static acpi_status setup_resource(struct acpi_resource *acpi_res, void *data)
 	} else
 		return AE_OK;
 
-	start = addr.minimum + addr.translation_offset;
-	orig_end = end = addr.maximum + addr.translation_offset;
+	start = addr.address.minimum + addr.address.translation_offset;
+	orig_end = end = addr.address.maximum + addr.address.translation_offset;
 
 	/* Exclude non-addressable range or non-addressable portion of range */
 	end = min(end, (u64)iomem_resource.end);
@@ -320,7 +320,7 @@ static acpi_status setup_resource(struct acpi_resource *acpi_res, void *data)
 	res->flags = flags;
 	res->start = start;
 	res->end = end;
-	info->res_offset[info->res_num] = addr.translation_offset;
+	info->res_offset[info->res_num] = addr.address.translation_offset;
 	info->res_num++;
 
 	if (!pci_use_crs)
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 326198a4434..5a8dceac309 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -397,12 +397,12 @@ static acpi_status check_mcfg_resource(struct acpi_resource *res, void *data)
 
 	status = acpi_resource_to_address64(res, &address);
 	if (ACPI_FAILURE(status) ||
-	   (address.address_length <= 0) ||
+	   (address.address.address_length <= 0) ||
 	   (address.resource_type != ACPI_MEMORY_RANGE))
 		return AE_OK;
 
-	if ((mcfg_res->start >= address.minimum) &&
-	    (mcfg_res->end < (address.minimum + address.address_length))) {
+	if ((mcfg_res->start >= address.address.minimum) &&
+	    (mcfg_res->end < (address.address.minimum + address.address.address_length))) {
 		mcfg_res->flags = 1;
 		return AE_CTRL_TERMINATE;
 	}
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 23e2319ead4..ee28f4d1562 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -101,8 +101,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context)
 		/* Can we combine the resource range information? */
 		if ((info->caching == address64.info.mem.caching) &&
 		    (info->write_protect == address64.info.mem.write_protect) &&
-		    (info->start_addr + info->length == address64.minimum)) {
-			info->length += address64.address_length;
+		    (info->start_addr + info->length == address64.address.minimum)) {
+			info->length += address64.address.address_length;
 			return AE_OK;
 		}
 	}
@@ -114,8 +114,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context)
 	INIT_LIST_HEAD(&new->list);
 	new->caching = address64.info.mem.caching;
 	new->write_protect = address64.info.mem.write_protect;
-	new->start_addr = address64.minimum;
-	new->length = address64.address_length;
+	new->start_addr = address64.address.minimum;
+	new->length = address64.address.address_length;
 	list_add_tail(&new->list, &mem_device->res_list);
 
 	return AE_OK;
diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c
index 916fd095ff3..94a3a057042 100644
--- a/drivers/acpi/acpica/rsaddr.c
+++ b/drivers/acpi/acpica/rsaddr.c
@@ -74,7 +74,7 @@ struct acpi_rsconvert_info acpi_rs_convert_address16[5] = {
 	 * Address Translation Offset
 	 * Address Length
 	 */
-	{ACPI_RSC_MOVE16, ACPI_RS_OFFSET(data.address16.granularity),
+	{ACPI_RSC_MOVE16, ACPI_RS_OFFSET(data.address16.address.granularity),
 	 AML_OFFSET(address16.granularity),
 	 5},
 
@@ -112,7 +112,7 @@ struct acpi_rsconvert_info acpi_rs_convert_address32[5] = {
 	 * Address Translation Offset
 	 * Address Length
 	 */
-	{ACPI_RSC_MOVE32, ACPI_RS_OFFSET(data.address32.granularity),
+	{ACPI_RSC_MOVE32, ACPI_RS_OFFSET(data.address32.address.granularity),
 	 AML_OFFSET(address32.granularity),
 	 5},
 
@@ -150,7 +150,7 @@ struct acpi_rsconvert_info acpi_rs_convert_address64[5] = {
 	 * Address Translation Offset
 	 * Address Length
 	 */
-	{ACPI_RSC_MOVE64, ACPI_RS_OFFSET(data.address64.granularity),
+	{ACPI_RSC_MOVE64, ACPI_RS_OFFSET(data.address64.address.granularity),
 	 AML_OFFSET(address64.granularity),
 	 5},
 
@@ -194,7 +194,8 @@ struct acpi_rsconvert_info acpi_rs_convert_ext_address64[5] = {
 	 * Address Length
 	 * Type-Specific Attribute
 	 */
-	{ACPI_RSC_MOVE64, ACPI_RS_OFFSET(data.ext_address64.granularity),
+	{ACPI_RSC_MOVE64,
+	 ACPI_RS_OFFSET(data.ext_address64.address.granularity),
 	 AML_OFFSET(ext_address64.granularity),
 	 6}
 };
diff --git a/drivers/acpi/acpica/rsdumpinfo.c b/drivers/acpi/acpica/rsdumpinfo.c
index 2f9332d5c97..6ba7ad5faa9 100644
--- a/drivers/acpi/acpica/rsdumpinfo.c
+++ b/drivers/acpi/acpica/rsdumpinfo.c
@@ -183,15 +183,15 @@ struct acpi_rsdump_info acpi_rs_dump_address16[8] = {
 	{ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_address16),
 	 "16-Bit WORD Address Space", NULL},
 	{ACPI_RSD_ADDRESS, 0, NULL, NULL},
-	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.granularity), "Granularity",
-	 NULL},
-	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.minimum), "Address Minimum",
-	 NULL},
-	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.maximum), "Address Maximum",
-	 NULL},
-	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.translation_offset),
+	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.granularity),
+	 "Granularity", NULL},
+	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.minimum),
+	 "Address Minimum", NULL},
+	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.maximum),
+	 "Address Maximum", NULL},
+	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.translation_offset),
 	 "Translation Offset", NULL},
-	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address_length),
+	{ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.address_length),
 	 "Address Length", NULL},
 	{ACPI_RSD_SOURCE, ACPI_RSD_OFFSET(address16.resource_source), NULL, NULL}
 };
@@ -200,15 +200,15 @@ struct acpi_rsdump_info acpi_rs_dump_address32[8] = {
 	{ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_address32),
 	 "32-Bit DWORD Address Space", NULL},
 	{ACPI_RSD_ADDRESS, 0, NULL, NULL},
-	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.granularity), "Granularity",
-	 NULL},
-	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.minimum), "Address Minimum",
-	 NULL},
-	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.maximum), "Address Maximum",
-	 NULL},
-	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.translation_offset),
+	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.granularity),
+	 "Granularity", NULL},
+	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.minimum),
+	 "Address Minimum", NULL},
+	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.maximum),
+	 "Address Maximum", NULL},
+	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.translation_offset),
 	 "Translation Offset", NULL},
-	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address_length),
+	{ACPI_RSD_UINT32, ACPI_RSD_OFFSET(address32.address.address_length),
 	 "Address Length", NULL},
 	{ACPI_RSD_SOURCE, ACPI_RSD_OFFSET(address32.resource_source), NULL, NULL}
 };
@@ -217,15 +217,15 @@ struct acpi_rsdump_info acpi_rs_dump_address64[8] = {
 	{ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_address64),
 	 "64-Bit QWORD Address Space", NULL},
 	{ACPI_RSD_ADDRESS, 0, NULL, NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.granularity), "Granularity",
-	 NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.minimum), "Address Minimum",
-	 NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.maximum), "Address Maximum",
-	 NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.translation_offset),
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.granularity),
+	 "Granularity", NULL},
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.minimum),
+	 "Address Minimum", NULL},
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.maximum),
+	 "Address Maximum", NULL},
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.translation_offset),
 	 "Translation Offset", NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address_length),
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(address64.address.address_length),
 	 "Address Length", NULL},
 	{ACPI_RSD_SOURCE, ACPI_RSD_OFFSET(address64.resource_source), NULL, NULL}
 };
@@ -234,15 +234,16 @@ struct acpi_rsdump_info acpi_rs_dump_ext_address64[8] = {
 	{ACPI_RSD_TITLE, ACPI_RSD_TABLE_SIZE(acpi_rs_dump_ext_address64),
 	 "64-Bit Extended Address Space", NULL},
 	{ACPI_RSD_ADDRESS, 0, NULL, NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.granularity),
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.granularity),
 	 "Granularity", NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.minimum),
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.minimum),
 	 "Address Minimum", NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.maximum),
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.maximum),
 	 "Address Maximum", NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.translation_offset),
+	{ACPI_RSD_UINT64,
+	 ACPI_RSD_OFFSET(ext_address64.address.translation_offset),
 	 "Translation Offset", NULL},
-	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address_length),
+	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.address.address_length),
 	 "Address Length", NULL},
 	{ACPI_RSD_UINT64, ACPI_RSD_OFFSET(ext_address64.type_specific),
 	 "Type-Specific Attribute", NULL}
diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c
index 877ab920213..29528789117 100644
--- a/drivers/acpi/acpica/rsxface.c
+++ b/drivers/acpi/acpica/rsxface.c
@@ -60,11 +60,11 @@ ACPI_MODULE_NAME("rsxface")
 	ACPI_COPY_FIELD(out, in, min_address_fixed);         \
 	ACPI_COPY_FIELD(out, in, max_address_fixed);         \
 	ACPI_COPY_FIELD(out, in, info);                      \
-	ACPI_COPY_FIELD(out, in, granularity);               \
-	ACPI_COPY_FIELD(out, in, minimum);                   \
-	ACPI_COPY_FIELD(out, in, maximum);                   \
-	ACPI_COPY_FIELD(out, in, translation_offset);        \
-	ACPI_COPY_FIELD(out, in, address_length);            \
+	ACPI_COPY_FIELD(out, in, address.granularity);       \
+	ACPI_COPY_FIELD(out, in, address.minimum);           \
+	ACPI_COPY_FIELD(out, in, address.maximum);           \
+	ACPI_COPY_FIELD(out, in, address.translation_offset); \
+	ACPI_COPY_FIELD(out, in, address.address_length);    \
 	ACPI_COPY_FIELD(out, in, resource_source);
 /* Local prototypes */
 static acpi_status
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index c6bcb8c719d..e53e0f65920 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -112,10 +112,10 @@ get_root_bridge_busnr_callback(struct acpi_resource *resource, void *data)
 	if (ACPI_FAILURE(status))
 		return AE_OK;
 
-	if ((address.address_length > 0) &&
+	if ((address.address.address_length > 0) &&
 	    (address.resource_type == ACPI_BUS_NUMBER_RANGE)) {
-		res->start = address.minimum;
-		res->end = address.minimum + address.address_length - 1;
+		res->start = address.address.minimum;
+		res->end = address.address.minimum + address.address.address_length - 1;
 	}
 
 	return AE_OK;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 782a0d15c25..d0a4d90c6bc 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -202,22 +202,22 @@ bool acpi_dev_resource_address_space(struct acpi_resource *ares,
 	if (ACPI_FAILURE(status))
 		return false;
 
-	res->start = addr.minimum;
-	res->end = addr.maximum;
+	res->start = addr.address.minimum;
+	res->end = addr.address.maximum;
 	window = addr.producer_consumer == ACPI_PRODUCER;
 
 	switch(addr.resource_type) {
 	case ACPI_MEMORY_RANGE:
-		len = addr.maximum - addr.minimum + 1;
+		len = addr.address.maximum - addr.address.minimum + 1;
 		res->flags = acpi_dev_memresource_flags(len,
 						addr.info.mem.write_protect,
 						window);
 		break;
 	case ACPI_IO_RANGE:
-		io_decode = addr.granularity == 0xfff ?
+		io_decode = addr.address.granularity == 0xfff ?
 				ACPI_DECODE_10 : ACPI_DECODE_16;
-		res->flags = acpi_dev_ioresource_flags(addr.minimum,
-						       addr.maximum,
+		res->flags = acpi_dev_ioresource_flags(addr.address.minimum,
+						       addr.address.maximum,
 						       io_decode, window);
 		break;
 	case ACPI_BUS_NUMBER_RANGE:
@@ -253,22 +253,22 @@ bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares,
 
 	ext_addr = &ares->data.ext_address64;
 
-	res->start = ext_addr->minimum;
-	res->end = ext_addr->maximum;
+	res->start = ext_addr->address.minimum;
+	res->end = ext_addr->address.maximum;
 	window = ext_addr->producer_consumer == ACPI_PRODUCER;
 
 	switch(ext_addr->resource_type) {
 	case ACPI_MEMORY_RANGE:
-		len = ext_addr->maximum - ext_addr->minimum + 1;
+		len = ext_addr->address.maximum - ext_addr->address.minimum + 1;
 		res->flags = acpi_dev_memresource_flags(len,
 					ext_addr->info.mem.write_protect,
 					window);
 		break;
 	case ACPI_IO_RANGE:
-		io_decode = ext_addr->granularity == 0xfff ?
+		io_decode = ext_addr->address.granularity == 0xfff ?
 				ACPI_DECODE_10 : ACPI_DECODE_16;
-		res->flags = acpi_dev_ioresource_flags(ext_addr->minimum,
-						       ext_addr->maximum,
+		res->flags = acpi_dev_ioresource_flags(ext_addr->address.minimum,
+						       ext_addr->address.maximum,
 						       io_decode, window);
 		break;
 	case ACPI_BUS_NUMBER_RANGE:
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index d5d4cd82b9f..5c0baa9ffc6 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -976,8 +976,8 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data)
 	status = acpi_resource_to_address64(res, &addr);
 
 	if (ACPI_SUCCESS(status)) {
-		hdp->hd_phys_address = addr.minimum;
-		hdp->hd_address = ioremap(addr.minimum, addr.address_length);
+		hdp->hd_phys_address = addr.address.minimum;
+		hdp->hd_address = ioremap(addr.address.minimum, addr.address.address_length);
 
 		if (hpet_is_known(hdp)) {
 			iounmap(hdp->hd_address);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 4d6b26979fb..bb3725b672c 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -861,8 +861,8 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
 		break;
 
 	case ACPI_RESOURCE_TYPE_ADDRESS64:
-		hyperv_mmio.start = res->data.address64.minimum;
-		hyperv_mmio.end = res->data.address64.maximum;
+		hyperv_mmio.start = res->data.address64.address.minimum;
+		hyperv_mmio.end = res->data.address64.address.maximum;
 		break;
 	}
 
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 66977ebf13b..2d9bc789af0 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -410,12 +410,12 @@ static __init void pnpacpi_parse_address_option(struct pnp_dev *dev,
 	if (p->resource_type == ACPI_MEMORY_RANGE) {
 		if (p->info.mem.write_protect == ACPI_READ_WRITE_MEMORY)
 			flags = IORESOURCE_MEM_WRITEABLE;
-		pnp_register_mem_resource(dev, option_flags, p->minimum,
-					  p->minimum, 0, p->address_length,
+		pnp_register_mem_resource(dev, option_flags, p->address.minimum,
+					  p->address.minimum, 0, p->address.address_length,
 					  flags);
 	} else if (p->resource_type == ACPI_IO_RANGE)
-		pnp_register_port_resource(dev, option_flags, p->minimum,
-					   p->minimum, 0, p->address_length,
+		pnp_register_port_resource(dev, option_flags, p->address.minimum,
+					   p->address.minimum, 0, p->address.address_length,
 					   IORESOURCE_IO_FIXED);
 }
 
@@ -429,12 +429,12 @@ static __init void pnpacpi_parse_ext_address_option(struct pnp_dev *dev,
 	if (p->resource_type == ACPI_MEMORY_RANGE) {
 		if (p->info.mem.write_protect == ACPI_READ_WRITE_MEMORY)
 			flags = IORESOURCE_MEM_WRITEABLE;
-		pnp_register_mem_resource(dev, option_flags, p->minimum,
-					  p->minimum, 0, p->address_length,
+		pnp_register_mem_resource(dev, option_flags, p->address.minimum,
+					  p->address.minimum, 0, p->address.address_length,
 					  flags);
 	} else if (p->resource_type == ACPI_IO_RANGE)
-		pnp_register_port_resource(dev, option_flags, p->minimum,
-					   p->minimum, 0, p->address_length,
+		pnp_register_port_resource(dev, option_flags, p->address.minimum,
+					   p->address.minimum, 0, p->address.address_length,
 					   IORESOURCE_IO_FIXED);
 }
 
diff --git a/drivers/xen/xen-acpi-memhotplug.c b/drivers/xen/xen-acpi-memhotplug.c
index 34e40b733f9..4fc886cd558 100644
--- a/drivers/xen/xen-acpi-memhotplug.c
+++ b/drivers/xen/xen-acpi-memhotplug.c
@@ -117,8 +117,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context)
 	list_for_each_entry(info, &mem_device->res_list, list) {
 		if ((info->caching == address64.info.mem.caching) &&
 		    (info->write_protect == address64.info.mem.write_protect) &&
-		    (info->start_addr + info->length == address64.minimum)) {
-			info->length += address64.address_length;
+		    (info->start_addr + info->length == address64.address.minimum)) {
+			info->length += address64.address.address_length;
 			return AE_OK;
 		}
 	}
@@ -130,8 +130,8 @@ acpi_memory_get_resource(struct acpi_resource *resource, void *context)
 	INIT_LIST_HEAD(&new->list);
 	new->caching = address64.info.mem.caching;
 	new->write_protect = address64.info.mem.write_protect;
-	new->start_addr = address64.minimum;
-	new->length = address64.address_length;
+	new->start_addr = address64.address.minimum;
+	new->length = address64.address.address_length;
 	list_add_tail(&new->list, &mem_device->res_list);
 
 	return AE_OK;
diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h
index eb760ca0b2e..0b75e01212c 100644
--- a/include/acpi/acrestyp.h
+++ b/include/acpi/acrestyp.h
@@ -305,43 +305,51 @@ struct acpi_resource_source {
 	u8                                      max_address_fixed; \
 	union acpi_resource_attribute           info;
 
-struct acpi_resource_address {
-ACPI_RESOURCE_ADDRESS_COMMON};
-
-struct acpi_resource_address16 {
-	ACPI_RESOURCE_ADDRESS_COMMON u16 granularity;
+struct acpi_address16_attribute {
+	u16 granularity;
 	u16 minimum;
 	u16 maximum;
 	u16 translation_offset;
 	u16 address_length;
-	struct acpi_resource_source resource_source;
 };
 
-struct acpi_resource_address32 {
-	ACPI_RESOURCE_ADDRESS_COMMON u32 granularity;
+struct acpi_address32_attribute {
+	u32 granularity;
 	u32 minimum;
 	u32 maximum;
 	u32 translation_offset;
 	u32 address_length;
-	struct acpi_resource_source resource_source;
 };
 
-struct acpi_resource_address64 {
-	ACPI_RESOURCE_ADDRESS_COMMON u64 granularity;
+struct acpi_address64_attribute {
+	u64 granularity;
 	u64 minimum;
 	u64 maximum;
 	u64 translation_offset;
 	u64 address_length;
+};
+
+struct acpi_resource_address {
+ACPI_RESOURCE_ADDRESS_COMMON};
+
+struct acpi_resource_address16 {
+	ACPI_RESOURCE_ADDRESS_COMMON struct acpi_address16_attribute address;
+	struct acpi_resource_source resource_source;
+};
+
+struct acpi_resource_address32 {
+	ACPI_RESOURCE_ADDRESS_COMMON struct acpi_address32_attribute address;
+	struct acpi_resource_source resource_source;
+};
+
+struct acpi_resource_address64 {
+	ACPI_RESOURCE_ADDRESS_COMMON struct acpi_address64_attribute address;
 	struct acpi_resource_source resource_source;
 };
 
 struct acpi_resource_extended_address64 {
 	ACPI_RESOURCE_ADDRESS_COMMON u8 revision_ID;
-	u64 granularity;
-	u64 minimum;
-	u64 maximum;
-	u64 translation_offset;
-	u64 address_length;
+	struct acpi_address64_attribute address;
 	u64 type_specific;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 47e039413cacee70229ebbf6de5a8e3b27e6f057 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 23 Jan 2015 16:21:36 +0100
Subject: ASoC: Add support for allocating AC'97 device before registering it

In some cases it is necessary to before additional operations after the
device has been initialized and before the device is registered. This can
for example be resetting the device.

This patch introduces a new function snd_soc_alloc_ac97_codec() which is
similar to snd_soc_new_ac97_codec() except that it does not register the
device. Any users of snd_soc_alloc_ac97_codec() are responsible for calling
device_add() manually.

Fixes: 6794f709b712 ("ASoC: ac97: Drop delayed device registration")
Reported-by: Manuel Lauss <manuel.lauss@gmail.com>
Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Tested-by: Manuel Lauss <manuel.lauss@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
---
 include/sound/soc.h  |  1 +
 sound/soc/soc-ac97.c | 36 ++++++++++++++++++++++++++++++------
 2 files changed, 31 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc.h b/include/sound/soc.h
index b4fca9aed2a..ac8b333acb4 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -498,6 +498,7 @@ int snd_soc_test_bits(struct snd_soc_codec *codec, unsigned int reg,
 				unsigned int mask, unsigned int value);
 
 #ifdef CONFIG_SND_SOC_AC97_BUS
+struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec);
 struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec);
 void snd_soc_free_ac97_codec(struct snd_ac97 *ac97);
 
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index 2e10e9a3837..08d7259bbaa 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -48,15 +48,18 @@ static void soc_ac97_device_release(struct device *dev)
 }
 
 /**
- * snd_soc_new_ac97_codec - initailise AC97 device
- * @codec: audio codec
+ * snd_soc_alloc_ac97_codec() - Allocate new a AC'97 device
+ * @codec: The CODEC for which to create the AC'97 device
  *
- * Initialises AC97 codec resources for use by ad-hoc devices only.
+ * Allocated a new snd_ac97 device and intializes it, but does not yet register
+ * it. The caller is responsible to either call device_add(&ac97->dev) to
+ * register the device, or to call put_device(&ac97->dev) to free the device.
+ *
+ * Returns: A snd_ac97 device or a PTR_ERR in case of an error.
  */
-struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
+struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec)
 {
 	struct snd_ac97 *ac97;
-	int ret;
 
 	ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
 	if (ac97 == NULL)
@@ -73,7 +76,28 @@ struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
 		     codec->component.card->snd_card->number, 0,
 		     codec->component.name);
 
-	ret = device_register(&ac97->dev);
+	device_initialize(&ac97->dev);
+
+	return ac97;
+}
+EXPORT_SYMBOL(snd_soc_alloc_ac97_codec);
+
+/**
+ * snd_soc_new_ac97_codec - initailise AC97 device
+ * @codec: audio codec
+ *
+ * Initialises AC97 codec resources for use by ad-hoc devices only.
+ */
+struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
+{
+	struct snd_ac97 *ac97;
+	int ret;
+
+	ac97 = snd_soc_alloc_ac97_codec(codec);
+	if (IS_ERR(ac97))
+		return ac97;
+
+	ret = device_add(&ac97->dev);
 	if (ret) {
 		put_device(&ac97->dev);
 		return ERR_PTR(ret);
-- 
cgit v1.2.3-70-g09d2


From d5fd120e7860c2b3d4c936a2ebadb6b244bec4c8 Mon Sep 17 00:00:00 2001
From: Jean Delvare <jdelvare@suse.de>
Date: Mon, 26 Jan 2015 20:59:31 +0100
Subject: i2c: Only include slave support if selected

Make the slave support depend on CONFIG_I2C_SLAVE. Otherwise it gets
included unconditionally, even when it is not needed.

I2C bus drivers which implement slave support must select
I2C_SLAVE.

Signed-off-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/busses/Kconfig | 1 +
 drivers/i2c/i2c-core.c     | 2 ++
 include/linux/i2c.h        | 6 ++++++
 3 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 31e8308ba89..ab838d9e28b 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -881,6 +881,7 @@ config I2C_XLR
 config I2C_RCAR
 	tristate "Renesas R-Car I2C Controller"
 	depends on ARCH_SHMOBILE || COMPILE_TEST
+	select I2C_SLAVE
 	help
 	  If you say yes to this option, support will be included for the
 	  R-Car I2C controller.
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 39d25a8cb1a..e9eae57a2b5 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -2972,6 +2972,7 @@ trace:
 }
 EXPORT_SYMBOL(i2c_smbus_xfer);
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb)
 {
 	int ret;
@@ -3019,6 +3020,7 @@ int i2c_slave_unregister(struct i2c_client *client)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(i2c_slave_unregister);
+#endif
 
 MODULE_AUTHOR("Simon G. Vogl <simon@tk.uni-linz.ac.at>");
 MODULE_DESCRIPTION("I2C-Bus main module");
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index e3a1721c835..7c7695940dd 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -228,7 +228,9 @@ struct i2c_client {
 	struct device dev;		/* the device structure		*/
 	int irq;			/* irq issued by device		*/
 	struct list_head detected;
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 	i2c_slave_cb_t slave_cb;	/* callback for slave mode	*/
+#endif
 };
 #define to_i2c_client(d) container_of(d, struct i2c_client, dev)
 
@@ -253,6 +255,7 @@ static inline void i2c_set_clientdata(struct i2c_client *dev, void *data)
 
 /* I2C slave support */
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 enum i2c_slave_event {
 	I2C_SLAVE_REQ_READ_START,
 	I2C_SLAVE_REQ_READ_END,
@@ -269,6 +272,7 @@ static inline int i2c_slave_event(struct i2c_client *client,
 {
 	return client->slave_cb(client, event, val);
 }
+#endif
 
 /**
  * struct i2c_board_info - template for device creation
@@ -404,8 +408,10 @@ struct i2c_algorithm {
 	/* To determine what the adapter supports */
 	u32 (*functionality) (struct i2c_adapter *);
 
+#if IS_ENABLED(CONFIG_I2C_SLAVE)
 	int (*reg_slave)(struct i2c_client *client);
 	int (*unreg_slave)(struct i2c_client *client);
+#endif
 };
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 9879de7373fcfb466ec198293b6ccc1ad7a42dd8 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Mon, 26 Jan 2015 12:58:32 -0800
Subject: mm: page_alloc: embed OOM killing naturally into allocation slowpath

The OOM killing invocation does a lot of duplicative checks against the
task's allocation context.  Rework it to take advantage of the existing
checks in the allocator slowpath.

The OOM killer is invoked when the allocator is unable to reclaim any
pages but the allocation has to keep looping.  Instead of having a check
for __GFP_NORETRY hidden in oom_gfp_allowed(), just move the OOM
invocation to the true branch of should_alloc_retry().  The __GFP_FS
check from oom_gfp_allowed() can then be moved into the OOM avoidance
branch in __alloc_pages_may_oom(), along with the PF_DUMPCORE test.

__alloc_pages_may_oom() can then signal to the caller whether the OOM
killer was invoked, instead of requiring it to duplicate the order and
high_zoneidx checks to guess this when deciding whether to continue.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/oom.h |  5 ----
 mm/page_alloc.c     | 82 +++++++++++++++++++++++------------------------------
 2 files changed, 35 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/linux/oom.h b/include/linux/oom.h
index 853698c721f..76200984d1e 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -85,11 +85,6 @@ static inline void oom_killer_enable(void)
 	oom_killer_disabled = false;
 }
 
-static inline bool oom_gfp_allowed(gfp_t gfp_mask)
-{
-	return (gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY);
-}
-
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
 static inline bool task_will_free_mem(struct task_struct *task)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7633c503a11..8e20f9c2fa5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2332,12 +2332,21 @@ static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int classzone_idx, int migratetype)
+	int classzone_idx, int migratetype, unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	/* Acquire the per-zone oom lock for each zone */
+	*did_some_progress = 0;
+
+	if (oom_killer_disabled)
+		return NULL;
+
+	/*
+	 * Acquire the per-zone oom lock for each zone.  If that
+	 * fails, somebody else is making progress for us.
+	 */
 	if (!oom_zonelist_trylock(zonelist, gfp_mask)) {
+		*did_some_progress = 1;
 		schedule_timeout_uninterruptible(1);
 		return NULL;
 	}
@@ -2363,12 +2372,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 		goto out;
 
 	if (!(gfp_mask & __GFP_NOFAIL)) {
+		/* Coredumps can quickly deplete all memory reserves */
+		if (current->flags & PF_DUMPCORE)
+			goto out;
 		/* The OOM killer will not help higher order allocs */
 		if (order > PAGE_ALLOC_COSTLY_ORDER)
 			goto out;
 		/* The OOM killer does not needlessly kill tasks for lowmem */
 		if (high_zoneidx < ZONE_NORMAL)
 			goto out;
+		/* The OOM killer does not compensate for light reclaim */
+		if (!(gfp_mask & __GFP_FS))
+			goto out;
 		/*
 		 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
 		 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -2381,7 +2396,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 	/* Exhausted what can be done so it's blamo time */
 	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
-
+	*did_some_progress = 1;
 out:
 	oom_zonelist_unlock(zonelist, gfp_mask);
 	return page;
@@ -2658,7 +2673,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	    (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
-restart:
+retry:
 	if (!(gfp_mask & __GFP_NO_KSWAPD))
 		wake_all_kswapds(order, zonelist, high_zoneidx,
 				preferred_zone, nodemask);
@@ -2681,7 +2696,6 @@ restart:
 		classzone_idx = zonelist_zone_idx(preferred_zoneref);
 	}
 
-rebalance:
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2788,54 +2802,28 @@ rebalance:
 	if (page)
 		goto got_pg;
 
-	/*
-	 * If we failed to make any progress reclaiming, then we are
-	 * running out of options and have to consider going OOM
-	 */
-	if (!did_some_progress) {
-		if (oom_gfp_allowed(gfp_mask)) {
-			if (oom_killer_disabled)
-				goto nopage;
-			/* Coredumps can quickly deplete all memory reserves */
-			if ((current->flags & PF_DUMPCORE) &&
-			    !(gfp_mask & __GFP_NOFAIL))
-				goto nopage;
-			page = __alloc_pages_may_oom(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask, preferred_zone,
-					classzone_idx, migratetype);
-			if (page)
-				goto got_pg;
-
-			if (!(gfp_mask & __GFP_NOFAIL)) {
-				/*
-				 * The oom killer is not called for high-order
-				 * allocations that may fail, so if no progress
-				 * is being made, there are no other options and
-				 * retrying is unlikely to help.
-				 */
-				if (order > PAGE_ALLOC_COSTLY_ORDER)
-					goto nopage;
-				/*
-				 * The oom killer is not called for lowmem
-				 * allocations to prevent needlessly killing
-				 * innocent tasks.
-				 */
-				if (high_zoneidx < ZONE_NORMAL)
-					goto nopage;
-			}
-
-			goto restart;
-		}
-	}
-
 	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, did_some_progress,
 						pages_reclaimed)) {
+		/*
+		 * If we fail to make progress by freeing individual
+		 * pages, but the allocation wants us to keep going,
+		 * start OOM killing tasks.
+		 */
+		if (!did_some_progress) {
+			page = __alloc_pages_may_oom(gfp_mask, order, zonelist,
+						high_zoneidx, nodemask,
+						preferred_zone, classzone_idx,
+						migratetype,&did_some_progress);
+			if (page)
+				goto got_pg;
+			if (!did_some_progress)
+				goto nopage;
+		}
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
-		goto rebalance;
+		goto retry;
 	} else {
 		/*
 		 * High-order allocations do not necessarily loop after
-- 
cgit v1.2.3-70-g09d2


From 07261edb971492c6b41b44d7b1b51f76807d30ad Mon Sep 17 00:00:00 2001
From: Pranith Kumar <bobby.prani@gmail.com>
Date: Mon, 26 Jan 2015 12:58:43 -0800
Subject: printk: add dummy routine for when CONFIG_PRINTK=n

There are missing dummy routines for log_buf_addr_get() and
log_buf_len_get() for when CONFIG_PRINTK is not set causing build
failures.

This patch adds these dummy routines at the appropriate location.

Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Petr Mladek <pmladek@suse.cz>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/printk.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index c8f170324e6..4d5bf572657 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -10,9 +10,6 @@
 extern const char linux_banner[];
 extern const char linux_proc_banner[];
 
-extern char *log_buf_addr_get(void);
-extern u32 log_buf_len_get(void);
-
 static inline int printk_get_level(const char *buffer)
 {
 	if (buffer[0] == KERN_SOH_ASCII && buffer[1]) {
@@ -163,6 +160,8 @@ extern int kptr_restrict;
 
 extern void wake_up_klogd(void);
 
+char *log_buf_addr_get(void);
+u32 log_buf_len_get(void);
 void log_buf_kexec_setup(void);
 void __init setup_log_buf(int early);
 void dump_stack_set_arch_desc(const char *fmt, ...);
@@ -198,6 +197,16 @@ static inline void wake_up_klogd(void)
 {
 }
 
+static inline char *log_buf_addr_get(void)
+{
+	return NULL;
+}
+
+static inline u32 log_buf_len_get(void)
+{
+	return 0;
+}
+
 static inline void log_buf_kexec_setup(void)
 {
 }
-- 
cgit v1.2.3-70-g09d2


From 0b35fa7daefe9da6fdef91d95e07eebb714a8fcc Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 25 Jan 2015 23:33:30 +0100
Subject: NFC: st21nfcb: Remove useless include

include/linux/platform_data/st21nfcb.h is phy generic.
There is no need to include linux/i2c.h

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/platform_data/st21nfcb.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/platform_data/st21nfcb.h b/include/linux/platform_data/st21nfcb.h
index c3b432f5b63..05c54c958cc 100644
--- a/include/linux/platform_data/st21nfcb.h
+++ b/include/linux/platform_data/st21nfcb.h
@@ -19,8 +19,6 @@
 #ifndef _ST21NFCB_NCI_H_
 #define _ST21NFCB_NCI_H_
 
-#include <linux/i2c.h>
-
 #define ST21NFCB_NCI_DRIVER_NAME "st21nfcb_nci"
 
 struct st21nfcb_nfc_platform_data {
-- 
cgit v1.2.3-70-g09d2


From 6da7c85c75eed769423b428eb654eaaf89d273c1 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 25 Jan 2015 23:33:31 +0100
Subject: NFC: st21nfcb: Fix copy/paste error in comment

include/linux/platform_data/st21nfcb.h is based on
include/linux/platform_data/st21nfca.h.

The endif comment is inacurrate for st21nfcb.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/platform_data/st21nfcb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/platform_data/st21nfcb.h b/include/linux/platform_data/st21nfcb.h
index 05c54c958cc..b023373d987 100644
--- a/include/linux/platform_data/st21nfcb.h
+++ b/include/linux/platform_data/st21nfcb.h
@@ -26,4 +26,4 @@ struct st21nfcb_nfc_platform_data {
 	unsigned int irq_polarity;
 };
 
-#endif /* _ST21NFCA_HCI_H_ */
+#endif /* _ST21NFCB_NCI_H_ */
-- 
cgit v1.2.3-70-g09d2


From 7b1883cefc288b2725966357edd2d8f321605622 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joestringer@nicira.com>
Date: Wed, 21 Jan 2015 16:42:51 -0800
Subject: genetlink: Add genlmsg_parse() helper function.

The first user will be the next patch.

Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/genetlink.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

(limited to 'include')

diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index f24aa83b80b..d5a9a8b5af3 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -205,6 +205,23 @@ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr,
 				   NLMSG_HDRLEN);
 }
 
+/**
+ * genlmsg_parse - parse attributes of a genetlink message
+ * @nlh: netlink message header
+ * @family: genetlink message family
+ * @tb: destination array with maxtype+1 elements
+ * @maxtype: maximum attribute type to be expected
+ * @policy: validation policy
+ * */
+static inline int genlmsg_parse(const struct nlmsghdr *nlh,
+				const struct genl_family *family,
+				struct nlattr *tb[], int maxtype,
+				const struct nla_policy *policy)
+{
+	return nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype,
+			   policy);
+}
+
 /**
  * genl_dump_check_consistent - check if sequence is consistent and advertise if not
  * @cb: netlink callback structure that stores the sequence number
-- 
cgit v1.2.3-70-g09d2


From 74ed7ab9264c54471c7f057409d352052820d750 Mon Sep 17 00:00:00 2001
From: Joe Stringer <joestringer@nicira.com>
Date: Wed, 21 Jan 2015 16:42:52 -0800
Subject: openvswitch: Add support for unique flow IDs.

Previously, flows were manipulated by userspace specifying a full,
unmasked flow key. This adds significant burden onto flow
serialization/deserialization, particularly when dumping flows.

This patch adds an alternative way to refer to flows using a
variable-length "unique flow identifier" (UFID). At flow setup time,
userspace may specify a UFID for a flow, which is stored with the flow
and inserted into a separate table for lookup, in addition to the
standard flow table. Flows created using a UFID must be fetched or
deleted using the UFID.

All flow dump operations may now be made more terse with OVS_UFID_F_*
flags. For example, the OVS_UFID_F_OMIT_KEY flag allows responses to
omit the flow key from a datapath operation if the flow has a
corresponding UFID. This significantly reduces the time spent assembling
and transacting netlink messages. With all OVS_UFID_F_OMIT_* flags
enabled, the datapath only returns the UFID and statistics for each flow
during flow dump, increasing ovs-vswitchd revalidator performance by 40%
or more.

Signed-off-by: Joe Stringer <joestringer@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/openvswitch.txt |  13 ++
 include/uapi/linux/openvswitch.h         |  20 +++
 net/openvswitch/datapath.c               | 207 +++++++++++++++++++++++--------
 net/openvswitch/flow.h                   |  28 ++++-
 net/openvswitch/flow_netlink.c           |  68 +++++++++-
 net/openvswitch/flow_netlink.h           |   8 +-
 net/openvswitch/flow_table.c             | 187 +++++++++++++++++++++++-----
 net/openvswitch/flow_table.h             |   8 +-
 8 files changed, 448 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/openvswitch.txt b/Documentation/networking/openvswitch.txt
index 37c20ee2455..b3b9ac61d29 100644
--- a/Documentation/networking/openvswitch.txt
+++ b/Documentation/networking/openvswitch.txt
@@ -131,6 +131,19 @@ performs best-effort detection of overlapping wildcarded flows and may reject
 some but not all of them. However, this behavior may change in future versions.
 
 
+Unique flow identifiers
+-----------------------
+
+An alternative to using the original match portion of a key as the handle for
+flow identification is a unique flow identifier, or "UFID". UFIDs are optional
+for both the kernel and user space program.
+
+User space programs that support UFID are expected to provide it during flow
+setup in addition to the flow, then refer to the flow using the UFID for all
+future operations. The kernel is not required to index flows by the original
+flow key if a UFID is specified.
+
+
 Basic rule for evolving flow keys
 ---------------------------------
 
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index cd8d933963c..7a8785a9924 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -459,6 +459,14 @@ struct ovs_key_nd {
  * a wildcarded match. Omitting attribute is treated as wildcarding all
  * corresponding fields. Optional for all requests. If not present,
  * all flow key bits are exact match bits.
+ * @OVS_FLOW_ATTR_UFID: A value between 1-16 octets specifying a unique
+ * identifier for the flow. Causes the flow to be indexed by this value rather
+ * than the value of the %OVS_FLOW_ATTR_KEY attribute. Optional for all
+ * requests. Present in notifications if the flow was created with this
+ * attribute.
+ * @OVS_FLOW_ATTR_UFID_FLAGS: A 32-bit value of OR'd %OVS_UFID_F_*
+ * flags that provide alternative semantics for flow installation and
+ * retrieval. Optional for all requests.
  *
  * These attributes follow the &struct ovs_header within the Generic Netlink
  * payload for %OVS_FLOW_* commands.
@@ -474,11 +482,23 @@ enum ovs_flow_attr {
 	OVS_FLOW_ATTR_MASK,      /* Sequence of OVS_KEY_ATTR_* attributes. */
 	OVS_FLOW_ATTR_PROBE,     /* Flow operation is a feature probe, error
 				  * logging should be suppressed. */
+	OVS_FLOW_ATTR_UFID,      /* Variable length unique flow identifier. */
+	OVS_FLOW_ATTR_UFID_FLAGS,/* u32 of OVS_UFID_F_*. */
 	__OVS_FLOW_ATTR_MAX
 };
 
 #define OVS_FLOW_ATTR_MAX (__OVS_FLOW_ATTR_MAX - 1)
 
+/**
+ * Omit attributes for notifications.
+ *
+ * If a datapath request contains an %OVS_UFID_F_OMIT_* flag, then the datapath
+ * may omit the corresponding %OVS_FLOW_ATTR_* from the response.
+ */
+#define OVS_UFID_F_OMIT_KEY      (1 << 0)
+#define OVS_UFID_F_OMIT_MASK     (1 << 1)
+#define OVS_UFID_F_OMIT_ACTIONS  (1 << 2)
+
 /**
  * enum ovs_sample_attr - Attributes for %OVS_ACTION_ATTR_SAMPLE action.
  * @OVS_SAMPLE_ATTR_PROBABILITY: 32-bit fraction of packets to sample with
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 257b97546b3..ae5e77cdc0c 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -65,6 +65,8 @@ static struct genl_family dp_packet_genl_family;
 static struct genl_family dp_flow_genl_family;
 static struct genl_family dp_datapath_genl_family;
 
+static const struct nla_policy flow_policy[];
+
 static const struct genl_multicast_group ovs_dp_flow_multicast_group = {
 	.name = OVS_FLOW_MCGROUP,
 };
@@ -662,15 +664,48 @@ static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats,
 	}
 }
 
-static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
+static bool should_fill_key(const struct sw_flow_id *sfid, uint32_t ufid_flags)
+{
+	return ovs_identifier_is_ufid(sfid) &&
+	       !(ufid_flags & OVS_UFID_F_OMIT_KEY);
+}
+
+static bool should_fill_mask(uint32_t ufid_flags)
+{
+	return !(ufid_flags & OVS_UFID_F_OMIT_MASK);
+}
+
+static bool should_fill_actions(uint32_t ufid_flags)
 {
-	return NLMSG_ALIGN(sizeof(struct ovs_header))
-		+ nla_total_size(ovs_key_attr_size()) /* OVS_FLOW_ATTR_KEY */
-		+ nla_total_size(ovs_key_attr_size()) /* OVS_FLOW_ATTR_MASK */
+	return !(ufid_flags & OVS_UFID_F_OMIT_ACTIONS);
+}
+
+static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts,
+				    const struct sw_flow_id *sfid,
+				    uint32_t ufid_flags)
+{
+	size_t len = NLMSG_ALIGN(sizeof(struct ovs_header));
+
+	/* OVS_FLOW_ATTR_UFID */
+	if (sfid && ovs_identifier_is_ufid(sfid))
+		len += nla_total_size(sfid->ufid_len);
+
+	/* OVS_FLOW_ATTR_KEY */
+	if (!sfid || should_fill_key(sfid, ufid_flags))
+		len += nla_total_size(ovs_key_attr_size());
+
+	/* OVS_FLOW_ATTR_MASK */
+	if (should_fill_mask(ufid_flags))
+		len += nla_total_size(ovs_key_attr_size());
+
+	/* OVS_FLOW_ATTR_ACTIONS */
+	if (should_fill_actions(ufid_flags))
+		len += nla_total_size(acts->actions_len);
+
+	return len
 		+ nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */
 		+ nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */
-		+ nla_total_size(8) /* OVS_FLOW_ATTR_USED */
-		+ nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */
+		+ nla_total_size(8); /* OVS_FLOW_ATTR_USED */
 }
 
 /* Called with ovs_mutex or RCU read lock. */
@@ -741,7 +776,7 @@ static int ovs_flow_cmd_fill_actions(const struct sw_flow *flow,
 /* Called with ovs_mutex or RCU read lock. */
 static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 				  struct sk_buff *skb, u32 portid,
-				  u32 seq, u32 flags, u8 cmd)
+				  u32 seq, u32 flags, u8 cmd, u32 ufid_flags)
 {
 	const int skb_orig_len = skb->len;
 	struct ovs_header *ovs_header;
@@ -754,21 +789,31 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 
 	ovs_header->dp_ifindex = dp_ifindex;
 
-	err = ovs_nla_put_unmasked_key(flow, skb);
+	err = ovs_nla_put_identifier(flow, skb);
 	if (err)
 		goto error;
 
-	err = ovs_nla_put_mask(flow, skb);
-	if (err)
-		goto error;
+	if (should_fill_key(&flow->id, ufid_flags)) {
+		err = ovs_nla_put_masked_key(flow, skb);
+		if (err)
+			goto error;
+	}
+
+	if (should_fill_mask(ufid_flags)) {
+		err = ovs_nla_put_mask(flow, skb);
+		if (err)
+			goto error;
+	}
 
 	err = ovs_flow_cmd_fill_stats(flow, skb);
 	if (err)
 		goto error;
 
-	err = ovs_flow_cmd_fill_actions(flow, skb, skb_orig_len);
-	if (err)
-		goto error;
+	if (should_fill_actions(ufid_flags)) {
+		err = ovs_flow_cmd_fill_actions(flow, skb, skb_orig_len);
+		if (err)
+			goto error;
+	}
 
 	genlmsg_end(skb, ovs_header);
 	return 0;
@@ -780,15 +825,19 @@ error:
 
 /* May not be called with RCU read lock. */
 static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts,
+					       const struct sw_flow_id *sfid,
 					       struct genl_info *info,
-					       bool always)
+					       bool always,
+					       uint32_t ufid_flags)
 {
 	struct sk_buff *skb;
+	size_t len;
 
 	if (!always && !ovs_must_notify(&dp_flow_genl_family, info, 0))
 		return NULL;
 
-	skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL);
+	len = ovs_flow_cmd_msg_size(acts, sfid, ufid_flags);
+	skb = genlmsg_new_unicast(len, info, GFP_KERNEL);
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
@@ -799,19 +848,19 @@ static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *act
 static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
 					       int dp_ifindex,
 					       struct genl_info *info, u8 cmd,
-					       bool always)
+					       bool always, u32 ufid_flags)
 {
 	struct sk_buff *skb;
 	int retval;
 
-	skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info,
-				      always);
+	skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts),
+				      &flow->id, info, always, ufid_flags);
 	if (IS_ERR_OR_NULL(skb))
 		return skb;
 
 	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
 					info->snd_portid, info->snd_seq, 0,
-					cmd);
+					cmd, ufid_flags);
 	BUG_ON(retval < 0);
 	return skb;
 }
@@ -820,12 +869,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
 	struct ovs_header *ovs_header = info->userhdr;
-	struct sw_flow *flow, *new_flow;
+	struct sw_flow *flow = NULL, *new_flow;
 	struct sw_flow_mask mask;
 	struct sk_buff *reply;
 	struct datapath *dp;
+	struct sw_flow_key key;
 	struct sw_flow_actions *acts;
 	struct sw_flow_match match;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 	int error;
 	bool log = !a[OVS_FLOW_ATTR_PROBE];
 
@@ -850,13 +901,19 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	/* Extract key. */
-	ovs_match_init(&match, &new_flow->unmasked_key, &mask);
+	ovs_match_init(&match, &key, &mask);
 	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
 				  a[OVS_FLOW_ATTR_MASK], log);
 	if (error)
 		goto err_kfree_flow;
 
-	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
+	ovs_flow_mask_key(&new_flow->key, &key, &mask);
+
+	/* Extract flow identifier. */
+	error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID],
+				       &key, log);
+	if (error)
+		goto err_kfree_flow;
 
 	/* Validate actions. */
 	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
@@ -866,7 +923,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		goto err_kfree_flow;
 	}
 
-	reply = ovs_flow_cmd_alloc_info(acts, info, false);
+	reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false,
+					ufid_flags);
 	if (IS_ERR(reply)) {
 		error = PTR_ERR(reply);
 		goto err_kfree_acts;
@@ -878,8 +936,12 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		error = -ENODEV;
 		goto err_unlock_ovs;
 	}
+
 	/* Check if this is a duplicate flow */
-	flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->unmasked_key);
+	if (ovs_identifier_is_ufid(&new_flow->id))
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &new_flow->id);
+	if (!flow)
+		flow = ovs_flow_tbl_lookup(&dp->table, &key);
 	if (likely(!flow)) {
 		rcu_assign_pointer(new_flow->sf_acts, acts);
 
@@ -895,7 +957,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
-						       OVS_FLOW_CMD_NEW);
+						       OVS_FLOW_CMD_NEW,
+						       ufid_flags);
 			BUG_ON(error < 0);
 		}
 		ovs_unlock();
@@ -913,10 +976,15 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 			error = -EEXIST;
 			goto err_unlock_ovs;
 		}
-		/* The unmasked key has to be the same for flow updates. */
-		if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
-			/* Look for any overlapping flow. */
-			flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+		/* The flow identifier has to be the same for flow updates.
+		 * Look for any overlapping flow.
+		 */
+		if (unlikely(!ovs_flow_cmp(flow, &match))) {
+			if (ovs_identifier_is_key(&flow->id))
+				flow = ovs_flow_tbl_lookup_exact(&dp->table,
+								 &match);
+			else /* UFID matches but key is different */
+				flow = NULL;
 			if (!flow) {
 				error = -ENOENT;
 				goto err_unlock_ovs;
@@ -931,7 +999,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
-						       OVS_FLOW_CMD_NEW);
+						       OVS_FLOW_CMD_NEW,
+						       ufid_flags);
 			BUG_ON(error < 0);
 		}
 		ovs_unlock();
@@ -987,8 +1056,11 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct sw_flow_actions *old_acts = NULL, *acts = NULL;
 	struct sw_flow_match match;
+	struct sw_flow_id sfid;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 	int error;
 	bool log = !a[OVS_FLOW_ATTR_PROBE];
+	bool ufid_present;
 
 	/* Extract key. */
 	error = -EINVAL;
@@ -997,6 +1069,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		goto error;
 	}
 
+	ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log);
 	ovs_match_init(&match, &key, &mask);
 	error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY],
 				  a[OVS_FLOW_ATTR_MASK], log);
@@ -1013,7 +1086,8 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		}
 
 		/* Can allocate before locking if have acts. */
-		reply = ovs_flow_cmd_alloc_info(acts, info, false);
+		reply = ovs_flow_cmd_alloc_info(acts, &sfid, info, false,
+						ufid_flags);
 		if (IS_ERR(reply)) {
 			error = PTR_ERR(reply);
 			goto err_kfree_acts;
@@ -1027,7 +1101,10 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock_ovs;
 	}
 	/* Check that the flow exists. */
-	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (ufid_present)
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &sfid);
+	else
+		flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 	if (unlikely(!flow)) {
 		error = -ENOENT;
 		goto err_unlock_ovs;
@@ -1043,13 +1120,16 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 						       ovs_header->dp_ifindex,
 						       reply, info->snd_portid,
 						       info->snd_seq, 0,
-						       OVS_FLOW_CMD_NEW);
+						       OVS_FLOW_CMD_NEW,
+						       ufid_flags);
 			BUG_ON(error < 0);
 		}
 	} else {
 		/* Could not alloc without acts before locking. */
 		reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex,
-						info, OVS_FLOW_CMD_NEW, false);
+						info, OVS_FLOW_CMD_NEW, false,
+						ufid_flags);
+
 		if (unlikely(IS_ERR(reply))) {
 			error = PTR_ERR(reply);
 			goto err_unlock_ovs;
@@ -1086,17 +1166,22 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow *flow;
 	struct datapath *dp;
 	struct sw_flow_match match;
-	int err;
+	struct sw_flow_id ufid;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
+	int err = 0;
 	bool log = !a[OVS_FLOW_ATTR_PROBE];
+	bool ufid_present;
 
-	if (!a[OVS_FLOW_ATTR_KEY]) {
+	ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log);
+	if (a[OVS_FLOW_ATTR_KEY]) {
+		ovs_match_init(&match, &key, NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL,
+					log);
+	} else if (!ufid_present) {
 		OVS_NLERR(log,
 			  "Flow get message rejected, Key attribute missing.");
-		return -EINVAL;
+		err = -EINVAL;
 	}
-
-	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, log);
 	if (err)
 		return err;
 
@@ -1107,14 +1192,17 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (ufid_present)
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid);
+	else
+		flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 	if (!flow) {
 		err = -ENOENT;
 		goto unlock;
 	}
 
 	reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info,
-					OVS_FLOW_CMD_NEW, true);
+					OVS_FLOW_CMD_NEW, true, ufid_flags);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
 		goto unlock;
@@ -1133,13 +1221,17 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct ovs_header *ovs_header = info->userhdr;
 	struct sw_flow_key key;
 	struct sk_buff *reply;
-	struct sw_flow *flow;
+	struct sw_flow *flow = NULL;
 	struct datapath *dp;
 	struct sw_flow_match match;
+	struct sw_flow_id ufid;
+	u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 	int err;
 	bool log = !a[OVS_FLOW_ATTR_PROBE];
+	bool ufid_present;
 
-	if (likely(a[OVS_FLOW_ATTR_KEY])) {
+	ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log);
+	if (a[OVS_FLOW_ATTR_KEY]) {
 		ovs_match_init(&match, &key, NULL);
 		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL,
 					log);
@@ -1154,12 +1246,15 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	if (unlikely(!a[OVS_FLOW_ATTR_KEY])) {
+	if (unlikely(!a[OVS_FLOW_ATTR_KEY] && !ufid_present)) {
 		err = ovs_flow_tbl_flush(&dp->table);
 		goto unlock;
 	}
 
-	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (ufid_present)
+		flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid);
+	else
+		flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
 	if (unlikely(!flow)) {
 		err = -ENOENT;
 		goto unlock;
@@ -1169,14 +1264,15 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	ovs_unlock();
 
 	reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts,
-					info, false);
+					&flow->id, info, false, ufid_flags);
 	if (likely(reply)) {
 		if (likely(!IS_ERR(reply))) {
 			rcu_read_lock();	/*To keep RCU checker happy. */
 			err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex,
 						     reply, info->snd_portid,
 						     info->snd_seq, 0,
-						     OVS_FLOW_CMD_DEL);
+						     OVS_FLOW_CMD_DEL,
+						     ufid_flags);
 			rcu_read_unlock();
 			BUG_ON(err < 0);
 
@@ -1195,9 +1291,18 @@ unlock:
 
 static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct nlattr *a[__OVS_FLOW_ATTR_MAX];
 	struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
 	struct table_instance *ti;
 	struct datapath *dp;
+	u32 ufid_flags;
+	int err;
+
+	err = genlmsg_parse(cb->nlh, &dp_flow_genl_family, a,
+			    OVS_FLOW_ATTR_MAX, flow_policy);
+	if (err)
+		return err;
+	ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]);
 
 	rcu_read_lock();
 	dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
@@ -1220,7 +1325,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
-					   OVS_FLOW_CMD_NEW) < 0)
+					   OVS_FLOW_CMD_NEW, ufid_flags) < 0)
 			break;
 
 		cb->args[0] = bucket;
@@ -1236,6 +1341,8 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
 	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
 	[OVS_FLOW_ATTR_PROBE] = { .type = NLA_FLAG },
+	[OVS_FLOW_ATTR_UFID] = { .type = NLA_UNSPEC, .len = 1 },
+	[OVS_FLOW_ATTR_UFID_FLAGS] = { .type = NLA_U32 },
 };
 
 static const struct genl_ops dp_flow_genl_ops[] = {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index d3d0a406562..a076e445ccc 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -197,6 +197,16 @@ struct sw_flow_match {
 	struct sw_flow_mask *mask;
 };
 
+#define MAX_UFID_LENGTH 16 /* 128 bits */
+
+struct sw_flow_id {
+	u32 ufid_len;
+	union {
+		u32 ufid[MAX_UFID_LENGTH / 4];
+		struct sw_flow_key *unmasked_key;
+	};
+};
+
 struct sw_flow_actions {
 	struct rcu_head rcu;
 	u32 actions_len;
@@ -213,13 +223,15 @@ struct flow_stats {
 
 struct sw_flow {
 	struct rcu_head rcu;
-	struct hlist_node hash_node[2];
-	u32 hash;
+	struct {
+		struct hlist_node node[2];
+		u32 hash;
+	} flow_table, ufid_table;
 	int stats_last_writer;		/* NUMA-node id of the last writer on
 					 * 'stats[0]'.
 					 */
 	struct sw_flow_key key;
-	struct sw_flow_key unmasked_key;
+	struct sw_flow_id id;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
 	struct flow_stats __rcu *stats[]; /* One for each NUMA node.  First one
@@ -243,6 +255,16 @@ struct arp_eth_header {
 	unsigned char       ar_tip[4];		/* target IP address        */
 } __packed;
 
+static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid)
+{
+	return sfid->ufid_len;
+}
+
+static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid)
+{
+	return !ovs_identifier_is_ufid(sfid);
+}
+
 void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
 			   const struct sk_buff *);
 void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 33751f81bfc..8b9a612b39d 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1180,6 +1180,59 @@ free_newmask:
 	return err;
 }
 
+static size_t get_ufid_len(const struct nlattr *attr, bool log)
+{
+	size_t len;
+
+	if (!attr)
+		return 0;
+
+	len = nla_len(attr);
+	if (len < 1 || len > MAX_UFID_LENGTH) {
+		OVS_NLERR(log, "ufid size %u bytes exceeds the range (1, %d)",
+			  nla_len(attr), MAX_UFID_LENGTH);
+		return 0;
+	}
+
+	return len;
+}
+
+/* Initializes 'flow->ufid', returning true if 'attr' contains a valid UFID,
+ * or false otherwise.
+ */
+bool ovs_nla_get_ufid(struct sw_flow_id *sfid, const struct nlattr *attr,
+		      bool log)
+{
+	sfid->ufid_len = get_ufid_len(attr, log);
+	if (sfid->ufid_len)
+		memcpy(sfid->ufid, nla_data(attr), sfid->ufid_len);
+
+	return sfid->ufid_len;
+}
+
+int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
+			   const struct sw_flow_key *key, bool log)
+{
+	struct sw_flow_key *new_key;
+
+	if (ovs_nla_get_ufid(sfid, ufid, log))
+		return 0;
+
+	/* If UFID was not provided, use unmasked key. */
+	new_key = kmalloc(sizeof(*new_key), GFP_KERNEL);
+	if (!new_key)
+		return -ENOMEM;
+	memcpy(new_key, key, sizeof(*key));
+	sfid->unmasked_key = new_key;
+
+	return 0;
+}
+
+u32 ovs_nla_get_ufid_flags(const struct nlattr *attr)
+{
+	return attr ? nla_get_u32(attr) : 0;
+}
+
 /**
  * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key.
  * @key: Receives extracted in_port, priority, tun_key and skb_mark.
@@ -1450,9 +1503,20 @@ int ovs_nla_put_key(const struct sw_flow_key *swkey,
 }
 
 /* Called with ovs_mutex or RCU read lock. */
-int ovs_nla_put_unmasked_key(const struct sw_flow *flow, struct sk_buff *skb)
+int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb)
+{
+	if (ovs_identifier_is_ufid(&flow->id))
+		return nla_put(skb, OVS_FLOW_ATTR_UFID, flow->id.ufid_len,
+			       flow->id.ufid);
+
+	return ovs_nla_put_key(flow->id.unmasked_key, flow->id.unmasked_key,
+			       OVS_FLOW_ATTR_KEY, false, skb);
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb)
 {
-	return ovs_nla_put_key(&flow->unmasked_key, &flow->unmasked_key,
+	return ovs_nla_put_key(&flow->mask->key, &flow->key,
 				OVS_FLOW_ATTR_KEY, false, skb);
 }
 
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index 9ed09e66876..5c3d75bff31 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -48,7 +48,8 @@ int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *,
 int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *,
 			      bool log);
 
-int ovs_nla_put_unmasked_key(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb);
+int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb);
 int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb);
 
 int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key,
@@ -56,6 +57,11 @@ int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key,
 int ovs_nla_put_egress_tunnel_key(struct sk_buff *,
 				  const struct ovs_tunnel_info *);
 
+bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log);
+int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
+			   const struct sw_flow_key *key, bool log);
+u32 ovs_nla_get_ufid_flags(const struct nlattr *attr);
+
 int ovs_nla_copy_actions(const struct nlattr *attr,
 			 const struct sw_flow_key *key,
 			 struct sw_flow_actions **sfa, bool log);
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 9a3f41f26da..5e57628e658 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -139,6 +139,8 @@ static void flow_free(struct sw_flow *flow)
 {
 	int node;
 
+	if (ovs_identifier_is_key(&flow->id))
+		kfree(flow->id.unmasked_key);
 	kfree((struct sw_flow_actions __force *)flow->sf_acts);
 	for_each_node(node)
 		if (flow->stats[node])
@@ -200,18 +202,28 @@ static struct table_instance *table_instance_alloc(int new_size)
 
 int ovs_flow_tbl_init(struct flow_table *table)
 {
-	struct table_instance *ti;
+	struct table_instance *ti, *ufid_ti;
 
 	ti = table_instance_alloc(TBL_MIN_BUCKETS);
 
 	if (!ti)
 		return -ENOMEM;
 
+	ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!ufid_ti)
+		goto free_ti;
+
 	rcu_assign_pointer(table->ti, ti);
+	rcu_assign_pointer(table->ufid_ti, ufid_ti);
 	INIT_LIST_HEAD(&table->mask_list);
 	table->last_rehash = jiffies;
 	table->count = 0;
+	table->ufid_count = 0;
 	return 0;
+
+free_ti:
+	__table_instance_destroy(ti);
+	return -ENOMEM;
 }
 
 static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
@@ -221,13 +233,16 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
 	__table_instance_destroy(ti);
 }
 
-static void table_instance_destroy(struct table_instance *ti, bool deferred)
+static void table_instance_destroy(struct table_instance *ti,
+				   struct table_instance *ufid_ti,
+				   bool deferred)
 {
 	int i;
 
 	if (!ti)
 		return;
 
+	BUG_ON(!ufid_ti);
 	if (ti->keep_flows)
 		goto skip_flows;
 
@@ -236,18 +251,24 @@ static void table_instance_destroy(struct table_instance *ti, bool deferred)
 		struct hlist_head *head = flex_array_get(ti->buckets, i);
 		struct hlist_node *n;
 		int ver = ti->node_ver;
+		int ufid_ver = ufid_ti->node_ver;
 
-		hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
-			hlist_del_rcu(&flow->hash_node[ver]);
+		hlist_for_each_entry_safe(flow, n, head, flow_table.node[ver]) {
+			hlist_del_rcu(&flow->flow_table.node[ver]);
+			if (ovs_identifier_is_ufid(&flow->id))
+				hlist_del_rcu(&flow->ufid_table.node[ufid_ver]);
 			ovs_flow_free(flow, deferred);
 		}
 	}
 
 skip_flows:
-	if (deferred)
+	if (deferred) {
 		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
-	else
+		call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb);
+	} else {
 		__table_instance_destroy(ti);
+		__table_instance_destroy(ufid_ti);
+	}
 }
 
 /* No need for locking this function is called from RCU callback or
@@ -256,8 +277,9 @@ skip_flows:
 void ovs_flow_tbl_destroy(struct flow_table *table)
 {
 	struct table_instance *ti = rcu_dereference_raw(table->ti);
+	struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti);
 
-	table_instance_destroy(ti, false);
+	table_instance_destroy(ti, ufid_ti, false);
 }
 
 struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
@@ -272,7 +294,7 @@ struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti,
 	while (*bucket < ti->n_buckets) {
 		i = 0;
 		head = flex_array_get(ti->buckets, *bucket);
-		hlist_for_each_entry_rcu(flow, head, hash_node[ver]) {
+		hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) {
 			if (i < *last) {
 				i++;
 				continue;
@@ -294,16 +316,26 @@ static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash)
 				(hash & (ti->n_buckets - 1)));
 }
 
-static void table_instance_insert(struct table_instance *ti, struct sw_flow *flow)
+static void table_instance_insert(struct table_instance *ti,
+				  struct sw_flow *flow)
 {
 	struct hlist_head *head;
 
-	head = find_bucket(ti, flow->hash);
-	hlist_add_head_rcu(&flow->hash_node[ti->node_ver], head);
+	head = find_bucket(ti, flow->flow_table.hash);
+	hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head);
+}
+
+static void ufid_table_instance_insert(struct table_instance *ti,
+				       struct sw_flow *flow)
+{
+	struct hlist_head *head;
+
+	head = find_bucket(ti, flow->ufid_table.hash);
+	hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head);
 }
 
 static void flow_table_copy_flows(struct table_instance *old,
-				  struct table_instance *new)
+				  struct table_instance *new, bool ufid)
 {
 	int old_ver;
 	int i;
@@ -318,15 +350,21 @@ static void flow_table_copy_flows(struct table_instance *old,
 
 		head = flex_array_get(old->buckets, i);
 
-		hlist_for_each_entry(flow, head, hash_node[old_ver])
-			table_instance_insert(new, flow);
+		if (ufid)
+			hlist_for_each_entry(flow, head,
+					     ufid_table.node[old_ver])
+				ufid_table_instance_insert(new, flow);
+		else
+			hlist_for_each_entry(flow, head,
+					     flow_table.node[old_ver])
+				table_instance_insert(new, flow);
 	}
 
 	old->keep_flows = true;
 }
 
 static struct table_instance *table_instance_rehash(struct table_instance *ti,
-					    int n_buckets)
+						    int n_buckets, bool ufid)
 {
 	struct table_instance *new_ti;
 
@@ -334,27 +372,38 @@ static struct table_instance *table_instance_rehash(struct table_instance *ti,
 	if (!new_ti)
 		return NULL;
 
-	flow_table_copy_flows(ti, new_ti);
+	flow_table_copy_flows(ti, new_ti, ufid);
 
 	return new_ti;
 }
 
 int ovs_flow_tbl_flush(struct flow_table *flow_table)
 {
-	struct table_instance *old_ti;
-	struct table_instance *new_ti;
+	struct table_instance *old_ti, *new_ti;
+	struct table_instance *old_ufid_ti, *new_ufid_ti;
 
-	old_ti = ovsl_dereference(flow_table->ti);
 	new_ti = table_instance_alloc(TBL_MIN_BUCKETS);
 	if (!new_ti)
 		return -ENOMEM;
+	new_ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS);
+	if (!new_ufid_ti)
+		goto err_free_ti;
+
+	old_ti = ovsl_dereference(flow_table->ti);
+	old_ufid_ti = ovsl_dereference(flow_table->ufid_ti);
 
 	rcu_assign_pointer(flow_table->ti, new_ti);
+	rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti);
 	flow_table->last_rehash = jiffies;
 	flow_table->count = 0;
+	flow_table->ufid_count = 0;
 
-	table_instance_destroy(old_ti, true);
+	table_instance_destroy(old_ti, old_ufid_ti, true);
 	return 0;
+
+err_free_ti:
+	__table_instance_destroy(new_ti);
+	return -ENOMEM;
 }
 
 static u32 flow_hash(const struct sw_flow_key *key,
@@ -402,14 +451,15 @@ static bool flow_cmp_masked_key(const struct sw_flow *flow,
 	return cmp_key(&flow->key, key, range->start, range->end);
 }
 
-bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
-			       const struct sw_flow_match *match)
+static bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
+				      const struct sw_flow_match *match)
 {
 	struct sw_flow_key *key = match->key;
 	int key_start = flow_key_start(key);
 	int key_end = match->range.end;
 
-	return cmp_key(&flow->unmasked_key, key, key_start, key_end);
+	BUG_ON(ovs_identifier_is_ufid(&flow->id));
+	return cmp_key(flow->id.unmasked_key, key, key_start, key_end);
 }
 
 static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
@@ -424,8 +474,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	ovs_flow_mask_key(&masked_key, unmasked, mask);
 	hash = flow_hash(&masked_key, &mask->range);
 	head = find_bucket(ti, hash);
-	hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) {
-		if (flow->mask == mask && flow->hash == hash &&
+	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) {
+		if (flow->mask == mask && flow->flow_table.hash == hash &&
 		    flow_cmp_masked_key(flow, &masked_key, &mask->range))
 			return flow;
 	}
@@ -468,7 +518,48 @@ struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
 	/* Always called under ovs-mutex. */
 	list_for_each_entry(mask, &tbl->mask_list, list) {
 		flow = masked_flow_lookup(ti, match->key, mask);
-		if (flow && ovs_flow_cmp_unmasked_key(flow, match))  /* Found */
+		if (flow && ovs_identifier_is_key(&flow->id) &&
+		    ovs_flow_cmp_unmasked_key(flow, match))
+			return flow;
+	}
+	return NULL;
+}
+
+static u32 ufid_hash(const struct sw_flow_id *sfid)
+{
+	return jhash(sfid->ufid, sfid->ufid_len, 0);
+}
+
+static bool ovs_flow_cmp_ufid(const struct sw_flow *flow,
+			      const struct sw_flow_id *sfid)
+{
+	if (flow->id.ufid_len != sfid->ufid_len)
+		return false;
+
+	return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len);
+}
+
+bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match)
+{
+	if (ovs_identifier_is_ufid(&flow->id))
+		return flow_cmp_masked_key(flow, match->key, &match->range);
+
+	return ovs_flow_cmp_unmasked_key(flow, match);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl,
+					 const struct sw_flow_id *ufid)
+{
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ufid_ti);
+	struct sw_flow *flow;
+	struct hlist_head *head;
+	u32 hash;
+
+	hash = ufid_hash(ufid);
+	head = find_bucket(ti, hash);
+	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) {
+		if (flow->ufid_table.hash == hash &&
+		    ovs_flow_cmp_ufid(flow, ufid))
 			return flow;
 	}
 	return NULL;
@@ -485,9 +576,10 @@ int ovs_flow_tbl_num_masks(const struct flow_table *table)
 	return num;
 }
 
-static struct table_instance *table_instance_expand(struct table_instance *ti)
+static struct table_instance *table_instance_expand(struct table_instance *ti,
+						    bool ufid)
 {
-	return table_instance_rehash(ti, ti->n_buckets * 2);
+	return table_instance_rehash(ti, ti->n_buckets * 2, ufid);
 }
 
 /* Remove 'mask' from the mask list, if it is not needed any more. */
@@ -512,10 +604,15 @@ static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
 void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
 {
 	struct table_instance *ti = ovsl_dereference(table->ti);
+	struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti);
 
 	BUG_ON(table->count == 0);
-	hlist_del_rcu(&flow->hash_node[ti->node_ver]);
+	hlist_del_rcu(&flow->flow_table.node[ti->node_ver]);
 	table->count--;
+	if (ovs_identifier_is_ufid(&flow->id)) {
+		hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]);
+		table->ufid_count--;
+	}
 
 	/* RCU delete the mask. 'flow->mask' is not NULLed, as it should be
 	 * accessible as long as the RCU read lock is held.
@@ -589,24 +686,46 @@ static void flow_key_insert(struct flow_table *table, struct sw_flow *flow)
 	struct table_instance *new_ti = NULL;
 	struct table_instance *ti;
 
-	flow->hash = flow_hash(&flow->key, &flow->mask->range);
+	flow->flow_table.hash = flow_hash(&flow->key, &flow->mask->range);
 	ti = ovsl_dereference(table->ti);
 	table_instance_insert(ti, flow);
 	table->count++;
 
 	/* Expand table, if necessary, to make room. */
 	if (table->count > ti->n_buckets)
-		new_ti = table_instance_expand(ti);
+		new_ti = table_instance_expand(ti, false);
 	else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL))
-		new_ti = table_instance_rehash(ti, ti->n_buckets);
+		new_ti = table_instance_rehash(ti, ti->n_buckets, false);
 
 	if (new_ti) {
 		rcu_assign_pointer(table->ti, new_ti);
-		table_instance_destroy(ti, true);
+		call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
 		table->last_rehash = jiffies;
 	}
 }
 
+/* Must be called with OVS mutex held. */
+static void flow_ufid_insert(struct flow_table *table, struct sw_flow *flow)
+{
+	struct table_instance *ti;
+
+	flow->ufid_table.hash = ufid_hash(&flow->id);
+	ti = ovsl_dereference(table->ufid_ti);
+	ufid_table_instance_insert(ti, flow);
+	table->ufid_count++;
+
+	/* Expand table, if necessary, to make room. */
+	if (table->ufid_count > ti->n_buckets) {
+		struct table_instance *new_ti;
+
+		new_ti = table_instance_expand(ti, true);
+		if (new_ti) {
+			rcu_assign_pointer(table->ufid_ti, new_ti);
+			call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb);
+		}
+	}
+}
+
 /* Must be called with OVS mutex held. */
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
 			const struct sw_flow_mask *mask)
@@ -617,6 +736,8 @@ int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
 	if (err)
 		return err;
 	flow_key_insert(table, flow);
+	if (ovs_identifier_is_ufid(&flow->id))
+		flow_ufid_insert(table, flow);
 
 	return 0;
 }
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 309fa641568..616eda10d95 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -47,9 +47,11 @@ struct table_instance {
 
 struct flow_table {
 	struct table_instance __rcu *ti;
+	struct table_instance __rcu *ufid_ti;
 	struct list_head mask_list;
 	unsigned long last_rehash;
 	unsigned int count;
+	unsigned int ufid_count;
 };
 
 extern struct kmem_cache *flow_stats_cache;
@@ -78,8 +80,10 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
 				    const struct sw_flow_key *);
 struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
 					  const struct sw_flow_match *match);
-bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
-			       const struct sw_flow_match *match);
+struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *,
+					 const struct sw_flow_id *);
+
+bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *);
 
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 		       const struct sw_flow_mask *mask);
-- 
cgit v1.2.3-70-g09d2


From df4d92549f23e1c037e83323aff58a21b3de7fe0 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Fri, 23 Jan 2015 12:01:26 +0100
Subject: ipv4: try to cache dst_entries which would cause a redirect

Not caching dst_entries which cause redirects could be exploited by hosts
on the same subnet, causing a severe DoS attack. This effect aggravated
since commit f88649721268999 ("ipv4: fix dst race in sk_dst_get()").

Lookups causing redirects will be allocated with DST_NOCACHE set which
will force dst_release to free them via RCU.  Unfortunately waiting for
RCU grace period just takes too long, we can end up with >1M dst_entries
waiting to be released and the system will run OOM. rcuos threads cannot
catch up under high softirq load.

Attaching the flag to emit a redirect later on to the specific skb allows
us to cache those dst_entries thus reducing the pressure on allocation
and deallocation.

This issue was discovered by Marcelo Leitner.

Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Marcelo Leitner <mleitner@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h      | 11 ++++++-----
 net/ipv4/ip_forward.c |  3 ++-
 net/ipv4/route.c      |  9 +++++----
 3 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index 0bb62070292..f7cbd703d15 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -39,11 +39,12 @@ struct inet_skb_parm {
 	struct ip_options	opt;		/* Compiled IP options		*/
 	unsigned char		flags;
 
-#define IPSKB_FORWARDED		1
-#define IPSKB_XFRM_TUNNEL_SIZE	2
-#define IPSKB_XFRM_TRANSFORMED	4
-#define IPSKB_FRAG_COMPLETE	8
-#define IPSKB_REROUTED		16
+#define IPSKB_FORWARDED		BIT(0)
+#define IPSKB_XFRM_TUNNEL_SIZE	BIT(1)
+#define IPSKB_XFRM_TRANSFORMED	BIT(2)
+#define IPSKB_FRAG_COMPLETE	BIT(3)
+#define IPSKB_REROUTED		BIT(4)
+#define IPSKB_DOREDIRECT	BIT(5)
 
 	u16			frag_max_size;
 };
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3a83ce5efa8..787b3c294ce 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -129,7 +129,8 @@ int ip_forward(struct sk_buff *skb)
 	 *	We now generate an ICMP HOST REDIRECT giving the route
 	 *	we calculated.
 	 */
-	if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT && !opt->srr &&
+	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
 	skb->priority = rt_tos2priority(iph->tos);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a2155b0260..d58dd0ec3e5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1554,11 +1554,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	do_cache = res->fi && !itag;
 	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
+	    skb->protocol == htons(ETH_P_IP) &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
-		flags |= RTCF_DOREDIRECT;
-		do_cache = false;
-	}
+	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+		IPCB(skb)->flags |= IPSKB_DOREDIRECT;
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -2303,6 +2302,8 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	r->rtm_flags	= (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
 	if (rt->rt_flags & RTCF_NOTIFY)
 		r->rtm_flags |= RTM_F_NOTIFY;
+	if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
+		r->rtm_flags |= RTCF_DOREDIRECT;
 
 	if (nla_put_be32(skb, RTA_DST, dst))
 		goto nla_put_failure;
-- 
cgit v1.2.3-70-g09d2


From aae88261abd58fffef7ee0e00160ce4ea105b0f3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 26 Jan 2015 22:05:38 -0800
Subject: net: phy: document has_fixups field

has_fixups was introduced to help keeping track of fixups/quirks running
on a PHY device, but we did not update the comment above struct
phy_device accordingly.

Fixes: b0ae009f3dc14 (net: phy: add "has_fixups" boolean property")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 9c189a1fa3a..1b3690b597d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -327,6 +327,7 @@ struct phy_c45_device_ids {
  * c45_ids: 802.3-c45 Device Identifers if is_c45.
  * is_c45:  Set to true if this phy uses clause 45 addressing.
  * is_internal: Set to true if this phy is internal to a MAC.
+ * has_fixups: Set to true if this phy has fixups/quirks.
  * state: state of the PHY for management purposes
  * dev_flags: Device-specific flags used by the PHY driver.
  * addr: Bus address of PHY
-- 
cgit v1.2.3-70-g09d2


From 8a477a6fb6a33651adda772360b85fd813569743 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 26 Jan 2015 22:05:39 -0800
Subject: net: phy: keep track of the PHY suspend state

In order to avoid double calls to phydev->drv->suspend and resume, keep
track of whether the PHY has already been suspended as a consequence of
a successful call to phy_suspend(). We will use this in our MDIO bus
suspend/resume hooks to avoid a double suspend call.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 22 ++++++++++++++++++----
 include/linux/phy.h          |  2 ++
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 3fc91e89f5a..bdfe51fc3a6 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -699,6 +699,7 @@ int phy_suspend(struct phy_device *phydev)
 {
 	struct phy_driver *phydrv = to_phy_driver(phydev->dev.driver);
 	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+	int ret = 0;
 
 	/* If the device has WOL enabled, we cannot suspend the PHY */
 	phy_ethtool_get_wol(phydev, &wol);
@@ -706,18 +707,31 @@ int phy_suspend(struct phy_device *phydev)
 		return -EBUSY;
 
 	if (phydrv->suspend)
-		return phydrv->suspend(phydev);
-	return 0;
+		ret = phydrv->suspend(phydev);
+
+	if (ret)
+		return ret;
+
+	phydev->suspended = true;
+
+	return ret;
 }
 EXPORT_SYMBOL(phy_suspend);
 
 int phy_resume(struct phy_device *phydev)
 {
 	struct phy_driver *phydrv = to_phy_driver(phydev->dev.driver);
+	int ret = 0;
 
 	if (phydrv->resume)
-		return phydrv->resume(phydev);
-	return 0;
+		ret = phydrv->resume(phydev);
+
+	if (ret)
+		return ret;
+
+	phydev->suspended = false;
+
+	return ret;
 }
 EXPORT_SYMBOL(phy_resume);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 1b3690b597d..685809835b5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -328,6 +328,7 @@ struct phy_c45_device_ids {
  * is_c45:  Set to true if this phy uses clause 45 addressing.
  * is_internal: Set to true if this phy is internal to a MAC.
  * has_fixups: Set to true if this phy has fixups/quirks.
+ * suspended: Set to true if this phy has been suspended successfully.
  * state: state of the PHY for management purposes
  * dev_flags: Device-specific flags used by the PHY driver.
  * addr: Bus address of PHY
@@ -365,6 +366,7 @@ struct phy_device {
 	bool is_c45;
 	bool is_internal;
 	bool has_fixups;
+	bool suspended;
 
 	enum phy_state state;
 
-- 
cgit v1.2.3-70-g09d2


From e9fb8b7e4f6af17e3aa4835281e06fdc920341f9 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 6 Jan 2015 16:48:36 +0000
Subject: compat: Declare compat_sys_sigpending and compat_sys_sigprocmask
 prototypes

__ARCH_WANT_SYS_SIGPENDING or __ARCH_WANT_SYS_SIGPROGMASK may be defined
for compat support but the corresponding prototypes are missing from
linux/compat.h.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
---
 include/linux/compat.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/linux/compat.h b/include/linux/compat.h
index 7450ca2ac1f..ab25814690b 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -689,6 +689,15 @@ asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd,
 asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr,
 				       compat_stack_t __user *uoss_ptr);
 
+#ifdef __ARCH_WANT_SYS_SIGPENDING
+asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set);
+#endif
+
+#ifdef __ARCH_WANT_SYS_SIGPROCMASK
+asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *nset,
+				       compat_old_sigset_t __user *oset);
+#endif
+
 int compat_restore_altstack(const compat_stack_t __user *uss);
 int __compat_save_altstack(compat_stack_t __user *, unsigned long);
 #define compat_save_altstack_ex(uss, sp) do { \
-- 
cgit v1.2.3-70-g09d2


From 54e45c169dbce43cf46d00eb1521b655b6e4f9e9 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Tue, 6 Jan 2015 16:52:38 +0000
Subject: syscalls: Declare sys_*stat64 prototypes if
 __ARCH_WANT_(COMPAT_)STAT64

Currently, the sys_stat64, sys_fstat64 and sys_lstat64 prototpyes are
only declared if BITS_PER_LONG == 32. Following commit 0753f70f07fb
(fs: Build sys_stat64() and friends if __ARCH_WANT_COMPAT_STAT64), the
implementation of these functions is allowed on 64-bit systems for
compat support. The patch changes the condition on the prototype
declaration from BITS_PER_LONG == 32 to defined(__ARCH_WANT_STAT64) ||
defined(__ARCH_WANT_COMPAT_STAT64).

In addition, it moves the sys_fstatat64 prototype under the same #if
block

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
---
 include/linux/syscalls.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 85893d74490..76d1e38aabe 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -410,12 +410,16 @@ asmlinkage long sys_newlstat(const char __user *filename,
 				struct stat __user *statbuf);
 asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf);
 asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf);
-#if BITS_PER_LONG == 32
+#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64)
 asmlinkage long sys_stat64(const char __user *filename,
 				struct stat64 __user *statbuf);
 asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf);
 asmlinkage long sys_lstat64(const char __user *filename,
 				struct stat64 __user *statbuf);
+asmlinkage long sys_fstatat64(int dfd, const char __user *filename,
+			       struct stat64 __user *statbuf, int flag);
+#endif
+#if BITS_PER_LONG == 32
 asmlinkage long sys_truncate64(const char __user *path, loff_t length);
 asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length);
 #endif
@@ -771,8 +775,6 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
 			   umode_t mode);
 asmlinkage long sys_newfstatat(int dfd, const char __user *filename,
 			       struct stat __user *statbuf, int flag);
-asmlinkage long sys_fstatat64(int dfd, const char __user *filename,
-			       struct stat64 __user *statbuf, int flag);
 asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf,
 			       int bufsiz);
 asmlinkage long sys_utimensat(int dfd, const char __user *filename,
-- 
cgit v1.2.3-70-g09d2


From cfcf1682c4ca8f601a4702255958e0b1c9aa12cc Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni@qca.qualcomm.com>
Date: Sat, 24 Jan 2015 19:52:05 +0200
Subject: cfg80211: Add new GCMP, CCMP-256, BIP-GMAC, BIP-CMAC-256 ciphers

This makes cfg80211 aware of the GCMP, GCMP-256, CCMP-256, BIP-GMAC-128,
BIP-GMAC-256, and BIP-CMAC-256 cipher suites. These new cipher suites
were defined in IEEE Std 802.11ac-2013.

Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 18 ++++++++++++++++++
 net/wireless/util.c       | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 4f4eea8a628..dbf417bf25b 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1994,9 +1994,15 @@ enum ieee80211_key_len {
 	WLAN_KEY_LEN_WEP40 = 5,
 	WLAN_KEY_LEN_WEP104 = 13,
 	WLAN_KEY_LEN_CCMP = 16,
+	WLAN_KEY_LEN_CCMP_256 = 32,
 	WLAN_KEY_LEN_TKIP = 32,
 	WLAN_KEY_LEN_AES_CMAC = 16,
 	WLAN_KEY_LEN_SMS4 = 32,
+	WLAN_KEY_LEN_GCMP = 16,
+	WLAN_KEY_LEN_GCMP_256 = 32,
+	WLAN_KEY_LEN_BIP_CMAC_256 = 32,
+	WLAN_KEY_LEN_BIP_GMAC_128 = 16,
+	WLAN_KEY_LEN_BIP_GMAC_256 = 32,
 };
 
 #define IEEE80211_WEP_IV_LEN		4
@@ -2004,9 +2010,16 @@ enum ieee80211_key_len {
 #define IEEE80211_CCMP_HDR_LEN		8
 #define IEEE80211_CCMP_MIC_LEN		8
 #define IEEE80211_CCMP_PN_LEN		6
+#define IEEE80211_CCMP_256_HDR_LEN	8
+#define IEEE80211_CCMP_256_MIC_LEN	16
+#define IEEE80211_CCMP_256_PN_LEN	6
 #define IEEE80211_TKIP_IV_LEN		8
 #define IEEE80211_TKIP_ICV_LEN		4
 #define IEEE80211_CMAC_PN_LEN		6
+#define IEEE80211_GMAC_PN_LEN		6
+#define IEEE80211_GCMP_HDR_LEN		8
+#define IEEE80211_GCMP_MIC_LEN		16
+#define IEEE80211_GCMP_PN_LEN		6
 
 /* Public action codes */
 enum ieee80211_pub_actioncode {
@@ -2230,6 +2243,11 @@ enum ieee80211_sa_query_action {
 #define WLAN_CIPHER_SUITE_WEP104	0x000FAC05
 #define WLAN_CIPHER_SUITE_AES_CMAC	0x000FAC06
 #define WLAN_CIPHER_SUITE_GCMP		0x000FAC08
+#define WLAN_CIPHER_SUITE_GCMP_256	0x000FAC09
+#define WLAN_CIPHER_SUITE_CCMP_256	0x000FAC0A
+#define WLAN_CIPHER_SUITE_BIP_GMAC_128	0x000FAC0B
+#define WLAN_CIPHER_SUITE_BIP_GMAC_256	0x000FAC0C
+#define WLAN_CIPHER_SUITE_BIP_CMAC_256	0x000FAC0D
 
 #define WLAN_CIPHER_SUITE_SMS4		0x00147201
 
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 08f136ad2ea..919fee807dd 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -230,6 +230,9 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 	switch (params->cipher) {
 	case WLAN_CIPHER_SUITE_TKIP:
 	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 		/* Disallow pairwise keys with non-zero index unless it's WEP
 		 * or a vendor specific cipher (because current deployments use
 		 * pairwise WEP keys with non-zero indices and for vendor
@@ -240,6 +243,9 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 		/* Disallow BIP (group-only) cipher as pairwise cipher */
 		if (pairwise)
 			return -EINVAL;
@@ -261,6 +267,18 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 		if (params->key_len != WLAN_KEY_LEN_CCMP)
 			return -EINVAL;
 		break;
+	case WLAN_CIPHER_SUITE_CCMP_256:
+		if (params->key_len != WLAN_KEY_LEN_CCMP_256)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+		if (params->key_len != WLAN_KEY_LEN_GCMP)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (params->key_len != WLAN_KEY_LEN_GCMP_256)
+			return -EINVAL;
+		break;
 	case WLAN_CIPHER_SUITE_WEP104:
 		if (params->key_len != WLAN_KEY_LEN_WEP104)
 			return -EINVAL;
@@ -269,6 +287,18 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 		if (params->key_len != WLAN_KEY_LEN_AES_CMAC)
 			return -EINVAL;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		if (params->key_len != WLAN_KEY_LEN_BIP_CMAC_256)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_128)
+			return -EINVAL;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_256)
+			return -EINVAL;
+		break;
 	default:
 		/*
 		 * We don't know anything about this algorithm,
@@ -288,7 +318,13 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 		case WLAN_CIPHER_SUITE_TKIP:
 		case WLAN_CIPHER_SUITE_CCMP:
+		case WLAN_CIPHER_SUITE_CCMP_256:
+		case WLAN_CIPHER_SUITE_GCMP:
+		case WLAN_CIPHER_SUITE_GCMP_256:
 		case WLAN_CIPHER_SUITE_AES_CMAC:
+		case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 			if (params->seq_len != 6)
 				return -EINVAL;
 			break;
-- 
cgit v1.2.3-70-g09d2


From 00b9cfa3ff38401bd70c34b250ca13e5ea347b4a Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni@qca.qualcomm.com>
Date: Sat, 24 Jan 2015 19:52:06 +0200
Subject: mac80111: Add GCMP and GCMP-256 ciphers

This allows mac80211 to configure GCMP and GCMP-256 to the driver and
also use software-implementation within mac80211 when the driver does
not support this with hardware accelaration.

Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
[remove a spurious newline]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  15 ++-
 net/mac80211/Kconfig       |   1 +
 net/mac80211/Makefile      |   1 +
 net/mac80211/aes_gcm.c     |  95 +++++++++++++++++++
 net/mac80211/aes_gcm.h     |  22 +++++
 net/mac80211/cfg.c         |  13 +++
 net/mac80211/debugfs_key.c |  22 +++++
 net/mac80211/key.c         |  74 ++++++++++++++-
 net/mac80211/key.h         |  11 +++
 net/mac80211/main.c        |   9 +-
 net/mac80211/rx.c          |   4 +
 net/mac80211/tx.c          |   5 +
 net/mac80211/wpa.c         | 224 +++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/wpa.h         |   5 +
 14 files changed, 492 insertions(+), 9 deletions(-)
 create mode 100644 net/mac80211/aes_gcm.c
 create mode 100644 net/mac80211/aes_gcm.h

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 866073e27ea..ae663843611 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1294,8 +1294,8 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  * @IEEE80211_KEY_FLAG_PAIRWISE: Set by mac80211, this flag indicates
  *	that the key is pairwise rather then a shared key.
  * @IEEE80211_KEY_FLAG_SW_MGMT_TX: This flag should be set by the driver for a
- *	CCMP key if it requires CCMP encryption of management frames (MFP) to
- *	be done in software.
+ *	CCMP/GCMP key if it requires CCMP/GCMP encryption of management frames
+ *	(MFP) to be done in software.
  * @IEEE80211_KEY_FLAG_PUT_IV_SPACE: This flag should be set by the driver
  *	if space should be prepared for the IV, but the IV
  *	itself should not be generated. Do not set together with
@@ -1310,7 +1310,7 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  *	RX, if your crypto engine can't deal with TX you can also set the
  *	%IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW.
  * @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the
- *	driver for a CCMP key to indicate that is requires IV generation
+ *	driver for a CCMP/GCMP key to indicate that is requires IV generation
  *	only for managment frames (MFP).
  * @IEEE80211_KEY_FLAG_RESERVE_TAILROOM: This flag should be set by the
  *	driver for a key to indicate that sufficient tailroom must always
@@ -4098,6 +4098,8 @@ void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf,
  *	reverse order than in packet)
  * @aes_cmac: PN data, most significant byte first (big endian,
  *	reverse order than in packet)
+ * @gcmp: PN data, most significant byte first (big endian,
+ *	reverse order than in packet)
  */
 struct ieee80211_key_seq {
 	union {
@@ -4111,6 +4113,9 @@ struct ieee80211_key_seq {
 		struct {
 			u8 pn[6];
 		} aes_cmac;
+		struct {
+			u8 pn[6];
+		} gcmp;
 	};
 };
 
@@ -4135,7 +4140,7 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
  * ieee80211_get_key_rx_seq - get key RX sequence counter
  *
  * @keyconf: the parameter passed with the set key
- * @tid: The TID, or -1 for the management frame value (CCMP only);
+ * @tid: The TID, or -1 for the management frame value (CCMP/GCMP only);
  *	the value on TID 0 is also used for non-QoS frames. For
  *	CMAC, only TID 0 is valid.
  * @seq: buffer to receive the sequence data
@@ -4171,7 +4176,7 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
  * ieee80211_set_key_rx_seq - set key RX sequence counter
  *
  * @keyconf: the parameter passed with the set key
- * @tid: The TID, or -1 for the management frame value (CCMP only);
+ * @tid: The TID, or -1 for the management frame value (CCMP/GCMP only);
  *	the value on TID 0 is also used for non-QoS frames. For
  *	CMAC, only TID 0 is valid.
  * @seq: new sequence data
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 75cc6801a43..64a012a0c6e 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -5,6 +5,7 @@ config MAC80211
 	select CRYPTO_ARC4
 	select CRYPTO_AES
 	select CRYPTO_CCM
+	select CRYPTO_GCM
 	select CRC32
 	select AVERAGE
 	---help---
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index e53671b1105..0cbf9361843 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -15,6 +15,7 @@ mac80211-y := \
 	michael.o \
 	tkip.o \
 	aes_ccm.o \
+	aes_gcm.o \
 	aes_cmac.o \
 	cfg.o \
 	ethtool.o \
diff --git a/net/mac80211/aes_gcm.c b/net/mac80211/aes_gcm.c
new file mode 100644
index 00000000000..c2bf6698d73
--- /dev/null
+++ b/net/mac80211/aes_gcm.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2014-2015, Qualcomm Atheros, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/aes.h>
+
+#include <net/mac80211.h>
+#include "key.h"
+#include "aes_gcm.h"
+
+void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			       u8 *data, size_t data_len, u8 *mic)
+{
+	struct scatterlist assoc, pt, ct[2];
+
+	char aead_req_data[sizeof(struct aead_request) +
+			   crypto_aead_reqsize(tfm)]
+		__aligned(__alignof__(struct aead_request));
+	struct aead_request *aead_req = (void *)aead_req_data;
+
+	memset(aead_req, 0, sizeof(aead_req_data));
+
+	sg_init_one(&pt, data, data_len);
+	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_init_table(ct, 2);
+	sg_set_buf(&ct[0], data, data_len);
+	sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN);
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_assoc(aead_req, &assoc, assoc.length);
+	aead_request_set_crypt(aead_req, &pt, ct, data_len, j_0);
+
+	crypto_aead_encrypt(aead_req);
+}
+
+int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic)
+{
+	struct scatterlist assoc, pt, ct[2];
+	char aead_req_data[sizeof(struct aead_request) +
+			   crypto_aead_reqsize(tfm)]
+		__aligned(__alignof__(struct aead_request));
+	struct aead_request *aead_req = (void *)aead_req_data;
+
+	if (data_len == 0)
+		return -EINVAL;
+
+	memset(aead_req, 0, sizeof(aead_req_data));
+
+	sg_init_one(&pt, data, data_len);
+	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
+	sg_init_table(ct, 2);
+	sg_set_buf(&ct[0], data, data_len);
+	sg_set_buf(&ct[1], mic, IEEE80211_GCMP_MIC_LEN);
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_assoc(aead_req, &assoc, assoc.length);
+	aead_request_set_crypt(aead_req, ct, &pt,
+			       data_len + IEEE80211_GCMP_MIC_LEN, j_0);
+
+	return crypto_aead_decrypt(aead_req);
+}
+
+struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
+							size_t key_len)
+{
+	struct crypto_aead *tfm;
+	int err;
+
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return tfm;
+
+	err = crypto_aead_setkey(tfm, key, key_len);
+	if (!err)
+		err = crypto_aead_setauthsize(tfm, IEEE80211_GCMP_MIC_LEN);
+	if (!err)
+		return tfm;
+
+	crypto_free_aead(tfm);
+	return ERR_PTR(err);
+}
+
+void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm)
+{
+	crypto_free_aead(tfm);
+}
diff --git a/net/mac80211/aes_gcm.h b/net/mac80211/aes_gcm.h
new file mode 100644
index 00000000000..1347fda6b76
--- /dev/null
+++ b/net/mac80211/aes_gcm.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright 2014-2015, Qualcomm Atheros, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef AES_GCM_H
+#define AES_GCM_H
+
+#include <linux/crypto.h>
+
+void ieee80211_aes_gcm_encrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			       u8 *data, size_t data_len, u8 *mic);
+int ieee80211_aes_gcm_decrypt(struct crypto_aead *tfm, u8 *j_0, u8 *aad,
+			      u8 *data, size_t data_len, u8 *mic);
+struct crypto_aead *ieee80211_aes_gcm_key_setup_encrypt(const u8 key[],
+							size_t key_len);
+void ieee80211_aes_gcm_key_free(struct crypto_aead *tfm);
+
+#endif /* AES_GCM_H */
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index a777114d663..1c1d061cff5 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -164,6 +164,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 		break;
 	default:
 		cs = ieee80211_cs_get(local, params->cipher, sdata->vif.type);
@@ -369,6 +370,18 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
 		params.seq = seq;
 		params.seq_len = 6;
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn64 = atomic64_read(&key->u.gcmp.tx_pn);
+		seq[0] = pn64;
+		seq[1] = pn64 >> 8;
+		seq[2] = pn64 >> 16;
+		seq[3] = pn64 >> 24;
+		seq[4] = pn64 >> 32;
+		seq[5] = pn64 >> 40;
+		params.seq = seq;
+		params.seq_len = 6;
+		break;
 	}
 
 	params.key = key->conf.key;
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 5523b94c7c9..0e223e60229 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -105,6 +105,13 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
 				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
 				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn = atomic64_read(&key->u.gcmp.tx_pn);
+		len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
+				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
+				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
+		break;
 	default:
 		return 0;
 	}
@@ -151,6 +158,17 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 			       rpn[3], rpn[4], rpn[5]);
 		len = p - buf;
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) {
+			rpn = key->u.gcmp.rx_pn[i];
+			p += scnprintf(p, sizeof(buf)+buf-p,
+				       "%02x%02x%02x%02x%02x%02x\n",
+				       rpn[0], rpn[1], rpn[2],
+				       rpn[3], rpn[4], rpn[5]);
+		}
+		len = p - buf;
+		break;
 	default:
 		return 0;
 	}
@@ -173,6 +191,10 @@ static ssize_t key_replays_read(struct file *file, char __user *userbuf,
 		len = scnprintf(buf, sizeof(buf), "%u\n",
 				key->u.aes_cmac.replays);
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		len = scnprintf(buf, sizeof(buf), "%u\n", key->u.gcmp.replays);
+		break;
 	default:
 		return 0;
 	}
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 5167c53aa15..cbee2f5180c 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -24,6 +24,7 @@
 #include "debugfs_key.h"
 #include "aes_ccm.h"
 #include "aes_cmac.h"
+#include "aes_gcm.h"
 
 
 /**
@@ -163,6 +164,8 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_TKIP:
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
 		/* all of these we can do in software - if driver can */
 		if (ret == 1)
 			return 0;
@@ -412,6 +415,25 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 			return ERR_PTR(err);
 		}
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		key->conf.iv_len = IEEE80211_GCMP_HDR_LEN;
+		key->conf.icv_len = IEEE80211_GCMP_MIC_LEN;
+		for (i = 0; seq && i < IEEE80211_NUM_TIDS + 1; i++)
+			for (j = 0; j < IEEE80211_GCMP_PN_LEN; j++)
+				key->u.gcmp.rx_pn[i][j] =
+					seq[IEEE80211_GCMP_PN_LEN - j - 1];
+		/* Initialize AES key state here as an optimization so that
+		 * it does not need to be initialized for every packet.
+		 */
+		key->u.gcmp.tfm = ieee80211_aes_gcm_key_setup_encrypt(key_data,
+								      key_len);
+		if (IS_ERR(key->u.gcmp.tfm)) {
+			err = PTR_ERR(key->u.gcmp.tfm);
+			kfree(key);
+			return ERR_PTR(err);
+		}
+		break;
 	default:
 		if (cs) {
 			size_t len = (seq_len > MAX_PN_LEN) ?
@@ -433,10 +455,18 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 
 static void ieee80211_key_free_common(struct ieee80211_key *key)
 {
-	if (key->conf.cipher == WLAN_CIPHER_SUITE_CCMP)
+	switch (key->conf.cipher) {
+	case WLAN_CIPHER_SUITE_CCMP:
 		ieee80211_aes_key_free(key->u.ccmp.tfm);
-	if (key->conf.cipher == WLAN_CIPHER_SUITE_AES_CMAC)
+		break;
+	case WLAN_CIPHER_SUITE_AES_CMAC:
 		ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm);
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		ieee80211_aes_gcm_key_free(key->u.gcmp.tfm);
+		break;
+	}
 	kzfree(key);
 }
 
@@ -760,6 +790,16 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		seq->ccmp.pn[1] = pn64 >> 32;
 		seq->ccmp.pn[0] = pn64 >> 40;
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn64 = atomic64_read(&key->u.gcmp.tx_pn);
+		seq->gcmp.pn[5] = pn64;
+		seq->gcmp.pn[4] = pn64 >> 8;
+		seq->gcmp.pn[3] = pn64 >> 16;
+		seq->gcmp.pn[2] = pn64 >> 24;
+		seq->gcmp.pn[1] = pn64 >> 32;
+		seq->gcmp.pn[0] = pn64 >> 40;
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -796,6 +836,16 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		pn = key->u.aes_cmac.rx_pn;
 		memcpy(seq->aes_cmac.pn, pn, IEEE80211_CMAC_PN_LEN);
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
+			return;
+		if (tid < 0)
+			pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS];
+		else
+			pn = key->u.gcmp.rx_pn[tid];
+		memcpy(seq->gcmp.pn, pn, IEEE80211_GCMP_PN_LEN);
+		break;
 	}
 }
 EXPORT_SYMBOL(ieee80211_get_key_rx_seq);
@@ -831,6 +881,16 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		       ((u64)seq->aes_cmac.pn[0] << 40);
 		atomic64_set(&key->u.aes_cmac.tx_pn, pn64);
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		pn64 = (u64)seq->gcmp.pn[5] |
+		       ((u64)seq->gcmp.pn[4] << 8) |
+		       ((u64)seq->gcmp.pn[3] << 16) |
+		       ((u64)seq->gcmp.pn[2] << 24) |
+		       ((u64)seq->gcmp.pn[1] << 32) |
+		       ((u64)seq->gcmp.pn[0] << 40);
+		atomic64_set(&key->u.gcmp.tx_pn, pn64);
+		break;
 	default:
 		WARN_ON(1);
 		break;
@@ -868,6 +928,16 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		pn = key->u.aes_cmac.rx_pn;
 		memcpy(pn, seq->aes_cmac.pn, IEEE80211_CMAC_PN_LEN);
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
+			return;
+		if (tid < 0)
+			pn = key->u.gcmp.rx_pn[IEEE80211_NUM_TIDS];
+		else
+			pn = key->u.gcmp.rx_pn[tid];
+		memcpy(pn, seq->gcmp.pn, IEEE80211_GCMP_PN_LEN);
+		break;
 	default:
 		WARN_ON(1);
 		break;
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 19db68663d7..27580da851c 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -94,6 +94,17 @@ struct ieee80211_key {
 			u32 replays; /* dot11RSNAStatsCMACReplays */
 			u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
 		} aes_cmac;
+		struct {
+			atomic64_t tx_pn;
+			/* Last received packet number. The first
+			 * IEEE80211_NUM_TIDS counters are used with Data
+			 * frames and the last counter is used with Robust
+			 * Management frames.
+			 */
+			u8 rx_pn[IEEE80211_NUM_TIDS + 1][IEEE80211_GCMP_PN_LEN];
+			struct crypto_aead *tfm;
+			u32 replays; /* dot11RSNAStatsGCMPReplays */
+		} gcmp;
 		struct {
 			/* generic cipher scheme */
 			u8 rx_pn[IEEE80211_NUM_TIDS + 1][MAX_PN_LEN];
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index ea6b82ac4f0..7223b4e1675 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -666,6 +666,8 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		WLAN_CIPHER_SUITE_WEP104,
 		WLAN_CIPHER_SUITE_TKIP,
 		WLAN_CIPHER_SUITE_CCMP,
+		WLAN_CIPHER_SUITE_GCMP,
+		WLAN_CIPHER_SUITE_GCMP_256,
 
 		/* keep last -- depends on hw flags! */
 		WLAN_CIPHER_SUITE_AES_CMAC
@@ -724,9 +726,10 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		/* Driver specifies cipher schemes only (but not cipher suites
 		 * including the schemes)
 		 *
-		 * We start counting ciphers defined by schemes, TKIP and CCMP
+		 * We start counting ciphers defined by schemes, TKIP, CCMP,
+		 * GCMP, and GCMP-256
 		 */
-		n_suites = local->hw.n_cipher_schemes + 2;
+		n_suites = local->hw.n_cipher_schemes + 4;
 
 		/* check if we have WEP40 and WEP104 */
 		if (have_wep)
@@ -742,6 +745,8 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 
 		suites[w++] = WLAN_CIPHER_SUITE_CCMP;
 		suites[w++] = WLAN_CIPHER_SUITE_TKIP;
+		suites[w++] = WLAN_CIPHER_SUITE_GCMP;
+		suites[w++] = WLAN_CIPHER_SUITE_GCMP_256;
 
 		if (have_wep) {
 			suites[w++] = WLAN_CIPHER_SUITE_WEP40;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index ed516ae80a3..a11d2518c36 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1655,6 +1655,10 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 		result = ieee80211_crypto_aes_cmac_decrypt(rx);
 		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		result = ieee80211_crypto_gcmp_decrypt(rx);
+		break;
 	default:
 		result = ieee80211_crypto_hw_decrypt(rx);
 	}
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 02ed6f60629..e4c6fbc4bf7 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -626,6 +626,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 				tx->key = NULL;
 			break;
 		case WLAN_CIPHER_SUITE_CCMP:
+		case WLAN_CIPHER_SUITE_GCMP:
+		case WLAN_CIPHER_SUITE_GCMP_256:
 			if (!ieee80211_is_data_present(hdr->frame_control) &&
 			    !ieee80211_use_mfp(hdr->frame_control, tx->sta,
 					       tx->skb))
@@ -1014,6 +1016,9 @@ ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx)
 		return ieee80211_crypto_ccmp_encrypt(tx);
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 		return ieee80211_crypto_aes_cmac_encrypt(tx);
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		return ieee80211_crypto_gcmp_encrypt(tx);
 	default:
 		return ieee80211_crypto_hw_encrypt(tx);
 	}
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 12398fde02e..96b65c24010 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -22,6 +22,7 @@
 #include "tkip.h"
 #include "aes_ccm.h"
 #include "aes_cmac.h"
+#include "aes_gcm.h"
 #include "wpa.h"
 
 ieee80211_tx_result
@@ -546,6 +547,229 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
 	return RX_CONTINUE;
 }
 
+static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad)
+{
+	__le16 mask_fc;
+	u8 qos_tid;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	memcpy(j_0, hdr->addr2, ETH_ALEN);
+	memcpy(&j_0[ETH_ALEN], pn, IEEE80211_GCMP_PN_LEN);
+	j_0[13] = 0;
+	j_0[14] = 0;
+	j_0[AES_BLOCK_SIZE - 1] = 0x01;
+
+	/* AAD (extra authenticate-only data) / masked 802.11 header
+	 * FC | A1 | A2 | A3 | SC | [A4] | [QC]
+	 */
+	put_unaligned_be16(ieee80211_hdrlen(hdr->frame_control) - 2, &aad[0]);
+	/* Mask FC: zero subtype b4 b5 b6 (if not mgmt)
+	 * Retry, PwrMgt, MoreData; set Protected
+	 */
+	mask_fc = hdr->frame_control;
+	mask_fc &= ~cpu_to_le16(IEEE80211_FCTL_RETRY |
+				IEEE80211_FCTL_PM | IEEE80211_FCTL_MOREDATA);
+	if (!ieee80211_is_mgmt(hdr->frame_control))
+		mask_fc &= ~cpu_to_le16(0x0070);
+	mask_fc |= cpu_to_le16(IEEE80211_FCTL_PROTECTED);
+
+	put_unaligned(mask_fc, (__le16 *)&aad[2]);
+	memcpy(&aad[4], &hdr->addr1, 3 * ETH_ALEN);
+
+	/* Mask Seq#, leave Frag# */
+	aad[22] = *((u8 *)&hdr->seq_ctrl) & 0x0f;
+	aad[23] = 0;
+
+	if (ieee80211_is_data_qos(hdr->frame_control))
+		qos_tid = *ieee80211_get_qos_ctl(hdr) &
+			IEEE80211_QOS_CTL_TID_MASK;
+	else
+		qos_tid = 0;
+
+	if (ieee80211_has_a4(hdr->frame_control)) {
+		memcpy(&aad[24], hdr->addr4, ETH_ALEN);
+		aad[30] = qos_tid;
+		aad[31] = 0;
+	} else {
+		memset(&aad[24], 0, ETH_ALEN + IEEE80211_QOS_CTL_LEN);
+		aad[24] = qos_tid;
+	}
+}
+
+static inline void gcmp_pn2hdr(u8 *hdr, const u8 *pn, int key_id)
+{
+	hdr[0] = pn[5];
+	hdr[1] = pn[4];
+	hdr[2] = 0;
+	hdr[3] = 0x20 | (key_id << 6);
+	hdr[4] = pn[3];
+	hdr[5] = pn[2];
+	hdr[6] = pn[1];
+	hdr[7] = pn[0];
+}
+
+static inline void gcmp_hdr2pn(u8 *pn, const u8 *hdr)
+{
+	pn[0] = hdr[7];
+	pn[1] = hdr[6];
+	pn[2] = hdr[5];
+	pn[3] = hdr[4];
+	pn[4] = hdr[1];
+	pn[5] = hdr[0];
+}
+
+static int gcmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ieee80211_key *key = tx->key;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	int hdrlen, len, tail;
+	u8 *pos;
+	u8 pn[6];
+	u64 pn64;
+	u8 aad[2 * AES_BLOCK_SIZE];
+	u8 j_0[AES_BLOCK_SIZE];
+
+	if (info->control.hw_key &&
+	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV) &&
+	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
+	    !((info->control.hw_key->flags &
+	       IEEE80211_KEY_FLAG_GENERATE_IV_MGMT) &&
+	      ieee80211_is_mgmt(hdr->frame_control))) {
+		/* hwaccel has no need for preallocated room for GCMP
+		 * header or MIC fields
+		 */
+		return 0;
+	}
+
+	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	len = skb->len - hdrlen;
+
+	if (info->control.hw_key)
+		tail = 0;
+	else
+		tail = IEEE80211_GCMP_MIC_LEN;
+
+	if (WARN_ON(skb_tailroom(skb) < tail ||
+		    skb_headroom(skb) < IEEE80211_GCMP_HDR_LEN))
+		return -1;
+
+	pos = skb_push(skb, IEEE80211_GCMP_HDR_LEN);
+	memmove(pos, pos + IEEE80211_GCMP_HDR_LEN, hdrlen);
+	skb_set_network_header(skb, skb_network_offset(skb) +
+				    IEEE80211_GCMP_HDR_LEN);
+
+	/* the HW only needs room for the IV, but not the actual IV */
+	if (info->control.hw_key &&
+	    (info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE))
+		return 0;
+
+	hdr = (struct ieee80211_hdr *)pos;
+	pos += hdrlen;
+
+	pn64 = atomic64_inc_return(&key->u.gcmp.tx_pn);
+
+	pn[5] = pn64;
+	pn[4] = pn64 >> 8;
+	pn[3] = pn64 >> 16;
+	pn[2] = pn64 >> 24;
+	pn[1] = pn64 >> 32;
+	pn[0] = pn64 >> 40;
+
+	gcmp_pn2hdr(pos, pn, key->conf.keyidx);
+
+	/* hwaccel - with software GCMP header */
+	if (info->control.hw_key)
+		return 0;
+
+	pos += IEEE80211_GCMP_HDR_LEN;
+	gcmp_special_blocks(skb, pn, j_0, aad);
+	ieee80211_aes_gcm_encrypt(key->u.gcmp.tfm, j_0, aad, pos, len,
+				  skb_put(skb, IEEE80211_GCMP_MIC_LEN));
+
+	return 0;
+}
+
+ieee80211_tx_result
+ieee80211_crypto_gcmp_encrypt(struct ieee80211_tx_data *tx)
+{
+	struct sk_buff *skb;
+
+	ieee80211_tx_set_protected(tx);
+
+	skb_queue_walk(&tx->skbs, skb) {
+		if (gcmp_encrypt_skb(tx, skb) < 0)
+			return TX_DROP;
+	}
+
+	return TX_CONTINUE;
+}
+
+ieee80211_rx_result
+ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data;
+	int hdrlen;
+	struct ieee80211_key *key = rx->key;
+	struct sk_buff *skb = rx->skb;
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	u8 pn[IEEE80211_GCMP_PN_LEN];
+	int data_len;
+	int queue;
+
+	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+
+	if (!ieee80211_is_data(hdr->frame_control) &&
+	    !ieee80211_is_robust_mgmt_frame(skb))
+		return RX_CONTINUE;
+
+	data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN -
+		   IEEE80211_GCMP_MIC_LEN;
+	if (!rx->sta || data_len < 0)
+		return RX_DROP_UNUSABLE;
+
+	if (status->flag & RX_FLAG_DECRYPTED) {
+		if (!pskb_may_pull(rx->skb, hdrlen + IEEE80211_GCMP_HDR_LEN))
+			return RX_DROP_UNUSABLE;
+	} else {
+		if (skb_linearize(rx->skb))
+			return RX_DROP_UNUSABLE;
+	}
+
+	gcmp_hdr2pn(pn, skb->data + hdrlen);
+
+	queue = rx->security_idx;
+
+	if (memcmp(pn, key->u.gcmp.rx_pn[queue], IEEE80211_GCMP_PN_LEN) <= 0) {
+		key->u.gcmp.replays++;
+		return RX_DROP_UNUSABLE;
+	}
+
+	if (!(status->flag & RX_FLAG_DECRYPTED)) {
+		u8 aad[2 * AES_BLOCK_SIZE];
+		u8 j_0[AES_BLOCK_SIZE];
+		/* hardware didn't decrypt/verify MIC */
+		gcmp_special_blocks(skb, pn, j_0, aad);
+
+		if (ieee80211_aes_gcm_decrypt(
+			    key->u.gcmp.tfm, j_0, aad,
+			    skb->data + hdrlen + IEEE80211_GCMP_HDR_LEN,
+			    data_len,
+			    skb->data + skb->len - IEEE80211_GCMP_MIC_LEN))
+			return RX_DROP_UNUSABLE;
+	}
+
+	memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN);
+
+	/* Remove GCMP header and MIC */
+	if (pskb_trim(skb, skb->len - IEEE80211_GCMP_MIC_LEN))
+		return RX_DROP_UNUSABLE;
+	memmove(skb->data + IEEE80211_GCMP_HDR_LEN, skb->data, hdrlen);
+	skb_pull(skb, IEEE80211_GCMP_HDR_LEN);
+
+	return RX_CONTINUE;
+}
+
 static ieee80211_tx_result
 ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx,
 			    struct sk_buff *skb)
diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h
index 62e5a12dfe0..ea955f27835 100644
--- a/net/mac80211/wpa.h
+++ b/net/mac80211/wpa.h
@@ -37,4 +37,9 @@ ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx);
 ieee80211_rx_result
 ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx);
 
+ieee80211_tx_result
+ieee80211_crypto_gcmp_encrypt(struct ieee80211_tx_data *tx);
+ieee80211_rx_result
+ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx);
+
 #endif /* WPA_H */
-- 
cgit v1.2.3-70-g09d2


From 56c52da2d554f081e8fce58ecbcf6a40c605b95b Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni@qca.qualcomm.com>
Date: Sat, 24 Jan 2015 19:52:08 +0200
Subject: mac80111: Add BIP-CMAC-256 cipher

This allows mac80211 to configure BIP-CMAC-256 to the driver and also
use software-implementation within mac80211 when the driver does not
support this with hardware accelaration.

Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  |  9 +++++
 net/mac80211/aes_cmac.c    | 34 +++++++++++++----
 net/mac80211/aes_cmac.h    |  5 ++-
 net/mac80211/cfg.c         |  2 +
 net/mac80211/debugfs_key.c |  4 ++
 net/mac80211/key.c         | 14 ++++++-
 net/mac80211/main.c        | 13 ++++---
 net/mac80211/rx.c          | 21 ++++++++---
 net/mac80211/tx.c          |  3 ++
 net/mac80211/wpa.c         | 92 ++++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/wpa.h         |  4 ++
 11 files changed, 180 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index dbf417bf25b..b9c7897dc56 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1017,6 +1017,15 @@ struct ieee80211_mmie {
 	u8 mic[8];
 } __packed;
 
+/* Management MIC information element (IEEE 802.11w) for GMAC and CMAC-256 */
+struct ieee80211_mmie_16 {
+	u8 element_id;
+	u8 length;
+	__le16 key_id;
+	u8 sequence_number[6];
+	u8 mic[16];
+} __packed;
+
 struct ieee80211_vendor_ie {
 	u8 element_id;
 	u8 len;
diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c
index 9b9009f9955..4192806be3d 100644
--- a/net/mac80211/aes_cmac.c
+++ b/net/mac80211/aes_cmac.c
@@ -18,8 +18,8 @@
 #include "key.h"
 #include "aes_cmac.h"
 
-#define AES_CMAC_KEY_LEN 16
 #define CMAC_TLEN 8 /* CMAC TLen = 64 bits (8 octets) */
+#define CMAC_TLEN_256 16 /* CMAC TLen = 128 bits (16 octets) */
 #define AAD_LEN 20
 
 
@@ -35,9 +35,9 @@ static void gf_mulx(u8 *pad)
 		pad[AES_BLOCK_SIZE - 1] ^= 0x87;
 }
 
-
-static void aes_128_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
-				const u8 *addr[], const size_t *len, u8 *mac)
+static void aes_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
+			    const u8 *addr[], const size_t *len, u8 *mac,
+			    size_t mac_len)
 {
 	u8 cbc[AES_BLOCK_SIZE], pad[AES_BLOCK_SIZE];
 	const u8 *pos, *end;
@@ -88,7 +88,7 @@ static void aes_128_cmac_vector(struct crypto_cipher *tfm, size_t num_elem,
 	for (i = 0; i < AES_BLOCK_SIZE; i++)
 		pad[i] ^= cbc[i];
 	crypto_cipher_encrypt_one(tfm, pad, pad);
-	memcpy(mac, pad, CMAC_TLEN);
+	memcpy(mac, pad, mac_len);
 }
 
 
@@ -107,17 +107,35 @@ void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad,
 	addr[2] = zero;
 	len[2] = CMAC_TLEN;
 
-	aes_128_cmac_vector(tfm, 3, addr, len, mic);
+	aes_cmac_vector(tfm, 3, addr, len, mic, CMAC_TLEN);
 }
 
+void ieee80211_aes_cmac_256(struct crypto_cipher *tfm, const u8 *aad,
+			    const u8 *data, size_t data_len, u8 *mic)
+{
+	const u8 *addr[3];
+	size_t len[3];
+	u8 zero[CMAC_TLEN_256];
+
+	memset(zero, 0, CMAC_TLEN_256);
+	addr[0] = aad;
+	len[0] = AAD_LEN;
+	addr[1] = data;
+	len[1] = data_len - CMAC_TLEN_256;
+	addr[2] = zero;
+	len[2] = CMAC_TLEN_256;
+
+	aes_cmac_vector(tfm, 3, addr, len, mic, CMAC_TLEN_256);
+}
 
-struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[])
+struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[],
+						   size_t key_len)
 {
 	struct crypto_cipher *tfm;
 
 	tfm = crypto_alloc_cipher("aes", 0, CRYPTO_ALG_ASYNC);
 	if (!IS_ERR(tfm))
-		crypto_cipher_setkey(tfm, key, AES_CMAC_KEY_LEN);
+		crypto_cipher_setkey(tfm, key, key_len);
 
 	return tfm;
 }
diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h
index 0ce6487af79..3702041f44f 100644
--- a/net/mac80211/aes_cmac.h
+++ b/net/mac80211/aes_cmac.h
@@ -11,9 +11,12 @@
 
 #include <linux/crypto.h>
 
-struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[]);
+struct crypto_cipher *ieee80211_aes_cmac_key_setup(const u8 key[],
+						   size_t key_len);
 void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad,
 			const u8 *data, size_t data_len, u8 *mic);
+void ieee80211_aes_cmac_256(struct crypto_cipher *tfm, const u8 *aad,
+			    const u8 *data, size_t data_len, u8 *mic);
 void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm);
 
 #endif /* AES_CMAC_H */
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index ef84441c119..b7e528bbecc 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -164,6 +164,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		break;
@@ -362,6 +363,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
 		params.seq_len = 6;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn64 = atomic64_read(&key->u.aes_cmac.tx_pn);
 		seq[0] = pn64;
 		seq[1] = pn64 >> 8;
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 64de07b1609..d1b60eb014a 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -101,6 +101,7 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
 				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn = atomic64_read(&key->u.aes_cmac.tx_pn);
 		len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
 				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
@@ -153,6 +154,7 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 		len = p - buf;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		rpn = key->u.aes_cmac.rx_pn;
 		p += scnprintf(p, sizeof(buf)+buf-p,
 			       "%02x%02x%02x%02x%02x%02x\n",
@@ -191,6 +193,7 @@ static ssize_t key_replays_read(struct file *file, char __user *userbuf,
 		len = scnprintf(buf, sizeof(buf), "%u\n", key->u.ccmp.replays);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		len = scnprintf(buf, sizeof(buf), "%u\n",
 				key->u.aes_cmac.replays);
 		break;
@@ -214,6 +217,7 @@ static ssize_t key_icverrors_read(struct file *file, char __user *userbuf,
 
 	switch (key->conf.cipher) {
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		len = scnprintf(buf, sizeof(buf), "%u\n",
 				key->u.aes_cmac.icverrors);
 		break;
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 83c61085c3f..7ceea9d9fcd 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -165,6 +165,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		/* all of these we can do in software - if driver can */
@@ -417,8 +418,12 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 		}
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		key->conf.iv_len = 0;
-		key->conf.icv_len = sizeof(struct ieee80211_mmie);
+		if (cipher == WLAN_CIPHER_SUITE_AES_CMAC)
+			key->conf.icv_len = sizeof(struct ieee80211_mmie);
+		else
+			key->conf.icv_len = sizeof(struct ieee80211_mmie_16);
 		if (seq)
 			for (j = 0; j < IEEE80211_CMAC_PN_LEN; j++)
 				key->u.aes_cmac.rx_pn[j] =
@@ -428,7 +433,7 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 		 * it does not need to be initialized for every packet.
 		 */
 		key->u.aes_cmac.tfm =
-			ieee80211_aes_cmac_key_setup(key_data);
+			ieee80211_aes_cmac_key_setup(key_data, key_len);
 		if (IS_ERR(key->u.aes_cmac.tfm)) {
 			err = PTR_ERR(key->u.aes_cmac.tfm);
 			kfree(key);
@@ -481,6 +486,7 @@ static void ieee80211_key_free_common(struct ieee80211_key *key)
 		ieee80211_aes_key_free(key->u.ccmp.tfm);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm);
 		break;
 	case WLAN_CIPHER_SUITE_GCMP:
@@ -804,6 +810,7 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		seq->ccmp.pn[0] = pn64 >> 40;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn64 = atomic64_read(&key->u.aes_cmac.tx_pn);
 		seq->ccmp.pn[5] = pn64;
 		seq->ccmp.pn[4] = pn64 >> 8;
@@ -854,6 +861,7 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		memcpy(seq->ccmp.pn, pn, IEEE80211_CCMP_PN_LEN);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		if (WARN_ON(tid != 0))
 			return;
 		pn = key->u.aes_cmac.rx_pn;
@@ -897,6 +905,7 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		atomic64_set(&key->u.ccmp.tx_pn, pn64);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		pn64 = (u64)seq->aes_cmac.pn[5] |
 		       ((u64)seq->aes_cmac.pn[4] << 8) |
 		       ((u64)seq->aes_cmac.pn[3] << 16) |
@@ -948,6 +957,7 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		memcpy(pn, seq->ccmp.pn, IEEE80211_CCMP_PN_LEN);
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		if (WARN_ON(tid != 0))
 			return;
 		pn = key->u.aes_cmac.rx_pn;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index a5ad2d5bb29..053a17c5023 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -671,7 +671,8 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		WLAN_CIPHER_SUITE_GCMP_256,
 
 		/* keep last -- depends on hw flags! */
-		WLAN_CIPHER_SUITE_AES_CMAC
+		WLAN_CIPHER_SUITE_AES_CMAC,
+		WLAN_CIPHER_SUITE_BIP_CMAC_256,
 	};
 
 	if (local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL ||
@@ -710,7 +711,7 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
 
 		if (!have_mfp)
-			local->hw.wiphy->n_cipher_suites--;
+			local->hw.wiphy->n_cipher_suites -= 2;
 
 		if (!have_wep) {
 			local->hw.wiphy->cipher_suites += 2;
@@ -736,9 +737,9 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		if (have_wep)
 			n_suites += 2;
 
-		/* check if we have AES_CMAC */
+		/* check if we have AES_CMAC, BIP-CMAC-256 */
 		if (have_mfp)
-			n_suites++;
+			n_suites += 2;
 
 		suites = kmalloc(sizeof(u32) * n_suites, GFP_KERNEL);
 		if (!suites)
@@ -755,8 +756,10 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 			suites[w++] = WLAN_CIPHER_SUITE_WEP104;
 		}
 
-		if (have_mfp)
+		if (have_mfp) {
 			suites[w++] = WLAN_CIPHER_SUITE_AES_CMAC;
+			suites[w++] = WLAN_CIPHER_SUITE_BIP_CMAC_256;
+		}
 
 		for (r = 0; r < local->hw.n_cipher_schemes; r++)
 			suites[w++] = cs[r].cipher;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index e8c6ba5ce70..93ebc952547 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -647,6 +647,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb)
 {
 	struct ieee80211_mgmt *hdr = (struct ieee80211_mgmt *) skb->data;
 	struct ieee80211_mmie *mmie;
+	struct ieee80211_mmie_16 *mmie16;
 
 	if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da))
 		return -1;
@@ -656,11 +657,18 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb)
 
 	mmie = (struct ieee80211_mmie *)
 		(skb->data + skb->len - sizeof(*mmie));
-	if (mmie->element_id != WLAN_EID_MMIE ||
-	    mmie->length != sizeof(*mmie) - 2)
-		return -1;
-
-	return le16_to_cpu(mmie->key_id);
+	if (mmie->element_id == WLAN_EID_MMIE &&
+	    mmie->length == sizeof(*mmie) - 2)
+		return le16_to_cpu(mmie->key_id);
+
+	mmie16 = (struct ieee80211_mmie_16 *)
+		(skb->data + skb->len - sizeof(*mmie16));
+	if (skb->len >= 24 + sizeof(*mmie16) &&
+	    mmie16->element_id == WLAN_EID_MMIE &&
+	    mmie16->length == sizeof(*mmie16) - 2)
+		return le16_to_cpu(mmie16->key_id);
+
+	return -1;
 }
 
 static int iwl80211_get_cs_keyid(const struct ieee80211_cipher_scheme *cs,
@@ -1660,6 +1668,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 		result = ieee80211_crypto_aes_cmac_decrypt(rx);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		result = ieee80211_crypto_aes_cmac_256_decrypt(rx);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		result = ieee80211_crypto_gcmp_decrypt(rx);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index be57e0afd01..909c27be1fd 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -639,6 +639,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 					ieee80211_is_mgmt(hdr->frame_control);
 			break;
 		case WLAN_CIPHER_SUITE_AES_CMAC:
+		case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 			if (!ieee80211_is_mgmt(hdr->frame_control))
 				tx->key = NULL;
 			break;
@@ -1021,6 +1022,8 @@ ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx)
 			tx, IEEE80211_CCMP_256_MIC_LEN);
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 		return ieee80211_crypto_aes_cmac_encrypt(tx);
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		return ieee80211_crypto_aes_cmac_256_encrypt(tx);
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		return ieee80211_crypto_gcmp_encrypt(tx);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index ae654de9782..549af118de9 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -955,6 +955,48 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx)
 	return TX_CONTINUE;
 }
 
+ieee80211_tx_result
+ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx)
+{
+	struct sk_buff *skb;
+	struct ieee80211_tx_info *info;
+	struct ieee80211_key *key = tx->key;
+	struct ieee80211_mmie_16 *mmie;
+	u8 aad[20];
+	u64 pn64;
+
+	if (WARN_ON(skb_queue_len(&tx->skbs) != 1))
+		return TX_DROP;
+
+	skb = skb_peek(&tx->skbs);
+
+	info = IEEE80211_SKB_CB(skb);
+
+	if (info->control.hw_key)
+		return TX_CONTINUE;
+
+	if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie)))
+		return TX_DROP;
+
+	mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie));
+	mmie->element_id = WLAN_EID_MMIE;
+	mmie->length = sizeof(*mmie) - 2;
+	mmie->key_id = cpu_to_le16(key->conf.keyidx);
+
+	/* PN = PN + 1 */
+	pn64 = atomic64_inc_return(&key->u.aes_cmac.tx_pn);
+
+	bip_ipn_set64(mmie->sequence_number, pn64);
+
+	bip_aad(skb, aad);
+
+	/* MIC = AES-256-CMAC(IGTK, AAD || Management Frame Body || MMIE, 128)
+	 */
+	ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad,
+			       skb->data + 24, skb->len - 24, mmie->mic);
+
+	return TX_CONTINUE;
+}
 
 ieee80211_rx_result
 ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx)
@@ -1006,6 +1048,56 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx)
 	return RX_CONTINUE;
 }
 
+ieee80211_rx_result
+ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx)
+{
+	struct sk_buff *skb = rx->skb;
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_key *key = rx->key;
+	struct ieee80211_mmie_16 *mmie;
+	u8 aad[20], mic[16], ipn[6];
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	if (!ieee80211_is_mgmt(hdr->frame_control))
+		return RX_CONTINUE;
+
+	/* management frames are already linear */
+
+	if (skb->len < 24 + sizeof(*mmie))
+		return RX_DROP_UNUSABLE;
+
+	mmie = (struct ieee80211_mmie_16 *)
+		(skb->data + skb->len - sizeof(*mmie));
+	if (mmie->element_id != WLAN_EID_MMIE ||
+	    mmie->length != sizeof(*mmie) - 2)
+		return RX_DROP_UNUSABLE; /* Invalid MMIE */
+
+	bip_ipn_swap(ipn, mmie->sequence_number);
+
+	if (memcmp(ipn, key->u.aes_cmac.rx_pn, 6) <= 0) {
+		key->u.aes_cmac.replays++;
+		return RX_DROP_UNUSABLE;
+	}
+
+	if (!(status->flag & RX_FLAG_DECRYPTED)) {
+		/* hardware didn't decrypt/verify MIC */
+		bip_aad(skb, aad);
+		ieee80211_aes_cmac_256(key->u.aes_cmac.tfm, aad,
+				       skb->data + 24, skb->len - 24, mic);
+		if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) {
+			key->u.aes_cmac.icverrors++;
+			return RX_DROP_UNUSABLE;
+		}
+	}
+
+	memcpy(key->u.aes_cmac.rx_pn, ipn, 6);
+
+	/* Remove MMIE */
+	skb_trim(skb, skb->len - sizeof(*mmie));
+
+	return RX_CONTINUE;
+}
+
 ieee80211_tx_result
 ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx)
 {
diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h
index 43e109f27a8..06b7f167a17 100644
--- a/net/mac80211/wpa.h
+++ b/net/mac80211/wpa.h
@@ -32,8 +32,12 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx,
 
 ieee80211_tx_result
 ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx);
+ieee80211_tx_result
+ieee80211_crypto_aes_cmac_256_encrypt(struct ieee80211_tx_data *tx);
 ieee80211_rx_result
 ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx);
+ieee80211_rx_result
+ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx);
 ieee80211_tx_result
 ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx);
 ieee80211_rx_result
-- 
cgit v1.2.3-70-g09d2


From 8ade538bf39b1ee53418528fdacd36b8e65621b9 Mon Sep 17 00:00:00 2001
From: Jouni Malinen <jouni@qca.qualcomm.com>
Date: Sat, 24 Jan 2015 19:52:09 +0200
Subject: mac80111: Add BIP-GMAC-128 and BIP-GMAC-256 ciphers

This allows mac80211 to configure BIP-GMAC-128 and BIP-GMAC-256 to the
driver and also use software-implementation within mac80211 when the
driver does not support this with hardware accelaration.

Signed-off-by: Jouni Malinen <jouni@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |   5 +++
 net/mac80211/Makefile      |   1 +
 net/mac80211/aes_gmac.c    |  84 ++++++++++++++++++++++++++++++++++++
 net/mac80211/aes_gmac.h    |  20 +++++++++
 net/mac80211/cfg.c         |  14 ++++++
 net/mac80211/debugfs_key.c |  26 +++++++++++
 net/mac80211/key.c         |  60 ++++++++++++++++++++++++++
 net/mac80211/key.h         |   7 +++
 net/mac80211/main.c        |  12 ++++--
 net/mac80211/rx.c          |   4 ++
 net/mac80211/tx.c          |   5 +++
 net/mac80211/wpa.c         | 105 +++++++++++++++++++++++++++++++++++++++++++++
 net/mac80211/wpa.h         |   4 ++
 13 files changed, 344 insertions(+), 3 deletions(-)
 create mode 100644 net/mac80211/aes_gmac.c
 create mode 100644 net/mac80211/aes_gmac.h

(limited to 'include')

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ae663843611..d52914b7533 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -4098,6 +4098,8 @@ void ieee80211_aes_cmac_calculate_k1_k2(struct ieee80211_key_conf *keyconf,
  *	reverse order than in packet)
  * @aes_cmac: PN data, most significant byte first (big endian,
  *	reverse order than in packet)
+ * @aes_gmac: PN data, most significant byte first (big endian,
+ *	reverse order than in packet)
  * @gcmp: PN data, most significant byte first (big endian,
  *	reverse order than in packet)
  */
@@ -4113,6 +4115,9 @@ struct ieee80211_key_seq {
 		struct {
 			u8 pn[6];
 		} aes_cmac;
+		struct {
+			u8 pn[6];
+		} aes_gmac;
 		struct {
 			u8 pn[6];
 		} gcmp;
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 0cbf9361843..3275f01881b 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -17,6 +17,7 @@ mac80211-y := \
 	aes_ccm.o \
 	aes_gcm.o \
 	aes_cmac.o \
+	aes_gmac.o \
 	cfg.o \
 	ethtool.o \
 	rx.o \
diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c
new file mode 100644
index 00000000000..1c72edcb008
--- /dev/null
+++ b/net/mac80211/aes_gmac.c
@@ -0,0 +1,84 @@
+/*
+ * AES-GMAC for IEEE 802.11 BIP-GMAC-128 and BIP-GMAC-256
+ * Copyright 2015, Qualcomm Atheros, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/aes.h>
+
+#include <net/mac80211.h>
+#include "key.h"
+#include "aes_gmac.h"
+
+#define GMAC_MIC_LEN 16
+#define GMAC_NONCE_LEN 12
+#define AAD_LEN 20
+
+int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
+		       const u8 *data, size_t data_len, u8 *mic)
+{
+	struct scatterlist sg[3], ct[1];
+	char aead_req_data[sizeof(struct aead_request) +
+			   crypto_aead_reqsize(tfm)]
+		__aligned(__alignof__(struct aead_request));
+	struct aead_request *aead_req = (void *)aead_req_data;
+	u8 zero[GMAC_MIC_LEN], iv[AES_BLOCK_SIZE];
+
+	if (data_len < GMAC_MIC_LEN)
+		return -EINVAL;
+
+	memset(aead_req, 0, sizeof(aead_req_data));
+
+	memset(zero, 0, GMAC_MIC_LEN);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], aad, AAD_LEN);
+	sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN);
+	sg_set_buf(&sg[2], zero, GMAC_MIC_LEN);
+
+	memcpy(iv, nonce, GMAC_NONCE_LEN);
+	memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN);
+	iv[AES_BLOCK_SIZE - 1] = 0x01;
+
+	sg_init_table(ct, 1);
+	sg_set_buf(&ct[0], mic, GMAC_MIC_LEN);
+
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_assoc(aead_req, sg, AAD_LEN + data_len);
+	aead_request_set_crypt(aead_req, NULL, ct, 0, iv);
+
+	crypto_aead_encrypt(aead_req);
+
+	return 0;
+}
+
+struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],
+						 size_t key_len)
+{
+	struct crypto_aead *tfm;
+	int err;
+
+	tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return tfm;
+
+	err = crypto_aead_setkey(tfm, key, key_len);
+	if (!err)
+		return tfm;
+	if (!err)
+		err = crypto_aead_setauthsize(tfm, GMAC_MIC_LEN);
+
+	crypto_free_aead(tfm);
+	return ERR_PTR(err);
+}
+
+void ieee80211_aes_gmac_key_free(struct crypto_aead *tfm)
+{
+	crypto_free_aead(tfm);
+}
diff --git a/net/mac80211/aes_gmac.h b/net/mac80211/aes_gmac.h
new file mode 100644
index 00000000000..d328204d73a
--- /dev/null
+++ b/net/mac80211/aes_gmac.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright 2015, Qualcomm Atheros, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef AES_GMAC_H
+#define AES_GMAC_H
+
+#include <linux/crypto.h>
+
+struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],
+						 size_t key_len);
+int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce,
+		       const u8 *data, size_t data_len, u8 *mic);
+void ieee80211_aes_gmac_key_free(struct crypto_aead *tfm);
+
+#endif /* AES_GMAC_H */
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b7e528bbecc..dd4ff36c557 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -165,6 +165,8 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		break;
@@ -374,6 +376,18 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev,
 		params.seq = seq;
 		params.seq_len = 6;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn64 = atomic64_read(&key->u.aes_gmac.tx_pn);
+		seq[0] = pn64;
+		seq[1] = pn64 >> 8;
+		seq[2] = pn64 >> 16;
+		seq[3] = pn64 >> 24;
+		seq[4] = pn64 >> 32;
+		seq[5] = pn64 >> 40;
+		params.seq = seq;
+		params.seq_len = 6;
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		pn64 = atomic64_read(&key->u.gcmp.tx_pn);
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index d1b60eb014a..71ac1b5f4da 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -107,6 +107,13 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf,
 				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
 				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn = atomic64_read(&key->u.aes_gmac.tx_pn);
+		len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n",
+				(u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24),
+				(u8)(pn >> 16), (u8)(pn >> 8), (u8)pn);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		pn = atomic64_read(&key->u.gcmp.tx_pn);
@@ -162,6 +169,15 @@ static ssize_t key_rx_spec_read(struct file *file, char __user *userbuf,
 			       rpn[3], rpn[4], rpn[5]);
 		len = p - buf;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		rpn = key->u.aes_gmac.rx_pn;
+		p += scnprintf(p, sizeof(buf)+buf-p,
+			       "%02x%02x%02x%02x%02x%02x\n",
+			       rpn[0], rpn[1], rpn[2],
+			       rpn[3], rpn[4], rpn[5]);
+		len = p - buf;
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) {
@@ -197,6 +213,11 @@ static ssize_t key_replays_read(struct file *file, char __user *userbuf,
 		len = scnprintf(buf, sizeof(buf), "%u\n",
 				key->u.aes_cmac.replays);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		len = scnprintf(buf, sizeof(buf), "%u\n",
+				key->u.aes_gmac.replays);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		len = scnprintf(buf, sizeof(buf), "%u\n", key->u.gcmp.replays);
@@ -221,6 +242,11 @@ static ssize_t key_icverrors_read(struct file *file, char __user *userbuf,
 		len = scnprintf(buf, sizeof(buf), "%u\n",
 				key->u.aes_cmac.icverrors);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		len = scnprintf(buf, sizeof(buf), "%u\n",
+				key->u.aes_gmac.icverrors);
+		break;
 	default:
 		return 0;
 	}
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 7ceea9d9fcd..0825d76edcf 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -24,6 +24,7 @@
 #include "debugfs_key.h"
 #include "aes_ccm.h"
 #include "aes_cmac.h"
+#include "aes_gmac.h"
 #include "aes_gcm.h"
 
 
@@ -166,6 +167,8 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		/* all of these we can do in software - if driver can */
@@ -440,6 +443,25 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 			return ERR_PTR(err);
 		}
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		key->conf.iv_len = 0;
+		key->conf.icv_len = sizeof(struct ieee80211_mmie_16);
+		if (seq)
+			for (j = 0; j < IEEE80211_GMAC_PN_LEN; j++)
+				key->u.aes_gmac.rx_pn[j] =
+					seq[IEEE80211_GMAC_PN_LEN - j - 1];
+		/* Initialize AES key state here as an optimization so that
+		 * it does not need to be initialized for every packet.
+		 */
+		key->u.aes_gmac.tfm =
+			ieee80211_aes_gmac_key_setup(key_data, key_len);
+		if (IS_ERR(key->u.aes_gmac.tfm)) {
+			err = PTR_ERR(key->u.aes_gmac.tfm);
+			kfree(key);
+			return ERR_PTR(err);
+		}
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		key->conf.iv_len = IEEE80211_GCMP_HDR_LEN;
@@ -489,6 +511,10 @@ static void ieee80211_key_free_common(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		ieee80211_aes_gmac_key_free(key->u.aes_gmac.tfm);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		ieee80211_aes_gcm_key_free(key->u.gcmp.tfm);
@@ -819,6 +845,16 @@ void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		seq->ccmp.pn[1] = pn64 >> 32;
 		seq->ccmp.pn[0] = pn64 >> 40;
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn64 = atomic64_read(&key->u.aes_gmac.tx_pn);
+		seq->ccmp.pn[5] = pn64;
+		seq->ccmp.pn[4] = pn64 >> 8;
+		seq->ccmp.pn[3] = pn64 >> 16;
+		seq->ccmp.pn[2] = pn64 >> 24;
+		seq->ccmp.pn[1] = pn64 >> 32;
+		seq->ccmp.pn[0] = pn64 >> 40;
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		pn64 = atomic64_read(&key->u.gcmp.tx_pn);
@@ -867,6 +903,13 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		pn = key->u.aes_cmac.rx_pn;
 		memcpy(seq->aes_cmac.pn, pn, IEEE80211_CMAC_PN_LEN);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		if (WARN_ON(tid != 0))
+			return;
+		pn = key->u.aes_gmac.rx_pn;
+		memcpy(seq->aes_gmac.pn, pn, IEEE80211_GMAC_PN_LEN);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
@@ -914,6 +957,16 @@ void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf,
 		       ((u64)seq->aes_cmac.pn[0] << 40);
 		atomic64_set(&key->u.aes_cmac.tx_pn, pn64);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		pn64 = (u64)seq->aes_gmac.pn[5] |
+		       ((u64)seq->aes_gmac.pn[4] << 8) |
+		       ((u64)seq->aes_gmac.pn[3] << 16) |
+		       ((u64)seq->aes_gmac.pn[2] << 24) |
+		       ((u64)seq->aes_gmac.pn[1] << 32) |
+		       ((u64)seq->aes_gmac.pn[0] << 40);
+		atomic64_set(&key->u.aes_gmac.tx_pn, pn64);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		pn64 = (u64)seq->gcmp.pn[5] |
@@ -963,6 +1016,13 @@ void ieee80211_set_key_rx_seq(struct ieee80211_key_conf *keyconf,
 		pn = key->u.aes_cmac.rx_pn;
 		memcpy(pn, seq->aes_cmac.pn, IEEE80211_CMAC_PN_LEN);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		if (WARN_ON(tid != 0))
+			return;
+		pn = key->u.aes_gmac.rx_pn;
+		memcpy(pn, seq->aes_gmac.pn, IEEE80211_GMAC_PN_LEN);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		if (WARN_ON(tid < -1 || tid >= IEEE80211_NUM_TIDS))
diff --git a/net/mac80211/key.h b/net/mac80211/key.h
index 27580da851c..d57a9915494 100644
--- a/net/mac80211/key.h
+++ b/net/mac80211/key.h
@@ -94,6 +94,13 @@ struct ieee80211_key {
 			u32 replays; /* dot11RSNAStatsCMACReplays */
 			u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
 		} aes_cmac;
+		struct {
+			atomic64_t tx_pn;
+			u8 rx_pn[IEEE80211_GMAC_PN_LEN];
+			struct crypto_aead *tfm;
+			u32 replays; /* dot11RSNAStatsCMACReplays */
+			u32 icverrors; /* dot11RSNAStatsCMACICVErrors */
+		} aes_gmac;
 		struct {
 			atomic64_t tx_pn;
 			/* Last received packet number. The first
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 053a17c5023..5e09d354c5a 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -673,6 +673,8 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		/* keep last -- depends on hw flags! */
 		WLAN_CIPHER_SUITE_AES_CMAC,
 		WLAN_CIPHER_SUITE_BIP_CMAC_256,
+		WLAN_CIPHER_SUITE_BIP_GMAC_128,
+		WLAN_CIPHER_SUITE_BIP_GMAC_256,
 	};
 
 	if (local->hw.flags & IEEE80211_HW_SW_CRYPTO_CONTROL ||
@@ -711,7 +713,7 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites);
 
 		if (!have_mfp)
-			local->hw.wiphy->n_cipher_suites -= 2;
+			local->hw.wiphy->n_cipher_suites -= 4;
 
 		if (!have_wep) {
 			local->hw.wiphy->cipher_suites += 2;
@@ -737,9 +739,11 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		if (have_wep)
 			n_suites += 2;
 
-		/* check if we have AES_CMAC, BIP-CMAC-256 */
+		/* check if we have AES_CMAC, BIP-CMAC-256, BIP-GMAC-128,
+		 * BIP-GMAC-256
+		 */
 		if (have_mfp)
-			n_suites += 2;
+			n_suites += 4;
 
 		suites = kmalloc(sizeof(u32) * n_suites, GFP_KERNEL);
 		if (!suites)
@@ -759,6 +763,8 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 		if (have_mfp) {
 			suites[w++] = WLAN_CIPHER_SUITE_AES_CMAC;
 			suites[w++] = WLAN_CIPHER_SUITE_BIP_CMAC_256;
+			suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_128;
+			suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_256;
 		}
 
 		for (r = 0; r < local->hw.n_cipher_schemes; r++)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 93ebc952547..ed38d830265 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1671,6 +1671,10 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		result = ieee80211_crypto_aes_cmac_256_decrypt(rx);
 		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		result = ieee80211_crypto_aes_gmac_decrypt(rx);
+		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		result = ieee80211_crypto_gcmp_decrypt(rx);
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 909c27be1fd..88a18ffe297 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -640,6 +640,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 			break;
 		case WLAN_CIPHER_SUITE_AES_CMAC:
 		case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_256:
 			if (!ieee80211_is_mgmt(hdr->frame_control))
 				tx->key = NULL;
 			break;
@@ -1024,6 +1026,9 @@ ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx)
 		return ieee80211_crypto_aes_cmac_encrypt(tx);
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 		return ieee80211_crypto_aes_cmac_256_encrypt(tx);
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		return ieee80211_crypto_aes_gmac_encrypt(tx);
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		return ieee80211_crypto_gcmp_encrypt(tx);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 549af118de9..75de6fac40d 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -22,6 +22,7 @@
 #include "tkip.h"
 #include "aes_ccm.h"
 #include "aes_cmac.h"
+#include "aes_gmac.h"
 #include "aes_gcm.h"
 #include "wpa.h"
 
@@ -1098,6 +1099,110 @@ ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx)
 	return RX_CONTINUE;
 }
 
+ieee80211_tx_result
+ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx)
+{
+	struct sk_buff *skb;
+	struct ieee80211_tx_info *info;
+	struct ieee80211_key *key = tx->key;
+	struct ieee80211_mmie_16 *mmie;
+	struct ieee80211_hdr *hdr;
+	u8 aad[20];
+	u64 pn64;
+	u8 nonce[12];
+
+	if (WARN_ON(skb_queue_len(&tx->skbs) != 1))
+		return TX_DROP;
+
+	skb = skb_peek(&tx->skbs);
+
+	info = IEEE80211_SKB_CB(skb);
+
+	if (info->control.hw_key)
+		return TX_CONTINUE;
+
+	if (WARN_ON(skb_tailroom(skb) < sizeof(*mmie)))
+		return TX_DROP;
+
+	mmie = (struct ieee80211_mmie_16 *)skb_put(skb, sizeof(*mmie));
+	mmie->element_id = WLAN_EID_MMIE;
+	mmie->length = sizeof(*mmie) - 2;
+	mmie->key_id = cpu_to_le16(key->conf.keyidx);
+
+	/* PN = PN + 1 */
+	pn64 = atomic64_inc_return(&key->u.aes_gmac.tx_pn);
+
+	bip_ipn_set64(mmie->sequence_number, pn64);
+
+	bip_aad(skb, aad);
+
+	hdr = (struct ieee80211_hdr *)skb->data;
+	memcpy(nonce, hdr->addr2, ETH_ALEN);
+	bip_ipn_swap(nonce + ETH_ALEN, mmie->sequence_number);
+
+	/* MIC = AES-GMAC(IGTK, AAD || Management Frame Body || MMIE, 128) */
+	if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce,
+			       skb->data + 24, skb->len - 24, mmie->mic) < 0)
+		return TX_DROP;
+
+	return TX_CONTINUE;
+}
+
+ieee80211_rx_result
+ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx)
+{
+	struct sk_buff *skb = rx->skb;
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_key *key = rx->key;
+	struct ieee80211_mmie_16 *mmie;
+	u8 aad[20], mic[16], ipn[6], nonce[12];
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	if (!ieee80211_is_mgmt(hdr->frame_control))
+		return RX_CONTINUE;
+
+	/* management frames are already linear */
+
+	if (skb->len < 24 + sizeof(*mmie))
+		return RX_DROP_UNUSABLE;
+
+	mmie = (struct ieee80211_mmie_16 *)
+		(skb->data + skb->len - sizeof(*mmie));
+	if (mmie->element_id != WLAN_EID_MMIE ||
+	    mmie->length != sizeof(*mmie) - 2)
+		return RX_DROP_UNUSABLE; /* Invalid MMIE */
+
+	bip_ipn_swap(ipn, mmie->sequence_number);
+
+	if (memcmp(ipn, key->u.aes_gmac.rx_pn, 6) <= 0) {
+		key->u.aes_gmac.replays++;
+		return RX_DROP_UNUSABLE;
+	}
+
+	if (!(status->flag & RX_FLAG_DECRYPTED)) {
+		/* hardware didn't decrypt/verify MIC */
+		bip_aad(skb, aad);
+
+		memcpy(nonce, hdr->addr2, ETH_ALEN);
+		memcpy(nonce + ETH_ALEN, ipn, 6);
+
+		if (ieee80211_aes_gmac(key->u.aes_gmac.tfm, aad, nonce,
+				       skb->data + 24, skb->len - 24,
+				       mic) < 0 ||
+		    memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) {
+			key->u.aes_gmac.icverrors++;
+			return RX_DROP_UNUSABLE;
+		}
+	}
+
+	memcpy(key->u.aes_gmac.rx_pn, ipn, 6);
+
+	/* Remove MMIE */
+	skb_trim(skb, skb->len - sizeof(*mmie));
+
+	return RX_CONTINUE;
+}
+
 ieee80211_tx_result
 ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx)
 {
diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h
index 06b7f167a17..d98011ee8f5 100644
--- a/net/mac80211/wpa.h
+++ b/net/mac80211/wpa.h
@@ -39,6 +39,10 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx);
 ieee80211_rx_result
 ieee80211_crypto_aes_cmac_256_decrypt(struct ieee80211_rx_data *rx);
 ieee80211_tx_result
+ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx);
+ieee80211_rx_result
+ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx);
+ieee80211_tx_result
 ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx);
 ieee80211_rx_result
 ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx);
-- 
cgit v1.2.3-70-g09d2


From 861360a56d0bcbc0bec92a1f1266c66880b2e5ae Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Tue, 23 Dec 2014 09:46:27 -0300
Subject: [media] videobuf: make unused exported functions static

The videobuf_dma_init* and videobuf_dma_map() functions are no longer
used except in videobuf-dma-sg.c itself. Make them static.

These functions were abused in various drivers. All those drivers
have now been fixed, so by no longer exporting these functions
future abuse is now prevented.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/v4l2-core/videobuf-dma-sg.c | 15 +++++----------
 include/media/videobuf-dma-sg.h           |  8 --------
 2 files changed, 5 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 3ff15f1c9d7..f669cedca8b 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -145,12 +145,11 @@ struct videobuf_dmabuf *videobuf_to_dma(struct videobuf_buffer *buf)
 }
 EXPORT_SYMBOL_GPL(videobuf_to_dma);
 
-void videobuf_dma_init(struct videobuf_dmabuf *dma)
+static void videobuf_dma_init(struct videobuf_dmabuf *dma)
 {
 	memset(dma, 0, sizeof(*dma));
 	dma->magic = MAGIC_DMABUF;
 }
-EXPORT_SYMBOL_GPL(videobuf_dma_init);
 
 static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 			int direction, unsigned long data, unsigned long size)
@@ -195,7 +194,7 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 	return 0;
 }
 
-int videobuf_dma_init_user(struct videobuf_dmabuf *dma, int direction,
+static int videobuf_dma_init_user(struct videobuf_dmabuf *dma, int direction,
 			   unsigned long data, unsigned long size)
 {
 	int ret;
@@ -206,9 +205,8 @@ int videobuf_dma_init_user(struct videobuf_dmabuf *dma, int direction,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(videobuf_dma_init_user);
 
-int videobuf_dma_init_kernel(struct videobuf_dmabuf *dma, int direction,
+static int videobuf_dma_init_kernel(struct videobuf_dmabuf *dma, int direction,
 			     int nr_pages)
 {
 	int i;
@@ -267,9 +265,8 @@ out_free_pages:
 	return -ENOMEM;
 
 }
-EXPORT_SYMBOL_GPL(videobuf_dma_init_kernel);
 
-int videobuf_dma_init_overlay(struct videobuf_dmabuf *dma, int direction,
+static int videobuf_dma_init_overlay(struct videobuf_dmabuf *dma, int direction,
 			      dma_addr_t addr, int nr_pages)
 {
 	dprintk(1, "init overlay [%d pages @ bus 0x%lx]\n",
@@ -284,9 +281,8 @@ int videobuf_dma_init_overlay(struct videobuf_dmabuf *dma, int direction,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(videobuf_dma_init_overlay);
 
-int videobuf_dma_map(struct device *dev, struct videobuf_dmabuf *dma)
+static int videobuf_dma_map(struct device *dev, struct videobuf_dmabuf *dma)
 {
 	MAGIC_CHECK(dma->magic, MAGIC_DMABUF);
 	BUG_ON(0 == dma->nr_pages);
@@ -328,7 +324,6 @@ int videobuf_dma_map(struct device *dev, struct videobuf_dmabuf *dma)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(videobuf_dma_map);
 
 int videobuf_dma_unmap(struct device *dev, struct videobuf_dmabuf *dma)
 {
diff --git a/include/media/videobuf-dma-sg.h b/include/media/videobuf-dma-sg.h
index fb6fd4d8f4e..d8b27854e3b 100644
--- a/include/media/videobuf-dma-sg.h
+++ b/include/media/videobuf-dma-sg.h
@@ -84,16 +84,8 @@ struct videobuf_dma_sg_memory {
  * Despite the name, this is totally unrelated to videobuf, except that
  * videobuf-dma-sg uses the same API internally.
  */
-void videobuf_dma_init(struct videobuf_dmabuf *dma);
-int videobuf_dma_init_user(struct videobuf_dmabuf *dma, int direction,
-			   unsigned long data, unsigned long size);
-int videobuf_dma_init_kernel(struct videobuf_dmabuf *dma, int direction,
-			     int nr_pages);
-int videobuf_dma_init_overlay(struct videobuf_dmabuf *dma, int direction,
-			      dma_addr_t addr, int nr_pages);
 int videobuf_dma_free(struct videobuf_dmabuf *dma);
 
-int videobuf_dma_map(struct device *dev, struct videobuf_dmabuf *dma);
 int videobuf_dma_unmap(struct device *dev, struct videobuf_dmabuf *dma);
 struct videobuf_dmabuf *videobuf_to_dma(struct videobuf_buffer *buf);
 
-- 
cgit v1.2.3-70-g09d2


From 6994ca3df1b4cd7a2577a1b6e41431d8ace457a4 Mon Sep 17 00:00:00 2001
From: Ondrej Zary <linux@rainbow-software.org>
Date: Thu, 15 Jan 2015 17:10:46 -0300
Subject: [media] tea575x: split and export functions

Split ioctl interface from enum_freq_bands, g_tuner and s_hw_freq_seek
functions and export them to be used in other drivers like bttv.

Signed-off-by: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/radio/tea575x.c | 41 ++++++++++++++++++++++++++++++++---------
 include/media/tea575x.h       |  5 +++++
 2 files changed, 37 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/media/radio/tea575x.c b/drivers/media/radio/tea575x.c
index f1a0867789f..43d1ea53cb6 100644
--- a/drivers/media/radio/tea575x.c
+++ b/drivers/media/radio/tea575x.c
@@ -247,10 +247,9 @@ static int vidioc_querycap(struct file *file, void  *priv,
 	return 0;
 }
 
-static int vidioc_enum_freq_bands(struct file *file, void *priv,
-					 struct v4l2_frequency_band *band)
+int snd_tea575x_enum_freq_bands(struct snd_tea575x *tea,
+					struct v4l2_frequency_band *band)
 {
-	struct snd_tea575x *tea = video_drvdata(file);
 	int index;
 
 	if (band->tuner != 0)
@@ -279,18 +278,25 @@ static int vidioc_enum_freq_bands(struct file *file, void *priv,
 
 	return 0;
 }
+EXPORT_SYMBOL(snd_tea575x_enum_freq_bands);
 
-static int vidioc_g_tuner(struct file *file, void *priv,
-					struct v4l2_tuner *v)
+static int vidioc_enum_freq_bands(struct file *file, void *priv,
+					 struct v4l2_frequency_band *band)
 {
 	struct snd_tea575x *tea = video_drvdata(file);
+
+	return snd_tea575x_enum_freq_bands(tea, band);
+}
+
+int snd_tea575x_g_tuner(struct snd_tea575x *tea, struct v4l2_tuner *v)
+{
 	struct v4l2_frequency_band band_fm = { 0, };
 
 	if (v->index > 0)
 		return -EINVAL;
 
 	snd_tea575x_read(tea);
-	vidioc_enum_freq_bands(file, priv, &band_fm);
+	snd_tea575x_enum_freq_bands(tea, &band_fm);
 
 	memset(v, 0, sizeof(*v));
 	strlcpy(v->name, tea->has_am ? "FM/AM" : "FM", sizeof(v->name));
@@ -304,6 +310,15 @@ static int vidioc_g_tuner(struct file *file, void *priv,
 	v->signal = tea->tuned ? 0xffff : 0;
 	return 0;
 }
+EXPORT_SYMBOL(snd_tea575x_g_tuner);
+
+static int vidioc_g_tuner(struct file *file, void *priv,
+					struct v4l2_tuner *v)
+{
+	struct snd_tea575x *tea = video_drvdata(file);
+
+	return snd_tea575x_g_tuner(tea, v);
+}
 
 static int vidioc_s_tuner(struct file *file, void *priv,
 					const struct v4l2_tuner *v)
@@ -356,10 +371,9 @@ static int vidioc_s_frequency(struct file *file, void *priv,
 	return 0;
 }
 
-static int vidioc_s_hw_freq_seek(struct file *file, void *fh,
-					const struct v4l2_hw_freq_seek *a)
+int snd_tea575x_s_hw_freq_seek(struct file *file, struct snd_tea575x *tea,
+				const struct v4l2_hw_freq_seek *a)
 {
-	struct snd_tea575x *tea = video_drvdata(file);
 	unsigned long timeout;
 	int i, spacing;
 
@@ -442,6 +456,15 @@ static int vidioc_s_hw_freq_seek(struct file *file, void *fh,
 	snd_tea575x_set_freq(tea);
 	return -ENODATA;
 }
+EXPORT_SYMBOL(snd_tea575x_s_hw_freq_seek);
+
+static int vidioc_s_hw_freq_seek(struct file *file, void *fh,
+					const struct v4l2_hw_freq_seek *a)
+{
+	struct snd_tea575x *tea = video_drvdata(file);
+
+	return snd_tea575x_s_hw_freq_seek(file, tea, a);
+}
 
 static int tea575x_s_ctrl(struct v4l2_ctrl *ctrl)
 {
diff --git a/include/media/tea575x.h b/include/media/tea575x.h
index 2d4fa59db90..5d096578b73 100644
--- a/include/media/tea575x.h
+++ b/include/media/tea575x.h
@@ -71,6 +71,11 @@ struct snd_tea575x {
 	int (*ext_init)(struct snd_tea575x *tea);
 };
 
+int snd_tea575x_enum_freq_bands(struct snd_tea575x *tea,
+					struct v4l2_frequency_band *band);
+int snd_tea575x_g_tuner(struct snd_tea575x *tea, struct v4l2_tuner *v);
+int snd_tea575x_s_hw_freq_seek(struct file *file, struct snd_tea575x *tea,
+				const struct v4l2_hw_freq_seek *a);
 int snd_tea575x_hw_init(struct snd_tea575x *tea);
 int snd_tea575x_init(struct snd_tea575x *tea, struct module *owner);
 void snd_tea575x_exit(struct snd_tea575x *tea);
-- 
cgit v1.2.3-70-g09d2


From 05c80d75f10ad7d3f95444b65788d6a0bbb4380d Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Fri, 19 Dec 2014 09:14:20 -0300
Subject: [media] hdmi: add new HDMI 2.0 defines

Add new Video InfoFrame colorspace information introduced in HDMI 2.0
and new Audio Coding Extension Types, also from HDMI 2.0.

HDMI_CONTENT_TYPE_NONE was renamed to _GRAPHICS since that's what
it is called in CEA-861-F.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 include/linux/hdmi.h | 30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index cbb5790a35c..5afc0bff2bb 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -52,12 +52,18 @@ enum hdmi_colorspace {
 	HDMI_COLORSPACE_RGB,
 	HDMI_COLORSPACE_YUV422,
 	HDMI_COLORSPACE_YUV444,
+	HDMI_COLORSPACE_YUV420,
+	HDMI_COLORSPACE_RESERVED4,
+	HDMI_COLORSPACE_RESERVED5,
+	HDMI_COLORSPACE_RESERVED6,
+	HDMI_COLORSPACE_IDO_DEFINED,
 };
 
 enum hdmi_scan_mode {
 	HDMI_SCAN_MODE_NONE,
 	HDMI_SCAN_MODE_OVERSCAN,
 	HDMI_SCAN_MODE_UNDERSCAN,
+	HDMI_SCAN_MODE_RESERVED,
 };
 
 enum hdmi_colorimetry {
@@ -71,6 +77,7 @@ enum hdmi_picture_aspect {
 	HDMI_PICTURE_ASPECT_NONE,
 	HDMI_PICTURE_ASPECT_4_3,
 	HDMI_PICTURE_ASPECT_16_9,
+	HDMI_PICTURE_ASPECT_RESERVED,
 };
 
 enum hdmi_active_aspect {
@@ -92,12 +99,18 @@ enum hdmi_extended_colorimetry {
 	HDMI_EXTENDED_COLORIMETRY_S_YCC_601,
 	HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601,
 	HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB,
+
+	/* The following EC values are only defined in CEA-861-F. */
+	HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM,
+	HDMI_EXTENDED_COLORIMETRY_BT2020,
+	HDMI_EXTENDED_COLORIMETRY_RESERVED,
 };
 
 enum hdmi_quantization_range {
 	HDMI_QUANTIZATION_RANGE_DEFAULT,
 	HDMI_QUANTIZATION_RANGE_LIMITED,
 	HDMI_QUANTIZATION_RANGE_FULL,
+	HDMI_QUANTIZATION_RANGE_RESERVED,
 };
 
 /* non-uniform picture scaling */
@@ -114,7 +127,7 @@ enum hdmi_ycc_quantization_range {
 };
 
 enum hdmi_content_type {
-	HDMI_CONTENT_TYPE_NONE,
+	HDMI_CONTENT_TYPE_GRAPHICS,
 	HDMI_CONTENT_TYPE_PHOTO,
 	HDMI_CONTENT_TYPE_CINEMA,
 	HDMI_CONTENT_TYPE_GAME,
@@ -194,6 +207,7 @@ enum hdmi_audio_coding_type {
 	HDMI_AUDIO_CODING_TYPE_MLP,
 	HDMI_AUDIO_CODING_TYPE_DST,
 	HDMI_AUDIO_CODING_TYPE_WMA_PRO,
+	HDMI_AUDIO_CODING_TYPE_CXT,
 };
 
 enum hdmi_audio_sample_size {
@@ -216,9 +230,23 @@ enum hdmi_audio_sample_frequency {
 
 enum hdmi_audio_coding_type_ext {
 	HDMI_AUDIO_CODING_TYPE_EXT_STREAM,
+
+	/*
+	 * The next three CXT values are defined in CEA-861-E only.
+	 * They do not exist in older versions, and in CEA-861-F they are
+	 * defined as 'Not in use'.
+	 */
 	HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC,
 	HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC_V2,
 	HDMI_AUDIO_CODING_TYPE_EXT_MPEG_SURROUND,
+
+	/* The following CXT values are only defined in CEA-861-F. */
+	HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC,
+	HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_V2,
+	HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC,
+	HDMI_AUDIO_CODING_TYPE_EXT_DRA,
+	HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_SURROUND,
+	HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC_SURROUND = 10,
 };
 
 struct hdmi_audio_infoframe {
-- 
cgit v1.2.3-70-g09d2


From 2c676f378edb16cb68f7815581c8119fc43a4b85 Mon Sep 17 00:00:00 2001
From: Martin Bugge <marbugge@cisco.com>
Date: Fri, 19 Dec 2014 09:14:21 -0300
Subject: [media] hdmi: added unpack and logging functions for InfoFrames

When receiving video it is very useful to be able to unpack the InfoFrames.
Logging is useful as well, both for transmitters and receivers.

Especially when implementing the VIDIOC_LOG_STATUS ioctl (supported by many
V4L2 drivers) for a receiver it is important to be able to easily log what
the InfoFrame contains. This greatly simplifies debugging.

Signed-off-by: Martin Bugge <marbugge@cisco.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/video/hdmi.c | 822 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/hdmi.h |   4 +
 2 files changed, 819 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c
index 9e758a8f890..a7c6ae4e10e 100644
--- a/drivers/video/hdmi.c
+++ b/drivers/video/hdmi.c
@@ -27,10 +27,12 @@
 #include <linux/export.h>
 #include <linux/hdmi.h>
 #include <linux/string.h>
+#include <linux/device.h>
 
-static void hdmi_infoframe_checksum(void *buffer, size_t size)
+#define hdmi_log(fmt, ...) dev_printk(level, dev, fmt, ##__VA_ARGS__)
+
+static u8 hdmi_infoframe_checksum(u8 *ptr, size_t size)
 {
-	u8 *ptr = buffer;
 	u8 csum = 0;
 	size_t i;
 
@@ -38,7 +40,14 @@ static void hdmi_infoframe_checksum(void *buffer, size_t size)
 	for (i = 0; i < size; i++)
 		csum += ptr[i];
 
-	ptr[3] = 256 - csum;
+	return 256 - csum;
+}
+
+static void hdmi_infoframe_set_checksum(void *buffer, size_t size)
+{
+	u8 *ptr = buffer;
+
+	ptr[3] = hdmi_infoframe_checksum(buffer, size);
 }
 
 /**
@@ -136,7 +145,7 @@ ssize_t hdmi_avi_infoframe_pack(struct hdmi_avi_infoframe *frame, void *buffer,
 	ptr[11] = frame->right_bar & 0xff;
 	ptr[12] = (frame->right_bar >> 8) & 0xff;
 
-	hdmi_infoframe_checksum(buffer, length);
+	hdmi_infoframe_set_checksum(buffer, length);
 
 	return length;
 }
@@ -206,7 +215,7 @@ ssize_t hdmi_spd_infoframe_pack(struct hdmi_spd_infoframe *frame, void *buffer,
 
 	ptr[24] = frame->sdi;
 
-	hdmi_infoframe_checksum(buffer, length);
+	hdmi_infoframe_set_checksum(buffer, length);
 
 	return length;
 }
@@ -281,7 +290,7 @@ ssize_t hdmi_audio_infoframe_pack(struct hdmi_audio_infoframe *frame,
 	if (frame->downmix_inhibit)
 		ptr[4] |= BIT(7);
 
-	hdmi_infoframe_checksum(buffer, length);
+	hdmi_infoframe_set_checksum(buffer, length);
 
 	return length;
 }
@@ -373,7 +382,7 @@ ssize_t hdmi_vendor_infoframe_pack(struct hdmi_vendor_infoframe *frame,
 			ptr[9] = (frame->s3d_ext_data & 0xf) << 4;
 	}
 
-	hdmi_infoframe_checksum(buffer, length);
+	hdmi_infoframe_set_checksum(buffer, length);
 
 	return length;
 }
@@ -434,3 +443,802 @@ hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size)
 	return length;
 }
 EXPORT_SYMBOL(hdmi_infoframe_pack);
+
+static const char *hdmi_infoframe_type_get_name(enum hdmi_infoframe_type type)
+{
+	if (type < 0x80 || type > 0x9f)
+		return "Invalid";
+	switch (type) {
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		return "Vendor";
+	case HDMI_INFOFRAME_TYPE_AVI:
+		return "Auxiliary Video Information (AVI)";
+	case HDMI_INFOFRAME_TYPE_SPD:
+		return "Source Product Description (SPD)";
+	case HDMI_INFOFRAME_TYPE_AUDIO:
+		return "Audio";
+	}
+	return "Reserved";
+}
+
+static void hdmi_infoframe_log_header(const char *level,
+				      struct device *dev,
+				      struct hdmi_any_infoframe *frame)
+{
+	hdmi_log("HDMI infoframe: %s, version %u, length %u\n",
+		hdmi_infoframe_type_get_name(frame->type),
+		frame->version, frame->length);
+}
+
+static const char *hdmi_colorspace_get_name(enum hdmi_colorspace colorspace)
+{
+	switch (colorspace) {
+	case HDMI_COLORSPACE_RGB:
+		return "RGB";
+	case HDMI_COLORSPACE_YUV422:
+		return "YCbCr 4:2:2";
+	case HDMI_COLORSPACE_YUV444:
+		return "YCbCr 4:4:4";
+	case HDMI_COLORSPACE_YUV420:
+		return "YCbCr 4:2:0";
+	case HDMI_COLORSPACE_RESERVED4:
+		return "Reserved (4)";
+	case HDMI_COLORSPACE_RESERVED5:
+		return "Reserved (5)";
+	case HDMI_COLORSPACE_RESERVED6:
+		return "Reserved (6)";
+	case HDMI_COLORSPACE_IDO_DEFINED:
+		return "IDO Defined";
+	}
+	return "Invalid";
+}
+
+static const char *hdmi_scan_mode_get_name(enum hdmi_scan_mode scan_mode)
+{
+	switch (scan_mode) {
+	case HDMI_SCAN_MODE_NONE:
+		return "No Data";
+	case HDMI_SCAN_MODE_OVERSCAN:
+		return "Overscan";
+	case HDMI_SCAN_MODE_UNDERSCAN:
+		return "Underscan";
+	case HDMI_SCAN_MODE_RESERVED:
+		return "Reserved";
+	}
+	return "Invalid";
+}
+
+static const char *hdmi_colorimetry_get_name(enum hdmi_colorimetry colorimetry)
+{
+	switch (colorimetry) {
+	case HDMI_COLORIMETRY_NONE:
+		return "No Data";
+	case HDMI_COLORIMETRY_ITU_601:
+		return "ITU601";
+	case HDMI_COLORIMETRY_ITU_709:
+		return "ITU709";
+	case HDMI_COLORIMETRY_EXTENDED:
+		return "Extended";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_picture_aspect_get_name(enum hdmi_picture_aspect picture_aspect)
+{
+	switch (picture_aspect) {
+	case HDMI_PICTURE_ASPECT_NONE:
+		return "No Data";
+	case HDMI_PICTURE_ASPECT_4_3:
+		return "4:3";
+	case HDMI_PICTURE_ASPECT_16_9:
+		return "16:9";
+	case HDMI_PICTURE_ASPECT_RESERVED:
+		return "Reserved";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_active_aspect_get_name(enum hdmi_active_aspect active_aspect)
+{
+	if (active_aspect < 0 || active_aspect > 0xf)
+		return "Invalid";
+
+	switch (active_aspect) {
+	case HDMI_ACTIVE_ASPECT_16_9_TOP:
+		return "16:9 Top";
+	case HDMI_ACTIVE_ASPECT_14_9_TOP:
+		return "14:9 Top";
+	case HDMI_ACTIVE_ASPECT_16_9_CENTER:
+		return "16:9 Center";
+	case HDMI_ACTIVE_ASPECT_PICTURE:
+		return "Same as Picture";
+	case HDMI_ACTIVE_ASPECT_4_3:
+		return "4:3";
+	case HDMI_ACTIVE_ASPECT_16_9:
+		return "16:9";
+	case HDMI_ACTIVE_ASPECT_14_9:
+		return "14:9";
+	case HDMI_ACTIVE_ASPECT_4_3_SP_14_9:
+		return "4:3 SP 14:9";
+	case HDMI_ACTIVE_ASPECT_16_9_SP_14_9:
+		return "16:9 SP 14:9";
+	case HDMI_ACTIVE_ASPECT_16_9_SP_4_3:
+		return "16:9 SP 4:3";
+	}
+	return "Reserved";
+}
+
+static const char *
+hdmi_extended_colorimetry_get_name(enum hdmi_extended_colorimetry ext_col)
+{
+	switch (ext_col) {
+	case HDMI_EXTENDED_COLORIMETRY_XV_YCC_601:
+		return "xvYCC 601";
+	case HDMI_EXTENDED_COLORIMETRY_XV_YCC_709:
+		return "xvYCC 709";
+	case HDMI_EXTENDED_COLORIMETRY_S_YCC_601:
+		return "sYCC 601";
+	case HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601:
+		return "Adobe YCC 601";
+	case HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB:
+		return "Adobe RGB";
+	case HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM:
+		return "BT.2020 Constant Luminance";
+	case HDMI_EXTENDED_COLORIMETRY_BT2020:
+		return "BT.2020";
+	case HDMI_EXTENDED_COLORIMETRY_RESERVED:
+		return "Reserved";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_quantization_range_get_name(enum hdmi_quantization_range qrange)
+{
+	switch (qrange) {
+	case HDMI_QUANTIZATION_RANGE_DEFAULT:
+		return "Default";
+	case HDMI_QUANTIZATION_RANGE_LIMITED:
+		return "Limited";
+	case HDMI_QUANTIZATION_RANGE_FULL:
+		return "Full";
+	case HDMI_QUANTIZATION_RANGE_RESERVED:
+		return "Reserved";
+	}
+	return "Invalid";
+}
+
+static const char *hdmi_nups_get_name(enum hdmi_nups nups)
+{
+	switch (nups) {
+	case HDMI_NUPS_UNKNOWN:
+		return "Unknown Non-uniform Scaling";
+	case HDMI_NUPS_HORIZONTAL:
+		return "Horizontally Scaled";
+	case HDMI_NUPS_VERTICAL:
+		return "Vertically Scaled";
+	case HDMI_NUPS_BOTH:
+		return "Horizontally and Vertically Scaled";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_ycc_quantization_range_get_name(enum hdmi_ycc_quantization_range qrange)
+{
+	switch (qrange) {
+	case HDMI_YCC_QUANTIZATION_RANGE_LIMITED:
+		return "Limited";
+	case HDMI_YCC_QUANTIZATION_RANGE_FULL:
+		return "Full";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_content_type_get_name(enum hdmi_content_type content_type)
+{
+	switch (content_type) {
+	case HDMI_CONTENT_TYPE_GRAPHICS:
+		return "Graphics";
+	case HDMI_CONTENT_TYPE_PHOTO:
+		return "Photo";
+	case HDMI_CONTENT_TYPE_CINEMA:
+		return "Cinema";
+	case HDMI_CONTENT_TYPE_GAME:
+		return "Game";
+	}
+	return "Invalid";
+}
+
+/**
+ * hdmi_avi_infoframe_log() - log info of HDMI AVI infoframe
+ * @level: logging level
+ * @dev: device
+ * @frame: HDMI AVI infoframe
+ */
+static void hdmi_avi_infoframe_log(const char *level,
+				   struct device *dev,
+				   struct hdmi_avi_infoframe *frame)
+{
+	hdmi_infoframe_log_header(level, dev,
+				  (struct hdmi_any_infoframe *)frame);
+
+	hdmi_log("    colorspace: %s\n",
+			hdmi_colorspace_get_name(frame->colorspace));
+	hdmi_log("    scan mode: %s\n",
+			hdmi_scan_mode_get_name(frame->scan_mode));
+	hdmi_log("    colorimetry: %s\n",
+			hdmi_colorimetry_get_name(frame->colorimetry));
+	hdmi_log("    picture aspect: %s\n",
+			hdmi_picture_aspect_get_name(frame->picture_aspect));
+	hdmi_log("    active aspect: %s\n",
+			hdmi_active_aspect_get_name(frame->active_aspect));
+	hdmi_log("    itc: %s\n", frame->itc ? "IT Content" : "No Data");
+	hdmi_log("    extended colorimetry: %s\n",
+			hdmi_extended_colorimetry_get_name(frame->extended_colorimetry));
+	hdmi_log("    quantization range: %s\n",
+			hdmi_quantization_range_get_name(frame->quantization_range));
+	hdmi_log("    nups: %s\n", hdmi_nups_get_name(frame->nups));
+	hdmi_log("    video code: %u\n", frame->video_code);
+	hdmi_log("    ycc quantization range: %s\n",
+			hdmi_ycc_quantization_range_get_name(frame->ycc_quantization_range));
+	hdmi_log("    hdmi content type: %s\n",
+			hdmi_content_type_get_name(frame->content_type));
+	hdmi_log("    pixel repeat: %u\n", frame->pixel_repeat);
+	hdmi_log("    bar top %u, bottom %u, left %u, right %u\n",
+			frame->top_bar, frame->bottom_bar,
+			frame->left_bar, frame->right_bar);
+}
+
+static const char *hdmi_spd_sdi_get_name(enum hdmi_spd_sdi sdi)
+{
+	if (sdi < 0 || sdi > 0xff)
+		return "Invalid";
+	switch (sdi) {
+	case HDMI_SPD_SDI_UNKNOWN:
+		return "Unknown";
+	case HDMI_SPD_SDI_DSTB:
+		return "Digital STB";
+	case HDMI_SPD_SDI_DVDP:
+		return "DVD Player";
+	case HDMI_SPD_SDI_DVHS:
+		return "D-VHS";
+	case HDMI_SPD_SDI_HDDVR:
+		return "HDD Videorecorder";
+	case HDMI_SPD_SDI_DVC:
+		return "DVC";
+	case HDMI_SPD_SDI_DSC:
+		return "DSC";
+	case HDMI_SPD_SDI_VCD:
+		return "Video CD";
+	case HDMI_SPD_SDI_GAME:
+		return "Game";
+	case HDMI_SPD_SDI_PC:
+		return "PC General";
+	case HDMI_SPD_SDI_BD:
+		return "Blu-Ray Disc (BD)";
+	case HDMI_SPD_SDI_SACD:
+		return "Super Audio CD";
+	case HDMI_SPD_SDI_HDDVD:
+		return "HD DVD";
+	case HDMI_SPD_SDI_PMP:
+		return "PMP";
+	}
+	return "Reserved";
+}
+
+/**
+ * hdmi_spd_infoframe_log() - log info of HDMI SPD infoframe
+ * @level: logging level
+ * @dev: device
+ * @frame: HDMI SPD infoframe
+ */
+static void hdmi_spd_infoframe_log(const char *level,
+				   struct device *dev,
+				   struct hdmi_spd_infoframe *frame)
+{
+	u8 buf[17];
+
+	hdmi_infoframe_log_header(level, dev,
+				  (struct hdmi_any_infoframe *)frame);
+
+	memset(buf, 0, sizeof(buf));
+
+	strncpy(buf, frame->vendor, 8);
+	hdmi_log("    vendor: %s\n", buf);
+	strncpy(buf, frame->product, 16);
+	hdmi_log("    product: %s\n", buf);
+	hdmi_log("    source device information: %s (0x%x)\n",
+		hdmi_spd_sdi_get_name(frame->sdi), frame->sdi);
+}
+
+static const char *
+hdmi_audio_coding_type_get_name(enum hdmi_audio_coding_type coding_type)
+{
+	switch (coding_type) {
+	case HDMI_AUDIO_CODING_TYPE_STREAM:
+		return "Refer to Stream Header";
+	case HDMI_AUDIO_CODING_TYPE_PCM:
+		return "PCM";
+	case HDMI_AUDIO_CODING_TYPE_AC3:
+		return "AC-3";
+	case HDMI_AUDIO_CODING_TYPE_MPEG1:
+		return "MPEG1";
+	case HDMI_AUDIO_CODING_TYPE_MP3:
+		return "MP3";
+	case HDMI_AUDIO_CODING_TYPE_MPEG2:
+		return "MPEG2";
+	case HDMI_AUDIO_CODING_TYPE_AAC_LC:
+		return "AAC";
+	case HDMI_AUDIO_CODING_TYPE_DTS:
+		return "DTS";
+	case HDMI_AUDIO_CODING_TYPE_ATRAC:
+		return "ATRAC";
+	case HDMI_AUDIO_CODING_TYPE_DSD:
+		return "One Bit Audio";
+	case HDMI_AUDIO_CODING_TYPE_EAC3:
+		return "Dolby Digital +";
+	case HDMI_AUDIO_CODING_TYPE_DTS_HD:
+		return "DTS-HD";
+	case HDMI_AUDIO_CODING_TYPE_MLP:
+		return "MAT (MLP)";
+	case HDMI_AUDIO_CODING_TYPE_DST:
+		return "DST";
+	case HDMI_AUDIO_CODING_TYPE_WMA_PRO:
+		return "WMA PRO";
+	case HDMI_AUDIO_CODING_TYPE_CXT:
+		return "Refer to CXT";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_audio_sample_size_get_name(enum hdmi_audio_sample_size sample_size)
+{
+	switch (sample_size) {
+	case HDMI_AUDIO_SAMPLE_SIZE_STREAM:
+		return "Refer to Stream Header";
+	case HDMI_AUDIO_SAMPLE_SIZE_16:
+		return "16 bit";
+	case HDMI_AUDIO_SAMPLE_SIZE_20:
+		return "20 bit";
+	case HDMI_AUDIO_SAMPLE_SIZE_24:
+		return "24 bit";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_audio_sample_frequency_get_name(enum hdmi_audio_sample_frequency freq)
+{
+	switch (freq) {
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_STREAM:
+		return "Refer to Stream Header";
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_32000:
+		return "32 kHz";
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_44100:
+		return "44.1 kHz (CD)";
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_48000:
+		return "48 kHz";
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_88200:
+		return "88.2 kHz";
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_96000:
+		return "96 kHz";
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_176400:
+		return "176.4 kHz";
+	case HDMI_AUDIO_SAMPLE_FREQUENCY_192000:
+		return "192 kHz";
+	}
+	return "Invalid";
+}
+
+static const char *
+hdmi_audio_coding_type_ext_get_name(enum hdmi_audio_coding_type_ext ctx)
+{
+	if (ctx < 0 || ctx > 0x1f)
+		return "Invalid";
+
+	switch (ctx) {
+	case HDMI_AUDIO_CODING_TYPE_EXT_STREAM:
+		return "Refer to CT";
+	case HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC:
+		return "HE AAC";
+	case HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC_V2:
+		return "HE AAC v2";
+	case HDMI_AUDIO_CODING_TYPE_EXT_MPEG_SURROUND:
+		return "MPEG SURROUND";
+	case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC:
+		return "MPEG-4 HE AAC";
+	case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_V2:
+		return "MPEG-4 HE AAC v2";
+	case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC:
+		return "MPEG-4 AAC LC";
+	case HDMI_AUDIO_CODING_TYPE_EXT_DRA:
+		return "DRA";
+	case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_HE_AAC_SURROUND:
+		return "MPEG-4 HE AAC + MPEG Surround";
+	case HDMI_AUDIO_CODING_TYPE_EXT_MPEG4_AAC_LC_SURROUND:
+		return "MPEG-4 AAC LC + MPEG Surround";
+	}
+	return "Reserved";
+}
+
+/**
+ * hdmi_audio_infoframe_log() - log info of HDMI AUDIO infoframe
+ * @level: logging level
+ * @dev: device
+ * @frame: HDMI AUDIO infoframe
+ */
+static void hdmi_audio_infoframe_log(const char *level,
+				     struct device *dev,
+				     struct hdmi_audio_infoframe *frame)
+{
+	hdmi_infoframe_log_header(level, dev,
+				  (struct hdmi_any_infoframe *)frame);
+
+	if (frame->channels)
+		hdmi_log("    channels: %u\n", frame->channels - 1);
+	else
+		hdmi_log("    channels: Refer to stream header\n");
+	hdmi_log("    coding type: %s\n",
+			hdmi_audio_coding_type_get_name(frame->coding_type));
+	hdmi_log("    sample size: %s\n",
+			hdmi_audio_sample_size_get_name(frame->sample_size));
+	hdmi_log("    sample frequency: %s\n",
+			hdmi_audio_sample_frequency_get_name(frame->sample_frequency));
+	hdmi_log("    coding type ext: %s\n",
+			hdmi_audio_coding_type_ext_get_name(frame->coding_type_ext));
+	hdmi_log("    channel allocation: 0x%x\n",
+			frame->channel_allocation);
+	hdmi_log("    level shift value: %u dB\n",
+			frame->level_shift_value);
+	hdmi_log("    downmix inhibit: %s\n",
+			frame->downmix_inhibit ? "Yes" : "No");
+}
+
+static const char *
+hdmi_3d_structure_get_name(enum hdmi_3d_structure s3d_struct)
+{
+	if (s3d_struct < 0 || s3d_struct > 0xf)
+		return "Invalid";
+
+	switch (s3d_struct) {
+	case HDMI_3D_STRUCTURE_FRAME_PACKING:
+		return "Frame Packing";
+	case HDMI_3D_STRUCTURE_FIELD_ALTERNATIVE:
+		return "Field Alternative";
+	case HDMI_3D_STRUCTURE_LINE_ALTERNATIVE:
+		return "Line Alternative";
+	case HDMI_3D_STRUCTURE_SIDE_BY_SIDE_FULL:
+		return "Side-by-side (Full)";
+	case HDMI_3D_STRUCTURE_L_DEPTH:
+		return "L + Depth";
+	case HDMI_3D_STRUCTURE_L_DEPTH_GFX_GFX_DEPTH:
+		return "L + Depth + Graphics + Graphics-depth";
+	case HDMI_3D_STRUCTURE_TOP_AND_BOTTOM:
+		return "Top-and-Bottom";
+	case HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF:
+		return "Side-by-side (Half)";
+	default:
+		break;
+	}
+	return "Reserved";
+}
+
+/**
+ * hdmi_vendor_infoframe_log() - log info of HDMI VENDOR infoframe
+ * @level: logging level
+ * @dev: device
+ * @frame: HDMI VENDOR infoframe
+ */
+static void
+hdmi_vendor_any_infoframe_log(const char *level,
+			      struct device *dev,
+			      union hdmi_vendor_any_infoframe *frame)
+{
+	struct hdmi_vendor_infoframe *hvf = &frame->hdmi;
+
+	hdmi_infoframe_log_header(level, dev,
+				  (struct hdmi_any_infoframe *)frame);
+
+	if (frame->any.oui != HDMI_IEEE_OUI) {
+		hdmi_log("    not a HDMI vendor infoframe\n");
+		return;
+	}
+	if (hvf->vic == 0 && hvf->s3d_struct == HDMI_3D_STRUCTURE_INVALID) {
+		hdmi_log("    empty frame\n");
+		return;
+	}
+
+	if (hvf->vic)
+		hdmi_log("    HDMI VIC: %u\n", hvf->vic);
+	if (hvf->s3d_struct != HDMI_3D_STRUCTURE_INVALID) {
+		hdmi_log("    3D structure: %s\n",
+				hdmi_3d_structure_get_name(hvf->s3d_struct));
+		if (hvf->s3d_struct >= HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF)
+			hdmi_log("    3D extension data: %d\n",
+					hvf->s3d_ext_data);
+	}
+}
+
+/**
+ * hdmi_infoframe_log() - log info of HDMI infoframe
+ * @level: logging level
+ * @dev: device
+ * @frame: HDMI infoframe
+ */
+void hdmi_infoframe_log(const char *level,
+			struct device *dev,
+			union hdmi_infoframe *frame)
+{
+	switch (frame->any.type) {
+	case HDMI_INFOFRAME_TYPE_AVI:
+		hdmi_avi_infoframe_log(level, dev, &frame->avi);
+		break;
+	case HDMI_INFOFRAME_TYPE_SPD:
+		hdmi_spd_infoframe_log(level, dev, &frame->spd);
+		break;
+	case HDMI_INFOFRAME_TYPE_AUDIO:
+		hdmi_audio_infoframe_log(level, dev, &frame->audio);
+		break;
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		hdmi_vendor_any_infoframe_log(level, dev, &frame->vendor);
+		break;
+	}
+}
+EXPORT_SYMBOL(hdmi_infoframe_log);
+
+/**
+ * hdmi_avi_infoframe_unpack() - unpack binary buffer to a HDMI AVI infoframe
+ * @buffer: source buffer
+ * @frame: HDMI AVI infoframe
+ *
+ * Unpacks the information contained in binary @buffer into a structured
+ * @frame of the HDMI Auxiliary Video (AVI) information frame.
+ * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4
+ * specification.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+static int hdmi_avi_infoframe_unpack(struct hdmi_avi_infoframe *frame,
+				     void *buffer)
+{
+	u8 *ptr = buffer;
+	int ret;
+
+	if (ptr[0] != HDMI_INFOFRAME_TYPE_AVI ||
+	    ptr[1] != 2 ||
+	    ptr[2] != HDMI_AVI_INFOFRAME_SIZE)
+		return -EINVAL;
+
+	if (hdmi_infoframe_checksum(buffer, HDMI_INFOFRAME_SIZE(AVI)) != 0)
+		return -EINVAL;
+
+	ret = hdmi_avi_infoframe_init(frame);
+	if (ret)
+		return ret;
+
+	ptr += HDMI_INFOFRAME_HEADER_SIZE;
+
+	frame->colorspace = (ptr[0] >> 5) & 0x3;
+	if (ptr[0] & 0x10)
+		frame->active_aspect = ptr[1] & 0xf;
+	if (ptr[0] & 0x8) {
+		frame->top_bar = (ptr[5] << 8) + ptr[6];
+		frame->bottom_bar = (ptr[7] << 8) + ptr[8];
+	}
+	if (ptr[0] & 0x4) {
+		frame->left_bar = (ptr[9] << 8) + ptr[10];
+		frame->right_bar = (ptr[11] << 8) + ptr[12];
+	}
+	frame->scan_mode = ptr[0] & 0x3;
+
+	frame->colorimetry = (ptr[1] >> 6) & 0x3;
+	frame->picture_aspect = (ptr[1] >> 4) & 0x3;
+	frame->active_aspect = ptr[1] & 0xf;
+
+	frame->itc = ptr[2] & 0x80 ? true : false;
+	frame->extended_colorimetry = (ptr[2] >> 4) & 0x7;
+	frame->quantization_range = (ptr[2] >> 2) & 0x3;
+	frame->nups = ptr[2] & 0x3;
+
+	frame->video_code = ptr[3] & 0x7f;
+	frame->ycc_quantization_range = (ptr[4] >> 6) & 0x3;
+	frame->content_type = (ptr[4] >> 4) & 0x3;
+
+	frame->pixel_repeat = ptr[4] & 0xf;
+
+	return 0;
+}
+
+/**
+ * hdmi_spd_infoframe_unpack() - unpack binary buffer to a HDMI SPD infoframe
+ * @buffer: source buffer
+ * @frame: HDMI SPD infoframe
+ *
+ * Unpacks the information contained in binary @buffer into a structured
+ * @frame of the HDMI Source Product Description (SPD) information frame.
+ * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4
+ * specification.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+static int hdmi_spd_infoframe_unpack(struct hdmi_spd_infoframe *frame,
+				     void *buffer)
+{
+	u8 *ptr = buffer;
+	int ret;
+
+	if (ptr[0] != HDMI_INFOFRAME_TYPE_SPD ||
+	    ptr[1] != 1 ||
+	    ptr[2] != HDMI_SPD_INFOFRAME_SIZE) {
+		return -EINVAL;
+	}
+
+	if (hdmi_infoframe_checksum(buffer, HDMI_INFOFRAME_SIZE(SPD)) != 0)
+		return -EINVAL;
+
+	ptr += HDMI_INFOFRAME_HEADER_SIZE;
+
+	ret = hdmi_spd_infoframe_init(frame, ptr, ptr + 8);
+	if (ret)
+		return ret;
+
+	frame->sdi = ptr[24];
+
+	return 0;
+}
+
+/**
+ * hdmi_audio_infoframe_unpack() - unpack binary buffer to a HDMI AUDIO infoframe
+ * @buffer: source buffer
+ * @frame: HDMI Audio infoframe
+ *
+ * Unpacks the information contained in binary @buffer into a structured
+ * @frame of the HDMI Audio information frame.
+ * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4
+ * specification.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+static int hdmi_audio_infoframe_unpack(struct hdmi_audio_infoframe *frame,
+				       void *buffer)
+{
+	u8 *ptr = buffer;
+	int ret;
+
+	if (ptr[0] != HDMI_INFOFRAME_TYPE_AUDIO ||
+	    ptr[1] != 1 ||
+	    ptr[2] != HDMI_AUDIO_INFOFRAME_SIZE) {
+		return -EINVAL;
+	}
+
+	if (hdmi_infoframe_checksum(buffer, HDMI_INFOFRAME_SIZE(AUDIO)) != 0)
+		return -EINVAL;
+
+	ret = hdmi_audio_infoframe_init(frame);
+	if (ret)
+		return ret;
+
+	ptr += HDMI_INFOFRAME_HEADER_SIZE;
+
+	frame->channels = ptr[0] & 0x7;
+	frame->coding_type = (ptr[0] >> 4) & 0xf;
+	frame->sample_size = ptr[1] & 0x3;
+	frame->sample_frequency = (ptr[1] >> 2) & 0x7;
+	frame->coding_type_ext = ptr[2] & 0x1f;
+	frame->channel_allocation = ptr[3];
+	frame->level_shift_value = (ptr[4] >> 3) & 0xf;
+	frame->downmix_inhibit = ptr[4] & 0x80 ? true : false;
+
+	return 0;
+}
+
+/**
+ * hdmi_vendor_infoframe_unpack() - unpack binary buffer to a HDMI vendor infoframe
+ * @buffer: source buffer
+ * @frame: HDMI Vendor infoframe
+ *
+ * Unpacks the information contained in binary @buffer into a structured
+ * @frame of the HDMI Vendor information frame.
+ * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4
+ * specification.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+static int
+hdmi_vendor_any_infoframe_unpack(union hdmi_vendor_any_infoframe *frame,
+				 void *buffer)
+{
+	u8 *ptr = buffer;
+	size_t length;
+	int ret;
+	u8 hdmi_video_format;
+	struct hdmi_vendor_infoframe *hvf = &frame->hdmi;
+
+	if (ptr[0] != HDMI_INFOFRAME_TYPE_VENDOR ||
+	    ptr[1] != 1 ||
+	    (ptr[2] != 5 && ptr[2] != 6))
+		return -EINVAL;
+
+	length = ptr[2];
+
+	if (hdmi_infoframe_checksum(buffer,
+				    HDMI_INFOFRAME_HEADER_SIZE + length) != 0)
+		return -EINVAL;
+
+	ptr += HDMI_INFOFRAME_HEADER_SIZE;
+
+	/* HDMI OUI */
+	if ((ptr[0] != 0x03) ||
+	    (ptr[1] != 0x0c) ||
+	    (ptr[2] != 0x00))
+		return -EINVAL;
+
+	hdmi_video_format = ptr[3] >> 5;
+
+	if (hdmi_video_format > 0x2)
+		return -EINVAL;
+
+	ret = hdmi_vendor_infoframe_init(hvf);
+	if (ret)
+		return ret;
+
+	hvf->length = length;
+
+	if (hdmi_video_format == 0x1) {
+		hvf->vic = ptr[4];
+	} else if (hdmi_video_format == 0x2) {
+		hvf->s3d_struct = ptr[4] >> 4;
+		if (hvf->s3d_struct >= HDMI_3D_STRUCTURE_SIDE_BY_SIDE_HALF) {
+			if (length == 6)
+				hvf->s3d_ext_data = ptr[5] >> 4;
+			else
+				return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * hdmi_infoframe_unpack() - unpack binary buffer to a HDMI infoframe
+ * @buffer: source buffer
+ * @frame: HDMI infoframe
+ *
+ * Unpacks the information contained in binary buffer @buffer into a structured
+ * @frame of a HDMI infoframe.
+ * Also verifies the checksum as required by section 5.3.5 of the HDMI 1.4
+ * specification.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int hdmi_infoframe_unpack(union hdmi_infoframe *frame, void *buffer)
+{
+	int ret;
+	u8 *ptr = buffer;
+
+	switch (ptr[0]) {
+	case HDMI_INFOFRAME_TYPE_AVI:
+		ret = hdmi_avi_infoframe_unpack(&frame->avi, buffer);
+		break;
+	case HDMI_INFOFRAME_TYPE_SPD:
+		ret = hdmi_spd_infoframe_unpack(&frame->spd, buffer);
+		break;
+	case HDMI_INFOFRAME_TYPE_AUDIO:
+		ret = hdmi_audio_infoframe_unpack(&frame->audio, buffer);
+		break;
+	case HDMI_INFOFRAME_TYPE_VENDOR:
+		ret = hdmi_vendor_any_infoframe_unpack(&frame->vendor, buffer);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(hdmi_infoframe_unpack);
diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index 5afc0bff2bb..2ff34315a1b 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -25,6 +25,7 @@
 #define __LINUX_HDMI_H_
 
 #include <linux/types.h>
+#include <linux/device.h>
 
 enum hdmi_infoframe_type {
 	HDMI_INFOFRAME_TYPE_VENDOR = 0x81,
@@ -327,5 +328,8 @@ union hdmi_infoframe {
 
 ssize_t
 hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer, size_t size);
+int hdmi_infoframe_unpack(union hdmi_infoframe *frame, void *buffer);
+void hdmi_infoframe_log(const char *level, struct device *dev,
+			union hdmi_infoframe *frame);
 
 #endif /* _DRM_HDMI_H */
-- 
cgit v1.2.3-70-g09d2


From dc189053e1a5ae606c56e432dae1afc28261a819 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Fri, 19 Dec 2014 09:14:22 -0300
Subject: [media] hdmi: rename HDMI_AUDIO_CODING_TYPE_EXT_STREAM to _EXT_CT

As per the suggestion of Thierry Reding rename
HDMI_AUDIO_CODING_TYPE_EXT_STREAM to HDMI_AUDIO_CODING_TYPE_EXT_CT to
be consistent with the CEA-861 spec.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/video/hdmi.c | 2 +-
 include/linux/hdmi.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c
index a7c6ae4e10e..162689227a2 100644
--- a/drivers/video/hdmi.c
+++ b/drivers/video/hdmi.c
@@ -842,7 +842,7 @@ hdmi_audio_coding_type_ext_get_name(enum hdmi_audio_coding_type_ext ctx)
 		return "Invalid";
 
 	switch (ctx) {
-	case HDMI_AUDIO_CODING_TYPE_EXT_STREAM:
+	case HDMI_AUDIO_CODING_TYPE_EXT_CT:
 		return "Refer to CT";
 	case HDMI_AUDIO_CODING_TYPE_EXT_HE_AAC:
 		return "HE AAC";
diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index 2ff34315a1b..e9744202fa2 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -230,7 +230,8 @@ enum hdmi_audio_sample_frequency {
 };
 
 enum hdmi_audio_coding_type_ext {
-	HDMI_AUDIO_CODING_TYPE_EXT_STREAM,
+	/* Refer to Audio Coding Type (CT) field in Data Byte 1 */
+	HDMI_AUDIO_CODING_TYPE_EXT_CT,
 
 	/*
 	 * The next three CXT values are defined in CEA-861-E only.
-- 
cgit v1.2.3-70-g09d2


From f27b37f5993a080700ccecdce9960d1563eccd36 Mon Sep 17 00:00:00 2001
From: Bintian Wang <bintian.wang@huawei.com>
Date: Tue, 27 Jan 2015 20:50:29 +0800
Subject: regmap: correct the description of structure element in reg_field

Fix incorrect description of structure element "msb", which is
described as "reg".

Signed-off-by: Bintian Wang <bintian.wang@huawei.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regmap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4419b99d8d6..116655d9226 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -468,7 +468,7 @@ bool regmap_reg_in_ranges(unsigned int reg,
  *
  * @reg: Offset of the register within the regmap bank
  * @lsb: lsb of the register field.
- * @reg: msb of the register field.
+ * @msb: msb of the register field.
  * @id_size: port size if it has some ports
  * @id_offset: address offset for each ports
  */
-- 
cgit v1.2.3-70-g09d2


From 5929b8a38ce02b7769e8b79605a8690f442a2933 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Mon, 26 Jan 2015 18:05:22 +0100
Subject: PCI: Add defines for PCIe Max_Read_Request_Size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are a few drivers using magic numbers when operating with PCIe
capabilities and PCI_EXP_DEVCTL_READRQ.  Define known values to allow
cleaning their code a bit.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/uapi/linux/pci_regs.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 4a1d0cc38ff..efe3443572b 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -451,6 +451,10 @@
 #define  PCI_EXP_DEVCTL_AUX_PME	0x0400	/* Auxiliary Power PM Enable */
 #define  PCI_EXP_DEVCTL_NOSNOOP_EN 0x0800  /* Enable No Snoop */
 #define  PCI_EXP_DEVCTL_READRQ	0x7000	/* Max_Read_Request_Size */
+#define  PCI_EXP_DEVCTL_READRQ_128B  0x0000 /* 128 Bytes */
+#define  PCI_EXP_DEVCTL_READRQ_256B  0x1000 /* 256 Bytes */
+#define  PCI_EXP_DEVCTL_READRQ_512B  0x2000 /* 512 Bytes */
+#define  PCI_EXP_DEVCTL_READRQ_1024B 0x3000 /* 1024 Bytes */
 #define  PCI_EXP_DEVCTL_BCR_FLR 0x8000  /* Bridge Configuration Retry / FLR */
 #define PCI_EXP_DEVSTA		10	/* Device Status */
 #define  PCI_EXP_DEVSTA_CED	0x0001	/* Correctable Error Detected */
-- 
cgit v1.2.3-70-g09d2


From f04b1e760a51120f358826d815d12c3f8ecdf1b4 Mon Sep 17 00:00:00 2001
From: Thomas Niederprüm <niederp@physik.uni-kl.de>
Date: Thu, 22 Jan 2015 00:01:58 +0100
Subject: ASoC: sta32x: add device tree binding.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

make the sta32x driver usable with device tree configs.  Code is heavily based
on the sta350 driver.

Signed-off-by: Thomas Niederprüm <niederp@physik.uni-kl.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/st,sta32x.txt        |  92 ++++++++++++++++++
 include/sound/sta32x.h                             |  18 +++-
 sound/soc/codecs/sta32x.c                          | 108 ++++++++++++++++++++-
 3 files changed, 211 insertions(+), 7 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/sound/st,sta32x.txt

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/sound/st,sta32x.txt b/Documentation/devicetree/bindings/sound/st,sta32x.txt
new file mode 100644
index 00000000000..255de3ae5b2
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/st,sta32x.txt
@@ -0,0 +1,92 @@
+STA32X audio CODEC
+
+The driver for this device only supports I2C.
+
+Required properties:
+
+  - compatible: "st,sta32x"
+  - reg: the I2C address of the device for I2C
+  - reset-gpios: a GPIO spec for the reset pin. If specified, it will be
+		 deasserted before communication to the codec starts.
+
+  - power-down-gpios: a GPIO spec for the power down pin. If specified,
+		      it will be deasserted before communication to the codec
+		      starts.
+
+  - Vdda-supply: regulator spec, providing 3.3V
+  - Vdd3-supply: regulator spec, providing 3.3V
+  - Vcc-supply: regulator spec, providing 5V - 26V
+
+Optional properties:
+
+  -  st,output-conf: number, Selects the output configuration:
+	0: 2-channel (full-bridge) power, 2-channel data-out
+	1: 2 (half-bridge). 1 (full-bridge) on-board power
+	2: 2 Channel (Full-Bridge) Power, 1 Channel FFX
+	3: 1 Channel Mono-Parallel
+	If parameter is missing, mode 0 will be enabled.
+	This property has to be specified as '/bits/ 8' value.
+
+  -  st,ch1-output-mapping: Channel 1 output mapping
+  -  st,ch2-output-mapping: Channel 2 output mapping
+  -  st,ch3-output-mapping: Channel 3 output mapping
+	0: Channel 1
+	1: Channel 2
+	2: Channel 3
+	If parameter is missing, channel 1 is chosen.
+	This properties have to be specified as '/bits/ 8' values.
+
+  -  st,thermal-warning-recover:
+	If present, thermal warning recovery is enabled.
+
+  -  st,thermal-warning-adjustment:
+	If present, thermal warning adjustment is enabled.
+
+  -  st,fault-detect-recovery:
+	If present, then fault recovery will be enabled.
+
+  -  st,drop-compensation-ns: number
+	Only required for "st,ffx-power-output-mode" ==
+	"variable-drop-compensation".
+	Specifies the drop compensation in nanoseconds.
+	The value must be in the range of 0..300, and only
+	multiples of 20 are allowed. Default is 140ns.
+
+  -  st,max-power-use-mpcc:
+	If present, then MPCC bits are used for MPC coefficients,
+	otherwise standard MPC coefficients are used.
+
+  -  st,max-power-corr:
+	If present, power bridge correction for THD reduction near maximum
+	power output is enabled.
+
+  -  st,am-reduction-mode:
+	If present, FFX mode runs in AM reduction mode, otherwise normal
+	FFX mode is used.
+
+  -  st,odd-pwm-speed-mode:
+	If present, PWM speed mode run on odd speed mode (341.3 kHz) on all
+	channels. If not present, normal PWM spped mode (384 kHz) will be used.
+
+  -  st,invalid-input-detect-mute:
+	If present, automatic invalid input detect mute is enabled.
+
+Example:
+
+codec: sta32x@38 {
+	compatible = "st,sta32x";
+	reg = <0x1c>;
+	reset-gpios = <&gpio1 19 0>;
+	power-down-gpios = <&gpio1 16 0>;
+	st,output-conf = /bits/ 8  <0x3>;	// set output to 2-channel
+						// (full-bridge) power,
+						// 2-channel data-out
+	st,ch1-output-mapping = /bits/ 8 <0>;	// set channel 1 output ch 1
+	st,ch2-output-mapping = /bits/ 8 <0>;	// set channel 2 output ch 1
+	st,ch3-output-mapping = /bits/ 8 <0>;	// set channel 3 output ch 1
+	st,max-power-correction;		// enables power bridge
+						// correction for THD reduction
+						// near maximum power output
+	st,invalid-input-detect-mute;		// mute if no valid digital
+						// audio signal is provided.
+};
diff --git a/include/sound/sta32x.h b/include/sound/sta32x.h
index 8d93b0357a1..a894f7d17b1 100644
--- a/include/sound/sta32x.h
+++ b/include/sound/sta32x.h
@@ -24,12 +24,20 @@
 #define STA32X_THERMAL_RECOVERY_ENABLE		2
 
 struct sta32x_platform_data {
-	int output_conf;
-	int ch1_output_mapping;
-	int ch2_output_mapping;
-	int ch3_output_mapping;
-	int thermal_conf;
+	u8 output_conf;
+	u8 ch1_output_mapping;
+	u8 ch2_output_mapping;
+	u8 ch3_output_mapping;
 	int needs_esd_watchdog;
+	u8 drop_compensation_ns;
+	unsigned int thermal_warning_recovery:1;
+	unsigned int thermal_warning_adjustment:1;
+	unsigned int fault_detect_recovery:1;
+	unsigned int max_power_use_mpcc:1;
+	unsigned int max_power_correction:1;
+	unsigned int am_reduction_mode:1;
+	unsigned int odd_pwm_speed_mode:1;
+	unsigned int invalid_input_detect_mute:1;
 };
 
 #endif /* __LINUX_SND__STA32X_H */
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index ec2372498c9..669b67f8cee 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -24,6 +24,8 @@
 #include <linux/delay.h>
 #include <linux/pm.h>
 #include <linux/i2c.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/gpio/consumer.h>
@@ -893,15 +895,49 @@ static int sta32x_probe(struct snd_soc_codec *codec)
 		dev_err(codec->dev, "Failed to startup device\n");
 		return ret;
 	}
-	/* set thermal warning adjustment and recovery */
+
+	/* CONFA */
 	if (!pdata->thermal_warning_recovery)
 		thermal |= STA32X_CONFA_TWAB;
 	if (!pdata->thermal_warning_adjustment)
 		thermal |= STA32X_CONFA_TWRB;
+	if (!pdata->fault_detect_recovery)
+		thermal |= STA32X_CONFA_FDRB;
 	regmap_update_bits(sta32x->regmap, STA32X_CONFA,
-			   STA32X_CONFA_TWAB | STA32X_CONFA_TWRB,
+			   STA32X_CONFA_TWAB | STA32X_CONFA_TWRB |
+			   STA32X_CONFA_FDRB,
 			   thermal);
 
+	/* CONFC */
+	regmap_update_bits(sta32x->regmap, STA32X_CONFC,
+			   STA32X_CONFC_CSZ_MASK,
+			   pdata->drop_compensation_ns
+				<< STA32X_CONFC_CSZ_SHIFT);
+
+	/* CONFE */
+	regmap_update_bits(sta32x->regmap, STA32X_CONFE,
+			   STA32X_CONFE_MPCV,
+			   pdata->max_power_use_mpcc ?
+				STA32X_CONFE_MPCV : 0);
+	regmap_update_bits(sta32x->regmap, STA32X_CONFE,
+			   STA32X_CONFE_MPC,
+			   pdata->max_power_correction ?
+				STA32X_CONFE_MPC : 0);
+	regmap_update_bits(sta32x->regmap, STA32X_CONFE,
+			   STA32X_CONFE_AME,
+			   pdata->am_reduction_mode ?
+				STA32X_CONFE_AME : 0);
+	regmap_update_bits(sta32x->regmap, STA32X_CONFE,
+			   STA32X_CONFE_PWMS,
+			   pdata->odd_pwm_speed_mode ?
+				STA32X_CONFE_PWMS : 0);
+
+	/*  CONFF */
+	regmap_update_bits(sta32x->regmap, STA32X_CONFF,
+			   STA32X_CONFF_IDE,
+			   pdata->invalid_input_detect_mute ?
+				STA32X_CONFF_IDE : 0);
+
 	/* select output configuration  */
 	regmap_update_bits(sta32x->regmap, STA32X_CONFF,
 			   STA32X_CONFF_OCFG_MASK,
@@ -977,7 +1013,66 @@ static const struct regmap_config sta32x_regmap = {
 	.rd_table =		&sta32x_read_regs,
 	.volatile_table =	&sta32x_volatile_regs,
 };
+
+#ifdef CONFIG_OF
+static const struct of_device_id st32x_dt_ids[] = {
+	{ .compatible = "st,sta32x", },
+	{ }
 };
+MODULE_DEVICE_TABLE(of, st32x_dt_ids);
+
+static int sta32x_probe_dt(struct device *dev, struct sta32x_priv *sta32x)
+{
+	struct device_node *np = dev->of_node;
+	struct sta32x_platform_data *pdata;
+	u16 tmp;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
+
+	of_property_read_u8(np, "st,output-conf",
+			    &pdata->output_conf);
+	of_property_read_u8(np, "st,ch1-output-mapping",
+			    &pdata->ch1_output_mapping);
+	of_property_read_u8(np, "st,ch2-output-mapping",
+			    &pdata->ch2_output_mapping);
+	of_property_read_u8(np, "st,ch3-output-mapping",
+			    &pdata->ch3_output_mapping);
+
+	if (of_get_property(np, "st,thermal-warning-recovery", NULL))
+		pdata->thermal_warning_recovery = 1;
+	if (of_get_property(np, "st,thermal-warning-adjustment", NULL))
+		pdata->thermal_warning_adjustment = 1;
+	if (of_get_property(np, "st,needs_esd_watchdog", NULL))
+		pdata->needs_esd_watchdog = 1;
+
+	tmp = 140;
+	of_property_read_u16(np, "st,drop-compensation-ns", &tmp);
+	pdata->drop_compensation_ns = clamp_t(u16, tmp, 0, 300) / 20;
+
+	/* CONFE */
+	if (of_get_property(np, "st,max-power-use-mpcc", NULL))
+		pdata->max_power_use_mpcc = 1;
+
+	if (of_get_property(np, "st,max-power-correction", NULL))
+		pdata->max_power_correction = 1;
+
+	if (of_get_property(np, "st,am-reduction-mode", NULL))
+		pdata->am_reduction_mode = 1;
+
+	if (of_get_property(np, "st,odd-pwm-speed-mode", NULL))
+		pdata->odd_pwm_speed_mode = 1;
+
+	/* CONFF */
+	if (of_get_property(np, "st,invalid-input-detect-mute", NULL))
+		pdata->invalid_input_detect_mute = 1;
+
+	sta32x->pdata = pdata;
+
+	return 0;
+}
+#endif
 
 static int sta32x_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
@@ -994,6 +1089,14 @@ static int sta32x_i2c_probe(struct i2c_client *i2c,
 	mutex_init(&sta32x->coeff_lock);
 	sta32x->pdata = dev_get_platdata(dev);
 
+#ifdef CONFIG_OF
+	if (dev->of_node) {
+		ret = sta32x_probe_dt(dev, sta32x);
+		if (ret < 0)
+			return ret;
+	}
+#endif
+
 	/* GPIOs */
 	sta32x->gpiod_nreset = devm_gpiod_get(dev, "reset");
 	if (IS_ERR(sta32x->gpiod_nreset)) {
@@ -1051,6 +1154,7 @@ static struct i2c_driver sta32x_i2c_driver = {
 	.driver = {
 		.name = "sta32x",
 		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(st32x_dt_ids),
 	},
 	.probe =    sta32x_i2c_probe,
 	.remove =   sta32x_i2c_remove,
-- 
cgit v1.2.3-70-g09d2


From fda7a49cb991e9da15f5955d1ea292f8ec74f27a Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 27 Jan 2015 01:18:11 +0100
Subject: NFC: hci: Change event_received handler gate parameter to pipe

Several pipes may point to the same CLF gate, so getting the gate ID
as an input is not enough.
For example dual secure element may have 2 pipes (1 for uicc and
1 for eSE) pointing to the connectivity gate.

As resolving gate and host IDs can be done from a pipe, we now pass
the pipe ID to the event received handler.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h | 2 +-
 net/nfc/hci/core.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 14bd0e1c47f..031c0be9fb3 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -51,7 +51,7 @@ struct nfc_hci_ops {
 	int (*tm_send)(struct nfc_hci_dev *hdev, struct sk_buff *skb);
 	int (*check_presence)(struct nfc_hci_dev *hdev,
 			      struct nfc_target *target);
-	int (*event_received)(struct nfc_hci_dev *hdev, u8 gate, u8 event,
+	int (*event_received)(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			      struct sk_buff *skb);
 	int (*fw_download)(struct nfc_hci_dev *hdev, const char *firmware_name);
 	int (*discover_se)(struct nfc_hci_dev *dev);
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index ef50e7716c4..12a9a4b956d 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -338,7 +338,7 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 	}
 
 	if (hdev->ops->event_received) {
-		r = hdev->ops->event_received(hdev, gate, event, skb);
+		r = hdev->ops->event_received(hdev, pipe, event, skb);
 		if (r <= 0)
 			goto exit_noskb;
 	}
-- 
cgit v1.2.3-70-g09d2


From 118278f20aa89efe45fa1e2b1829f198d557f8fe Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 27 Jan 2015 01:18:12 +0100
Subject: NFC: hci: Add pipes table to reference them with a tuple {gate, host}

In order to keep host source information on specific hci event (such as
evt_connectivity or evt_transaction) and because 2 pipes can be connected
to the same gate, it is necessary to add a table referencing every pipe
with a {gate, host} tuple.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h | 13 ++++++++++++-
 net/nfc/hci/command.c |  6 ++++--
 net/nfc/hci/core.c    | 36 +++++++++++++++++++++++++++++++-----
 3 files changed, 47 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 031c0be9fb3..5570f4a316d 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -63,8 +63,10 @@ struct nfc_hci_ops {
 };
 
 /* Pipes */
-#define NFC_HCI_INVALID_PIPE	0x80
 #define NFC_HCI_DO_NOT_CREATE_PIPE	0x81
+#define NFC_HCI_INVALID_PIPE	0x80
+#define NFC_HCI_INVALID_GATE	0xFF
+#define NFC_HCI_INVALID_HOST	0x80
 #define NFC_HCI_LINK_MGMT_PIPE	0x00
 #define NFC_HCI_ADMIN_PIPE	0x01
 
@@ -73,7 +75,13 @@ struct nfc_hci_gate {
 	u8 pipe;
 };
 
+struct nfc_hci_pipe {
+	u8 gate;
+	u8 dest_host;
+};
+
 #define NFC_HCI_MAX_CUSTOM_GATES	50
+#define NFC_HCI_MAX_PIPES		127
 struct nfc_hci_init_data {
 	u8 gate_count;
 	struct nfc_hci_gate gates[NFC_HCI_MAX_CUSTOM_GATES];
@@ -125,6 +133,7 @@ struct nfc_hci_dev {
 	void *clientdata;
 
 	u8 gate2pipe[NFC_HCI_MAX_GATES];
+	struct nfc_hci_pipe pipes[NFC_HCI_MAX_PIPES];
 
 	u8 sw_romlib;
 	u8 sw_patch;
@@ -167,6 +176,8 @@ void *nfc_hci_get_clientdata(struct nfc_hci_dev *hdev);
 void nfc_hci_driver_failure(struct nfc_hci_dev *hdev, int err);
 
 int nfc_hci_result_to_errno(u8 result);
+void nfc_hci_reset_pipes(struct nfc_hci_dev *dev);
+void nfc_hci_reset_pipes_per_host(struct nfc_hci_dev *hdev, u8 host);
 
 /* Host IDs */
 #define NFC_HCI_HOST_CONTROLLER_ID	0x00
diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c
index 91df487aa0a..9acf586c98d 100644
--- a/net/nfc/hci/command.c
+++ b/net/nfc/hci/command.c
@@ -331,7 +331,7 @@ int nfc_hci_disconnect_all_gates(struct nfc_hci_dev *hdev)
 	if (r < 0)
 		return r;
 
-	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+	nfc_hci_reset_pipes(hdev);
 
 	return 0;
 }
@@ -345,7 +345,7 @@ int nfc_hci_connect_gate(struct nfc_hci_dev *hdev, u8 dest_host, u8 dest_gate,
 
 	pr_debug("\n");
 
-	if (hdev->gate2pipe[dest_gate] == NFC_HCI_DO_NOT_CREATE_PIPE)
+	if (pipe == NFC_HCI_DO_NOT_CREATE_PIPE)
 		return 0;
 
 	if (hdev->gate2pipe[dest_gate] != NFC_HCI_INVALID_PIPE)
@@ -380,6 +380,8 @@ open_pipe:
 		return r;
 	}
 
+	hdev->pipes[pipe].gate = dest_gate;
+	hdev->pipes[pipe].dest_host = dest_host;
 	hdev->gate2pipe[dest_gate] = pipe;
 
 	return 0;
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 12a9a4b956d..8f8abfed7f6 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -46,6 +46,32 @@ int nfc_hci_result_to_errno(u8 result)
 }
 EXPORT_SYMBOL(nfc_hci_result_to_errno);
 
+void nfc_hci_reset_pipes(struct nfc_hci_dev *hdev)
+{
+	int i = 0;
+
+	for (i = 0; i < NFC_HCI_MAX_PIPES; i++) {
+		hdev->pipes[i].gate = NFC_HCI_INVALID_GATE;
+		hdev->pipes[i].dest_host = NFC_HCI_INVALID_HOST;
+	}
+	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+}
+EXPORT_SYMBOL(nfc_hci_reset_pipes);
+
+void nfc_hci_reset_pipes_per_host(struct nfc_hci_dev *hdev, u8 host)
+{
+	int i = 0;
+
+	for (i = 0; i < NFC_HCI_MAX_PIPES; i++) {
+		if (hdev->pipes[i].dest_host != host)
+			continue;
+
+		hdev->pipes[i].gate = NFC_HCI_INVALID_GATE;
+		hdev->pipes[i].dest_host = NFC_HCI_INVALID_HOST;
+	}
+}
+EXPORT_SYMBOL(nfc_hci_reset_pipes_per_host);
+
 static void nfc_hci_msg_tx_work(struct work_struct *work)
 {
 	struct nfc_hci_dev *hdev = container_of(work, struct nfc_hci_dev,
@@ -168,7 +194,7 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 			  struct sk_buff *skb)
 {
 	int r = 0;
-	u8 gate = nfc_hci_pipe2gate(hdev, pipe);
+	u8 gate = hdev->pipes[pipe].gate;
 	u8 local_gate, new_pipe;
 	u8 gate_opened = 0x00;
 
@@ -330,9 +356,9 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			    struct sk_buff *skb)
 {
 	int r = 0;
-	u8 gate = nfc_hci_pipe2gate(hdev, pipe);
+	u8 gate = hdev->pipes[pipe].gate;
 
-	if (gate == 0xff) {
+	if (gate == NFC_HCI_INVALID_GATE) {
 		pr_err("Discarded event %x to unopened pipe %x\n", event, pipe);
 		goto exit;
 	}
@@ -573,7 +599,7 @@ static int hci_dev_down(struct nfc_dev *nfc_dev)
 	if (hdev->ops->close)
 		hdev->ops->close(hdev);
 
-	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+	nfc_hci_reset_pipes(hdev);
 
 	return 0;
 }
@@ -932,7 +958,7 @@ struct nfc_hci_dev *nfc_hci_allocate_device(struct nfc_hci_ops *ops,
 
 	nfc_set_drvdata(hdev->ndev, hdev);
 
-	memset(hdev->gate2pipe, NFC_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+	nfc_hci_reset_pipes(hdev);
 
 	hdev->quirks = quirks;
 
-- 
cgit v1.2.3-70-g09d2


From af77522320aa0e5b4b52dce615ad067d92e15fbf Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 27 Jan 2015 01:18:13 +0100
Subject: NFC: hci: Change nfc_hci_send_response gate parameter to pipe

As there can be several pipes connected to the same gate, we need
to know which pipe ID to use when sending an HCI response. A gate
ID is not enough.

Instead of changing the nfc_hci_send_response() API to something
not aligned with the rest of the HCI API, we call nfc_hci_hcp_message_tx
directly.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h |  2 --
 net/nfc/hci/command.c | 17 -----------------
 net/nfc/hci/core.c    | 12 ++++++++----
 3 files changed, 8 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 5570f4a316d..1d1fd2b98f1 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -260,8 +260,6 @@ int nfc_hci_send_cmd(struct nfc_hci_dev *hdev, u8 gate, u8 cmd,
 int nfc_hci_send_cmd_async(struct nfc_hci_dev *hdev, u8 gate, u8 cmd,
 			   const u8 *param, size_t param_len,
 			   data_exchange_cb_t cb, void *cb_context);
-int nfc_hci_send_response(struct nfc_hci_dev *hdev, u8 gate, u8 response,
-			  const u8 *param, size_t param_len);
 int nfc_hci_send_event(struct nfc_hci_dev *hdev, u8 gate, u8 event,
 		       const u8 *param, size_t param_len);
 int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate);
diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c
index 9acf586c98d..844673cb7c1 100644
--- a/net/nfc/hci/command.c
+++ b/net/nfc/hci/command.c
@@ -116,23 +116,6 @@ int nfc_hci_send_event(struct nfc_hci_dev *hdev, u8 gate, u8 event,
 }
 EXPORT_SYMBOL(nfc_hci_send_event);
 
-int nfc_hci_send_response(struct nfc_hci_dev *hdev, u8 gate, u8 response,
-			  const u8 *param, size_t param_len)
-{
-	u8 pipe;
-
-	pr_debug("\n");
-
-	pipe = hdev->gate2pipe[gate];
-	if (pipe == NFC_HCI_INVALID_PIPE)
-		return -EADDRNOTAVAIL;
-
-	return nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE,
-				      response, param, param_len, NULL, NULL,
-				      0);
-}
-EXPORT_SYMBOL(nfc_hci_send_response);
-
 /*
  * Execute an hci command sent to gate.
  * skb will contain response data if success. skb can be NULL if you are not
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index 8f8abfed7f6..e351e94f8d4 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -209,7 +209,8 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 
 		local_gate = skb->data[3];
 		new_pipe = skb->data[4];
-		nfc_hci_send_response(hdev, gate, NFC_HCI_ANY_OK, NULL, 0);
+		nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE,
+				       NFC_HCI_ANY_OK, NULL, 0, NULL, NULL, 0);
 
 		/* save the new created pipe and bind with local gate,
 		 * the description for skb->data[3] is destination gate id
@@ -223,11 +224,14 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 		 * open it
 		 */
 		if (gate != 0xff)
-			nfc_hci_send_response(hdev, gate, NFC_HCI_ANY_OK,
-					      &gate_opened, 1);
+			nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE,
+					       NFC_HCI_ANY_OK, &gate_opened, 1,
+					       NULL, NULL, 0);
 		break;
 	case NFC_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED:
-		nfc_hci_send_response(hdev, gate, NFC_HCI_ANY_OK, NULL, 0);
+		nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE,
+				       NFC_HCI_ANY_OK, NULL, 0, NULL, NULL, 0);
+
 		break;
 	default:
 		pr_info("Discarded unknown cmd %x to gate %x\n", cmd, gate);
-- 
cgit v1.2.3-70-g09d2


From 8409e4283c1ca62ce107564de7ff93b4dd476d41 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 27 Jan 2015 01:18:15 +0100
Subject: NFC: hci: Add cmd_received handler

When a command is received, it is sometime needed to let the CLF driver do
some additional operations. (ex: count remaining pipe notification...)

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/hci.h | 8 ++++++++
 net/nfc/hci/core.c    | 3 +++
 2 files changed, 11 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 1d1fd2b98f1..ab672b537dd 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -53,6 +53,8 @@ struct nfc_hci_ops {
 			      struct nfc_target *target);
 	int (*event_received)(struct nfc_hci_dev *hdev, u8 pipe, u8 event,
 			      struct sk_buff *skb);
+	void (*cmd_received)(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
+			    struct sk_buff *skb);
 	int (*fw_download)(struct nfc_hci_dev *hdev, const char *firmware_name);
 	int (*discover_se)(struct nfc_hci_dev *dev);
 	int (*enable_se)(struct nfc_hci_dev *dev, u32 se_idx);
@@ -230,6 +232,12 @@ void nfc_hci_reset_pipes_per_host(struct nfc_hci_dev *hdev, u8 host);
 #define NFC_HCI_EVT_POST_DATA			0x02
 #define NFC_HCI_EVT_HOT_PLUG			0x03
 
+/* Generic commands */
+#define NFC_HCI_ANY_SET_PARAMETER	0x01
+#define NFC_HCI_ANY_GET_PARAMETER	0x02
+#define NFC_HCI_ANY_OPEN_PIPE		0x03
+#define NFC_HCI_ANY_CLOSE_PIPE		0x04
+
 /* Reader RF gates events */
 #define NFC_HCI_EVT_READER_REQUESTED	0x10
 #define NFC_HCI_EVT_END_OPERATION	0x11
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index a664a67dff1..6e061da2258 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -249,6 +249,9 @@ void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 		break;
 	}
 
+	if (hdev->ops->cmd_received)
+		hdev->ops->cmd_received(hdev, pipe, cmd, skb);
+
 exit:
 	nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_RESPONSE,
 			       status, NULL, 0, NULL, NULL, 0);
-- 
cgit v1.2.3-70-g09d2


From 2130fb97fecf9a51bb4a21da220cff3f72496a94 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 27 Jan 2015 01:18:19 +0100
Subject: NFC: st21nfca: Adding support for secure element

st21nfca has 1 physical SWP line and can support up to 2 secure elements
(UICC & eSE) thanks to an external switch managed with a gpio.

The platform integrator needs to specify thanks to 2 initialization
properties, uicc-present and ese-present, if it is suppose to have uicc
and/or ese. Of course if the platform does not have an external switch,
only one kind of secure element can be supported. Those parameters are
under platform integrator responsibilities.

During initialization, the white_list will be set according to those
parameters.

The discovery_se function will assume a secure element is physically
present according to uicc-present and ese-present values and will add it
to the secure element list. On ese activation, the atr is retrieved to
calculate a command exchange timeout based on the first atr(TB) value.

The se_io will allow to transfer data over SWP. 2 kind of events may appear
after a data is sent over:
- ST21NFCA_EVT_TRANSMIT_DATA when receiving an apdu answer
- ST21NFCA_EVT_WTX_REQUEST when the secure element needs more time than
expected to compute a command. If this timeout expired, a first recovery
tentative consist to send a simple software reset proprietary command.
If this tentative still fail, a second recovery tentative consist to send
a hardware reset proprietary command.
This function is only relevant for eSE like secure element.

This patch also change the way a pipe is referenced. There can be
different pipe connected to the same gate with different host destination
(ex: CONNECTIVITY). In order to keep host information every pipe are
reference with a tuple (gate, host). In order to reduce changes, we are
keeping unchanged the way a gate is addressed on the Terminal Host.
However, this is working because we consider the apdu reader gate is only
present on the eSE slot also the connectivity gate cannot give a reliable
value; it will give the latest stored pipe value.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/st21nfca/Makefile          |   2 +-
 drivers/nfc/st21nfca/i2c.c             |  17 +-
 drivers/nfc/st21nfca/st21nfca.c        | 134 +++++++++--
 drivers/nfc/st21nfca/st21nfca.h        |  21 +-
 drivers/nfc/st21nfca/st21nfca_se.c     | 390 +++++++++++++++++++++++++++++++++
 drivers/nfc/st21nfca/st21nfca_se.h     |  63 ++++++
 include/linux/platform_data/st21nfca.h |   2 +
 7 files changed, 608 insertions(+), 21 deletions(-)
 create mode 100644 drivers/nfc/st21nfca/st21nfca_se.c
 create mode 100644 drivers/nfc/st21nfca/st21nfca_se.h

(limited to 'include')

diff --git a/drivers/nfc/st21nfca/Makefile b/drivers/nfc/st21nfca/Makefile
index 7d688f97aa2..97edab4bbdf 100644
--- a/drivers/nfc/st21nfca/Makefile
+++ b/drivers/nfc/st21nfca/Makefile
@@ -2,7 +2,7 @@
 # Makefile for ST21NFCA HCI based NFC driver
 #
 
-st21nfca_hci-objs = st21nfca.o st21nfca_dep.o
+st21nfca_hci-objs = st21nfca.o st21nfca_dep.o st21nfca_se.o
 obj-$(CONFIG_NFC_ST21NFCA)     += st21nfca_hci.o
 
 st21nfca_i2c-objs  = i2c.o
diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
index 82b82dbd299..a3214395161 100644
--- a/drivers/nfc/st21nfca/i2c.c
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -74,6 +74,8 @@ struct st21nfca_i2c_phy {
 	unsigned int gpio_ena;
 	unsigned int irq_polarity;
 
+	struct st21nfca_se_status se_status;
+
 	struct sk_buff *pending_skb;
 	int current_read_len;
 	/*
@@ -537,6 +539,11 @@ static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client)
 
 	phy->irq_polarity = irq_get_trigger_type(client->irq);
 
+	phy->se_status.is_ese_present =
+				of_property_read_bool(pp, "ese-present");
+	phy->se_status.is_uicc_present =
+				of_property_read_bool(pp, "uicc-present");
+
 	return 0;
 }
 #else
@@ -571,6 +578,9 @@ static int st21nfca_hci_i2c_request_resources(struct i2c_client *client)
 		}
 	}
 
+	phy->se_status.is_ese_present = pdata->is_ese_present;
+	phy->se_status.is_uicc_present = pdata->is_uicc_present;
+
 	return 0;
 }
 
@@ -638,8 +648,11 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	}
 
 	return st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
-			       ST21NFCA_FRAME_HEADROOM, ST21NFCA_FRAME_TAILROOM,
-			       ST21NFCA_HCI_LLC_MAX_PAYLOAD, &phy->hdev);
+					ST21NFCA_FRAME_HEADROOM,
+					ST21NFCA_FRAME_TAILROOM,
+					ST21NFCA_HCI_LLC_MAX_PAYLOAD,
+					&phy->hdev,
+					&phy->se_status);
 }
 
 static int st21nfca_hci_i2c_remove(struct i2c_client *client)
diff --git a/drivers/nfc/st21nfca/st21nfca.c b/drivers/nfc/st21nfca/st21nfca.c
index 7cb7ce47d2a..24d3d240d5f 100644
--- a/drivers/nfc/st21nfca/st21nfca.c
+++ b/drivers/nfc/st21nfca/st21nfca.c
@@ -23,6 +23,7 @@
 
 #include "st21nfca.h"
 #include "st21nfca_dep.h"
+#include "st21nfca_se.h"
 
 #define DRIVER_DESC "HCI NFC driver for ST21NFCA"
 
@@ -62,7 +63,6 @@
 #define ST21NFCA_RF_CARD_F_DATARATE		0x08
 #define ST21NFCA_RF_CARD_F_DATARATE_212_424	0x01
 
-#define ST21NFCA_DEVICE_MGNT_GATE		0x01
 #define ST21NFCA_DEVICE_MGNT_PIPE		0x02
 
 #define ST21NFCA_DM_GETINFO			0x13
@@ -78,6 +78,11 @@
 
 #define ST21NFCA_NFC_MODE			0x03	/* NFC_MODE parameter*/
 
+#define ST21NFCA_EVT_HOT_PLUG			0x03
+#define ST21NFCA_EVT_HOT_PLUG_IS_INHIBITED(x) (x->data[0] & 0x80)
+
+#define ST21NFCA_SE_TO_PIPES			2000
+
 static DECLARE_BITMAP(dev_mask, ST21NFCA_NUM_DEVICES);
 
 static struct nfc_hci_gate st21nfca_gates[] = {
@@ -92,6 +97,10 @@ static struct nfc_hci_gate st21nfca_gates[] = {
 	{ST21NFCA_RF_READER_14443_3_A_GATE, NFC_HCI_INVALID_PIPE},
 	{ST21NFCA_RF_READER_ISO15693_GATE, NFC_HCI_INVALID_PIPE},
 	{ST21NFCA_RF_CARD_F_GATE, NFC_HCI_INVALID_PIPE},
+
+	/* Secure element pipes are created by secure element host */
+	{ST21NFCA_CONNECTIVITY_GATE, NFC_HCI_DO_NOT_CREATE_PIPE},
+	{ST21NFCA_APDU_READER_GATE, NFC_HCI_DO_NOT_CREATE_PIPE},
 };
 
 struct st21nfca_pipe_info {
@@ -136,7 +145,8 @@ static int st21nfca_hci_load_session(struct nfc_hci_dev *hdev)
 	 * Pipe can be closed and need to be open.
 	 */
 	r = nfc_hci_connect_gate(hdev, NFC_HCI_HOST_CONTROLLER_ID,
-		ST21NFCA_DEVICE_MGNT_GATE, ST21NFCA_DEVICE_MGNT_PIPE);
+				ST21NFCA_DEVICE_MGNT_GATE,
+				ST21NFCA_DEVICE_MGNT_PIPE);
 	if (r < 0)
 		goto free_info;
 
@@ -167,17 +177,28 @@ static int st21nfca_hci_load_session(struct nfc_hci_dev *hdev)
 		 * - destination gid (1byte)
 		 */
 		info = (struct st21nfca_pipe_info *) skb_pipe_info->data;
+		if (info->dst_gate_id == ST21NFCA_APDU_READER_GATE &&
+			info->src_host_id != ST21NFCA_ESE_HOST_ID) {
+			pr_err("Unexpected apdu_reader pipe on host %x\n",
+				info->src_host_id);
+			continue;
+		}
+
 		for (j = 0; (j < ARRAY_SIZE(st21nfca_gates)) &&
-			(st21nfca_gates[j].gate != info->dst_gate_id);
-			j++)
+			(st21nfca_gates[j].gate != info->dst_gate_id) ; j++)
 			;
 
 		if (j < ARRAY_SIZE(st21nfca_gates) &&
 			st21nfca_gates[j].gate == info->dst_gate_id &&
 			ST21NFCA_DM_IS_PIPE_OPEN(info->pipe_state)) {
 			st21nfca_gates[j].pipe = pipe_info[2];
+
 			hdev->gate2pipe[st21nfca_gates[j].gate] =
-				st21nfca_gates[j].pipe;
+							st21nfca_gates[j].pipe;
+			hdev->pipes[st21nfca_gates[j].pipe].gate =
+							st21nfca_gates[j].gate;
+			hdev->pipes[st21nfca_gates[j].pipe].dest_host =
+							info->src_host_id;
 		}
 	}
 
@@ -187,7 +208,7 @@ static int st21nfca_hci_load_session(struct nfc_hci_dev *hdev)
 	 */
 	if (skb_pipe_list->len + 3 < ARRAY_SIZE(st21nfca_gates)) {
 		for (i = skb_pipe_list->len + 3;
-				i < ARRAY_SIZE(st21nfca_gates); i++) {
+				i < ARRAY_SIZE(st21nfca_gates) - 2; i++) {
 			r = nfc_hci_connect_gate(hdev,
 					NFC_HCI_HOST_CONTROLLER_ID,
 					st21nfca_gates[i].gate,
@@ -244,16 +265,33 @@ out:
 
 static int st21nfca_hci_ready(struct nfc_hci_dev *hdev)
 {
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
 	struct sk_buff *skb;
 
 	u8 param;
+	u8 white_list[2];
+	int wl_size = 0;
 	int r;
 
-	param = NFC_HCI_UICC_HOST_ID;
-	r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
-			      NFC_HCI_ADMIN_WHITELIST, &param, 1);
-	if (r < 0)
-		return r;
+	if (info->se_status->is_ese_present &&
+		info->se_status->is_uicc_present) {
+		white_list[wl_size++] = NFC_HCI_UICC_HOST_ID;
+		white_list[wl_size++] = ST21NFCA_ESE_HOST_ID;
+	} else if (!info->se_status->is_ese_present &&
+			 info->se_status->is_uicc_present) {
+		white_list[wl_size++] = NFC_HCI_UICC_HOST_ID;
+	} else if (info->se_status->is_ese_present &&
+			!info->se_status->is_uicc_present) {
+		white_list[wl_size++] = ST21NFCA_ESE_HOST_ID;
+	}
+
+	if (wl_size) {
+		r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
+					NFC_HCI_ADMIN_WHITELIST,
+					(u8 *) &white_list, wl_size);
+		if (r < 0)
+			return r;
+	}
 
 	/* Set NFC_MODE in device management gate to enable */
 	r = nfc_hci_get_param(hdev, ST21NFCA_DEVICE_MGNT_GATE,
@@ -821,19 +859,79 @@ static int st21nfca_hci_check_presence(struct nfc_hci_dev *hdev,
 	}
 }
 
+static void st21nfca_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
+				struct sk_buff *skb)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+	u8 gate = hdev->pipes[pipe].gate;
+
+	pr_debug("cmd: %x\n", cmd);
+
+	switch (cmd) {
+	case NFC_HCI_ANY_OPEN_PIPE:
+		if (gate != ST21NFCA_APDU_READER_GATE &&
+			hdev->pipes[pipe].dest_host != NFC_HCI_UICC_HOST_ID)
+			info->se_info.count_pipes++;
+
+		if (info->se_info.count_pipes == info->se_info.expected_pipes) {
+			del_timer_sync(&info->se_info.se_active_timer);
+			info->se_info.se_active = false;
+			info->se_info.count_pipes = 0;
+			complete(&info->se_info.req_completion);
+		}
+	break;
+	}
+}
+
+static int st21nfca_admin_event_received(struct nfc_hci_dev *hdev, u8 event,
+					struct sk_buff *skb)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	pr_debug("admin event: %x\n", event);
+
+	switch (event) {
+	case ST21NFCA_EVT_HOT_PLUG:
+		if (info->se_info.se_active) {
+			if (!ST21NFCA_EVT_HOT_PLUG_IS_INHIBITED(skb)) {
+				del_timer_sync(&info->se_info.se_active_timer);
+				info->se_info.se_active = false;
+				complete(&info->se_info.req_completion);
+			} else {
+				mod_timer(&info->se_info.se_active_timer,
+					jiffies +
+					msecs_to_jiffies(ST21NFCA_SE_TO_PIPES));
+			}
+		}
+	break;
+	}
+	kfree_skb(skb);
+	return 0;
+}
+
 /*
  * Returns:
  * <= 0: driver handled the event, skb consumed
  *    1: driver does not handle the event, please do standard processing
  */
-static int st21nfca_hci_event_received(struct nfc_hci_dev *hdev, u8 gate,
+static int st21nfca_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe,
 				       u8 event, struct sk_buff *skb)
 {
+	u8 gate = hdev->pipes[pipe].gate;
+	u8 host = hdev->pipes[pipe].dest_host;
+
 	pr_debug("hci event: %d gate: %x\n", event, gate);
 
 	switch (gate) {
+	case NFC_HCI_ADMIN_GATE:
+		return st21nfca_admin_event_received(hdev, event, skb);
 	case ST21NFCA_RF_CARD_F_GATE:
 		return st21nfca_dep_event_received(hdev, event, skb);
+	case ST21NFCA_CONNECTIVITY_GATE:
+		return st21nfca_connectivity_event_received(hdev, host,
+							event, skb);
+	case ST21NFCA_APDU_READER_GATE:
+		return st21nfca_apdu_reader_event_received(hdev, event, skb);
 	default:
 		return 1;
 	}
@@ -855,11 +953,17 @@ static struct nfc_hci_ops st21nfca_hci_ops = {
 	.tm_send = st21nfca_hci_tm_send,
 	.check_presence = st21nfca_hci_check_presence,
 	.event_received = st21nfca_hci_event_received,
+	.cmd_received = st21nfca_hci_cmd_received,
+	.discover_se = st21nfca_hci_discover_se,
+	.enable_se = st21nfca_hci_enable_se,
+	.disable_se = st21nfca_hci_disable_se,
+	.se_io = st21nfca_hci_se_io,
 };
 
 int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
 		       char *llc_name, int phy_headroom, int phy_tailroom,
-		       int phy_payload, struct nfc_hci_dev **hdev)
+		       int phy_payload, struct nfc_hci_dev **hdev,
+			   struct st21nfca_se_status *se_status)
 {
 	struct st21nfca_hci_info *info;
 	int r = 0;
@@ -919,6 +1023,8 @@ int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
 		goto err_alloc_hdev;
 	}
 
+	info->se_status = se_status;
+
 	nfc_hci_set_clientdata(info->hdev, info);
 
 	r = nfc_hci_register_device(info->hdev);
@@ -927,6 +1033,7 @@ int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
 
 	*hdev = info->hdev;
 	st21nfca_dep_init(info->hdev);
+	st21nfca_se_init(info->hdev);
 
 	return 0;
 
@@ -945,6 +1052,7 @@ void st21nfca_hci_remove(struct nfc_hci_dev *hdev)
 	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
 
 	st21nfca_dep_deinit(hdev);
+	st21nfca_se_deinit(hdev);
 	nfc_hci_unregister_device(hdev);
 	nfc_hci_free_device(hdev);
 	kfree(info);
diff --git a/drivers/nfc/st21nfca/st21nfca.h b/drivers/nfc/st21nfca/st21nfca.h
index 7c2a8529223..15a78d330a9 100644
--- a/drivers/nfc/st21nfca/st21nfca.h
+++ b/drivers/nfc/st21nfca/st21nfca.h
@@ -20,6 +20,7 @@
 #include <net/nfc/hci.h>
 
 #include "st21nfca_dep.h"
+#include "st21nfca_se.h"
 
 #define HCI_MODE 0
 
@@ -51,9 +52,15 @@
 
 #define ST21NFCA_NUM_DEVICES 256
 
+struct st21nfca_se_status {
+	bool is_ese_present;
+	bool is_uicc_present;
+};
+
 int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
 		       char *llc_name, int phy_headroom, int phy_tailroom,
-		       int phy_payload, struct nfc_hci_dev **hdev);
+		       int phy_payload, struct nfc_hci_dev **hdev,
+			   struct st21nfca_se_status *se_status);
 void st21nfca_hci_remove(struct nfc_hci_dev *hdev);
 
 enum st21nfca_state {
@@ -66,6 +73,7 @@ struct st21nfca_hci_info {
 	void *phy_id;
 
 	struct nfc_hci_dev *hdev;
+	struct st21nfca_se_status *se_status;
 
 	enum st21nfca_state state;
 
@@ -76,13 +84,16 @@ struct st21nfca_hci_info {
 	void *async_cb_context;
 
 	struct st21nfca_dep_info dep_info;
+	struct st21nfca_se_info se_info;
 };
 
 /* Reader RF commands */
-#define ST21NFCA_WR_XCHG_DATA            0x10
-
-#define ST21NFCA_RF_READER_F_GATE               0x14
+#define ST21NFCA_WR_XCHG_DATA           0x10
 
-#define ST21NFCA_RF_CARD_F_GATE 0x24
+#define ST21NFCA_DEVICE_MGNT_GATE       0x01
+#define ST21NFCA_RF_READER_F_GATE       0x14
+#define ST21NFCA_RF_CARD_F_GATE			0x24
+#define ST21NFCA_APDU_READER_GATE		0xf0
+#define ST21NFCA_CONNECTIVITY_GATE		0x41
 
 #endif /* __LOCAL_ST21NFCA_H_ */
diff --git a/drivers/nfc/st21nfca/st21nfca_se.c b/drivers/nfc/st21nfca/st21nfca_se.c
new file mode 100644
index 00000000000..9b93d3904ab
--- /dev/null
+++ b/drivers/nfc/st21nfca/st21nfca_se.c
@@ -0,0 +1,390 @@
+/*
+ * Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <net/nfc/hci.h>
+
+#include "st21nfca.h"
+#include "st21nfca_se.h"
+
+#define ST21NFCA_EVT_UICC_ACTIVATE		0x10
+#define ST21NFCA_EVT_UICC_DEACTIVATE	0x13
+#define ST21NFCA_EVT_SE_HARD_RESET		0x20
+#define ST21NFCA_EVT_SE_SOFT_RESET		0x11
+#define ST21NFCA_EVT_SE_END_OF_APDU_TRANSFER	0x21
+#define ST21NFCA_EVT_SE_ACTIVATE		0x22
+#define ST21NFCA_EVT_SE_DEACTIVATE		0x23
+
+#define ST21NFCA_EVT_TRANSMIT_DATA		0x10
+#define ST21NFCA_EVT_WTX_REQUEST		0x11
+
+#define ST21NFCA_EVT_CONNECTIVITY		0x10
+#define ST21NFCA_EVT_TRANSACTION		0x12
+
+#define ST21NFCA_ESE_HOST_ID			0xc0
+
+#define ST21NFCA_SE_TO_HOT_PLUG			1000
+/* Connectivity pipe only */
+#define ST21NFCA_SE_COUNT_PIPE_UICC		0x01
+/* Connectivity + APDU Reader pipe */
+#define ST21NFCA_SE_COUNT_PIPE_EMBEDDED	0x02
+
+#define ST21NFCA_SE_MODE_OFF			0x00
+#define ST21NFCA_SE_MODE_ON				0x01
+
+#define ST21NFCA_PARAM_ATR				0x01
+#define ST21NFCA_ATR_DEFAULT_BWI		0x04
+
+/*
+ * WT = 2^BWI/10[s], convert into msecs and add a secure
+ * room by increasing by 2 this timeout
+ */
+#define ST21NFCA_BWI_TO_TIMEOUT(x)		((1 << x) * 200)
+#define ST21NFCA_ATR_GET_Y_FROM_TD(x)	(x >> 4)
+
+/* If TA is present bit 0 is set */
+#define ST21NFCA_ATR_TA_PRESENT(x) (x & 0x01)
+/* If TB is present bit 1 is set */
+#define ST21NFCA_ATR_TB_PRESENT(x) (x & 0x02)
+
+static u8 st21nfca_se_get_bwi(struct nfc_hci_dev *hdev)
+{
+	int i;
+	u8 td;
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	/* Bits 8 to 5 of the first TB for T=1 encode BWI from zero to nine */
+	for (i = 1; i < ST21NFCA_ESE_MAX_LENGTH; i++) {
+		td = ST21NFCA_ATR_GET_Y_FROM_TD(info->se_info.atr[i]);
+		if (ST21NFCA_ATR_TA_PRESENT(td))
+			i++;
+		if (ST21NFCA_ATR_TB_PRESENT(td)) {
+			i++;
+			return info->se_info.atr[i] >> 4;
+		}
+	}
+	return ST21NFCA_ATR_DEFAULT_BWI;
+}
+
+static void st21nfca_se_get_atr(struct nfc_hci_dev *hdev)
+{
+	int r;
+	struct sk_buff *skb;
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	r = nfc_hci_get_param(hdev, ST21NFCA_APDU_READER_GATE,
+			ST21NFCA_PARAM_ATR, &skb);
+	if (r < 0)
+		return;
+
+	if (skb->len <= ST21NFCA_ESE_MAX_LENGTH) {
+		memcpy(info->se_info.atr, skb->data, skb->len);
+		info->se_info.wt_timeout =
+			ST21NFCA_BWI_TO_TIMEOUT(st21nfca_se_get_bwi(hdev));
+	}
+	kfree_skb(skb);
+}
+
+static int st21nfca_hci_control_se(struct nfc_hci_dev *hdev, u32 se_idx,
+				u8 state)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+	int r;
+	struct sk_buff *sk_host_list;
+	u8 se_event, host_id;
+
+	switch (se_idx) {
+	case NFC_HCI_UICC_HOST_ID:
+		se_event = (state == ST21NFCA_SE_MODE_ON ?
+					ST21NFCA_EVT_UICC_ACTIVATE :
+					ST21NFCA_EVT_UICC_DEACTIVATE);
+
+		info->se_info.count_pipes = 0;
+		info->se_info.expected_pipes = ST21NFCA_SE_COUNT_PIPE_UICC;
+		break;
+	case ST21NFCA_ESE_HOST_ID:
+		se_event = (state == ST21NFCA_SE_MODE_ON ?
+					ST21NFCA_EVT_SE_ACTIVATE :
+					ST21NFCA_EVT_SE_DEACTIVATE);
+
+		info->se_info.count_pipes = 0;
+		info->se_info.expected_pipes = ST21NFCA_SE_COUNT_PIPE_EMBEDDED;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * Wait for an EVT_HOT_PLUG in order to
+	 * retrieve a relevant host list.
+	 */
+	reinit_completion(&info->se_info.req_completion);
+	r = nfc_hci_send_event(hdev, ST21NFCA_DEVICE_MGNT_GATE, se_event,
+			       NULL, 0);
+	if (r < 0)
+		return r;
+
+	mod_timer(&info->se_info.se_active_timer, jiffies +
+		msecs_to_jiffies(ST21NFCA_SE_TO_HOT_PLUG));
+	info->se_info.se_active = true;
+
+	/* Ignore return value and check in any case the host_list */
+	wait_for_completion_interruptible(&info->se_info.req_completion);
+
+	r = nfc_hci_get_param(hdev, NFC_HCI_ADMIN_GATE,
+			NFC_HCI_ADMIN_HOST_LIST,
+			&sk_host_list);
+	if (r < 0)
+		return r;
+
+	host_id = sk_host_list->data[sk_host_list->len - 1];
+	kfree_skb(sk_host_list);
+
+	if (state == ST21NFCA_SE_MODE_ON && host_id == se_idx)
+		return se_idx;
+	else if (state == ST21NFCA_SE_MODE_OFF && host_id != se_idx)
+		return se_idx;
+
+	return -1;
+}
+
+int st21nfca_hci_discover_se(struct nfc_hci_dev *hdev)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+	int se_count = 0;
+
+	if (info->se_status->is_uicc_present) {
+		nfc_add_se(hdev->ndev, NFC_HCI_UICC_HOST_ID, NFC_SE_UICC);
+		se_count++;
+	}
+
+	if (info->se_status->is_ese_present) {
+		nfc_add_se(hdev->ndev, ST21NFCA_ESE_HOST_ID, NFC_SE_EMBEDDED);
+		se_count++;
+	}
+
+	return !se_count;
+}
+EXPORT_SYMBOL(st21nfca_hci_discover_se);
+
+int st21nfca_hci_enable_se(struct nfc_hci_dev *hdev, u32 se_idx)
+{
+	int r;
+
+	/*
+	 * According to upper layer, se_idx == NFC_SE_UICC when
+	 * info->se_status->is_uicc_enable is true should never happen.
+	 * Same for eSE.
+	 */
+	r = st21nfca_hci_control_se(hdev, se_idx, ST21NFCA_SE_MODE_ON);
+
+	if (r == ST21NFCA_ESE_HOST_ID) {
+		st21nfca_se_get_atr(hdev);
+		r = nfc_hci_send_event(hdev, ST21NFCA_APDU_READER_GATE,
+				ST21NFCA_EVT_SE_SOFT_RESET, NULL, 0);
+		if (r < 0)
+			return r;
+	} else if (r < 0) {
+		/*
+		 * The activation tentative failed, the secure element
+		 * is not connected. Remove from the list.
+		 */
+		nfc_remove_se(hdev->ndev, se_idx);
+		return r;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(st21nfca_hci_enable_se);
+
+int st21nfca_hci_disable_se(struct nfc_hci_dev *hdev, u32 se_idx)
+{
+	int r;
+
+	/*
+	 * According to upper layer, se_idx == NFC_SE_UICC when
+	 * info->se_status->is_uicc_enable is true should never happen
+	 * Same for eSE.
+	 */
+	r = st21nfca_hci_control_se(hdev, se_idx, ST21NFCA_SE_MODE_OFF);
+	if (r < 0)
+		return r;
+
+	return 0;
+}
+EXPORT_SYMBOL(st21nfca_hci_disable_se);
+
+int st21nfca_hci_se_io(struct nfc_hci_dev *hdev, u32 se_idx,
+			u8 *apdu, size_t apdu_length,
+			se_io_cb_t cb, void *cb_context)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	pr_debug("se_io %x\n", se_idx);
+
+	switch (se_idx) {
+	case ST21NFCA_ESE_HOST_ID:
+		info->se_info.cb = cb;
+		info->se_info.cb_context = cb_context;
+		mod_timer(&info->se_info.bwi_timer, jiffies +
+			  msecs_to_jiffies(info->se_info.wt_timeout));
+		info->se_info.bwi_active = true;
+		return nfc_hci_send_event(hdev, ST21NFCA_APDU_READER_GATE,
+					ST21NFCA_EVT_TRANSMIT_DATA,
+					apdu, apdu_length);
+	default:
+		return -ENODEV;
+	}
+}
+EXPORT_SYMBOL(st21nfca_hci_se_io);
+
+static void st21nfca_se_wt_timeout(unsigned long data)
+{
+	/*
+	 * No answer from the secure element
+	 * within the defined timeout.
+	 * Let's send a reset request as recovery procedure.
+	 * According to the situation, we first try to send a software reset
+	 * to the secure element. If the next command is still not
+	 * answering in time, we send to the CLF a secure element hardware
+	 * reset request.
+	 */
+	/* hardware reset managed through VCC_UICC_OUT power supply */
+	u8 param = 0x01;
+	struct st21nfca_hci_info *info = (struct st21nfca_hci_info *) data;
+
+	pr_debug("\n");
+
+	info->se_info.bwi_active = false;
+
+	if (!info->se_info.xch_error) {
+		info->se_info.xch_error = true;
+		nfc_hci_send_event(info->hdev, ST21NFCA_APDU_READER_GATE,
+				ST21NFCA_EVT_SE_SOFT_RESET, NULL, 0);
+	} else {
+		info->se_info.xch_error = false;
+		nfc_hci_send_event(info->hdev, ST21NFCA_DEVICE_MGNT_GATE,
+				ST21NFCA_EVT_SE_HARD_RESET, &param, 1);
+	}
+	info->se_info.cb(info->se_info.cb_context, NULL, 0, -ETIME);
+}
+
+static void st21nfca_se_activation_timeout(unsigned long data)
+{
+	struct st21nfca_hci_info *info = (struct st21nfca_hci_info *) data;
+
+	pr_debug("\n");
+
+	info->se_info.se_active = false;
+
+	complete(&info->se_info.req_completion);
+}
+
+/*
+ * Returns:
+ * <= 0: driver handled the event, skb consumed
+ *    1: driver does not handle the event, please do standard processing
+ */
+int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,
+				u8 event, struct sk_buff *skb)
+{
+	int r = 0;
+
+	pr_debug("connectivity gate event: %x\n", event);
+
+	switch (event) {
+	case ST21NFCA_EVT_CONNECTIVITY:
+		break;
+	case ST21NFCA_EVT_TRANSACTION:
+		break;
+	default:
+		return 1;
+	}
+	kfree_skb(skb);
+	return r;
+}
+EXPORT_SYMBOL(st21nfca_connectivity_event_received);
+
+int st21nfca_apdu_reader_event_received(struct nfc_hci_dev *hdev,
+					u8 event, struct sk_buff *skb)
+{
+	int r = 0;
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	pr_debug("apdu reader gate event: %x\n", event);
+
+	switch (event) {
+	case ST21NFCA_EVT_TRANSMIT_DATA:
+		del_timer_sync(&info->se_info.bwi_timer);
+		info->se_info.bwi_active = false;
+		r = nfc_hci_send_event(hdev, ST21NFCA_DEVICE_MGNT_GATE,
+				ST21NFCA_EVT_SE_END_OF_APDU_TRANSFER, NULL, 0);
+		if (r < 0)
+			goto exit;
+
+		info->se_info.cb(info->se_info.cb_context,
+			skb->data, skb->len, 0);
+		break;
+	case ST21NFCA_EVT_WTX_REQUEST:
+		mod_timer(&info->se_info.bwi_timer, jiffies +
+				msecs_to_jiffies(info->se_info.wt_timeout));
+		break;
+	}
+
+exit:
+	kfree_skb(skb);
+	return r;
+}
+EXPORT_SYMBOL(st21nfca_apdu_reader_event_received);
+
+void st21nfca_se_init(struct nfc_hci_dev *hdev)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	init_completion(&info->se_info.req_completion);
+	/* initialize timers */
+	init_timer(&info->se_info.bwi_timer);
+	info->se_info.bwi_timer.data = (unsigned long)info;
+	info->se_info.bwi_timer.function = st21nfca_se_wt_timeout;
+	info->se_info.bwi_active = false;
+
+	init_timer(&info->se_info.se_active_timer);
+	info->se_info.se_active_timer.data = (unsigned long)info;
+	info->se_info.se_active_timer.function = st21nfca_se_activation_timeout;
+	info->se_info.se_active = false;
+
+	info->se_info.count_pipes = 0;
+	info->se_info.expected_pipes = 0;
+
+	info->se_info.xch_error = false;
+
+	info->se_info.wt_timeout =
+			ST21NFCA_BWI_TO_TIMEOUT(ST21NFCA_ATR_DEFAULT_BWI);
+}
+EXPORT_SYMBOL(st21nfca_se_init);
+
+void st21nfca_se_deinit(struct nfc_hci_dev *hdev)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	if (info->se_info.bwi_active)
+		del_timer_sync(&info->se_info.bwi_timer);
+	if (info->se_info.se_active)
+		del_timer_sync(&info->se_info.se_active_timer);
+
+	info->se_info.bwi_active = false;
+	info->se_info.se_active = false;
+}
+EXPORT_SYMBOL(st21nfca_se_deinit);
diff --git a/drivers/nfc/st21nfca/st21nfca_se.h b/drivers/nfc/st21nfca/st21nfca_se.h
new file mode 100644
index 00000000000..b172cfcaeb9
--- /dev/null
+++ b/drivers/nfc/st21nfca/st21nfca_se.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ST21NFCA_SE_H
+#define __ST21NFCA_SE_H
+
+#include <linux/skbuff.h>
+#include <linux/workqueue.h>
+
+/*
+ * ref ISO7816-3 chap 8.1. the initial character TS is followed by a
+ * sequence of at most 32 characters.
+ */
+#define ST21NFCA_ESE_MAX_LENGTH			33
+#define ST21NFCA_ESE_HOST_ID			0xc0
+
+struct st21nfca_se_info {
+	u8 atr[ST21NFCA_ESE_MAX_LENGTH];
+	struct completion req_completion;
+
+	struct timer_list bwi_timer;
+	int wt_timeout; /* in msecs */
+	bool bwi_active;
+
+	struct timer_list se_active_timer;
+	bool se_active;
+	int expected_pipes;
+	int count_pipes;
+
+	bool xch_error;
+
+	se_io_cb_t cb;
+	void *cb_context;
+};
+
+int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host,
+					u8 event, struct sk_buff *skb);
+int st21nfca_apdu_reader_event_received(struct nfc_hci_dev *hdev,
+					u8 event, struct sk_buff *skb);
+
+int st21nfca_hci_discover_se(struct nfc_hci_dev *hdev);
+int st21nfca_hci_enable_se(struct nfc_hci_dev *hdev, u32 se_idx);
+int st21nfca_hci_disable_se(struct nfc_hci_dev *hdev, u32 se_idx);
+int st21nfca_hci_se_io(struct nfc_hci_dev *hdev, u32 se_idx,
+		u8 *apdu, size_t apdu_length,
+		se_io_cb_t cb, void *cb_context);
+
+void st21nfca_se_init(struct nfc_hci_dev *hdev);
+void st21nfca_se_deinit(struct nfc_hci_dev *hdev);
+#endif /* __ST21NFCA_SE_H */
diff --git a/include/linux/platform_data/st21nfca.h b/include/linux/platform_data/st21nfca.h
index 5087fff96d8..cc2bdafb0c6 100644
--- a/include/linux/platform_data/st21nfca.h
+++ b/include/linux/platform_data/st21nfca.h
@@ -26,6 +26,8 @@
 struct st21nfca_nfc_platform_data {
 	unsigned int gpio_ena;
 	unsigned int irq_polarity;
+	bool is_ese_present;
+	bool is_uicc_present;
 };
 
 #endif /* _ST21NFCA_HCI_H_ */
-- 
cgit v1.2.3-70-g09d2


From 2477bc9a3db53540c64687c79efae9a7f1f60cef Mon Sep 17 00:00:00 2001
From: Jonathan Toppins <jtoppins@cumulusnetworks.com>
Date: Mon, 26 Jan 2015 01:16:57 -0500
Subject: bonding: update bond carrier state when min_links option changes

Cc: Andy Gospodarek <gospo@cumulusnetworks.com>
Signed-off-by: Jonathan Toppins <jtoppins@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c    | 2 +-
 drivers/net/bonding/bond_options.c | 1 +
 include/net/bonding.h              | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f47bc433407..f83ace6bab2 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -334,7 +334,7 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
  *
  * Returns zero if carrier state does not change, nonzero if it does.
  */
-static int bond_set_carrier(struct bonding *bond)
+int bond_set_carrier(struct bonding *bond)
 {
 	struct list_head *iter;
 	struct slave *slave;
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 9bd538d4474..4df28943d22 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1181,6 +1181,7 @@ static int bond_option_min_links_set(struct bonding *bond,
 	netdev_info(bond->dev, "Setting min links value to %llu\n",
 		    newval->value);
 	bond->params.min_links = newval->value;
+	bond_set_carrier(bond);
 
 	return 0;
 }
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 983a94b86b9..29f53eacac0 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -525,6 +525,7 @@ void bond_sysfs_slave_del(struct slave *slave);
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
 int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
 u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb);
+int bond_set_carrier(struct bonding *bond);
 void bond_select_active_slave(struct bonding *bond);
 void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
 void bond_create_debugfs(void);
-- 
cgit v1.2.3-70-g09d2


From 303691042d2fc996125f479cf01bd5ead8b90a16 Mon Sep 17 00:00:00 2001
From: Jonathan Toppins <jtoppins@cumulusnetworks.com>
Date: Mon, 26 Jan 2015 01:17:01 -0500
Subject: bonding: cleanup and remove dead code

fix sparse warning about non-static function

drivers/net/bonding/bond_main.c:3737:5: warning: symbol
'bond_3ad_xor_xmit' was not declared. Should it be static?

Reviewed-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: Jonathan Toppins <jtoppins@cumulusnetworks.com>
Signed-off-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 2 +-
 include/net/bond_3ad.h          | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index beff00e7e11..e229a8657de 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3734,7 +3734,7 @@ out:
  * usable slave array is formed in the control path. The xmit function
  * just calculates hash and sends the packet out.
  */
-int bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev)
+static int bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct bonding *bond = netdev_priv(dev);
 	struct slave *slave;
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index e01d903633e..f04cdbb7848 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -274,7 +274,6 @@ void bond_3ad_handle_link_change(struct slave *slave, char link);
 int  bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info);
 int  __bond_3ad_get_active_agg_info(struct bonding *bond,
 				    struct ad_info *ad_info);
-int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev);
 int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 			 struct slave *slave);
 int bond_3ad_set_carrier(struct bonding *bond);
-- 
cgit v1.2.3-70-g09d2


From 4967082b469320eeba54ffbca632af1962858fb7 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Mon, 26 Jan 2015 14:10:53 +0100
Subject: vxlan: advertise link netns in fdb messages

Previous commit is based on a wrong assumption, fdb messages are always sent
into the netns where the interface stands (see vxlan_fdb_notify()).

These fdb messages doesn't embed the rtnl attribute IFLA_LINK_NETNSID, thus we
need to add it (useful to interpret NDA_IFINDEX or NDA_DST for example).

Note also that vxlan_nlmsg_size() was not updated.

Fixes: 193523bf9373 ("vxlan: advertise netns of vxlan dev in fdb msg")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c            | 5 +++--
 include/uapi/linux/neighbour.h | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 87736e65cd1..31bac2a21ce 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -341,8 +341,8 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	ndm->ndm_type = RTN_UNICAST;
 
 	if (!net_eq(dev_net(vxlan->dev), vxlan->net) &&
-	    nla_put_s32(skb, NDA_NDM_IFINDEX_NETNSID,
-			peernet2id(vxlan->net, dev_net(vxlan->dev))))
+	    nla_put_s32(skb, NDA_LINK_NETNSID,
+			peernet2id(dev_net(vxlan->dev), vxlan->net)))
 		goto nla_put_failure;
 
 	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
@@ -385,6 +385,7 @@ static inline size_t vxlan_nlmsg_size(void)
 		+ nla_total_size(sizeof(__be16)) /* NDA_PORT */
 		+ nla_total_size(sizeof(__be32)) /* NDA_VNI */
 		+ nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */
+		+ nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */
 		+ nla_total_size(sizeof(struct nda_cacheinfo));
 }
 
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index 38f236853cc..3873a35509a 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -25,7 +25,7 @@ enum {
 	NDA_VNI,
 	NDA_IFINDEX,
 	NDA_MASTER,
-	NDA_NDM_IFINDEX_NETNSID,
+	NDA_LINK_NETNSID,
 	__NDA_MAX
 };
 
-- 
cgit v1.2.3-70-g09d2


From be6a6b43b597a37d96dbf74985f72045ccef0940 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 27 Jan 2015 15:57:59 +0200
Subject: net/mlx4_core: Add bad-cable event support

If the firmware can detect a bad cable, allow it to generate an
event, and print the problem in the log.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 22 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/fw.c |  9 ++++++++-
 include/linux/mlx4/device.h             | 14 +++++++++++++-
 3 files changed, 43 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 2f2e6067426..4df006d8afa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -88,6 +88,8 @@ static u64 get_async_ev_mask(struct mlx4_dev *dev)
 	u64 async_ev_mask = MLX4_ASYNC_EVENT_MASK;
 	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV)
 		async_ev_mask |= (1ull << MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT);
+	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT)
+		async_ev_mask |= (1ull << MLX4_EVENT_TYPE_RECOVERABLE_ERROR_EVENT);
 
 	return async_ev_mask;
 }
@@ -736,6 +738,26 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					    (unsigned long) eqe);
 			break;
 
+		case MLX4_EVENT_TYPE_RECOVERABLE_ERROR_EVENT:
+			switch (eqe->subtype) {
+			case MLX4_RECOVERABLE_ERROR_EVENT_SUBTYPE_BAD_CABLE:
+				mlx4_warn(dev, "Bad cable detected on port %u\n",
+					  eqe->event.bad_cable.port);
+				break;
+			case MLX4_RECOVERABLE_ERROR_EVENT_SUBTYPE_UNSUPPORTED_CABLE:
+				mlx4_warn(dev, "Unsupported cable detected\n");
+				break;
+			default:
+				mlx4_dbg(dev,
+					 "Unhandled recoverable error event detected: %02x(%02x) on EQ %d at index %u. owner=%x, nent=0x%x, ownership=%s\n",
+					 eqe->type, eqe->subtype, eq->eqn,
+					 eq->cons_index, eqe->owner, eq->nent,
+					 !!(eqe->owner & 0x80) ^
+					 !!(eq->cons_index & eq->nent) ? "HW" : "SW");
+				break;
+			}
+			break;
+
 		case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
 		case MLX4_EVENT_TYPE_ECC_DETECT:
 		default:
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 982861d1df4..2eadc2882e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -145,7 +145,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[16] = "CONFIG DEV support",
 		[17] = "Asymmetric EQs support",
 		[18] = "More than 80 VFs support",
-		[19] = "Performance optimized for limited rule configuration flow steering support"
+		[19] = "Performance optimized for limited rule configuration flow steering support",
+		[20] = "Recoverable error events support"
 	};
 	int i;
 
@@ -859,6 +860,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_ETH_BACKPL_OFFSET);
 	if (field32 & (1 << 0))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP;
+	if (field32 & (1 << 7))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_FW_REASSIGN_MAC);
 	if (field & 1<<6)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_REASSIGN_MAC_EN;
@@ -1562,6 +1565,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 #define INIT_HCA_VXLAN_OFFSET		 0x0c
 #define INIT_HCA_CACHELINE_SZ_OFFSET	 0x0e
 #define INIT_HCA_FLAGS_OFFSET		 0x014
+#define INIT_HCA_RECOVERABLE_ERROR_EVENT_OFFSET 0x018
 #define INIT_HCA_QPC_OFFSET		 0x020
 #define	 INIT_HCA_QPC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x10)
 #define	 INIT_HCA_LOG_QP_OFFSET		 (INIT_HCA_QPC_OFFSET + 0x17)
@@ -1668,6 +1672,9 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 		dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE;
 	}
 
+	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT)
+		*(inbox + INIT_HCA_RECOVERABLE_ERROR_EVENT_OFFSET / 4) |= cpu_to_be32(1 << 31);
+
 	/* QPC/EEC/CQC/EQC/RDMARC attributes */
 
 	MLX4_PUT(inbox, param->qpc_base,      INIT_HCA_QPC_BASE_OFFSET);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 5ef54e145e4..c95d659a39f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -200,7 +200,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16,
 	MLX4_DEV_CAP_FLAG2_SYS_EQS		= 1LL <<  17,
 	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18,
-	MLX4_DEV_CAP_FLAG2_FS_A0		= 1LL <<  19
+	MLX4_DEV_CAP_FLAG2_FS_A0		= 1LL <<  19,
+	MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20
 };
 
 enum {
@@ -280,6 +281,7 @@ enum mlx4_event {
 	MLX4_EVENT_TYPE_FATAL_WARNING	   = 0x1b,
 	MLX4_EVENT_TYPE_FLR_EVENT	   = 0x1c,
 	MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT = 0x1d,
+	MLX4_EVENT_TYPE_RECOVERABLE_ERROR_EVENT  = 0x3e,
 	MLX4_EVENT_TYPE_NONE		   = 0xff,
 };
 
@@ -288,6 +290,11 @@ enum {
 	MLX4_PORT_CHANGE_SUBTYPE_ACTIVE	= 4
 };
 
+enum {
+	MLX4_RECOVERABLE_ERROR_EVENT_SUBTYPE_BAD_CABLE		= 1,
+	MLX4_RECOVERABLE_ERROR_EVENT_SUBTYPE_UNSUPPORTED_CABLE	= 2,
+};
+
 enum {
 	MLX4_FATAL_WARNING_SUBTYPE_WARMING = 0,
 };
@@ -860,6 +867,11 @@ struct mlx4_eqe {
 				} __packed tbl_change_info;
 			} params;
 		} __packed port_mgmt_change;
+		struct {
+			u8 reserved[3];
+			u8 port;
+			u32 reserved1[5];
+		} __packed bad_cable;
 	}			event;
 	u8			slave_id;
 	u8			reserved3[2];
-- 
cgit v1.2.3-70-g09d2


From 5a03108689c6f3e448a920b42af04e6d28401f80 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Tue, 27 Jan 2015 15:58:02 +0200
Subject: net/mlx4_core: Adjust command timeouts to conform to the firmware
 spec

The firmware spec states that the timeout for all commands should be 60 seconds.

In the past, the spec indicated that there were several classes of timeout
(short, medium, and long).  The driver has these different timeout classes.
We leave the class differentiation in the driver as-is (to protect against any
future spec changes), but set the timeout for all classes to be 60 seconds.

In addition, we fix a few commands which had hard-coded numeric timeouts specified.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/fw.c | 19 ++++++++++---------
 drivers/net/ethernet/mellanox/mlx4/mr.c |  4 ++--
 include/linux/mlx4/cmd.h                |  6 +++---
 3 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 2aa7c232d0b..0c90d1072e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1774,8 +1774,8 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 		MLX4_PUT(inbox, parser_params,	INIT_HCA_VXLAN_OFFSET);
 	}
 
-	err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000,
-		       MLX4_CMD_NATIVE);
+	err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA,
+		       MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 
 	if (err)
 		mlx4_err(dev, "INIT_HCA returns %d\n", err);
@@ -2029,7 +2029,7 @@ int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
 	if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) {
 		if (priv->mfunc.master.init_port_ref[port] == 1) {
 			err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT,
-				       1000, MLX4_CMD_NATIVE);
+				       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 			if (err)
 				return err;
 		}
@@ -2040,7 +2040,7 @@ int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			if (!priv->mfunc.master.qp0_state[port].qp0_active &&
 			    priv->mfunc.master.qp0_state[port].port_active) {
 				err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT,
-					       1000, MLX4_CMD_NATIVE);
+					       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 				if (err)
 					return err;
 				priv->mfunc.master.slave_state[slave].init_port_mask &= ~(1 << port);
@@ -2055,15 +2055,15 @@ int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
 
 int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port)
 {
-	return mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000,
-			MLX4_CMD_WRAPPED);
+	return mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT,
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 }
 EXPORT_SYMBOL_GPL(mlx4_CLOSE_PORT);
 
 int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic)
 {
-	return mlx4_cmd(dev, 0, 0, panic, MLX4_CMD_CLOSE_HCA, 1000,
-			MLX4_CMD_NATIVE);
+	return mlx4_cmd(dev, 0, 0, panic, MLX4_CMD_CLOSE_HCA,
+			MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 }
 
 struct mlx4_config_dev {
@@ -2202,7 +2202,8 @@ int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
 int mlx4_NOP(struct mlx4_dev *dev)
 {
 	/* Input modifier of 0x1f means "finish as soon as possible." */
-	return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100, MLX4_CMD_NATIVE);
+	return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, MLX4_CMD_TIME_CLASS_A,
+			MLX4_CMD_NATIVE);
 }
 
 int mlx4_get_phys_port_id(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 8dbdf1d2935..d21e884a083 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -1155,7 +1155,7 @@ EXPORT_SYMBOL_GPL(mlx4_fmr_free);
 
 int mlx4_SYNC_TPT(struct mlx4_dev *dev)
 {
-	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT, 1000,
-			MLX4_CMD_NATIVE);
+	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT,
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 }
 EXPORT_SYMBOL_GPL(mlx4_SYNC_TPT);
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index c989442ffc6..ae95adc7850 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -165,9 +165,9 @@ enum {
 };
 
 enum {
-	MLX4_CMD_TIME_CLASS_A	= 10000,
-	MLX4_CMD_TIME_CLASS_B	= 10000,
-	MLX4_CMD_TIME_CLASS_C	= 10000,
+	MLX4_CMD_TIME_CLASS_A	= 60000,
+	MLX4_CMD_TIME_CLASS_B	= 60000,
+	MLX4_CMD_TIME_CLASS_C	= 60000,
 };
 
 enum {
-- 
cgit v1.2.3-70-g09d2


From 14bf61ffe6ac54afcd1e888a4407fe16054483db Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 9 Oct 2014 16:03:13 +0200
Subject: quota: Switch ->get_dqblk() and ->set_dqblk() to use bytes as space
 units

Currently ->get_dqblk() and ->set_dqblk() use struct fs_disk_quota which
tracks space limits and usage in 512-byte blocks. However VFS quotas
track usage in bytes (as some filesystems require that) and we need to
somehow pass this information. Upto now it wasn't a problem because we
didn't do any unit conversion (thus VFS quota routines happily stuck
number of bytes into d_bcount field of struct fd_disk_quota). Only if
you tried to use Q_XGETQUOTA or Q_XSETQLIM for VFS quotas (or Q_GETQUOTA
/ Q_SETQUOTA for XFS quotas), you got bogus results. Hardly anyone
tried this but reportedly some Samba users hit the problem in practice.
So when we want interfaces compatible we need to fix this.

We bite the bullet and define another quota structure used for passing
information from/to ->get_dqblk()/->set_dqblk. It's somewhat sad we have
to have more conversion routines in fs/quota/quota.c and another copying
of quota structure slows down getting of quota information by about 2%
but it seems cleaner than overloading e.g. units of d_bcount to bytes.

CC: stable@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/gfs2/quota.c          |  49 +++++++-------
 fs/quota/dquot.c         |  83 ++++++++++++------------
 fs/quota/quota.c         | 162 +++++++++++++++++++++++++++++++++++++++--------
 fs/xfs/xfs_qm.h          |   4 +-
 fs/xfs/xfs_qm_syscalls.c | 156 +++++++++++++++++++--------------------------
 fs/xfs/xfs_quotaops.c    |   8 +--
 include/linux/quota.h    |  47 +++++++++++++-
 include/linux/quotaops.h |   4 +-
 8 files changed, 318 insertions(+), 195 deletions(-)

(limited to 'include')

diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index c8b148bbdc8..3e193cb3699 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -667,7 +667,7 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change)
 
 static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 			     s64 change, struct gfs2_quota_data *qd,
-			     struct fs_disk_quota *fdq)
+			     struct qc_dqblk *fdq)
 {
 	struct inode *inode = &ip->i_inode;
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -697,16 +697,16 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	be64_add_cpu(&q.qu_value, change);
 	qd->qd_qb.qb_value = q.qu_value;
 	if (fdq) {
-		if (fdq->d_fieldmask & FS_DQ_BSOFT) {
-			q.qu_warn = cpu_to_be64(fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPC_SOFT) {
+			q.qu_warn = cpu_to_be64(fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_warn = q.qu_warn;
 		}
-		if (fdq->d_fieldmask & FS_DQ_BHARD) {
-			q.qu_limit = cpu_to_be64(fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPC_HARD) {
+			q.qu_limit = cpu_to_be64(fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_limit = q.qu_limit;
 		}
-		if (fdq->d_fieldmask & FS_DQ_BCOUNT) {
-			q.qu_value = cpu_to_be64(fdq->d_bcount >> sdp->sd_fsb2bb_shift);
+		if (fdq->d_fieldmask & QC_SPACE) {
+			q.qu_value = cpu_to_be64(fdq->d_space >> sdp->sd_sb.sb_bsize_shift);
 			qd->qd_qb.qb_value = q.qu_value;
 		}
 	}
@@ -1497,7 +1497,7 @@ static int gfs2_quota_get_xstate(struct super_block *sb,
 }
 
 static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
-			  struct fs_disk_quota *fdq)
+			  struct qc_dqblk *fdq)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_quota_lvb *qlvb;
@@ -1505,7 +1505,7 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
 	struct gfs2_holder q_gh;
 	int error;
 
-	memset(fdq, 0, sizeof(struct fs_disk_quota));
+	memset(fdq, 0, sizeof(*fdq));
 
 	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
 		return -ESRCH; /* Crazy XFS error code */
@@ -1522,12 +1522,9 @@ static int gfs2_get_dqblk(struct super_block *sb, struct kqid qid,
 		goto out;
 
 	qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lksb.sb_lvbptr;
-	fdq->d_version = FS_DQUOT_VERSION;
-	fdq->d_flags = (qid.type == USRQUOTA) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
-	fdq->d_id = from_kqid_munged(current_user_ns(), qid);
-	fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_fsb2bb_shift;
-	fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_fsb2bb_shift;
-	fdq->d_bcount = be64_to_cpu(qlvb->qb_value) << sdp->sd_fsb2bb_shift;
+	fdq->d_spc_hardlimit = be64_to_cpu(qlvb->qb_limit) << sdp->sd_sb.sb_bsize_shift;
+	fdq->d_spc_softlimit = be64_to_cpu(qlvb->qb_warn) << sdp->sd_sb.sb_bsize_shift;
+	fdq->d_space = be64_to_cpu(qlvb->qb_value) << sdp->sd_sb.sb_bsize_shift;
 
 	gfs2_glock_dq_uninit(&q_gh);
 out:
@@ -1536,10 +1533,10 @@ out:
 }
 
 /* GFS2 only supports a subset of the XFS fields */
-#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD|FS_DQ_BCOUNT)
+#define GFS2_FIELDMASK (QC_SPC_SOFT|QC_SPC_HARD|QC_SPACE)
 
 static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
-			  struct fs_disk_quota *fdq)
+			  struct qc_dqblk *fdq)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
@@ -1583,17 +1580,17 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
 		goto out_i;
 
 	/* If nothing has changed, this is a no-op */
-	if ((fdq->d_fieldmask & FS_DQ_BSOFT) &&
-	    ((fdq->d_blk_softlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
-		fdq->d_fieldmask ^= FS_DQ_BSOFT;
+	if ((fdq->d_fieldmask & QC_SPC_SOFT) &&
+	    ((fdq->d_spc_softlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_warn)))
+		fdq->d_fieldmask ^= QC_SPC_SOFT;
 
-	if ((fdq->d_fieldmask & FS_DQ_BHARD) &&
-	    ((fdq->d_blk_hardlimit >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
-		fdq->d_fieldmask ^= FS_DQ_BHARD;
+	if ((fdq->d_fieldmask & QC_SPC_HARD) &&
+	    ((fdq->d_spc_hardlimit >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_limit)))
+		fdq->d_fieldmask ^= QC_SPC_HARD;
 
-	if ((fdq->d_fieldmask & FS_DQ_BCOUNT) &&
-	    ((fdq->d_bcount >> sdp->sd_fsb2bb_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
-		fdq->d_fieldmask ^= FS_DQ_BCOUNT;
+	if ((fdq->d_fieldmask & QC_SPACE) &&
+	    ((fdq->d_space >> sdp->sd_sb.sb_bsize_shift) == be64_to_cpu(qd->qd_qb.qb_value)))
+		fdq->d_fieldmask ^= QC_SPACE;
 
 	if (fdq->d_fieldmask == 0)
 		goto out_i;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 8f0acef3d18..69df5b23984 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2396,30 +2396,25 @@ static inline qsize_t stoqb(qsize_t space)
 }
 
 /* Generic routine for getting common part of quota structure */
-static void do_get_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
+static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 
 	memset(di, 0, sizeof(*di));
-	di->d_version = FS_DQUOT_VERSION;
-	di->d_flags = dquot->dq_id.type == USRQUOTA ?
-			FS_USER_QUOTA : FS_GROUP_QUOTA;
-	di->d_id = from_kqid_munged(current_user_ns(), dquot->dq_id);
-
 	spin_lock(&dq_data_lock);
-	di->d_blk_hardlimit = stoqb(dm->dqb_bhardlimit);
-	di->d_blk_softlimit = stoqb(dm->dqb_bsoftlimit);
+	di->d_spc_hardlimit = dm->dqb_bhardlimit;
+	di->d_spc_softlimit = dm->dqb_bsoftlimit;
 	di->d_ino_hardlimit = dm->dqb_ihardlimit;
 	di->d_ino_softlimit = dm->dqb_isoftlimit;
-	di->d_bcount = dm->dqb_curspace + dm->dqb_rsvspace;
-	di->d_icount = dm->dqb_curinodes;
-	di->d_btimer = dm->dqb_btime;
-	di->d_itimer = dm->dqb_itime;
+	di->d_space = dm->dqb_curspace + dm->dqb_rsvspace;
+	di->d_ino_count = dm->dqb_curinodes;
+	di->d_spc_timer = dm->dqb_btime;
+	di->d_ino_timer = dm->dqb_itime;
 	spin_unlock(&dq_data_lock);
 }
 
 int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
-		    struct fs_disk_quota *di)
+		    struct qc_dqblk *di)
 {
 	struct dquot *dquot;
 
@@ -2433,70 +2428,70 @@ int dquot_get_dqblk(struct super_block *sb, struct kqid qid,
 }
 EXPORT_SYMBOL(dquot_get_dqblk);
 
-#define VFS_FS_DQ_MASK \
-	(FS_DQ_BCOUNT | FS_DQ_BSOFT | FS_DQ_BHARD | \
-	 FS_DQ_ICOUNT | FS_DQ_ISOFT | FS_DQ_IHARD | \
-	 FS_DQ_BTIMER | FS_DQ_ITIMER)
+#define VFS_QC_MASK \
+	(QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \
+	 QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \
+	 QC_SPC_TIMER | QC_INO_TIMER)
 
 /* Generic routine for setting common part of quota structure */
-static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
+static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 {
 	struct mem_dqblk *dm = &dquot->dq_dqb;
 	int check_blim = 0, check_ilim = 0;
 	struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type];
 
-	if (di->d_fieldmask & ~VFS_FS_DQ_MASK)
+	if (di->d_fieldmask & ~VFS_QC_MASK)
 		return -EINVAL;
 
-	if (((di->d_fieldmask & FS_DQ_BSOFT) &&
-	     (di->d_blk_softlimit > dqi->dqi_maxblimit)) ||
-	    ((di->d_fieldmask & FS_DQ_BHARD) &&
-	     (di->d_blk_hardlimit > dqi->dqi_maxblimit)) ||
-	    ((di->d_fieldmask & FS_DQ_ISOFT) &&
+	if (((di->d_fieldmask & QC_SPC_SOFT) &&
+	     stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) ||
+	    ((di->d_fieldmask & QC_SPC_HARD) &&
+	     stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) ||
+	    ((di->d_fieldmask & QC_INO_SOFT) &&
 	     (di->d_ino_softlimit > dqi->dqi_maxilimit)) ||
-	    ((di->d_fieldmask & FS_DQ_IHARD) &&
+	    ((di->d_fieldmask & QC_INO_HARD) &&
 	     (di->d_ino_hardlimit > dqi->dqi_maxilimit)))
 		return -ERANGE;
 
 	spin_lock(&dq_data_lock);
-	if (di->d_fieldmask & FS_DQ_BCOUNT) {
-		dm->dqb_curspace = di->d_bcount - dm->dqb_rsvspace;
+	if (di->d_fieldmask & QC_SPACE) {
+		dm->dqb_curspace = di->d_space - dm->dqb_rsvspace;
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_BSOFT)
-		dm->dqb_bsoftlimit = qbtos(di->d_blk_softlimit);
-	if (di->d_fieldmask & FS_DQ_BHARD)
-		dm->dqb_bhardlimit = qbtos(di->d_blk_hardlimit);
-	if (di->d_fieldmask & (FS_DQ_BSOFT | FS_DQ_BHARD)) {
+	if (di->d_fieldmask & QC_SPC_SOFT)
+		dm->dqb_bsoftlimit = di->d_spc_softlimit;
+	if (di->d_fieldmask & QC_SPC_HARD)
+		dm->dqb_bhardlimit = di->d_spc_hardlimit;
+	if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) {
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ICOUNT) {
-		dm->dqb_curinodes = di->d_icount;
+	if (di->d_fieldmask & QC_INO_COUNT) {
+		dm->dqb_curinodes = di->d_ino_count;
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ISOFT)
+	if (di->d_fieldmask & QC_INO_SOFT)
 		dm->dqb_isoftlimit = di->d_ino_softlimit;
-	if (di->d_fieldmask & FS_DQ_IHARD)
+	if (di->d_fieldmask & QC_INO_HARD)
 		dm->dqb_ihardlimit = di->d_ino_hardlimit;
-	if (di->d_fieldmask & (FS_DQ_ISOFT | FS_DQ_IHARD)) {
+	if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) {
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_BTIMER) {
-		dm->dqb_btime = di->d_btimer;
+	if (di->d_fieldmask & QC_SPC_TIMER) {
+		dm->dqb_btime = di->d_spc_timer;
 		check_blim = 1;
 		set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
 	}
 
-	if (di->d_fieldmask & FS_DQ_ITIMER) {
-		dm->dqb_itime = di->d_itimer;
+	if (di->d_fieldmask & QC_INO_TIMER) {
+		dm->dqb_itime = di->d_ino_timer;
 		check_ilim = 1;
 		set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
 	}
@@ -2506,7 +2501,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
 		    dm->dqb_curspace < dm->dqb_bsoftlimit) {
 			dm->dqb_btime = 0;
 			clear_bit(DQ_BLKS_B, &dquot->dq_flags);
-		} else if (!(di->d_fieldmask & FS_DQ_BTIMER))
+		} else if (!(di->d_fieldmask & QC_SPC_TIMER))
 			/* Set grace only if user hasn't provided his own... */
 			dm->dqb_btime = get_seconds() + dqi->dqi_bgrace;
 	}
@@ -2515,7 +2510,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
 		    dm->dqb_curinodes < dm->dqb_isoftlimit) {
 			dm->dqb_itime = 0;
 			clear_bit(DQ_INODES_B, &dquot->dq_flags);
-		} else if (!(di->d_fieldmask & FS_DQ_ITIMER))
+		} else if (!(di->d_fieldmask & QC_INO_TIMER))
 			/* Set grace only if user hasn't provided his own... */
 			dm->dqb_itime = get_seconds() + dqi->dqi_igrace;
 	}
@@ -2531,7 +2526,7 @@ static int do_set_dqblk(struct dquot *dquot, struct fs_disk_quota *di)
 }
 
 int dquot_set_dqblk(struct super_block *sb, struct kqid qid,
-		  struct fs_disk_quota *di)
+		  struct qc_dqblk *di)
 {
 	struct dquot *dquot;
 	int rc;
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 2aa4151f99d..6f3856328ee 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -118,17 +118,27 @@ static int quota_setinfo(struct super_block *sb, int type, void __user *addr)
 	return sb->s_qcop->set_info(sb, type, &info);
 }
 
-static void copy_to_if_dqblk(struct if_dqblk *dst, struct fs_disk_quota *src)
+static inline qsize_t qbtos(qsize_t blocks)
+{
+	return blocks << QIF_DQBLKSIZE_BITS;
+}
+
+static inline qsize_t stoqb(qsize_t space)
+{
+	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
+}
+
+static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src)
 {
 	memset(dst, 0, sizeof(*dst));
-	dst->dqb_bhardlimit = src->d_blk_hardlimit;
-	dst->dqb_bsoftlimit = src->d_blk_softlimit;
-	dst->dqb_curspace = src->d_bcount;
+	dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit);
+	dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit);
+	dst->dqb_curspace = src->d_space;
 	dst->dqb_ihardlimit = src->d_ino_hardlimit;
 	dst->dqb_isoftlimit = src->d_ino_softlimit;
-	dst->dqb_curinodes = src->d_icount;
-	dst->dqb_btime = src->d_btimer;
-	dst->dqb_itime = src->d_itimer;
+	dst->dqb_curinodes = src->d_ino_count;
+	dst->dqb_btime = src->d_spc_timer;
+	dst->dqb_itime = src->d_ino_timer;
 	dst->dqb_valid = QIF_ALL;
 }
 
@@ -136,7 +146,7 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 			  void __user *addr)
 {
 	struct kqid qid;
-	struct fs_disk_quota fdq;
+	struct qc_dqblk fdq;
 	struct if_dqblk idq;
 	int ret;
 
@@ -154,36 +164,36 @@ static int quota_getquota(struct super_block *sb, int type, qid_t id,
 	return 0;
 }
 
-static void copy_from_if_dqblk(struct fs_disk_quota *dst, struct if_dqblk *src)
+static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src)
 {
-	dst->d_blk_hardlimit = src->dqb_bhardlimit;
-	dst->d_blk_softlimit  = src->dqb_bsoftlimit;
-	dst->d_bcount = src->dqb_curspace;
+	dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit);
+	dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit);
+	dst->d_space = src->dqb_curspace;
 	dst->d_ino_hardlimit = src->dqb_ihardlimit;
 	dst->d_ino_softlimit = src->dqb_isoftlimit;
-	dst->d_icount = src->dqb_curinodes;
-	dst->d_btimer = src->dqb_btime;
-	dst->d_itimer = src->dqb_itime;
+	dst->d_ino_count = src->dqb_curinodes;
+	dst->d_spc_timer = src->dqb_btime;
+	dst->d_ino_timer = src->dqb_itime;
 
 	dst->d_fieldmask = 0;
 	if (src->dqb_valid & QIF_BLIMITS)
-		dst->d_fieldmask |= FS_DQ_BSOFT | FS_DQ_BHARD;
+		dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD;
 	if (src->dqb_valid & QIF_SPACE)
-		dst->d_fieldmask |= FS_DQ_BCOUNT;
+		dst->d_fieldmask |= QC_SPACE;
 	if (src->dqb_valid & QIF_ILIMITS)
-		dst->d_fieldmask |= FS_DQ_ISOFT | FS_DQ_IHARD;
+		dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD;
 	if (src->dqb_valid & QIF_INODES)
-		dst->d_fieldmask |= FS_DQ_ICOUNT;
+		dst->d_fieldmask |= QC_INO_COUNT;
 	if (src->dqb_valid & QIF_BTIME)
-		dst->d_fieldmask |= FS_DQ_BTIMER;
+		dst->d_fieldmask |= QC_SPC_TIMER;
 	if (src->dqb_valid & QIF_ITIME)
-		dst->d_fieldmask |= FS_DQ_ITIMER;
+		dst->d_fieldmask |= QC_INO_TIMER;
 }
 
 static int quota_setquota(struct super_block *sb, int type, qid_t id,
 			  void __user *addr)
 {
-	struct fs_disk_quota fdq;
+	struct qc_dqblk fdq;
 	struct if_dqblk idq;
 	struct kqid qid;
 
@@ -247,10 +257,78 @@ static int quota_getxstatev(struct super_block *sb, void __user *addr)
 	return ret;
 }
 
+/*
+ * XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them
+ * out of there as xfsprogs rely on definitions being in that header file. So
+ * just define same functions here for quota purposes.
+ */
+#define XFS_BB_SHIFT 9
+
+static inline u64 quota_bbtob(u64 blocks)
+{
+	return blocks << XFS_BB_SHIFT;
+}
+
+static inline u64 quota_btobb(u64 bytes)
+{
+	return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT;
+}
+
+static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src)
+{
+	dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit);
+	dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit);
+	dst->d_ino_hardlimit = src->d_ino_hardlimit;
+	dst->d_ino_softlimit = src->d_ino_softlimit;
+	dst->d_space = quota_bbtob(src->d_bcount);
+	dst->d_ino_count = src->d_icount;
+	dst->d_ino_timer = src->d_itimer;
+	dst->d_spc_timer = src->d_btimer;
+	dst->d_ino_warns = src->d_iwarns;
+	dst->d_spc_warns = src->d_bwarns;
+	dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit);
+	dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit);
+	dst->d_rt_space = quota_bbtob(src->d_rtbcount);
+	dst->d_rt_spc_timer = src->d_rtbtimer;
+	dst->d_rt_spc_warns = src->d_rtbwarns;
+	dst->d_fieldmask = 0;
+	if (src->d_fieldmask & FS_DQ_ISOFT)
+		dst->d_fieldmask |= QC_INO_SOFT;
+	if (src->d_fieldmask & FS_DQ_IHARD)
+		dst->d_fieldmask |= QC_INO_HARD;
+	if (src->d_fieldmask & FS_DQ_BSOFT)
+		dst->d_fieldmask |= QC_SPC_SOFT;
+	if (src->d_fieldmask & FS_DQ_BHARD)
+		dst->d_fieldmask |= QC_SPC_HARD;
+	if (src->d_fieldmask & FS_DQ_RTBSOFT)
+		dst->d_fieldmask |= QC_RT_SPC_SOFT;
+	if (src->d_fieldmask & FS_DQ_RTBHARD)
+		dst->d_fieldmask |= QC_RT_SPC_HARD;
+	if (src->d_fieldmask & FS_DQ_BTIMER)
+		dst->d_fieldmask |= QC_SPC_TIMER;
+	if (src->d_fieldmask & FS_DQ_ITIMER)
+		dst->d_fieldmask |= QC_INO_TIMER;
+	if (src->d_fieldmask & FS_DQ_RTBTIMER)
+		dst->d_fieldmask |= QC_RT_SPC_TIMER;
+	if (src->d_fieldmask & FS_DQ_BWARNS)
+		dst->d_fieldmask |= QC_SPC_WARNS;
+	if (src->d_fieldmask & FS_DQ_IWARNS)
+		dst->d_fieldmask |= QC_INO_WARNS;
+	if (src->d_fieldmask & FS_DQ_RTBWARNS)
+		dst->d_fieldmask |= QC_RT_SPC_WARNS;
+	if (src->d_fieldmask & FS_DQ_BCOUNT)
+		dst->d_fieldmask |= QC_SPACE;
+	if (src->d_fieldmask & FS_DQ_ICOUNT)
+		dst->d_fieldmask |= QC_INO_COUNT;
+	if (src->d_fieldmask & FS_DQ_RTBCOUNT)
+		dst->d_fieldmask |= QC_RT_SPACE;
+}
+
 static int quota_setxquota(struct super_block *sb, int type, qid_t id,
 			   void __user *addr)
 {
 	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
 	struct kqid qid;
 
 	if (copy_from_user(&fdq, addr, sizeof(fdq)))
@@ -260,13 +338,44 @@ static int quota_setxquota(struct super_block *sb, int type, qid_t id,
 	qid = make_kqid(current_user_ns(), type, id);
 	if (!qid_valid(qid))
 		return -EINVAL;
-	return sb->s_qcop->set_dqblk(sb, qid, &fdq);
+	copy_from_xfs_dqblk(&qdq, &fdq);
+	return sb->s_qcop->set_dqblk(sb, qid, &qdq);
+}
+
+static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src,
+			      int type, qid_t id)
+{
+	memset(dst, 0, sizeof(*dst));
+	dst->d_version = FS_DQUOT_VERSION;
+	dst->d_id = id;
+	if (type == USRQUOTA)
+		dst->d_flags = FS_USER_QUOTA;
+	else if (type == PRJQUOTA)
+		dst->d_flags = FS_PROJ_QUOTA;
+	else
+		dst->d_flags = FS_GROUP_QUOTA;
+	dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit);
+	dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit);
+	dst->d_ino_hardlimit = src->d_ino_hardlimit;
+	dst->d_ino_softlimit = src->d_ino_softlimit;
+	dst->d_bcount = quota_btobb(src->d_space);
+	dst->d_icount = src->d_ino_count;
+	dst->d_itimer = src->d_ino_timer;
+	dst->d_btimer = src->d_spc_timer;
+	dst->d_iwarns = src->d_ino_warns;
+	dst->d_bwarns = src->d_spc_warns;
+	dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit);
+	dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit);
+	dst->d_rtbcount = quota_btobb(src->d_rt_space);
+	dst->d_rtbtimer = src->d_rt_spc_timer;
+	dst->d_rtbwarns = src->d_rt_spc_warns;
 }
 
 static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 			   void __user *addr)
 {
 	struct fs_disk_quota fdq;
+	struct qc_dqblk qdq;
 	struct kqid qid;
 	int ret;
 
@@ -275,8 +384,11 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 	qid = make_kqid(current_user_ns(), type, id);
 	if (!qid_valid(qid))
 		return -EINVAL;
-	ret = sb->s_qcop->get_dqblk(sb, qid, &fdq);
-	if (!ret && copy_to_user(addr, &fdq, sizeof(fdq)))
+	ret = sb->s_qcop->get_dqblk(sb, qid, &qdq);
+	if (ret)
+		return ret;
+	copy_to_xfs_dqblk(&fdq, &qdq, type, id);
+	if (copy_to_user(addr, &fdq, sizeof(fdq)))
 		return -EFAULT;
 	return ret;
 }
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 3a07a937e23..41f6c0b9d51 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -166,9 +166,9 @@ extern void		xfs_qm_dqrele_all_inodes(struct xfs_mount *, uint);
 /* quota ops */
 extern int		xfs_qm_scall_trunc_qfiles(struct xfs_mount *, uint);
 extern int		xfs_qm_scall_getquota(struct xfs_mount *, xfs_dqid_t,
-					uint, struct fs_disk_quota *);
+					uint, struct qc_dqblk *);
 extern int		xfs_qm_scall_setqlim(struct xfs_mount *, xfs_dqid_t, uint,
-					struct fs_disk_quota *);
+					struct qc_dqblk *);
 extern int		xfs_qm_scall_getqstat(struct xfs_mount *,
 					struct fs_quota_stat *);
 extern int		xfs_qm_scall_getqstatv(struct xfs_mount *,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 74fca68e43b..cb6168ec92c 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -39,7 +39,6 @@ STATIC int	xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
 					uint);
 STATIC uint	xfs_qm_export_flags(uint);
-STATIC uint	xfs_qm_export_qtype_flags(uint);
 
 /*
  * Turn off quota accounting and/or enforcement for all udquots and/or
@@ -573,8 +572,8 @@ xfs_qm_scall_getqstatv(
 	return 0;
 }
 
-#define XFS_DQ_MASK \
-	(FS_DQ_LIMIT_MASK | FS_DQ_TIMER_MASK | FS_DQ_WARNS_MASK)
+#define XFS_QC_MASK \
+	(QC_LIMIT_MASK | QC_TIMER_MASK | QC_WARNS_MASK)
 
 /*
  * Adjust quota limits, and start/stop timers accordingly.
@@ -584,7 +583,7 @@ xfs_qm_scall_setqlim(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
 	uint			type,
-	fs_disk_quota_t		*newlim)
+	struct qc_dqblk		*newlim)
 {
 	struct xfs_quotainfo	*q = mp->m_quotainfo;
 	struct xfs_disk_dquot	*ddq;
@@ -593,9 +592,9 @@ xfs_qm_scall_setqlim(
 	int			error;
 	xfs_qcnt_t		hard, soft;
 
-	if (newlim->d_fieldmask & ~XFS_DQ_MASK)
+	if (newlim->d_fieldmask & ~XFS_QC_MASK)
 		return -EINVAL;
-	if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0)
+	if ((newlim->d_fieldmask & XFS_QC_MASK) == 0)
 		return 0;
 
 	/*
@@ -633,11 +632,11 @@ xfs_qm_scall_setqlim(
 	/*
 	 * Make sure that hardlimits are >= soft limits before changing.
 	 */
-	hard = (newlim->d_fieldmask & FS_DQ_BHARD) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_hardlimit) :
+	hard = (newlim->d_fieldmask & QC_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_hardlimit) :
 			be64_to_cpu(ddq->d_blk_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_BSOFT) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_blk_softlimit) :
+	soft = (newlim->d_fieldmask & QC_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_spc_softlimit) :
 			be64_to_cpu(ddq->d_blk_softlimit);
 	if (hard == 0 || hard >= soft) {
 		ddq->d_blk_hardlimit = cpu_to_be64(hard);
@@ -650,11 +649,11 @@ xfs_qm_scall_setqlim(
 	} else {
 		xfs_debug(mp, "blkhard %Ld < blksoft %Ld", hard, soft);
 	}
-	hard = (newlim->d_fieldmask & FS_DQ_RTBHARD) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_hardlimit) :
+	hard = (newlim->d_fieldmask & QC_RT_SPC_HARD) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_hardlimit) :
 			be64_to_cpu(ddq->d_rtb_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_RTBSOFT) ?
-		(xfs_qcnt_t) XFS_BB_TO_FSB(mp, newlim->d_rtb_softlimit) :
+	soft = (newlim->d_fieldmask & QC_RT_SPC_SOFT) ?
+		(xfs_qcnt_t) XFS_B_TO_FSB(mp, newlim->d_rt_spc_softlimit) :
 			be64_to_cpu(ddq->d_rtb_softlimit);
 	if (hard == 0 || hard >= soft) {
 		ddq->d_rtb_hardlimit = cpu_to_be64(hard);
@@ -667,10 +666,10 @@ xfs_qm_scall_setqlim(
 		xfs_debug(mp, "rtbhard %Ld < rtbsoft %Ld", hard, soft);
 	}
 
-	hard = (newlim->d_fieldmask & FS_DQ_IHARD) ?
+	hard = (newlim->d_fieldmask & QC_INO_HARD) ?
 		(xfs_qcnt_t) newlim->d_ino_hardlimit :
 			be64_to_cpu(ddq->d_ino_hardlimit);
-	soft = (newlim->d_fieldmask & FS_DQ_ISOFT) ?
+	soft = (newlim->d_fieldmask & QC_INO_SOFT) ?
 		(xfs_qcnt_t) newlim->d_ino_softlimit :
 			be64_to_cpu(ddq->d_ino_softlimit);
 	if (hard == 0 || hard >= soft) {
@@ -687,12 +686,12 @@ xfs_qm_scall_setqlim(
 	/*
 	 * Update warnings counter(s) if requested
 	 */
-	if (newlim->d_fieldmask & FS_DQ_BWARNS)
-		ddq->d_bwarns = cpu_to_be16(newlim->d_bwarns);
-	if (newlim->d_fieldmask & FS_DQ_IWARNS)
-		ddq->d_iwarns = cpu_to_be16(newlim->d_iwarns);
-	if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
-		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rtbwarns);
+	if (newlim->d_fieldmask & QC_SPC_WARNS)
+		ddq->d_bwarns = cpu_to_be16(newlim->d_spc_warns);
+	if (newlim->d_fieldmask & QC_INO_WARNS)
+		ddq->d_iwarns = cpu_to_be16(newlim->d_ino_warns);
+	if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
+		ddq->d_rtbwarns = cpu_to_be16(newlim->d_rt_spc_warns);
 
 	if (id == 0) {
 		/*
@@ -702,24 +701,24 @@ xfs_qm_scall_setqlim(
 		 * soft and hard limit values (already done, above), and
 		 * for warnings.
 		 */
-		if (newlim->d_fieldmask & FS_DQ_BTIMER) {
-			q->qi_btimelimit = newlim->d_btimer;
-			ddq->d_btimer = cpu_to_be32(newlim->d_btimer);
+		if (newlim->d_fieldmask & QC_SPC_TIMER) {
+			q->qi_btimelimit = newlim->d_spc_timer;
+			ddq->d_btimer = cpu_to_be32(newlim->d_spc_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_ITIMER) {
-			q->qi_itimelimit = newlim->d_itimer;
-			ddq->d_itimer = cpu_to_be32(newlim->d_itimer);
+		if (newlim->d_fieldmask & QC_INO_TIMER) {
+			q->qi_itimelimit = newlim->d_ino_timer;
+			ddq->d_itimer = cpu_to_be32(newlim->d_ino_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_RTBTIMER) {
-			q->qi_rtbtimelimit = newlim->d_rtbtimer;
-			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rtbtimer);
+		if (newlim->d_fieldmask & QC_RT_SPC_TIMER) {
+			q->qi_rtbtimelimit = newlim->d_rt_spc_timer;
+			ddq->d_rtbtimer = cpu_to_be32(newlim->d_rt_spc_timer);
 		}
-		if (newlim->d_fieldmask & FS_DQ_BWARNS)
-			q->qi_bwarnlimit = newlim->d_bwarns;
-		if (newlim->d_fieldmask & FS_DQ_IWARNS)
-			q->qi_iwarnlimit = newlim->d_iwarns;
-		if (newlim->d_fieldmask & FS_DQ_RTBWARNS)
-			q->qi_rtbwarnlimit = newlim->d_rtbwarns;
+		if (newlim->d_fieldmask & QC_SPC_WARNS)
+			q->qi_bwarnlimit = newlim->d_spc_warns;
+		if (newlim->d_fieldmask & QC_INO_WARNS)
+			q->qi_iwarnlimit = newlim->d_ino_warns;
+		if (newlim->d_fieldmask & QC_RT_SPC_WARNS)
+			q->qi_rtbwarnlimit = newlim->d_rt_spc_warns;
 	} else {
 		/*
 		 * If the user is now over quota, start the timelimit.
@@ -824,7 +823,7 @@ xfs_qm_scall_getquota(
 	struct xfs_mount	*mp,
 	xfs_dqid_t		id,
 	uint			type,
-	struct fs_disk_quota	*dst)
+	struct qc_dqblk		*dst)
 {
 	struct xfs_dquot	*dqp;
 	int			error;
@@ -848,28 +847,25 @@ xfs_qm_scall_getquota(
 	}
 
 	memset(dst, 0, sizeof(*dst));
-	dst->d_version = FS_DQUOT_VERSION;
-	dst->d_flags = xfs_qm_export_qtype_flags(dqp->q_core.d_flags);
-	dst->d_id = be32_to_cpu(dqp->q_core.d_id);
-	dst->d_blk_hardlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
-	dst->d_blk_softlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit));
+	dst->d_spc_hardlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_hardlimit));
+	dst->d_spc_softlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_blk_softlimit));
 	dst->d_ino_hardlimit = be64_to_cpu(dqp->q_core.d_ino_hardlimit);
 	dst->d_ino_softlimit = be64_to_cpu(dqp->q_core.d_ino_softlimit);
-	dst->d_bcount = XFS_FSB_TO_BB(mp, dqp->q_res_bcount);
-	dst->d_icount = dqp->q_res_icount;
-	dst->d_btimer = be32_to_cpu(dqp->q_core.d_btimer);
-	dst->d_itimer = be32_to_cpu(dqp->q_core.d_itimer);
-	dst->d_iwarns = be16_to_cpu(dqp->q_core.d_iwarns);
-	dst->d_bwarns = be16_to_cpu(dqp->q_core.d_bwarns);
-	dst->d_rtb_hardlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit));
-	dst->d_rtb_softlimit =
-		XFS_FSB_TO_BB(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit));
-	dst->d_rtbcount = XFS_FSB_TO_BB(mp, dqp->q_res_rtbcount);
-	dst->d_rtbtimer = be32_to_cpu(dqp->q_core.d_rtbtimer);
-	dst->d_rtbwarns = be16_to_cpu(dqp->q_core.d_rtbwarns);
+	dst->d_space = XFS_FSB_TO_B(mp, dqp->q_res_bcount);
+	dst->d_ino_count = dqp->q_res_icount;
+	dst->d_spc_timer = be32_to_cpu(dqp->q_core.d_btimer);
+	dst->d_ino_timer = be32_to_cpu(dqp->q_core.d_itimer);
+	dst->d_ino_warns = be16_to_cpu(dqp->q_core.d_iwarns);
+	dst->d_spc_warns = be16_to_cpu(dqp->q_core.d_bwarns);
+	dst->d_rt_spc_hardlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_hardlimit));
+	dst->d_rt_spc_softlimit =
+		XFS_FSB_TO_B(mp, be64_to_cpu(dqp->q_core.d_rtb_softlimit));
+	dst->d_rt_space = XFS_FSB_TO_B(mp, dqp->q_res_rtbcount);
+	dst->d_rt_spc_timer = be32_to_cpu(dqp->q_core.d_rtbtimer);
+	dst->d_rt_spc_warns = be16_to_cpu(dqp->q_core.d_rtbwarns);
 
 	/*
 	 * Internally, we don't reset all the timers when quota enforcement
@@ -882,23 +878,23 @@ xfs_qm_scall_getquota(
 	     dqp->q_core.d_flags == XFS_DQ_GROUP) ||
 	    (!XFS_IS_PQUOTA_ENFORCED(mp) &&
 	     dqp->q_core.d_flags == XFS_DQ_PROJ)) {
-		dst->d_btimer = 0;
-		dst->d_itimer = 0;
-		dst->d_rtbtimer = 0;
+		dst->d_spc_timer = 0;
+		dst->d_ino_timer = 0;
+		dst->d_rt_spc_timer = 0;
 	}
 
 #ifdef DEBUG
-	if (((XFS_IS_UQUOTA_ENFORCED(mp) && dst->d_flags == FS_USER_QUOTA) ||
-	     (XFS_IS_GQUOTA_ENFORCED(mp) && dst->d_flags == FS_GROUP_QUOTA) ||
-	     (XFS_IS_PQUOTA_ENFORCED(mp) && dst->d_flags == FS_PROJ_QUOTA)) &&
-	    dst->d_id != 0) {
-		if ((dst->d_bcount > dst->d_blk_softlimit) &&
-		    (dst->d_blk_softlimit > 0)) {
-			ASSERT(dst->d_btimer != 0);
+	if (((XFS_IS_UQUOTA_ENFORCED(mp) && type == XFS_DQ_USER) ||
+	     (XFS_IS_GQUOTA_ENFORCED(mp) && type == XFS_DQ_GROUP) ||
+	     (XFS_IS_PQUOTA_ENFORCED(mp) && type == XFS_DQ_PROJ)) &&
+	    id != 0) {
+		if ((dst->d_space > dst->d_spc_softlimit) &&
+		    (dst->d_spc_softlimit > 0)) {
+			ASSERT(dst->d_spc_timer != 0);
 		}
-		if ((dst->d_icount > dst->d_ino_softlimit) &&
+		if ((dst->d_ino_count > dst->d_ino_softlimit) &&
 		    (dst->d_ino_softlimit > 0)) {
-			ASSERT(dst->d_itimer != 0);
+			ASSERT(dst->d_ino_timer != 0);
 		}
 	}
 #endif
@@ -907,26 +903,6 @@ out_put:
 	return error;
 }
 
-STATIC uint
-xfs_qm_export_qtype_flags(
-	uint flags)
-{
-	/*
-	 * Can't be more than one, or none.
-	 */
-	ASSERT((flags & (FS_PROJ_QUOTA | FS_USER_QUOTA)) !=
-		(FS_PROJ_QUOTA | FS_USER_QUOTA));
-	ASSERT((flags & (FS_PROJ_QUOTA | FS_GROUP_QUOTA)) !=
-		(FS_PROJ_QUOTA | FS_GROUP_QUOTA));
-	ASSERT((flags & (FS_USER_QUOTA | FS_GROUP_QUOTA)) !=
-		(FS_USER_QUOTA | FS_GROUP_QUOTA));
-	ASSERT((flags & (FS_PROJ_QUOTA|FS_USER_QUOTA|FS_GROUP_QUOTA)) != 0);
-
-	return (flags & XFS_DQ_USER) ?
-		FS_USER_QUOTA : (flags & XFS_DQ_PROJ) ?
-			FS_PROJ_QUOTA : FS_GROUP_QUOTA;
-}
-
 STATIC uint
 xfs_qm_export_flags(
 	uint flags)
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 7542bbeca6a..801a84c1cdc 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -131,7 +131,7 @@ STATIC int
 xfs_fs_get_dqblk(
 	struct super_block	*sb,
 	struct kqid		qid,
-	struct fs_disk_quota	*fdq)
+	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
@@ -141,14 +141,14 @@ xfs_fs_get_dqblk(
 		return -ESRCH;
 
 	return xfs_qm_scall_getquota(mp, from_kqid(&init_user_ns, qid),
-				      xfs_quota_type(qid.type), fdq);
+				      xfs_quota_type(qid.type), qdq);
 }
 
 STATIC int
 xfs_fs_set_dqblk(
 	struct super_block	*sb,
 	struct kqid		qid,
-	struct fs_disk_quota	*fdq)
+	struct qc_dqblk		*qdq)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
@@ -160,7 +160,7 @@ xfs_fs_set_dqblk(
 		return -ESRCH;
 
 	return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid),
-				     xfs_quota_type(qid.type), fdq);
+				     xfs_quota_type(qid.type), qdq);
 }
 
 const struct quotactl_ops xfs_quotactl_operations = {
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 50978b781a1..097d7eb2441 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -321,6 +321,49 @@ struct dquot_operations {
 
 struct path;
 
+/* Structure for communicating via ->get_dqblk() & ->set_dqblk() */
+struct qc_dqblk {
+	int d_fieldmask;	/* mask of fields to change in ->set_dqblk() */
+	u64 d_spc_hardlimit;	/* absolute limit on used space */
+	u64 d_spc_softlimit;	/* preferred limit on used space */
+	u64 d_ino_hardlimit;	/* maximum # allocated inodes */
+	u64 d_ino_softlimit;	/* preferred inode limit */
+	u64 d_space;		/* Space owned by the user */
+	u64 d_ino_count;	/* # inodes owned by the user */
+	s64 d_ino_timer;	/* zero if within inode limits */
+				/* if not, we refuse service */
+	s64 d_spc_timer;	/* similar to above; for space */
+	int d_ino_warns;	/* # warnings issued wrt num inodes */
+	int d_spc_warns;	/* # warnings issued wrt used space */
+	u64 d_rt_spc_hardlimit;	/* absolute limit on realtime space */
+	u64 d_rt_spc_softlimit;	/* preferred limit on RT space */
+	u64 d_rt_space;		/* realtime space owned */
+	s64 d_rt_spc_timer;	/* similar to above; for RT space */
+	int d_rt_spc_warns;	/* # warnings issued wrt RT space */
+};
+
+/* Field specifiers for ->set_dqblk() in struct qc_dqblk */
+#define	QC_INO_SOFT	(1<<0)
+#define	QC_INO_HARD	(1<<1)
+#define	QC_SPC_SOFT	(1<<2)
+#define	QC_SPC_HARD	(1<<3)
+#define	QC_RT_SPC_SOFT	(1<<4)
+#define	QC_RT_SPC_HARD	(1<<5)
+#define QC_LIMIT_MASK (QC_INO_SOFT | QC_INO_HARD | QC_SPC_SOFT | QC_SPC_HARD | \
+		       QC_RT_SPC_SOFT | QC_RT_SPC_HARD)
+#define	QC_SPC_TIMER	(1<<6)
+#define	QC_INO_TIMER	(1<<7)
+#define	QC_RT_SPC_TIMER	(1<<8)
+#define QC_TIMER_MASK (QC_SPC_TIMER | QC_INO_TIMER | QC_RT_SPC_TIMER)
+#define	QC_SPC_WARNS	(1<<9)
+#define	QC_INO_WARNS	(1<<10)
+#define	QC_RT_SPC_WARNS	(1<<11)
+#define QC_WARNS_MASK (QC_SPC_WARNS | QC_INO_WARNS | QC_RT_SPC_WARNS)
+#define	QC_SPACE	(1<<12)
+#define	QC_INO_COUNT	(1<<13)
+#define	QC_RT_SPACE	(1<<14)
+#define QC_ACCT_MASK (QC_SPACE | QC_INO_COUNT | QC_RT_SPACE)
+
 /* Operations handling requests from userspace */
 struct quotactl_ops {
 	int (*quota_on)(struct super_block *, int, int, struct path *);
@@ -329,8 +372,8 @@ struct quotactl_ops {
 	int (*quota_sync)(struct super_block *, int);
 	int (*get_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*set_info)(struct super_block *, int, struct if_dqinfo *);
-	int (*get_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *);
-	int (*set_dqblk)(struct super_block *, struct kqid, struct fs_disk_quota *);
+	int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
+	int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
 	int (*get_xstate)(struct super_block *, struct fs_quota_stat *);
 	int (*set_xstate)(struct super_block *, unsigned int, int);
 	int (*get_xstatev)(struct super_block *, struct fs_quota_statv *);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index f23538a6e41..29e3455f7d4 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -98,9 +98,9 @@ int dquot_quota_sync(struct super_block *sb, int type);
 int dquot_get_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_set_dqinfo(struct super_block *sb, int type, struct if_dqinfo *ii);
 int dquot_get_dqblk(struct super_block *sb, struct kqid id,
-		struct fs_disk_quota *di);
+		struct qc_dqblk *di);
 int dquot_set_dqblk(struct super_block *sb, struct kqid id,
-		struct fs_disk_quota *di);
+		struct qc_dqblk *di);
 
 int __dquot_transfer(struct inode *inode, struct dquot **transfer_to);
 int dquot_transfer(struct inode *inode, struct iattr *iattr);
-- 
cgit v1.2.3-70-g09d2


From 3aa8793f751d4cfcaca886e75ab30dfb00cf1d88 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 28 Nov 2014 14:38:36 +0100
Subject: mmc: core: Initial support for MMC power sequences

System on chip designs may specify a specific MMC power sequence. To
successfully detect an (e)MMC/SD/SDIO card, that power sequence must
be followed while initializing the card.

To be able to handle these SOC specific power sequences, let's add a
MMC power sequence interface. It provides the following functions to
help the mmc core to deal with these power sequences.

mmc_pwrseq_alloc() - Invoked from mmc_of_parse(), to initialize data.
mmc_pwrseq_pre_power_on()- Invoked in the beginning of mmc_power_up().
mmc_pwrseq_post_power_on()- Invoked at the end in mmc_power_up().
mmc_pwrseq_power_off()- Invoked from mmc_power_off().
mmc_pwrseq_free() - Invoked from mmc_free_host(), to free data.

Each MMC power sequence provider will be responsible to implement a set
of callbacks. These callbacks mirrors the functions above.

This patch adds the skeleton, following patches will extend the core of
the MMC power sequence and add support for a specific simple MMC power
sequence.

Do note, since the mmc_pwrseq_alloc() is invoked from mmc_of_parse(),
host drivers needs to make use of this API to enable the support for
MMC power sequences. Moreover the MMC power sequence support depends on
CONFIG_OF.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
---
 drivers/mmc/core/Makefile |  2 +-
 drivers/mmc/core/core.c   |  7 +++++++
 drivers/mmc/core/host.c   |  4 +++-
 drivers/mmc/core/pwrseq.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/mmc/core/pwrseq.h | 40 +++++++++++++++++++++++++++++++++++++
 include/linux/mmc/host.h  |  2 ++
 6 files changed, 103 insertions(+), 2 deletions(-)
 create mode 100644 drivers/mmc/core/pwrseq.c
 create mode 100644 drivers/mmc/core/pwrseq.h

(limited to 'include')

diff --git a/drivers/mmc/core/Makefile b/drivers/mmc/core/Makefile
index 38ed210ce2f..ccdd35f7825 100644
--- a/drivers/mmc/core/Makefile
+++ b/drivers/mmc/core/Makefile
@@ -8,5 +8,5 @@ mmc_core-y			:= core.o bus.o host.o \
 				   sdio.o sdio_ops.o sdio_bus.o \
 				   sdio_cis.o sdio_io.o sdio_irq.o \
 				   quirks.o slot-gpio.o
-
+mmc_core-$(CONFIG_OF)		+= pwrseq.o
 mmc_core-$(CONFIG_DEBUG_FS)	+= debugfs.o
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index d5c176e8795..1be7055548c 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -40,6 +40,7 @@
 #include "bus.h"
 #include "host.h"
 #include "sdio_bus.h"
+#include "pwrseq.h"
 
 #include "mmc_ops.h"
 #include "sd_ops.h"
@@ -1615,6 +1616,8 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 
 	mmc_host_clk_hold(host);
 
+	mmc_pwrseq_pre_power_on(host);
+
 	host->ios.vdd = fls(ocr) - 1;
 	host->ios.power_mode = MMC_POWER_UP;
 	/* Set initial state and call mmc_set_ios */
@@ -1645,6 +1648,8 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 	 */
 	mmc_delay(10);
 
+	mmc_pwrseq_post_power_on(host);
+
 	mmc_host_clk_release(host);
 }
 
@@ -1655,6 +1660,8 @@ void mmc_power_off(struct mmc_host *host)
 
 	mmc_host_clk_hold(host);
 
+	mmc_pwrseq_power_off(host);
+
 	host->ios.clock = 0;
 	host->ios.vdd = 0;
 
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 07636449b4d..8be0df758e6 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -30,6 +30,7 @@
 #include "core.h"
 #include "host.h"
 #include "slot-gpio.h"
+#include "pwrseq.h"
 
 #define cls_dev_to_mmc_host(d)	container_of(d, struct mmc_host, class_dev)
 
@@ -448,7 +449,7 @@ int mmc_of_parse(struct mmc_host *host)
 		host->dsr_req = 0;
 	}
 
-	return 0;
+	return mmc_pwrseq_alloc(host);
 }
 
 EXPORT_SYMBOL(mmc_of_parse);
@@ -588,6 +589,7 @@ EXPORT_SYMBOL(mmc_remove_host);
  */
 void mmc_free_host(struct mmc_host *host)
 {
+	mmc_pwrseq_free(host);
 	put_device(&host->class_dev);
 }
 
diff --git a/drivers/mmc/core/pwrseq.c b/drivers/mmc/core/pwrseq.c
new file mode 100644
index 00000000000..bd087723929
--- /dev/null
+++ b/drivers/mmc/core/pwrseq.c
@@ -0,0 +1,50 @@
+/*
+ *  Copyright (C) 2014 Linaro Ltd
+ *
+ * Author: Ulf Hansson <ulf.hansson@linaro.org>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ *
+ *  MMC power sequence management
+ */
+#include <linux/mmc/host.h>
+
+#include "pwrseq.h"
+
+
+int mmc_pwrseq_alloc(struct mmc_host *host)
+{
+	return 0;
+}
+
+void mmc_pwrseq_pre_power_on(struct mmc_host *host)
+{
+	struct mmc_pwrseq *pwrseq = host->pwrseq;
+
+	if (pwrseq && pwrseq->ops && pwrseq->ops->pre_power_on)
+		pwrseq->ops->pre_power_on(host);
+}
+
+void mmc_pwrseq_post_power_on(struct mmc_host *host)
+{
+	struct mmc_pwrseq *pwrseq = host->pwrseq;
+
+	if (pwrseq && pwrseq->ops && pwrseq->ops->post_power_on)
+		pwrseq->ops->post_power_on(host);
+}
+
+void mmc_pwrseq_power_off(struct mmc_host *host)
+{
+	struct mmc_pwrseq *pwrseq = host->pwrseq;
+
+	if (pwrseq && pwrseq->ops && pwrseq->ops->power_off)
+		pwrseq->ops->power_off(host);
+}
+
+void mmc_pwrseq_free(struct mmc_host *host)
+{
+	struct mmc_pwrseq *pwrseq = host->pwrseq;
+
+	if (pwrseq && pwrseq->ops && pwrseq->ops->free)
+		pwrseq->ops->free(host);
+}
diff --git a/drivers/mmc/core/pwrseq.h b/drivers/mmc/core/pwrseq.h
new file mode 100644
index 00000000000..12aaf2b4745
--- /dev/null
+++ b/drivers/mmc/core/pwrseq.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd
+ *
+ * Author: Ulf Hansson <ulf.hansson@linaro.org>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+#ifndef _MMC_CORE_PWRSEQ_H
+#define _MMC_CORE_PWRSEQ_H
+
+struct mmc_pwrseq_ops {
+	void (*pre_power_on)(struct mmc_host *host);
+	void (*post_power_on)(struct mmc_host *host);
+	void (*power_off)(struct mmc_host *host);
+	void (*free)(struct mmc_host *host);
+};
+
+struct mmc_pwrseq {
+	struct mmc_pwrseq_ops *ops;
+};
+
+#ifdef CONFIG_OF
+
+int mmc_pwrseq_alloc(struct mmc_host *host);
+void mmc_pwrseq_pre_power_on(struct mmc_host *host);
+void mmc_pwrseq_post_power_on(struct mmc_host *host);
+void mmc_pwrseq_power_off(struct mmc_host *host);
+void mmc_pwrseq_free(struct mmc_host *host);
+
+#else
+
+static inline int mmc_pwrseq_alloc(struct mmc_host *host) { return 0; }
+static inline void mmc_pwrseq_pre_power_on(struct mmc_host *host) {}
+static inline void mmc_pwrseq_post_power_on(struct mmc_host *host) {}
+static inline void mmc_pwrseq_power_off(struct mmc_host *host) {}
+static inline void mmc_pwrseq_free(struct mmc_host *host) {}
+
+#endif
+
+#endif
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index b6bf718c349..0c8cbe5d155 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -195,6 +195,7 @@ struct mmc_context_info {
 };
 
 struct regulator;
+struct mmc_pwrseq;
 
 struct mmc_supply {
 	struct regulator *vmmc;		/* Card power supply */
@@ -206,6 +207,7 @@ struct mmc_host {
 	struct device		class_dev;
 	int			index;
 	const struct mmc_host_ops *ops;
+	struct mmc_pwrseq	*pwrseq;
 	unsigned int		f_min;
 	unsigned int		f_max;
 	unsigned int		f_init;
-- 
cgit v1.2.3-70-g09d2


From c3c87e770458aa004bd7ed3f29945ff436fd6511 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 23 Jan 2015 11:19:48 +0100
Subject: perf: Tighten (and fix) the grouping condition

The fix from 9fc81d87420d ("perf: Fix events installation during
moving group") was incomplete in that it failed to recognise that
creating a group with events for different CPUs is semantically
broken -- they cannot be co-scheduled.

Furthermore, it leads to real breakage where, when we create an event
for CPU Y and then migrate it to form a group on CPU X, the code gets
confused where the counter is programmed -- triggered in practice
as well by me via the perf fuzzer.

Fix this by tightening the rules for creating groups. Only allow
grouping of counters that can be co-scheduled in the same context.
This means for the same task and/or the same cpu.

Fixes: 9fc81d87420d ("perf: Fix events installation during moving group")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150123125834.090683288@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/perf_event.h |  6 ------
 kernel/events/core.c       | 15 +++++++++++++--
 2 files changed, 13 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4f7a61ca4b3..664de5a4ec4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -450,11 +450,6 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
-enum perf_event_context_type {
-	task_context,
-	cpu_context,
-};
-
 /**
  * struct perf_event_context - event context structure
  *
@@ -462,7 +457,6 @@ enum perf_event_context_type {
  */
 struct perf_event_context {
 	struct pmu			*pmu;
-	enum perf_event_context_type	type;
 	/*
 	 * Protect the states of the events in the list,
 	 * nr_active, and the list:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 882f835a0d8..19efcf13375 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6776,7 +6776,6 @@ skip_type:
 		__perf_event_init_context(&cpuctx->ctx);
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
-		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 
 		__perf_cpu_hrtimer_init(cpuctx, cpu);
@@ -7420,7 +7419,19 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * task or CPU context:
 		 */
 		if (move_group) {
-			if (group_leader->ctx->type != ctx->type)
+			/*
+			 * Make sure we're both on the same task, or both
+			 * per-cpu events.
+			 */
+			if (group_leader->ctx->task != ctx->task)
+				goto err_context;
+
+			/*
+			 * Make sure we're both events for the same CPU;
+			 * grouping events for different CPUs is broken; since
+			 * you can never concurrently schedule them anyhow.
+			 */
+			if (group_leader->cpu != event->cpu)
 				goto err_context;
 		} else {
 			if (group_leader->ctx != ctx)
-- 
cgit v1.2.3-70-g09d2


From 667a0a06c99d5291433b869ed35dabdd95ba1453 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Thu, 18 Dec 2014 14:48:15 +0000
Subject: mm: provide a find_special_page vma operation

The optional find_special_page VMA operation is used to lookup the
pages backing a VMA.  This is useful in cases where the normal
mechanisms for finding the page don't work.  This is only called if
the PTE is special.

One use case is a Xen PV guest mapping foreign pages into userspace.

In a Xen PV guest, the PTEs contain MFNs so get_user_pages() (for
example) must do an MFN to PFN (M2P) lookup before it can get the
page.  For foreign pages (those owned by another guest) the M2P lookup
returns the PFN as seen by the foreign guest (which would be
completely the wrong page for the local guest).

This cannot be fixed up improving the M2P lookup since one MFN may be
mapped onto two or more pages so getting the right page is impossible
given just the MFN.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 8 ++++++++
 mm/memory.c        | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80fc92a4964..9269af7349f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -290,6 +290,14 @@ struct vm_operations_struct {
 	/* called by sys_remap_file_pages() to populate non-linear mapping */
 	int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,
 			   unsigned long size, pgoff_t pgoff);
+
+	/*
+	 * Called by vm_normal_page() for special PTEs to find the
+	 * page for @addr.  This is useful if the default behavior
+	 * (using pte_page()) would not find the correct page.
+	 */
+	struct page *(*find_special_page)(struct vm_area_struct *vma,
+					  unsigned long addr);
 };
 
 struct mmu_gather;
diff --git a/mm/memory.c b/mm/memory.c
index 54f3a9b0095..dc2e01a315e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -754,6 +754,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 	if (HAVE_PTE_SPECIAL) {
 		if (likely(!pte_special(pte)))
 			goto check_pfn;
+		if (vma->vm_ops && vma->vm_ops->find_special_page)
+			return vma->vm_ops->find_special_page(vma, addr);
 		if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
 			return NULL;
 		if (!is_zero_pfn(pfn))
-- 
cgit v1.2.3-70-g09d2


From d8ac3dd41aea245f65465449efc35dd3ac71e91d Mon Sep 17 00:00:00 2001
From: Jennifer Herbert <jennifer.herbert@citrix.com>
Date: Mon, 5 Jan 2015 13:24:09 +0000
Subject: mm: add 'foreign' alias for the 'pinned' page flag

The foreign page flag will be used by Xen guests to mark pages that
have grant mappings of frames from other (foreign) guests.

The foreign flag is an alias for the existing (Xen-specific) pinned
flag.  This is safe because pinned is only used on pages used for page
tables and these cannot also be foreign.

Signed-off-by: Jennifer Herbert <jennifer.herbert@citrix.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 include/linux/page-flags.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index e1f5fcd7979..5ed7bdaf22d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -121,8 +121,12 @@ enum pageflags {
 	PG_fscache = PG_private_2,	/* page backed by cache */
 
 	/* XEN */
+	/* Pinned in Xen as a read-only pagetable page. */
 	PG_pinned = PG_owner_priv_1,
+	/* Pinned as part of domain save (see xen_mm_pin_all()). */
 	PG_savepinned = PG_dirty,
+	/* Has a grant mapping of another (foreign) domain's page. */
+	PG_foreign = PG_owner_priv_1,
 
 	/* SLOB */
 	PG_slob_free = PG_private,
@@ -215,6 +219,7 @@ __PAGEFLAG(Slab, slab)
 PAGEFLAG(Checked, checked)		/* Used by some filesystems */
 PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
 PAGEFLAG(SavePinned, savepinned);			/* Xen */
+PAGEFLAG(Foreign, foreign);				/* Xen */
 PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
 PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
 	__SETPAGEFLAG(SwapBacked, swapbacked)
-- 
cgit v1.2.3-70-g09d2


From 853d0289340026b30f93fd0e768340221d4e605c Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Mon, 5 Jan 2015 14:13:41 +0000
Subject: xen/grant-table: pre-populate kernel unmap ops for
 xen_gnttab_unmap_refs()

When unmapping grants, instead of converting the kernel map ops to
unmap ops on the fly, pre-populate the set of unmap ops.

This allows the grant unmap for the kernel mappings to be trivially
batched in the future.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 arch/arm/include/asm/xen/page.h |  2 +-
 arch/arm/xen/p2m.c              |  2 +-
 arch/x86/include/asm/xen/page.h |  2 +-
 arch/x86/xen/p2m.c              | 21 ++++++++++-----------
 drivers/xen/gntdev.c            | 20 ++++++++++++++------
 drivers/xen/grant-table.c       |  4 ++--
 include/xen/grant_table.h       |  2 +-
 7 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 68c739b3fdf..2f7e6ff67d5 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -92,7 +92,7 @@ extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 				   struct page **pages, unsigned int count);
 
 extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
-				     struct gnttab_map_grant_ref *kmap_ops,
+				     struct gnttab_unmap_grant_ref *kunmap_ops,
 				     struct page **pages, unsigned int count);
 
 bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index 05485777625..cb7a14c5cd6 100644
--- a/arch/arm/xen/p2m.c
+++ b/arch/arm/xen/p2m.c
@@ -102,7 +102,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
 
 int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
-			      struct gnttab_map_grant_ref *kmap_ops,
+			      struct gnttab_unmap_grant_ref *kunmap_ops,
 			      struct page **pages, unsigned int count)
 {
 	int i;
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 5eea09915a1..e9f52fe2d56 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -55,7 +55,7 @@ extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 				   struct gnttab_map_grant_ref *kmap_ops,
 				   struct page **pages, unsigned int count);
 extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
-				     struct gnttab_map_grant_ref *kmap_ops,
+				     struct gnttab_unmap_grant_ref *kunmap_ops,
 				     struct page **pages, unsigned int count);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 70fb5075c90..df40b2888ea 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -816,7 +816,7 @@ static struct page *m2p_find_override(unsigned long mfn)
 }
 
 static int m2p_remove_override(struct page *page,
-			       struct gnttab_map_grant_ref *kmap_op,
+			       struct gnttab_unmap_grant_ref *kunmap_op,
 			       unsigned long mfn)
 {
 	unsigned long flags;
@@ -840,7 +840,7 @@ static int m2p_remove_override(struct page *page,
 	list_del(&page->lru);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
 
-	if (kmap_op != NULL) {
+	if (kunmap_op != NULL) {
 		if (!PageHighMem(page)) {
 			struct multicall_space mcs;
 			struct gnttab_unmap_and_replace *unmap_op;
@@ -855,13 +855,13 @@ static int m2p_remove_override(struct page *page,
 			 * issued. In this case handle is going to -1 because
 			 * it hasn't been modified yet.
 			 */
-			if (kmap_op->handle == -1)
+			if (kunmap_op->handle == -1)
 				xen_mc_flush();
 			/*
 			 * Now if kmap_op->handle is negative it means that the
 			 * hypercall actually returned an error.
 			 */
-			if (kmap_op->handle == GNTST_general_error) {
+			if (kunmap_op->handle == GNTST_general_error) {
 				pr_warn("m2p_remove_override: pfn %lx mfn %lx, failed to modify kernel mappings",
 					pfn, mfn);
 				put_balloon_scratch_page();
@@ -873,9 +873,9 @@ static int m2p_remove_override(struct page *page,
 			mcs = __xen_mc_entry(
 				sizeof(struct gnttab_unmap_and_replace));
 			unmap_op = mcs.args;
-			unmap_op->host_addr = kmap_op->host_addr;
+			unmap_op->host_addr = kunmap_op->host_addr;
 			unmap_op->new_addr = scratch_page_address;
-			unmap_op->handle = kmap_op->handle;
+			unmap_op->handle = kunmap_op->handle;
 
 			MULTI_grant_table_op(mcs.mc,
 				GNTTABOP_unmap_and_replace, unmap_op, 1);
@@ -887,7 +887,6 @@ static int m2p_remove_override(struct page *page,
 
 			xen_mc_issue(PARAVIRT_LAZY_MMU);
 
-			kmap_op->host_addr = 0;
 			put_balloon_scratch_page();
 		}
 	}
@@ -912,7 +911,7 @@ static int m2p_remove_override(struct page *page,
 }
 
 int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
-			      struct gnttab_map_grant_ref *kmap_ops,
+			      struct gnttab_unmap_grant_ref *kunmap_ops,
 			      struct page **pages, unsigned int count)
 {
 	int i, ret = 0;
@@ -921,7 +920,7 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return 0;
 
-	if (kmap_ops &&
+	if (kunmap_ops &&
 	    !in_interrupt() &&
 	    paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
 		arch_enter_lazy_mmu_mode();
@@ -942,8 +941,8 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 		ClearPagePrivate(pages[i]);
 		set_phys_to_machine(pfn, pages[i]->index);
 
-		if (kmap_ops)
-			ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
+		if (kunmap_ops)
+			ret = m2p_remove_override(pages[i], &kunmap_ops[i], mfn);
 		if (ret)
 			goto out;
 	}
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 073b4a19a8b..6444172f284 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -91,6 +91,7 @@ struct grant_map {
 	struct gnttab_map_grant_ref   *map_ops;
 	struct gnttab_unmap_grant_ref *unmap_ops;
 	struct gnttab_map_grant_ref   *kmap_ops;
+	struct gnttab_unmap_grant_ref *kunmap_ops;
 	struct page **pages;
 };
 
@@ -124,6 +125,7 @@ static void gntdev_free_map(struct grant_map *map)
 	kfree(map->map_ops);
 	kfree(map->unmap_ops);
 	kfree(map->kmap_ops);
+	kfree(map->kunmap_ops);
 	kfree(map);
 }
 
@@ -140,11 +142,13 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	add->map_ops   = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
 	add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
 	add->kmap_ops  = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
+	add->kunmap_ops = kcalloc(count, sizeof(add->kunmap_ops[0]), GFP_KERNEL);
 	add->pages     = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
 	    NULL == add->unmap_ops ||
 	    NULL == add->kmap_ops  ||
+	    NULL == add->kunmap_ops ||
 	    NULL == add->pages)
 		goto err;
 
@@ -155,6 +159,7 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 		add->map_ops[i].handle = -1;
 		add->unmap_ops[i].handle = -1;
 		add->kmap_ops[i].handle = -1;
+		add->kunmap_ops[i].handle = -1;
 	}
 
 	add->index = 0;
@@ -280,6 +285,8 @@ static int map_grant_pages(struct grant_map *map)
 				map->flags | GNTMAP_host_map,
 				map->grants[i].ref,
 				map->grants[i].domid);
+			gnttab_set_unmap_op(&map->kunmap_ops[i], address,
+				map->flags | GNTMAP_host_map, -1);
 		}
 	}
 
@@ -290,13 +297,14 @@ static int map_grant_pages(struct grant_map *map)
 		return err;
 
 	for (i = 0; i < map->count; i++) {
-		if (map->map_ops[i].status)
+		if (map->map_ops[i].status) {
 			err = -EINVAL;
-		else {
-			BUG_ON(map->map_ops[i].handle == -1);
-			map->unmap_ops[i].handle = map->map_ops[i].handle;
-			pr_debug("map handle=%d\n", map->map_ops[i].handle);
+			continue;
 		}
+
+		map->unmap_ops[i].handle = map->map_ops[i].handle;
+		if (use_ptemod)
+			map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
 	}
 	return err;
 }
@@ -316,7 +324,7 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
 	}
 
 	err = gnttab_unmap_refs(map->unmap_ops + offset,
-			use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset,
+			use_ptemod ? map->kunmap_ops + offset : NULL, map->pages + offset,
 			pages);
 	if (err)
 		return err;
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 7786291ba22..999d7abdbce 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -738,7 +738,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 EXPORT_SYMBOL_GPL(gnttab_map_refs);
 
 int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
-		      struct gnttab_map_grant_ref *kmap_ops,
+		      struct gnttab_unmap_grant_ref *kunmap_ops,
 		      struct page **pages, unsigned int count)
 {
 	int ret;
@@ -747,7 +747,7 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 	if (ret)
 		return ret;
 
-	return clear_foreign_p2m_mapping(unmap_ops, kmap_ops, pages, count);
+	return clear_foreign_p2m_mapping(unmap_ops, kunmap_ops, pages, count);
 }
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
 
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 3387465b9ca..7235d8f3545 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -167,7 +167,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count);
 int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
-		      struct gnttab_map_grant_ref *kunmap_ops,
+		      struct gnttab_unmap_grant_ref *kunmap_ops,
 		      struct page **pages, unsigned int count);
 
 /* Perform a batch of grant map/copy operations. Retry every batch slot
-- 
cgit v1.2.3-70-g09d2


From ff4b156f166b3931894d2a8b5cdba6cdf4da0618 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Thu, 8 Jan 2015 18:06:01 +0000
Subject: xen/grant-table: add helpers for allocating pages

Add gnttab_alloc_pages() and gnttab_free_pages() to allocate/free pages
suitable to for granted maps.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 drivers/block/xen-blkback/blkback.c |  8 ++++----
 drivers/net/xen-netback/interface.c |  7 +++----
 drivers/xen/gntdev.c                |  4 ++--
 drivers/xen/grant-table.c           | 29 +++++++++++++++++++++++++++++
 drivers/xen/xen-scsiback.c          |  6 +++---
 include/xen/grant_table.h           |  3 +++
 6 files changed, 44 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 63fc7f06a01..908e630240b 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -100,7 +100,7 @@ module_param(log_stats, int, 0644);
 
 #define BLKBACK_INVALID_HANDLE (~0)
 
-/* Number of free pages to remove on each call to free_xenballooned_pages */
+/* Number of free pages to remove on each call to gnttab_free_pages */
 #define NUM_BATCH_FREE_PAGES 10
 
 static inline int get_free_page(struct xen_blkif *blkif, struct page **page)
@@ -111,7 +111,7 @@ static inline int get_free_page(struct xen_blkif *blkif, struct page **page)
 	if (list_empty(&blkif->free_pages)) {
 		BUG_ON(blkif->free_pages_num != 0);
 		spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
-		return alloc_xenballooned_pages(1, page, false);
+		return gnttab_alloc_pages(1, page);
 	}
 	BUG_ON(blkif->free_pages_num == 0);
 	page[0] = list_first_entry(&blkif->free_pages, struct page, lru);
@@ -151,14 +151,14 @@ static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num)
 		blkif->free_pages_num--;
 		if (++num_pages == NUM_BATCH_FREE_PAGES) {
 			spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
-			free_xenballooned_pages(num_pages, page);
+			gnttab_free_pages(num_pages, page);
 			spin_lock_irqsave(&blkif->free_pages_lock, flags);
 			num_pages = 0;
 		}
 	}
 	spin_unlock_irqrestore(&blkif->free_pages_lock, flags);
 	if (num_pages != 0)
-		free_xenballooned_pages(num_pages, page);
+		gnttab_free_pages(num_pages, page);
 }
 
 #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page)))
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 9259a732e8a..2e07f843341 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -483,9 +483,8 @@ int xenvif_init_queue(struct xenvif_queue *queue)
 	 * better enable it. The long term solution would be to use just a
 	 * bunch of valid page descriptors, without dependency on ballooning
 	 */
-	err = alloc_xenballooned_pages(MAX_PENDING_REQS,
-				       queue->mmap_pages,
-				       false);
+	err = gnttab_alloc_pages(MAX_PENDING_REQS,
+				 queue->mmap_pages);
 	if (err) {
 		netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n");
 		return -ENOMEM;
@@ -662,7 +661,7 @@ void xenvif_disconnect(struct xenvif *vif)
  */
 void xenvif_deinit_queue(struct xenvif_queue *queue)
 {
-	free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages);
+	gnttab_free_pages(MAX_PENDING_REQS, queue->mmap_pages);
 }
 
 void xenvif_free(struct xenvif *vif)
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 6444172f284..8cc3f069a10 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -119,7 +119,7 @@ static void gntdev_free_map(struct grant_map *map)
 		return;
 
 	if (map->pages)
-		free_xenballooned_pages(map->count, map->pages);
+		gnttab_free_pages(map->count, map->pages);
 	kfree(map->pages);
 	kfree(map->grants);
 	kfree(map->map_ops);
@@ -152,7 +152,7 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	    NULL == add->pages)
 		goto err;
 
-	if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */))
+	if (gnttab_alloc_pages(count, add->pages))
 		goto err;
 
 	for (i = 0; i < count; i++) {
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 999d7abdbce..b4f93c490f8 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -50,6 +50,7 @@
 #include <xen/interface/memory.h>
 #include <xen/hvc-console.h>
 #include <xen/swiotlb-xen.h>
+#include <xen/balloon.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -671,6 +672,34 @@ void gnttab_free_auto_xlat_frames(void)
 }
 EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
 
+/**
+ * gnttab_alloc_pages - alloc pages suitable for grant mapping into
+ * @nr_pages: number of pages to alloc
+ * @pages: returns the pages
+ */
+int gnttab_alloc_pages(int nr_pages, struct page **pages)
+{
+	int ret;
+
+	ret = alloc_xenballooned_pages(nr_pages, pages, false);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(gnttab_alloc_pages);
+
+/**
+ * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
+ * @nr_pages; number of pages to free
+ * @pages: the pages
+ */
+void gnttab_free_pages(int nr_pages, struct page **pages)
+{
+	free_xenballooned_pages(nr_pages, pages);
+}
+EXPORT_SYMBOL(gnttab_free_pages);
+
 /* Handling of paged out grant targets (GNTST_eagain) */
 #define MAX_DELAY 256
 static inline void
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index e999496eda3..ecd540a7a56 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -227,7 +227,7 @@ static void put_free_pages(struct page **page, int num)
 		return;
 	if (i > scsiback_max_buffer_pages) {
 		n = min(num, i - scsiback_max_buffer_pages);
-		free_xenballooned_pages(n, page + num - n);
+		gnttab_free_pages(n, page + num - n);
 		n = num - n;
 	}
 	spin_lock_irqsave(&free_pages_lock, flags);
@@ -244,7 +244,7 @@ static int get_free_page(struct page **page)
 	spin_lock_irqsave(&free_pages_lock, flags);
 	if (list_empty(&scsiback_free_pages)) {
 		spin_unlock_irqrestore(&free_pages_lock, flags);
-		return alloc_xenballooned_pages(1, page, false);
+		return gnttab_alloc_pages(1, page);
 	}
 	page[0] = list_first_entry(&scsiback_free_pages, struct page, lru);
 	list_del(&page[0]->lru);
@@ -2106,7 +2106,7 @@ static void __exit scsiback_exit(void)
 	while (free_pages_num) {
 		if (get_free_page(&page))
 			BUG();
-		free_xenballooned_pages(1, &page);
+		gnttab_free_pages(1, &page);
 	}
 	scsiback_deregister_configfs();
 	xenbus_unregister_driver(&scsiback_driver);
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 7235d8f3545..949803e2087 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -163,6 +163,9 @@ void gnttab_free_auto_xlat_frames(void);
 
 #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr))
 
+int gnttab_alloc_pages(int nr_pages, struct page **pages);
+void gnttab_free_pages(int nr_pages, struct page **pages);
+
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count);
-- 
cgit v1.2.3-70-g09d2


From 8da7633f168b5428e2cfb7342408b2c44088f5df Mon Sep 17 00:00:00 2001
From: Jennifer Herbert <jennifer.herbert@citrix.com>
Date: Wed, 24 Dec 2014 14:17:06 +0000
Subject: xen: mark grant mapped pages as foreign

Use the "foreign" page flag to mark pages that have a grant map.  Use
page->private to store information of the grant (the granting domain
and the grant reference).

Signed-off-by: Jennifer Herbert <jennifer.herbert@citrix.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 arch/x86/xen/p2m.c        |  7 -------
 drivers/xen/grant-table.c | 43 +++++++++++++++++++++++++++++++++++++++++--
 include/xen/grant_table.h | 20 ++++++++++++++++++++
 3 files changed, 61 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index a8691cb0842..f18fd1d411f 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -681,12 +681,8 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 		}
 		pfn = page_to_pfn(pages[i]);
 
-		WARN_ON(PagePrivate(pages[i]));
 		WARN(pfn_to_mfn(pfn) != INVALID_P2M_ENTRY, "page must be ballooned");
 
-		SetPagePrivate(pages[i]);
-		set_page_private(pages[i], mfn);
-
 		if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
 			ret = -ENOMEM;
 			goto out;
@@ -716,9 +712,6 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 			goto out;
 		}
 
-		set_page_private(pages[i], INVALID_P2M_ENTRY);
-		WARN_ON(!PagePrivate(pages[i]));
-		ClearPagePrivate(pages[i]);
 		set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 	}
 	if (kunmap_ops)
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index b4f93c490f8..89dcca448bb 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -679,12 +679,27 @@ EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
  */
 int gnttab_alloc_pages(int nr_pages, struct page **pages)
 {
+	int i;
 	int ret;
 
 	ret = alloc_xenballooned_pages(nr_pages, pages, false);
 	if (ret < 0)
 		return ret;
 
+	for (i = 0; i < nr_pages; i++) {
+#if BITS_PER_LONG < 64
+		struct xen_page_foreign *foreign;
+
+		foreign = kzalloc(sizeof(*foreign), GFP_KERNEL);
+		if (!foreign) {
+			gnttab_free_pages(nr_pages, pages);
+			return -ENOMEM;
+		}
+		set_page_private(pages[i], (unsigned long)foreign);
+#endif
+		SetPagePrivate(pages[i]);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL(gnttab_alloc_pages);
@@ -696,6 +711,16 @@ EXPORT_SYMBOL(gnttab_alloc_pages);
  */
 void gnttab_free_pages(int nr_pages, struct page **pages)
 {
+	int i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (PagePrivate(pages[i])) {
+#if BITS_PER_LONG < 64
+			kfree((void *)page_private(pages[i]));
+#endif
+			ClearPagePrivate(pages[i]);
+		}
+	}
 	free_xenballooned_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL(gnttab_free_pages);
@@ -756,12 +781,22 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 	if (ret)
 		return ret;
 
-	/* Retry eagain maps */
-	for (i = 0; i < count; i++)
+	for (i = 0; i < count; i++) {
+		/* Retry eagain maps */
 		if (map_ops[i].status == GNTST_eagain)
 			gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i,
 						&map_ops[i].status, __func__);
 
+		if (map_ops[i].status == GNTST_okay) {
+			struct xen_page_foreign *foreign;
+
+			SetPageForeign(pages[i]);
+			foreign = xen_page_foreign(pages[i]);
+			foreign->domid = map_ops[i].dom;
+			foreign->gref = map_ops[i].ref;
+		}
+	}
+
 	return set_foreign_p2m_mapping(map_ops, kmap_ops, pages, count);
 }
 EXPORT_SYMBOL_GPL(gnttab_map_refs);
@@ -770,12 +805,16 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		      struct gnttab_unmap_grant_ref *kunmap_ops,
 		      struct page **pages, unsigned int count)
 {
+	unsigned int i;
 	int ret;
 
 	ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
 	if (ret)
 		return ret;
 
+	for (i = 0; i < count; i++)
+		ClearPageForeign(pages[i]);
+
 	return clear_foreign_p2m_mapping(unmap_ops, kunmap_ops, pages, count);
 }
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 949803e2087..d3bef563e8d 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -45,6 +45,8 @@
 #include <asm/xen/hypervisor.h>
 
 #include <xen/features.h>
+#include <linux/mm_types.h>
+#include <linux/page-flags.h>
 
 #define GNTTAB_RESERVED_XENSTORE 1
 
@@ -185,4 +187,22 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 void gnttab_batch_map(struct gnttab_map_grant_ref *batch, unsigned count);
 void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count);
 
+
+struct xen_page_foreign {
+	domid_t domid;
+	grant_ref_t gref;
+};
+
+static inline struct xen_page_foreign *xen_page_foreign(struct page *page)
+{
+	if (!PageForeign(page))
+		return NULL;
+#if BITS_PER_LONG < 64
+	return (struct xen_page_foreign *)page->private;
+#else
+	BUILD_BUG_ON(sizeof(struct xen_page_foreign) > BITS_PER_LONG);
+	return (struct xen_page_foreign *)&page->private;
+#endif
+}
+
 #endif /* __ASM_GNTTAB_H__ */
-- 
cgit v1.2.3-70-g09d2


From 3f9f1c67572f5e5e6dc84216d48d1480f3c4fcf6 Mon Sep 17 00:00:00 2001
From: Jennifer Herbert <jennifer.herbert@citrix.com>
Date: Tue, 9 Dec 2014 18:28:37 +0000
Subject: xen/grant-table: add a mechanism to safely unmap pages that are in
 use

Introduce gnttab_unmap_refs_async() that can be used to safely unmap
pages that may be in use (ref count > 1).  If the pages are in use the
unmap is deferred and retried later.  This polling is not very clever
but it should be good enough if the cases where the delay is necessary
are rare.

The initial delay is 5 ms and is increased linearly on each subsequent
retry (to reduce load if the page is in use for a long time).

This is needed to allow block backends using grant mapping to safely
use network storage (block or filesystem based such as iSCSI or NFS).

The network storage driver may complete a block request whilst there
is a queued network packet retry (because the ack from the remote end
races with deciding to queue the retry).  The pages for the retried
packet would be grant unmapped and the network driver (or hardware)
would access the unmapped page.

Signed-off-by: Jennifer Herbert <jennifer.herbert@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
---
 drivers/xen/grant-table.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/xen/grant_table.h | 18 ++++++++++++++++++
 2 files changed, 62 insertions(+)

(limited to 'include')

diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 89dcca448bb..17972fbacdd 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -42,6 +42,7 @@
 #include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/hardirq.h>
+#include <linux/workqueue.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -819,6 +820,49 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 }
 EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
 
+#define GNTTAB_UNMAP_REFS_DELAY 5
+
+static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item);
+
+static void gnttab_unmap_work(struct work_struct *work)
+{
+	struct gntab_unmap_queue_data
+		*unmap_data = container_of(work, 
+					   struct gntab_unmap_queue_data,
+					   gnttab_work.work);
+	if (unmap_data->age != UINT_MAX)
+		unmap_data->age++;
+	__gnttab_unmap_refs_async(unmap_data);
+}
+
+static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
+{
+	int ret;
+	int pc;
+
+	for (pc = 0; pc < item->count; pc++) {
+		if (page_count(item->pages[pc]) > 1) {
+			unsigned long delay = GNTTAB_UNMAP_REFS_DELAY * (item->age + 1);
+			schedule_delayed_work(&item->gnttab_work,
+					      msecs_to_jiffies(delay));
+			return;
+		}
+	}
+
+	ret = gnttab_unmap_refs(item->unmap_ops, item->kunmap_ops,
+				item->pages, item->count);
+	item->done(ret, item);
+}
+
+void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
+{
+	INIT_DELAYED_WORK(&item->gnttab_work, gnttab_unmap_work);
+	item->age = 0;
+
+	__gnttab_unmap_refs_async(item);
+}
+EXPORT_SYMBOL_GPL(gnttab_unmap_refs_async);
+
 static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes)
 {
 	int rc;
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index d3bef563e8d..143ca5ffab7 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -60,6 +60,22 @@ struct gnttab_free_callback {
 	u16 count;
 };
 
+struct gntab_unmap_queue_data;
+
+typedef void (*gnttab_unmap_refs_done)(int result, struct gntab_unmap_queue_data *data);
+
+struct gntab_unmap_queue_data
+{
+	struct delayed_work	gnttab_work;
+	void *data;
+	gnttab_unmap_refs_done	done;
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_unmap_grant_ref *kunmap_ops;
+	struct page **pages;
+	unsigned int count;
+	unsigned int age;
+};
+
 int gnttab_init(void);
 int gnttab_suspend(void);
 int gnttab_resume(void);
@@ -174,6 +190,8 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		      struct gnttab_unmap_grant_ref *kunmap_ops,
 		      struct page **pages, unsigned int count);
+void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item);
+
 
 /* Perform a batch of grant map/copy operations. Retry every batch slot
  * for which the hypervisor returns GNTST_eagain. This is typically due
-- 
cgit v1.2.3-70-g09d2


From 923b2919e2c318ee1c360a2119a14889fd0fcce4 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Thu, 18 Dec 2014 14:56:54 +0000
Subject: xen/gntdev: mark userspace PTEs as special on x86 PV guests

In an x86 PV guest, get_user_pages_fast() on a userspace address range
containing foreign mappings does not work correctly because the M2P
lookup of the MFN from a userspace PTE may return the wrong page.

Force get_user_pages_fast() to fail on such addresses by marking the PTEs
as special.

If Xen has XENFEAT_gnttab_map_avail_bits (available since at least
4.0), we can do so efficiently in the grant map hypercall.  Otherwise,
it needs to be done afterwards.  This is both inefficient and racy
(the mapping is visible to the task before we fixup the PTEs), but
will be fine for well-behaved applications that do not use the mapping
until after the mmap() system call returns.

Guests with XENFEAT_auto_translated_physmap (ARM and x86 HVM or PVH)
do not need this since get_user_pages() has always worked correctly
for them.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 drivers/xen/gntdev.c                | 34 ++++++++++++++++++++++++++++++++++
 include/xen/interface/features.h    |  6 ++++++
 include/xen/interface/grant_table.h |  7 +++++++
 3 files changed, 47 insertions(+)

(limited to 'include')

diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index bccc54a8055..20c65771017 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -244,6 +244,14 @@ static int find_grant_ptes(pte_t *pte, pgtable_t token,
 	BUG_ON(pgnr >= map->count);
 	pte_maddr = arbitrary_virt_to_machine(pte).maddr;
 
+	/*
+	 * Set the PTE as special to force get_user_pages_fast() fall
+	 * back to the slow path.  If this is not supported as part of
+	 * the grant map, it will be done afterwards.
+	 */
+	if (xen_feature(XENFEAT_gnttab_map_avail_bits))
+		flags |= (1 << _GNTMAP_guest_avail0);
+
 	gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags,
 			  map->grants[pgnr].ref,
 			  map->grants[pgnr].domid);
@@ -252,6 +260,15 @@ static int find_grant_ptes(pte_t *pte, pgtable_t token,
 	return 0;
 }
 
+#ifdef CONFIG_X86
+static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token,
+				     unsigned long addr, void *data)
+{
+	set_pte_at(current->mm, addr, pte, pte_mkspecial(*pte));
+	return 0;
+}
+#endif
+
 static int map_grant_pages(struct grant_map *map)
 {
 	int i, err = 0;
@@ -840,6 +857,23 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 			if (err)
 				goto out_put_map;
 		}
+	} else {
+#ifdef CONFIG_X86
+		/*
+		 * If the PTEs were not made special by the grant map
+		 * hypercall, do so here.
+		 *
+		 * This is racy since the mapping is already visible
+		 * to userspace but userspace should be well-behaved
+		 * enough to not touch it until the mmap() call
+		 * returns.
+		 */
+		if (!xen_feature(XENFEAT_gnttab_map_avail_bits)) {
+			apply_to_page_range(vma->vm_mm, vma->vm_start,
+					    vma->vm_end - vma->vm_start,
+					    set_grant_ptes_as_special, NULL);
+		}
+#endif
 	}
 
 	return 0;
diff --git a/include/xen/interface/features.h b/include/xen/interface/features.h
index 131a6ccdba2..6ad3d110bb8 100644
--- a/include/xen/interface/features.h
+++ b/include/xen/interface/features.h
@@ -41,6 +41,12 @@
 /* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */
 #define XENFEAT_mmu_pt_update_preserve_ad  5
 
+/*
+ * If set, GNTTABOP_map_grant_ref honors flags to be placed into guest kernel
+ * available pte bits.
+ */
+#define XENFEAT_gnttab_map_avail_bits      7
+
 /* x86: Does this Xen host support the HVM callback vector type? */
 #define XENFEAT_hvm_callback_vector        8
 
diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h
index bcce56439d6..56806bc90c2 100644
--- a/include/xen/interface/grant_table.h
+++ b/include/xen/interface/grant_table.h
@@ -525,6 +525,13 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush);
 #define _GNTMAP_contains_pte    (4)
 #define GNTMAP_contains_pte     (1<<_GNTMAP_contains_pte)
 
+/*
+ * Bits to be placed in guest kernel available PTE bits (architecture
+ * dependent; only supported when XENFEAT_gnttab_map_avail_bits is set).
+ */
+#define _GNTMAP_guest_avail0    (16)
+#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0)
+
 /*
  * Values for error status returns. All errors are -ve.
  */
-- 
cgit v1.2.3-70-g09d2


From 6ea22486ba46bcb665de36514094d74575cd1330 Mon Sep 17 00:00:00 2001
From: Dave Martin <Dave.Martin@arm.com>
Date: Wed, 28 Jan 2015 12:48:53 +0000
Subject: tracing: Add array printing helper

If a trace event contains an array, there is currently no standard
way to format this for text output.  Drivers are currently hacking
around this by a) local hacks that use the trace_seq functionailty
directly, or b) just not printing that information.  For fixed size
arrays, formatting of the elements can be open-coded, but this gets
cumbersome for arrays of non-trivial size.

These approaches result in non-standard content of the event format
description delivered to userspace, so userland tools needs to be
taught to understand and parse each array printing method
individually.

This patch implements a __print_array() helper that tracepoint
implementations can use instead of reinventing it.  A simple C-style
syntax is used to delimit the array and its elements {like,this}.

So that the helpers can be used with large static arrays as well as
dynamic arrays, they take a pointer and element count: they can be
used with __get_dynamic_array() for use with dynamic arrays.
Link: http://lkml.kernel.org/r/1422449335-8289-2-git-send-email-javi.merino@arm.com

Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Javi Merino <javi.merino@arm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |  4 ++++
 include/trace/ftrace.h       |  9 +++++++++
 kernel/trace/trace_output.c  | 44 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 57 insertions(+)

(limited to 'include')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 0bebb5c348b..5aa4a926954 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -44,6 +44,10 @@ const char *ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr,
 const char *ftrace_print_hex_seq(struct trace_seq *p,
 				 const unsigned char *buf, int len);
 
+const char *ftrace_print_array_seq(struct trace_seq *p,
+				   const void *buf, int buf_len,
+				   size_t el_size);
+
 struct trace_iterator;
 struct trace_event;
 
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 139b5067345..304901fc5f3 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -263,6 +263,14 @@
 #undef __print_hex
 #define __print_hex(buf, buf_len) ftrace_print_hex_seq(p, buf, buf_len)
 
+#undef __print_array
+#define __print_array(array, count, el_size)				\
+	({								\
+		BUILD_BUG_ON(el_size != 1 && el_size != 2 &&		\
+			     el_size != 4 && el_size != 8);		\
+		ftrace_print_array_seq(p, array, count, el_size);	\
+	})
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace enum print_line_t					\
@@ -674,6 +682,7 @@ static inline void ftrace_test_probe_##call(void)			\
 #undef __get_dynamic_array_len
 #undef __get_str
 #undef __get_bitmask
+#undef __print_array
 
 #undef TP_printk
 #define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index b77b9a69761..692bf7184c8 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -177,6 +177,50 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 }
 EXPORT_SYMBOL(ftrace_print_hex_seq);
 
+const char *
+ftrace_print_array_seq(struct trace_seq *p, const void *buf, int buf_len,
+		       size_t el_size)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+	const char *prefix = "";
+	void *ptr = (void *)buf;
+
+	trace_seq_putc(p, '{');
+
+	while (ptr < buf + buf_len) {
+		switch (el_size) {
+		case 1:
+			trace_seq_printf(p, "%s0x%x", prefix,
+					 *(u8 *)ptr);
+			break;
+		case 2:
+			trace_seq_printf(p, "%s0x%x", prefix,
+					 *(u16 *)ptr);
+			break;
+		case 4:
+			trace_seq_printf(p, "%s0x%x", prefix,
+					 *(u32 *)ptr);
+			break;
+		case 8:
+			trace_seq_printf(p, "%s0x%llx", prefix,
+					 *(u64 *)ptr);
+			break;
+		default:
+			trace_seq_printf(p, "BAD SIZE:%zu 0x%x", el_size,
+					 *(u8 *)ptr);
+			el_size = 1;
+		}
+		prefix = ",";
+		ptr += el_size;
+	}
+
+	trace_seq_putc(p, '}');
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL(ftrace_print_array_seq);
+
 int ftrace_raw_output_prep(struct trace_iterator *iter,
 			   struct trace_event *trace_event)
 {
-- 
cgit v1.2.3-70-g09d2


From 6cbbfe1c8ddb6ac1322a87795dff9d8712c3e359 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 28 Jan 2015 16:49:33 +0100
Subject: ALSA: Include linux/io.h instead of asm/io.h

Nowadays it's recommended.  Replace all in a shot.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/emu10k1.h               | 2 +-
 include/sound/gus.h                   | 2 +-
 include/sound/sb.h                    | 2 +-
 sound/aoa/soundbus/i2sbus/control.c   | 2 +-
 sound/aoa/soundbus/i2sbus/pcm.c       | 2 +-
 sound/core/memory.c                   | 2 +-
 sound/core/pcm_memory.c               | 2 +-
 sound/core/pcm_native.c               | 2 +-
 sound/drivers/mpu401/mpu401_uart.c    | 2 +-
 sound/drivers/opl3/opl3_lib.c         | 2 +-
 sound/drivers/opl4/opl4_lib.c         | 2 +-
 sound/drivers/opl4/opl4_synth.c       | 2 +-
 sound/drivers/pcsp/pcsp_input.c       | 2 +-
 sound/drivers/pcsp/pcsp_lib.c         | 2 +-
 sound/drivers/serial-u16550.c         | 3 +--
 sound/drivers/vx/vx_core.c            | 2 +-
 sound/i2c/other/ak4xxx-adda.c         | 2 +-
 sound/isa/ad1816a/ad1816a_lib.c       | 2 +-
 sound/isa/azt2320.c                   | 2 +-
 sound/isa/cs423x/cs4236_lib.c         | 2 +-
 sound/isa/es1688/es1688_lib.c         | 2 +-
 sound/isa/es18xx.c                    | 2 +-
 sound/isa/opl3sa2.c                   | 3 +--
 sound/isa/opti9xx/miro.c              | 2 +-
 sound/isa/opti9xx/opti92x-ad1848.c    | 2 +-
 sound/isa/sb/emu8000.c                | 2 +-
 sound/isa/sb/sb16_main.c              | 2 +-
 sound/isa/sb/sb8_main.c               | 2 +-
 sound/isa/sb/sb8_midi.c               | 2 +-
 sound/isa/sb/sb_common.c              | 2 +-
 sound/isa/sb/sb_mixer.c               | 2 +-
 sound/isa/wavefront/wavefront_fx.c    | 2 +-
 sound/isa/wavefront/wavefront_midi.c  | 2 +-
 sound/isa/wavefront/wavefront_synth.c | 2 +-
 sound/isa/wss/wss_lib.c               | 2 +-
 sound/parisc/harmony.c                | 2 +-
 sound/pci/ad1889.c                    | 3 +--
 sound/pci/ali5451/ali5451.c           | 2 +-
 sound/pci/als300.c                    | 3 +--
 sound/pci/als4000.c                   | 2 +-
 sound/pci/atiixp.c                    | 2 +-
 sound/pci/atiixp_modem.c              | 2 +-
 sound/pci/au88x0/au88x0.h             | 2 +-
 sound/pci/aw2/aw2-saa7146.c           | 2 +-
 sound/pci/azt3328.c                   | 2 +-
 sound/pci/bt87x.c                     | 2 +-
 sound/pci/ca0106/ca0106_mixer.c       | 2 +-
 sound/pci/ca0106/ca0106_proc.c        | 2 +-
 sound/pci/cmipci.c                    | 2 +-
 sound/pci/cs4281.c                    | 2 +-
 sound/pci/cs46xx/cs46xx_lib.c         | 3 +--
 sound/pci/cs46xx/dsp_spos.c           | 2 +-
 sound/pci/cs46xx/dsp_spos_scb_lib.c   | 2 +-
 sound/pci/cs5535audio/cs5535audio.c   | 2 +-
 sound/pci/echoaudio/darla20.c         | 2 +-
 sound/pci/echoaudio/darla24.c         | 2 +-
 sound/pci/echoaudio/echo3g.c          | 2 +-
 sound/pci/echoaudio/gina20.c          | 2 +-
 sound/pci/echoaudio/gina24.c          | 2 +-
 sound/pci/echoaudio/indigo.c          | 2 +-
 sound/pci/echoaudio/indigodj.c        | 2 +-
 sound/pci/echoaudio/indigoio.c        | 2 +-
 sound/pci/echoaudio/layla20.c         | 2 +-
 sound/pci/echoaudio/layla24.c         | 2 +-
 sound/pci/echoaudio/mia.c             | 2 +-
 sound/pci/echoaudio/mona.c            | 2 +-
 sound/pci/ens1370.c                   | 2 +-
 sound/pci/es1938.c                    | 3 +--
 sound/pci/es1968.c                    | 2 +-
 sound/pci/ice1712/ak4xxx.c            | 2 +-
 sound/pci/intel8x0.c                  | 2 +-
 sound/pci/intel8x0m.c                 | 2 +-
 sound/pci/korg1212/korg1212.c         | 3 +--
 sound/pci/maestro3.c                  | 2 +-
 sound/pci/mixart/mixart_core.c        | 2 +-
 sound/pci/mixart/mixart_hwdep.c       | 2 +-
 sound/pci/nm256/nm256.c               | 2 +-
 sound/pci/oxygen/oxygen_io.c          | 2 +-
 sound/pci/pcxhr/pcxhr_core.c          | 2 +-
 sound/pci/pcxhr/pcxhr_hwdep.c         | 2 +-
 sound/pci/riptide/riptide.c           | 2 +-
 sound/pci/rme32.c                     | 3 +--
 sound/pci/rme96.c                     | 3 +--
 sound/pci/rme9652/hdsp.c              | 2 +-
 sound/pci/rme9652/hdspm.c             | 2 +-
 sound/pci/rme9652/rme9652.c           | 2 +-
 sound/pci/sonicvibes.c                | 3 +--
 sound/pci/trident/trident_main.c      | 3 +--
 sound/pci/trident/trident_memory.c    | 2 +-
 sound/pci/via82xx.c                   | 2 +-
 sound/pci/via82xx_modem.c             | 2 +-
 sound/pci/vx222/vx222_ops.c           | 2 +-
 sound/pci/ymfpci/ymfpci_main.c        | 2 +-
 sound/ppc/awacs.c                     | 2 +-
 sound/ppc/beep.c                      | 2 +-
 sound/ppc/burgundy.c                  | 2 +-
 sound/ppc/pmac.c                      | 2 +-
 sound/ppc/tumbler.c                   | 2 +-
 sound/sh/aica.c                       | 2 +-
 sound/sparc/amd7930.c                 | 2 +-
 100 files changed, 100 insertions(+), 111 deletions(-)

(limited to 'include')

diff --git a/include/sound/emu10k1.h b/include/sound/emu10k1.h
index 7f6ab6cd565..0de95ccb92c 100644
--- a/include/sound/emu10k1.h
+++ b/include/sound/emu10k1.h
@@ -33,8 +33,8 @@
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/firmware.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <uapi/sound/emu10k1.h>
 
 /* ------------------- DEFINES -------------------- */
diff --git a/include/sound/gus.h b/include/sound/gus.h
index 06bbdc25917..07c116fe78c 100644
--- a/include/sound/gus.h
+++ b/include/sound/gus.h
@@ -27,7 +27,7 @@
 #include <sound/timer.h>
 #include <sound/seq_midi_emul.h>
 #include <sound/seq_device.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 /* IO ports */
 
diff --git a/include/sound/sb.h b/include/sound/sb.h
index 33e2d11deed..bacefaee411 100644
--- a/include/sound/sb.h
+++ b/include/sound/sb.h
@@ -25,7 +25,7 @@
 #include <sound/pcm.h>
 #include <sound/rawmidi.h>
 #include <linux/interrupt.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 enum sb_hw_type {
 	SB_HW_AUTO,
diff --git a/sound/aoa/soundbus/i2sbus/control.c b/sound/aoa/soundbus/i2sbus/control.c
index 4dc9b49c02c..f4495decc69 100644
--- a/sound/aoa/soundbus/i2sbus/control.c
+++ b/sound/aoa/soundbus/i2sbus/control.c
@@ -9,8 +9,8 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/macio.h>
 #include <asm/pmac_feature.h>
diff --git a/sound/aoa/soundbus/i2sbus/pcm.c b/sound/aoa/soundbus/i2sbus/pcm.c
index 7b74a4ba75f..4177d9729d0 100644
--- a/sound/aoa/soundbus/i2sbus/pcm.c
+++ b/sound/aoa/soundbus/i2sbus/pcm.c
@@ -6,7 +6,7 @@
  * GPL v2, can be found in COPYING.
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <sound/core.h>
diff --git a/sound/core/memory.c b/sound/core/memory.c
index 36c0f1a2e18..ca775d7589d 100644
--- a/sound/core/memory.c
+++ b/sound/core/memory.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/export.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/uaccess.h>
 #include <sound/core.h>
 
diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c
index 54debc07f5c..b45f6aa3226 100644
--- a/sound/core/pcm_memory.c
+++ b/sound/core/pcm_memory.c
@@ -19,7 +19,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/slab.h>
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index ff3abc3b4ff..932234d8792 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -26,6 +26,7 @@
 #include <linux/time.h>
 #include <linux/pm_qos.h>
 #include <linux/aio.h>
+#include <linux/io.h>
 #include <linux/dma-mapping.h>
 #include <sound/core.h>
 #include <sound/control.h>
@@ -34,7 +35,6 @@
 #include <sound/pcm_params.h>
 #include <sound/timer.h>
 #include <sound/minors.h>
-#include <asm/io.h>
 
 /*
  *  Compatibility
diff --git a/sound/drivers/mpu401/mpu401_uart.c b/sound/drivers/mpu401/mpu401_uart.c
index 1e19eb9e159..776596b5ee0 100644
--- a/sound/drivers/mpu401/mpu401_uart.c
+++ b/sound/drivers/mpu401/mpu401_uart.c
@@ -28,7 +28,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/slab.h>
diff --git a/sound/drivers/opl3/opl3_lib.c b/sound/drivers/opl3/opl3_lib.c
index f66af5884c4..369cef212ea 100644
--- a/sound/drivers/opl3/opl3_lib.c
+++ b/sound/drivers/opl3/opl3_lib.c
@@ -24,7 +24,7 @@
  */
 
 #include <sound/opl3.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/sound/drivers/opl4/opl4_lib.c b/sound/drivers/opl4/opl4_lib.c
index b953fb4aa29..3b0ee42a534 100644
--- a/sound/drivers/opl4/opl4_lib.c
+++ b/sound/drivers/opl4/opl4_lib.c
@@ -23,7 +23,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
 MODULE_DESCRIPTION("OPL4 driver");
diff --git a/sound/drivers/opl4/opl4_synth.c b/sound/drivers/opl4/opl4_synth.c
index 4b91adc0238..7bc1e58c95a 100644
--- a/sound/drivers/opl4/opl4_synth.c
+++ b/sound/drivers/opl4/opl4_synth.c
@@ -33,7 +33,7 @@
 
 #include "opl4_local.h"
 #include <linux/delay.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/asoundef.h>
 
 /* GM2 controllers */
diff --git a/sound/drivers/pcsp/pcsp_input.c b/sound/drivers/pcsp/pcsp_input.c
index 0ecf8a453e0..bfc25811985 100644
--- a/sound/drivers/pcsp/pcsp_input.c
+++ b/sound/drivers/pcsp/pcsp_input.c
@@ -14,7 +14,7 @@
 
 #include <linux/init.h>
 #include <linux/input.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include "pcsp.h"
 #include "pcsp_input.h"
 
diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c
index 29ebaa4ec0f..3689f5f6be6 100644
--- a/sound/drivers/pcsp/pcsp_lib.c
+++ b/sound/drivers/pcsp/pcsp_lib.c
@@ -10,8 +10,8 @@
 #include <linux/gfp.h>
 #include <linux/moduleparam.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <sound/pcm.h>
-#include <asm/io.h>
 #include "pcsp.h"
 
 static bool nforce_wa;
diff --git a/sound/drivers/serial-u16550.c b/sound/drivers/serial-u16550.c
index 8c1dc73e14e..1927b89e1d1 100644
--- a/sound/drivers/serial-u16550.c
+++ b/sound/drivers/serial-u16550.c
@@ -37,6 +37,7 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/rawmidi.h>
 #include <sound/initval.h>
@@ -44,8 +45,6 @@
 #include <linux/serial_reg.h>
 #include <linux/jiffies.h>
 
-#include <asm/io.h>
-
 MODULE_DESCRIPTION("MIDI serial u16550");
 MODULE_LICENSE("GPL");
 MODULE_SUPPORTED_DEVICE("{{ALSA, MIDI serial u16550}}");
diff --git a/sound/drivers/vx/vx_core.c b/sound/drivers/vx/vx_core.c
index fc05a37fd01..289f041706c 100644
--- a/sound/drivers/vx/vx_core.c
+++ b/sound/drivers/vx/vx_core.c
@@ -27,11 +27,11 @@
 #include <linux/device.h>
 #include <linux/firmware.h>
 #include <linux/module.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/asoundef.h>
 #include <sound/info.h>
-#include <asm/io.h>
 #include <sound/vx_core.h>
 #include "vx_cmd.h"
 
diff --git a/sound/i2c/other/ak4xxx-adda.c b/sound/i2c/other/ak4xxx-adda.c
index 67dbfde837a..c65731088aa 100644
--- a/sound/i2c/other/ak4xxx-adda.c
+++ b/sound/i2c/other/ak4xxx-adda.c
@@ -21,7 +21,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/isa/ad1816a/ad1816a_lib.c b/sound/isa/ad1816a/ad1816a_lib.c
index 5f99102cc0c..5c815f5fb04 100644
--- a/sound/isa/ad1816a/ad1816a_lib.c
+++ b/sound/isa/ad1816a/ad1816a_lib.c
@@ -22,11 +22,11 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/ioport.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/tlv.h>
 #include <sound/ad1816a.h>
 
-#include <asm/io.h>
 #include <asm/dma.h>
 
 static inline int snd_ad1816a_busy_wait(struct snd_ad1816a *chip)
diff --git a/sound/isa/azt2320.c b/sound/isa/azt2320.c
index b8e768e5ce8..fff186fa621 100644
--- a/sound/isa/azt2320.c
+++ b/sound/isa/azt2320.c
@@ -29,7 +29,7 @@
     activation method (full-duplex audio!).
 */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/time.h>
diff --git a/sound/isa/cs423x/cs4236_lib.c b/sound/isa/cs423x/cs4236_lib.c
index add7ffc072c..2b7cc596f4c 100644
--- a/sound/isa/cs423x/cs4236_lib.c
+++ b/sound/isa/cs423x/cs4236_lib.c
@@ -79,7 +79,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/time.h>
diff --git a/sound/isa/es1688/es1688_lib.c b/sound/isa/es1688/es1688_lib.c
index 52aac846717..e2cf508841b 100644
--- a/sound/isa/es1688/es1688_lib.c
+++ b/sound/isa/es1688/es1688_lib.c
@@ -25,11 +25,11 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/es1688.h>
 #include <sound/initval.h>
 
-#include <asm/io.h>
 #include <asm/dma.h>
 
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
diff --git a/sound/isa/es18xx.c b/sound/isa/es18xx.c
index 6cc2d2bbde6..5094b62d8f7 100644
--- a/sound/isa/es18xx.c
+++ b/sound/isa/es18xx.c
@@ -84,8 +84,8 @@
 #include <linux/isapnp.h>
 #include <linux/module.h>
 #include <linux/delay.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/dma.h>
 #include <sound/core.h>
 #include <sound/control.h>
diff --git a/sound/isa/opl3sa2.c b/sound/isa/opl3sa2.c
index d7aff527da8..ae133633a42 100644
--- a/sound/isa/opl3sa2.c
+++ b/sound/isa/opl3sa2.c
@@ -26,6 +26,7 @@
 #include <linux/pm.h>
 #include <linux/pnp.h>
 #include <linux/module.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/wss.h>
 #include <sound/mpu401.h>
@@ -33,8 +34,6 @@
 #include <sound/initval.h>
 #include <sound/tlv.h>
 
-#include <asm/io.h>
-
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Yamaha OPL3SA2+");
 MODULE_LICENSE("GPL");
diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c
index 546452888ae..3a9067db1a8 100644
--- a/sound/isa/opti9xx/miro.c
+++ b/sound/isa/opti9xx/miro.c
@@ -29,7 +29,7 @@
 #include <linux/delay.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/dma.h>
 #include <sound/core.h>
 #include <sound/wss.h>
diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index 840831f1dd4..0a526600378 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -29,7 +29,7 @@
 #include <linux/delay.h>
 #include <linux/pnp.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/dma.h>
 #include <sound/core.h>
 #include <sound/tlv.h>
diff --git a/sound/isa/sb/emu8000.c b/sound/isa/sb/emu8000.c
index 96e9d94d07e..1449354a23f 100644
--- a/sound/isa/sb/emu8000.c
+++ b/sound/isa/sb/emu8000.c
@@ -26,10 +26,10 @@
 #include <linux/ioport.h>
 #include <linux/export.h>
 #include <linux/delay.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/emu8000.h>
 #include <sound/emu8000_reg.h>
-#include <asm/io.h>
 #include <asm/uaccess.h>
 #include <linux/init.h>
 #include <sound/control.h>
diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index 63d11b7b9fe..8b2d6c6bfe9 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -33,7 +33,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/dma.h>
 #include <linux/init.h>
 #include <linux/time.h>
diff --git a/sound/isa/sb/sb8_main.c b/sound/isa/sb/sb8_main.c
index d4d8b0e604e..9043397fe62 100644
--- a/sound/isa/sb/sb8_main.c
+++ b/sound/isa/sb/sb8_main.c
@@ -30,7 +30,7 @@
  *   Cleaned up and rewrote lowlevel routines.
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/dma.h>
 #include <linux/init.h>
 #include <linux/time.h>
diff --git a/sound/isa/sb/sb8_midi.c b/sound/isa/sb/sb8_midi.c
index 925ea45b3d9..d551c50e549 100644
--- a/sound/isa/sb/sb8_midi.c
+++ b/sound/isa/sb/sb8_midi.c
@@ -26,7 +26,7 @@
  *   Added full duplex UART mode for DSP version 2.0 and later.
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/time.h>
 #include <sound/core.h>
 #include <sound/sb.h>
diff --git a/sound/isa/sb/sb_common.c b/sound/isa/sb/sb_common.c
index f22b4480828..787a4ade4af 100644
--- a/sound/isa/sb/sb_common.c
+++ b/sound/isa/sb/sb_common.c
@@ -26,11 +26,11 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/sb.h>
 #include <sound/initval.h>
 
-#include <asm/io.h>
 #include <asm/dma.h>
 
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
diff --git a/sound/isa/sb/sb_mixer.c b/sound/isa/sb/sb_mixer.c
index e403334a19a..add1d3f9960 100644
--- a/sound/isa/sb/sb_mixer.c
+++ b/sound/isa/sb/sb_mixer.c
@@ -19,7 +19,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/time.h>
 #include <sound/core.h>
diff --git a/sound/isa/wavefront/wavefront_fx.c b/sound/isa/wavefront/wavefront_fx.c
index b77883c7ee7..b5a19708473 100644
--- a/sound/isa/wavefront/wavefront_fx.c
+++ b/sound/isa/wavefront/wavefront_fx.c
@@ -16,7 +16,7 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/init.h>
 #include <linux/time.h>
 #include <linux/wait.h>
diff --git a/sound/isa/wavefront/wavefront_midi.c b/sound/isa/wavefront/wavefront_midi.c
index b8009cbcd34..8a80fc6a616 100644
--- a/sound/isa/wavefront/wavefront_midi.c
+++ b/sound/isa/wavefront/wavefront_midi.c
@@ -47,7 +47,7 @@
  *  
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/init.h>
 #include <linux/time.h>
 #include <linux/wait.h>
diff --git a/sound/isa/wavefront/wavefront_synth.c b/sound/isa/wavefront/wavefront_synth.c
index e5db001363e..33f5ec14fcf 100644
--- a/sound/isa/wavefront/wavefront_synth.c
+++ b/sound/isa/wavefront/wavefront_synth.c
@@ -20,7 +20,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/delay.h>
diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c
index 6530d32901b..913b731d223 100644
--- a/sound/isa/wss/wss_lib.c
+++ b/sound/isa/wss/wss_lib.c
@@ -31,12 +31,12 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/wss.h>
 #include <sound/pcm_params.h>
 #include <sound/tlv.h>
 
-#include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/irq.h>
 
diff --git a/sound/parisc/harmony.c b/sound/parisc/harmony.c
index f2350c1d6ee..99b64cb3cef 100644
--- a/sound/parisc/harmony.c
+++ b/sound/parisc/harmony.c
@@ -44,6 +44,7 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/dma-mapping.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -52,7 +53,6 @@
 #include <sound/initval.h>
 #include <sound/info.h>
 
-#include <asm/io.h>
 #include <asm/hardware.h>
 #include <asm/parisc-device.h>
 
diff --git a/sound/pci/ad1889.c b/sound/pci/ad1889.c
index 0de31290411..850a8c984c2 100644
--- a/sound/pci/ad1889.c
+++ b/sound/pci/ad1889.c
@@ -40,14 +40,13 @@
 #include <linux/compiler.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/initval.h>
 #include <sound/ac97_codec.h>
 
-#include <asm/io.h>
-
 #include "ad1889.h"
 #include "ac97/ac97_id.h"
 
diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c
index 4cd2210fd95..c8d499575c0 100644
--- a/sound/pci/ali5451/ali5451.c
+++ b/sound/pci/ali5451/ali5451.c
@@ -25,7 +25,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/als300.c b/sound/pci/als300.c
index bd01113de39..57e034f208d 100644
--- a/sound/pci/als300.c
+++ b/sound/pci/als300.c
@@ -37,8 +37,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
-
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
diff --git a/sound/pci/als4000.c b/sound/pci/als4000.c
index 94608524f3c..a3dea464134 100644
--- a/sound/pci/als4000.c
+++ b/sound/pci/als4000.c
@@ -65,7 +65,7 @@
  * - power management? (card can do voice wakeup according to datasheet!!)
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/gameport.h>
diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c
index eb4f9ee54f8..d5f15c9bbed 100644
--- a/sound/pci/atiixp.c
+++ b/sound/pci/atiixp.c
@@ -19,7 +19,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c
index 349dd7ba6e4..0a38e08164a 100644
--- a/sound/pci/atiixp_modem.c
+++ b/sound/pci/atiixp_modem.c
@@ -19,7 +19,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/au88x0/au88x0.h b/sound/pci/au88x0/au88x0.h
index 3a8fefefea7..98c53bbf883 100644
--- a/sound/pci/au88x0/au88x0.h
+++ b/sound/pci/au88x0/au88x0.h
@@ -19,7 +19,7 @@
 
 #ifdef __KERNEL__
 #include <linux/pci.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/rawmidi.h>
diff --git a/sound/pci/aw2/aw2-saa7146.c b/sound/pci/aw2/aw2-saa7146.c
index 6d24e953677..1d789045933 100644
--- a/sound/pci/aw2/aw2-saa7146.c
+++ b/sound/pci/aw2/aw2-saa7146.c
@@ -27,7 +27,7 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/initval.h>
 #include <sound/pcm.h>
diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c
index bbacc75c902..a40a2b4c8fd 100644
--- a/sound/pci/azt3328.c
+++ b/sound/pci/azt3328.c
@@ -179,7 +179,7 @@
  *  - use MMIO (memory-mapped I/O)? Slightly faster access, e.g. for gameport.
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/init.h>
 #include <linux/bug.h> /* WARN_ONCE */
 #include <linux/pci.h>
diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c
index e82ceacbe64..5925b7170e2 100644
--- a/sound/pci/bt87x.c
+++ b/sound/pci/bt87x.c
@@ -27,7 +27,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
diff --git a/sound/pci/ca0106/ca0106_mixer.c b/sound/pci/ca0106/ca0106_mixer.c
index 68c0eb0a280..025805cba77 100644
--- a/sound/pci/ca0106/ca0106_mixer.c
+++ b/sound/pci/ca0106/ca0106_mixer.c
@@ -70,7 +70,7 @@
 #include <sound/ac97_codec.h>
 #include <sound/info.h>
 #include <sound/tlv.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include "ca0106.h"
 
diff --git a/sound/pci/ca0106/ca0106_proc.c b/sound/pci/ca0106/ca0106_proc.c
index 4f9c2821bb3..2c5c28adbef 100644
--- a/sound/pci/ca0106/ca0106_proc.c
+++ b/sound/pci/ca0106/ca0106_proc.c
@@ -64,13 +64,13 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/moduleparam.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/initval.h>
 #include <sound/pcm.h>
 #include <sound/ac97_codec.h>
 #include <sound/info.h>
 #include <sound/asoundef.h>
-#include <asm/io.h>
 
 #include "ca0106.h"
 
diff --git a/sound/pci/cmipci.c b/sound/pci/cmipci.c
index 63d2c8236ec..1d0f2cad2f5 100644
--- a/sound/pci/cmipci.c
+++ b/sound/pci/cmipci.c
@@ -20,7 +20,7 @@
 /* Does not work. Warning may block system in capture mode */
 /* #define USE_VAR48KRATE */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/cs4281.c b/sound/pci/cs4281.c
index 754613b772a..c296fd0dbc9 100644
--- a/sound/pci/cs4281.c
+++ b/sound/pci/cs4281.c
@@ -19,7 +19,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/cs46xx/cs46xx_lib.c b/sound/pci/cs46xx/cs46xx_lib.c
index fb3abb2203c..8d74004b1ed 100644
--- a/sound/pci/cs46xx/cs46xx_lib.c
+++ b/sound/pci/cs46xx/cs46xx_lib.c
@@ -57,6 +57,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/vmalloc.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
@@ -65,8 +66,6 @@
 #include <sound/pcm_params.h>
 #include "cs46xx.h"
 
-#include <asm/io.h>
-
 #include "cs46xx_lib.h"
 #include "dsp_spos.h"
 
diff --git a/sound/pci/cs46xx/dsp_spos.c b/sound/pci/cs46xx/dsp_spos.c
index 1c4a0fb3ffe..5c99efb004c 100644
--- a/sound/pci/cs46xx/dsp_spos.c
+++ b/sound/pci/cs46xx/dsp_spos.c
@@ -20,7 +20,7 @@
  */
 
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/pm.h>
 #include <linux/init.h>
diff --git a/sound/pci/cs46xx/dsp_spos_scb_lib.c b/sound/pci/cs46xx/dsp_spos_scb_lib.c
index 8284bc9b585..2c90c0bded6 100644
--- a/sound/pci/cs46xx/dsp_spos_scb_lib.c
+++ b/sound/pci/cs46xx/dsp_spos_scb_lib.c
@@ -21,7 +21,7 @@
  */
 
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/pm.h>
 #include <linux/init.h>
diff --git a/sound/pci/cs5535audio/cs5535audio.c b/sound/pci/cs5535audio/cs5535audio.c
index 16288e4d338..802c33f1cc5 100644
--- a/sound/pci/cs5535audio/cs5535audio.c
+++ b/sound/pci/cs5535audio/cs5535audio.c
@@ -27,7 +27,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/pcm.h>
diff --git a/sound/pci/echoaudio/darla20.c b/sound/pci/echoaudio/darla20.c
index 4632946205a..c95da630167 100644
--- a/sound/pci/echoaudio/darla20.c
+++ b/sound/pci/echoaudio/darla20.c
@@ -43,6 +43,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -51,7 +52,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/darla24.c b/sound/pci/echoaudio/darla24.c
index f81c839cc88..3013b4daa19 100644
--- a/sound/pci/echoaudio/darla24.c
+++ b/sound/pci/echoaudio/darla24.c
@@ -47,6 +47,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -55,7 +56,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/echo3g.c b/sound/pci/echoaudio/echo3g.c
index 3a5346c33d7..1f34a07b0b1 100644
--- a/sound/pci/echoaudio/echo3g.c
+++ b/sound/pci/echoaudio/echo3g.c
@@ -54,6 +54,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -63,7 +64,6 @@
 #include <sound/asoundef.h>
 #include <sound/initval.h>
 #include <sound/rawmidi.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/gina20.c b/sound/pci/echoaudio/gina20.c
index 9cb81c50082..4fa32a2e97d 100644
--- a/sound/pci/echoaudio/gina20.c
+++ b/sound/pci/echoaudio/gina20.c
@@ -47,6 +47,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -55,7 +56,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/gina24.c b/sound/pci/echoaudio/gina24.c
index 35d3e6eac99..b1bcacaef25 100644
--- a/sound/pci/echoaudio/gina24.c
+++ b/sound/pci/echoaudio/gina24.c
@@ -53,6 +53,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -61,7 +62,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/indigo.c b/sound/pci/echoaudio/indigo.c
index 8d91842d126..175af9b1435 100644
--- a/sound/pci/echoaudio/indigo.c
+++ b/sound/pci/echoaudio/indigo.c
@@ -45,6 +45,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -53,7 +54,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/indigodj.c b/sound/pci/echoaudio/indigodj.c
index 289cb969f5b..8c60314e490 100644
--- a/sound/pci/echoaudio/indigodj.c
+++ b/sound/pci/echoaudio/indigodj.c
@@ -45,6 +45,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -53,7 +54,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/indigoio.c b/sound/pci/echoaudio/indigoio.c
index 405a3f2e496..f7618edfd79 100644
--- a/sound/pci/echoaudio/indigoio.c
+++ b/sound/pci/echoaudio/indigoio.c
@@ -46,6 +46,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -54,7 +55,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/layla20.c b/sound/pci/echoaudio/layla20.c
index b392dd776b7..12e5d2164dc 100644
--- a/sound/pci/echoaudio/layla20.c
+++ b/sound/pci/echoaudio/layla20.c
@@ -52,6 +52,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -61,7 +62,6 @@
 #include <sound/asoundef.h>
 #include <sound/initval.h>
 #include <sound/rawmidi.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/layla24.c b/sound/pci/echoaudio/layla24.c
index bc7f730b0ec..6e4023728ef 100644
--- a/sound/pci/echoaudio/layla24.c
+++ b/sound/pci/echoaudio/layla24.c
@@ -54,6 +54,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -63,7 +64,6 @@
 #include <sound/asoundef.h>
 #include <sound/initval.h>
 #include <sound/rawmidi.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/mia.c b/sound/pci/echoaudio/mia.c
index 27a9a6e5db2..2f7562f1aef 100644
--- a/sound/pci/echoaudio/mia.c
+++ b/sound/pci/echoaudio/mia.c
@@ -53,6 +53,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -62,7 +63,6 @@
 #include <sound/asoundef.h>
 #include <sound/initval.h>
 #include <sound/rawmidi.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/echoaudio/mona.c b/sound/pci/echoaudio/mona.c
index 3d13875c303..34d49946639 100644
--- a/sound/pci/echoaudio/mona.c
+++ b/sound/pci/echoaudio/mona.c
@@ -51,6 +51,7 @@
 #include <linux/module.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -59,7 +60,6 @@
 #include <sound/pcm_params.h>
 #include <sound/asoundef.h>
 #include <sound/initval.h>
-#include <asm/io.h>
 #include <linux/atomic.h>
 #include "echoaudio.h"
 
diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c
index 219b8af29a4..0dc44ebb003 100644
--- a/sound/pci/ens1370.c
+++ b/sound/pci/ens1370.c
@@ -26,7 +26,7 @@
  * by Kurt J. Bosch
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/es1938.c b/sound/pci/es1938.c
index a01454b545a..e1858d9d23d 100644
--- a/sound/pci/es1938.c
+++ b/sound/pci/es1938.c
@@ -55,6 +55,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/pcm.h>
@@ -63,8 +64,6 @@
 #include <sound/initval.h>
 #include <sound/tlv.h>
 
-#include <asm/io.h>
-
 MODULE_AUTHOR("Jaromir Koutek <miri@punknet.cz>");
 MODULE_DESCRIPTION("ESS Solo-1");
 MODULE_LICENSE("GPL");
diff --git a/sound/pci/es1968.c b/sound/pci/es1968.c
index 631be029f8c..059f3846d7b 100644
--- a/sound/pci/es1968.c
+++ b/sound/pci/es1968.c
@@ -94,7 +94,7 @@
  *	places.
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/ice1712/ak4xxx.c b/sound/pci/ice1712/ak4xxx.c
index 3981823f909..179ef7a5f0d 100644
--- a/sound/pci/ice1712/ak4xxx.c
+++ b/sound/pci/ice1712/ak4xxx.c
@@ -21,7 +21,7 @@
  *
  */      
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 67f9e8b7738..2c5484eeb96 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -26,7 +26,7 @@
  *
  */      
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c
index 748f6f67c98..7577f31cd50 100644
--- a/sound/pci/intel8x0m.c
+++ b/sound/pci/intel8x0m.c
@@ -23,7 +23,7 @@
  *
  */      
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c
index bd569e58027..7acbc21d642 100644
--- a/sound/pci/korg1212/korg1212.c
+++ b/sound/pci/korg1212/korg1212.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/firmware.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/info.h>
@@ -36,8 +37,6 @@
 #include <sound/pcm_params.h>
 #include <sound/initval.h>
 
-#include <asm/io.h>
-
 // ----------------------------------------------------------------------------
 // Debug Stuff
 // ----------------------------------------------------------------------------
diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c
index 18a60be6326..9be660993bd 100644
--- a/sound/pci/maestro3.c
+++ b/sound/pci/maestro3.c
@@ -31,7 +31,7 @@
 #define CARD_NAME "ESS Maestro3/Allegro/Canyon3D-2"
 #define DRIVER_NAME "Maestro3"
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c
index fe80313674d..dccf3db48fe 100644
--- a/sound/pci/mixart/mixart_core.c
+++ b/sound/pci/mixart/mixart_core.c
@@ -23,8 +23,8 @@
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <sound/core.h>
 #include "mixart.h"
 #include "mixart_hwdep.h"
diff --git a/sound/pci/mixart/mixart_hwdep.c b/sound/pci/mixart/mixart_hwdep.c
index 9996a4dead0..5bfd3ac80db 100644
--- a/sound/pci/mixart/mixart_hwdep.c
+++ b/sound/pci/mixart/mixart_hwdep.c
@@ -26,7 +26,7 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include "mixart.h"
 #include "mixart_mixer.h"
diff --git a/sound/pci/nm256/nm256.c b/sound/pci/nm256/nm256.c
index 90674b93b93..4735e27cc77 100644
--- a/sound/pci/nm256/nm256.c
+++ b/sound/pci/nm256/nm256.c
@@ -24,7 +24,7 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
   
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/oxygen/oxygen_io.c b/sound/pci/oxygen/oxygen_io.c
index 4b8a32c37e3..c7851da3774 100644
--- a/sound/pci/oxygen/oxygen_io.c
+++ b/sound/pci/oxygen/oxygen_io.c
@@ -20,9 +20,9 @@
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/export.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/mpu401.h>
-#include <asm/io.h>
 #include "oxygen.h"
 
 u8 oxygen_read8(struct oxygen *chip, unsigned int reg)
diff --git a/sound/pci/pcxhr/pcxhr_core.c b/sound/pci/pcxhr/pcxhr_core.c
index 181f7729d40..c5194f5b150 100644
--- a/sound/pci/pcxhr/pcxhr_core.c
+++ b/sound/pci/pcxhr/pcxhr_core.c
@@ -24,7 +24,7 @@
 #include <linux/firmware.h>
 #include <linux/interrupt.h>
 #include <linux/pci.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include "pcxhr.h"
 #include "pcxhr_mixer.h"
diff --git a/sound/pci/pcxhr/pcxhr_hwdep.c b/sound/pci/pcxhr/pcxhr_hwdep.c
index 15a8ce5f1f4..80633055e17 100644
--- a/sound/pci/pcxhr/pcxhr_hwdep.c
+++ b/sound/pci/pcxhr/pcxhr_hwdep.c
@@ -25,7 +25,7 @@
 #include <linux/firmware.h>
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/hwdep.h>
 #include "pcxhr.h"
diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index a1521047e61..29f28273b2c 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -99,7 +99,7 @@
 #include <linux/firmware.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/info.h>
 #include <sound/control.h>
diff --git a/sound/pci/rme32.c b/sound/pci/rme32.c
index 1a7affad716..23d7f5d30c4 100644
--- a/sound/pci/rme32.c
+++ b/sound/pci/rme32.c
@@ -75,6 +75,7 @@
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/module.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/info.h>
@@ -85,8 +86,6 @@
 #include <sound/asoundef.h>
 #include <sound/initval.h>
 
-#include <asm/io.h>
-
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
 static bool enable[SNDRV_CARDS] = SNDRV_DEFAULT_ENABLE_PNP;	/* Enable this card */
diff --git a/sound/pci/rme96.c b/sound/pci/rme96.c
index 236ac1d4818..2306ccf7281 100644
--- a/sound/pci/rme96.c
+++ b/sound/pci/rme96.c
@@ -29,6 +29,7 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/info.h>
@@ -38,8 +39,6 @@
 #include <sound/asoundef.h>
 #include <sound/initval.h>
 
-#include <asm/io.h>
-
 /* note, two last pcis should be equal, it is not a bug */
 
 MODULE_AUTHOR("Anders Torger <torger@ludd.luth.se>");
diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index 98a2d911ef1..c19e021ccf6 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/math64.h>
 #include <linux/vmalloc.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
@@ -42,7 +43,6 @@
 
 #include <asm/byteorder.h>
 #include <asm/current.h>
-#include <asm/io.h>
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index 1716323fed9..2c363fdca9f 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -136,7 +136,7 @@
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/math64.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index 648911c1a22..fdbc0aa2776 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/pci.h>
 #include <linux/module.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
@@ -34,7 +35,6 @@
 #include <sound/initval.h>
 
 #include <asm/current.h>
-#include <asm/io.h>
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;	/* Index 0-MAX */
 static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;	/* ID for this card */
diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c
index 34cee5c1abd..0f40624a427 100644
--- a/sound/pci/sonicvibes.c
+++ b/sound/pci/sonicvibes.c
@@ -30,6 +30,7 @@
 #include <linux/gameport.h>
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -39,8 +40,6 @@
 #include <sound/opl3.h>
 #include <sound/initval.h>
 
-#include <asm/io.h>
-
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("S3 SonicVibes PCI");
 MODULE_LICENSE("GPL");
diff --git a/sound/pci/trident/trident_main.c b/sound/pci/trident/trident_main.c
index 2870cbf8cee..b72be035f78 100644
--- a/sound/pci/trident/trident_main.c
+++ b/sound/pci/trident/trident_main.c
@@ -36,6 +36,7 @@
 #include <linux/gameport.h>
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/info.h>
@@ -44,8 +45,6 @@
 #include "trident.h"
 #include <sound/asoundef.h>
 
-#include <asm/io.h>
-
 static int snd_trident_pcm_mixer_build(struct snd_trident *trident,
 				       struct snd_trident_voice * voice,
 				       struct snd_pcm_substream *substream);
diff --git a/sound/pci/trident/trident_memory.c b/sound/pci/trident/trident_memory.c
index 04c474658e3..b9ebb51893c 100644
--- a/sound/pci/trident/trident_memory.c
+++ b/sound/pci/trident/trident_memory.c
@@ -23,7 +23,7 @@
  *
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/pci.h>
 #include <linux/time.h>
 #include <linux/mutex.h>
diff --git a/sound/pci/via82xx.c b/sound/pci/via82xx.c
index 120fccbb246..8622283e89f 100644
--- a/sound/pci/via82xx.c
+++ b/sound/pci/via82xx.c
@@ -46,7 +46,7 @@
  *	- Optimize position calculation for the 823x chips. 
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/via82xx_modem.c b/sound/pci/via82xx_modem.c
index 884f49eea49..99b9137bc67 100644
--- a/sound/pci/via82xx_modem.c
+++ b/sound/pci/via82xx_modem.c
@@ -31,7 +31,7 @@
  *      modems.
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
diff --git a/sound/pci/vx222/vx222_ops.c b/sound/pci/vx222/vx222_ops.c
index 52c1a8d5b88..af83b3b3805 100644
--- a/sound/pci/vx222/vx222_ops.c
+++ b/sound/pci/vx222/vx222_ops.c
@@ -24,11 +24,11 @@
 #include <linux/device.h>
 #include <linux/firmware.h>
 #include <linux/mutex.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/tlv.h>
-#include <asm/io.h>
 #include "vx222.h"
 
 
diff --git a/sound/pci/ymfpci/ymfpci_main.c b/sound/pci/ymfpci/ymfpci_main.c
index 227d5c9dfe0..4c26076dbf7 100644
--- a/sound/pci/ymfpci/ymfpci_main.c
+++ b/sound/pci/ymfpci/ymfpci_main.c
@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/control.h>
@@ -36,7 +37,6 @@
 #include <sound/asoundef.h>
 #include <sound/mpu401.h>
 
-#include <asm/io.h>
 #include <asm/byteorder.h>
 
 /*
diff --git a/sound/ppc/awacs.c b/sound/ppc/awacs.c
index 5fbf5db2543..09da7b52bc2 100644
--- a/sound/ppc/awacs.c
+++ b/sound/ppc/awacs.c
@@ -20,7 +20,7 @@
  */
 
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/nvram.h>
 #include <linux/init.h>
 #include <linux/delay.h>
diff --git a/sound/ppc/beep.c b/sound/ppc/beep.c
index 0040f048221..d3524f9fa05 100644
--- a/sound/ppc/beep.c
+++ b/sound/ppc/beep.c
@@ -18,7 +18,7 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/irq.h>
 #include <linux/init.h>
 #include <linux/slab.h>
diff --git a/sound/ppc/burgundy.c b/sound/ppc/burgundy.c
index cb4f0a5e984..b86159e0449 100644
--- a/sound/ppc/burgundy.c
+++ b/sound/ppc/burgundy.c
@@ -19,7 +19,7 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <sound/core.h>
diff --git a/sound/ppc/pmac.c b/sound/ppc/pmac.c
index d399df47389..13146d70141 100644
--- a/sound/ppc/pmac.c
+++ b/sound/ppc/pmac.c
@@ -20,7 +20,7 @@
  */
 
 
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/irq.h>
 #include <linux/init.h>
 #include <linux/delay.h>
diff --git a/sound/ppc/tumbler.c b/sound/ppc/tumbler.c
index 24c8766a925..c8fafba218a 100644
--- a/sound/ppc/tumbler.c
+++ b/sound/ppc/tumbler.c
@@ -32,8 +32,8 @@
 #include <linux/interrupt.h>
 #include <linux/string.h>
 #include <linux/of_irq.h>
+#include <linux/io.h>
 #include <sound/core.h>
-#include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/machdep.h>
 #include <asm/pmac_feature.h>
diff --git a/sound/sh/aica.c b/sound/sh/aica.c
index 8212300088f..ad3d9ae3803 100644
--- a/sound/sh/aica.c
+++ b/sound/sh/aica.c
@@ -35,12 +35,12 @@
 #include <linux/timer.h>
 #include <linux/delay.h>
 #include <linux/workqueue.h>
+#include <linux/io.h>
 #include <sound/core.h>
 #include <sound/control.h>
 #include <sound/pcm.h>
 #include <sound/initval.h>
 #include <sound/info.h>
-#include <asm/io.h>
 #include <asm/dma.h>
 #include <mach/sysasic.h>
 #include "aica.h"
diff --git a/sound/sparc/amd7930.c b/sound/sparc/amd7930.c
index 86280d63b76..1b1a89e80d1 100644
--- a/sound/sparc/amd7930.c
+++ b/sound/sparc/amd7930.c
@@ -37,6 +37,7 @@
 #include <linux/moduleparam.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/io.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -44,7 +45,6 @@
 #include <sound/control.h>
 #include <sound/initval.h>
 
-#include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/prom.h>
 
-- 
cgit v1.2.3-70-g09d2


From 5da7f924a41949797875c98a776dca1737a0f372 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 28 Jan 2015 17:32:22 +0100
Subject: ALSA: usx2y: Move UAPI definition into
 include/uapi/sound/usb_stream.h

The user-space API definition for usb_stream stuff should be moved
to include/uapi/sound to be exposed publicly.

While we're at it, add the missing ifdef guard for double inclusion,
too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/uapi/sound/usb_stream.h | 76 +++++++++++++++++++++++++++++++++++++++
 sound/usb/usx2y/usb_stream.h    | 78 +++--------------------------------------
 2 files changed, 80 insertions(+), 74 deletions(-)
 create mode 100644 include/uapi/sound/usb_stream.h

(limited to 'include')

diff --git a/include/uapi/sound/usb_stream.h b/include/uapi/sound/usb_stream.h
new file mode 100644
index 00000000000..cfe8fba0071
--- /dev/null
+++ b/include/uapi/sound/usb_stream.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright (C) 2007, 2008 Karsten Wiese <fzu@wemgehoertderstaat.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _UAPI__SOUND_USB_STREAM_H
+#define _UAPI__SOUND_USB_STREAM_H
+
+#define USB_STREAM_INTERFACE_VERSION 2
+
+#define SNDRV_USB_STREAM_IOCTL_SET_PARAMS \
+	_IOW('H', 0x90, struct usb_stream_config)
+
+struct usb_stream_packet {
+	unsigned offset;
+	unsigned length;
+};
+
+
+struct usb_stream_config {
+	unsigned version;
+	unsigned sample_rate;
+	unsigned period_frames;
+	unsigned frame_size;
+};
+
+struct usb_stream {
+	struct usb_stream_config cfg;
+	unsigned read_size;
+	unsigned write_size;
+
+	int period_size;
+
+	unsigned state;
+
+	int idle_insize;
+	int idle_outsize;
+	int sync_packet;
+	unsigned insize_done;
+	unsigned periods_done;
+	unsigned periods_polled;
+
+	struct usb_stream_packet outpacket[2];
+	unsigned		 inpackets;
+	unsigned		 inpacket_head;
+	unsigned		 inpacket_split;
+	unsigned		 inpacket_split_at;
+	unsigned		 next_inpacket_split;
+	unsigned		 next_inpacket_split_at;
+	struct usb_stream_packet inpacket[0];
+};
+
+enum usb_stream_state {
+	usb_stream_invalid,
+	usb_stream_stopped,
+	usb_stream_sync0,
+	usb_stream_sync1,
+	usb_stream_ready,
+	usb_stream_running,
+	usb_stream_xrun,
+};
+
+#endif /* _UAPI__SOUND_USB_STREAM_H */
diff --git a/sound/usb/usx2y/usb_stream.h b/sound/usb/usx2y/usb_stream.h
index 4dd74ab1e9c..90369001eab 100644
--- a/sound/usb/usx2y/usb_stream.h
+++ b/sound/usb/usx2y/usb_stream.h
@@ -1,76 +1,7 @@
-/*
- * Copyright (C) 2007, 2008 Karsten Wiese <fzu@wemgehoertderstaat.de>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software Foundation,
- * Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
+#ifndef __USB_STREAM_H
+#define __USB_STREAM_H
 
-#define USB_STREAM_INTERFACE_VERSION 2
-
-#define SNDRV_USB_STREAM_IOCTL_SET_PARAMS \
-	_IOW('H', 0x90, struct usb_stream_config)
-
-struct usb_stream_packet {
-	unsigned offset;
-	unsigned length;
-};
-
-
-struct usb_stream_config {
-	unsigned version;
-	unsigned sample_rate;
-	unsigned period_frames;
-	unsigned frame_size;
-};
-
-struct usb_stream {
-	struct usb_stream_config cfg;
-	unsigned read_size;
-	unsigned write_size;
-
-	int period_size;
-
-	unsigned state;
-
-	int idle_insize;
-	int idle_outsize;
-	int sync_packet;
-	unsigned insize_done;
-	unsigned periods_done;
-	unsigned periods_polled;
-
-	struct usb_stream_packet outpacket[2];
-	unsigned		 inpackets;
-	unsigned		 inpacket_head;
-	unsigned		 inpacket_split;
-	unsigned		 inpacket_split_at;
-	unsigned		 next_inpacket_split;
-	unsigned		 next_inpacket_split_at;
-	struct usb_stream_packet inpacket[0];
-};
-
-enum usb_stream_state {
-	usb_stream_invalid,
-	usb_stream_stopped,
-	usb_stream_sync0,
-	usb_stream_sync1,
-	usb_stream_ready,
-	usb_stream_running,
-	usb_stream_xrun,
-};
-
-#if __KERNEL__
+#include <uapi/sound/usb_stream.h>
 
 #define USB_STREAM_NURBS 4
 #define USB_STREAM_URBDEPTH 4
@@ -108,5 +39,4 @@ void usb_stream_free(struct usb_stream_kernel *);
 int usb_stream_start(struct usb_stream_kernel *);
 void usb_stream_stop(struct usb_stream_kernel *);
 
-
-#endif
+#endif /* __USB_STREAM_H */
-- 
cgit v1.2.3-70-g09d2


From 8c7dd8bce05345ca5fe249b64782e8feeb3b9259 Mon Sep 17 00:00:00 2001
From: James Ban <james.ban.opensource@diasemi.com>
Date: Wed, 28 Jan 2015 09:28:08 +0900
Subject: regulator: da9211: Add gpio control for enable/disable of buck

This is a patch for adding gpio control about enable/disable of buck.

Signed-off-by: James Ban <james.ban.opensource@diasemi.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/regulator/da9211.txt |  7 ++++++-
 drivers/regulator/da9211-regulator.c                   | 12 ++++++++++++
 include/linux/regulator/da9211.h                       |  1 +
 3 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/regulator/da9211.txt b/Documentation/devicetree/bindings/regulator/da9211.txt
index 240019a82f9..eb618907c7d 100644
--- a/Documentation/devicetree/bindings/regulator/da9211.txt
+++ b/Documentation/devicetree/bindings/regulator/da9211.txt
@@ -11,6 +11,7 @@ Required properties:
   BUCKA and BUCKB.
 
 Optional properties:
+- enable-gpios: platform gpio for control of BUCKA/BUCKB.
 - Any optional property defined in regulator.txt
 
 Example 1) DA9211
@@ -27,6 +28,7 @@ Example 1) DA9211
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <2000000>;
 				regulator-max-microamp 	= <5000000>;
+				enable-gpios = <&gpio 27 0>;
 			};
 			BUCKB {
 				regulator-name = "VBUCKB";
@@ -34,11 +36,12 @@ Example 1) DA9211
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <2000000>;
 				regulator-max-microamp 	= <5000000>;
+				enable-gpios = <&gpio 17 0>;
 			};
 		};
 	};
 
-Example 2) DA92113
+Example 2) DA9213
 	pmic: da9213@68 {
 		compatible = "dlg,da9213";
 		reg = <0x68>;
@@ -51,6 +54,7 @@ Example 2) DA92113
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <3000000>;
 				regulator-max-microamp 	= <6000000>;
+				enable-gpios = <&gpio 27 0>;
 			};
 			BUCKB {
 				regulator-name = "VBUCKB";
@@ -58,6 +62,7 @@ Example 2) DA92113
 				regulator-max-microvolt = <1570000>;
 				regulator-min-microamp 	= <3000000>;
 				regulator-max-microamp 	= <6000000>;
+				enable-gpios = <&gpio 17 0>;
 			};
 		};
 	};
diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index 8e6957c63a6..01343419555 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -24,6 +24,7 @@
 #include <linux/regmap.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/of_gpio.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/da9211.h>
 #include "da9211-regulator.h"
@@ -277,6 +278,9 @@ static struct da9211_pdata *da9211_parse_regulators_dt(
 
 		pdata->init_data[n] = da9211_matches[i].init_data;
 		pdata->reg_node[n] = da9211_matches[i].of_node;
+		pdata->gpio_ren[n] =
+			of_get_named_gpio(da9211_matches[i].of_node,
+				"enable-gpios", 0);
 		n++;
 	}
 
@@ -366,6 +370,14 @@ static int da9211_regulator_init(struct da9211 *chip)
 		config.regmap = chip->regmap;
 		config.of_node = chip->pdata->reg_node[i];
 
+		if (gpio_is_valid(chip->pdata->gpio_ren[i])) {
+			config.ena_gpio = chip->pdata->gpio_ren[i];
+			config.ena_gpio_initialized = true;
+		} else {
+			config.ena_gpio = -EINVAL;
+			config.ena_gpio_initialized = false;
+		}
+
 		chip->rdev[i] = devm_regulator_register(chip->dev,
 			&da9211_regulators[i], &config);
 		if (IS_ERR(chip->rdev[i])) {
diff --git a/include/linux/regulator/da9211.h b/include/linux/regulator/da9211.h
index d1d9d3849bd..5dd65acc2a6 100644
--- a/include/linux/regulator/da9211.h
+++ b/include/linux/regulator/da9211.h
@@ -32,6 +32,7 @@ struct da9211_pdata {
 	 * 2 : 2 phase 2 buck
 	 */
 	int num_buck;
+	int gpio_ren[DA9211_MAX_REGULATORS];
 	struct device_node *reg_node[DA9211_MAX_REGULATORS];
 	struct regulator_init_data *init_data[DA9211_MAX_REGULATORS];
 };
-- 
cgit v1.2.3-70-g09d2


From f66f898e953d56779367a6cbc39cbb4808b208c0 Mon Sep 17 00:00:00 2001
From: Peter Rosin <peda@axentia.se>
Date: Wed, 28 Jan 2015 15:16:06 +0100
Subject: ALSA: pcm: Add snd_interval_ranges() and
 snd_pcm_hw_constraint_ranges()

Add helper functions to allow drivers to specify several disjoint
ranges for a variable. In particular, there is a codec (PCM512x) that
has a hole in its supported range of rates, due to PLL and divider
restrictions.

This is like snd_pcm_hw_constraint_list(), but for ranges instead of
points.

Signed-off-by: Peter Rosin <peda@axentia.se>
Reviewed-by: Lars-Peter Clausen <lars@metafoo.de>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/pcm.h  | 12 ++++++++
 sound/core/pcm_lib.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 1e7f74acc2e..04fc037e055 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -275,6 +275,12 @@ struct snd_pcm_hw_constraint_list {
 	unsigned int mask;
 };
 
+struct snd_pcm_hw_constraint_ranges {
+	unsigned int count;
+	const struct snd_interval *ranges;
+	unsigned int mask;
+};
+
 struct snd_pcm_hwptr_log;
 
 struct snd_pcm_runtime {
@@ -910,6 +916,8 @@ void snd_interval_mulkdiv(const struct snd_interval *a, unsigned int k,
 			  const struct snd_interval *b, struct snd_interval *c);
 int snd_interval_list(struct snd_interval *i, unsigned int count,
 		      const unsigned int *list, unsigned int mask);
+int snd_interval_ranges(struct snd_interval *i, unsigned int count,
+			const struct snd_interval *list, unsigned int mask);
 int snd_interval_ratnum(struct snd_interval *i,
 			unsigned int rats_count, struct snd_ratnum *rats,
 			unsigned int *nump, unsigned int *denp);
@@ -934,6 +942,10 @@ int snd_pcm_hw_constraint_list(struct snd_pcm_runtime *runtime,
 			       unsigned int cond,
 			       snd_pcm_hw_param_t var,
 			       const struct snd_pcm_hw_constraint_list *l);
+int snd_pcm_hw_constraint_ranges(struct snd_pcm_runtime *runtime,
+				 unsigned int cond,
+				 snd_pcm_hw_param_t var,
+				 const struct snd_pcm_hw_constraint_ranges *r);
 int snd_pcm_hw_constraint_ratnums(struct snd_pcm_runtime *runtime, 
 				  unsigned int cond,
 				  snd_pcm_hw_param_t var,
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index ec9e7866177..446c00bd908 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1015,6 +1015,60 @@ int snd_interval_list(struct snd_interval *i, unsigned int count,
 
 EXPORT_SYMBOL(snd_interval_list);
 
+/**
+ * snd_interval_ranges - refine the interval value from the list of ranges
+ * @i: the interval value to refine
+ * @count: the number of elements in the list of ranges
+ * @ranges: the ranges list
+ * @mask: the bit-mask to evaluate
+ *
+ * Refines the interval value from the list of ranges.
+ * When mask is non-zero, only the elements corresponding to bit 1 are
+ * evaluated.
+ *
+ * Return: Positive if the value is changed, zero if it's not changed, or a
+ * negative error code.
+ */
+int snd_interval_ranges(struct snd_interval *i, unsigned int count,
+			const struct snd_interval *ranges, unsigned int mask)
+{
+	unsigned int k;
+	struct snd_interval range_union;
+	struct snd_interval range;
+
+	if (!count) {
+		snd_interval_none(i);
+		return -EINVAL;
+	}
+	snd_interval_any(&range_union);
+	range_union.min = UINT_MAX;
+	range_union.max = 0;
+	for (k = 0; k < count; k++) {
+		if (mask && !(mask & (1 << k)))
+			continue;
+		snd_interval_copy(&range, &ranges[k]);
+		if (snd_interval_refine(&range, i) < 0)
+			continue;
+		if (snd_interval_empty(&range))
+			continue;
+
+		if (range.min < range_union.min) {
+			range_union.min = range.min;
+			range_union.openmin = 1;
+		}
+		if (range.min == range_union.min && !range.openmin)
+			range_union.openmin = 0;
+		if (range.max > range_union.max) {
+			range_union.max = range.max;
+			range_union.openmax = 1;
+		}
+		if (range.max == range_union.max && !range.openmax)
+			range_union.openmax = 0;
+	}
+	return snd_interval_refine(i, &range_union);
+}
+EXPORT_SYMBOL(snd_interval_ranges);
+
 static int snd_interval_step(struct snd_interval *i, unsigned int step)
 {
 	unsigned int n;
@@ -1221,6 +1275,37 @@ int snd_pcm_hw_constraint_list(struct snd_pcm_runtime *runtime,
 
 EXPORT_SYMBOL(snd_pcm_hw_constraint_list);
 
+static int snd_pcm_hw_rule_ranges(struct snd_pcm_hw_params *params,
+				  struct snd_pcm_hw_rule *rule)
+{
+	struct snd_pcm_hw_constraint_ranges *r = rule->private;
+	return snd_interval_ranges(hw_param_interval(params, rule->var),
+				   r->count, r->ranges, r->mask);
+}
+
+
+/**
+ * snd_pcm_hw_constraint_ranges - apply list of range constraints to a parameter
+ * @runtime: PCM runtime instance
+ * @cond: condition bits
+ * @var: hw_params variable to apply the list of range constraints
+ * @r: ranges
+ *
+ * Apply the list of range constraints to an interval parameter.
+ *
+ * Return: Zero if successful, or a negative error code on failure.
+ */
+int snd_pcm_hw_constraint_ranges(struct snd_pcm_runtime *runtime,
+				 unsigned int cond,
+				 snd_pcm_hw_param_t var,
+				 const struct snd_pcm_hw_constraint_ranges *r)
+{
+	return snd_pcm_hw_rule_add(runtime, cond, var,
+				   snd_pcm_hw_rule_ranges, (void *)r,
+				   var, -1);
+}
+EXPORT_SYMBOL(snd_pcm_hw_constraint_ranges);
+
 static int snd_pcm_hw_rule_ratnums(struct snd_pcm_hw_params *params,
 				   struct snd_pcm_hw_rule *rule)
 {
-- 
cgit v1.2.3-70-g09d2


From c7741d16a57cbf97eebe53f27e8216b1ff20e20c Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Wed, 28 Jan 2015 11:09:55 -0800
Subject: Bluetooth: Perform a power cycle when receiving hardware error event

When receiving a HCI Hardware Error event, the controller should be
assumed to be non-functional until issuing a HCI Reset command.

The Bluetooth hardware errors are vendor specific and so add a
new hdev->hw_error callback that drivers can provide to run extra
code to handle the hardware error.

After completing the vendor specific error handling perform a full
reset of the Bluetooth stack by closing and re-opening the transport.

Based-on-patch-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  3 +++
 net/bluetooth/hci_core.c         | 21 +++++++++++++++++++++
 net/bluetooth/hci_event.c        |  4 +++-
 3 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 0f5e59f1e3c..1780f1681ec 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -232,6 +232,7 @@ struct hci_dev {
 	__u16		conn_info_min_age;
 	__u16		conn_info_max_age;
 	__u8		ssp_debug_mode;
+	__u8		hw_error_code;
 	__u32		clock;
 
 	__u16		devid_source;
@@ -293,6 +294,7 @@ struct hci_dev {
 
 	struct work_struct	power_on;
 	struct delayed_work	power_off;
+	struct work_struct	error_reset;
 
 	__u16			discov_timeout;
 	struct delayed_work	discov_off;
@@ -369,6 +371,7 @@ struct hci_dev {
 	int (*setup)(struct hci_dev *hdev);
 	int (*send)(struct hci_dev *hdev, struct sk_buff *skb);
 	void (*notify)(struct hci_dev *hdev, unsigned int evt);
+	void (*hw_error)(struct hci_dev *hdev, u8 code);
 	int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr);
 };
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index d4c9152474a..79693a9ef4e 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2151,6 +2151,26 @@ static void hci_power_off(struct work_struct *work)
 	smp_unregister(hdev);
 }
 
+static void hci_error_reset(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset);
+
+	BT_DBG("%s", hdev->name);
+
+	if (hdev->hw_error)
+		hdev->hw_error(hdev, hdev->hw_error_code);
+	else
+		BT_ERR("%s hardware error 0x%2.2x", hdev->name,
+		       hdev->hw_error_code);
+
+	if (hci_dev_do_close(hdev))
+		return;
+
+	smp_unregister(hdev);
+
+	hci_dev_do_open(hdev);
+}
+
 static void hci_discov_off(struct work_struct *work)
 {
 	struct hci_dev *hdev;
@@ -2943,6 +2963,7 @@ struct hci_dev *hci_alloc_dev(void)
 	INIT_WORK(&hdev->cmd_work, hci_cmd_work);
 	INIT_WORK(&hdev->tx_work, hci_tx_work);
 	INIT_WORK(&hdev->power_on, hci_power_on);
+	INIT_WORK(&hdev->error_reset, hci_error_reset);
 
 	INIT_DELAYED_WORK(&hdev->power_off, hci_power_off);
 	INIT_DELAYED_WORK(&hdev->discov_off, hci_discov_off);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4175470ff48..a72a5f50728 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3100,7 +3100,9 @@ static void hci_hardware_error_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_hardware_error *ev = (void *) skb->data;
 
-	BT_ERR("%s hardware error 0x%2.2x", hdev->name, ev->code);
+	hdev->hw_error_code = ev->code;
+
+	queue_work(hdev->req_workqueue, &hdev->error_reset);
 }
 
 static void hci_role_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
-- 
cgit v1.2.3-70-g09d2


From 4161b4505f1690358ac0a9ee59845a7887336b21 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 13 Jan 2015 10:53:20 +0100
Subject: ALSA: ak411x: Fix stall in work callback

When ak4114 work calls its callback and the callback invokes
ak4114_reinit(), it stalls due to flush_delayed_work().  For avoiding
this, control the reentrance by introducing a refcount.  Also
flush_delayed_work() is replaced with cancel_delayed_work_sync().

The exactly same bug is present in ak4113.c and fixed as well.

Reported-by: Pavel Hofman <pavel.hofman@ivitera.com>
Acked-by: Jaroslav Kysela <perex@perex.cz>
Tested-by: Pavel Hofman <pavel.hofman@ivitera.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/ak4113.h   |  2 +-
 include/sound/ak4114.h   |  2 +-
 sound/i2c/other/ak4113.c | 17 ++++++++---------
 sound/i2c/other/ak4114.c | 18 ++++++++----------
 4 files changed, 18 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h
index 2609048c1d4..3a34f6edc2d 100644
--- a/include/sound/ak4113.h
+++ b/include/sound/ak4113.h
@@ -286,7 +286,7 @@ struct ak4113 {
 	ak4113_write_t *write;
 	ak4113_read_t *read;
 	void *private_data;
-	unsigned int init:1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[AK4113_WRITABLE_REGS];
 	struct snd_kcontrol *kctls[AK4113_CONTROLS];
diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index 52f02a60dba..069299a8891 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -168,7 +168,7 @@ struct ak4114 {
 	ak4114_write_t * write;
 	ak4114_read_t * read;
 	void * private_data;
-	unsigned int init: 1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[6];
 	unsigned char txcsb[5];
diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c
index 1a3a6fa2715..c6bba99a90b 100644
--- a/sound/i2c/other/ak4113.c
+++ b/sound/i2c/other/ak4113.c
@@ -56,8 +56,7 @@ static inline unsigned char reg_read(struct ak4113 *ak4113, unsigned char reg)
 
 static void snd_ak4113_free(struct ak4113 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -89,6 +88,7 @@ int snd_ak4113_create(struct snd_card *card, ak4113_read_t *read,
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4113_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -139,13 +139,11 @@ static void ak4113_init_regs(struct ak4113 *chip)
 
 void snd_ak4113_reinit(struct ak4113 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4113_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 EXPORT_SYMBOL_GPL(snd_ak4113_reinit);
@@ -632,8 +630,9 @@ static void ak4113_stats(struct work_struct *work)
 {
 	struct ak4113 *chip = container_of(work, struct ak4113, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4113_check_rate_and_errors(chip, chip->check_flags);
 
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index c7f56339415..b70e6eccbd0 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -66,8 +66,7 @@ static void reg_dump(struct ak4114 *ak4114)
 
 static void snd_ak4114_free(struct ak4114 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -100,6 +99,7 @@ int snd_ak4114_create(struct snd_card *card,
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4114_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < 6; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -152,13 +152,11 @@ static void ak4114_init_regs(struct ak4114 *chip)
 
 void snd_ak4114_reinit(struct ak4114 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4114_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
@@ -612,10 +610,10 @@ static void ak4114_stats(struct work_struct *work)
 {
 	struct ak4114 *chip = container_of(work, struct ak4114, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4114_check_rate_and_errors(chip, chip->check_flags);
-
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
 EXPORT_SYMBOL(snd_ak4114_create);
-- 
cgit v1.2.3-70-g09d2


From 1293617cddc40971917150e3f5bf66b7306e2e7e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 13 Jan 2015 11:24:08 +0100
Subject: ALSA: ak411x: Add PM helper functions

Define snd_ak4114_suspend() and snd_ak4114_resume() functions to
handle PM properly, stopping and restarting the work at PM.
Currently only ice1712/juli.c deals with the PM and ak4114, so fix the
calls there appropriately.

The same PM functions are defined in ak4113.c, too, although they
aren't currently called yet (ice1712/quartet.c may be enhanced to
support PM later).

Acked-by: Jaroslav Kysela <perex@perex.cz>
Tested-by: Pavel Hofman <pavel.hofman@ivitera.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/ak4113.h   |  8 ++++++++
 include/sound/ak4114.h   |  8 ++++++++
 sound/i2c/other/ak4113.c | 16 ++++++++++++++++
 sound/i2c/other/ak4114.c | 16 ++++++++++++++++
 sound/pci/ice1712/juli.c |  4 +++-
 5 files changed, 51 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h
index 3a34f6edc2d..f4fbf6888e7 100644
--- a/include/sound/ak4113.h
+++ b/include/sound/ak4113.h
@@ -317,5 +317,13 @@ int snd_ak4113_build(struct ak4113 *ak4113,
 int snd_ak4113_external_rate(struct ak4113 *ak4113);
 int snd_ak4113_check_rate_and_errors(struct ak4113 *ak4113, unsigned int flags);
 
+#ifdef CONFIG_PM
+void snd_ak4113_suspend(struct ak4113 *chip);
+void snd_ak4113_resume(struct ak4113 *chip);
+#else
+static inline void snd_ak4113_suspend(struct ak4113 *chip) {}
+static inline void snd_ak4113_resume(struct ak4113 *chip) {}
+#endif
+
 #endif /* __SOUND_AK4113_H */
 
diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index 069299a8891..e681df2c95e 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -199,5 +199,13 @@ int snd_ak4114_build(struct ak4114 *ak4114,
 int snd_ak4114_external_rate(struct ak4114 *ak4114);
 int snd_ak4114_check_rate_and_errors(struct ak4114 *ak4114, unsigned int flags);
 
+#ifdef CONFIG_PM
+void snd_ak4114_suspend(struct ak4114 *chip);
+void snd_ak4114_resume(struct ak4114 *chip);
+#else
+static inline void snd_ak4114_suspend(struct ak4114 *chip) {}
+static inline void snd_ak4114_resume(struct ak4114 *chip) {}
+#endif
+
 #endif /* __SOUND_AK4114_H */
 
diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c
index c6bba99a90b..c2b14d981fa 100644
--- a/sound/i2c/other/ak4113.c
+++ b/sound/i2c/other/ak4113.c
@@ -636,3 +636,19 @@ static void ak4113_stats(struct work_struct *work)
 	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
+
+#ifdef CONFIG_PM
+void snd_ak4113_suspend(struct ak4113 *chip)
+{
+	atomic_inc(&chip->wq_processing); /* don't schedule new work */
+	cancel_delayed_work_sync(&chip->work);
+}
+EXPORT_SYMBOL(snd_ak4113_suspend);
+
+void snd_ak4113_resume(struct ak4113 *chip)
+{
+	atomic_dec(&chip->wq_processing);
+	snd_ak4113_reinit(chip);
+}
+EXPORT_SYMBOL(snd_ak4113_resume);
+#endif
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index f6ee1e7a9bb..ee639f57b66 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -621,3 +621,19 @@ static void ak4114_stats(struct work_struct *work)
 	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
+
+#ifdef CONFIG_PM
+void snd_ak4114_suspend(struct ak4114 *chip)
+{
+	atomic_inc(&chip->wq_processing); /* don't schedule new work */
+	cancel_delayed_work_sync(&chip->work);
+}
+EXPORT_SYMBOL(snd_ak4114_suspend);
+
+void snd_ak4114_resume(struct ak4114 *chip)
+{
+	atomic_dec(&chip->wq_processing);
+	snd_ak4114_reinit(chip);
+}
+EXPORT_SYMBOL(snd_ak4114_resume);
+#endif
diff --git a/sound/pci/ice1712/juli.c b/sound/pci/ice1712/juli.c
index a1536c1a7ed..4f021342715 100644
--- a/sound/pci/ice1712/juli.c
+++ b/sound/pci/ice1712/juli.c
@@ -491,15 +491,17 @@ static int juli_resume(struct snd_ice1712 *ice)
 	/* akm4358 un-reset, un-mute */
 	snd_akm4xxx_reset(ak, 0);
 	/* reinit ak4114 */
-	snd_ak4114_reinit(spec->ak4114);
+	snd_ak4114_resume(spec->ak4114);
 	return 0;
 }
 
 static int juli_suspend(struct snd_ice1712 *ice)
 {
 	struct snd_akm4xxx *ak = ice->akm;
+	struct juli_spec *spec = ice->spec;
 	/* akm4358 reset and soft-mute */
 	snd_akm4xxx_reset(ak, 1);
+	snd_ak4114_suspend(spec->ak4114);
 	return 0;
 }
 #endif
-- 
cgit v1.2.3-70-g09d2


From 1781e78c63317c04e6ae6a076acfd53236f420bc Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 16 Jan 2015 13:03:28 +0100
Subject: ALSA: ak411x: Fix race of reinit() calls

Protect the call with a mutex, as this may be called in parallel
(either from the PCM rate change and the clock change).

Acked-by: Jaroslav Kysela <perex@perex.cz>
Tested-by: Pavel Hofman <pavel.hofman@ivitera.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/ak4113.h   | 1 +
 include/sound/ak4114.h   | 1 +
 sound/i2c/other/ak4113.c | 3 +++
 sound/i2c/other/ak4114.c | 3 +++
 4 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h
index f4fbf6888e7..58c145620c3 100644
--- a/include/sound/ak4113.h
+++ b/include/sound/ak4113.h
@@ -287,6 +287,7 @@ struct ak4113 {
 	ak4113_read_t *read;
 	void *private_data;
 	atomic_t wq_processing;
+	struct mutex reinit_mutex;
 	spinlock_t lock;
 	unsigned char regmap[AK4113_WRITABLE_REGS];
 	struct snd_kcontrol *kctls[AK4113_CONTROLS];
diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index e681df2c95e..b6feb7e225f 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -169,6 +169,7 @@ struct ak4114 {
 	ak4114_read_t * read;
 	void * private_data;
 	atomic_t wq_processing;
+	struct mutex reinit_mutex;
 	spinlock_t lock;
 	unsigned char regmap[6];
 	unsigned char txcsb[5];
diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c
index c2b14d981fa..88844881cbf 100644
--- a/sound/i2c/other/ak4113.c
+++ b/sound/i2c/other/ak4113.c
@@ -89,6 +89,7 @@ int snd_ak4113_create(struct snd_card *card, ak4113_read_t *read,
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4113_stats);
 	atomic_set(&chip->wq_processing, 0);
+	mutex_init(&chip->reinit_mutex);
 
 	for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -141,7 +142,9 @@ void snd_ak4113_reinit(struct ak4113 *chip)
 {
 	if (atomic_inc_return(&chip->wq_processing) == 1)
 		cancel_delayed_work_sync(&chip->work);
+	mutex_lock(&chip->reinit_mutex);
 	ak4113_init_regs(chip);
+	mutex_unlock(&chip->reinit_mutex);
 	/* bring up statistics / event queing */
 	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index ee639f57b66..5a4cf3fab4a 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -100,6 +100,7 @@ int snd_ak4114_create(struct snd_card *card,
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4114_stats);
 	atomic_set(&chip->wq_processing, 0);
+	mutex_init(&chip->reinit_mutex);
 
 	for (reg = 0; reg < 6; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -156,7 +157,9 @@ void snd_ak4114_reinit(struct ak4114 *chip)
 {
 	if (atomic_inc_return(&chip->wq_processing) == 1)
 		cancel_delayed_work_sync(&chip->work);
+	mutex_lock(&chip->reinit_mutex);
 	ak4114_init_regs(chip);
+	mutex_unlock(&chip->reinit_mutex);
 	/* bring up statistics / event queing */
 	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
-- 
cgit v1.2.3-70-g09d2


From 018d5ef2048fcab339467bcbebccf588c9bd2531 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Thu, 29 Jan 2015 08:30:29 +0900
Subject: ata: ahci_platform: fix owner module reference mismatch for scsi host

The owner module reference of the ahci platform's scsi_host is
initialized to libahci_platform's one, because these drivers use a
scsi_host_template defined in libahci_platform.  So these drivers can
be unloaded even if the scsi device is being accessed.

This fixes it by pushing the scsi_host_template from libahci_platform
to all leaf drivers.  The scsi_host_template is passed through a new
argument of ahci_platform_init_host().

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: linux-ide@vger.kernel.org
Cc: linux-scsi@vger.kernel.org
---
 drivers/ata/ahci.h             |  4 ++++
 drivers/ata/ahci_da850.c       | 11 +++++++++--
 drivers/ata/ahci_imx.c         | 11 +++++++++--
 drivers/ata/ahci_mvebu.c       | 11 +++++++++--
 drivers/ata/ahci_platform.c    | 11 +++++++++--
 drivers/ata/ahci_st.c          | 11 +++++++++--
 drivers/ata/ahci_sunxi.c       | 11 +++++++++--
 drivers/ata/ahci_tegra.c       | 11 +++++++++--
 drivers/ata/ahci_xgene.c       | 11 +++++++++--
 drivers/ata/libahci_platform.c | 10 ++++------
 include/linux/ahci_platform.h  |  4 +++-
 include/linux/libata.h         |  6 ++++++
 12 files changed, 89 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 275358ae0b3..71262e08648 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -354,6 +354,10 @@ extern int ahci_ignore_sss;
 extern struct device_attribute *ahci_shost_attrs[];
 extern struct device_attribute *ahci_sdev_attrs[];
 
+/*
+ * This must be instantiated by the edge drivers.  Read the comments
+ * for ATA_BASE_SHT
+ */
 #define AHCI_SHT(drv_name)						\
 	ATA_NCQ_SHT(drv_name),						\
 	.can_queue		= AHCI_MAX_CMDS - 1,			\
diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c
index ce8a7a6d6c7..267a3d3e79f 100644
--- a/drivers/ata/ahci_da850.c
+++ b/drivers/ata/ahci_da850.c
@@ -16,6 +16,8 @@
 #include <linux/ahci_platform.h>
 #include "ahci.h"
 
+#define DRV_NAME "ahci_da850"
+
 /* SATA PHY Control Register offset from AHCI base */
 #define SATA_P0PHYCR_REG	0x178
 
@@ -59,6 +61,10 @@ static const struct ata_port_info ahci_da850_port_info = {
 	.port_ops	= &ahci_platform_ops,
 };
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int ahci_da850_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -85,7 +91,8 @@ static int ahci_da850_probe(struct platform_device *pdev)
 
 	da850_sata_init(dev, pwrdn_reg, hpriv->mmio);
 
-	rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info);
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info,
+				     &ahci_platform_sht);
 	if (rc)
 		goto disable_resources;
 
@@ -102,7 +109,7 @@ static struct platform_driver ahci_da850_driver = {
 	.probe = ahci_da850_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
-		.name = "ahci_da850",
+		.name = DRV_NAME,
 		.pm = &ahci_da850_pm_ops,
 	},
 };
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index 41632e57d46..3f3a7db208a 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -28,6 +28,8 @@
 #include <linux/libata.h>
 #include "ahci.h"
 
+#define DRV_NAME "ahci-imx"
+
 enum {
 	/* Timer 1-ms Register */
 	IMX_TIMER1MS				= 0x00e0,
@@ -520,6 +522,10 @@ static u32 imx_ahci_parse_props(struct device *dev,
 	return reg_value;
 }
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int imx_ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -616,7 +622,8 @@ static int imx_ahci_probe(struct platform_device *pdev)
 	reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000;
 	writel(reg_val, hpriv->mmio + IMX_TIMER1MS);
 
-	ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info);
+	ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info,
+				      &ahci_platform_sht);
 	if (ret)
 		goto disable_sata;
 
@@ -674,7 +681,7 @@ static struct platform_driver imx_ahci_driver = {
 	.probe = imx_ahci_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
-		.name = "ahci-imx",
+		.name = DRV_NAME,
 		.of_match_table = imx_ahci_of_match,
 		.pm = &ahci_imx_pm_ops,
 	},
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index 64bb08432b6..23716dd8a7e 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -19,6 +19,8 @@
 #include <linux/platform_device.h>
 #include "ahci.h"
 
+#define DRV_NAME "ahci-mvebu"
+
 #define AHCI_VENDOR_SPECIFIC_0_ADDR  0xa0
 #define AHCI_VENDOR_SPECIFIC_0_DATA  0xa4
 
@@ -67,6 +69,10 @@ static const struct ata_port_info ahci_mvebu_port_info = {
 	.port_ops  = &ahci_platform_ops,
 };
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int ahci_mvebu_probe(struct platform_device *pdev)
 {
 	struct ahci_host_priv *hpriv;
@@ -88,7 +94,8 @@ static int ahci_mvebu_probe(struct platform_device *pdev)
 	ahci_mvebu_mbus_config(hpriv, dram);
 	ahci_mvebu_regret_option(hpriv);
 
-	rc = ahci_platform_init_host(pdev, hpriv, &ahci_mvebu_port_info);
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_mvebu_port_info,
+				     &ahci_platform_sht);
 	if (rc)
 		goto disable_resources;
 
@@ -114,7 +121,7 @@ static struct platform_driver ahci_mvebu_driver = {
 	.probe = ahci_mvebu_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
-		.name = "ahci-mvebu",
+		.name = DRV_NAME,
 		.of_match_table = ahci_mvebu_of_match,
 	},
 };
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 18d53983704..78d6ae0b90c 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -22,6 +22,8 @@
 #include <linux/ahci_platform.h>
 #include "ahci.h"
 
+#define DRV_NAME "ahci"
+
 static const struct ata_port_info ahci_port_info = {
 	.flags		= AHCI_FLAG_COMMON,
 	.pio_mask	= ATA_PIO4,
@@ -29,6 +31,10 @@ static const struct ata_port_info ahci_port_info = {
 	.port_ops	= &ahci_platform_ops,
 };
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -46,7 +52,8 @@ static int ahci_probe(struct platform_device *pdev)
 	if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci"))
 		hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ;
 
-	rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info);
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info,
+				     &ahci_platform_sht);
 	if (rc)
 		goto disable_resources;
 
@@ -75,7 +82,7 @@ static struct platform_driver ahci_driver = {
 	.probe = ahci_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
-		.name = "ahci",
+		.name = DRV_NAME,
 		.of_match_table = ahci_of_match,
 		.pm = &ahci_pm_ops,
 	},
diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c
index 2f9e8317cc1..bc971af262e 100644
--- a/drivers/ata/ahci_st.c
+++ b/drivers/ata/ahci_st.c
@@ -23,6 +23,8 @@
 
 #include "ahci.h"
 
+#define DRV_NAME  "st_ahci"
+
 #define ST_AHCI_OOBR			0xbc
 #define ST_AHCI_OOBR_WE			BIT(31)
 #define ST_AHCI_OOBR_CWMIN_SHIFT	24
@@ -140,6 +142,10 @@ static const struct ata_port_info st_ahci_port_info = {
 	.port_ops       = &st_ahci_port_ops,
 };
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int st_ahci_probe(struct platform_device *pdev)
 {
 	struct st_ahci_drv_data *drv_data;
@@ -166,7 +172,8 @@ static int st_ahci_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info);
+	err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info,
+				      &ahci_platform_sht);
 	if (err) {
 		ahci_platform_disable_resources(hpriv);
 		return err;
@@ -229,7 +236,7 @@ MODULE_DEVICE_TABLE(of, st_ahci_match);
 
 static struct platform_driver st_ahci_driver = {
 	.driver = {
-		.name = "st_ahci",
+		.name = DRV_NAME,
 		.pm = &st_ahci_pm_ops,
 		.of_match_table = of_match_ptr(st_ahci_match),
 	},
diff --git a/drivers/ata/ahci_sunxi.c b/drivers/ata/ahci_sunxi.c
index e2e0da539a2..b2643743016 100644
--- a/drivers/ata/ahci_sunxi.c
+++ b/drivers/ata/ahci_sunxi.c
@@ -27,6 +27,8 @@
 #include <linux/regulator/consumer.h>
 #include "ahci.h"
 
+#define DRV_NAME "ahci-sunxi"
+
 /* Insmod parameters */
 static bool enable_pmp;
 module_param(enable_pmp, bool, 0);
@@ -169,6 +171,10 @@ static const struct ata_port_info ahci_sunxi_port_info = {
 	.port_ops	= &ahci_platform_ops,
 };
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int ahci_sunxi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -200,7 +206,8 @@ static int ahci_sunxi_probe(struct platform_device *pdev)
 	if (!enable_pmp)
 		hpriv->flags |= AHCI_HFLAG_NO_PMP;
 
-	rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info);
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info,
+				     &ahci_platform_sht);
 	if (rc)
 		goto disable_resources;
 
@@ -251,7 +258,7 @@ static struct platform_driver ahci_sunxi_driver = {
 	.probe = ahci_sunxi_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
-		.name = "ahci-sunxi",
+		.name = DRV_NAME,
 		.of_match_table = ahci_sunxi_of_match,
 		.pm = &ahci_sunxi_pm_ops,
 	},
diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c
index 032904402c9..3a62eb246d8 100644
--- a/drivers/ata/ahci_tegra.c
+++ b/drivers/ata/ahci_tegra.c
@@ -31,6 +31,8 @@
 
 #include "ahci.h"
 
+#define DRV_NAME "tegra-ahci"
+
 #define SATA_CONFIGURATION_0				0x180
 #define SATA_CONFIGURATION_EN_FPCI			BIT(0)
 
@@ -289,6 +291,10 @@ static const struct of_device_id tegra_ahci_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, tegra_ahci_of_match);
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int tegra_ahci_probe(struct platform_device *pdev)
 {
 	struct ahci_host_priv *hpriv;
@@ -354,7 +360,8 @@ static int tegra_ahci_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = ahci_platform_init_host(pdev, hpriv, &ahci_tegra_port_info);
+	ret = ahci_platform_init_host(pdev, hpriv, &ahci_tegra_port_info,
+				      &ahci_platform_sht);
 	if (ret)
 		goto deinit_controller;
 
@@ -370,7 +377,7 @@ static struct platform_driver tegra_ahci_driver = {
 	.probe = tegra_ahci_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
-		.name = "tegra-ahci",
+		.name = DRV_NAME,
 		.of_match_table = tegra_ahci_of_match,
 	},
 	/* LP0 suspend support not implemented */
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index 7f6887535c1..e3b8750e8e9 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -30,6 +30,8 @@
 #include <linux/phy/phy.h>
 #include "ahci.h"
 
+#define DRV_NAME "xgene-ahci"
+
 /* Max # of disk per a controller */
 #define MAX_AHCI_CHN_PERCTR		2
 
@@ -621,6 +623,10 @@ static int xgene_ahci_mux_select(struct xgene_ahci_context *ctx)
 	return val & CFG_SATA_ENET_SELECT_MASK ? -1 : 0;
 }
 
+static struct scsi_host_template ahci_platform_sht = {
+	AHCI_SHT(DRV_NAME),
+};
+
 static int xgene_ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -698,7 +704,8 @@ static int xgene_ahci_probe(struct platform_device *pdev)
 skip_clk_phy:
 	hpriv->flags = AHCI_HFLAG_NO_PMP | AHCI_HFLAG_NO_NCQ;
 
-	rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info);
+	rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info,
+				     &ahci_platform_sht);
 	if (rc)
 		goto disable_resources;
 
@@ -720,7 +727,7 @@ static struct platform_driver xgene_ahci_driver = {
 	.probe = xgene_ahci_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
-		.name = "xgene-ahci",
+		.name = DRV_NAME,
 		.of_match_table = xgene_ahci_of_match,
 	},
 };
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 504d534ccbf..077c7a26135 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -35,10 +35,6 @@ struct ata_port_operations ahci_platform_ops = {
 };
 EXPORT_SYMBOL_GPL(ahci_platform_ops);
 
-static struct scsi_host_template ahci_platform_sht = {
-	AHCI_SHT("ahci_platform"),
-};
-
 /**
  * ahci_platform_enable_phys - Enable PHYs
  * @hpriv: host private area to store config values
@@ -494,6 +490,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources);
  * @pdev: platform device pointer for the host
  * @hpriv: ahci-host private data for the host
  * @pi_template: template for the ata_port_info to use
+ * @sht: scsi_host_template to use when registering
  *
  * This function does all the usual steps needed to bring up an
  * ahci-platform host, note any necessary resources (ie clks, phys, etc.)
@@ -504,7 +501,8 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources);
  */
 int ahci_platform_init_host(struct platform_device *pdev,
 			    struct ahci_host_priv *hpriv,
-			    const struct ata_port_info *pi_template)
+			    const struct ata_port_info *pi_template,
+			    struct scsi_host_template *sht)
 {
 	struct device *dev = &pdev->dev;
 	struct ata_port_info pi = *pi_template;
@@ -588,7 +586,7 @@ int ahci_platform_init_host(struct platform_device *pdev,
 	ahci_init_controller(host);
 	ahci_print_info(host, "platform");
 
-	return ahci_host_activate(host, irq, &ahci_platform_sht);
+	return ahci_host_activate(host, irq, sht);
 }
 EXPORT_SYMBOL_GPL(ahci_platform_init_host);
 
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index f65b3380917..a270f25ee7c 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -21,6 +21,7 @@ struct device;
 struct ata_port_info;
 struct ahci_host_priv;
 struct platform_device;
+struct scsi_host_template;
 
 int ahci_platform_enable_clks(struct ahci_host_priv *hpriv);
 void ahci_platform_disable_clks(struct ahci_host_priv *hpriv);
@@ -32,7 +33,8 @@ struct ahci_host_priv *ahci_platform_get_resources(
 	struct platform_device *pdev);
 int ahci_platform_init_host(struct platform_device *pdev,
 			    struct ahci_host_priv *hpriv,
-			    const struct ata_port_info *pi_template);
+			    const struct ata_port_info *pi_template,
+			    struct scsi_host_template *sht);
 
 int ahci_platform_suspend_host(struct device *dev);
 int ahci_platform_resume_host(struct device *dev);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 2d182413b1d..11beb4196c3 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1338,6 +1338,12 @@ extern const struct ata_port_operations ata_base_port_ops;
 extern const struct ata_port_operations sata_port_ops;
 extern struct device_attribute *ata_common_sdev_attrs[];
 
+/*
+ * All sht initializers (BASE, PIO, BMDMA, NCQ) must be instantiated
+ * by the edge drivers.  Because the 'module' field of sht must be the
+ * edge driver's module reference, otherwise the driver can be unloaded
+ * even if the scsi_device is being accessed.
+ */
 #define ATA_BASE_SHT(drv_name)					\
 	.module			= THIS_MODULE,			\
 	.name			= drv_name,			\
-- 
cgit v1.2.3-70-g09d2


From 17263905399471016cda6c1975044d14291c5ba5 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Thu, 29 Jan 2015 08:30:30 +0900
Subject: ata: pata_platform: fix owner module reference mismatch for scsi host

The owner module reference of the pata_of_platform's scsi_host is
initialized to pata_platform's one, because pata_of_platform driver
use a scsi_host_template defined in pata_platform.  So this drivers
can be unloaded even if the scsi device is being accessed.

This fixes it by propagating the scsi_host_template to pata_of_platform
driver.  The scsi_host_template is passed through a new
argument of __pata_platform_probe().

Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: linux-ide@vger.kernel.org
Cc: linux-scsi@vger.kernel.org
---
 drivers/ata/pata_of_platform.c | 10 ++++++++--
 drivers/ata/pata_platform.c    |  8 +++++---
 include/linux/ata_platform.h   |  5 ++++-
 3 files changed, 17 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/pata_of_platform.c b/drivers/ata/pata_of_platform.c
index dcc408abe17..b6b7af894d9 100644
--- a/drivers/ata/pata_of_platform.c
+++ b/drivers/ata/pata_of_platform.c
@@ -16,6 +16,12 @@
 #include <linux/ata_platform.h>
 #include <linux/libata.h>
 
+#define DRV_NAME "pata_of_platform"
+
+static struct scsi_host_template pata_platform_sht = {
+	ATA_PIO_SHT(DRV_NAME),
+};
+
 static int pata_of_platform_probe(struct platform_device *ofdev)
 {
 	int ret;
@@ -63,7 +69,7 @@ static int pata_of_platform_probe(struct platform_device *ofdev)
 	pio_mask |= (1 << pio_mode) - 1;
 
 	return __pata_platform_probe(&ofdev->dev, &io_res, &ctl_res, irq_res,
-				     reg_shift, pio_mask);
+				     reg_shift, pio_mask, &pata_platform_sht);
 }
 
 static struct of_device_id pata_of_platform_match[] = {
@@ -74,7 +80,7 @@ MODULE_DEVICE_TABLE(of, pata_of_platform_match);
 
 static struct platform_driver pata_of_platform_driver = {
 	.driver = {
-		.name = "pata_of_platform",
+		.name = DRV_NAME,
 		.of_match_table = pata_of_platform_match,
 	},
 	.probe		= pata_of_platform_probe,
diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
index 1eedfe46d7c..c503ded87bb 100644
--- a/drivers/ata/pata_platform.c
+++ b/drivers/ata/pata_platform.c
@@ -78,6 +78,7 @@ static void pata_platform_setup_port(struct ata_ioports *ioaddr,
  *	@irq_res: Resource representing IRQ and its flags
  *	@ioport_shift: I/O port shift
  *	@__pio_mask: PIO mask
+ *	@sht: scsi_host_template to use when registering
  *
  *	Register a platform bus IDE interface. Such interfaces are PIO and we
  *	assume do not support IRQ sharing.
@@ -99,7 +100,8 @@ static void pata_platform_setup_port(struct ata_ioports *ioaddr,
  */
 int __pata_platform_probe(struct device *dev, struct resource *io_res,
 			  struct resource *ctl_res, struct resource *irq_res,
-			  unsigned int ioport_shift, int __pio_mask)
+			  unsigned int ioport_shift, int __pio_mask,
+			  struct scsi_host_template *sht)
 {
 	struct ata_host *host;
 	struct ata_port *ap;
@@ -170,7 +172,7 @@ int __pata_platform_probe(struct device *dev, struct resource *io_res,
 
 	/* activate */
 	return ata_host_activate(host, irq, irq ? ata_sff_interrupt : NULL,
-				 irq_flags, &pata_platform_sht);
+				 irq_flags, sht);
 }
 EXPORT_SYMBOL_GPL(__pata_platform_probe);
 
@@ -216,7 +218,7 @@ static int pata_platform_probe(struct platform_device *pdev)
 
 	return __pata_platform_probe(&pdev->dev, io_res, ctl_res, irq_res,
 				     pp_info ? pp_info->ioport_shift : 0,
-				     pio_mask);
+				     pio_mask, &pata_platform_sht);
 }
 
 static struct platform_driver pata_platform_driver = {
diff --git a/include/linux/ata_platform.h b/include/linux/ata_platform.h
index 5c618a08422..619d9e78e64 100644
--- a/include/linux/ata_platform.h
+++ b/include/linux/ata_platform.h
@@ -10,12 +10,15 @@ struct pata_platform_info {
 	unsigned int ioport_shift;
 };
 
+struct scsi_host_template;
+
 extern int __pata_platform_probe(struct device *dev,
 				 struct resource *io_res,
 				 struct resource *ctl_res,
 				 struct resource *irq_res,
 				 unsigned int ioport_shift,
-				 int __pio_mask);
+				 int __pio_mask,
+				 struct scsi_host_template *sht);
 
 /*
  * Marvell SATA private data
-- 
cgit v1.2.3-70-g09d2


From e73ebb0881ea5534ce606c1d71b4ac44db5c6930 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Wed, 28 Jan 2015 20:01:35 -0500
Subject: tcp: stretch ACK fixes prep

LRO, GRO, delayed ACKs, and middleboxes can cause "stretch ACKs" that
cover more than the RFC-specified maximum of 2 packets. These stretch
ACKs can cause serious performance shortfalls in common congestion
control algorithms that were designed and tuned years ago with
receiver hosts that were not using LRO or GRO, and were instead
politely ACKing every other packet.

This patch series fixes Reno and CUBIC to handle stretch ACKs.

This patch prepares for the upcoming stretch ACK bug fix patches. It
adds an "acked" parameter to tcp_cong_avoid_ai() to allow for future
fixes to tcp_cong_avoid_ai() to correctly handle stretch ACKs, and
changes all congestion control algorithms to pass in 1 for the ACKed
count. It also changes tcp_slow_start() to return the number of packet
ACK "credits" that were not processed in slow start mode, and can be
processed by the congestion control module in additive increase mode.

In future patches we will fix tcp_cong_avoid_ai() to handle stretch
ACKs, and fix Reno and CUBIC handling of stretch ACKs in slow start
and additive increase mode.

Reported-by: Eyal Perry <eyalpe@mellanox.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h       |  4 ++--
 net/ipv4/tcp_bic.c      |  2 +-
 net/ipv4/tcp_cong.c     | 11 +++++++----
 net/ipv4/tcp_cubic.c    |  2 +-
 net/ipv4/tcp_scalable.c |  3 ++-
 net/ipv4/tcp_veno.c     |  2 +-
 net/ipv4/tcp_yeah.c     |  2 +-
 7 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f50f29faf76..9d9111ef43a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -834,8 +834,8 @@ void tcp_get_available_congestion_control(char *buf, size_t len);
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name);
-void tcp_slow_start(struct tcp_sock *tp, u32 acked);
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
 u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index bb395d46a38..c037644eafb 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -150,7 +150,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		tcp_slow_start(tp, acked);
 	else {
 		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		tcp_cong_avoid_ai(tp, ca->cnt, 1);
 	}
 }
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 27ead0dd16b..6826017c12d 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -291,25 +291,28 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
  * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
  * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-void tcp_slow_start(struct tcp_sock *tp, u32 acked)
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
 	u32 cwnd = tp->snd_cwnd + acked;
 
 	if (cwnd > tp->snd_ssthresh)
 		cwnd = tp->snd_ssthresh + 1;
+	acked -= cwnd - tp->snd_cwnd;
 	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+	return acked;
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
 /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
 	if (tp->snd_cwnd_cnt >= w) {
 		if (tp->snd_cwnd < tp->snd_cwnd_clamp)
 			tp->snd_cwnd++;
 		tp->snd_cwnd_cnt = 0;
 	} else {
-		tp->snd_cwnd_cnt++;
+		tp->snd_cwnd_cnt += acked;
 	}
 }
 EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
@@ -333,7 +336,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		tcp_slow_start(tp, acked);
 	/* In dangerous area, increase slowly. */
 	else
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+		tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 6b6002416a7..df4bc4d87e5 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -320,7 +320,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 		tcp_slow_start(tp, acked);
 	} else {
 		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		tcp_cong_avoid_ai(tp, ca->cnt, 1);
 	}
 }
 
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 6824afb65d9..333bcb2415f 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -25,7 +25,8 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
 		tcp_slow_start(tp, acked);
 	else
-		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT));
+		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
+				  1);
 }
 
 static u32 tcp_scalable_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index a4d2d2d88dc..112151eeee4 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -159,7 +159,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 				/* In the "non-congestive state", increase cwnd
 				 *  every rtt.
 				 */
-				tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+				tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 			} else {
 				/* In the "congestive state", increase cwnd
 				 * every other rtt.
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index cd727321859..17d35662930 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -92,7 +92,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 
 	} else {
 		/* Reno */
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+		tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 	}
 
 	/* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt.
-- 
cgit v1.2.3-70-g09d2


From b8693877ae016ac525d674d5d7a84ea0ea68ba60 Mon Sep 17 00:00:00 2001
From: Jesse Gross <jesse@nicira.com>
Date: Wed, 28 Jan 2015 16:32:46 -0800
Subject: openvswitch: Add support for checksums on UDP tunnels.

Currently, it isn't possible to request checksums on the outer UDP
header of tunnels - the TUNNEL_CSUM flag is ignored. This adds
support for requesting that UDP checksums be computed on transmit
and properly reported if they are present on receive.

Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/geneve.h           | 2 +-
 net/ipv4/geneve.c              | 6 +++---
 net/openvswitch/vport-geneve.c | 2 +-
 net/openvswitch/vport-vxlan.c  | 7 +++++--
 4 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/geneve.h b/include/net/geneve.h
index 03aa2adb5ba..14fb8d3390b 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -90,7 +90,7 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
 		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
 		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
-		    bool xnet);
+		    bool csum, bool xnet);
 #endif /*ifdef CONFIG_INET */
 
 #endif /*ifdef__NET_GENEVE_H */
diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
index 93e51199e44..5a4828ba05a 100644
--- a/net/ipv4/geneve.c
+++ b/net/ipv4/geneve.c
@@ -107,13 +107,13 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 		    struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos,
 		    __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port,
 		    __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt,
-		    bool xnet)
+		    bool csum, bool xnet)
 {
 	struct genevehdr *gnvh;
 	int min_headroom;
 	int err;
 
-	skb = udp_tunnel_handle_offloads(skb, !gs->sock->sk->sk_no_check_tx);
+	skb = udp_tunnel_handle_offloads(skb, csum);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
@@ -138,7 +138,7 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
 
 	return udp_tunnel_xmit_skb(rt, skb, src, dst,
 				   tos, ttl, df, src_port, dst_port, xnet,
-				   gs->sock->sk->sk_no_check_tx);
+				   !csum);
 }
 EXPORT_SYMBOL_GPL(geneve_xmit_skb);
 
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
index 7ca3d454ff3..bf02fd5808c 100644
--- a/net/openvswitch/vport-geneve.c
+++ b/net/openvswitch/vport-geneve.c
@@ -212,7 +212,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
 			      tun_key->ipv4_dst, tun_key->ipv4_tos,
 			      tun_key->ipv4_ttl, df, sport, dport,
 			      tun_key->tun_flags, vni, opts_len, opts,
-			      false);
+			      !!(tun_key->tun_flags & TUNNEL_CSUM), false);
 	if (err < 0)
 		ip_rt_put(rt);
 	return err;
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 3cc983bf444..ff07d4062d6 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -74,7 +74,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 	__be64 key;
 	__be16 flags;
 
-	flags = TUNNEL_KEY;
+	flags = TUNNEL_KEY | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0);
 	vxlan_port = vxlan_vport(vport);
 	if (vxlan_port->exts & VXLAN_F_GBP)
 		flags |= TUNNEL_VXLAN_OPT;
@@ -230,6 +230,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	__be16 src_port;
 	__be16 df;
 	int err;
+	u32 vxflags;
 
 	if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
 		err = -EINVAL;
@@ -251,11 +252,13 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	src_port = udp_flow_src_port(net, skb, 0, 0, true);
 	md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
 	md.gbp = vxlan_ext_gbp(skb);
+	vxflags = vxlan_port->exts |
+		      (tun_key->tun_flags & TUNNEL_CSUM ? VXLAN_F_UDP_CSUM : 0);
 
 	err = vxlan_xmit_skb(rt, skb, fl.saddr, tun_key->ipv4_dst,
 			     tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
 			     src_port, dst_port,
-			     &md, false, vxlan_port->exts);
+			     &md, false, vxflags);
 	if (err < 0)
 		ip_rt_put(rt);
 	return err;
-- 
cgit v1.2.3-70-g09d2


From 7cc05662682da4b0e0a4fdf3c3f190577803ae81 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 28 Jan 2015 18:04:53 +0100
Subject: net: remove sock_iocb

The sock_iocb structure is allocate on stack for each read/write-like
operation on sockets, and contains various fields of which only the
embedded msghdr and sometimes a pointer to the scm_cookie is ever used.
Get rid of the sock_iocb and put a msghdr directly on the stack and pass
the scm_cookie explicitly to netlink_mmap_sendmsg.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h       | 23 ---------------
 net/netlink/af_netlink.c | 28 +++++++------------
 net/socket.c             | 45 +++--------------------------
 net/unix/af_unix.c       | 73 +++++++++++++++++++-----------------------------
 4 files changed, 43 insertions(+), 126 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 2210fec6566..15341499786 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1374,29 +1374,6 @@ void sk_prot_clear_portaddr_nulls(struct sock *sk, int size);
 #define SOCK_BINDADDR_LOCK	4
 #define SOCK_BINDPORT_LOCK	8
 
-/* sock_iocb: used to kick off async processing of socket ios */
-struct sock_iocb {
-	struct list_head	list;
-
-	int			flags;
-	int			size;
-	struct socket		*sock;
-	struct sock		*sk;
-	struct scm_cookie	*scm;
-	struct msghdr		*msg, async_msg;
-	struct kiocb		*kiocb;
-};
-
-static inline struct sock_iocb *kiocb_to_siocb(struct kiocb *iocb)
-{
-	return (struct sock_iocb *)iocb->private;
-}
-
-static inline struct kiocb *siocb_to_kiocb(struct sock_iocb *si)
-{
-	return si->kiocb;
-}
-
 struct socket_alloc {
 	struct socket socket;
 	struct inode vfs_inode;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2197af00673..a36777b7cfb 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -695,7 +695,7 @@ static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk,
 
 static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 				u32 dst_portid, u32 dst_group,
-				struct sock_iocb *siocb)
+				struct scm_cookie *scm)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
@@ -741,7 +741,7 @@ static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
 
 		NETLINK_CB(skb).portid	  = nlk->portid;
 		NETLINK_CB(skb).dst_group = dst_group;
-		NETLINK_CB(skb).creds	  = siocb->scm->creds;
+		NETLINK_CB(skb).creds	  = scm->creds;
 
 		err = security_netlink_send(sk, skb);
 		if (err) {
@@ -820,7 +820,7 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
 #define netlink_poll			datagram_poll
-#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, siocb)	0
+#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, scm)	0
 #endif /* CONFIG_NETLINK_MMAP */
 
 static void netlink_skb_destructor(struct sk_buff *skb)
@@ -2259,7 +2259,6 @@ static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			   struct msghdr *msg, size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
@@ -2273,10 +2272,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &scm;
-
-	err = scm_send(sock, msg, siocb->scm, true);
+	err = scm_send(sock, msg, &scm, true);
 	if (err < 0)
 		return err;
 
@@ -2305,7 +2301,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (netlink_tx_is_mmaped(sk) &&
 	    msg->msg_iter.iov->iov_base == NULL) {
 		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
-					   siocb);
+					   &scm);
 		goto out;
 	}
 
@@ -2319,7 +2315,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
-	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).creds	= scm.creds;
 	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
@@ -2341,7 +2337,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT);
 
 out:
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return err;
 }
 
@@ -2349,7 +2345,6 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 			   struct msghdr *msg, size_t len,
 			   int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -2412,11 +2407,8 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	if (nlk->flags & NETLINK_RECV_PKTINFO)
 		netlink_cmsg_recv_pktinfo(msg, skb);
 
-	if (NULL == siocb->scm) {
-		memset(&scm, 0, sizeof(scm));
-		siocb->scm = &scm;
-	}
-	siocb->scm->creds = *NETLINK_CREDS(skb);
+	memset(&scm, 0, sizeof(scm));
+	scm.creds = *NETLINK_CREDS(skb);
 	if (flags & MSG_TRUNC)
 		copied = data_skb->len;
 
@@ -2431,7 +2423,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 		}
 	}
 
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 out:
 	netlink_rcv_wake(sk);
 	return err ? : copied;
diff --git a/net/socket.c b/net/socket.c
index 3acd35f144d..3326d67482a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -613,13 +613,6 @@ EXPORT_SYMBOL(__sock_tx_timestamp);
 static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
 				       struct msghdr *msg, size_t size)
 {
-	struct sock_iocb *si = kiocb_to_siocb(iocb);
-
-	si->sock = sock;
-	si->scm = NULL;
-	si->msg = msg;
-	si->size = size;
-
 	return sock->ops->sendmsg(iocb, sock, msg, size);
 }
 
@@ -635,11 +628,9 @@ static int do_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 			   size_t size, bool nosec)
 {
 	struct kiocb iocb;
-	struct sock_iocb siocb;
 	int ret;
 
 	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
 	ret = nosec ? __sock_sendmsg_nosec(&iocb, sock, msg, size) :
 		      __sock_sendmsg(&iocb, sock, msg, size);
 	if (-EIOCBQUEUED == ret)
@@ -756,14 +747,6 @@ EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
 static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
 				       struct msghdr *msg, size_t size, int flags)
 {
-	struct sock_iocb *si = kiocb_to_siocb(iocb);
-
-	si->sock = sock;
-	si->scm = NULL;
-	si->msg = msg;
-	si->size = size;
-	si->flags = flags;
-
 	return sock->ops->recvmsg(iocb, sock, msg, size, flags);
 }
 
@@ -779,11 +762,9 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg,
 		 size_t size, int flags)
 {
 	struct kiocb iocb;
-	struct sock_iocb siocb;
 	int ret;
 
 	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
 	ret = __sock_recvmsg(&iocb, sock, msg, size, flags);
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&iocb);
@@ -795,11 +776,9 @@ static int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
 			      size_t size, int flags)
 {
 	struct kiocb iocb;
-	struct sock_iocb siocb;
 	int ret;
 
 	init_sync_kiocb(&iocb, NULL);
-	iocb.private = &siocb;
 	ret = __sock_recvmsg_nosec(&iocb, sock, msg, size, flags);
 	if (-EIOCBQUEUED == ret)
 		ret = wait_on_sync_kiocb(&iocb);
@@ -866,14 +845,6 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
 
-static struct sock_iocb *alloc_sock_iocb(struct kiocb *iocb,
-					 struct sock_iocb *siocb)
-{
-	siocb->kiocb = iocb;
-	iocb->private = siocb;
-	return siocb;
-}
-
 static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
 		struct file *file, const struct iovec *iov,
 		unsigned long nr_segs)
@@ -893,7 +864,7 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb,
 static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos)
 {
-	struct sock_iocb siocb, *x;
+	struct msghdr msg;
 
 	if (pos != 0)
 		return -ESPIPE;
@@ -901,11 +872,7 @@ static ssize_t sock_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	if (iocb->ki_nbytes == 0)	/* Match SYS5 behaviour */
 		return 0;
 
-
-	x = alloc_sock_iocb(iocb, &siocb);
-	if (!x)
-		return -ENOMEM;
-	return do_sock_read(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
+	return do_sock_read(&msg, iocb, iocb->ki_filp, iov, nr_segs);
 }
 
 static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
@@ -929,16 +896,12 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb,
 static ssize_t sock_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			  unsigned long nr_segs, loff_t pos)
 {
-	struct sock_iocb siocb, *x;
+	struct msghdr msg;
 
 	if (pos != 0)
 		return -ESPIPE;
 
-	x = alloc_sock_iocb(iocb, &siocb);
-	if (!x)
-		return -ENOMEM;
-
-	return do_sock_write(&x->async_msg, iocb, iocb->ki_filp, iov, nr_segs);
+	return do_sock_write(&msg, iocb, iocb->ki_filp, iov, nr_segs);
 }
 
 /*
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8e1b10274b0..526b6edab01 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1445,7 +1445,6 @@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock,
 static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			      struct msghdr *msg, size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct net *net = sock_net(sk);
 	struct unix_sock *u = unix_sk(sk);
@@ -1456,14 +1455,12 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	unsigned int hash;
 	struct sk_buff *skb;
 	long timeo;
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	int max_level;
 	int data_len = 0;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm, false);
+	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
@@ -1507,11 +1504,11 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (skb == NULL)
 		goto out;
 
-	err = unix_scm_to_skb(siocb->scm, skb, true);
+	err = unix_scm_to_skb(&scm, skb, true);
 	if (err < 0)
 		goto out_free;
 	max_level = err + 1;
-	unix_get_secdata(siocb->scm, skb);
+	unix_get_secdata(&scm, skb);
 
 	skb_put(skb, len - data_len);
 	skb->data_len = data_len;
@@ -1606,7 +1603,7 @@ restart:
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
 	sock_put(other);
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return len;
 
 out_unlock:
@@ -1616,7 +1613,7 @@ out_free:
 out:
 	if (other)
 		sock_put(other);
-	scm_destroy(siocb->scm);
+	scm_destroy(&scm);
 	return err;
 }
 
@@ -1628,21 +1625,18 @@ out:
 static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			       struct msghdr *msg, size_t len)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct sock *other = NULL;
 	int err, size;
 	struct sk_buff *skb;
 	int sent = 0;
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	bool fds_sent = false;
 	int max_level;
 	int data_len;
 
-	if (NULL == siocb->scm)
-		siocb->scm = &tmp_scm;
 	wait_for_unix_gc();
-	err = scm_send(sock, msg, siocb->scm, false);
+	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
@@ -1683,7 +1677,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto out_err;
 
 		/* Only send the fds in the first buffer */
-		err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
+		err = unix_scm_to_skb(&scm, skb, !fds_sent);
 		if (err < 0) {
 			kfree_skb(skb);
 			goto out_err;
@@ -1715,8 +1709,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		sent += size;
 	}
 
-	scm_destroy(siocb->scm);
-	siocb->scm = NULL;
+	scm_destroy(&scm);
 
 	return sent;
 
@@ -1728,8 +1721,7 @@ pipe_err:
 		send_sig(SIGPIPE, current, 0);
 	err = -EPIPE;
 out_err:
-	scm_destroy(siocb->scm);
-	siocb->scm = NULL;
+	scm_destroy(&scm);
 	return sent ? : err;
 }
 
@@ -1778,8 +1770,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 			      struct msghdr *msg, size_t size,
 			      int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
 	int noblock = flags & MSG_DONTWAIT;
@@ -1831,16 +1822,14 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (sock_flag(sk, SOCK_RCVTSTAMP))
 		__sock_recv_timestamp(msg, sk, skb);
 
-	if (!siocb->scm) {
-		siocb->scm = &tmp_scm;
-		memset(&tmp_scm, 0, sizeof(tmp_scm));
-	}
-	scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
-	unix_set_secdata(siocb->scm, skb);
+	memset(&scm, 0, sizeof(scm));
+
+	scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
+	unix_set_secdata(&scm, skb);
 
 	if (!(flags & MSG_PEEK)) {
 		if (UNIXCB(skb).fp)
-			unix_detach_fds(siocb->scm, skb);
+			unix_detach_fds(&scm, skb);
 
 		sk_peek_offset_bwd(sk, skb->len);
 	} else {
@@ -1860,11 +1849,11 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
 		sk_peek_offset_fwd(sk, size);
 
 		if (UNIXCB(skb).fp)
-			siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+			scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 	}
 	err = (flags & MSG_TRUNC) ? skb->len - skip : size;
 
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 
 out_free:
 	skb_free_datagram(sk, skb);
@@ -1915,8 +1904,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 			       struct msghdr *msg, size_t size,
 			       int flags)
 {
-	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
-	struct scm_cookie tmp_scm;
+	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, msg->msg_name);
@@ -1943,10 +1931,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 	 * while sleeps in memcpy_tomsg
 	 */
 
-	if (!siocb->scm) {
-		siocb->scm = &tmp_scm;
-		memset(&tmp_scm, 0, sizeof(tmp_scm));
-	}
+	memset(&scm, 0, sizeof(scm));
 
 	err = mutex_lock_interruptible(&u->readlock);
 	if (unlikely(err)) {
@@ -2012,13 +1997,13 @@ again:
 
 		if (check_creds) {
 			/* Never glue messages from different writers */
-			if ((UNIXCB(skb).pid  != siocb->scm->pid) ||
-			    !uid_eq(UNIXCB(skb).uid, siocb->scm->creds.uid) ||
-			    !gid_eq(UNIXCB(skb).gid, siocb->scm->creds.gid))
+			if ((UNIXCB(skb).pid  != scm.pid) ||
+			    !uid_eq(UNIXCB(skb).uid, scm.creds.uid) ||
+			    !gid_eq(UNIXCB(skb).gid, scm.creds.gid))
 				break;
 		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
 			/* Copy credentials */
-			scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
+			scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
 			check_creds = 1;
 		}
 
@@ -2045,7 +2030,7 @@ again:
 			sk_peek_offset_bwd(sk, chunk);
 
 			if (UNIXCB(skb).fp)
-				unix_detach_fds(siocb->scm, skb);
+				unix_detach_fds(&scm, skb);
 
 			if (unix_skb_len(skb))
 				break;
@@ -2053,13 +2038,13 @@ again:
 			skb_unlink(skb, &sk->sk_receive_queue);
 			consume_skb(skb);
 
-			if (siocb->scm->fp)
+			if (scm.fp)
 				break;
 		} else {
 			/* It is questionable, see note in unix_dgram_recvmsg.
 			 */
 			if (UNIXCB(skb).fp)
-				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
 			sk_peek_offset_fwd(sk, chunk);
 
@@ -2068,7 +2053,7 @@ again:
 	} while (size);
 
 	mutex_unlock(&u->readlock);
-	scm_recv(sock, msg, siocb->scm, flags);
+	scm_recv(sock, msg, &scm, flags);
 out:
 	return copied ? : err;
 }
-- 
cgit v1.2.3-70-g09d2


From 61f552141c9c0e88b3fdc7046265781ffd8fa68a Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Sun, 18 Jan 2015 16:45:42 +0100
Subject: ftrace: let notrace function attribute disable hotpatching if
 necessary

gcc supports an s390 specific function attribute called "hotpatch".
It can be used to specify the number of halfwords that shall be added before
and after a function and which shall be filled with nops for runtime patching.

s390 will use the hotpatch attribute for function tracing, therefore make
sure that the notrace function attribute either disables the mcount call
or in case of hotpatch nop generation.

Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 include/linux/compiler.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index d5ad7b1118f..1ef679f4b88 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -54,7 +54,11 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 #include <linux/compiler-gcc.h>
 #endif
 
+#ifdef CC_USING_HOTPATCH
+#define notrace __attribute__((hotpatch(0,0)))
+#else
 #define notrace __attribute__((no_instrument_function))
+#endif
 
 /* Intel compiler defines __GNUC__. So we will overwrite implementations
  * coming from above header files here
-- 
cgit v1.2.3-70-g09d2


From 3c313161353ad527de1a6ecde0f0d41700858fd6 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Sat, 24 Jan 2015 18:47:20 +0100
Subject: bcma: detect SPROM revision 11
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extracting values from it is still unsupported, but at least we'll
display some meaningful error now.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/bcma/sprom.c         | 3 ++-
 include/linux/ssb/ssb_regs.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/bcma/sprom.c b/drivers/bcma/sprom.c
index efb037f9c98..206edd3ba66 100644
--- a/drivers/bcma/sprom.c
+++ b/drivers/bcma/sprom.c
@@ -579,7 +579,8 @@ int bcma_sprom_get(struct bcma_bus *bus)
 	u16 offset = BCMA_CC_SPROM;
 	u16 *sprom;
 	size_t sprom_sizes[] = { SSB_SPROMSIZE_WORDS_R4,
-				 SSB_SPROMSIZE_WORDS_R10, };
+				 SSB_SPROMSIZE_WORDS_R10,
+				 SSB_SPROMSIZE_WORDS_R11, };
 	int i, err = 0;
 
 	if (!bus->drv_cc.core)
diff --git a/include/linux/ssb/ssb_regs.h b/include/linux/ssb/ssb_regs.h
index f7b9100686c..c0f707ac192 100644
--- a/include/linux/ssb/ssb_regs.h
+++ b/include/linux/ssb/ssb_regs.h
@@ -173,6 +173,7 @@
 #define SSB_SPROMSIZE_BYTES_R123	(SSB_SPROMSIZE_WORDS_R123 * sizeof(u16))
 #define SSB_SPROMSIZE_BYTES_R4		(SSB_SPROMSIZE_WORDS_R4 * sizeof(u16))
 #define SSB_SPROMSIZE_WORDS_R10		230
+#define SSB_SPROMSIZE_WORDS_R11		234
 #define SSB_SPROM_BASE1			0x1000
 #define SSB_SPROM_BASE31		0x0800
 #define SSB_SPROM_REVISION		0x007E
-- 
cgit v1.2.3-70-g09d2


From b504075f5903b969a54ef3a6ae994c0872edb259 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Sun, 25 Jan 2015 11:11:14 +0100
Subject: bcma: add early_init function for PCIe core and move some fix into it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are some PCIe core fixes that need to be applied before accessing
SPROM, otherwise reading it may fail.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/bcma/driver_pci.c            | 66 ++++++++++++++++++++++++------------
 drivers/bcma/main.c                  |  7 ++++
 include/linux/bcma/bcma_driver_pci.h |  2 ++
 3 files changed, 53 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/driver_pci.c b/drivers/bcma/driver_pci.c
index b85a505603e..786666488a2 100644
--- a/drivers/bcma/driver_pci.c
+++ b/drivers/bcma/driver_pci.c
@@ -144,6 +144,47 @@ static u16 bcma_pcie_mdio_writeread(struct bcma_drv_pci *pc, u16 device,
 	return bcma_pcie_mdio_read(pc, device, address);
 }
 
+/**************************************************
+ * Early init.
+ **************************************************/
+
+static void bcma_core_pci_fixcfg(struct bcma_drv_pci *pc)
+{
+	struct bcma_device *core = pc->core;
+	u16 val16, core_index;
+	uint regoff;
+
+	regoff = BCMA_CORE_PCI_SPROM(BCMA_CORE_PCI_SPROM_PI_OFFSET);
+	core_index = (u16)core->core_index;
+
+	val16 = pcicore_read16(pc, regoff);
+	if (((val16 & BCMA_CORE_PCI_SPROM_PI_MASK) >> BCMA_CORE_PCI_SPROM_PI_SHIFT)
+	     != core_index) {
+		val16 = (core_index << BCMA_CORE_PCI_SPROM_PI_SHIFT) |
+			(val16 & ~BCMA_CORE_PCI_SPROM_PI_MASK);
+		pcicore_write16(pc, regoff, val16);
+	}
+}
+
+/*
+ * Apply some early fixes required before accessing SPROM.
+ * See also si_pci_fixcfg.
+ */
+void bcma_core_pci_early_init(struct bcma_drv_pci *pc)
+{
+	if (pc->early_setup_done)
+		return;
+
+	pc->hostmode = bcma_core_pci_is_in_hostmode(pc);
+	if (pc->hostmode)
+		goto out;
+
+	bcma_core_pci_fixcfg(pc);
+
+out:
+	pc->early_setup_done = true;
+}
+
 /**************************************************
  * Workarounds.
  **************************************************/
@@ -175,24 +216,6 @@ static void bcma_pcicore_serdes_workaround(struct bcma_drv_pci *pc)
 		                     tmp & ~BCMA_CORE_PCI_PLL_CTRL_FREQDET_EN);
 }
 
-static void bcma_core_pci_fixcfg(struct bcma_drv_pci *pc)
-{
-	struct bcma_device *core = pc->core;
-	u16 val16, core_index;
-	uint regoff;
-
-	regoff = BCMA_CORE_PCI_SPROM(BCMA_CORE_PCI_SPROM_PI_OFFSET);
-	core_index = (u16)core->core_index;
-
-	val16 = pcicore_read16(pc, regoff);
-	if (((val16 & BCMA_CORE_PCI_SPROM_PI_MASK) >> BCMA_CORE_PCI_SPROM_PI_SHIFT)
-	     != core_index) {
-		val16 = (core_index << BCMA_CORE_PCI_SPROM_PI_SHIFT) |
-			(val16 & ~BCMA_CORE_PCI_SPROM_PI_MASK);
-		pcicore_write16(pc, regoff, val16);
-	}
-}
-
 /* Fix MISC config to allow coming out of L2/L3-Ready state w/o PRST */
 /* Needs to happen when coming out of 'standby'/'hibernate' */
 static void bcma_core_pci_config_fixup(struct bcma_drv_pci *pc)
@@ -216,7 +239,6 @@ static void bcma_core_pci_config_fixup(struct bcma_drv_pci *pc)
 
 static void bcma_core_pci_clientmode_init(struct bcma_drv_pci *pc)
 {
-	bcma_core_pci_fixcfg(pc);
 	bcma_pcicore_serdes_workaround(pc);
 	bcma_core_pci_config_fixup(pc);
 }
@@ -226,11 +248,11 @@ void bcma_core_pci_init(struct bcma_drv_pci *pc)
 	if (pc->setup_done)
 		return;
 
-	pc->hostmode = bcma_core_pci_is_in_hostmode(pc);
+	bcma_core_pci_early_init(pc);
+
 	if (pc->hostmode)
 		bcma_core_pci_hostmode_init(pc);
-
-	if (!pc->hostmode)
+	else
 		bcma_core_pci_clientmode_init(pc);
 }
 
diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c
index 73b2ee3de97..38bde6eab8a 100644
--- a/drivers/bcma/main.c
+++ b/drivers/bcma/main.c
@@ -402,6 +402,13 @@ int bcma_bus_register(struct bcma_bus *bus)
 		bcma_core_chipcommon_early_init(&bus->drv_cc);
 	}
 
+	/* Early init PCIE core */
+	core = bcma_find_core(bus, BCMA_CORE_PCIE);
+	if (core) {
+		bus->drv_pci[0].core = core;
+		bcma_core_pci_early_init(&bus->drv_pci[0]);
+	}
+
 	/* Cores providing flash access go before SPROM init */
 	list_for_each_entry(core, &bus->cores, list) {
 		if (bcma_is_core_needed_early(core->id.id))
diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h
index 0333e605ea0..3f809ae372c 100644
--- a/include/linux/bcma/bcma_driver_pci.h
+++ b/include/linux/bcma/bcma_driver_pci.h
@@ -223,6 +223,7 @@ struct bcma_drv_pci_host {
 
 struct bcma_drv_pci {
 	struct bcma_device *core;
+	u8 early_setup_done:1;
 	u8 setup_done:1;
 	u8 hostmode:1;
 
@@ -237,6 +238,7 @@ struct bcma_drv_pci {
 #define pcicore_write16(pc, offset, val)	bcma_write16((pc)->core, offset, val)
 #define pcicore_write32(pc, offset, val)	bcma_write32((pc)->core, offset, val)
 
+extern void bcma_core_pci_early_init(struct bcma_drv_pci *pc);
 extern void bcma_core_pci_init(struct bcma_drv_pci *pc);
 extern int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc,
 				 struct bcma_device *core, bool enable);
-- 
cgit v1.2.3-70-g09d2


From 8be08a39d498d5d93ff5149276e34ccb4ec3757f Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Sun, 25 Jan 2015 13:41:19 +0100
Subject: bcma: implement host code support for PCIe Gen 2 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is stil incomplete, so we don't add PCI IDs of new devices yet.
Purpose of this patch is to allow testing & adjusting rest of the code.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/bcma/host_pci.c        | 6 ++++--
 include/linux/bcma/bcma.h      | 1 +
 include/linux/bcma/bcma_regs.h | 2 ++
 3 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/bcma/host_pci.c b/drivers/bcma/host_pci.c
index cd9161a8b3a..53c6a8a5885 100644
--- a/drivers/bcma/host_pci.c
+++ b/drivers/bcma/host_pci.c
@@ -13,10 +13,12 @@
 
 static void bcma_host_pci_switch_core(struct bcma_device *core)
 {
+	int win2 = core->bus->host_is_pcie2 ?
+		BCMA_PCIE2_BAR0_WIN2 : BCMA_PCI_BAR0_WIN2;
+
 	pci_write_config_dword(core->bus->host_pci, BCMA_PCI_BAR0_WIN,
 			       core->addr);
-	pci_write_config_dword(core->bus->host_pci, BCMA_PCI_BAR0_WIN2,
-			       core->wrap);
+	pci_write_config_dword(core->bus->host_pci, win2, core->wrap);
 	core->bus->mapped_core = core;
 	bcma_debug(core->bus, "Switched to core: 0x%X\n", core->id.id);
 }
diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h
index eb1c6a47b67..994739da827 100644
--- a/include/linux/bcma/bcma.h
+++ b/include/linux/bcma/bcma.h
@@ -318,6 +318,7 @@ struct bcma_bus {
 	const struct bcma_host_ops *ops;
 
 	enum bcma_hosttype hosttype;
+	bool host_is_pcie2; /* Used for BCMA_HOSTTYPE_PCI only */
 	union {
 		/* Pointer to the PCI bus (only for BCMA_HOSTTYPE_PCI) */
 		struct pci_dev *host_pci;
diff --git a/include/linux/bcma/bcma_regs.h b/include/linux/bcma/bcma_regs.h
index e64ae7bf80a..ebd5c1fcdea 100644
--- a/include/linux/bcma/bcma_regs.h
+++ b/include/linux/bcma/bcma_regs.h
@@ -64,6 +64,8 @@
 #define  BCMA_PCI_GPIO_XTAL		0x40	/* PCI config space GPIO 14 for Xtal powerup */
 #define  BCMA_PCI_GPIO_PLL		0x80	/* PCI config space GPIO 15 for PLL powerdown */
 
+#define BCMA_PCIE2_BAR0_WIN2		0x70
+
 /* SiliconBackplane Address Map.
  * All regions may not exist on all chips.
  */
-- 
cgit v1.2.3-70-g09d2


From 0501be6429e4eb02f417ad83eacd84b8c57b0283 Mon Sep 17 00:00:00 2001
From: Alexey Skidanov <alexey.skidanov@sandisk.com>
Date: Thu, 29 Jan 2015 10:49:43 +0200
Subject: mmc: Resolve BKOPS compatability issue

This patch is coming to fix compatibility issue of BKOPS_EN  field of EXT_CSD.
In eMMC-5.1, BKOPS_EN was changed, and now it has two operational bits:
Bit 0 - MANUAL_EN
Bit 1 - AUTO_EN
In previous eMMC revisions, only Bit 0 was supported.

Signed-off-by: Alexey Skidanov <alexey.skidanov@sandisk.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/core.c  | 2 +-
 drivers/mmc/core/mmc.c   | 8 +++++---
 include/linux/mmc/card.h | 2 +-
 include/linux/mmc/mmc.h  | 5 +++++
 4 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 1be7055548c..0dc64e6e00d 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -275,7 +275,7 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception)
 
 	BUG_ON(!card);
 
-	if (!card->ext_csd.bkops_en || mmc_card_doing_bkops(card))
+	if (!card->ext_csd.man_bkops_en || mmc_card_doing_bkops(card))
 		return;
 
 	err = mmc_read_bkops_status(card);
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 1fc48a28065..1d41e8541f3 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -483,11 +483,13 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		/* check whether the eMMC card supports BKOPS */
 		if (ext_csd[EXT_CSD_BKOPS_SUPPORT] & 0x1) {
 			card->ext_csd.bkops = 1;
-			card->ext_csd.bkops_en = ext_csd[EXT_CSD_BKOPS_EN];
+			card->ext_csd.man_bkops_en =
+					(ext_csd[EXT_CSD_BKOPS_EN] &
+						EXT_CSD_MANUAL_BKOPS_MASK);
 			card->ext_csd.raw_bkops_status =
 				ext_csd[EXT_CSD_BKOPS_STATUS];
-			if (!card->ext_csd.bkops_en)
-				pr_info("%s: BKOPS_EN bit is not set\n",
+			if (!card->ext_csd.man_bkops_en)
+				pr_info("%s: MAN_BKOPS_EN bit is not set\n",
 					mmc_hostname(card->host));
 		}
 
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 4d69c00497b..a6cf4c063e4 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -83,7 +83,7 @@ struct mmc_ext_csd {
 	bool			hpi;			/* HPI support bit */
 	unsigned int		hpi_cmd;		/* cmd used as HPI */
 	bool			bkops;		/* background support bit */
-	bool			bkops_en;	/* background enable bit */
+	bool			man_bkops_en;	/* manual bkops enable bit */
 	unsigned int            data_sector_size;       /* 512 bytes or 4KB */
 	unsigned int            data_tag_unit_size;     /* DATA TAG UNIT size */
 	unsigned int		boot_ro_lock;		/* ro lock support */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index fb97b5cc91c..124f562118b 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -427,6 +427,11 @@ struct _mmc_csd {
  */
 #define EXT_CSD_BKOPS_LEVEL_2		0x2
 
+/*
+ * BKOPS modes
+ */
+#define EXT_CSD_MANUAL_BKOPS_MASK	0x01
+
 /*
  * MMC_SWITCH access modes
  */
-- 
cgit v1.2.3-70-g09d2


From 500d4160abe9a2e88b12e319c13ae3ebd1e18108 Mon Sep 17 00:00:00 2001
From: Ping Cheng <pinglinux@gmail.com>
Date: Tue, 27 Jan 2015 13:30:03 -0800
Subject: HID: wacom: add support for Cintiq 27QHD and 27QHD touch

These devices have accelerometers. To report accelerometer coordinates, a new
property, INPUT_PROP_ACCELEROMETER, is added.

Signed-off-by: Ping Cheng <pingc@wacom.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/wacom_sys.c    |  3 ++
 drivers/hid/wacom_wac.c    | 87 ++++++++++++++++++++++++++++++++++++++--------
 drivers/hid/wacom_wac.h    |  7 +++-
 include/uapi/linux/input.h |  1 +
 4 files changed, 83 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index f01ab3a0c5f..f0568a7e6de 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -403,6 +403,9 @@ static int wacom_query_tablet_data(struct hid_device *hdev,
 		else if (features->type == WACOM_24HDT || features->type == CINTIQ_HYBRID) {
 			return wacom_set_device_mode(hdev, 18, 3, 2);
 		}
+		else if (features->type == WACOM_27QHDT) {
+			return wacom_set_device_mode(hdev, 131, 3, 2);
+		}
 	} else if (features->device_type == BTN_TOOL_PEN) {
 		if (features->type <= BAMBOO_PT && features->type != WIRELESS) {
 			return wacom_set_device_mode(hdev, 2, 2, 2);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index d239d82a1f9..1a6507999a6 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -656,6 +656,8 @@ static int wacom_intuos_irq(struct wacom_wac *wacom)
 	    data[0] != WACOM_REPORT_INTUOSREAD &&
 	    data[0] != WACOM_REPORT_INTUOSWRITE &&
 	    data[0] != WACOM_REPORT_INTUOSPAD &&
+	    data[0] != WACOM_REPORT_CINTIQ &&
+	    data[0] != WACOM_REPORT_CINTIQPAD &&
 	    data[0] != WACOM_REPORT_INTUOS5PAD) {
 		dev_dbg(input->dev.parent,
 			"%s: received unknown report #%d\n", __func__, data[0]);
@@ -667,7 +669,8 @@ static int wacom_intuos_irq(struct wacom_wac *wacom)
 		idx = data[1] & 0x01;
 
 	/* pad packets. Works as a second tool and is always in prox */
-	if (data[0] == WACOM_REPORT_INTUOSPAD || data[0] == WACOM_REPORT_INTUOS5PAD) {
+	if (data[0] == WACOM_REPORT_INTUOSPAD || data[0] == WACOM_REPORT_INTUOS5PAD ||
+	    data[0] == WACOM_REPORT_CINTIQPAD) {
 		input = wacom->pad_input;
 		if (features->type >= INTUOS4S && features->type <= INTUOS4L) {
 			input_report_key(input, BTN_0, (data[2] & 0x01));
@@ -767,6 +770,14 @@ static int wacom_intuos_irq(struct wacom_wac *wacom)
 			} else {
 				input_report_abs(input, ABS_MISC, 0);
 			}
+		} else if (features->type == WACOM_27QHD) {
+			input_report_key(input, KEY_PROG1, data[2] & 0x01);
+			input_report_key(input, KEY_PROG2, data[2] & 0x02);
+			input_report_key(input, KEY_PROG3, data[2] & 0x04);
+
+			input_report_abs(input, ABS_X, be16_to_cpup((__be16 *)&data[4]));
+			input_report_abs(input, ABS_Y, be16_to_cpup((__be16 *)&data[6]));
+			input_report_abs(input, ABS_Z, be16_to_cpup((__be16 *)&data[8]));
 		} else if (features->type == CINTIQ_HYBRID) {
 			/*
 			 * Do not send hardware buttons under Android. They
@@ -1027,8 +1038,20 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom)
 	struct input_dev *input = wacom->input;
 	unsigned char *data = wacom->data;
 	int i;
-	int current_num_contacts = data[61];
+	int current_num_contacts = 0;
 	int contacts_to_send = 0;
+	int num_contacts_left = 4; /* maximum contacts per packet */
+	int byte_per_packet = WACOM_BYTES_PER_24HDT_PACKET;
+	int y_offset = 2;
+
+	if (wacom->features.type == WACOM_27QHDT) {
+		current_num_contacts = data[63];
+		num_contacts_left = 10;
+		byte_per_packet = WACOM_BYTES_PER_QHDTHID_PACKET;
+		y_offset = 0;
+	} else {
+		current_num_contacts = data[61];
+	}
 
 	/*
 	 * First packet resets the counter since only the first
@@ -1037,11 +1060,10 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom)
 	if (current_num_contacts)
 		wacom->num_contacts_left = current_num_contacts;
 
-	/* There are at most 4 contacts per packet */
-	contacts_to_send = min(4, wacom->num_contacts_left);
+	contacts_to_send = min(num_contacts_left, wacom->num_contacts_left);
 
 	for (i = 0; i < contacts_to_send; i++) {
-		int offset = (WACOM_BYTES_PER_24HDT_PACKET * i) + 1;
+		int offset = (byte_per_packet * i) + 1;
 		bool touch = (data[offset] & 0x1) && !wacom->shared->stylus_in_proximity;
 		int slot = input_mt_get_slot_by_key(input, data[offset + 1]);
 
@@ -1052,18 +1074,23 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom)
 
 		if (touch) {
 			int t_x = get_unaligned_le16(&data[offset + 2]);
-			int c_x = get_unaligned_le16(&data[offset + 4]);
-			int t_y = get_unaligned_le16(&data[offset + 6]);
-			int c_y = get_unaligned_le16(&data[offset + 8]);
-			int w = get_unaligned_le16(&data[offset + 10]);
-			int h = get_unaligned_le16(&data[offset + 12]);
+			int t_y = get_unaligned_le16(&data[offset + 4 + y_offset]);
 
 			input_report_abs(input, ABS_MT_POSITION_X, t_x);
 			input_report_abs(input, ABS_MT_POSITION_Y, t_y);
-			input_report_abs(input, ABS_MT_TOUCH_MAJOR, min(w,h));
-			input_report_abs(input, ABS_MT_WIDTH_MAJOR, min(w, h) + int_dist(t_x, t_y, c_x, c_y));
-			input_report_abs(input, ABS_MT_WIDTH_MINOR, min(w, h));
-			input_report_abs(input, ABS_MT_ORIENTATION, w > h);
+
+			if (wacom->features.type != WACOM_27QHDT) {
+				int c_x = get_unaligned_le16(&data[offset + 4]);
+				int c_y = get_unaligned_le16(&data[offset + 8]);
+				int w = get_unaligned_le16(&data[offset + 10]);
+				int h = get_unaligned_le16(&data[offset + 12]);
+
+				input_report_abs(input, ABS_MT_TOUCH_MAJOR, min(w,h));
+				input_report_abs(input, ABS_MT_WIDTH_MAJOR,
+						 min(w, h) + int_dist(t_x, t_y, c_x, c_y));
+				input_report_abs(input, ABS_MT_WIDTH_MINOR, min(w, h));
+				input_report_abs(input, ABS_MT_ORIENTATION, w > h);
+			}
 		}
 	}
 	input_mt_report_pointer_emulation(input, true);
@@ -1894,6 +1921,7 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 	case WACOM_21UX2:
 	case WACOM_22HD:
 	case WACOM_24HD:
+	case WACOM_27QHD:
 	case DTK:
 	case CINTIQ_HYBRID:
 		sync = wacom_intuos_irq(wacom_wac);
@@ -1904,6 +1932,7 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 		break;
 
 	case WACOM_24HDT:
+	case WACOM_27QHDT:
 		sync = wacom_24hdt_irq(wacom_wac);
 		break;
 
@@ -2115,6 +2144,7 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
 		break;
 
+	case WACOM_27QHD:
 	case WACOM_24HD:
 	case DTK:
 	case WACOM_22HD:
@@ -2183,6 +2213,7 @@ int wacom_setup_pentouch_input_capabilities(struct input_dev *input_dev,
 		}
 		/* fall through */
 
+	case WACOM_27QHDT:
 	case MTSCREEN:
 	case MTTPC:
 	case MTTPC_B:
@@ -2330,6 +2361,19 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 		input_set_abs_params(input_dev, ABS_THROTTLE, 0, 71, 0, 0);
 		break;
 
+	case WACOM_27QHD:
+		__set_bit(KEY_PROG1, input_dev->keybit);
+		__set_bit(KEY_PROG2, input_dev->keybit);
+		__set_bit(KEY_PROG3, input_dev->keybit);
+		input_set_abs_params(input_dev, ABS_X, -2048, 2048, 0, 0);
+		input_abs_set_res(input_dev, ABS_X, 1024); /* points/g */
+		input_set_abs_params(input_dev, ABS_Y, -2048, 2048, 0, 0);
+		input_abs_set_res(input_dev, ABS_Y, 1024);
+		input_set_abs_params(input_dev, ABS_Z, -2048, 2048, 0, 0);
+		input_abs_set_res(input_dev, ABS_Z, 1024);
+		__set_bit(INPUT_PROP_ACCELEROMETER, input_dev->propbit);
+		break;
+
 	case DTK:
 		for (i = 0; i < 6; i++)
 			__set_bit(BTN_0 + i, input_dev->keybit);
@@ -2680,6 +2724,18 @@ static const struct wacom_features wacom_features_0xF6 =
 	{ "Wacom Cintiq 24HD touch", .type = WACOM_24HDT, /* Touch */
 	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0xf8, .touch_max = 10,
 	  .check_for_hid_type = true, .hid_type = HID_TYPE_USBNONE };
+static const struct wacom_features wacom_features_0x32A =
+	{ "Wacom Cintiq 27QHD", 119740, 67520, 2047,
+	  63, WACOM_27QHD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
+	  WACOM_27QHD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
+static const struct wacom_features wacom_features_0x32B =
+	{ "Wacom Cintiq 27QHD touch", 119740, 67520, 2047, 63,
+	  WACOM_27QHD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
+	  WACOM_CINTIQ_OFFSET, WACOM_CINTIQ_OFFSET,
+	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x32C };
+static const struct wacom_features wacom_features_0x32C =
+	{ "Wacom Cintiq 27QHD touch", .type = WACOM_27QHDT,
+	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x32B, .touch_max = 10 };
 static const struct wacom_features wacom_features_0x3F =
 	{ "Wacom Cintiq 21UX", 87200, 65600, 1023, 63,
 	  CINTIQ, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
@@ -3046,6 +3102,9 @@ const struct hid_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x315) },
 	{ USB_DEVICE_WACOM(0x317) },
 	{ USB_DEVICE_WACOM(0x323) },
+	{ USB_DEVICE_WACOM(0x32A) },
+	{ USB_DEVICE_WACOM(0x32B) },
+	{ USB_DEVICE_WACOM(0x32C) },
 	{ USB_DEVICE_WACOM(0x32F) },
 	{ USB_DEVICE_WACOM(0x4001) },
 	{ USB_DEVICE_WACOM(0x4004) },
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index 72e78cc1893..021ee1c1980 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -13,7 +13,7 @@
 #include <linux/hid.h>
 
 /* maximum packet length for USB devices */
-#define WACOM_PKGLEN_MAX	68
+#define WACOM_PKGLEN_MAX	192
 
 #define WACOM_NAME_MAX		64
 
@@ -37,6 +37,7 @@
 /* wacom data size per MT contact */
 #define WACOM_BYTES_PER_MT_PACKET	11
 #define WACOM_BYTES_PER_24HDT_PACKET	14
+#define WACOM_BYTES_PER_QHDTHID_PACKET	 6
 
 /* device IDs */
 #define STYLUS_DEVICE_ID	0x02
@@ -58,6 +59,8 @@
 #define WACOM_REPORT_TPCMT		13
 #define WACOM_REPORT_TPCMT2		3
 #define WACOM_REPORT_TPCHID		15
+#define WACOM_REPORT_CINTIQ		16
+#define WACOM_REPORT_CINTIQPAD		17
 #define WACOM_REPORT_TPCST		16
 #define WACOM_REPORT_DTUS		17
 #define WACOM_REPORT_TPC1FGE		18
@@ -109,6 +112,7 @@ enum {
 	WACOM_22HD,
 	DTK,
 	WACOM_24HD,
+	WACOM_27QHD,
 	CINTIQ_HYBRID,
 	CINTIQ,
 	WACOM_BEE,
@@ -117,6 +121,7 @@ enum {
 	WIRELESS,
 	BAMBOO_PT,
 	WACOM_24HDT,
+	WACOM_27QHDT,
 	TABLETPC,   /* add new TPC below */
 	TABLETPCE,
 	TABLETPC2FG,
diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index a1d7e931ab7..b0a81307985 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -166,6 +166,7 @@ struct input_keymap_entry {
 #define INPUT_PROP_SEMI_MT		0x03	/* touch rectangle only */
 #define INPUT_PROP_TOPBUTTONPAD		0x04	/* softbuttons at top of pad */
 #define INPUT_PROP_POINTING_STICK	0x05	/* is a pointing stick */
+#define INPUT_PROP_ACCELEROMETER	0x06	/* has accelerometer */
 
 #define INPUT_PROP_MAX			0x1f
 #define INPUT_PROP_CNT			(INPUT_PROP_MAX + 1)
-- 
cgit v1.2.3-70-g09d2


From a12c6b861fab9229f002dc2eddc0aee988170e2b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 29 Jan 2015 16:52:16 +0100
Subject: nl80211: don't document per-wiphy interface dump

Such a feature doesn't exist and isn't really needed since you
probably won't have enough interfaces to make it worthwhile, so
just remove that from the documentation.

Reported-by: booto [on IRC]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/uapi/linux/nl80211.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 1cbc3aae425..68b294e8394 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -180,8 +180,8 @@
  *	%NL80211_ATTR_WIPHY and %NL80211_ATTR_WIPHY_NAME.
  *
  * @NL80211_CMD_GET_INTERFACE: Request an interface's configuration;
- *	either a dump request on a %NL80211_ATTR_WIPHY or a specific get
- *	on an %NL80211_ATTR_IFINDEX is supported.
+ *	either a dump request for all interfaces or a specific get with a
+ *	single %NL80211_ATTR_IFINDEX is supported.
  * @NL80211_CMD_SET_INTERFACE: Set type of a virtual interface, requires
  *	%NL80211_ATTR_IFINDEX and %NL80211_ATTR_IFTYPE.
  * @NL80211_CMD_NEW_INTERFACE: Newly created virtual interface or response
-- 
cgit v1.2.3-70-g09d2


From 33692f27597fcab536d7cbbcc8f52905133e4aa7 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 29 Jan 2015 10:51:32 -0800
Subject: vm: add VM_FAULT_SIGSEGV handling support

The core VM already knows about VM_FAULT_SIGBUS, but cannot return a
"you should SIGSEGV" error, because the SIGSEGV case was generally
handled by the caller - usually the architecture fault handler.

That results in lots of duplication - all the architecture fault
handlers end up doing very similar "look up vma, check permissions, do
retries etc" - but it generally works.  However, there are cases where
the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV.

In particular, when accessing the stack guard page, libsigsegv expects a
SIGSEGV.  And it usually got one, because the stack growth is handled by
that duplicated architecture fault handler.

However, when the generic VM layer started propagating the error return
from the stack expansion in commit fee7e49d4514 ("mm: propagate error
from stack expansion even for guard page"), that now exposed the
existing VM_FAULT_SIGBUS result to user space.  And user space really
expected SIGSEGV, not SIGBUS.

To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those
duplicate architecture fault handlers about it.  They all already have
the code to handle SIGSEGV, so it's about just tying that new return
value to the existing code, but it's all a bit annoying.

This is the mindless minimal patch to do this.  A more extensive patch
would be to try to gather up the mostly shared fault handling logic into
one generic helper routine, and long-term we really should do that
cleanup.

Just from this patch, you can generally see that most architectures just
copied (directly or indirectly) the old x86 way of doing things, but in
the meantime that original x86 model has been improved to hold the VM
semaphore for shorter times etc and to handle VM_FAULT_RETRY and other
"newer" things, so it would be a good idea to bring all those
improvements to the generic case and teach other architectures about
them too.

Reported-and-tested-by: Takashi Iwai <tiwai@suse.de>
Tested-by: Jan Engelhardt <jengelh@inai.de>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots"
Cc: linux-arch@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/mm/fault.c                        | 2 ++
 arch/arc/mm/fault.c                          | 2 ++
 arch/avr32/mm/fault.c                        | 2 ++
 arch/cris/mm/fault.c                         | 2 ++
 arch/frv/mm/fault.c                          | 2 ++
 arch/ia64/mm/fault.c                         | 2 ++
 arch/m32r/mm/fault.c                         | 2 ++
 arch/m68k/mm/fault.c                         | 2 ++
 arch/metag/mm/fault.c                        | 2 ++
 arch/microblaze/mm/fault.c                   | 2 ++
 arch/mips/mm/fault.c                         | 2 ++
 arch/mn10300/mm/fault.c                      | 2 ++
 arch/nios2/mm/fault.c                        | 2 ++
 arch/openrisc/mm/fault.c                     | 2 ++
 arch/parisc/mm/fault.c                       | 2 ++
 arch/powerpc/mm/copro_fault.c                | 2 +-
 arch/powerpc/mm/fault.c                      | 2 ++
 arch/s390/mm/fault.c                         | 6 ++++++
 arch/score/mm/fault.c                        | 2 ++
 arch/sh/mm/fault.c                           | 2 ++
 arch/sparc/mm/fault_32.c                     | 2 ++
 arch/sparc/mm/fault_64.c                     | 2 ++
 arch/tile/mm/fault.c                         | 2 ++
 arch/um/kernel/trap.c                        | 2 ++
 arch/x86/mm/fault.c                          | 2 ++
 arch/xtensa/mm/fault.c                       | 2 ++
 drivers/staging/lustre/lustre/llite/vvp_io.c | 2 +-
 include/linux/mm.h                           | 6 ++++--
 mm/gup.c                                     | 4 ++--
 mm/ksm.c                                     | 2 +-
 30 files changed, 63 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index 98838a05ba6..9d0ac091a52 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -156,6 +156,8 @@ retry:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 6f7e3a68803..0f8df3b5b1b 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -161,6 +161,8 @@ good_area:
 
 	if (fault & VM_FAULT_OOM)
 		goto out_of_memory;
+	else if (fault & VM_FAULT_SIGSEV)
+		goto bad_area;
 	else if (fault & VM_FAULT_SIGBUS)
 		goto do_sigbus;
 
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index 0eca9332719..d223a8b57c1 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -142,6 +142,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 1790f22e71a..2686a7aa8ec 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -176,6 +176,8 @@ retry:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 9a66372fc7c..ec4917ddf67 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -168,6 +168,8 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 7225dad8709..ba5ba7accd0 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -172,6 +172,8 @@ retry:
 		 */
 		if (fault & VM_FAULT_OOM) {
 			goto out_of_memory;
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			goto bad_area;
 		} else if (fault & VM_FAULT_SIGBUS) {
 			signal = SIGBUS;
 			goto bad_area;
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index e9c6a8014bd..e3d4d489010 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -200,6 +200,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index 2bd7487440c..b2f04aee46e 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -145,6 +145,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto map_err;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bus_err;
 		BUG();
diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c
index 332680e5ebf..2de5dc695a8 100644
--- a/arch/metag/mm/fault.c
+++ b/arch/metag/mm/fault.c
@@ -141,6 +141,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index fa4cf52aa7a..d46a5ebb757 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -224,6 +224,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index becc42bb184..70ab5d66433 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -158,6 +158,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index 3516cbdf1ee..0c2cc5d39c8 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -262,6 +262,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c
index 15a0bb5fc06..34429d5a0cc 100644
--- a/arch/nios2/mm/fault.c
+++ b/arch/nios2/mm/fault.c
@@ -135,6 +135,8 @@ survive:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c
index 0703acf7d32..230ac20ae79 100644
--- a/arch/openrisc/mm/fault.c
+++ b/arch/openrisc/mm/fault.c
@@ -171,6 +171,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 3ca9c1131cf..e5120e65324 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -256,6 +256,8 @@ good_area:
 		 */
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto bad_area;
 		BUG();
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 5a236f082c7..1b5305d4bda 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -76,7 +76,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		if (*flt & VM_FAULT_OOM) {
 			ret = -ENOMEM;
 			goto out_unlock;
-		} else if (*flt & VM_FAULT_SIGBUS) {
+		} else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 			ret = -EFAULT;
 			goto out_unlock;
 		}
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index eb79907f34f..6154b0a2b06 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -437,6 +437,8 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+		if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		rc = mm_fault_error(regs, address, fault);
 		if (rc >= MM_FAULT_RETURN)
 			goto bail;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 811937bb90b..9065d5aa393 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -374,6 +374,12 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
 				do_no_context(regs);
 			else
 				pagefault_out_of_memory();
+		} else if (fault & VM_FAULT_SIGSEGV) {
+			/* Kernel mode? Handle exceptions or die */
+			if (!user_mode(regs))
+				do_no_context(regs);
+			else
+				do_sigsegv(regs, SEGV_MAPERR);
 		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
 			if (!user_mode(regs))
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index 52238983527..6860beb2a28 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -114,6 +114,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index 541dc610150..a58fec9b55e 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -353,6 +353,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	} else {
 		if (fault & VM_FAULT_SIGBUS)
 			do_sigbus(regs, error_code, address);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area(regs, error_code, address);
 		else
 			BUG();
 	}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 908e8c17c90..70d817154fe 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -249,6 +249,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 18fcd716709..47982324942 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -446,6 +446,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index 565e25a9833..0f61a73534e 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -442,6 +442,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 5678c3571e7..209617302df 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -80,6 +80,8 @@ good_area:
 		if (unlikely(fault & VM_FAULT_ERROR)) {
 			if (fault & VM_FAULT_OOM) {
 				goto out_of_memory;
+			} else if (fault & VM_FAULT_SIGSEGV) {
+				goto out;
 			} else if (fault & VM_FAULT_SIGBUS) {
 				err = -EACCES;
 				goto out;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 38dcec403b4..e3ff27a5b63 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -898,6 +898,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))
 			do_sigbus(regs, error_code, address, fault);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area_nosemaphore(regs, error_code, address);
 		else
 			BUG();
 	}
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index b57c4f91f48..9e3571a6535 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -117,6 +117,8 @@ good_area:
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGSEGV)
+			goto bad_area;
 		else if (fault & VM_FAULT_SIGBUS)
 			goto do_sigbus;
 		BUG();
diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c
index 930f6010203..65d610abe06 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_io.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_io.c
@@ -632,7 +632,7 @@ static int vvp_io_kernel_fault(struct vvp_fault_io *cfio)
 		return 0;
 	}
 
-	if (cfio->fault.ft_flags & VM_FAULT_SIGBUS) {
+	if (cfio->fault.ft_flags & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
 		CDEBUG(D_PAGE, "got addr %p - SIGBUS\n", vmf->virtual_address);
 		return -EFAULT;
 	}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80fc92a4964..dd5ea3016fc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1070,6 +1070,7 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
 #define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned small page */
 #define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
+#define VM_FAULT_SIGSEGV 0x0040
 
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
@@ -1078,8 +1079,9 @@ static inline int page_mapped(struct page *page)
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
-#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
-			 VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | \
+			 VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \
+			 VM_FAULT_FALLBACK)
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
diff --git a/mm/gup.c b/mm/gup.c
index a900759cc80..8dd50ce6326 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -296,7 +296,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
@@ -571,7 +571,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return -EHWPOISON;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
diff --git a/mm/ksm.c b/mm/ksm.c
index d247efab507..15647fb0394 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);
-	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
 	/*
 	 * We must loop because handle_mm_fault() may back out if there's
 	 * any difficulty e.g. if pte accessed bit gets updated concurrently.
-- 
cgit v1.2.3-70-g09d2


From 7866a621043fbaca3d7389e9b9f69dd1a2e5a855 Mon Sep 17 00:00:00 2001
From: Salam Noureddine <noureddine@arista.com>
Date: Tue, 27 Jan 2015 11:35:48 -0800
Subject: dev: add per net_device packet type chains

When many pf_packet listeners are created on a lot of interfaces the
current implementation using global packet type lists scales poorly.
This patch adds per net_device packet type lists to fix this problem.

The patch was originally written by Eric Biederman for linux-2.6.29.
Tested on linux-3.16.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Salam Noureddine <noureddine@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |   2 +
 net/core/dev.c            | 132 +++++++++++++++++++++++++++++-----------------
 2 files changed, 86 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 642d426a668..3d37c6eb173 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1514,6 +1514,8 @@ struct net_device {
 	struct list_head	napi_list;
 	struct list_head	unreg_list;
 	struct list_head	close_list;
+	struct list_head	ptype_all;
+	struct list_head	ptype_specific;
 
 	struct {
 		struct list_head upper;
diff --git a/net/core/dev.c b/net/core/dev.c
index 7f028d441e9..1d564d68e31 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -371,9 +371,10 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
 static inline struct list_head *ptype_head(const struct packet_type *pt)
 {
 	if (pt->type == htons(ETH_P_ALL))
-		return &ptype_all;
+		return pt->dev ? &pt->dev->ptype_all : &ptype_all;
 	else
-		return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
+		return pt->dev ? &pt->dev->ptype_specific :
+				 &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
 }
 
 /**
@@ -1734,6 +1735,23 @@ static inline int deliver_skb(struct sk_buff *skb,
 	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 }
 
+static inline void deliver_ptype_list_skb(struct sk_buff *skb,
+					  struct packet_type **pt,
+					  struct net_device *dev, __be16 type,
+					  struct list_head *ptype_list)
+{
+	struct packet_type *ptype, *pt_prev = *pt;
+
+	list_for_each_entry_rcu(ptype, ptype_list, list) {
+		if (ptype->type != type)
+			continue;
+		if (pt_prev)
+			deliver_skb(skb, pt_prev, dev);
+		pt_prev = ptype;
+	}
+	*pt = pt_prev;
+}
+
 static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
 {
 	if (!ptype->af_packet_priv || !skb->sk)
@@ -1757,45 +1775,54 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 	struct packet_type *ptype;
 	struct sk_buff *skb2 = NULL;
 	struct packet_type *pt_prev = NULL;
+	struct list_head *ptype_list = &ptype_all;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ptype, &ptype_all, list) {
+again:
+	list_for_each_entry_rcu(ptype, ptype_list, list) {
 		/* Never send packets back to the socket
 		 * they originated from - MvS (miquels@drinkel.ow.org)
 		 */
-		if ((ptype->dev == dev || !ptype->dev) &&
-		    (!skb_loop_sk(ptype, skb))) {
-			if (pt_prev) {
-				deliver_skb(skb2, pt_prev, skb->dev);
-				pt_prev = ptype;
-				continue;
-			}
+		if (skb_loop_sk(ptype, skb))
+			continue;
 
-			skb2 = skb_clone(skb, GFP_ATOMIC);
-			if (!skb2)
-				break;
+		if (pt_prev) {
+			deliver_skb(skb2, pt_prev, skb->dev);
+			pt_prev = ptype;
+			continue;
+		}
 
-			net_timestamp_set(skb2);
+		/* need to clone skb, done only once */
+		skb2 = skb_clone(skb, GFP_ATOMIC);
+		if (!skb2)
+			goto out_unlock;
 
-			/* skb->nh should be correctly
-			   set by sender, so that the second statement is
-			   just protection against buggy protocols.
-			 */
-			skb_reset_mac_header(skb2);
-
-			if (skb_network_header(skb2) < skb2->data ||
-			    skb_network_header(skb2) > skb_tail_pointer(skb2)) {
-				net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
-						     ntohs(skb2->protocol),
-						     dev->name);
-				skb_reset_network_header(skb2);
-			}
+		net_timestamp_set(skb2);
 
-			skb2->transport_header = skb2->network_header;
-			skb2->pkt_type = PACKET_OUTGOING;
-			pt_prev = ptype;
+		/* skb->nh should be correctly
+		 * set by sender, so that the second statement is
+		 * just protection against buggy protocols.
+		 */
+		skb_reset_mac_header(skb2);
+
+		if (skb_network_header(skb2) < skb2->data ||
+		    skb_network_header(skb2) > skb_tail_pointer(skb2)) {
+			net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
+					     ntohs(skb2->protocol),
+					     dev->name);
+			skb_reset_network_header(skb2);
 		}
+
+		skb2->transport_header = skb2->network_header;
+		skb2->pkt_type = PACKET_OUTGOING;
+		pt_prev = ptype;
+	}
+
+	if (ptype_list == &ptype_all) {
+		ptype_list = &dev->ptype_all;
+		goto again;
 	}
+out_unlock:
 	if (pt_prev)
 		pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
 	rcu_read_unlock();
@@ -2617,7 +2644,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 	unsigned int len;
 	int rc;
 
-	if (!list_empty(&ptype_all))
+	if (!list_empty(&ptype_all) || !list_empty(&dev->ptype_all))
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
@@ -3615,7 +3642,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
 	struct net_device *orig_dev;
-	struct net_device *null_or_dev;
 	bool deliver_exact = false;
 	int ret = NET_RX_DROP;
 	__be16 type;
@@ -3658,11 +3684,15 @@ another_round:
 		goto skip_taps;
 
 	list_for_each_entry_rcu(ptype, &ptype_all, list) {
-		if (!ptype->dev || ptype->dev == skb->dev) {
-			if (pt_prev)
-				ret = deliver_skb(skb, pt_prev, orig_dev);
-			pt_prev = ptype;
-		}
+		if (pt_prev)
+			ret = deliver_skb(skb, pt_prev, orig_dev);
+		pt_prev = ptype;
+	}
+
+	list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) {
+		if (pt_prev)
+			ret = deliver_skb(skb, pt_prev, orig_dev);
+		pt_prev = ptype;
 	}
 
 skip_taps:
@@ -3718,19 +3748,21 @@ ncls:
 		skb->vlan_tci = 0;
 	}
 
+	type = skb->protocol;
+
 	/* deliver only exact match when indicated */
-	null_or_dev = deliver_exact ? skb->dev : NULL;
+	if (likely(!deliver_exact)) {
+		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
+				       &ptype_base[ntohs(type) &
+						   PTYPE_HASH_MASK]);
+	}
 
-	type = skb->protocol;
-	list_for_each_entry_rcu(ptype,
-			&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
-		if (ptype->type == type &&
-		    (ptype->dev == null_or_dev || ptype->dev == skb->dev ||
-		     ptype->dev == orig_dev)) {
-			if (pt_prev)
-				ret = deliver_skb(skb, pt_prev, orig_dev);
-			pt_prev = ptype;
-		}
+	deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
+			       &orig_dev->ptype_specific);
+
+	if (unlikely(skb->dev != orig_dev)) {
+		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
+				       &skb->dev->ptype_specific);
 	}
 
 	if (pt_prev) {
@@ -6579,6 +6611,8 @@ void netdev_run_todo(void)
 
 		/* paranoia */
 		BUG_ON(netdev_refcnt_read(dev));
+		BUG_ON(!list_empty(&dev->ptype_all));
+		BUG_ON(!list_empty(&dev->ptype_specific));
 		WARN_ON(rcu_access_pointer(dev->ip_ptr));
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 		WARN_ON(dev->dn_ptr);
@@ -6761,6 +6795,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	INIT_LIST_HEAD(&dev->adj_list.lower);
 	INIT_LIST_HEAD(&dev->all_adj_list.upper);
 	INIT_LIST_HEAD(&dev->all_adj_list.lower);
+	INIT_LIST_HEAD(&dev->ptype_all);
+	INIT_LIST_HEAD(&dev->ptype_specific);
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
-- 
cgit v1.2.3-70-g09d2


From f262f28c147051e7aa6daaf4fb5996833ffadff4 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Mon, 26 Jan 2015 13:16:27 +0900
Subject: PM / devfreq: event: Add devfreq_event class

This patch adds a new class in devfreq, devfreq_event, which provides
raw data (e.g., memory bus utilization, GPU utilization) for devfreq
governors.

- devfreq_event device : Provides raw data for a governor of a devfreq device
- devfreq device       : Monitors device state and changes frequency/voltage
			of the device using the raw data from its
			devfreq_event device.

A devfreq device dertermines performance states (normally the frequency
and the voltage vlues) based on the results its designtated devfreq governor:
e.g., ondemand, performance, powersave.

In order to give such results required by a devfreq device, the devfreq
governor requires data that indicates the performance requirement given
to the devfreq device. The conventional (previous) implementatino of
devfreq subsystem requires a devfreq device driver to implement its own
mechanism to acquire performance requirement for its governor. However,
there had been issues with such requirements:

1. Although performance requirement of such devices is usually acquired
 from common devices (PMU/PPMU), we do not have any abstract structure to
 represent them properly.
2. Such performance requirement devices (PMU/PPMU) are actual hardware
 pieces that may be represented by Device Tree directly while devfreq device
 itself is a virtual entity that are not considered to be represented by
 Device Tree according to Device Tree folks.

In order to address such issues, a devferq_event device (represented by
this patch) provides a template for device drivers representing
performance monitoring unit, which gives the basic or raw data for
preformance requirement, which in turn, is required by devfreq governors.

The following description explains the feature of two kind of devfreq class:
- devfreq class (existing)
 : devfreq consumer device use raw data from devfreq_event device for
   determining proper current system state and change voltage/frequency
   dynamically using various governors.

- devfreq_event class (new)
 : Provide measured raw data to devfreq device for governor

Cc: MyungJoo Ham <myungjoo.ham@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
[Commit message rewritten & conflict resolved by MyungJoo]
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/Kconfig             |   2 +
 drivers/devfreq/Makefile            |   3 +
 drivers/devfreq/devfreq-event.c     | 494 ++++++++++++++++++++++++++++++++++++
 drivers/devfreq/event/Kconfig       |  25 ++
 drivers/devfreq/event/Makefile      |   2 +
 drivers/devfreq/event/exynos-ppmu.c | 374 +++++++++++++++++++++++++++
 drivers/devfreq/event/exynos-ppmu.h |  93 +++++++
 include/linux/devfreq-event.h       | 196 ++++++++++++++
 8 files changed, 1189 insertions(+)
 create mode 100644 drivers/devfreq/devfreq-event.c
 create mode 100644 drivers/devfreq/event/Kconfig
 create mode 100644 drivers/devfreq/event/Makefile
 create mode 100644 drivers/devfreq/event/exynos-ppmu.c
 create mode 100644 drivers/devfreq/event/exynos-ppmu.h
 create mode 100644 include/linux/devfreq-event.h

(limited to 'include')

diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index 4aab799712b..51dccb3620e 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -97,4 +97,6 @@ config ARM_TEGRA_DEVFREQ
          It reads ACTMON counters of memory controllers and adjusts the
          operating frequencies and voltages with OPP support.
 
+source "drivers/devfreq/event/Kconfig"
+
 endif # PM_DEVFREQ
diff --git a/drivers/devfreq/Makefile b/drivers/devfreq/Makefile
index 0ea991f3a48..9256c35bcce 100644
--- a/drivers/devfreq/Makefile
+++ b/drivers/devfreq/Makefile
@@ -8,3 +8,6 @@ obj-$(CONFIG_DEVFREQ_GOV_USERSPACE)	+= governor_userspace.o
 obj-$(CONFIG_ARM_EXYNOS4_BUS_DEVFREQ)	+= exynos/
 obj-$(CONFIG_ARM_EXYNOS5_BUS_DEVFREQ)	+= exynos/
 obj-$(CONFIG_ARM_TEGRA_DEVFREQ)		+= tegra-devfreq.o
+
+# DEVFREQ Event Drivers
+obj-$(CONFIG_PM_DEVFREQ_EVENT)		+= event/
diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
new file mode 100644
index 00000000000..f304a0289ed
--- /dev/null
+++ b/drivers/devfreq/devfreq-event.c
@@ -0,0 +1,494 @@
+/*
+ * devfreq-event: a framework to provide raw data and events of devfreq devices
+ *
+ * Copyright (C) 2015 Samsung Electronics
+ * Author: Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This driver is based on drivers/devfreq/devfreq.c.
+ */
+
+#include <linux/devfreq-event.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/of.h>
+
+static struct class *devfreq_event_class;
+
+/* The list of all devfreq event list */
+static LIST_HEAD(devfreq_event_list);
+static DEFINE_MUTEX(devfreq_event_list_lock);
+
+#define to_devfreq_event(DEV) container_of(DEV, struct devfreq_event_dev, dev)
+
+/**
+ * devfreq_event_enable_edev() - Enable the devfreq-event dev and increase
+ *				 the enable_count of devfreq-event dev.
+ * @edev	: the devfreq-event device
+ *
+ * Note that this function increase the enable_count and enable the
+ * devfreq-event device. The devfreq-event device should be enabled before
+ * using it by devfreq device.
+ */
+int devfreq_event_enable_edev(struct devfreq_event_dev *edev)
+{
+	int ret = 0;
+
+	if (!edev || !edev->desc)
+		return -EINVAL;
+
+	mutex_lock(&edev->lock);
+	if (edev->desc->ops && edev->desc->ops->enable
+			&& edev->enable_count == 0) {
+		ret = edev->desc->ops->enable(edev);
+		if (ret < 0)
+			goto err;
+	}
+	edev->enable_count++;
+err:
+	mutex_unlock(&edev->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_enable_edev);
+
+/**
+ * devfreq_event_disable_edev() - Disable the devfreq-event dev and decrease
+ *				  the enable_count of the devfreq-event dev.
+ * @edev	: the devfreq-event device
+ *
+ * Note that this function decrease the enable_count and disable the
+ * devfreq-event device. After the devfreq-event device is disabled,
+ * devfreq device can't use the devfreq-event device for get/set/reset
+ * operations.
+ */
+int devfreq_event_disable_edev(struct devfreq_event_dev *edev)
+{
+	int ret = 0;
+
+	if (!edev || !edev->desc)
+		return -EINVAL;
+
+	mutex_lock(&edev->lock);
+	if (edev->enable_count <= 0) {
+		dev_warn(&edev->dev, "unbalanced enable_count\n");
+		ret = -EIO;
+		goto err;
+	}
+
+	if (edev->desc->ops && edev->desc->ops->disable
+			&& edev->enable_count == 1) {
+		ret = edev->desc->ops->disable(edev);
+		if (ret < 0)
+			goto err;
+	}
+	edev->enable_count--;
+err:
+	mutex_unlock(&edev->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_disable_edev);
+
+/**
+ * devfreq_event_is_enabled() - Check whether devfreq-event dev is enabled or
+ *				not.
+ * @edev	: the devfreq-event device
+ *
+ * Note that this function check whether devfreq-event dev is enabled or not.
+ * If return true, the devfreq-event dev is enabeld. If return false, the
+ * devfreq-event dev is disabled.
+ */
+bool devfreq_event_is_enabled(struct devfreq_event_dev *edev)
+{
+	bool enabled = false;
+
+	if (!edev || !edev->desc)
+		return enabled;
+
+	mutex_lock(&edev->lock);
+
+	if (edev->enable_count > 0)
+		enabled = true;
+
+	mutex_unlock(&edev->lock);
+
+	return enabled;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_is_enabled);
+
+/**
+ * devfreq_event_set_event() - Set event to devfreq-event dev to start.
+ * @edev	: the devfreq-event device
+ *
+ * Note that this function set the event to the devfreq-event device to start
+ * for getting the event data which could be various event type.
+ */
+int devfreq_event_set_event(struct devfreq_event_dev *edev)
+{
+	int ret;
+
+	if (!edev || !edev->desc)
+		return -EINVAL;
+
+	if (!edev->desc->ops || !edev->desc->ops->set_event)
+		return -EINVAL;
+
+	if (!devfreq_event_is_enabled(edev))
+		return -EPERM;
+
+	mutex_lock(&edev->lock);
+	ret = edev->desc->ops->set_event(edev);
+	mutex_unlock(&edev->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_set_event);
+
+/**
+ * devfreq_event_get_event() - Get {load|total}_count from devfreq-event dev.
+ * @edev	: the devfreq-event device
+ * @edata	: the calculated data of devfreq-event device
+ *
+ * Note that this function get the calculated event data from devfreq-event dev
+ * after stoping the progress of whole sequence of devfreq-event dev.
+ */
+int devfreq_event_get_event(struct devfreq_event_dev *edev,
+			    struct devfreq_event_data *edata)
+{
+	int ret;
+
+	if (!edev || !edev->desc)
+		return -EINVAL;
+
+	if (!edev->desc->ops || !edev->desc->ops->get_event)
+		return -EINVAL;
+
+	if (!devfreq_event_is_enabled(edev))
+		return -EINVAL;
+
+	edata->total_count = edata->load_count = 0;
+
+	mutex_lock(&edev->lock);
+	ret = edev->desc->ops->get_event(edev, edata);
+	if (ret < 0)
+		edata->total_count = edata->load_count = 0;
+	mutex_unlock(&edev->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_get_event);
+
+/**
+ * devfreq_event_reset_event() - Reset all opeations of devfreq-event dev.
+ * @edev	: the devfreq-event device
+ *
+ * Note that this function stop all operations of devfreq-event dev and reset
+ * the current event data to make the devfreq-event device into initial state.
+ */
+int devfreq_event_reset_event(struct devfreq_event_dev *edev)
+{
+	int ret = 0;
+
+	if (!edev || !edev->desc)
+		return -EINVAL;
+
+	if (!devfreq_event_is_enabled(edev))
+		return -EPERM;
+
+	mutex_lock(&edev->lock);
+	if (edev->desc->ops && edev->desc->ops->reset)
+		ret = edev->desc->ops->reset(edev);
+	mutex_unlock(&edev->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_reset_event);
+
+/**
+ * devfreq_event_get_edev_by_phandle() - Get the devfreq-event dev from
+ *					 devicetree.
+ * @dev		: the pointer to the given device
+ * @index	: the index into list of devfreq-event device
+ *
+ * Note that this function return the pointer of devfreq-event device.
+ */
+struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev,
+						      int index)
+{
+	struct device_node *node;
+	struct devfreq_event_dev *edev;
+
+	if (!dev->of_node) {
+		dev_err(dev, "device does not have a device node entry\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	node = of_parse_phandle(dev->of_node, "devfreq-events", index);
+	if (!node) {
+		dev_err(dev, "failed to get phandle in %s node\n",
+			dev->of_node->full_name);
+		return ERR_PTR(-ENODEV);
+	}
+
+	mutex_lock(&devfreq_event_list_lock);
+	list_for_each_entry(edev, &devfreq_event_list, node) {
+		if (!strcmp(edev->desc->name, node->name))
+			goto out;
+	}
+	edev = NULL;
+out:
+	mutex_unlock(&devfreq_event_list_lock);
+
+	if (!edev) {
+		dev_err(dev, "unable to get devfreq-event device : %s\n",
+			node->name);
+		of_node_put(node);
+		return ERR_PTR(-ENODEV);
+	}
+
+	of_node_put(node);
+
+	return edev;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_get_edev_by_phandle);
+
+/**
+ * devfreq_event_get_edev_count() - Get the count of devfreq-event dev
+ * @dev		: the pointer to the given device
+ *
+ * Note that this function return the count of devfreq-event devices.
+ */
+int devfreq_event_get_edev_count(struct device *dev)
+{
+	int count;
+
+	if (!dev->of_node) {
+		dev_err(dev, "device does not have a device node entry\n");
+		return -EINVAL;
+	}
+
+	count = of_property_count_elems_of_size(dev->of_node, "devfreq-events",
+						sizeof(u32));
+	if (count < 0 ) {
+		dev_err(dev,
+			"failed to get the count of devfreq-event in %s node\n",
+			dev->of_node->full_name);
+		return count;
+	}
+
+	return count;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_get_edev_count);
+
+static void devfreq_event_release_edev(struct device *dev)
+{
+	struct devfreq_event_dev *edev = to_devfreq_event(dev);
+
+	kfree(edev);
+}
+
+/**
+ * devfreq_event_add_edev() - Add new devfreq-event device.
+ * @dev		: the device owning the devfreq-event device being created
+ * @desc	: the devfreq-event device's decriptor which include essential
+ *		  data for devfreq-event device.
+ *
+ * Note that this function add new devfreq-event device to devfreq-event class
+ * list and register the device of the devfreq-event device.
+ */
+struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
+						struct devfreq_event_desc *desc)
+{
+	struct devfreq_event_dev *edev;
+	static atomic_t event_no = ATOMIC_INIT(0);
+	int ret;
+
+	if (!dev || !desc)
+		return ERR_PTR(-EINVAL);
+
+	if (!desc->name || !desc->ops)
+		return ERR_PTR(-EINVAL);
+
+	if (!desc->ops->set_event || !desc->ops->get_event)
+		return ERR_PTR(-EINVAL);
+
+	edev = kzalloc(sizeof(struct devfreq_event_dev), GFP_KERNEL);
+	if (!edev)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&edev->lock);
+	edev->desc = desc;
+	edev->enable_count = 0;
+	edev->dev.parent = dev;
+	edev->dev.class = devfreq_event_class;
+	edev->dev.release = devfreq_event_release_edev;
+
+	dev_set_name(&edev->dev, "event.%d", atomic_inc_return(&event_no) - 1);
+	ret = device_register(&edev->dev);
+	if (ret < 0) {
+		put_device(&edev->dev);
+		return ERR_PTR(ret);
+	}
+	dev_set_drvdata(&edev->dev, edev);
+
+	INIT_LIST_HEAD(&edev->node);
+
+	mutex_lock(&devfreq_event_list_lock);
+	list_add(&edev->node, &devfreq_event_list);
+	mutex_unlock(&devfreq_event_list_lock);
+
+	return edev;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_add_edev);
+
+/**
+ * devfreq_event_remove_edev() - Remove the devfreq-event device registered.
+ * @dev		: the devfreq-event device
+ *
+ * Note that this function remove the registered devfreq-event device.
+ */
+int devfreq_event_remove_edev(struct devfreq_event_dev *edev)
+{
+	if (!edev)
+		return -EINVAL;
+
+	WARN_ON(edev->enable_count);
+
+	mutex_lock(&devfreq_event_list_lock);
+	list_del(&edev->node);
+	mutex_unlock(&devfreq_event_list_lock);
+
+	device_unregister(&edev->dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devfreq_event_remove_edev);
+
+static int devm_devfreq_event_match(struct device *dev, void *res, void *data)
+{
+	struct devfreq_event_dev **r = res;
+
+	if (WARN_ON(!r || !*r))
+		return 0;
+
+	return *r == data;
+}
+
+static void devm_devfreq_event_release(struct device *dev, void *res)
+{
+	devfreq_event_remove_edev(*(struct devfreq_event_dev **)res);
+}
+
+/**
+ * devm_devfreq_event_add_edev() - Resource-managed devfreq_event_add_edev()
+ * @dev		: the device owning the devfreq-event device being created
+ * @desc	: the devfreq-event device's decriptor which include essential
+ *		  data for devfreq-event device.
+ *
+ * Note that this function manages automatically the memory of devfreq-event
+ * device using device resource management and simplify the free operation
+ * for memory of devfreq-event device.
+ */
+struct devfreq_event_dev *devm_devfreq_event_add_edev(struct device *dev,
+						struct devfreq_event_desc *desc)
+{
+	struct devfreq_event_dev **ptr, *edev;
+
+	ptr = devres_alloc(devm_devfreq_event_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	edev = devfreq_event_add_edev(dev, desc);
+	if (IS_ERR(edev)) {
+		devres_free(ptr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	*ptr = edev;
+	devres_add(dev, ptr);
+
+	return edev;
+}
+EXPORT_SYMBOL_GPL(devm_devfreq_event_add_edev);
+
+/**
+ * devm_devfreq_event_remove_edev()- Resource-managed devfreq_event_remove_edev()
+ * @dev		: the device owning the devfreq-event device being created
+ * @edev	: the devfreq-event device
+ *
+ * Note that this function manages automatically the memory of devfreq-event
+ * device using device resource management.
+ */
+void devm_devfreq_event_remove_edev(struct device *dev,
+				struct devfreq_event_dev *edev)
+{
+	WARN_ON(devres_release(dev, devm_devfreq_event_release,
+			       devm_devfreq_event_match, edev));
+}
+EXPORT_SYMBOL_GPL(devm_devfreq_event_remove_edev);
+
+/*
+ * Device attributes for devfreq-event class.
+ */
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct devfreq_event_dev *edev = to_devfreq_event(dev);
+
+	if (!edev || !edev->desc)
+		return -EINVAL;
+
+	return sprintf(buf, "%s\n", edev->desc->name);
+}
+static DEVICE_ATTR_RO(name);
+
+static ssize_t enable_count_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct devfreq_event_dev *edev = to_devfreq_event(dev);
+
+	if (!edev || !edev->desc)
+		return -EINVAL;
+
+	return sprintf(buf, "%d\n", edev->enable_count);
+}
+static DEVICE_ATTR_RO(enable_count);
+
+static struct attribute *devfreq_event_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_enable_count.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(devfreq_event);
+
+static int __init devfreq_event_init(void)
+{
+	devfreq_event_class = class_create(THIS_MODULE, "devfreq-event");
+	if (IS_ERR(devfreq_event_class)) {
+		pr_err("%s: couldn't create class\n", __FILE__);
+		return PTR_ERR(devfreq_event_class);
+	}
+
+	devfreq_event_class->dev_groups = devfreq_event_groups;
+
+	return 0;
+}
+subsys_initcall(devfreq_event_init);
+
+static void __exit devfreq_event_exit(void)
+{
+	class_destroy(devfreq_event_class);
+}
+module_exit(devfreq_event_exit);
+
+MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
+MODULE_DESCRIPTION("DEVFREQ-Event class support");
+MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/event/Kconfig b/drivers/devfreq/event/Kconfig
new file mode 100644
index 00000000000..a11720affc3
--- /dev/null
+++ b/drivers/devfreq/event/Kconfig
@@ -0,0 +1,25 @@
+menuconfig PM_DEVFREQ_EVENT
+	bool "DEVFREQ-Event device Support"
+	help
+	  The devfreq-event device provide the raw data and events which
+	  indicate the current state of devfreq-event device. The provided
+	  data from devfreq-event device is used to monitor the state of
+	  device and determine the suitable size of resource to reduce the
+	  wasted resource.
+
+	  The devfreq-event device can support the various type of events
+	  (e.g., raw data, utilization, latency, bandwidth). The events
+	  may be used by devfreq governor and other subsystem.
+
+if PM_DEVFREQ_EVENT
+
+config DEVFREQ_EVENT_EXYNOS_PPMU
+	bool "EXYNOS PPMU (Platform Performance Monitoring Unit) DEVFREQ event Driver"
+	depends on ARCH_EXYNOS
+	select PM_OPP
+	help
+	  This add the devfreq-event driver for Exynos SoC. It provides PPMU
+	  (Platform Performance Monitoring Unit) counters to estimate the
+	  utilization of each module.
+
+endif # PM_DEVFREQ_EVENT
diff --git a/drivers/devfreq/event/Makefile b/drivers/devfreq/event/Makefile
new file mode 100644
index 00000000000..be146ead79c
--- /dev/null
+++ b/drivers/devfreq/event/Makefile
@@ -0,0 +1,2 @@
+# Exynos DEVFREQ Event Drivers
+obj-$(CONFIG_DEVFREQ_EVENT_EXYNOS_PPMU) += exynos-ppmu.o
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
new file mode 100644
index 00000000000..135be0aada9
--- /dev/null
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -0,0 +1,374 @@
+/*
+ * exynos_ppmu.c - EXYNOS PPMU (Platform Performance Monitoring Unit) support
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author : Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This driver is based on drivers/devfreq/exynos/exynos_ppmu.c
+ */
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/suspend.h>
+#include <linux/devfreq-event.h>
+
+#include "exynos-ppmu.h"
+
+struct exynos_ppmu_data {
+	void __iomem *base;
+	struct clk *clk;
+};
+
+struct exynos_ppmu {
+	struct devfreq_event_dev **edev;
+	struct devfreq_event_desc *desc;
+	unsigned int num_events;
+
+	struct device *dev;
+	struct mutex lock;
+
+	struct exynos_ppmu_data ppmu;
+};
+
+#define PPMU_EVENT(name)			\
+	{ "ppmu-event0-"#name, PPMU_PMNCNT0 },	\
+	{ "ppmu-event1-"#name, PPMU_PMNCNT1 },	\
+	{ "ppmu-event2-"#name, PPMU_PMNCNT2 },	\
+	{ "ppmu-event3-"#name, PPMU_PMNCNT3 }
+
+struct __exynos_ppmu_events {
+	char *name;
+	int id;
+} ppmu_events[] = {
+	/* For Exynos3250, Exynos4 and Exynos5260 */
+	PPMU_EVENT(g3d),
+	PPMU_EVENT(fsys),
+
+	/* For Exynos4 SoCs and Exynos3250 */
+	PPMU_EVENT(dmc0),
+	PPMU_EVENT(dmc1),
+	PPMU_EVENT(cpu),
+	PPMU_EVENT(rightbus),
+	PPMU_EVENT(leftbus),
+	PPMU_EVENT(lcd0),
+	PPMU_EVENT(camif),
+
+	/* Only for Exynos3250 and Exynos5260 */
+	PPMU_EVENT(mfc),
+
+	/* Only for Exynos4 SoCs */
+	PPMU_EVENT(mfc-left),
+	PPMU_EVENT(mfc-right),
+
+	/* Only for Exynos5260 SoCs */
+	PPMU_EVENT(drex0-s0),
+	PPMU_EVENT(drex0-s1),
+	PPMU_EVENT(drex1-s0),
+	PPMU_EVENT(drex1-s1),
+	PPMU_EVENT(eagle),
+	PPMU_EVENT(kfc),
+	PPMU_EVENT(isp),
+	PPMU_EVENT(fimc),
+	PPMU_EVENT(gscl),
+	PPMU_EVENT(mscl),
+	PPMU_EVENT(fimd0x),
+	PPMU_EVENT(fimd1x),
+	{ /* sentinel */ },
+};
+
+static int exynos_ppmu_find_ppmu_id(struct devfreq_event_dev *edev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ppmu_events); i++)
+		if (!strcmp(edev->desc->name, ppmu_events[i].name))
+			return ppmu_events[i].id;
+
+	return -EINVAL;
+}
+
+static int exynos_ppmu_disable(struct devfreq_event_dev *edev)
+{
+	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	u32 pmnc;
+
+	/* Disable all counters */
+	__raw_writel(PPMU_CCNT_MASK |
+		     PPMU_PMCNT0_MASK |
+		     PPMU_PMCNT1_MASK |
+		     PPMU_PMCNT2_MASK |
+		     PPMU_PMCNT3_MASK,
+		     info->ppmu.base + PPMU_CNTENC);
+
+	/* Disable PPMU */
+	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
+	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+
+	return 0;
+}
+
+static int exynos_ppmu_set_event(struct devfreq_event_dev *edev)
+{
+	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int id = exynos_ppmu_find_ppmu_id(edev);
+	u32 pmnc, cntens;
+
+	if (id < 0)
+		return id;
+
+	/* Enable specific counter */
+	cntens = __raw_readl(info->ppmu.base + PPMU_CNTENS);
+	cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
+	__raw_writel(cntens, info->ppmu.base + PPMU_CNTENS);
+
+	/* Set the event of Read/Write data count  */
+	__raw_writel(PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT,
+			info->ppmu.base + PPMU_BEVTxSEL(id));
+
+	/* Reset cycle counter/performance counter and enable PPMU */
+	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	pmnc &= ~(PPMU_PMNC_ENABLE_MASK
+			| PPMU_PMNC_COUNTER_RESET_MASK
+			| PPMU_PMNC_CC_RESET_MASK);
+	pmnc |= (PPMU_ENABLE << PPMU_PMNC_ENABLE_SHIFT);
+	pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT);
+	pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT);
+	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+
+	return 0;
+}
+
+static int exynos_ppmu_get_event(struct devfreq_event_dev *edev,
+				struct devfreq_event_data *edata)
+{
+	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int id = exynos_ppmu_find_ppmu_id(edev);
+	u32 pmnc, cntenc;
+
+	if (id < 0)
+		return -EINVAL;
+
+	/* Disable PPMU */
+	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
+	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+
+	/* Read cycle count */
+	edata->total_count = __raw_readl(info->ppmu.base + PPMU_CCNT);
+
+	/* Read performance count */
+	switch (id) {
+	case PPMU_PMNCNT0:
+	case PPMU_PMNCNT1:
+	case PPMU_PMNCNT2:
+		edata->load_count
+			= __raw_readl(info->ppmu.base + PPMU_PMNCT(id));
+		break;
+	case PPMU_PMNCNT3:
+		edata->load_count =
+			((__raw_readl(info->ppmu.base + PPMU_PMCNT3_HIGH) << 8)
+			| __raw_readl(info->ppmu.base + PPMU_PMCNT3_LOW));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Disable specific counter */
+	cntenc = __raw_readl(info->ppmu.base + PPMU_CNTENC);
+	cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
+	__raw_writel(cntenc, info->ppmu.base + PPMU_CNTENC);
+
+	dev_dbg(&edev->dev, "%s (event: %ld/%ld)\n", edev->desc->name,
+					edata->load_count, edata->total_count);
+
+	return 0;
+}
+
+static struct devfreq_event_ops exynos_ppmu_ops = {
+	.disable = exynos_ppmu_disable,
+	.set_event = exynos_ppmu_set_event,
+	.get_event = exynos_ppmu_get_event,
+};
+
+static int of_get_devfreq_events(struct device_node *np,
+				 struct exynos_ppmu *info)
+{
+	struct devfreq_event_desc *desc;
+	struct device *dev = info->dev;
+	struct device_node *events_np, *node;
+	int i, j, count;
+
+	events_np = of_get_child_by_name(np, "events");
+	if (!events_np) {
+		dev_err(dev,
+			"failed to get child node of devfreq-event devices\n");
+		return -EINVAL;
+	}
+
+	count = of_get_child_count(events_np);
+	desc = devm_kzalloc(dev, sizeof(*desc) * count, GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+	info->num_events = count;
+
+	j = 0;
+	for_each_child_of_node(events_np, node) {
+		for (i = 0; i < ARRAY_SIZE(ppmu_events); i++) {
+			if (!ppmu_events[i].name)
+				continue;
+
+			if (!of_node_cmp(node->name, ppmu_events[i].name))
+				break;
+		}
+
+		if (i == ARRAY_SIZE(ppmu_events)) {
+			dev_warn(dev,
+				"don't know how to configure events : %s\n",
+				node->name);
+			continue;
+		}
+
+		desc[j].ops = &exynos_ppmu_ops;
+		desc[j].driver_data = info;
+
+		of_property_read_string(node, "event-name", &desc[j].name);
+
+		j++;
+
+		of_node_put(node);
+	}
+	info->desc = desc;
+
+	of_node_put(events_np);
+
+	return 0;
+}
+
+static int exynos_ppmu_parse_dt(struct exynos_ppmu *info)
+{
+	struct device *dev = info->dev;
+	struct device_node *np = dev->of_node;
+	int ret = 0;
+
+	if (!np) {
+		dev_err(dev, "failed to find devicetree node\n");
+		return -EINVAL;
+	}
+
+	/* Maps the memory mapped IO to control PPMU register */
+	info->ppmu.base = of_iomap(np, 0);
+	if (IS_ERR_OR_NULL(info->ppmu.base)) {
+		dev_err(dev, "failed to map memory region\n");
+		return -ENOMEM;
+	}
+
+	info->ppmu.clk = devm_clk_get(dev, "ppmu");
+	if (IS_ERR(info->ppmu.clk)) {
+		info->ppmu.clk = NULL;
+		dev_warn(dev, "cannot get PPMU clock\n");
+	}
+
+	ret = of_get_devfreq_events(np, info);
+	if (ret < 0) {
+		dev_err(dev, "failed to parse exynos ppmu dt node\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	iounmap(info->ppmu.base);
+
+	return ret;
+}
+
+static int exynos_ppmu_probe(struct platform_device *pdev)
+{
+	struct exynos_ppmu *info;
+	struct devfreq_event_dev **edev;
+	struct devfreq_event_desc *desc;
+	int i, ret = 0, size;
+
+	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	mutex_init(&info->lock);
+	info->dev = &pdev->dev;
+
+	/* Parse dt data to get resource */
+	ret = exynos_ppmu_parse_dt(info);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"failed to parse devicetree for resource\n");
+		return ret;
+	}
+	desc = info->desc;
+
+	size = sizeof(struct devfreq_event_dev *) * info->num_events;
+	info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+	if (!info->edev) {
+		dev_err(&pdev->dev,
+			"failed to allocate memory devfreq-event devices\n");
+		return -ENOMEM;
+	}
+	edev = info->edev;
+	platform_set_drvdata(pdev, info);
+
+	for (i = 0; i < info->num_events; i++) {
+		edev[i] = devm_devfreq_event_add_edev(&pdev->dev, &desc[i]);
+		if (IS_ERR(edev)) {
+			ret = PTR_ERR(edev);
+			dev_err(&pdev->dev,
+				"failed to add devfreq-event device\n");
+			goto err;
+		}
+	}
+
+	clk_prepare_enable(info->ppmu.clk);
+
+	return 0;
+err:
+	iounmap(info->ppmu.base);
+
+	return ret;
+}
+
+static int exynos_ppmu_remove(struct platform_device *pdev)
+{
+	struct exynos_ppmu *info = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(info->ppmu.clk);
+	iounmap(info->ppmu.base);
+
+	return 0;
+}
+
+static struct of_device_id exynos_ppmu_id_match[] = {
+	{ .compatible = "samsung,exynos-ppmu", },
+	{ /* sentinel */ },
+};
+
+static struct platform_driver exynos_ppmu_driver = {
+	.probe	= exynos_ppmu_probe,
+	.remove	= exynos_ppmu_remove,
+	.driver = {
+		.name	= "exynos-ppmu",
+		.of_match_table = exynos_ppmu_id_match,
+	},
+};
+module_platform_driver(exynos_ppmu_driver);
+
+MODULE_DESCRIPTION("Exynos PPMU(Platform Performance Monitoring Unit) driver");
+MODULE_AUTHOR("Chanwoo Choi <cw00.choi@samsung.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/devfreq/event/exynos-ppmu.h b/drivers/devfreq/event/exynos-ppmu.h
new file mode 100644
index 00000000000..4e831d48c13
--- /dev/null
+++ b/drivers/devfreq/event/exynos-ppmu.h
@@ -0,0 +1,93 @@
+/*
+ * exynos_ppmu.h - EXYNOS PPMU header file
+ *
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ * Author : Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __EXYNOS_PPMU_H__
+#define __EXYNOS_PPMU_H__
+
+enum ppmu_state {
+	PPMU_DISABLE = 0,
+	PPMU_ENABLE,
+};
+
+enum ppmu_counter {
+	PPMU_PMNCNT0 = 0,
+	PPMU_PMNCNT1,
+	PPMU_PMNCNT2,
+	PPMU_PMNCNT3,
+
+	PPMU_PMNCNT_MAX,
+};
+
+enum ppmu_event_type {
+	PPMU_RO_BUSY_CYCLE_CNT	= 0x0,
+	PPMU_WO_BUSY_CYCLE_CNT	= 0x1,
+	PPMU_RW_BUSY_CYCLE_CNT	= 0x2,
+	PPMU_RO_REQUEST_CNT	= 0x3,
+	PPMU_WO_REQUEST_CNT	= 0x4,
+	PPMU_RO_DATA_CNT	= 0x5,
+	PPMU_WO_DATA_CNT	= 0x6,
+	PPMU_RO_LATENCY		= 0x12,
+	PPMU_WO_LATENCY		= 0x16,
+};
+
+enum ppmu_reg {
+	/* PPC control register */
+	PPMU_PMNC		= 0x00,
+	PPMU_CNTENS		= 0x10,
+	PPMU_CNTENC		= 0x20,
+	PPMU_INTENS		= 0x30,
+	PPMU_INTENC		= 0x40,
+	PPMU_FLAG		= 0x50,
+
+	/* Cycle Counter and Performance Event Counter Register */
+	PPMU_CCNT		= 0x100,
+	PPMU_PMCNT0		= 0x110,
+	PPMU_PMCNT1		= 0x120,
+	PPMU_PMCNT2		= 0x130,
+	PPMU_PMCNT3_HIGH	= 0x140,
+	PPMU_PMCNT3_LOW		= 0x150,
+
+	/* Bus Event Generator */
+	PPMU_BEVT0SEL		= 0x1000,
+	PPMU_BEVT1SEL		= 0x1100,
+	PPMU_BEVT2SEL		= 0x1200,
+	PPMU_BEVT3SEL		= 0x1300,
+	PPMU_COUNTER_RESET	= 0x1810,
+	PPMU_READ_OVERFLOW_CNT	= 0x1810,
+	PPMU_READ_UNDERFLOW_CNT	= 0x1814,
+	PPMU_WRITE_OVERFLOW_CNT	= 0x1850,
+	PPMU_WRITE_UNDERFLOW_CNT = 0x1854,
+	PPMU_READ_PENDING_CNT	= 0x1880,
+	PPMU_WRITE_PENDING_CNT	= 0x1884
+};
+
+/* PMNC register */
+#define PPMU_PMNC_CC_RESET_SHIFT	2
+#define PPMU_PMNC_COUNTER_RESET_SHIFT	1
+#define PPMU_PMNC_ENABLE_SHIFT		0
+#define PPMU_PMNC_START_MODE_MASK	BIT(16)
+#define PPMU_PMNC_CC_DIVIDER_MASK	BIT(3)
+#define PPMU_PMNC_CC_RESET_MASK		BIT(2)
+#define PPMU_PMNC_COUNTER_RESET_MASK	BIT(1)
+#define PPMU_PMNC_ENABLE_MASK		BIT(0)
+
+/* CNTENS/CNTENC/INTENS/INTENC/FLAG register */
+#define PPMU_CCNT_MASK			BIT(31)
+#define PPMU_PMCNT3_MASK		BIT(3)
+#define PPMU_PMCNT2_MASK		BIT(2)
+#define PPMU_PMCNT1_MASK		BIT(1)
+#define PPMU_PMCNT0_MASK		BIT(0)
+
+/* PPMU_PMNCTx/PPMU_BETxSEL registers */
+#define PPMU_PMNCT(x)			(PPMU_PMCNT0 + (0x10 * x))
+#define PPMU_BEVTxSEL(x)		(PPMU_BEVT0SEL + (0x100 * x))
+
+#endif /* __EXYNOS_PPMU_H__ */
diff --git a/include/linux/devfreq-event.h b/include/linux/devfreq-event.h
new file mode 100644
index 00000000000..602fbbfcfee
--- /dev/null
+++ b/include/linux/devfreq-event.h
@@ -0,0 +1,196 @@
+/*
+ * devfreq-event: a framework to provide raw data and events of devfreq devices
+ *
+ * Copyright (C) 2014 Samsung Electronics
+ * Author: Chanwoo Choi <cw00.choi@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_DEVFREQ_EVENT_H__
+#define __LINUX_DEVFREQ_EVENT_H__
+
+#include <linux/device.h>
+
+/**
+ * struct devfreq_event_dev - the devfreq-event device
+ *
+ * @node	: Contain the devfreq-event device that have been registered.
+ * @dev		: the device registered by devfreq-event class. dev.parent is
+ *		  the device using devfreq-event.
+ * @lock	: a mutex to protect accessing devfreq-event.
+ * @enable_count: the number of enable function have been called.
+ * @desc	: the description for devfreq-event device.
+ *
+ * This structure contains devfreq-event device information.
+ */
+struct devfreq_event_dev {
+	struct list_head node;
+
+	struct device dev;
+	struct mutex lock;
+	u32 enable_count;
+
+	const struct devfreq_event_desc *desc;
+};
+
+/**
+ * struct devfreq_event_data - the devfreq-event data
+ *
+ * @load_count	: load count of devfreq-event device for the given period.
+ * @total_count	: total count of devfreq-event device for the given period.
+ *		  each count may represent a clock cycle, a time unit
+ *		  (ns/us/...), or anything the device driver wants.
+ *		  Generally, utilization is load_count / total_count.
+ *
+ * This structure contains the data of devfreq-event device for polling period.
+ */
+struct devfreq_event_data {
+	unsigned long load_count;
+	unsigned long total_count;
+};
+
+/**
+ * struct devfreq_event_ops - the operations of devfreq-event device
+ *
+ * @enable	: Enable the devfreq-event device.
+ * @disable	: Disable the devfreq-event device.
+ * @reset	: Reset all setting of the devfreq-event device.
+ * @set_event	: Set the specific event type for the devfreq-event device.
+ * @get_event	: Get the result of the devfreq-event devie with specific
+ *		  event type.
+ *
+ * This structure contains devfreq-event device operations which can be
+ * implemented by devfreq-event device drivers.
+ */
+struct devfreq_event_ops {
+	/* Optional functions */
+	int (*enable)(struct devfreq_event_dev *edev);
+	int (*disable)(struct devfreq_event_dev *edev);
+	int (*reset)(struct devfreq_event_dev *edev);
+
+	/* Mandatory functions */
+	int (*set_event)(struct devfreq_event_dev *edev);
+	int (*get_event)(struct devfreq_event_dev *edev,
+			 struct devfreq_event_data *edata);
+};
+
+/**
+ * struct devfreq_event_desc - the descriptor of devfreq-event device
+ *
+ * @name	: the name of devfreq-event device.
+ * @driver_data	: the private data for devfreq-event driver.
+ * @ops		: the operation to control devfreq-event device.
+ *
+ * Each devfreq-event device is described with a this structure.
+ * This structure contains the various data for devfreq-event device.
+ */
+struct devfreq_event_desc {
+	const char *name;
+	void *driver_data;
+
+	struct devfreq_event_ops *ops;
+};
+
+#if defined(CONFIG_PM_DEVFREQ_EVENT)
+extern int devfreq_event_enable_edev(struct devfreq_event_dev *edev);
+extern int devfreq_event_disable_edev(struct devfreq_event_dev *edev);
+extern bool devfreq_event_is_enabled(struct devfreq_event_dev *edev);
+extern int devfreq_event_set_event(struct devfreq_event_dev *edev);
+extern int devfreq_event_get_event(struct devfreq_event_dev *edev,
+				struct devfreq_event_data *edata);
+extern int devfreq_event_reset_event(struct devfreq_event_dev *edev);
+extern struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
+				struct device *dev, int index);
+extern int devfreq_event_get_edev_count(struct device *dev);
+extern struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
+				struct devfreq_event_desc *desc);
+extern int devfreq_event_remove_edev(struct devfreq_event_dev *edev);
+extern struct devfreq_event_dev *devm_devfreq_event_add_edev(struct device *dev,
+				struct devfreq_event_desc *desc);
+extern void devm_devfreq_event_remove_edev(struct device *dev,
+				struct devfreq_event_dev *edev);
+static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev)
+{
+	return edev->desc->driver_data;
+}
+#else
+static inline int devfreq_event_enable_edev(struct devfreq_event_dev *edev)
+{
+	return -EINVAL;
+}
+
+static inline int devfreq_event_disable_edev(struct devfreq_event_dev *edev)
+{
+	return -EINVAL;
+}
+
+static inline bool devfreq_event_is_enabled(struct devfreq_event_dev *edev)
+{
+	return false;
+}
+
+static inline int devfreq_event_set_event(struct devfreq_event_dev *edev)
+{
+	return -EINVAL;
+}
+
+static inline int devfreq_event_get_event(struct devfreq_event_dev *edev,
+					struct devfreq_event_data *edata)
+{
+	return -EINVAL;
+}
+
+static inline int devfreq_event_reset_event(struct devfreq_event_dev *edev)
+{
+	return -EINVAL;
+}
+
+static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(
+					struct device *dev, int index)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int devfreq_event_get_edev_count(struct device *dev)
+{
+	return -EINVAL;
+}
+
+static inline struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
+					struct devfreq_event_desc *desc)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int devfreq_event_remove_edev(struct devfreq_event_dev *edev)
+{
+	return -EINVAL;
+}
+
+static inline struct devfreq_event_dev *devm_devfreq_event_add_edev(
+					struct device *dev,
+					struct devfreq_event_desc *desc)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline void devm_devfreq_event_remove_edev(struct device *dev,
+					struct devfreq_event_dev *edev)
+{
+}
+
+static inline void *devfreq_event_get_drvdata(struct devfreq_event_dev *edev)
+{
+	return NULL;
+}
+#endif /* CONFIG_PM_DEVFREQ_EVENT */
+
+#endif /* __LINUX_DEVFREQ_EVENT_H__ */
-- 
cgit v1.2.3-70-g09d2


From 38e478c4489a845a5e8baf7849c286af5fed5b66 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Oct 2014 15:56:21 +0200
Subject: quota: Split ->set_xstate callback into two

Split ->set_xstate callback into two callbacks - one for turning quotas
on (->quota_enable) and one for turning quotas off (->quota_disable). That
way we don't have to pass quotactl command into the callback which seems
cleaner.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/quota.c      | 20 +++++++++++++----
 fs/xfs/xfs_quotaops.c | 59 ++++++++++++++++++++++++++++++++-------------------
 include/linux/quota.h |  3 ++-
 3 files changed, 55 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 6f3856328ee..e2ae2b99e55 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -208,15 +208,26 @@ static int quota_setquota(struct super_block *sb, int type, qid_t id,
 	return sb->s_qcop->set_dqblk(sb, qid, &fdq);
 }
 
-static int quota_setxstate(struct super_block *sb, int cmd, void __user *addr)
+static int quota_enable(struct super_block *sb, void __user *addr)
 {
 	__u32 flags;
 
 	if (copy_from_user(&flags, addr, sizeof(flags)))
 		return -EFAULT;
-	if (!sb->s_qcop->set_xstate)
+	if (!sb->s_qcop->quota_enable)
 		return -ENOSYS;
-	return sb->s_qcop->set_xstate(sb, flags, cmd);
+	return sb->s_qcop->quota_enable(sb, flags);
+}
+
+static int quota_disable(struct super_block *sb, void __user *addr)
+{
+	__u32 flags;
+
+	if (copy_from_user(&flags, addr, sizeof(flags)))
+		return -EFAULT;
+	if (!sb->s_qcop->quota_disable)
+		return -ENOSYS;
+	return sb->s_qcop->quota_disable(sb, flags);
 }
 
 static int quota_getxstate(struct super_block *sb, void __user *addr)
@@ -447,8 +458,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 			return -ENOSYS;
 		return sb->s_qcop->quota_sync(sb, type);
 	case Q_XQUOTAON:
+		return quota_enable(sb, addr);
 	case Q_XQUOTAOFF:
-		return quota_setxstate(sb, cmd, addr);
+		return quota_disable(sb, addr);
 	case Q_XQUOTARM:
 		return quota_rmxquota(sb, addr);
 	case Q_XGETQSTAT:
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index a226203fa46..6923905ab33 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -64,19 +64,10 @@ xfs_fs_get_xstatev(
 	return xfs_qm_scall_getqstatv(mp, fqs);
 }
 
-STATIC int
-xfs_fs_set_xstate(
-	struct super_block	*sb,
-	unsigned int		uflags,
-	int			op)
+static unsigned int
+xfs_quota_flags(unsigned int uflags)
 {
-	struct xfs_mount	*mp = XFS_M(sb);
-	unsigned int		flags = 0;
-
-	if (sb->s_flags & MS_RDONLY)
-		return -EROFS;
-	if (!XFS_IS_QUOTA_RUNNING(mp))
-		return -ENOSYS;
+	unsigned int flags = 0;
 
 	if (uflags & FS_QUOTA_UDQ_ACCT)
 		flags |= XFS_UQUOTA_ACCT;
@@ -91,16 +82,39 @@ xfs_fs_set_xstate(
 	if (uflags & FS_QUOTA_PDQ_ENFD)
 		flags |= XFS_PQUOTA_ENFD;
 
-	switch (op) {
-	case Q_XQUOTAON:
-		return xfs_qm_scall_quotaon(mp, flags);
-	case Q_XQUOTAOFF:
-		if (!XFS_IS_QUOTA_ON(mp))
-			return -EINVAL;
-		return xfs_qm_scall_quotaoff(mp, flags);
-	}
+	return flags;
+}
+
+STATIC int
+xfs_quota_enable(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb->s_flags & MS_RDONLY)
+		return -EROFS;
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+
+	return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags));
+}
+
+STATIC int
+xfs_quota_disable(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb->s_flags & MS_RDONLY)
+		return -EROFS;
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -EINVAL;
 
-	return -EINVAL;
+	return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags));
 }
 
 STATIC int
@@ -166,7 +180,8 @@ xfs_fs_set_dqblk(
 const struct quotactl_ops xfs_quotactl_operations = {
 	.get_xstatev		= xfs_fs_get_xstatev,
 	.get_xstate		= xfs_fs_get_xstate,
-	.set_xstate		= xfs_fs_set_xstate,
+	.quota_enable		= xfs_quota_enable,
+	.quota_disable		= xfs_quota_disable,
 	.rm_xquota		= xfs_fs_rm_xquota,
 	.get_dqblk		= xfs_fs_get_dqblk,
 	.set_dqblk		= xfs_fs_set_dqblk,
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 227f37f463c..4da497b807c 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -371,13 +371,14 @@ struct quotactl_ops {
 	int (*quota_on)(struct super_block *, int, int, struct path *);
 	int (*quota_on_meta)(struct super_block *, int, int);
 	int (*quota_off)(struct super_block *, int);
+	int (*quota_enable)(struct super_block *, unsigned int);
+	int (*quota_disable)(struct super_block *, unsigned int);
 	int (*quota_sync)(struct super_block *, int);
 	int (*get_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*set_info)(struct super_block *, int, struct if_dqinfo *);
 	int (*get_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
 	int (*set_dqblk)(struct super_block *, struct kqid, struct qc_dqblk *);
 	int (*get_xstate)(struct super_block *, struct fs_quota_stat *);
-	int (*set_xstate)(struct super_block *, unsigned int, int);
 	int (*get_xstatev)(struct super_block *, struct fs_quota_statv *);
 	int (*rm_xquota)(struct super_block *, unsigned int);
 };
-- 
cgit v1.2.3-70-g09d2


From d3b863248577504f6eecca2a464d6ddf86b71584 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Oct 2014 16:07:12 +0200
Subject: quota: Wire up ->quota_{enable,disable} callbacks into
 Q_QUOTA{ON,OFF}

Make Q_QUOTAON / Q_QUOTAOFF quotactl call ->quota_enable /
->quota_disable callback when provided. To match current behavior of
ocfs2 & ext4 we make these quotactls turn on / off quota enforcement for
appropriate quota type.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/quota.c         | 31 +++++++++++++++++++++++++++----
 include/linux/quotaops.h |  2 ++
 2 files changed, 29 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index e2ae2b99e55..ce78a70a596 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -66,18 +66,43 @@ static int quota_sync_all(int type)
 	return ret;
 }
 
+unsigned int qtype_enforce_flag(int type)
+{
+	switch (type) {
+	case USRQUOTA:
+		return FS_QUOTA_UDQ_ENFD;
+	case GRPQUOTA:
+		return FS_QUOTA_GDQ_ENFD;
+	case PRJQUOTA:
+		return FS_QUOTA_PDQ_ENFD;
+	}
+	return 0;
+}
+
 static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id,
 		         struct path *path)
 {
-	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta)
+	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta &&
+	    !sb->s_qcop->quota_enable)
 		return -ENOSYS;
 	if (sb->s_qcop->quota_on_meta)
 		return sb->s_qcop->quota_on_meta(sb, type, id);
+	if (sb->s_qcop->quota_enable)
+		return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type));
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	return sb->s_qcop->quota_on(sb, type, id, path);
 }
 
+static int quota_quotaoff(struct super_block *sb, int type)
+{
+	if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable)
+		return -ENOSYS;
+	if (sb->s_qcop->quota_disable)
+		return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type));
+	return sb->s_qcop->quota_off(sb, type);
+}
+
 static int quota_getfmt(struct super_block *sb, int type, void __user *addr)
 {
 	__u32 fmt;
@@ -440,9 +465,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 	case Q_QUOTAON:
 		return quota_quotaon(sb, type, cmd, id, path);
 	case Q_QUOTAOFF:
-		if (!sb->s_qcop->quota_off)
-			return -ENOSYS;
-		return sb->s_qcop->quota_off(sb, type);
+		return quota_quotaoff(sb, type);
 	case Q_GETFMT:
 		return quota_getfmt(sb, type, addr);
 	case Q_GETINFO:
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 29e3455f7d4..ff0b665591d 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -386,4 +386,6 @@ static inline void dquot_release_reservation_block(struct inode *inode,
 	__dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE);
 }
 
+unsigned int qtype_enforce_flag(int type);
+
 #endif /* _LINUX_QUOTAOPS_ */
-- 
cgit v1.2.3-70-g09d2


From 3e2af67e66ff025796af1a8a1fcbb4236304f90c Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 6 Oct 2014 18:40:51 +0200
Subject: quota: Add ->quota_{enable,disable} callbacks for VFS quotas

Add functions which translate ->quota_enable / ->quota_disable calls
into appropriate changes in VFS quota. This will enable filesystems
supporting VFS quota files in system inodes to be controlled via
Q_XQUOTA[ON|OFF] quotactls for better userspace compatibility.

Also provide a vector for quotactl using these functions which can be
used by filesystems with quota files stored in hidden system files.

Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/dquot.c         | 91 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/quotaops.h |  1 +
 2 files changed, 92 insertions(+)

(limited to 'include')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 29eb9dc5728..b47d0c17ea6 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2385,6 +2385,86 @@ out:
 }
 EXPORT_SYMBOL(dquot_quota_on_mount);
 
+static int dquot_quota_enable(struct super_block *sb, unsigned int flags)
+{
+	int ret;
+	int type;
+	struct quota_info *dqopt = sb_dqopt(sb);
+
+	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE))
+		return -ENOSYS;
+	/* Accounting cannot be turned on while fs is mounted */
+	flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT);
+	if (!flags)
+		return -EINVAL;
+	for (type = 0; type < MAXQUOTAS; type++) {
+		if (!(flags & qtype_enforce_flag(type)))
+			continue;
+		/* Can't enforce without accounting */
+		if (!sb_has_quota_usage_enabled(sb, type))
+			return -EINVAL;
+		ret = dquot_enable(dqopt->files[type], type,
+				   dqopt->info[type].dqi_fmt_id,
+				   DQUOT_LIMITS_ENABLED);
+		if (ret < 0)
+			goto out_err;
+	}
+	return 0;
+out_err:
+	/* Backout enforcement enablement we already did */
+	for (type--; type >= 0; type--)  {
+		if (flags & qtype_enforce_flag(type))
+			dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
+	}
+	/* Error code translation for better compatibility with XFS */
+	if (ret == -EBUSY)
+		ret = -EEXIST;
+	return ret;
+}
+
+static int dquot_quota_disable(struct super_block *sb, unsigned int flags)
+{
+	int ret;
+	int type;
+	struct quota_info *dqopt = sb_dqopt(sb);
+
+	if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE))
+		return -ENOSYS;
+	/*
+	 * We don't support turning off accounting via quotactl. In principle
+	 * quota infrastructure can do this but filesystems don't expect
+	 * userspace to be able to do it.
+	 */
+	if (flags &
+		  (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT))
+		return -EOPNOTSUPP;
+
+	/* Filter out limits not enabled */
+	for (type = 0; type < MAXQUOTAS; type++)
+		if (!sb_has_quota_limits_enabled(sb, type))
+			flags &= ~qtype_enforce_flag(type);
+	/* Nothing left? */
+	if (!flags)
+		return -EEXIST;
+	for (type = 0; type < MAXQUOTAS; type++) {
+		if (flags & qtype_enforce_flag(type)) {
+			ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
+			if (ret < 0)
+				goto out_err;
+		}
+	}
+	return 0;
+out_err:
+	/* Backout enforcement disabling we already did */
+	for (type--; type >= 0; type--)  {
+		if (flags & qtype_enforce_flag(type))
+			dquot_enable(dqopt->files[type], type,
+				     dqopt->info[type].dqi_fmt_id,
+				     DQUOT_LIMITS_ENABLED);
+	}
+	return ret;
+}
+
 static inline qsize_t qbtos(qsize_t blocks)
 {
 	return blocks << QIF_DQBLKSIZE_BITS;
@@ -2614,6 +2694,17 @@ const struct quotactl_ops dquot_quotactl_ops = {
 };
 EXPORT_SYMBOL(dquot_quotactl_ops);
 
+const struct quotactl_ops dquot_quotactl_sysfile_ops = {
+	.quota_enable	= dquot_quota_enable,
+	.quota_disable	= dquot_quota_disable,
+	.quota_sync	= dquot_quota_sync,
+	.get_info	= dquot_get_dqinfo,
+	.set_info	= dquot_set_dqinfo,
+	.get_dqblk	= dquot_get_dqblk,
+	.set_dqblk	= dquot_set_dqblk
+};
+EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
+
 static int do_proc_dqstats(struct ctl_table *table, int write,
 		     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index ff0b665591d..df73258cca4 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -166,6 +166,7 @@ static inline bool sb_has_quota_active(struct super_block *sb, int type)
  */
 extern const struct dquot_operations dquot_operations;
 extern const struct quotactl_ops dquot_quotactl_ops;
+extern const struct quotactl_ops dquot_quotactl_sysfile_ops;
 
 #else
 
-- 
cgit v1.2.3-70-g09d2


From aaa3daed156ff3c6acb28c8b18028f8b57d6c91b Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 8 Oct 2014 18:35:31 +0200
Subject: quota: Remove quota_on_meta callback

There are no more users for quota_on_meta callback. Just remove it.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/quota.c      | 5 +----
 include/linux/quota.h | 1 -
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index ce78a70a596..d14a799c778 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -82,11 +82,8 @@ unsigned int qtype_enforce_flag(int type)
 static int quota_quotaon(struct super_block *sb, int type, int cmd, qid_t id,
 		         struct path *path)
 {
-	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_on_meta &&
-	    !sb->s_qcop->quota_enable)
+	if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable)
 		return -ENOSYS;
-	if (sb->s_qcop->quota_on_meta)
-		return sb->s_qcop->quota_on_meta(sb, type, id);
 	if (sb->s_qcop->quota_enable)
 		return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type));
 	if (IS_ERR(path))
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 4da497b807c..0938159d65c 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -369,7 +369,6 @@ struct qc_dqblk {
 /* Operations handling requests from userspace */
 struct quotactl_ops {
 	int (*quota_on)(struct super_block *, int, int, struct path *);
-	int (*quota_on_meta)(struct super_block *, int, int);
 	int (*quota_off)(struct super_block *, int);
 	int (*quota_enable)(struct super_block *, unsigned int);
 	int (*quota_disable)(struct super_block *, unsigned int);
-- 
cgit v1.2.3-70-g09d2


From b10a08194c2b615955dfab2300331a90ae9344c7 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 9 Oct 2014 16:54:13 +0200
Subject: quota: Store maximum space limit in bytes

Currently maximum space limit quota format supports is in blocks however
since we store space limits in bytes, this is somewhat confusing. So
store the maximum limit in bytes as well. Also rename the field to match
the new unit and related inode field to match the new naming scheme.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ocfs2/quota_local.c |  4 ++--
 fs/quota/dquot.c       | 18 ++++--------------
 fs/quota/quota_v1.c    |  4 ++--
 fs/quota/quota_v2.c    | 10 +++++-----
 include/linux/quota.h  |  4 ++--
 5 files changed, 15 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 55f832f553c..89c0b262081 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -701,8 +701,8 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	/* We don't need the lock and we have to acquire quota file locks
 	 * which will later depend on this lock */
 	mutex_unlock(&sb_dqopt(sb)->dqio_mutex);
-	info->dqi_maxblimit = 0x7fffffffffffffffLL;
-	info->dqi_maxilimit = 0x7fffffffffffffffLL;
+	info->dqi_max_spc_limit = 0x7fffffffffffffffLL;
+	info->dqi_max_ino_limit = 0x7fffffffffffffffLL;
 	oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS);
 	if (!oinfo) {
 		mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota"
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index b47d0c17ea6..0ccd4ba3a24 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2465,16 +2465,6 @@ out_err:
 	return ret;
 }
 
-static inline qsize_t qbtos(qsize_t blocks)
-{
-	return blocks << QIF_DQBLKSIZE_BITS;
-}
-
-static inline qsize_t stoqb(qsize_t space)
-{
-	return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
-}
-
 /* Generic routine for getting common part of quota structure */
 static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 {
@@ -2524,13 +2514,13 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di)
 		return -EINVAL;
 
 	if (((di->d_fieldmask & QC_SPC_SOFT) &&
-	     stoqb(di->d_spc_softlimit) > dqi->dqi_maxblimit) ||
+	     di->d_spc_softlimit > dqi->dqi_max_spc_limit) ||
 	    ((di->d_fieldmask & QC_SPC_HARD) &&
-	     stoqb(di->d_spc_hardlimit) > dqi->dqi_maxblimit) ||
+	     di->d_spc_hardlimit > dqi->dqi_max_spc_limit) ||
 	    ((di->d_fieldmask & QC_INO_SOFT) &&
-	     (di->d_ino_softlimit > dqi->dqi_maxilimit)) ||
+	     (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) ||
 	    ((di->d_fieldmask & QC_INO_HARD) &&
-	     (di->d_ino_hardlimit > dqi->dqi_maxilimit)))
+	     (di->d_ino_hardlimit > dqi->dqi_max_ino_limit)))
 		return -ERANGE;
 
 	spin_lock(&dq_data_lock);
diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c
index 469c6848b32..8fe79beced5 100644
--- a/fs/quota/quota_v1.c
+++ b/fs/quota/quota_v1.c
@@ -169,8 +169,8 @@ static int v1_read_file_info(struct super_block *sb, int type)
 	}
 	ret = 0;
 	/* limits are stored as unsigned 32-bit data */
-	dqopt->info[type].dqi_maxblimit = 0xffffffff;
-	dqopt->info[type].dqi_maxilimit = 0xffffffff;
+	dqopt->info[type].dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS;
+	dqopt->info[type].dqi_max_ino_limit = 0xffffffff;
 	dqopt->info[type].dqi_igrace =
 			dqblk.dqb_itime ? dqblk.dqb_itime : MAX_IQ_TIME;
 	dqopt->info[type].dqi_bgrace =
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index 54cac436ac7..9cb10d7197f 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -117,12 +117,12 @@ static int v2_read_file_info(struct super_block *sb, int type)
 	qinfo = info->dqi_priv;
 	if (version == 0) {
 		/* limits are stored as unsigned 32-bit data */
-		info->dqi_maxblimit = 0xffffffff;
-		info->dqi_maxilimit = 0xffffffff;
+		info->dqi_max_spc_limit = 0xffffffffULL << QUOTABLOCK_BITS;
+		info->dqi_max_ino_limit = 0xffffffff;
 	} else {
-		/* used space is stored as unsigned 64-bit value */
-		info->dqi_maxblimit = 0xffffffffffffffffULL;	/* 2^64-1 */
-		info->dqi_maxilimit = 0xffffffffffffffffULL;
+		/* used space is stored as unsigned 64-bit value in bytes */
+		info->dqi_max_spc_limit = 0xffffffffffffffffULL; /* 2^64-1 */
+		info->dqi_max_ino_limit = 0xffffffffffffffffULL;
 	}
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 0938159d65c..d534e8ed308 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -216,8 +216,8 @@ struct mem_dqinfo {
 	unsigned long dqi_flags;
 	unsigned int dqi_bgrace;
 	unsigned int dqi_igrace;
-	qsize_t dqi_maxblimit;
-	qsize_t dqi_maxilimit;
+	qsize_t dqi_max_spc_limit;
+	qsize_t dqi_max_ino_limit;
 	void *dqi_priv;
 };
 
-- 
cgit v1.2.3-70-g09d2


From d4bcef3fbe887ff93b58da4fcf6df1eee416e8fa Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Thu, 29 Jan 2015 20:37:07 +0900
Subject: net: Fix vlan_get_protocol for stacked vlan

vlan_get_protocol() could not get network protocol if a skb has a 802.1ad
vlan tag or multiple vlans, which caused incorrect checksum calculation
in several drivers.

Fix vlan_get_protocol() to retrieve network protocol instead of incorrect
vlan protocol.

As the logic is the same as skb_network_protocol(), create a common helper
function __vlan_get_protocol() and call it from existing functions.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 60 +++++++++++++++++++++++++++++++++++++------------
 net/core/dev.c          | 31 +------------------------
 2 files changed, 47 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 515a35e2a48..960e666c51e 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -472,27 +472,59 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 /**
  * vlan_get_protocol - get protocol EtherType.
  * @skb: skbuff to query
+ * @type: first vlan protocol
+ * @depth: buffer to store length of eth and vlan tags in bytes
  *
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
+static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+					 int *depth)
 {
-	__be16 protocol = 0;
-
-	if (vlan_tx_tag_present(skb) ||
-	     skb->protocol != cpu_to_be16(ETH_P_8021Q))
-		protocol = skb->protocol;
-	else {
-		__be16 proto, *protop;
-		protop = skb_header_pointer(skb, offsetof(struct vlan_ethhdr,
-						h_vlan_encapsulated_proto),
-						sizeof(proto), &proto);
-		if (likely(protop))
-			protocol = *protop;
+	unsigned int vlan_depth = skb->mac_len;
+
+	/* if type is 802.1Q/AD then the header should already be
+	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
+	 * ETH_HLEN otherwise
+	 */
+	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
+		if (vlan_depth) {
+			if (WARN_ON(vlan_depth < VLAN_HLEN))
+				return 0;
+			vlan_depth -= VLAN_HLEN;
+		} else {
+			vlan_depth = ETH_HLEN;
+		}
+		do {
+			struct vlan_hdr *vh;
+
+			if (unlikely(!pskb_may_pull(skb,
+						    vlan_depth + VLAN_HLEN)))
+				return 0;
+
+			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+			type = vh->h_vlan_encapsulated_proto;
+			vlan_depth += VLAN_HLEN;
+		} while (type == htons(ETH_P_8021Q) ||
+			 type == htons(ETH_P_8021AD));
 	}
 
-	return protocol;
+	if (depth)
+		*depth = vlan_depth;
+
+	return type;
+}
+
+/**
+ * vlan_get_protocol - get protocol EtherType.
+ * @skb: skbuff to query
+ *
+ * Returns the EtherType of the packet, regardless of whether it is
+ * vlan encapsulated (normal or hardware accelerated) or not.
+ */
+static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+{
+	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
diff --git a/net/core/dev.c b/net/core/dev.c
index 171420e75b0..c87a2264a02 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2352,7 +2352,6 @@ EXPORT_SYMBOL(skb_checksum_help);
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
 	__be16 type = skb->protocol;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
@@ -2366,35 +2365,7 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 		type = eth->h_proto;
 	}
 
-	/* if skb->protocol is 802.1Q/AD then the header should already be
-	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
-	 * ETH_HLEN otherwise
-	 */
-	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
-		if (vlan_depth) {
-			if (WARN_ON(vlan_depth < VLAN_HLEN))
-				return 0;
-			vlan_depth -= VLAN_HLEN;
-		} else {
-			vlan_depth = ETH_HLEN;
-		}
-		do {
-			struct vlan_hdr *vh;
-
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
-				return 0;
-
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
-			type = vh->h_vlan_encapsulated_proto;
-			vlan_depth += VLAN_HLEN;
-		} while (type == htons(ETH_P_8021Q) ||
-			 type == htons(ETH_P_8021AD));
-	}
-
-	*depth = vlan_depth;
-
-	return type;
+	return __vlan_get_protocol(skb, type, depth);
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From f7697b1602d13ef80779caf23d13fa1511193144 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 30 Jan 2015 23:20:55 -0800
Subject: Bluetooth: Store OOB data present value for each set of remote OOB
 data

Instead of doing complex calculation every time the OOB data is used,
just calculate the OOB data present value and store it with the OOB
data raw values.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/hci_core.c         | 8 ++++++++
 2 files changed, 9 insertions(+)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 1780f1681ec..a37e10f4e2b 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -145,6 +145,7 @@ struct oob_data {
 	struct list_head list;
 	bdaddr_t bdaddr;
 	u8 bdaddr_type;
+	u8 present;
 	u8 hash192[16];
 	u8 rand192[16];
 	u8 hash256[16];
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 5d4ac3fbbc0..f045c062f8f 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2581,9 +2581,15 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	if (hash192 && rand192) {
 		memcpy(data->hash192, hash192, sizeof(data->hash192));
 		memcpy(data->rand192, rand192, sizeof(data->rand192));
+		if (hash256 && rand256)
+			data->present = 0x03;
 	} else {
 		memset(data->hash192, 0, sizeof(data->hash192));
 		memset(data->rand192, 0, sizeof(data->rand192));
+		if (hash256 && rand256)
+			data->present = 0x02;
+		else
+			data->present = 0x00;
 	}
 
 	if (hash256 && rand256) {
@@ -2592,6 +2598,8 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	} else {
 		memset(data->hash256, 0, sizeof(data->hash256));
 		memset(data->rand256, 0, sizeof(data->rand256));
+		if (hash192 && rand192)
+			data->present = 0x01;
 	}
 
 	BT_DBG("%s for %pMR", hdev->name, bdaddr);
-- 
cgit v1.2.3-70-g09d2


From 349c9e3c7341bbab6efbea39acfadeba9ab19f61 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 29 Jan 2015 15:58:09 -0800
Subject: ipv4: icmp: use percpu allocation

Get rid of nr_cpu_ids and use modern percpu allocation.

Note that the sockets themselves are not yet allocated
using NUMA affinity.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h |  3 ++-
 net/ipv4/icmp.c          | 17 ++++++++---------
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 24945cefc4f..7283f4d39ae 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -48,7 +48,8 @@ struct netns_ipv4 {
 	struct hlist_head	*fib_table_hash;
 	struct sock		*fibnl;
 
-	struct sock		**icmp_sk;
+	struct sock  * __percpu	*icmp_sk;
+
 	struct inet_peer_base	*peers;
 	struct tcpm_hash_bucket	*tcp_metrics_hash;
 	unsigned int		tcp_metrics_hash_log;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 36f5584d93c..5e564014a0b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -205,7 +205,7 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
  */
 static struct sock *icmp_sk(struct net *net)
 {
-	return net->ipv4.icmp_sk[smp_processor_id()];
+	return *this_cpu_ptr(net->ipv4.icmp_sk);
 }
 
 static inline struct sock *icmp_xmit_lock(struct net *net)
@@ -1140,8 +1140,8 @@ static void __net_exit icmp_sk_exit(struct net *net)
 	int i;
 
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]);
-	kfree(net->ipv4.icmp_sk);
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
+	free_percpu(net->ipv4.icmp_sk);
 	net->ipv4.icmp_sk = NULL;
 }
 
@@ -1149,9 +1149,8 @@ static int __net_init icmp_sk_init(struct net *net)
 {
 	int i, err;
 
-	net->ipv4.icmp_sk =
-		kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
-	if (net->ipv4.icmp_sk == NULL)
+	net->ipv4.icmp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.icmp_sk)
 		return -ENOMEM;
 
 	for_each_possible_cpu(i) {
@@ -1162,7 +1161,7 @@ static int __net_init icmp_sk_init(struct net *net)
 		if (err < 0)
 			goto fail;
 
-		net->ipv4.icmp_sk[i] = sk;
+		*per_cpu_ptr(net->ipv4.icmp_sk, i) = sk;
 
 		/* Enough space for 2 64K ICMP packets, including
 		 * sk_buff/skb_shared_info struct overhead.
@@ -1203,8 +1202,8 @@ static int __net_init icmp_sk_init(struct net *net)
 
 fail:
 	for_each_possible_cpu(i)
-		inet_ctl_sock_destroy(net->ipv4.icmp_sk[i]);
-	kfree(net->ipv4.icmp_sk);
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
+	free_percpu(net->ipv4.icmp_sk);
 	return err;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 0d32ef8cef9aa8f375e128f78b77caceaa7e8da0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 29 Jan 2015 17:30:12 -0800
Subject: net: sched: fix panic in rate estimators

Doing the following commands on a non idle network device
panics the box instantly, because cpu_bstats gets overwritten
by stats.

tc qdisc add dev eth0 root <your_favorite_qdisc>
... some traffic (one packet is enough) ...
tc qdisc replace dev eth0 root est 1sec 4sec <your_favorite_qdisc>

[  325.355596] BUG: unable to handle kernel paging request at ffff8841dc5a074c
[  325.362609] IP: [<ffffffff81541c9e>] __gnet_stats_copy_basic+0x3e/0x90
[  325.369158] PGD 1fa7067 PUD 0
[  325.372254] Oops: 0000 [#1] SMP
[  325.375514] Modules linked in: ...
[  325.398346] CPU: 13 PID: 14313 Comm: tc Not tainted 3.19.0-smp-DEV #1163
[  325.412042] task: ffff8800793ab5d0 ti: ffff881ff2fa4000 task.ti: ffff881ff2fa4000
[  325.419518] RIP: 0010:[<ffffffff81541c9e>]  [<ffffffff81541c9e>] __gnet_stats_copy_basic+0x3e/0x90
[  325.428506] RSP: 0018:ffff881ff2fa7928  EFLAGS: 00010286
[  325.433824] RAX: 000000000000000c RBX: ffff881ff2fa796c RCX: 000000000000000c
[  325.440988] RDX: ffff8841dc5a0744 RSI: 0000000000000060 RDI: 0000000000000060
[  325.448120] RBP: ffff881ff2fa7948 R08: ffffffff81cd4f80 R09: 0000000000000000
[  325.455268] R10: ffff883ff223e400 R11: 0000000000000000 R12: 000000015cba0744
[  325.462405] R13: ffffffff81cd4f80 R14: ffff883ff223e460 R15: ffff883feea0722c
[  325.469536] FS:  00007f2ee30fa700(0000) GS:ffff88407fa20000(0000) knlGS:0000000000000000
[  325.477630] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  325.483380] CR2: ffff8841dc5a074c CR3: 0000003feeae9000 CR4: 00000000001407e0
[  325.490510] Stack:
[  325.492524]  ffff883feea0722c ffff883fef719dc0 ffff883feea0722c ffff883ff223e4a0
[  325.499990]  ffff881ff2fa79a8 ffffffff815424ee ffff883ff223e49c 000000015cba0744
[  325.507460]  00000000f2fa7978 0000000000000000 ffff881ff2fa79a8 ffff883ff223e4a0
[  325.514956] Call Trace:
[  325.517412]  [<ffffffff815424ee>] gen_new_estimator+0x8e/0x230
[  325.523250]  [<ffffffff815427aa>] gen_replace_estimator+0x4a/0x60
[  325.529349]  [<ffffffff815718ab>] tc_modify_qdisc+0x52b/0x590
[  325.535117]  [<ffffffff8155edd0>] rtnetlink_rcv_msg+0xa0/0x240
[  325.540963]  [<ffffffff8155ed30>] ? __rtnl_unlock+0x20/0x20
[  325.546532]  [<ffffffff8157f811>] netlink_rcv_skb+0xb1/0xc0
[  325.552145]  [<ffffffff8155b355>] rtnetlink_rcv+0x25/0x40
[  325.557558]  [<ffffffff8157f0d8>] netlink_unicast+0x168/0x220
[  325.563317]  [<ffffffff8157f47c>] netlink_sendmsg+0x2ec/0x3e0

Lets play safe and not use an union : percpu 'pointers' are mostly read
anyway, and we have typically few qdiscs per host.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Fixes: 22e0f8b9322c ("net: sched: make bstats per cpu and estimator RCU safe")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 3d282cbb66b..c605d305c57 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -79,6 +79,9 @@ struct Qdisc {
 	struct netdev_queue	*dev_queue;
 
 	struct gnet_stats_rate_est64	rate_est;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue	__percpu *cpu_qstats;
+
 	struct Qdisc		*next_sched;
 	struct sk_buff		*gso_skb;
 	/*
@@ -86,15 +89,9 @@ struct Qdisc {
 	 */
 	unsigned long		state;
 	struct sk_buff_head	q;
-	union {
-		struct gnet_stats_basic_packed bstats;
-		struct gnet_stats_basic_cpu __percpu *cpu_bstats;
-	} __packed;
+	struct gnet_stats_basic_packed bstats;
 	unsigned int		__state;
-	union {
-		struct gnet_stats_queue	qstats;
-		struct gnet_stats_queue	__percpu *cpu_qstats;
-	} __packed;
+	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	int			padded;
 	atomic_t		refcnt;
-- 
cgit v1.2.3-70-g09d2


From 448c7f3830ca283e485aa943279acea6bde8b270 Mon Sep 17 00:00:00 2001
From: Henrik Rydberg <rydberg@bitmath.org>
Date: Sun, 1 Feb 2015 11:25:14 -0800
Subject: Input: MT - add support for balanced slot assignment

Some devices are not fast enough to differentiate between a fast-moving
contact and a new contact. This problem cannot be fully resolved because
information is truly missing, but it is possible to safe-guard against
obvious mistakes by restricting movement with a maximum displacement.

The new problem formulation for dmax > 0 cannot benefit from the speedup
for positive definite matrices, but since the convergence is faster, the
result is about the same. For a handful of contacts, the latency difference
is truly negligible.

Suggested-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Tested-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Henrik Rydberg <rydberg@bitmath.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/input-mt.c                  | 31 ++++++++++++++++++++-----------
 drivers/input/mouse/alps.c                |  2 +-
 drivers/input/mouse/bcm5974.c             |  2 +-
 drivers/input/mouse/cypress_ps2.c         |  2 +-
 drivers/input/mouse/synaptics.c           |  2 +-
 drivers/input/touchscreen/pixcir_i2c_ts.c |  2 +-
 include/linux/input/mt.h                  |  3 ++-
 7 files changed, 27 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c
index fbe29fcb15c..cb150a1dbaf 100644
--- a/drivers/input/input-mt.c
+++ b/drivers/input/input-mt.c
@@ -293,7 +293,7 @@ void input_mt_sync_frame(struct input_dev *dev)
 }
 EXPORT_SYMBOL(input_mt_sync_frame);
 
-static int adjust_dual(int *begin, int step, int *end, int eq)
+static int adjust_dual(int *begin, int step, int *end, int eq, int mu)
 {
 	int f, *p, s, c;
 
@@ -311,9 +311,10 @@ static int adjust_dual(int *begin, int step, int *end, int eq)
 			s = *p;
 
 	c = (f + s + 1) / 2;
-	if (c == 0 || (c > 0 && !eq))
+	if (c == 0 || (c > mu && (!eq || mu > 0)))
 		return 0;
-	if (s < 0)
+	/* Improve convergence for positive matrices by penalizing overcovers */
+	if (s < 0 && mu <= 0)
 		c *= 2;
 
 	for (p = begin; p != end; p += step)
@@ -322,23 +323,24 @@ static int adjust_dual(int *begin, int step, int *end, int eq)
 	return (c < s && s <= 0) || (f >= 0 && f < c);
 }
 
-static void find_reduced_matrix(int *w, int nr, int nc, int nrc)
+static void find_reduced_matrix(int *w, int nr, int nc, int nrc, int mu)
 {
 	int i, k, sum;
 
 	for (k = 0; k < nrc; k++) {
 		for (i = 0; i < nr; i++)
-			adjust_dual(w + i, nr, w + i + nrc, nr <= nc);
+			adjust_dual(w + i, nr, w + i + nrc, nr <= nc, mu);
 		sum = 0;
 		for (i = 0; i < nrc; i += nr)
-			sum += adjust_dual(w + i, 1, w + i + nr, nc <= nr);
+			sum += adjust_dual(w + i, 1, w + i + nr, nc <= nr, mu);
 		if (!sum)
 			break;
 	}
 }
 
 static int input_mt_set_matrix(struct input_mt *mt,
-			       const struct input_mt_pos *pos, int num_pos)
+			       const struct input_mt_pos *pos, int num_pos,
+			       int mu)
 {
 	const struct input_mt_pos *p;
 	struct input_mt_slot *s;
@@ -352,7 +354,7 @@ static int input_mt_set_matrix(struct input_mt *mt,
 		y = input_mt_get_value(s, ABS_MT_POSITION_Y);
 		for (p = pos; p != pos + num_pos; p++) {
 			int dx = x - p->x, dy = y - p->y;
-			*w++ = dx * dx + dy * dy;
+			*w++ = dx * dx + dy * dy - mu;
 		}
 	}
 
@@ -393,17 +395,24 @@ static void input_mt_set_slots(struct input_mt *mt,
  * @slots: the slot assignment to be filled
  * @pos: the position array to match
  * @num_pos: number of positions
+ * @dmax: maximum ABS_MT_POSITION displacement (zero for infinite)
  *
  * Performs a best match against the current contacts and returns
  * the slot assignment list. New contacts are assigned to unused
  * slots.
  *
+ * The assignments are balanced so that all coordinate displacements are
+ * below the euclidian distance dmax. If no such assignment can be found,
+ * some contacts are assigned to unused slots.
+ *
  * Returns zero on success, or negative error in case of failure.
  */
 int input_mt_assign_slots(struct input_dev *dev, int *slots,
-			  const struct input_mt_pos *pos, int num_pos)
+			  const struct input_mt_pos *pos, int num_pos,
+			  int dmax)
 {
 	struct input_mt *mt = dev->mt;
+	int mu = 2 * dmax * dmax;
 	int nrc;
 
 	if (!mt || !mt->red)
@@ -413,8 +422,8 @@ int input_mt_assign_slots(struct input_dev *dev, int *slots,
 	if (num_pos < 1)
 		return 0;
 
-	nrc = input_mt_set_matrix(mt, pos, num_pos);
-	find_reduced_matrix(mt->red, num_pos, nrc / num_pos, nrc);
+	nrc = input_mt_set_matrix(mt, pos, num_pos, mu);
+	find_reduced_matrix(mt->red, num_pos, nrc / num_pos, nrc, mu);
 	input_mt_set_slots(mt, slots, num_pos);
 
 	return 0;
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index f719f28d370..f205b8be2ce 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -435,7 +435,7 @@ static void alps_report_mt_data(struct psmouse *psmouse, int n)
 	struct alps_fields *f = &priv->f;
 	int i, slot[MAX_TOUCHES];
 
-	input_mt_assign_slots(dev, slot, f->mt, n);
+	input_mt_assign_slots(dev, slot, f->mt, n, 0);
 	for (i = 0; i < n; i++)
 		alps_set_slot(dev, slot[i], f->mt[i].x, f->mt[i].y);
 
diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c
index c329cdb0b91..b10709f0461 100644
--- a/drivers/input/mouse/bcm5974.c
+++ b/drivers/input/mouse/bcm5974.c
@@ -564,7 +564,7 @@ static int report_tp_state(struct bcm5974 *dev, int size)
 		dev->index[n++] = &f[i];
 	}
 
-	input_mt_assign_slots(input, dev->slots, dev->pos, n);
+	input_mt_assign_slots(input, dev->slots, dev->pos, n, 0);
 
 	for (i = 0; i < n; i++)
 		report_finger_data(input, dev->slots[i],
diff --git a/drivers/input/mouse/cypress_ps2.c b/drivers/input/mouse/cypress_ps2.c
index 8af34ffe208..9118a1861a4 100644
--- a/drivers/input/mouse/cypress_ps2.c
+++ b/drivers/input/mouse/cypress_ps2.c
@@ -538,7 +538,7 @@ static void cypress_process_packet(struct psmouse *psmouse, bool zero_pkt)
 		pos[i].y = contact->y;
 	}
 
-	input_mt_assign_slots(input, slots, pos, n);
+	input_mt_assign_slots(input, slots, pos, n, 0);
 
 	for (i = 0; i < n; i++) {
 		contact = &report_data.contacts[i];
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index f89de8971bf..a3692e3b7ca 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -809,7 +809,7 @@ static void synaptics_report_mt_data(struct psmouse *psmouse,
 		pos[i].y = synaptics_invert_y(hw[i]->y);
 	}
 
-	input_mt_assign_slots(dev, slot, pos, nsemi);
+	input_mt_assign_slots(dev, slot, pos, nsemi, 0);
 
 	for (i = 0; i < nsemi; i++) {
 		input_mt_slot(dev, slot[i]);
diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c
index 4fb5537fdd4..2c210714731 100644
--- a/drivers/input/touchscreen/pixcir_i2c_ts.c
+++ b/drivers/input/touchscreen/pixcir_i2c_ts.c
@@ -126,7 +126,7 @@ static void pixcir_ts_report(struct pixcir_i2c_ts_data *ts,
 			pos[i].y = touch->y;
 		}
 
-		input_mt_assign_slots(ts->input, slots, pos, n);
+		input_mt_assign_slots(ts->input, slots, pos, n, 0);
 	}
 
 	for (i = 0; i < n; i++) {
diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h
index f583ff63977..d7188de4db9 100644
--- a/include/linux/input/mt.h
+++ b/include/linux/input/mt.h
@@ -119,7 +119,8 @@ struct input_mt_pos {
 };
 
 int input_mt_assign_slots(struct input_dev *dev, int *slots,
-			  const struct input_mt_pos *pos, int num_pos);
+			  const struct input_mt_pos *pos, int num_pos,
+			  int dmax);
 
 int input_mt_get_slot_by_key(struct input_dev *dev, int key);
 
-- 
cgit v1.2.3-70-g09d2


From 00845eb968ead28007338b2bb852b8beef816583 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 1 Feb 2015 12:23:32 -0800
Subject: sched: don't cause task state changes in nested sleep debugging
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8eb23b9f35aa ("sched: Debug nested sleeps") added code to report
on nested sleep conditions, which we generally want to avoid because the
inner sleeping operation can re-set the thread state to TASK_RUNNING,
but that will then cause the outer sleep loop not actually sleep when it
calls schedule.

However, that's actually valid traditional behavior, with the inner
sleep being some fairly rare case (like taking a sleeping lock that
normally doesn't actually need to sleep).

And the debug code would actually change the state of the task to
TASK_RUNNING internally, which makes that kind of traditional and
working code not work at all, because now the nested sleep doesn't just
sometimes cause the outer one to not block, but will cause it to happen
every time.

In particular, it will cause the cardbus kernel daemon (pccardd) to
basically busy-loop doing scheduling, converting a laptop into a heater,
as reported by Bruno Prémont.  But there may be other legacy uses of
that nested sleep model in other drivers that are also likely to never
get converted to the new model.

This fixes both cases:

 - don't set TASK_RUNNING when the nested condition happens (note: even
   if WARN_ONCE() only _warns_ once, the return value isn't whether the
   warning happened, but whether the condition for the warning was true.
   So despite the warning only happening once, the "if (WARN_ON(..))"
   would trigger for every nested sleep.

 - in the cases where we knowingly disable the warning by using
   "sched_annotate_sleep()", don't change the task state (that is used
   for all core scheduling decisions), instead use '->task_state_change'
   that is used for the debugging decision itself.

(Credit for the second part of the fix goes to Oleg Nesterov: "Can't we
avoid this subtle change in behaviour DEBUG_ATOMIC_SLEEP adds?" with the
suggested change to use 'task_state_change' as part of the test)

Reported-and-bisected-by: Bruno Prémont <bonbons@linux-vserver.org>
Tested-by: Rafael J Wysocki <rjw@rjwysocki.net>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>,
Cc: Ilya Dryomov <ilya.dryomov@inktank.com>,
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Hurley <peter@hurleysoftware.com>,
Cc: Davidlohr Bueso <dave@stgolabs.net>,
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h | 2 +-
 kernel/sched/core.c    | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5449d2f4a1e..64ce58bee6f 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -176,7 +176,7 @@ extern int _cond_resched(void);
  */
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
-# define sched_annotate_sleep()	__set_current_state(TASK_RUNNING)
+# define sched_annotate_sleep()	(current->task_state_change = 0)
 #else
   static inline void ___might_sleep(const char *file, int line,
 				   int preempt_offset) { }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c0accc00566..e628cb11b56 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7292,13 +7292,12 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 	 * since we will exit with TASK_RUNNING make sure we enter with it,
 	 * otherwise we will destroy state.
 	 */
-	if (WARN_ONCE(current->state != TASK_RUNNING,
+	WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
 			"do not call blocking ops when !TASK_RUNNING; "
 			"state=%lx set at [<%p>] %pS\n",
 			current->state,
 			(void *)current->task_state_change,
-			(void *)current->task_state_change))
-		__set_current_state(TASK_RUNNING);
+			(void *)current->task_state_change);
 
 	___might_sleep(file, line, preempt_offset);
 }
-- 
cgit v1.2.3-70-g09d2


From fd979c0132074856975a6e79bc2226b99435ec5b Mon Sep 17 00:00:00 2001
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Date: Fri, 30 Jan 2015 13:45:57 -0800
Subject: perf: provide sysfs_show for struct perf_pmu_events_attr

(struct perf_pmu_events_attr) is defined in include/linux/perf_event.h,
but the only "show" for it is in x86 and contains x86 specific stuff.

Make a generic one for those of us who are just using the event_str.

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 include/linux/perf_event.h |  3 +++
 kernel/events/core.c       | 12 ++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 486e84ccb1f..58f59bdb590 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -897,6 +897,9 @@ struct perf_pmu_events_attr {
 	const char *event_str;
 };
 
+ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
+			      char *page);
+
 #define PMU_EVENT_ATTR(_name, _var, _id, _show)				\
 static struct perf_pmu_events_attr _var = {				\
 	.attr = __ATTR(_name, 0444, _show, NULL),			\
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f2beb..934687f8d51 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8276,6 +8276,18 @@ void __init perf_event_init(void)
 		     != 1024);
 }
 
+ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
+			      char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr =
+		container_of(attr, struct perf_pmu_events_attr, attr);
+
+	if (pmu_attr->event_str)
+		return sprintf(page, "%s\n", pmu_attr->event_str);
+
+	return 0;
+}
+
 static int __init perf_event_sysfs_init(void)
 {
 	struct pmu *pmu;
-- 
cgit v1.2.3-70-g09d2


From f0405b816149665393cc62b9e5082fc2d79714df Mon Sep 17 00:00:00 2001
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Date: Fri, 30 Jan 2015 13:45:58 -0800
Subject: perf: add PMU_EVENT_ATTR_STRING() helper

Helper for constructing static struct perf_pmu_events_attr s.

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 include/linux/perf_event.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 58f59bdb590..1d3631448b9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -906,6 +906,13 @@ static struct perf_pmu_events_attr _var = {				\
 	.id   =  _id,							\
 };
 
+#define PMU_EVENT_ATTR_STRING(_name, _var, _str)			    \
+static struct perf_pmu_events_attr _var = {				    \
+	.attr		= __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \
+	.id		= 0,						    \
+	.event_str	= _str,						    \
+};
+
 #define PMU_FORMAT_ATTR(_name, _format)					\
 static ssize_t								\
 _name##_show(struct device *dev,					\
-- 
cgit v1.2.3-70-g09d2


From bdbbb8527b6f6a358dbcb70dac247034d665b8e4 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 29 Jan 2015 21:35:05 -0800
Subject: ipv4: tcp: get rid of ugly unicast_sock

In commit be9f4a44e7d41 ("ipv4: tcp: remove per net tcp_sock")
I tried to address contention on a socket lock, but the solution
I chose was horrible :

commit 3a7c384ffd57e ("ipv4: tcp: unicast_sock should not land outside
of TCP stack") addressed a selinux regression.

commit 0980e56e506b ("ipv4: tcp: set unicast_sock uc_ttl to -1")
took care of another regression.

commit b5ec8eeac46 ("ipv4: fix ip_send_skb()") fixed another regression.

commit 811230cd85 ("tcp: ipv4: initialize unicast_sock sk_pacing_rate")
was another shot in the dark.

Really, just use a proper socket per cpu, and remove the skb_orphan()
call, to re-enable flow control.

This solves a serious problem with FQ packet scheduler when used in
hostile environments, as we do not want to allocate a flow structure
for every RST packet sent in response to a spoofed packet.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h         |  2 +-
 include/net/netns/ipv4.h |  1 +
 net/ipv4/ip_output.c     | 30 +++---------------------------
 net/ipv4/tcp_ipv4.c      | 37 ++++++++++++++++++++++++++++++++-----
 4 files changed, 37 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/net/ip.h b/include/net/ip.h
index f7cbd703d15..09cf5aebb28 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -181,7 +181,7 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
 	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 24945cefc4f..0ffef1a38ef 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -52,6 +52,7 @@ struct netns_ipv4 {
 	struct inet_peer_base	*peers;
 	struct tcpm_hash_bucket	*tcp_metrics_hash;
 	unsigned int		tcp_metrics_hash_log;
+	struct sock  * __percpu	*tcp_sk;
 	struct netns_frags	frags;
 #ifdef CONFIG_NETFILTER
 	struct xt_table		*iptable_filter;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 38a20a9cca1..c373c0708d9 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1506,24 +1506,8 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 /*
  *	Generic function to send a packet as reply to another packet.
  *	Used to send some TCP resets/acks so far.
- *
- *	Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-	.sk = {
-		.__sk_common = {
-			.skc_refcnt = ATOMIC_INIT(1),
-		},
-		.sk_wmem_alloc	= ATOMIC_INIT(1),
-		.sk_allocation	= GFP_ATOMIC,
-		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
-		.sk_pacing_rate = ~0U,
-	},
-	.pmtudisc	= IP_PMTUDISC_WANT,
-	.uc_ttl		= -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
@@ -1533,9 +1517,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct rtable *rt = skb_rtable(skb);
+	struct net *net = sock_net(sk);
 	struct sk_buff *nskb;
-	struct sock *sk;
-	struct inet_sock *inet;
 	int err;
 
 	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
@@ -1566,15 +1549,11 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 	if (IS_ERR(rt))
 		return;
 
-	inet = &get_cpu_var(unicast_sock);
+	inet_sk(sk)->tos = arg->tos;
 
-	inet->tos = arg->tos;
-	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sock_net_set(sk, net);
-	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
@@ -1590,13 +1569,10 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
-		skb_orphan(nskb);
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
 out:
-	put_cpu_var(unicast_sock);
-
 	ip_rt_put(rt);
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a3f72d7fc06..d22f54482ba 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -683,7 +683,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -767,7 +768,8 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -2428,14 +2430,39 @@ struct proto tcp_prot = {
 };
 EXPORT_SYMBOL(tcp_prot);
 
+static void __net_exit tcp_sk_exit(struct net *net)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+	free_percpu(net->ipv4.tcp_sk);
+}
+
 static int __net_init tcp_sk_init(struct net *net)
 {
+	int res, cpu;
+
+	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.tcp_sk)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, net);
+		if (res)
+			goto fail;
+		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+	}
 	net->ipv4.sysctl_tcp_ecn = 2;
 	return 0;
-}
 
-static void __net_exit tcp_sk_exit(struct net *net)
-{
+fail:
+	tcp_sk_exit(net);
+
+	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
-- 
cgit v1.2.3-70-g09d2


From aafb3e98b27977148c8c86499684f8f5c3decfbb Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Thu, 29 Jan 2015 22:40:11 -0800
Subject: netdev: introduce new NETIF_F_HW_SWITCH_OFFLOAD feature flag for
 switch device offloads

This is a high level feature flag for all switch asic offloads

switch drivers set this flag on switch ports. Logical devices like
bridge, bonds, vxlans can inherit this flag from their slaves/ports.

The patch also adds the flag to NETIF_F_ONE_FOR_ALL, so that it gets
propagated to the upperdevices (bridges and bonds).

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 8e30685affe..7d59dc6ab78 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -66,6 +66,7 @@ enum {
 	NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */
 	NETIF_F_HW_L2FW_DOFFLOAD_BIT,	/* Allow L2 Forwarding in Hardware */
 	NETIF_F_BUSY_POLL_BIT,		/* Busy poll */
+	NETIF_F_HW_SWITCH_OFFLOAD_BIT,  /* HW switch offload */
 
 	/*
 	 * Add your fresh new feature above and remember to update
@@ -124,6 +125,7 @@ enum {
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
 #define NETIF_F_HW_L2FW_DOFFLOAD	__NETIF_F(HW_L2FW_DOFFLOAD)
 #define NETIF_F_BUSY_POLL	__NETIF_F(BUSY_POLL)
+#define NETIF_F_HW_SWITCH_OFFLOAD	__NETIF_F(HW_SWITCH_OFFLOAD)
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
@@ -159,7 +161,9 @@ enum {
  */
 #define NETIF_F_ONE_FOR_ALL	(NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
 				 NETIF_F_SG | NETIF_F_HIGHDMA |		\
-				 NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED)
+				 NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED | \
+				 NETIF_F_HW_SWITCH_OFFLOAD)
+
 /*
  * If one device doesn't support one of these features, then disable it
  * for all in netdev_increment_features.
-- 
cgit v1.2.3-70-g09d2


From add511b38266aa10c1079f9248854e6a415c4dc2 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Thu, 29 Jan 2015 22:40:12 -0800
Subject: bridge: add flags argument to ndo_bridge_setlink and
 ndo_bridge_dellink

bridge flags are needed inside ndo_bridge_setlink/dellink handlers to
avoid another call to parse IFLA_AF_SPEC inside these handlers

This is used later in this series

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c   |  3 ++-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |  2 +-
 drivers/net/ethernet/rocker/rocker.c          |  2 +-
 include/linux/netdevice.h                     |  6 ++++--
 net/bridge/br_netlink.c                       |  4 ++--
 net/bridge/br_private.h                       |  4 ++--
 net/core/rtnetlink.c                          | 10 ++++++----
 7 files changed, 18 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 598c5070c62..efed92c7b73 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4327,7 +4327,8 @@ fw_exit:
 	return status;
 }
 
-static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh)
+static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
+				 u16 flags)
 {
 	struct be_adapter *adapter = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 7bb421bfd84..e4086fea4be 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7786,7 +7786,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 }
 
 static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
-				    struct nlmsghdr *nlh)
+				    struct nlmsghdr *nlh, u16 flags)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 11f4ffcc113..f0d607ca5e7 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -3722,7 +3722,7 @@ skip:
 }
 
 static int rocker_port_bridge_setlink(struct net_device *dev,
-				      struct nlmsghdr *nlh)
+				      struct nlmsghdr *nlh, u16 flags)
 {
 	struct rocker_port *rocker_port = netdev_priv(dev);
 	struct nlattr *protinfo;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3d37c6eb173..16251e96e6a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1154,13 +1154,15 @@ struct net_device_ops {
 						int idx);
 
 	int			(*ndo_bridge_setlink)(struct net_device *dev,
-						      struct nlmsghdr *nlh);
+						      struct nlmsghdr *nlh,
+						      u16 flags);
 	int			(*ndo_bridge_getlink)(struct sk_buff *skb,
 						      u32 pid, u32 seq,
 						      struct net_device *dev,
 						      u32 filter_mask);
 	int			(*ndo_bridge_dellink)(struct net_device *dev,
-						      struct nlmsghdr *nlh);
+						      struct nlmsghdr *nlh,
+						      u16 flags);
 	int			(*ndo_change_carrier)(struct net_device *dev,
 						      bool new_carrier);
 	int			(*ndo_get_phys_port_id)(struct net_device *dev,
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e08b260f33f..088e8020384 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -494,7 +494,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 }
 
 /* Change state and parameters on port. */
-int br_setlink(struct net_device *dev, struct nlmsghdr *nlh)
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 {
 	struct nlattr *protinfo;
 	struct nlattr *afspec;
@@ -550,7 +550,7 @@ out:
 }
 
 /* Delete port information */
-int br_dellink(struct net_device *dev, struct nlmsghdr *nlh)
+int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags)
 {
 	struct nlattr *afspec;
 	struct net_bridge_port *p;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e8e3f368168..de0919975a2 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -819,8 +819,8 @@ extern struct rtnl_link_ops br_link_ops;
 int br_netlink_init(void);
 void br_netlink_fini(void);
 void br_ifinfo_notify(int event, struct net_bridge_port *port);
-int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg);
-int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg);
+int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
+int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
 int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev,
 	       u32 filter_mask);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index fedd7ab4085..673cb4c6f39 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2991,7 +2991,7 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 			goto out;
 		}
 
-		err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
+		err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh, flags);
 		if (err)
 			goto out;
 
@@ -3002,7 +3002,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (!dev->netdev_ops->ndo_bridge_setlink)
 			err = -EOPNOTSUPP;
 		else
-			err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh);
+			err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh,
+								  flags);
 		if (!err) {
 			flags &= ~BRIDGE_FLAGS_SELF;
 
@@ -3064,7 +3065,7 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 			goto out;
 		}
 
-		err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh);
+		err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh, flags);
 		if (err)
 			goto out;
 
@@ -3075,7 +3076,8 @@ static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (!dev->netdev_ops->ndo_bridge_dellink)
 			err = -EOPNOTSUPP;
 		else
-			err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh);
+			err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh,
+								  flags);
 
 		if (!err) {
 			flags &= ~BRIDGE_FLAGS_SELF;
-- 
cgit v1.2.3-70-g09d2


From 8a44dbb202617aa66968ba74fdabf1b654dfe661 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Thu, 29 Jan 2015 22:40:13 -0800
Subject: swdevice: add new apis to set and del bridge port attributes

This patch adds two new api's netdev_switch_port_bridge_setlink
and netdev_switch_port_bridge_dellink to offload bridge port attributes
to switch port

(The names of the apis look odd with 'switch_port_bridge',
but am more inclined to change the prefix of the api to something else.
Will take any suggestions).

The api's look at the NETIF_F_HW_SWITCH_OFFLOAD feature flag to
pass bridge port attributes to the port device.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/switchdev.h   |  37 +++++++++++++++-
 net/switchdev/switchdev.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 146 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index 205e63698da..cfcdac2e5d2 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -43,7 +43,14 @@ int register_netdev_switch_notifier(struct notifier_block *nb);
 int unregister_netdev_switch_notifier(struct notifier_block *nb);
 int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
 				 struct netdev_switch_notifier_info *info);
-
+int netdev_switch_port_bridge_setlink(struct net_device *dev,
+				struct nlmsghdr *nlh, u16 flags);
+int netdev_switch_port_bridge_dellink(struct net_device *dev,
+				struct nlmsghdr *nlh, u16 flags);
+int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
+					       struct nlmsghdr *nlh, u16 flags);
+int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
+					       struct nlmsghdr *nlh, u16 flags);
 #else
 
 static inline int netdev_switch_parent_id_get(struct net_device *dev,
@@ -74,6 +81,34 @@ static inline int call_netdev_switch_notifiers(unsigned long val, struct net_dev
 	return NOTIFY_DONE;
 }
 
+static inline int netdev_switch_port_bridge_setlink(struct net_device *dev,
+						    struct nlmsghdr *nlh,
+						    u16 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int netdev_switch_port_bridge_dellink(struct net_device *dev,
+						    struct nlmsghdr *nlh,
+						    u16 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
+							struct nlmsghdr *nlh,
+							u16 flags)
+{
+	return 0;
+}
+
+static inline int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
+							struct nlmsghdr *nlh,
+							u16 flags)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 22e02f4edd9..8c1e558db11 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -115,3 +115,113 @@ int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev,
 	return err;
 }
 EXPORT_SYMBOL(call_netdev_switch_notifiers);
+
+/**
+ *	netdev_switch_port_bridge_setlink - Notify switch device port of bridge
+ *	port attributes
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge setlink flags
+ *
+ *	Notify switch device port of bridge port attributes
+ */
+int netdev_switch_port_bridge_setlink(struct net_device *dev,
+				      struct nlmsghdr *nlh, u16 flags)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return 0;
+
+	if (!ops->ndo_bridge_setlink)
+		return -EOPNOTSUPP;
+
+	return ops->ndo_bridge_setlink(dev, nlh, flags);
+}
+EXPORT_SYMBOL(netdev_switch_port_bridge_setlink);
+
+/**
+ *	netdev_switch_port_bridge_dellink - Notify switch device port of bridge
+ *	port attribute delete
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge setlink flags
+ *
+ *	Notify switch device port of bridge port attribute delete
+ */
+int netdev_switch_port_bridge_dellink(struct net_device *dev,
+				      struct nlmsghdr *nlh, u16 flags)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return 0;
+
+	if (!ops->ndo_bridge_dellink)
+		return -EOPNOTSUPP;
+
+	return ops->ndo_bridge_dellink(dev, nlh, flags);
+}
+EXPORT_SYMBOL(netdev_switch_port_bridge_dellink);
+
+/**
+ *	ndo_dflt_netdev_switch_port_bridge_setlink - default ndo bridge setlink
+ *						     op for master devices
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge setlink flags
+ *
+ *	Notify master device slaves of bridge port attributes
+ */
+int ndo_dflt_netdev_switch_port_bridge_setlink(struct net_device *dev,
+					       struct nlmsghdr *nlh, u16 flags)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int ret = 0, err = 0;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return ret;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = netdev_switch_port_bridge_setlink(lower_dev, nlh, flags);
+		if (err && err != -EOPNOTSUPP)
+			ret = err;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_setlink);
+
+/**
+ *	ndo_dflt_netdev_switch_port_bridge_dellink - default ndo bridge dellink
+ *						     op for master devices
+ *
+ *	@dev: port device
+ *	@nlh: netlink msg with bridge port attributes
+ *	@flags: bridge dellink flags
+ *
+ *	Notify master device slaves of bridge port attribute deletes
+ */
+int ndo_dflt_netdev_switch_port_bridge_dellink(struct net_device *dev,
+					       struct nlmsghdr *nlh, u16 flags)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+	int ret = 0, err = 0;
+
+	if (!(dev->features & NETIF_F_HW_SWITCH_OFFLOAD))
+		return ret;
+
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		err = netdev_switch_port_bridge_dellink(lower_dev, nlh, flags);
+		if (err && err != -EOPNOTSUPP)
+			ret = err;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(ndo_dflt_netdev_switch_port_bridge_dellink);
-- 
cgit v1.2.3-70-g09d2


From 2d28cfe7aada495f87bb439151e9bcc86998fb6d Mon Sep 17 00:00:00 2001
From: Jakub Pawlowski <jpawlowski@google.com>
Date: Sun, 1 Feb 2015 23:07:54 -0800
Subject: Bluetooth: Add le_scan_restart work for LE scan restarting

Currently there is no way to restart le scan, and it's needed in
service scan method. The way it work: it disable, and then enable le
scan on controller.

During the restart, we must remember when the scan was started, and
it's duration, to later re-schedule the le_scan_disable work, that was
stopped during the stop scan phase.

Signed-off-by: Jakub Pawlowski <jpawlowski@google.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  5 +++
 net/bluetooth/hci_core.c         | 74 ++++++++++++++++++++++++++++++++++++++++
 net/bluetooth/mgmt.c             | 19 ++++++++++-
 3 files changed, 97 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a37e10f4e2b..d3a232be9d9 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -79,6 +79,8 @@ struct discovery_state {
 	s8			rssi;
 	u16			uuid_count;
 	u8			(*uuids)[16];
+	unsigned long		scan_start;
+	unsigned long		scan_duration;
 };
 
 struct hci_conn_hash {
@@ -354,6 +356,7 @@ struct hci_dev {
 	unsigned long		dev_flags;
 
 	struct delayed_work	le_scan_disable;
+	struct delayed_work	le_scan_restart;
 
 	__s8			adv_tx_power;
 	__u8			adv_data[HCI_MAX_AD_LENGTH];
@@ -531,6 +534,8 @@ static inline void hci_discovery_filter_clear(struct hci_dev *hdev)
 	hdev->discovery.uuid_count = 0;
 	kfree(hdev->discovery.uuids);
 	hdev->discovery.uuids = NULL;
+	hdev->discovery.scan_start = 0;
+	hdev->discovery.scan_duration = 0;
 }
 
 bool hci_discovery_active(struct hci_dev *hdev);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index f045c062f8f..3322d3f4c85 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1617,6 +1617,7 @@ static int hci_dev_do_close(struct hci_dev *hdev)
 		cancel_delayed_work(&hdev->service_cache);
 
 	cancel_delayed_work_sync(&hdev->le_scan_disable);
+	cancel_delayed_work_sync(&hdev->le_scan_restart);
 
 	if (test_bit(HCI_MGMT, &hdev->dev_flags))
 		cancel_delayed_work_sync(&hdev->rpa_expired);
@@ -2830,6 +2831,8 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status,
 		return;
 	}
 
+	hdev->discovery.scan_start = 0;
+
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_LE:
 		hci_dev_lock(hdev);
@@ -2869,6 +2872,8 @@ static void le_scan_disable_work(struct work_struct *work)
 
 	BT_DBG("%s", hdev->name);
 
+	cancel_delayed_work_sync(&hdev->le_scan_restart);
+
 	hci_req_init(&req, hdev);
 
 	hci_req_add_le_scan_disable(&req);
@@ -2878,6 +2883,74 @@ static void le_scan_disable_work(struct work_struct *work)
 		BT_ERR("Disable LE scanning request failed: err %d", err);
 }
 
+static void le_scan_restart_work_complete(struct hci_dev *hdev, u8 status,
+					  u16 opcode)
+{
+	unsigned long timeout, duration, scan_start, now;
+
+	BT_DBG("%s", hdev->name);
+
+	if (status) {
+		BT_ERR("Failed to restart LE scan: status %d", status);
+		return;
+	}
+
+	if (!test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks) ||
+	    !hdev->discovery.scan_start)
+		return;
+
+	/* When the scan was started, hdev->le_scan_disable has been queued
+	 * after duration from scan_start. During scan restart this job
+	 * has been canceled, and we need to queue it again after proper
+	 * timeout, to make sure that scan does not run indefinitely.
+	 */
+	duration = hdev->discovery.scan_duration;
+	scan_start = hdev->discovery.scan_start;
+	now = jiffies;
+	if (now - scan_start <= duration) {
+		int elapsed;
+
+		if (now >= scan_start)
+			elapsed = now - scan_start;
+		else
+			elapsed = ULONG_MAX - scan_start + now;
+
+		timeout = duration - elapsed;
+	} else {
+		timeout = 0;
+	}
+	queue_delayed_work(hdev->workqueue,
+			   &hdev->le_scan_disable, timeout);
+}
+
+static void le_scan_restart_work(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev,
+					    le_scan_restart.work);
+	struct hci_request req;
+	struct hci_cp_le_set_scan_enable cp;
+	int err;
+
+	BT_DBG("%s", hdev->name);
+
+	/* If controller is not scanning we are done. */
+	if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+		return;
+
+	hci_req_init(&req, hdev);
+
+	hci_req_add_le_scan_disable(&req);
+
+	memset(&cp, 0, sizeof(cp));
+	cp.enable = LE_SCAN_ENABLE;
+	cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+	hci_req_add(&req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+
+	err = hci_req_run(&req, le_scan_restart_work_complete);
+	if (err)
+		BT_ERR("Restart LE scan request failed: err %d", err);
+}
+
 /* Copy the Identity Address of the controller.
  *
  * If the controller has a public BD_ADDR, then by default use that one.
@@ -2974,6 +3047,7 @@ struct hci_dev *hci_alloc_dev(void)
 	INIT_DELAYED_WORK(&hdev->power_off, hci_power_off);
 	INIT_DELAYED_WORK(&hdev->discov_off, hci_discov_off);
 	INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable_work);
+	INIT_DELAYED_WORK(&hdev->le_scan_restart, le_scan_restart_work);
 
 	skb_queue_head_init(&hdev->rx_q);
 	skb_queue_head_init(&hdev->cmd_q);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ba3b4a5820b..8c2520a7f38 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3896,6 +3896,9 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status,
 
 	hci_discovery_set_state(hdev, DISCOVERY_FINDING);
 
+	/* If the scan involves LE scan, pick proper timeout to schedule
+	 * hdev->le_scan_disable that will stop it.
+	 */
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_LE:
 		timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT);
@@ -3912,9 +3915,23 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status,
 		break;
 	}
 
-	if (timeout)
+	if (timeout) {
+		/* When service discovery is used and the controller has
+		 * a strict duplicate filter, it is important to remember
+		 * the start and duration of the scan. This is required
+		 * for restarting scanning during the discovery phase.
+		 */
+		if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER,
+			     &hdev->quirks) &&
+		    (hdev->discovery.uuid_count > 0 ||
+		     hdev->discovery.rssi != HCI_RSSI_INVALID)) {
+			hdev->discovery.scan_start = jiffies;
+			hdev->discovery.scan_duration = timeout;
+		}
+
 		queue_delayed_work(hdev->workqueue,
 				   &hdev->le_scan_disable, timeout);
+	}
 
 unlock:
 	hci_dev_unlock(hdev);
-- 
cgit v1.2.3-70-g09d2


From 4b0e0ceddf085a89173805cace44cd3c4c9d9d77 Mon Sep 17 00:00:00 2001
From: Jakub Pawlowski <jpawlowski@google.com>
Date: Sun, 1 Feb 2015 23:07:55 -0800
Subject: Bluetooth: Add restarting to service discovery

When using LE_SCAN_FILTER_DUP_ENABLE, some controllers would send
advertising report from each LE device only once. That means that we
don't get any updates on RSSI value, and makes Service Discovery very
slow. This patch adds restarting scan when in Service Discovery, and
device with filtered uuid is found, but it's not in RSSI range to send
event yet. This way if device moves into range, we will quickly get RSSI
update.

Signed-off-by: Jakub Pawlowski <jpawlowski@google.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/mgmt.c             | 53 ++++++++++++++++++++++++++++++++++++----
 2 files changed, 49 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index d3a232be9d9..52863c3e0b1 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1334,6 +1334,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event);
 #define DISCOV_INTERLEAVED_TIMEOUT	5120	/* msec */
 #define DISCOV_INTERLEAVED_INQUIRY_LEN	0x04
 #define DISCOV_BREDR_INQUIRY_LEN	0x08
+#define DISCOV_LE_RESTART_DELAY		msecs_to_jiffies(200)	/* msec */
 
 int mgmt_control(struct sock *sk, struct msghdr *msg, size_t len);
 int mgmt_new_settings(struct hci_dev *hdev);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 8c2520a7f38..9e50b5c09b0 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7262,6 +7262,21 @@ static bool eir_has_uuids(u8 *eir, u16 eir_len, u16 uuid_count, u8 (*uuids)[16])
 	return false;
 }
 
+static void restart_le_scan(struct hci_dev *hdev)
+{
+	/* If controller is not scanning we are done. */
+	if (!test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+		return;
+
+	if (time_after(jiffies + DISCOV_LE_RESTART_DELAY,
+		       hdev->discovery.scan_start +
+		       hdev->discovery.scan_duration))
+		return;
+
+	queue_delayed_work(hdev->workqueue, &hdev->le_scan_restart,
+			   DISCOV_LE_RESTART_DELAY);
+}
+
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 addr_type, u8 *dev_class, s8 rssi, u32 flags,
 		       u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len)
@@ -7284,14 +7299,18 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 
 	/* When using service discovery with a RSSI threshold, then check
 	 * if such a RSSI threshold is specified. If a RSSI threshold has
-	 * been specified, then all results with a RSSI smaller than the
-	 * RSSI threshold will be dropped.
+	 * been specified, and HCI_QUIRK_STRICT_DUPLICATE_FILTER is not set,
+	 * then all results with a RSSI smaller than the RSSI threshold will be
+	 * dropped. If the quirk is set, let it through for further processing,
+	 * as we might need to restart the scan.
 	 *
 	 * For BR/EDR devices (pre 1.2) providing no RSSI during inquiry,
 	 * the results are also dropped.
 	 */
 	if (hdev->discovery.rssi != HCI_RSSI_INVALID &&
-	    (rssi < hdev->discovery.rssi || rssi == HCI_RSSI_INVALID))
+	    (rssi == HCI_RSSI_INVALID ||
+	    (rssi < hdev->discovery.rssi &&
+	     !test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks))))
 		return;
 
 	/* Make sure that the buffer is big enough. The 5 extra bytes
@@ -7326,12 +7345,20 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		 * kept and checking possible scan response data
 		 * will be skipped.
 		 */
-		if (hdev->discovery.uuid_count > 0)
+		if (hdev->discovery.uuid_count > 0) {
 			match = eir_has_uuids(eir, eir_len,
 					      hdev->discovery.uuid_count,
 					      hdev->discovery.uuids);
-		else
+			/* If duplicate filtering does not report RSSI changes,
+			 * then restart scanning to ensure updated result with
+			 * updated RSSI values.
+			 */
+			if (match && test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER,
+					      &hdev->quirks))
+				restart_le_scan(hdev);
+		} else {
 			match = true;
+		}
 
 		if (!match && !scan_rsp_len)
 			return;
@@ -7364,6 +7391,14 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 						     hdev->discovery.uuid_count,
 						     hdev->discovery.uuids))
 				return;
+
+			/* If duplicate filtering does not report RSSI changes,
+			 * then restart scanning to ensure updated result with
+			 * updated RSSI values.
+			 */
+			if (test_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER,
+				     &hdev->quirks))
+				restart_le_scan(hdev);
 		}
 
 		/* Append scan response data to event */
@@ -7377,6 +7412,14 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 			return;
 	}
 
+	/* Validate the reported RSSI value against the RSSI threshold once more
+	 * incase HCI_QUIRK_STRICT_DUPLICATE_FILTER forced a restart of LE
+	 * scanning.
+	 */
+	if (hdev->discovery.rssi != HCI_RSSI_INVALID &&
+	    rssi < hdev->discovery.rssi)
+		return;
+
 	ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len);
 	ev_size = sizeof(*ev) + eir_len + scan_rsp_len;
 
-- 
cgit v1.2.3-70-g09d2


From 92b7952da8279189aad352efbf9f2e7001de9524 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 29 Jan 2015 15:53:51 +0100
Subject: ALSA: Allow to pass the device object to snd_register_device*()

This is a preliminary patch for the further work on embedding struct
device into each sound device instance.  It changes
snd_register_device*() helpers to receive the device object directly
for skipping creating a device there.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/core.h | 14 +++++++-------
 sound/core/hwdep.c   |  3 ++-
 sound/core/pcm.c     |  2 +-
 sound/core/sound.c   | 54 +++++++++++++++++++++++++++++++++-------------------
 4 files changed, 44 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/sound/core.h b/include/sound/core.h
index 1df3f2fe535..39d14234961 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -186,6 +186,7 @@ struct snd_minor {
 	int type;			/* SNDRV_DEVICE_TYPE_XXX */
 	int card;			/* card number */
 	int device;			/* device number */
+	bool created;
 	const struct file_operations *f_ops;	/* file operations */
 	void *private_data;		/* private data for f_ops->open */
 	struct device *dev;		/* device for sysfs */
@@ -206,12 +207,10 @@ extern struct class *sound_class;
 
 void snd_request_card(int card);
 
-int snd_register_device_for_dev(int type, struct snd_card *card,
-				int dev,
+int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
 				const struct file_operations *f_ops,
-				void *private_data,
-				const char *name,
-				struct device *device);
+				void *private_data, struct device *device,
+				struct device *parent, const char *name);
 
 /**
  * snd_register_device - Register the ALSA device file for the card
@@ -236,8 +235,9 @@ static inline int snd_register_device(int type, struct snd_card *card, int dev,
 				      const char *name)
 {
 	return snd_register_device_for_dev(type, card, dev, f_ops,
-					   private_data, name,
-					   snd_card_get_device_link(card));
+					   private_data, NULL,
+					   snd_card_get_device_link(card),
+					   name);
 }
 
 int snd_unregister_device(int type, struct snd_card *card, int dev);
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index 69459e5f712..85096a150ed 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -433,7 +433,8 @@ static int snd_hwdep_dev_register(struct snd_device *device)
 		dev = snd_card_get_device_link(hwdep->card);
 	err = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_HWDEP,
 					  hwdep->card, hwdep->device,
-					  &snd_hwdep_f_ops, hwdep, name, dev);
+					  &snd_hwdep_f_ops, hwdep,
+					  NULL, dev, name);
 	if (err < 0) {
 		dev_err(dev,
 			"unable to register hardware dependent device %i:%i\n",
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index cfc56c80696..dba5180e5b8 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -1115,7 +1115,7 @@ static int snd_pcm_dev_register(struct snd_device *device)
 		err = snd_register_device_for_dev(devtype, pcm->card,
 						  pcm->device,
 						  &snd_pcm_f_ops[cidx],
-						  pcm, str, dev);
+						  pcm, NULL, dev, str);
 		if (err < 0) {
 			list_del(&pcm->list);
 			mutex_unlock(&register_mutex);
diff --git a/sound/core/sound.c b/sound/core/sound.c
index f1333060bf1..ea1af1acdbe 100644
--- a/sound/core/sound.c
+++ b/sound/core/sound.c
@@ -248,8 +248,9 @@ static int snd_kernel_minor(int type, struct snd_card *card, int dev)
  * @dev: the device index
  * @f_ops: the file operations
  * @private_data: user pointer for f_ops->open()
- * @name: the device file name
- * @device: the &struct device to link this new device to
+ * @device: the device to register, NULL to create a new one
+ * @parent: the &struct device to link this new device to (only for device=NULL)
+ * @name: the device file name (only for device=NULL)
  *
  * Registers an ALSA device file for the given card.
  * The operators have to be set in reg parameter.
@@ -258,14 +259,13 @@ static int snd_kernel_minor(int type, struct snd_card *card, int dev)
  */
 int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
 				const struct file_operations *f_ops,
-				void *private_data,
-				const char *name, struct device *device)
+				void *private_data, struct device *device,
+				struct device *parent, const char *name)
 {
 	int minor;
+	int err = 0;
 	struct snd_minor *preg;
 
-	if (snd_BUG_ON(!name))
-		return -EINVAL;
 	preg = kmalloc(sizeof *preg, GFP_KERNEL);
 	if (preg == NULL)
 		return -ENOMEM;
@@ -284,23 +284,32 @@ int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
 		minor = -EBUSY;
 #endif
 	if (minor < 0) {
-		mutex_unlock(&sound_mutex);
-		kfree(preg);
-		return minor;
+		err = minor;
+		goto error;
 	}
-	snd_minors[minor] = preg;
-	preg->dev = device_create(sound_class, device, MKDEV(major, minor),
-				  private_data, "%s", name);
-	if (IS_ERR(preg->dev)) {
-		snd_minors[minor] = NULL;
-		mutex_unlock(&sound_mutex);
-		minor = PTR_ERR(preg->dev);
-		kfree(preg);
-		return minor;
+
+	if (device) {
+		preg->created = false;
+		preg->dev = device;
+		device->devt = MKDEV(major, minor);
+		err = device_add(device);
+	} else {
+		preg->created = true;
+		preg->dev = device_create(sound_class, parent,
+					  MKDEV(major, minor), private_data,
+					  "%s", name);
+		if (IS_ERR(preg->dev))
+			err = PTR_ERR(preg->dev);
 	}
+	if (err < 0)
+		goto error;
 
+	snd_minors[minor] = preg;
+ error:
 	mutex_unlock(&sound_mutex);
-	return 0;
+	if (err < 0)
+		kfree(preg);
+	return err;
 }
 
 EXPORT_SYMBOL(snd_register_device_for_dev);
@@ -337,6 +346,7 @@ static int find_snd_minor(int type, struct snd_card *card, int dev)
 int snd_unregister_device(int type, struct snd_card *card, int dev)
 {
 	int minor;
+	struct snd_minor *preg;
 
 	mutex_lock(&sound_mutex);
 	minor = find_snd_minor(type, card, dev);
@@ -345,7 +355,11 @@ int snd_unregister_device(int type, struct snd_card *card, int dev)
 		return -EINVAL;
 	}
 
-	device_destroy(sound_class, MKDEV(major, minor));
+	preg = snd_minors[minor];
+	if (preg && !preg->created)
+		device_del(preg->dev);
+	else
+		device_destroy(sound_class, MKDEV(major, minor));
 
 	kfree(snd_minors[minor]);
 	snd_minors[minor] = NULL;
-- 
cgit v1.2.3-70-g09d2


From 23c18d4bfd73ee24070849faf98b3ab01263a3c4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 19 Feb 2014 14:30:29 +0100
Subject: ALSA: control: Provide a helper to look for the preferred subdevice

Instead of open-coding the search over the control file loop, provide
a helper function for the preferred subdevice assigned to the current
process.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/control.h | 11 +++++++++--
 sound/core/control.c    | 27 ++++++++++++++++++++++++---
 sound/core/pcm.c        | 15 +++------------
 sound/core/rawmidi.c    | 14 ++------------
 4 files changed, 38 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/sound/control.h b/include/sound/control.h
index 042613938a1..75f3054023f 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -93,12 +93,17 @@ struct snd_kctl_event {
 
 struct pid;
 
+enum {
+	SND_CTL_SUBDEV_PCM,
+	SND_CTL_SUBDEV_RAWMIDI,
+	SND_CTL_SUBDEV_ITEMS,
+};
+
 struct snd_ctl_file {
 	struct list_head list;		/* list of all control files */
 	struct snd_card *card;
 	struct pid *pid;
-	int prefer_pcm_subdevice;
-	int prefer_rawmidi_subdevice;
+	int preferred_subdevice[SND_CTL_SUBDEV_ITEMS];
 	wait_queue_head_t change_sleep;
 	spinlock_t read_lock;
 	struct fasync_struct *fasync;
@@ -138,6 +143,8 @@ int snd_ctl_unregister_ioctl_compat(snd_kctl_ioctl_func_t fcn);
 #define snd_ctl_unregister_ioctl_compat(fcn)
 #endif
 
+int snd_ctl_get_preferred_subdevice(struct snd_card *card, int type);
+
 static inline unsigned int snd_ctl_get_ioffnum(struct snd_kcontrol *kctl, struct snd_ctl_elem_id *id)
 {
 	return id->numid - kctl->id.numid;
diff --git a/sound/core/control.c b/sound/core/control.c
index bb96a467e88..cd246a0bcd5 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -50,7 +50,7 @@ static int snd_ctl_open(struct inode *inode, struct file *file)
 	unsigned long flags;
 	struct snd_card *card;
 	struct snd_ctl_file *ctl;
-	int err;
+	int i, err;
 
 	err = nonseekable_open(inode, file);
 	if (err < 0)
@@ -79,8 +79,8 @@ static int snd_ctl_open(struct inode *inode, struct file *file)
 	init_waitqueue_head(&ctl->change_sleep);
 	spin_lock_init(&ctl->read_lock);
 	ctl->card = card;
-	ctl->prefer_pcm_subdevice = -1;
-	ctl->prefer_rawmidi_subdevice = -1;
+	for (i = 0; i < SND_CTL_SUBDEV_ITEMS; i++)
+		ctl->preferred_subdevice[i] = -1;
 	ctl->pid = get_pid(task_pid(current));
 	file->private_data = ctl;
 	write_lock_irqsave(&card->ctl_files_rwlock, flags);
@@ -1607,6 +1607,27 @@ static int snd_ctl_fasync(int fd, struct file * file, int on)
 	return fasync_helper(fd, file, on, &ctl->fasync);
 }
 
+/* return the preferred subdevice number if already assigned;
+ * otherwise return -1
+ */
+int snd_ctl_get_preferred_subdevice(struct snd_card *card, int type)
+{
+	struct snd_ctl_file *kctl;
+	int subdevice = -1;
+
+	read_lock(&card->ctl_files_rwlock);
+	list_for_each_entry(kctl, &card->ctl_files, list) {
+		if (kctl->pid == task_pid(current)) {
+			subdevice = kctl->preferred_subdevice[type];
+			if (subdevice != -1)
+				break;
+		}
+	}
+	read_unlock(&card->ctl_files_rwlock);
+	return subdevice;
+}
+EXPORT_SYMBOL_GPL(snd_ctl_get_preferred_subdevice);
+
 /*
  * ioctl32 compat
  */
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index dba5180e5b8..1b7c473720f 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -161,7 +161,7 @@ static int snd_pcm_control_ioctl(struct snd_card *card,
 			
 			if (get_user(val, (int __user *)arg))
 				return -EFAULT;
-			control->prefer_pcm_subdevice = val;
+			control->preferred_subdevice[SND_CTL_SUBDEV_PCM] = val;
 			return 0;
 		}
 	}
@@ -901,9 +901,8 @@ int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream,
 	struct snd_pcm_str * pstr;
 	struct snd_pcm_substream *substream;
 	struct snd_pcm_runtime *runtime;
-	struct snd_ctl_file *kctl;
 	struct snd_card *card;
-	int prefer_subdevice = -1;
+	int prefer_subdevice;
 	size_t size;
 
 	if (snd_BUG_ON(!pcm || !rsubstream))
@@ -914,15 +913,7 @@ int snd_pcm_attach_substream(struct snd_pcm *pcm, int stream,
 		return -ENODEV;
 
 	card = pcm->card;
-	read_lock(&card->ctl_files_rwlock);
-	list_for_each_entry(kctl, &card->ctl_files, list) {
-		if (kctl->pid == task_pid(current)) {
-			prefer_subdevice = kctl->prefer_pcm_subdevice;
-			if (prefer_subdevice != -1)
-				break;
-		}
-	}
-	read_unlock(&card->ctl_files_rwlock);
+	prefer_subdevice = snd_ctl_get_preferred_subdevice(card, SND_CTL_SUBDEV_PCM);
 
 	switch (stream) {
 	case SNDRV_PCM_STREAM_PLAYBACK:
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 6fc71a4c8a5..be18162c380 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -369,7 +369,6 @@ static int snd_rawmidi_open(struct inode *inode, struct file *file)
 	struct snd_rawmidi *rmidi;
 	struct snd_rawmidi_file *rawmidi_file = NULL;
 	wait_queue_t wait;
-	struct snd_ctl_file *kctl;
 
 	if ((file->f_flags & O_APPEND) && !(file->f_flags & O_NONBLOCK)) 
 		return -EINVAL;		/* invalid combination */
@@ -413,16 +412,7 @@ static int snd_rawmidi_open(struct inode *inode, struct file *file)
 	init_waitqueue_entry(&wait, current);
 	add_wait_queue(&rmidi->open_wait, &wait);
 	while (1) {
-		subdevice = -1;
-		read_lock(&card->ctl_files_rwlock);
-		list_for_each_entry(kctl, &card->ctl_files, list) {
-			if (kctl->pid == task_pid(current)) {
-				subdevice = kctl->prefer_rawmidi_subdevice;
-				if (subdevice != -1)
-					break;
-			}
-		}
-		read_unlock(&card->ctl_files_rwlock);
+		subdevice = snd_ctl_get_preferred_subdevice(card, SND_CTL_SUBDEV_RAWMIDI);
 		err = rawmidi_open_priv(rmidi, subdevice, fflags, rawmidi_file);
 		if (err >= 0)
 			break;
@@ -862,7 +852,7 @@ static int snd_rawmidi_control_ioctl(struct snd_card *card,
 		
 		if (get_user(val, (int __user *)argp))
 			return -EFAULT;
-		control->prefer_rawmidi_subdevice = val;
+		control->preferred_subdevice[SND_CTL_SUBDEV_RAWMIDI] = val;
 		return 0;
 	}
 	case SNDRV_CTL_IOCTL_RAWMIDI_INFO:
-- 
cgit v1.2.3-70-g09d2


From 4b440be667c6187717c99e4d427119fa415ced29 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 29 Jan 2015 21:32:47 +0100
Subject: ALSA: Add a helper to initialize device

Introduce a new helper function snd_device_initialize() to initialize
the device object for sound devices.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/core.h |  2 ++
 sound/core/init.c    | 23 +++++++++++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'include')

diff --git a/include/sound/core.h b/include/sound/core.h
index 39d14234961..de7a878217d 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -207,6 +207,8 @@ extern struct class *sound_class;
 
 void snd_request_card(int card);
 
+void snd_device_initialize(struct device *dev, struct snd_card *card);
+
 int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
 				const struct file_operations *f_ops,
 				void *private_data, struct device *device,
diff --git a/sound/core/init.c b/sound/core/init.c
index 074875d68c1..96194599e82 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -157,6 +157,29 @@ static int get_slot_from_bitmask(int mask, int (*check)(struct module *, int),
 	return mask; /* unchanged */
 }
 
+/* the default release callback set in snd_device_initialize() below;
+ * this is just NOP for now, as almost all jobs are already done in
+ * dev_free callback of snd_device chain instead.
+ */
+static void default_release(struct device *dev)
+{
+}
+
+/**
+ * snd_device_initialize - Initialize struct device for sound devices
+ * @dev: device to initialize
+ * @card: card to assign, optional
+ */
+void snd_device_initialize(struct device *dev, struct snd_card *card)
+{
+	device_initialize(dev);
+	if (card)
+		dev->parent = &card->card_dev;
+	dev->class = sound_class;
+	dev->release = default_release;
+}
+EXPORT_SYMBOL_GPL(snd_device_initialize);
+
 static int snd_card_do_free(struct snd_card *card);
 static const struct attribute_group *card_dev_attr_groups[];
 
-- 
cgit v1.2.3-70-g09d2


From 0fcd9f4b3c60382205e5819c456aa9ea17b6f20f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 29 Jan 2015 16:41:27 +0100
Subject: ALSA: control: Embed struct device

This patch embeds a struct device for the control device into the card
object and avoid the device creation at registration time.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/core.h |  1 +
 sound/core/control.c | 40 ++++++++++++++++------------------------
 2 files changed, 17 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/include/sound/core.h b/include/sound/core.h
index de7a878217d..4b7e04e85e1 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -109,6 +109,7 @@ struct snd_card {
 								private data */
 	struct list_head devices;	/* devices */
 
+	struct device ctl_dev;		/* control device */
 	unsigned int last_numid;	/* last used numeric ID */
 	struct rw_semaphore controls_rwsem;	/* controls list lock */
 	rwlock_t ctl_files_rwlock;	/* ctl_files list lock */
diff --git a/sound/core/control.c b/sound/core/control.c
index cd246a0bcd5..e214fabbc67 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1660,19 +1660,10 @@ static const struct file_operations snd_ctl_f_ops =
 static int snd_ctl_dev_register(struct snd_device *device)
 {
 	struct snd_card *card = device->device_data;
-	int err, cardnum;
-	char name[16];
 
-	if (snd_BUG_ON(!card))
-		return -ENXIO;
-	cardnum = card->number;
-	if (snd_BUG_ON(cardnum < 0 || cardnum >= SNDRV_CARDS))
-		return -ENXIO;
-	sprintf(name, "controlC%i", cardnum);
-	if ((err = snd_register_device(SNDRV_DEVICE_TYPE_CONTROL, card, -1,
-				       &snd_ctl_f_ops, card, name)) < 0)
-		return err;
-	return 0;
+	return snd_register_device_for_dev(SNDRV_DEVICE_TYPE_CONTROL, card,
+					   -1, &snd_ctl_f_ops, card,
+					   &card->ctl_dev, NULL, NULL);
 }
 
 /*
@@ -1682,13 +1673,6 @@ static int snd_ctl_dev_disconnect(struct snd_device *device)
 {
 	struct snd_card *card = device->device_data;
 	struct snd_ctl_file *ctl;
-	int err, cardnum;
-
-	if (snd_BUG_ON(!card))
-		return -ENXIO;
-	cardnum = card->number;
-	if (snd_BUG_ON(cardnum < 0 || cardnum >= SNDRV_CARDS))
-		return -ENXIO;
 
 	read_lock(&card->ctl_files_rwlock);
 	list_for_each_entry(ctl, &card->ctl_files, list) {
@@ -1697,10 +1681,7 @@ static int snd_ctl_dev_disconnect(struct snd_device *device)
 	}
 	read_unlock(&card->ctl_files_rwlock);
 
-	if ((err = snd_unregister_device(SNDRV_DEVICE_TYPE_CONTROL,
-					 card, -1)) < 0)
-		return err;
-	return 0;
+	return snd_unregister_device(SNDRV_DEVICE_TYPE_CONTROL, card, -1);
 }
 
 /*
@@ -1717,6 +1698,7 @@ static int snd_ctl_dev_free(struct snd_device *device)
 		snd_ctl_remove(card, control);
 	}
 	up_write(&card->controls_rwsem);
+	put_device(&card->ctl_dev);
 	return 0;
 }
 
@@ -1731,10 +1713,20 @@ int snd_ctl_create(struct snd_card *card)
 		.dev_register =	snd_ctl_dev_register,
 		.dev_disconnect = snd_ctl_dev_disconnect,
 	};
+	int err;
 
 	if (snd_BUG_ON(!card))
 		return -ENXIO;
-	return snd_device_new(card, SNDRV_DEV_CONTROL, card, &ops);
+	if (snd_BUG_ON(card->number < 0 || card->number >= SNDRV_CARDS))
+		return -ENXIO;
+
+	snd_device_initialize(&card->ctl_dev, card);
+	dev_set_name(&card->ctl_dev, "controlC%d", card->number);
+
+	err = snd_device_new(card, SNDRV_DEV_CONTROL, card, &ops);
+	if (err < 0)
+		put_device(&card->ctl_dev);
+	return err;
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From 7b46160000197209f7ebca8b92bdbb75795c473f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 29 Jan 2015 17:13:32 +0100
Subject: ALSA: hwdep: Embed struct device

Like the previous patch, this one embeds the device object into hwdep
object.  For a proper object lifecycle, it's freed in the release
callback.

This also allows us to create sysfs entries via passing to the groups
field of the device without explicit function calls.  Since each
driver can see the device and touch its groups field directly, we
don't need to delegate in hwdep core any longer.  So, remove the
groups field from snd_hwdep, and let the user (in this case only
hda_hwdep.c) modify the device groups.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hwdep.h     |  3 +-
 sound/core/hwdep.c        | 82 ++++++++++++++++++-----------------------------
 sound/pci/hda/hda_hwdep.c |  7 ++--
 3 files changed, 38 insertions(+), 54 deletions(-)

(limited to 'include')

diff --git a/include/sound/hwdep.h b/include/sound/hwdep.h
index ae04a3ec9c7..ab9fcb2f97f 100644
--- a/include/sound/hwdep.h
+++ b/include/sound/hwdep.h
@@ -68,8 +68,7 @@ struct snd_hwdep {
 	wait_queue_head_t open_wait;
 	void *private_data;
 	void (*private_free) (struct snd_hwdep *hwdep);
-	struct device *dev;
-	const struct attribute_group **groups;
+	struct device dev;
 
 	struct mutex open_mutex;
 	int used;			/* reference counter */
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index 85096a150ed..506387ba645 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -38,7 +38,6 @@ MODULE_LICENSE("GPL");
 static LIST_HEAD(snd_hwdep_devices);
 static DEFINE_MUTEX(register_mutex);
 
-static int snd_hwdep_free(struct snd_hwdep *hwdep);
 static int snd_hwdep_dev_free(struct snd_device *device);
 static int snd_hwdep_dev_register(struct snd_device *device);
 static int snd_hwdep_dev_disconnect(struct snd_device *device);
@@ -345,6 +344,11 @@ static const struct file_operations snd_hwdep_f_ops =
 	.mmap =		snd_hwdep_mmap,
 };
 
+static void release_hwdep_device(struct device *dev)
+{
+	kfree(container_of(dev, struct snd_hwdep, dev));
+}
+
 /**
  * snd_hwdep_new - create a new hwdep instance
  * @card: the card instance
@@ -378,48 +382,49 @@ int snd_hwdep_new(struct snd_card *card, char *id, int device,
 		dev_err(card->dev, "hwdep: cannot allocate\n");
 		return -ENOMEM;
 	}
+
+	init_waitqueue_head(&hwdep->open_wait);
+	mutex_init(&hwdep->open_mutex);
 	hwdep->card = card;
 	hwdep->device = device;
 	if (id)
 		strlcpy(hwdep->id, id, sizeof(hwdep->id));
+
+	snd_device_initialize(&hwdep->dev, card);
+	hwdep->dev.release = release_hwdep_device;
+	dev_set_name(&hwdep->dev, "hwC%iD%i", card->number, device);
 #ifdef CONFIG_SND_OSSEMUL
 	hwdep->oss_type = -1;
 #endif
-	if ((err = snd_device_new(card, SNDRV_DEV_HWDEP, hwdep, &ops)) < 0) {
-		snd_hwdep_free(hwdep);
+
+	err = snd_device_new(card, SNDRV_DEV_HWDEP, hwdep, &ops);
+	if (err < 0) {
+		put_device(&hwdep->dev);
 		return err;
 	}
-	init_waitqueue_head(&hwdep->open_wait);
-	mutex_init(&hwdep->open_mutex);
+
 	if (rhwdep)
 		*rhwdep = hwdep;
 	return 0;
 }
 EXPORT_SYMBOL(snd_hwdep_new);
 
-static int snd_hwdep_free(struct snd_hwdep *hwdep)
+static int snd_hwdep_dev_free(struct snd_device *device)
 {
+	struct snd_hwdep *hwdep = device->device_data;
 	if (!hwdep)
 		return 0;
 	if (hwdep->private_free)
 		hwdep->private_free(hwdep);
-	kfree(hwdep);
+	put_device(&hwdep->dev);
 	return 0;
 }
 
-static int snd_hwdep_dev_free(struct snd_device *device)
-{
-	struct snd_hwdep *hwdep = device->device_data;
-	return snd_hwdep_free(hwdep);
-}
-
 static int snd_hwdep_dev_register(struct snd_device *device)
 {
 	struct snd_hwdep *hwdep = device->device_data;
 	struct snd_card *card = hwdep->card;
-	struct device *dev;
 	int err;
-	char name[32];
 
 	mutex_lock(&register_mutex);
 	if (snd_hwdep_search(card, hwdep->device)) {
@@ -427,54 +432,31 @@ static int snd_hwdep_dev_register(struct snd_device *device)
 		return -EBUSY;
 	}
 	list_add_tail(&hwdep->list, &snd_hwdep_devices);
-	sprintf(name, "hwC%iD%i", hwdep->card->number, hwdep->device);
-	dev = hwdep->dev;
-	if (!dev)
-		dev = snd_card_get_device_link(hwdep->card);
 	err = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_HWDEP,
 					  hwdep->card, hwdep->device,
 					  &snd_hwdep_f_ops, hwdep,
-					  NULL, dev, name);
+					  &hwdep->dev, NULL, NULL);
 	if (err < 0) {
-		dev_err(dev,
-			"unable to register hardware dependent device %i:%i\n",
-			card->number, hwdep->device);
+		dev_err(&hwdep->dev, "unable to register\n");
 		list_del(&hwdep->list);
 		mutex_unlock(&register_mutex);
 		return err;
 	}
 
-	if (hwdep->groups) {
-		struct device *d = snd_get_device(SNDRV_DEVICE_TYPE_HWDEP,
-						  hwdep->card, hwdep->device);
-		if (d) {
-			if (hwdep->private_data)
-				dev_set_drvdata(d, hwdep->private_data);
-			err = sysfs_create_groups(&d->kobj, hwdep->groups);
-			if (err < 0)
-				dev_warn(dev,
-					 "hwdep %d:%d: cannot create sysfs groups\n",
-					 card->number, hwdep->device);
-			put_device(d);
-		}
-	}
-
 #ifdef CONFIG_SND_OSSEMUL
 	hwdep->ossreg = 0;
 	if (hwdep->oss_type >= 0) {
-		if ((hwdep->oss_type == SNDRV_OSS_DEVICE_TYPE_DMFM) && (hwdep->device != 0)) {
-			dev_warn(dev,
+		if (hwdep->oss_type == SNDRV_OSS_DEVICE_TYPE_DMFM &&
+		    hwdep->device)
+			dev_warn(&hwdep->dev,
 				 "only hwdep device 0 can be registered as OSS direct FM device!\n");
-		} else {
-			if (snd_register_oss_device(hwdep->oss_type,
-						    card, hwdep->device,
-						    &snd_hwdep_f_ops, hwdep) < 0) {
-				dev_err(dev,
-					"unable to register OSS compatibility device %i:%i\n",
-					card->number, hwdep->device);
-			} else
-				hwdep->ossreg = 1;
-		}
+		else if (snd_register_oss_device(hwdep->oss_type,
+						 card, hwdep->device,
+						 &snd_hwdep_f_ops, hwdep) < 0)
+			dev_warn(&hwdep->dev,
+				 "unable to register OSS compatibility device\n");
+		else
+			hwdep->ossreg = 1;
 	}
 #endif
 	mutex_unlock(&register_mutex);
diff --git a/sound/pci/hda/hda_hwdep.c b/sound/pci/hda/hda_hwdep.c
index 014a7849e8f..11b5a42b4ec 100644
--- a/sound/pci/hda/hda_hwdep.c
+++ b/sound/pci/hda/hda_hwdep.c
@@ -109,7 +109,6 @@ int snd_hda_create_hwdep(struct hda_codec *codec)
 	hwdep->iface = SNDRV_HWDEP_IFACE_HDA;
 	hwdep->private_data = codec;
 	hwdep->exclusive = 1;
-	hwdep->groups = snd_hda_dev_attr_groups;
 
 	hwdep->ops.open = hda_hwdep_open;
 	hwdep->ops.ioctl = hda_hwdep_ioctl;
@@ -118,7 +117,11 @@ int snd_hda_create_hwdep(struct hda_codec *codec)
 #endif
 
 	/* link to codec */
-	hwdep->dev = &codec->dev;
+	hwdep->dev.parent = &codec->dev;
+
+	/* for sysfs */
+	hwdep->dev.groups = snd_hda_dev_attr_groups;
+	dev_set_drvdata(&hwdep->dev, codec);
 
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From ef46c7af93f98d07cd0ed891f93a26d135785526 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 29 Jan 2015 17:32:26 +0100
Subject: ALSA: pcm: Embed struct device

Like previous patches, at this time we embed the struct device into
PCM object.  However, this needs a bit more caution: struct snd_pcm
doesn't own one device but two, for both playback and capture!  Thus
not struct snd_pcm but struct snd_pcm_str object contains the device.

Along with this change, pcm->dev field is dropped for avoiding
confusion.  It was meant to point to a non-standard parent.  But,
since now we can touch each struct device directly, we can manipulate
the parent field easily there, too.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h                     |  2 +-
 sound/aoa/soundbus/i2sbus/pcm.c         |  5 ++++-
 sound/core/pcm.c                        | 38 +++++++++++++--------------------
 sound/pci/hda/hda_controller.c          |  3 ++-
 sound/soc/intel/sst-mfld-platform-pcm.c |  1 -
 5 files changed, 22 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index b429b73e875..735bd0cc734 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -449,6 +449,7 @@ struct snd_pcm_str {
 #endif
 #endif
 	struct snd_kcontrol *chmap_kctl; /* channel-mapping controls */
+	struct device dev;
 };
 
 struct snd_pcm {
@@ -465,7 +466,6 @@ struct snd_pcm {
 	wait_queue_head_t open_wait;
 	void *private_data;
 	void (*private_free) (struct snd_pcm *pcm);
-	struct device *dev; /* actual hw device this belongs to */
 	bool internal; /* pcm is for internal use only */
 	bool nonatomic; /* whole PCM operations are in non-atomic context */
 #if defined(CONFIG_SND_PCM_OSS) || defined(CONFIG_SND_PCM_OSS_MODULE)
diff --git a/sound/aoa/soundbus/i2sbus/pcm.c b/sound/aoa/soundbus/i2sbus/pcm.c
index 7b74a4ba75f..a02b7b8d353 100644
--- a/sound/aoa/soundbus/i2sbus/pcm.c
+++ b/sound/aoa/soundbus/i2sbus/pcm.c
@@ -968,7 +968,6 @@ i2sbus_attach_codec(struct soundbus_dev *dev, struct snd_card *card,
 			printk(KERN_DEBUG "i2sbus: failed to create pcm\n");
 			goto out_put_ci_module;
 		}
-		dev->pcm->dev = &dev->ofdev.dev;
 	}
 
 	/* ALSA yet again sucks.
@@ -988,6 +987,8 @@ i2sbus_attach_codec(struct soundbus_dev *dev, struct snd_card *card,
 			goto out_put_ci_module;
 		snd_pcm_set_ops(dev->pcm, SNDRV_PCM_STREAM_PLAYBACK,
 				&i2sbus_playback_ops);
+		dev->pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].dev.parent =
+			&dev->ofdev.dev;
 		i2sdev->out.created = 1;
 	}
 
@@ -1003,6 +1004,8 @@ i2sbus_attach_codec(struct soundbus_dev *dev, struct snd_card *card,
 			goto out_put_ci_module;
 		snd_pcm_set_ops(dev->pcm, SNDRV_PCM_STREAM_CAPTURE,
 				&i2sbus_record_ops);
+		dev->pcm->streams[SNDRV_PCM_STREAM_CAPTURE].dev.parent =
+			&dev->ofdev.dev;
 		i2sdev->in.created = 1;
 	}
 
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 1b7c473720f..4d5120f7a8a 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -673,6 +673,8 @@ static inline int snd_pcm_substream_proc_init(struct snd_pcm_substream *substrea
 static inline int snd_pcm_substream_proc_done(struct snd_pcm_substream *substream) { return 0; }
 #endif /* CONFIG_SND_VERBOSE_PROCFS */
 
+static const struct attribute_group *pcm_dev_attr_groups[];
+
 /**
  * snd_pcm_new_stream - create a new PCM stream
  * @pcm: the pcm instance
@@ -698,7 +700,15 @@ int snd_pcm_new_stream(struct snd_pcm *pcm, int stream, int substream_count)
 	pstr->stream = stream;
 	pstr->pcm = pcm;
 	pstr->substream_count = substream_count;
-	if (substream_count > 0 && !pcm->internal) {
+	if (!substream_count)
+		return 0;
+
+	snd_device_initialize(&pstr->dev, pcm->card);
+	pstr->dev.groups = pcm_dev_attr_groups;
+	dev_set_name(&pstr->dev, "pcmC%iD%i%c", pcm->card->number, pcm->device,
+		     stream == SNDRV_PCM_STREAM_PLAYBACK ? 'p' : 'c');
+
+	if (!pcm->internal) {
 		err = snd_pcm_stream_proc_init(pstr);
 		if (err < 0) {
 			pcm_err(pcm, "Error in snd_pcm_stream_proc_init\n");
@@ -868,6 +878,8 @@ static void snd_pcm_free_stream(struct snd_pcm_str * pstr)
 		kfree(setup);
 	}
 #endif
+	if (pstr->substream_count)
+		put_device(&pstr->dev);
 }
 
 static int snd_pcm_free(struct snd_pcm *pcm)
@@ -1069,9 +1081,7 @@ static int snd_pcm_dev_register(struct snd_device *device)
 	int cidx, err;
 	struct snd_pcm_substream *substream;
 	struct snd_pcm_notify *notify;
-	char str[16];
 	struct snd_pcm *pcm;
-	struct device *dev;
 
 	if (snd_BUG_ON(!device || !device->device_data))
 		return -ENXIO;
@@ -1088,42 +1098,24 @@ static int snd_pcm_dev_register(struct snd_device *device)
 			continue;
 		switch (cidx) {
 		case SNDRV_PCM_STREAM_PLAYBACK:
-			sprintf(str, "pcmC%iD%ip", pcm->card->number, pcm->device);
 			devtype = SNDRV_DEVICE_TYPE_PCM_PLAYBACK;
 			break;
 		case SNDRV_PCM_STREAM_CAPTURE:
-			sprintf(str, "pcmC%iD%ic", pcm->card->number, pcm->device);
 			devtype = SNDRV_DEVICE_TYPE_PCM_CAPTURE;
 			break;
 		}
-		/* device pointer to use, pcm->dev takes precedence if
-		 * it is assigned, otherwise fall back to card's device
-		 * if possible */
-		dev = pcm->dev;
-		if (!dev)
-			dev = snd_card_get_device_link(pcm->card);
 		/* register pcm */
 		err = snd_register_device_for_dev(devtype, pcm->card,
 						  pcm->device,
 						  &snd_pcm_f_ops[cidx],
-						  pcm, NULL, dev, str);
+						  pcm, &pcm->streams[cidx].dev,
+						  NULL, NULL);
 		if (err < 0) {
 			list_del(&pcm->list);
 			mutex_unlock(&register_mutex);
 			return err;
 		}
 
-		dev = snd_get_device(devtype, pcm->card, pcm->device);
-		if (dev) {
-			err = sysfs_create_groups(&dev->kobj,
-						  pcm_dev_attr_groups);
-			if (err < 0)
-				dev_warn(dev,
-					 "pcm %d:%d: cannot create sysfs groups\n",
-					 pcm->card->number, pcm->device);
-			put_device(dev);
-		}
-
 		for (substream = pcm->streams[cidx].substream; substream; substream = substream->next)
 			snd_pcm_timer_init(substream);
 	}
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 0cfc9c8c4b4..712ec5ceba4 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -939,7 +939,8 @@ static int azx_attach_pcm_stream(struct hda_bus *bus, struct hda_codec *codec,
 					      chip->card->dev,
 					      size, MAX_PREALLOC_SIZE);
 	/* link to codec */
-	pcm->dev = &codec->dev;
+	for (s = 0; s < 2; s++)
+		pcm->streams[s].dev.parent = &codec->dev;
 	return 0;
 }
 
diff --git a/sound/soc/intel/sst-mfld-platform-pcm.c b/sound/soc/intel/sst-mfld-platform-pcm.c
index a1a8d9d9153..2d80c4e1299 100644
--- a/sound/soc/intel/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/sst-mfld-platform-pcm.c
@@ -645,7 +645,6 @@ static struct snd_pcm_ops sst_platform_ops = {
 
 static void sst_pcm_free(struct snd_pcm *pcm)
 {
-	dev_dbg(pcm->dev, "sst_pcm_free called\n");
 	snd_pcm_lib_preallocate_free_for_all(pcm);
 }
 
-- 
cgit v1.2.3-70-g09d2


From aee5012fbb77dad6179c44d83d531ad62dd8098a Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 29 Jan 2015 17:55:52 +0100
Subject: ALSA: rawmidi: Embed struct device

Like previous patches, this changes the device management for rawmidi,
embedding the struct device into struct snd_rawmidi.  The required
change is more or less same as hwdep device.

The currently unused dev field is reused as the new embedded struct
field now.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/rawmidi.h |  4 +++-
 sound/core/rawmidi.c    | 24 +++++++++++++++++-------
 2 files changed, 20 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h
index 311dafe6cc4..f6cbef78db6 100644
--- a/include/sound/rawmidi.h
+++ b/include/sound/rawmidi.h
@@ -28,6 +28,7 @@
 #include <linux/wait.h>
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
+#include <linux/device.h>
 
 #if defined(CONFIG_SND_SEQUENCER) || defined(CONFIG_SND_SEQUENCER_MODULE)
 #include <sound/seq_device.h>
@@ -139,7 +140,8 @@ struct snd_rawmidi {
 	struct mutex open_mutex;
 	wait_queue_head_t open_wait;
 
-	struct snd_info_entry *dev;
+	struct device dev;
+
 	struct snd_info_entry *proc_entry;
 
 #if defined(CONFIG_SND_SEQUENCER) || defined(CONFIG_SND_SEQUENCER_MODULE)
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index be18162c380..932396c8103 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -1443,6 +1443,11 @@ static int snd_rawmidi_alloc_substreams(struct snd_rawmidi *rmidi,
 	return 0;
 }
 
+static void release_rawmidi_device(struct device *dev)
+{
+	kfree(container_of(dev, struct snd_rawmidi, dev));
+}
+
 /**
  * snd_rawmidi_new - create a rawmidi instance
  * @card: the card instance
@@ -1487,6 +1492,11 @@ int snd_rawmidi_new(struct snd_card *card, char *id, int device,
 
 	if (id != NULL)
 		strlcpy(rmidi->id, id, sizeof(rmidi->id));
+
+	snd_device_initialize(&rmidi->dev, card);
+	rmidi->dev.release = release_rawmidi_device;
+	dev_set_name(&rmidi->dev, "midiC%iD%i", card->number, device);
+
 	if ((err = snd_rawmidi_alloc_substreams(rmidi,
 						&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT],
 						SNDRV_RAWMIDI_STREAM_INPUT,
@@ -1538,7 +1548,7 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi)
 	snd_rawmidi_free_substreams(&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT]);
 	if (rmidi->private_free)
 		rmidi->private_free(rmidi);
-	kfree(rmidi);
+	put_device(&rmidi->dev);
 	return 0;
 }
 
@@ -1571,12 +1581,12 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 		return -EBUSY;
 	}
 	list_add_tail(&rmidi->list, &snd_rawmidi_devices);
-	sprintf(name, "midiC%iD%i", rmidi->card->number, rmidi->device);
-	if ((err = snd_register_device(SNDRV_DEVICE_TYPE_RAWMIDI,
-				       rmidi->card, rmidi->device,
-				       &snd_rawmidi_f_ops, rmidi, name)) < 0) {
-		rmidi_err(rmidi, "unable to register rawmidi device %i:%i\n",
-			  rmidi->card->number, rmidi->device);
+	err = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_RAWMIDI,
+					  rmidi->card, rmidi->device,
+					  &snd_rawmidi_f_ops, rmidi,
+					  &rmidi->dev, NULL, NULL);
+	if (err < 0) {
+		rmidi_err(rmidi, "unable to register\n");
 		list_del(&rmidi->list);
 		mutex_unlock(&register_mutex);
 		return err;
-- 
cgit v1.2.3-70-g09d2


From 04c5d5a430fca046cffac099a3f41e74816939da Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 30 Jan 2015 08:16:35 +0100
Subject: ALSA: compress: Embed struct device

Like previous patches, this one embeds the struct device into struct
snd_compr.  As the dev field wasn't used beforehand, it's reused as
the new device struct.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/compress_driver.h |  4 ++--
 sound/core/compress_offload.c   | 24 +++++++++++++++++++-----
 2 files changed, 21 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 396e8f73670..1d0593b5257 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -134,7 +134,7 @@ struct snd_compr_ops {
 /**
  * struct snd_compr: Compressed device
  * @name: DSP device name
- * @dev: Device pointer
+ * @dev: associated device instance
  * @ops: pointer to DSP callbacks
  * @private_data: pointer to DSP pvt data
  * @card: sound card pointer
@@ -144,7 +144,7 @@ struct snd_compr_ops {
  */
 struct snd_compr {
 	const char *name;
-	struct device *dev;
+	struct device dev;
 	struct snd_compr_ops *ops;
 	void *private_data;
 	struct snd_card *card;
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 89028fab64f..cb58c3f7f80 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -868,12 +868,13 @@ static int snd_compress_dev_register(struct snd_device *device)
 		return -EBADFD;
 	compr = device->device_data;
 
-	sprintf(str, "comprC%iD%i", compr->card->number, compr->device);
 	pr_debug("reg %s for device %s, direction %d\n", str, compr->name,
 			compr->direction);
 	/* register compressed device */
-	ret = snd_register_device(SNDRV_DEVICE_TYPE_COMPRESS, compr->card,
-			compr->device, &snd_compr_file_ops, compr, str);
+	ret = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_COMPRESS,
+					  compr->card, compr->device,
+					  &snd_compr_file_ops, compr,
+					  &compr->dev, NULL, NULL);
 	if (ret < 0) {
 		pr_err("snd_register_device failed\n %d", ret);
 		return ret;
@@ -892,6 +893,15 @@ static int snd_compress_dev_disconnect(struct snd_device *device)
 	return 0;
 }
 
+static int snd_compress_dev_free(struct snd_device *device)
+{
+	struct snd_compr *compr;
+
+	compr = device->device_data;
+	put_device(&compr->dev);
+	return 0;
+}
+
 /*
  * snd_compress_new: create new compress device
  * @card: sound card pointer
@@ -903,7 +913,7 @@ int snd_compress_new(struct snd_card *card, int device,
 			int dirn, struct snd_compr *compr)
 {
 	static struct snd_device_ops ops = {
-		.dev_free = NULL,
+		.dev_free = snd_compress_dev_free,
 		.dev_register = snd_compress_dev_register,
 		.dev_disconnect = snd_compress_dev_disconnect,
 	};
@@ -911,6 +921,10 @@ int snd_compress_new(struct snd_card *card, int device,
 	compr->card = card;
 	compr->device = device;
 	compr->direction = dirn;
+
+	snd_device_initialize(&compr->dev, card);
+	dev_set_name(&compr->dev, "comprC%iD%i", card->number, device);
+
 	return snd_device_new(card, SNDRV_DEV_COMPRESS, compr, &ops);
 }
 EXPORT_SYMBOL_GPL(snd_compress_new);
@@ -948,7 +962,7 @@ int snd_compress_register(struct snd_compr *device)
 {
 	int retval;
 
-	if (device->name == NULL || device->dev == NULL || device->ops == NULL)
+	if (device->name == NULL || device->ops == NULL)
 		return -EINVAL;
 
 	pr_debug("Registering compressed device %s\n", device->name);
-- 
cgit v1.2.3-70-g09d2


From 08b717c2ae8b7e23e1d018dad601fdf12bde3a96 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 23 Jan 2015 12:52:33 -0300
Subject: [media] adv7180: Add fast switch support

In fast switch mode the adv7180 (and similar) can lock onto a new signal
faster when switching between different inputs. As a downside though it is
no longer able to auto-detect the incoming format.

The fast switch mode is exposed as a boolean v4l control that allows
userspace applications to either enable or disable fast switch mode.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Acked-by: Federico Vaga <federico.vaga@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
---
 drivers/media/i2c/adv7180.c        | 29 +++++++++++++++++++++++++++++
 include/uapi/linux/v4l2-controls.h |  4 ++++
 2 files changed, 33 insertions(+)

(limited to 'include')

diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index 3c1c866d1e3..b75878c27c2 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -127,6 +127,9 @@
 #define ADV7180_REG_VPP_SLAVE_ADDR	0xFD
 #define ADV7180_REG_CSI_SLAVE_ADDR	0xFE
 
+#define ADV7180_REG_FLCONTROL 0x40e0
+#define ADV7180_FLCONTROL_FL_ENABLE 0x1
+
 #define ADV7180_CSI_REG_PWRDN	0x00
 #define ADV7180_CSI_PWRDN	0x80
 
@@ -164,6 +167,8 @@
 #define ADV7180_DEFAULT_CSI_I2C_ADDR 0x44
 #define ADV7180_DEFAULT_VPP_I2C_ADDR 0x42
 
+#define V4L2_CID_ADV_FAST_SWITCH	(V4L2_CID_USER_ADV7180_BASE + 0x00)
+
 struct adv7180_state;
 
 #define ADV7180_FLAG_RESET_POWERED	BIT(0)
@@ -508,6 +513,18 @@ static int adv7180_s_ctrl(struct v4l2_ctrl *ctrl)
 			break;
 		ret = adv7180_write(state, ADV7180_REG_SD_SAT_CR, val);
 		break;
+	case V4L2_CID_ADV_FAST_SWITCH:
+		if (ctrl->val) {
+			/* ADI required write */
+			adv7180_write(state, 0x80d9, 0x44);
+			adv7180_write(state, ADV7180_REG_FLCONTROL,
+				ADV7180_FLCONTROL_FL_ENABLE);
+		} else {
+			/* ADI required write */
+			adv7180_write(state, 0x80d9, 0xc4);
+			adv7180_write(state, ADV7180_REG_FLCONTROL, 0x00);
+		}
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -520,6 +537,16 @@ static const struct v4l2_ctrl_ops adv7180_ctrl_ops = {
 	.s_ctrl = adv7180_s_ctrl,
 };
 
+static const struct v4l2_ctrl_config adv7180_ctrl_fast_switch = {
+	.ops = &adv7180_ctrl_ops,
+	.id = V4L2_CID_ADV_FAST_SWITCH,
+	.name = "Fast Switching",
+	.type = V4L2_CTRL_TYPE_BOOLEAN,
+	.min = 0,
+	.max = 1,
+	.step = 1,
+};
+
 static int adv7180_init_controls(struct adv7180_state *state)
 {
 	v4l2_ctrl_handler_init(&state->ctrl_hdl, 4);
@@ -536,6 +563,8 @@ static int adv7180_init_controls(struct adv7180_state *state)
 	v4l2_ctrl_new_std(&state->ctrl_hdl, &adv7180_ctrl_ops,
 			  V4L2_CID_HUE, ADV7180_HUE_MIN,
 			  ADV7180_HUE_MAX, 1, ADV7180_HUE_DEF);
+	v4l2_ctrl_new_custom(&state->ctrl_hdl, &adv7180_ctrl_fast_switch, NULL);
+
 	state->sd.ctrl_handler = &state->ctrl_hdl;
 	if (state->ctrl_hdl.error) {
 		int err = state->ctrl_hdl.error;
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 661f119a51b..9f6e108ff4a 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -170,6 +170,10 @@ enum v4l2_colorfx {
  * We reserve 16 controls for this driver. */
 #define V4L2_CID_USER_SAA7134_BASE		(V4L2_CID_USER_BASE + 0x1060)
 
+/* The base for the adv7180 driver controls.
+ * We reserve 16 controls for this driver. */
+#define V4L2_CID_USER_ADV7180_BASE		(V4L2_CID_USER_BASE + 0x1070)
+
 /* MPEG-class control IDs */
 /* The MPEG controls are applicable to all codec controls
  * and the 'MPEG' part of the define is historical */
-- 
cgit v1.2.3-70-g09d2


From 40a4b263854346fe7c7d1c3964c106296f690816 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 30 Jan 2015 08:34:58 +0100
Subject: ALSA: Simplify snd_device_register() variants

Now that all callers have been replaced with
snd_device_register_for_dev(), let's drop the obsolete device
registration code and concentrate only on the code handling struct
device directly.  That said,

- remove the old snd_device_register(),
- rename snd_device_register_for_dev() with snd_device_register(),
- drop superfluous arguments from snd_device_register(),
- change snd_unregister_device() to pass the device pointer directly

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/core.h           | 39 +++----------------------
 sound/core/compress_offload.c  | 10 +++----
 sound/core/control.c           |  7 ++---
 sound/core/hwdep.c             |  9 +++---
 sound/core/pcm.c               | 21 ++++----------
 sound/core/rawmidi.c           | 11 ++++---
 sound/core/seq/seq_clientmgr.c |  7 ++---
 sound/core/sound.c             | 65 ++++++++++++++++--------------------------
 sound/core/timer.c             |  7 ++---
 9 files changed, 55 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/include/sound/core.h b/include/sound/core.h
index 4b7e04e85e1..67ac309bb21 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -187,7 +187,6 @@ struct snd_minor {
 	int type;			/* SNDRV_DEVICE_TYPE_XXX */
 	int card;			/* card number */
 	int device;			/* device number */
-	bool created;
 	const struct file_operations *f_ops;	/* file operations */
 	void *private_data;		/* private data for f_ops->open */
 	struct device *dev;		/* device for sysfs */
@@ -210,40 +209,10 @@ void snd_request_card(int card);
 
 void snd_device_initialize(struct device *dev, struct snd_card *card);
 
-int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
-				const struct file_operations *f_ops,
-				void *private_data, struct device *device,
-				struct device *parent, const char *name);
-
-/**
- * snd_register_device - Register the ALSA device file for the card
- * @type: the device type, SNDRV_DEVICE_TYPE_XXX
- * @card: the card instance
- * @dev: the device index
- * @f_ops: the file operations
- * @private_data: user pointer for f_ops->open()
- * @name: the device file name
- *
- * Registers an ALSA device file for the given card.
- * The operators have to be set in reg parameter.
- *
- * This function uses the card's device pointer to link to the
- * correct &struct device.
- *
- * Return: Zero if successful, or a negative error code on failure.
- */
-static inline int snd_register_device(int type, struct snd_card *card, int dev,
-				      const struct file_operations *f_ops,
-				      void *private_data,
-				      const char *name)
-{
-	return snd_register_device_for_dev(type, card, dev, f_ops,
-					   private_data, NULL,
-					   snd_card_get_device_link(card),
-					   name);
-}
-
-int snd_unregister_device(int type, struct snd_card *card, int dev);
+int snd_register_device(int type, struct snd_card *card, int dev,
+			const struct file_operations *f_ops,
+			void *private_data, struct device *device);
+int snd_unregister_device(struct device *dev);
 void *snd_lookup_minor_data(unsigned int minor, int type);
 struct device *snd_get_device(int type, struct snd_card *card, int dev);
 
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index cb58c3f7f80..b123c42e7dc 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -871,10 +871,9 @@ static int snd_compress_dev_register(struct snd_device *device)
 	pr_debug("reg %s for device %s, direction %d\n", str, compr->name,
 			compr->direction);
 	/* register compressed device */
-	ret = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_COMPRESS,
-					  compr->card, compr->device,
-					  &snd_compr_file_ops, compr,
-					  &compr->dev, NULL, NULL);
+	ret = snd_register_device(SNDRV_DEVICE_TYPE_COMPRESS,
+				  compr->card, compr->device,
+				  &snd_compr_file_ops, compr, &compr->dev);
 	if (ret < 0) {
 		pr_err("snd_register_device failed\n %d", ret);
 		return ret;
@@ -888,8 +887,7 @@ static int snd_compress_dev_disconnect(struct snd_device *device)
 	struct snd_compr *compr;
 
 	compr = device->device_data;
-	snd_unregister_device(SNDRV_DEVICE_TYPE_COMPRESS, compr->card,
-		compr->device);
+	snd_unregister_device(&compr->dev);
 	return 0;
 }
 
diff --git a/sound/core/control.c b/sound/core/control.c
index e214fabbc67..60caba1f221 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -1661,9 +1661,8 @@ static int snd_ctl_dev_register(struct snd_device *device)
 {
 	struct snd_card *card = device->device_data;
 
-	return snd_register_device_for_dev(SNDRV_DEVICE_TYPE_CONTROL, card,
-					   -1, &snd_ctl_f_ops, card,
-					   &card->ctl_dev, NULL, NULL);
+	return snd_register_device(SNDRV_DEVICE_TYPE_CONTROL, card, -1,
+				   &snd_ctl_f_ops, card, &card->ctl_dev);
 }
 
 /*
@@ -1681,7 +1680,7 @@ static int snd_ctl_dev_disconnect(struct snd_device *device)
 	}
 	read_unlock(&card->ctl_files_rwlock);
 
-	return snd_unregister_device(SNDRV_DEVICE_TYPE_CONTROL, card, -1);
+	return snd_unregister_device(&card->ctl_dev);
 }
 
 /*
diff --git a/sound/core/hwdep.c b/sound/core/hwdep.c
index 506387ba645..84244a5143c 100644
--- a/sound/core/hwdep.c
+++ b/sound/core/hwdep.c
@@ -432,10 +432,9 @@ static int snd_hwdep_dev_register(struct snd_device *device)
 		return -EBUSY;
 	}
 	list_add_tail(&hwdep->list, &snd_hwdep_devices);
-	err = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_HWDEP,
-					  hwdep->card, hwdep->device,
-					  &snd_hwdep_f_ops, hwdep,
-					  &hwdep->dev, NULL, NULL);
+	err = snd_register_device(SNDRV_DEVICE_TYPE_HWDEP,
+				  hwdep->card, hwdep->device,
+				  &snd_hwdep_f_ops, hwdep, &hwdep->dev);
 	if (err < 0) {
 		dev_err(&hwdep->dev, "unable to register\n");
 		list_del(&hwdep->list);
@@ -480,7 +479,7 @@ static int snd_hwdep_dev_disconnect(struct snd_device *device)
 	if (hwdep->ossreg)
 		snd_unregister_oss_device(hwdep->oss_type, hwdep->card, hwdep->device);
 #endif
-	snd_unregister_device(SNDRV_DEVICE_TYPE_HWDEP, hwdep->card, hwdep->device);
+	snd_unregister_device(&hwdep->dev);
 	list_del_init(&hwdep->list);
 	mutex_unlock(&hwdep->open_mutex);
 	mutex_unlock(&register_mutex);
diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 4d5120f7a8a..0345e53a340 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -1105,11 +1105,9 @@ static int snd_pcm_dev_register(struct snd_device *device)
 			break;
 		}
 		/* register pcm */
-		err = snd_register_device_for_dev(devtype, pcm->card,
-						  pcm->device,
-						  &snd_pcm_f_ops[cidx],
-						  pcm, &pcm->streams[cidx].dev,
-						  NULL, NULL);
+		err = snd_register_device(devtype, pcm->card, pcm->device,
+					  &snd_pcm_f_ops[cidx], pcm,
+					  &pcm->streams[cidx].dev);
 		if (err < 0) {
 			list_del(&pcm->list);
 			mutex_unlock(&register_mutex);
@@ -1132,7 +1130,7 @@ static int snd_pcm_dev_disconnect(struct snd_device *device)
 	struct snd_pcm *pcm = device->device_data;
 	struct snd_pcm_notify *notify;
 	struct snd_pcm_substream *substream;
-	int cidx, devtype;
+	int cidx;
 
 	mutex_lock(&register_mutex);
 	if (list_empty(&pcm->list))
@@ -1155,16 +1153,7 @@ static int snd_pcm_dev_disconnect(struct snd_device *device)
 		notify->n_disconnect(pcm);
 	}
 	for (cidx = 0; cidx < 2; cidx++) {
-		devtype = -1;
-		switch (cidx) {
-		case SNDRV_PCM_STREAM_PLAYBACK:
-			devtype = SNDRV_DEVICE_TYPE_PCM_PLAYBACK;
-			break;
-		case SNDRV_PCM_STREAM_CAPTURE:
-			devtype = SNDRV_DEVICE_TYPE_PCM_CAPTURE;
-			break;
-		}
-		snd_unregister_device(devtype, pcm->card, pcm->device);
+		snd_unregister_device(&pcm->streams[cidx].dev);
 		if (pcm->streams[cidx].chmap_kctl) {
 			snd_ctl_remove(pcm->card, pcm->streams[cidx].chmap_kctl);
 			pcm->streams[cidx].chmap_kctl = NULL;
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index bccbf7e375d..b5a748596fc 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -1581,10 +1581,9 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 		return -EBUSY;
 	}
 	list_add_tail(&rmidi->list, &snd_rawmidi_devices);
-	err = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_RAWMIDI,
-					  rmidi->card, rmidi->device,
-					  &snd_rawmidi_f_ops, rmidi,
-					  &rmidi->dev, NULL, NULL);
+	err = snd_register_device(SNDRV_DEVICE_TYPE_RAWMIDI,
+				  rmidi->card, rmidi->device,
+				  &snd_rawmidi_f_ops, rmidi, &rmidi->dev);
 	if (err < 0) {
 		rmidi_err(rmidi, "unable to register\n");
 		list_del(&rmidi->list);
@@ -1593,7 +1592,7 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 	}
 	if (rmidi->ops && rmidi->ops->dev_register &&
 	    (err = rmidi->ops->dev_register(rmidi)) < 0) {
-		snd_unregister_device(SNDRV_DEVICE_TYPE_RAWMIDI, rmidi->card, rmidi->device);
+		snd_unregister_device(&rmidi->dev);
 		list_del(&rmidi->list);
 		mutex_unlock(&register_mutex);
 		return err;
@@ -1681,7 +1680,7 @@ static int snd_rawmidi_dev_disconnect(struct snd_device *device)
 		rmidi->ossreg = 0;
 	}
 #endif /* CONFIG_SND_OSSEMUL */
-	snd_unregister_device(SNDRV_DEVICE_TYPE_RAWMIDI, rmidi->card, rmidi->device);
+	snd_unregister_device(&rmidi->dev);
 	mutex_unlock(&rmidi->open_mutex);
 	mutex_unlock(&register_mutex);
 	return 0;
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 65b320ec66f..2b62cd021bc 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -2586,9 +2586,8 @@ int __init snd_sequencer_device_init(void)
 	if (mutex_lock_interruptible(&register_mutex))
 		return -ERESTARTSYS;
 
-	err = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_SEQUENCER, NULL, 0,
-					  &snd_seq_f_ops, NULL,
-					  &seq_dev, NULL, NULL);
+	err = snd_register_device(SNDRV_DEVICE_TYPE_SEQUENCER, NULL, 0,
+				  &snd_seq_f_ops, NULL, &seq_dev);
 	if (err < 0) {
 		mutex_unlock(&register_mutex);
 		put_device(&seq_dev);
@@ -2607,6 +2606,6 @@ int __init snd_sequencer_device_init(void)
  */
 void __exit snd_sequencer_device_done(void)
 {
-	snd_unregister_device(SNDRV_DEVICE_TYPE_SEQUENCER, NULL, 0);
+	snd_unregister_device(&seq_dev);
 	put_device(&seq_dev);
 }
diff --git a/sound/core/sound.c b/sound/core/sound.c
index ea1af1acdbe..2e8aeb18d76 100644
--- a/sound/core/sound.c
+++ b/sound/core/sound.c
@@ -242,30 +242,30 @@ static int snd_kernel_minor(int type, struct snd_card *card, int dev)
 #endif
 
 /**
- * snd_register_device_for_dev - Register the ALSA device file for the card
+ * snd_register_device - Register the ALSA device file for the card
  * @type: the device type, SNDRV_DEVICE_TYPE_XXX
  * @card: the card instance
  * @dev: the device index
  * @f_ops: the file operations
  * @private_data: user pointer for f_ops->open()
- * @device: the device to register, NULL to create a new one
- * @parent: the &struct device to link this new device to (only for device=NULL)
- * @name: the device file name (only for device=NULL)
+ * @device: the device to register
  *
  * Registers an ALSA device file for the given card.
  * The operators have to be set in reg parameter.
  *
  * Return: Zero if successful, or a negative error code on failure.
  */
-int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
-				const struct file_operations *f_ops,
-				void *private_data, struct device *device,
-				struct device *parent, const char *name)
+int snd_register_device(int type, struct snd_card *card, int dev,
+			const struct file_operations *f_ops,
+			void *private_data, struct device *device)
 {
 	int minor;
 	int err = 0;
 	struct snd_minor *preg;
 
+	if (snd_BUG_ON(!device))
+		return -EINVAL;
+
 	preg = kmalloc(sizeof *preg, GFP_KERNEL);
 	if (preg == NULL)
 		return -ENOMEM;
@@ -288,19 +288,9 @@ int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
 		goto error;
 	}
 
-	if (device) {
-		preg->created = false;
-		preg->dev = device;
-		device->devt = MKDEV(major, minor);
-		err = device_add(device);
-	} else {
-		preg->created = true;
-		preg->dev = device_create(sound_class, parent,
-					  MKDEV(major, minor), private_data,
-					  "%s", name);
-		if (IS_ERR(preg->dev))
-			err = PTR_ERR(preg->dev);
-	}
+	preg->dev = device;
+	device->devt = MKDEV(major, minor);
+	err = device_add(device);
 	if (err < 0)
 		goto error;
 
@@ -311,8 +301,7 @@ int snd_register_device_for_dev(int type, struct snd_card *card, int dev,
 		kfree(preg);
 	return err;
 }
-
-EXPORT_SYMBOL(snd_register_device_for_dev);
+EXPORT_SYMBOL(snd_register_device);
 
 /* find the matching minor record
  * return the index of snd_minor, or -1 if not found
@@ -334,39 +323,33 @@ static int find_snd_minor(int type, struct snd_card *card, int dev)
 
 /**
  * snd_unregister_device - unregister the device on the given card
- * @type: the device type, SNDRV_DEVICE_TYPE_XXX
- * @card: the card instance
- * @dev: the device index
+ * @dev: the device instance
  *
  * Unregisters the device file already registered via
  * snd_register_device().
  *
  * Return: Zero if successful, or a negative error code on failure.
  */
-int snd_unregister_device(int type, struct snd_card *card, int dev)
+int snd_unregister_device(struct device *dev)
 {
 	int minor;
 	struct snd_minor *preg;
 
 	mutex_lock(&sound_mutex);
-	minor = find_snd_minor(type, card, dev);
-	if (minor < 0) {
-		mutex_unlock(&sound_mutex);
-		return -EINVAL;
+	for (minor = 0; minor < ARRAY_SIZE(snd_minors); ++minor) {
+		preg = snd_minors[minor];
+		if (preg && preg->dev == dev) {
+			snd_minors[minor] = NULL;
+			device_del(dev);
+			kfree(preg);
+			break;
+		}
 	}
-
-	preg = snd_minors[minor];
-	if (preg && !preg->created)
-		device_del(preg->dev);
-	else
-		device_destroy(sound_class, MKDEV(major, minor));
-
-	kfree(snd_minors[minor]);
-	snd_minors[minor] = NULL;
 	mutex_unlock(&sound_mutex);
+	if (minor >= ARRAY_SIZE(snd_minors))
+		return -ENOENT;
 	return 0;
 }
-
 EXPORT_SYMBOL(snd_unregister_device);
 
 /**
diff --git a/sound/core/timer.c b/sound/core/timer.c
index dae40ac11e0..9f0c703ef08 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -1976,9 +1976,8 @@ static int __init alsa_timer_init(void)
 		return err;
 	}
 
-	err = snd_register_device_for_dev(SNDRV_DEVICE_TYPE_TIMER, NULL, 0,
-					  &snd_timer_f_ops, NULL,
-					  &timer_dev, NULL, NULL);
+	err = snd_register_device(SNDRV_DEVICE_TYPE_TIMER, NULL, 0,
+				  &snd_timer_f_ops, NULL, &timer_dev);
 	if (err < 0) {
 		pr_err("ALSA: unable to register timer device (%i)\n", err);
 		snd_timer_free_all();
@@ -1992,7 +1991,7 @@ static int __init alsa_timer_init(void)
 
 static void __exit alsa_timer_exit(void)
 {
-	snd_unregister_device(SNDRV_DEVICE_TYPE_TIMER, NULL, 0);
+	snd_unregister_device(&timer_dev);
 	snd_timer_free_all();
 	put_device(&timer_dev);
 	snd_timer_proc_done();
-- 
cgit v1.2.3-70-g09d2


From 830953c0724b42be30a74febcde6c89c706ed286 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 30 Jan 2015 08:39:40 +0100
Subject: ALSA: Drop snd_get_device() helper

Since the device is no longer hidden but embedded into each component,
we no longer need snd_get_device().  Let's drop it and relevant codes.

Reviewed-by: Jaroslav Kysela <perex@perex.cz>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/core.h |  1 -
 sound/core/sound.c   | 43 -------------------------------------------
 2 files changed, 44 deletions(-)

(limited to 'include')

diff --git a/include/sound/core.h b/include/sound/core.h
index 67ac309bb21..58882bfacdd 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -214,7 +214,6 @@ int snd_register_device(int type, struct snd_card *card, int dev,
 			void *private_data, struct device *device);
 int snd_unregister_device(struct device *dev);
 void *snd_lookup_minor_data(unsigned int minor, int type);
-struct device *snd_get_device(int type, struct snd_card *card, int dev);
 
 #ifdef CONFIG_SND_OSSEMUL
 int snd_register_oss_device(int type, struct snd_card *card, int dev,
diff --git a/sound/core/sound.c b/sound/core/sound.c
index 2e8aeb18d76..185cec01ee2 100644
--- a/sound/core/sound.c
+++ b/sound/core/sound.c
@@ -303,24 +303,6 @@ int snd_register_device(int type, struct snd_card *card, int dev,
 }
 EXPORT_SYMBOL(snd_register_device);
 
-/* find the matching minor record
- * return the index of snd_minor, or -1 if not found
- */
-static int find_snd_minor(int type, struct snd_card *card, int dev)
-{
-	int cardnum, minor;
-	struct snd_minor *mptr;
-
-	cardnum = card ? card->number : -1;
-	for (minor = 0; minor < ARRAY_SIZE(snd_minors); ++minor)
-		if ((mptr = snd_minors[minor]) != NULL &&
-		    mptr->type == type &&
-		    mptr->card == cardnum &&
-		    mptr->device == dev)
-			return minor;
-	return -1;
-}
-
 /**
  * snd_unregister_device - unregister the device on the given card
  * @dev: the device instance
@@ -352,31 +334,6 @@ int snd_unregister_device(struct device *dev)
 }
 EXPORT_SYMBOL(snd_unregister_device);
 
-/**
- * snd_get_device - get the assigned device to the given type and device number
- * @type: the device type, SNDRV_DEVICE_TYPE_XXX
- * @card:the card instance
- * @dev: the device index
- *
- * The caller needs to release it via put_device() after using it.
- */
-struct device *snd_get_device(int type, struct snd_card *card, int dev)
-{
-	int minor;
-	struct device *d = NULL;
-
-	mutex_lock(&sound_mutex);
-	minor = find_snd_minor(type, card, dev);
-	if (minor >= 0) {
-		d = snd_minors[minor]->dev;
-		if (d)
-			get_device(d);
-	}
-	mutex_unlock(&sound_mutex);
-	return d;
-}
-EXPORT_SYMBOL(snd_get_device);
-
 #ifdef CONFIG_PROC_FS
 /*
  *  INFO PART
-- 
cgit v1.2.3-70-g09d2


From 15d0f5ea348b9c4e6d41df294dde38a56a39c7bf Mon Sep 17 00:00:00 2001
From: Al Viro <viro@ZenIV.linux.org.uk>
Date: Mon, 2 Feb 2015 10:07:59 -0700
Subject: Make super_blocks and sb_lock static

The only user outside of fs/super.c is gone now

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 fs/super.c         | 4 ++--
 include/linux/fs.h | 2 --
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/super.c b/fs/super.c
index 3b4dadafdd6..05a021638b1 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -36,8 +36,8 @@
 #include "internal.h"
 
 
-LIST_HEAD(super_blocks);
-DEFINE_SPINLOCK(sb_lock);
+static LIST_HEAD(super_blocks);
+static DEFINE_SPINLOCK(sb_lock);
 
 static char *sb_writers_name[SB_FREEZE_LEVELS] = {
 	"sb_writers",
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 65d02de342e..2f717baefdf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1183,8 +1183,6 @@ struct mm_struct;
 #define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
 #define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
 
-extern struct list_head super_blocks;
-extern spinlock_t sb_lock;
 
 /* Possible states of 'frozen' field */
 enum {
-- 
cgit v1.2.3-70-g09d2


From 6cae0a4648c0db2a74efb816cd2ce84390c90480 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 16 Aug 2014 13:31:51 +0200
Subject: nfs: add LAYOUT_TYPE_MAX enum value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This gives us a nice upper bound for later use in nfѕd.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/nfs4.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 022b761dbf0..8a3589c2542 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -516,6 +516,7 @@ enum pnfs_layouttype {
 	LAYOUT_NFSV4_1_FILES  = 1,
 	LAYOUT_OSD2_OBJECTS = 2,
 	LAYOUT_BLOCK_VOLUME = 3,
+	LAYOUT_TYPE_MAX
 };
 
 /* used for both layout return and recall */
-- 
cgit v1.2.3-70-g09d2


From 11afe9f76e121e960445deee5b7f26f0787a1990 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 21 Jan 2015 19:17:03 +0100
Subject: fs: add FL_LAYOUT lease type

This (ab-)uses the file locking code to allow filesystems to recall
outstanding pNFS layouts on a file.  This new lease type is similar but
not quite the same as FL_DELEG.  A FL_LAYOUT lease can always be granted,
an a per-filesystem lock (XFS iolock for the initial implementation)
ensures not FL_LAYOUT leases granted when we would need to recall them.

Also included are changes that allow multiple outstanding read
leases of different types on the same file as long as they have a
differnt owner.  This wasn't a problem until now as nfsd never set
FL_LEASE leases, and no one else used FL_DELEG leases, but given that
nfsd will also issues FL_LAYOUT leases we will have to handle it now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/locks.c         | 14 ++++++++++----
 include/linux/fs.h | 16 ++++++++++++++++
 2 files changed, 26 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index 22ac7694cc8..4753218f308 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -137,7 +137,7 @@
 
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
-#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG))
+#define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
 #define IS_OFDLCK(fl)	(fl->fl_flags & FL_OFDLCK)
 
 static bool lease_breaking(struct file_lock *fl)
@@ -1371,6 +1371,8 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose)
 
 static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
 {
+	if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT))
+		return false;
 	if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE))
 		return false;
 	return locks_conflict(breaker, lease);
@@ -1594,11 +1596,14 @@ int fcntl_getlease(struct file *filp)
  * conflict with the lease we're trying to set.
  */
 static int
-check_conflicting_open(const struct dentry *dentry, const long arg)
+check_conflicting_open(const struct dentry *dentry, const long arg, int flags)
 {
 	int ret = 0;
 	struct inode *inode = dentry->d_inode;
 
+	if (flags & FL_LAYOUT)
+		return 0;
+
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
 		return -EAGAIN;
 
@@ -1647,7 +1652,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 
 	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
-	error = check_conflicting_open(dentry, arg);
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
 	if (error)
 		goto out;
 
@@ -1703,7 +1708,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
 	 * precedes these checks.
 	 */
 	smp_mb();
-	error = check_conflicting_open(dentry, arg);
+	error = check_conflicting_open(dentry, arg, lease->fl_flags);
 	if (error) {
 		locks_unlink_lock_ctx(lease, &ctx->flc_lease_cnt);
 		goto out;
@@ -1787,6 +1792,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
 			WARN_ON_ONCE(1);
 			return -ENOLCK;
 		}
+
 		return generic_add_lease(filp, arg, flp, priv);
 	default:
 		return -EINVAL;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ddd2fa7cefd..84740145f83 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -875,6 +875,7 @@ static inline struct file *get_file(struct file *f)
 #define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
 #define FL_UNLOCK_PENDING	512 /* Lease is being broken */
 #define FL_OFDLCK	1024	/* lock is "owned" by struct file */
+#define FL_LAYOUT	2048	/* outstanding pNFS layout */
 
 /*
  * Special return value from posix_lock_file() and vfs_lock_file() for
@@ -2037,6 +2038,16 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 	return ret;
 }
 
+static inline int break_layout(struct inode *inode, bool wait)
+{
+	smp_mb();
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
+		return __break_lease(inode,
+				wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
+				FL_LAYOUT);
+	return 0;
+}
+
 #else /* !CONFIG_FILE_LOCKING */
 static inline int locks_mandatory_locked(struct file *file)
 {
@@ -2092,6 +2103,11 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 	return 0;
 }
 
+static inline int break_layout(struct inode *inode, bool wait)
+{
+	return 0;
+}
+
 #endif /* CONFIG_FILE_LOCKING */
 
 /* fs/open.c */
-- 
cgit v1.2.3-70-g09d2


From 9cf514ccfacb301f3b1b4509a8ce25dffad55880 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 5 May 2014 13:11:59 +0200
Subject: nfsd: implement pNFS operations

Add support for the GETDEVICEINFO, LAYOUTGET, LAYOUTCOMMIT and
LAYOUTRETURN NFSv4.1 operations, as well as backing code to manage
outstanding layouts and devices.

Layout management is very straight forward, with a nfs4_layout_stateid
structure that extends nfs4_stid to manage layout stateids as the
top-level structure.  It is linked into the nfs4_file and nfs4_client
structures like the other stateids, and contains a linked list of
layouts that hang of the stateid.  The actual layout operations are
implemented in layout drivers that are not part of this commit, but
will be added later.

The worst part of this commit is the management of the pNFS device IDs,
which suffers from a specification that is not sanely implementable due
to the fact that the device-IDs are global and not bound to an export,
and have a small enough size so that we can't store the fsid portion of
a file handle, and must never be reused.  As we still do need perform all
export authentication and validation checks on a device ID passed to
GETDEVICEINFO we are caught between a rock and a hard place.  To work
around this issue we add a new hash that maps from a 64-bit integer to a
fsid so that we can look up the export to authenticate against it,
a 32-bit integer as a generation that we can bump when changing the device,
and a currently unused 32-bit integer that could be used in the future
to handle more than a single device per export.  Entries in this hash
table are never deleted as we can't reuse the ids anyway, and would have
a severe lifetime problem anyway as Linux export structures are temporary
structures that can go away under load.

Parts of the XDR data, structures and marshaling/unmarshaling code, as
well as many concepts are derived from the old pNFS server implementation
from Andy Adamson, Benny Halevy, Dean Hildebrand, Marc Eshel, Fred Isaman,
Mike Sager, Ricardo Labiaga and many others.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/nfsd/Kconfig                  |  10 +
 fs/nfsd/Makefile                 |   1 +
 fs/nfsd/export.c                 |   8 +
 fs/nfsd/export.h                 |   2 +
 fs/nfsd/nfs4layouts.c            | 487 +++++++++++++++++++++++++++++++++++++++
 fs/nfsd/nfs4proc.c               | 302 ++++++++++++++++++++++++
 fs/nfsd/nfs4state.c              |  16 +-
 fs/nfsd/nfs4xdr.c                | 312 +++++++++++++++++++++++++
 fs/nfsd/nfsctl.c                 |   9 +-
 fs/nfsd/nfsd.h                   |  16 +-
 fs/nfsd/pnfs.h                   |  80 +++++++
 fs/nfsd/state.h                  |  21 ++
 fs/nfsd/xdr4.h                   |  59 +++++
 include/linux/nfs4.h             |   1 +
 include/uapi/linux/nfsd/debug.h  |   1 +
 include/uapi/linux/nfsd/export.h |   4 +-
 16 files changed, 1324 insertions(+), 5 deletions(-)
 create mode 100644 fs/nfsd/nfs4layouts.c
 create mode 100644 fs/nfsd/pnfs.h

(limited to 'include')

diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 73395156bdb..683bf718aea 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -82,6 +82,16 @@ config NFSD_V4
 
 	  If unsure, say N.
 
+config NFSD_PNFS
+	bool "NFSv4.1 server support for Parallel NFS (pNFS)"
+	depends on NFSD_V4
+	help
+	  This option enables support for the parallel NFS features of the
+	  minor version 1 of the NFSv4 protocol (RFC5661) in the kernel's NFS
+	  server.
+
+	  If unsure, say N.
+
 config NFSD_V4_SECURITY_LABEL
 	bool "Provide Security Label support for NFSv4 server"
 	depends on NFSD_V4 && SECURITY
diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile
index af32ef06b4f..5806270a856 100644
--- a/fs/nfsd/Makefile
+++ b/fs/nfsd/Makefile
@@ -12,3 +12,4 @@ nfsd-$(CONFIG_NFSD_V3)	+= nfs3proc.o nfs3xdr.o
 nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o
 nfsd-$(CONFIG_NFSD_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \
 			   nfs4acl.o nfs4callback.o nfs4recover.o
+nfsd-$(CONFIG_NFSD_PNFS) += nfs4layouts.o
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 30a739d896f..c3e3b6e55ae 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -20,6 +20,7 @@
 #include "nfsd.h"
 #include "nfsfh.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
@@ -545,6 +546,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 
 	exp.ex_client = dom;
 	exp.cd = cd;
+	exp.ex_devid_map = NULL;
 
 	/* expiry */
 	err = -EINVAL;
@@ -621,6 +623,8 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		if (!gid_valid(exp.ex_anon_gid))
 			goto out4;
 		err = 0;
+
+		nfsd4_setup_layout_type(&exp);
 	}
 
 	expp = svc_export_lookup(&exp);
@@ -703,6 +707,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_fslocs.locations = NULL;
 	new->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = 0;
+	new->ex_layout_type = 0;
 	new->ex_uuid = NULL;
 	new->cd = item->cd;
 }
@@ -717,6 +722,8 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	new->ex_anon_uid = item->ex_anon_uid;
 	new->ex_anon_gid = item->ex_anon_gid;
 	new->ex_fsid = item->ex_fsid;
+	new->ex_devid_map = item->ex_devid_map;
+	item->ex_devid_map = NULL;
 	new->ex_uuid = item->ex_uuid;
 	item->ex_uuid = NULL;
 	new->ex_fslocs.locations = item->ex_fslocs.locations;
@@ -725,6 +732,7 @@ static void export_update(struct cache_head *cnew, struct cache_head *citem)
 	item->ex_fslocs.locations_count = 0;
 	new->ex_fslocs.migrated = item->ex_fslocs.migrated;
 	item->ex_fslocs.migrated = 0;
+	new->ex_layout_type = item->ex_layout_type;
 	new->ex_nflavors = item->ex_nflavors;
 	for (i = 0; i < MAX_SECINFO_LIST; i++) {
 		new->ex_flavors[i] = item->ex_flavors[i];
diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
index 04dc8c167b0..1f52bfcc436 100644
--- a/fs/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -56,6 +56,8 @@ struct svc_export {
 	struct nfsd4_fs_locations ex_fslocs;
 	uint32_t		ex_nflavors;
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
+	enum pnfs_layouttype	ex_layout_type;
+	struct nfsd4_deviceid_map *ex_devid_map;
 	struct cache_detail	*cd;
 };
 
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
new file mode 100644
index 00000000000..8273270418b
--- /dev/null
+++ b/fs/nfsd/nfs4layouts.c
@@ -0,0 +1,487 @@
+/*
+ * Copyright (c) 2014 Christoph Hellwig.
+ */
+#include <linux/jhash.h>
+#include <linux/sched.h>
+
+#include "pnfs.h"
+#include "netns.h"
+
+#define NFSDDBG_FACILITY                NFSDDBG_PNFS
+
+struct nfs4_layout {
+	struct list_head		lo_perstate;
+	struct nfs4_layout_stateid	*lo_state;
+	struct nfsd4_layout_seg		lo_seg;
+};
+
+static struct kmem_cache *nfs4_layout_cache;
+static struct kmem_cache *nfs4_layout_stateid_cache;
+
+const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
+};
+
+/* pNFS device ID to export fsid mapping */
+#define DEVID_HASH_BITS	8
+#define DEVID_HASH_SIZE	(1 << DEVID_HASH_BITS)
+#define DEVID_HASH_MASK	(DEVID_HASH_SIZE - 1)
+static u64 nfsd_devid_seq = 1;
+static struct list_head nfsd_devid_hash[DEVID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfsd_devid_lock);
+
+static inline u32 devid_hashfn(u64 idx)
+{
+	return jhash_2words(idx, idx >> 32, 0) & DEVID_HASH_MASK;
+}
+
+static void
+nfsd4_alloc_devid_map(const struct svc_fh *fhp)
+{
+	const struct knfsd_fh *fh = &fhp->fh_handle;
+	size_t fsid_len = key_len(fh->fh_fsid_type);
+	struct nfsd4_deviceid_map *map, *old;
+	int i;
+
+	map = kzalloc(sizeof(*map) + fsid_len, GFP_KERNEL);
+	if (!map)
+		return;
+
+	map->fsid_type = fh->fh_fsid_type;
+	memcpy(&map->fsid, fh->fh_fsid, fsid_len);
+
+	spin_lock(&nfsd_devid_lock);
+	if (fhp->fh_export->ex_devid_map)
+		goto out_unlock;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		list_for_each_entry(old, &nfsd_devid_hash[i], hash) {
+			if (old->fsid_type != fh->fh_fsid_type)
+				continue;
+			if (memcmp(old->fsid, fh->fh_fsid,
+					key_len(old->fsid_type)))
+				continue;
+
+			fhp->fh_export->ex_devid_map = old;
+			goto out_unlock;
+		}
+	}
+
+	map->idx = nfsd_devid_seq++;
+	list_add_tail_rcu(&map->hash, &nfsd_devid_hash[devid_hashfn(map->idx)]);
+	fhp->fh_export->ex_devid_map = map;
+	map = NULL;
+
+out_unlock:
+	spin_unlock(&nfsd_devid_lock);
+	kfree(map);
+}
+
+struct nfsd4_deviceid_map *
+nfsd4_find_devid_map(int idx)
+{
+	struct nfsd4_deviceid_map *map, *ret = NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(map, &nfsd_devid_hash[devid_hashfn(idx)], hash)
+		if (map->idx == idx)
+			ret = map;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int
+nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation)
+{
+	if (!fhp->fh_export->ex_devid_map) {
+		nfsd4_alloc_devid_map(fhp);
+		if (!fhp->fh_export->ex_devid_map)
+			return -ENOMEM;
+	}
+
+	id->fsid_idx = fhp->fh_export->ex_devid_map->idx;
+	id->generation = device_generation;
+	id->pad = 0;
+	return 0;
+}
+
+void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+	if (exp->ex_flags & NFSEXP_NOPNFS)
+		return;
+}
+
+static void
+nfsd4_free_layout_stateid(struct nfs4_stid *stid)
+{
+	struct nfs4_layout_stateid *ls = layoutstateid(stid);
+	struct nfs4_client *clp = ls->ls_stid.sc_client;
+	struct nfs4_file *fp = ls->ls_stid.sc_file;
+
+	spin_lock(&clp->cl_lock);
+	list_del_init(&ls->ls_perclnt);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_del_init(&ls->ls_perfile);
+	spin_unlock(&fp->fi_lock);
+
+	kmem_cache_free(nfs4_layout_stateid_cache, ls);
+}
+
+static struct nfs4_layout_stateid *
+nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
+		struct nfs4_stid *parent, u32 layout_type)
+{
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_file *fp = parent->sc_file;
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stp;
+
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+	if (!stp)
+		return NULL;
+	stp->sc_free = nfsd4_free_layout_stateid;
+	get_nfs4_file(fp);
+	stp->sc_file = fp;
+
+	ls = layoutstateid(stp);
+	INIT_LIST_HEAD(&ls->ls_perclnt);
+	INIT_LIST_HEAD(&ls->ls_perfile);
+	spin_lock_init(&ls->ls_lock);
+	INIT_LIST_HEAD(&ls->ls_layouts);
+	ls->ls_layout_type = layout_type;
+
+	spin_lock(&clp->cl_lock);
+	stp->sc_type = NFS4_LAYOUT_STID;
+	list_add(&ls->ls_perclnt, &clp->cl_lo_states);
+	spin_unlock(&clp->cl_lock);
+
+	spin_lock(&fp->fi_lock);
+	list_add(&ls->ls_perfile, &fp->fi_lo_states);
+	spin_unlock(&fp->fi_lock);
+
+	return ls;
+}
+
+__be32
+nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_stid *stid;
+	unsigned char typemask = NFS4_LAYOUT_STID;
+	__be32 status;
+
+	if (create)
+		typemask |= (NFS4_OPEN_STID | NFS4_LOCK_STID | NFS4_DELEG_STID);
+
+	status = nfsd4_lookup_stateid(cstate, stateid, typemask, &stid,
+			net_generic(SVC_NET(rqstp), nfsd_net_id));
+	if (status)
+		goto out;
+
+	if (!fh_match(&cstate->current_fh.fh_handle,
+		      &stid->sc_file->fi_fhandle)) {
+		status = nfserr_bad_stateid;
+		goto out_put_stid;
+	}
+
+	if (stid->sc_type != NFS4_LAYOUT_STID) {
+		ls = nfsd4_alloc_layout_stateid(cstate, stid, layout_type);
+		nfs4_put_stid(stid);
+
+		status = nfserr_jukebox;
+		if (!ls)
+			goto out;
+	} else {
+		ls = container_of(stid, struct nfs4_layout_stateid, ls_stid);
+
+		status = nfserr_bad_stateid;
+		if (stateid->si_generation > stid->sc_stateid.si_generation)
+			goto out_put_stid;
+		if (layout_type != ls->ls_layout_type)
+			goto out_put_stid;
+	}
+
+	*lsp = ls;
+	return 0;
+
+out_put_stid:
+	nfs4_put_stid(stid);
+out:
+	return status;
+}
+
+static inline u64
+layout_end(struct nfsd4_layout_seg *seg)
+{
+	u64 end = seg->offset + seg->length;
+	return end >= seg->offset ? end : NFS4_MAX_UINT64;
+}
+
+static void
+layout_update_len(struct nfsd4_layout_seg *lo, u64 end)
+{
+	if (end == NFS4_MAX_UINT64)
+		lo->length = NFS4_MAX_UINT64;
+	else
+		lo->length = end - lo->offset;
+}
+
+static bool
+layouts_overlapping(struct nfs4_layout *lo, struct nfsd4_layout_seg *s)
+{
+	if (s->iomode != IOMODE_ANY && s->iomode != lo->lo_seg.iomode)
+		return false;
+	if (layout_end(&lo->lo_seg) <= s->offset)
+		return false;
+	if (layout_end(s) <= lo->lo_seg.offset)
+		return false;
+	return true;
+}
+
+static bool
+layouts_try_merge(struct nfsd4_layout_seg *lo, struct nfsd4_layout_seg *new)
+{
+	if (lo->iomode != new->iomode)
+		return false;
+	if (layout_end(new) < lo->offset)
+		return false;
+	if (layout_end(lo) < new->offset)
+		return false;
+
+	lo->offset = min(lo->offset, new->offset);
+	layout_update_len(lo, max(layout_end(lo), layout_end(new)));
+	return true;
+}
+
+__be32
+nfsd4_insert_layout(struct nfsd4_layoutget *lgp, struct nfs4_layout_stateid *ls)
+{
+	struct nfsd4_layout_seg *seg = &lgp->lg_seg;
+	struct nfs4_layout *lp, *new = NULL;
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	new = kmem_cache_alloc(nfs4_layout_cache, GFP_KERNEL);
+	if (!new)
+		return nfserr_jukebox;
+	memcpy(&new->lo_seg, seg, sizeof(lp->lo_seg));
+	new->lo_state = ls;
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry(lp, &ls->ls_layouts, lo_perstate) {
+		if (layouts_try_merge(&lp->lo_seg, seg))
+			goto done;
+	}
+
+	atomic_inc(&ls->ls_stid.sc_count);
+	list_add_tail(&new->lo_perstate, &ls->ls_layouts);
+	new = NULL;
+done:
+	update_stateid(&ls->ls_stid.sc_stateid);
+	memcpy(&lgp->lg_sid, &ls->ls_stid.sc_stateid, sizeof(stateid_t));
+	spin_unlock(&ls->ls_lock);
+	if (new)
+		kmem_cache_free(nfs4_layout_cache, new);
+	return nfs_ok;
+}
+
+static void
+nfsd4_free_layouts(struct list_head *reaplist)
+{
+	while (!list_empty(reaplist)) {
+		struct nfs4_layout *lp = list_first_entry(reaplist,
+				struct nfs4_layout, lo_perstate);
+
+		list_del(&lp->lo_perstate);
+		nfs4_put_stid(&lp->lo_state->ls_stid);
+		kmem_cache_free(nfs4_layout_cache, lp);
+	}
+}
+
+static void
+nfsd4_return_file_layout(struct nfs4_layout *lp, struct nfsd4_layout_seg *seg,
+		struct list_head *reaplist)
+{
+	struct nfsd4_layout_seg *lo = &lp->lo_seg;
+	u64 end = layout_end(lo);
+
+	if (seg->offset <= lo->offset) {
+		if (layout_end(seg) >= end) {
+			list_move_tail(&lp->lo_perstate, reaplist);
+			return;
+		}
+		end = seg->offset;
+	} else {
+		/* retain the whole layout segment on a split. */
+		if (layout_end(seg) < end) {
+			dprintk("%s: split not supported\n", __func__);
+			return;
+		}
+
+		lo->offset = layout_end(seg);
+	}
+
+	layout_update_len(lo, end);
+}
+
+__be32
+nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls;
+	struct nfs4_layout *lp, *n;
+	LIST_HEAD(reaplist);
+	__be32 nfserr;
+	int found = 0;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lrp->lr_sid,
+						false, lrp->lr_layout_type,
+						&ls);
+	if (nfserr)
+		return nfserr;
+
+	spin_lock(&ls->ls_lock);
+	list_for_each_entry_safe(lp, n, &ls->ls_layouts, lo_perstate) {
+		if (layouts_overlapping(lp, &lrp->lr_seg)) {
+			nfsd4_return_file_layout(lp, &lrp->lr_seg, &reaplist);
+			found++;
+		}
+	}
+	if (!list_empty(&ls->ls_layouts)) {
+		if (found) {
+			update_stateid(&ls->ls_stid.sc_stateid);
+			memcpy(&lrp->lr_sid, &ls->ls_stid.sc_stateid,
+				sizeof(stateid_t));
+		}
+		lrp->lrs_present = 1;
+	} else {
+		nfs4_unhash_stid(&ls->ls_stid);
+		lrp->lrs_present = 0;
+	}
+	spin_unlock(&ls->ls_lock);
+
+	nfs4_put_stid(&ls->ls_stid);
+	nfsd4_free_layouts(&reaplist);
+	return nfs_ok;
+}
+
+__be32
+nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_layout *lp, *t;
+	LIST_HEAD(reaplist);
+
+	lrp->lrs_present = 0;
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt) {
+		if (lrp->lr_return_type == RETURN_FSID &&
+		    !fh_fsid_match(&ls->ls_stid.sc_file->fi_fhandle,
+				   &cstate->current_fh.fh_handle))
+			continue;
+
+		spin_lock(&ls->ls_lock);
+		list_for_each_entry_safe(lp, t, &ls->ls_layouts, lo_perstate) {
+			if (lrp->lr_seg.iomode == IOMODE_ANY ||
+			    lrp->lr_seg.iomode == lp->lo_seg.iomode)
+				list_move_tail(&lp->lo_perstate, &reaplist);
+		}
+		spin_unlock(&ls->ls_lock);
+	}
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+	return 0;
+}
+
+static void
+nfsd4_return_all_layouts(struct nfs4_layout_stateid *ls,
+		struct list_head *reaplist)
+{
+	spin_lock(&ls->ls_lock);
+	list_splice_init(&ls->ls_layouts, reaplist);
+	spin_unlock(&ls->ls_lock);
+}
+
+void
+nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&clp->cl_lock);
+	list_for_each_entry_safe(ls, n, &clp->cl_lo_states, ls_perclnt)
+		nfsd4_return_all_layouts(ls, &reaplist);
+	spin_unlock(&clp->cl_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+void
+nfsd4_return_all_file_layouts(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_layout_stateid *ls, *n;
+	LIST_HEAD(reaplist);
+
+	spin_lock(&fp->fi_lock);
+	list_for_each_entry_safe(ls, n, &fp->fi_lo_states, ls_perfile) {
+		if (ls->ls_stid.sc_client == clp)
+			nfsd4_return_all_layouts(ls, &reaplist);
+	}
+	spin_unlock(&fp->fi_lock);
+
+	nfsd4_free_layouts(&reaplist);
+}
+
+int
+nfsd4_init_pnfs(void)
+{
+	int i;
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&nfsd_devid_hash[i]);
+
+	nfs4_layout_cache = kmem_cache_create("nfs4_layout",
+			sizeof(struct nfs4_layout), 0, 0, NULL);
+	if (!nfs4_layout_cache)
+		return -ENOMEM;
+
+	nfs4_layout_stateid_cache = kmem_cache_create("nfs4_layout_stateid",
+			sizeof(struct nfs4_layout_stateid), 0, 0, NULL);
+	if (!nfs4_layout_stateid_cache) {
+		kmem_cache_destroy(nfs4_layout_cache);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void
+nfsd4_exit_pnfs(void)
+{
+	int i;
+
+	kmem_cache_destroy(nfs4_layout_cache);
+	kmem_cache_destroy(nfs4_layout_stateid_cache);
+
+	for (i = 0; i < DEVID_HASH_SIZE; i++) {
+		struct nfsd4_deviceid_map *map, *n;
+
+		list_for_each_entry_safe(map, n, &nfsd_devid_hash[i], hash)
+			kfree(map);
+	}
+}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ac71d13c69e..2b91443497c 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -43,6 +43,7 @@
 #include "current_stateid.h"
 #include "netns.h"
 #include "acl.h"
+#include "pnfs.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1178,6 +1179,252 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status == nfserr_same ? nfs_ok : status;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static const struct nfsd4_layout_ops *
+nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
+{
+	if (!exp->ex_layout_type) {
+		dprintk("%s: export does not support pNFS\n", __func__);
+		return NULL;
+	}
+
+	if (exp->ex_layout_type != layout_type) {
+		dprintk("%s: layout type %d not supported\n",
+			__func__, layout_type);
+		return NULL;
+	}
+
+	return nfsd4_layout_ops[layout_type];
+}
+
+static __be32
+nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_getdeviceinfo *gdp)
+{
+	const struct nfsd4_layout_ops *ops;
+	struct nfsd4_deviceid_map *map;
+	struct svc_export *exp;
+	__be32 nfserr;
+
+	dprintk("%s: layout_type %u dev_id [0x%llx:0x%x] maxcnt %u\n",
+	       __func__,
+	       gdp->gd_layout_type,
+	       gdp->gd_devid.fsid_idx, gdp->gd_devid.generation,
+	       gdp->gd_maxcount);
+
+	map = nfsd4_find_devid_map(gdp->gd_devid.fsid_idx);
+	if (!map) {
+		dprintk("%s: couldn't find device ID to export mapping!\n",
+			__func__);
+		return nfserr_noent;
+	}
+
+	exp = rqst_exp_find(rqstp, map->fsid_type, map->fsid);
+	if (IS_ERR(exp)) {
+		dprintk("%s: could not find device id\n", __func__);
+		return nfserr_noent;
+	}
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(exp, gdp->gd_layout_type);
+	if (!ops)
+		goto out;
+
+	nfserr = nfs_ok;
+	if (gdp->gd_maxcount != 0)
+		nfserr = ops->proc_getdeviceinfo(exp->ex_path.mnt->mnt_sb, gdp);
+
+	gdp->gd_notify_types &= ops->notify_types;
+	exp_put(exp);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutget(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutget *lgp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+	int accmode;
+
+	switch (lgp->lg_seg.iomode) {
+	case IOMODE_READ:
+		accmode = NFSD_MAY_READ;
+		break;
+	case IOMODE_RW:
+		accmode = NFSD_MAY_READ | NFSD_MAY_WRITE;
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n",
+			__func__, lgp->lg_seg.iomode);
+		nfserr = nfserr_badiomode;
+		goto out;
+	}
+
+	nfserr = fh_verify(rqstp, current_fh, 0, accmode);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lgp->lg_layout_type);
+	if (!ops)
+		goto out;
+
+	/*
+	 * Verify minlength and range as per RFC5661:
+	 *  o  If loga_length is less than loga_minlength,
+	 *     the metadata server MUST return NFS4ERR_INVAL.
+	 *  o  If the sum of loga_offset and loga_minlength exceeds
+	 *     NFS4_UINT64_MAX, and loga_minlength is not
+	 *     NFS4_UINT64_MAX, the error NFS4ERR_INVAL MUST result.
+	 *  o  If the sum of loga_offset and loga_length exceeds
+	 *     NFS4_UINT64_MAX, and loga_length is not NFS4_UINT64_MAX,
+	 *     the error NFS4ERR_INVAL MUST result.
+	 */
+	nfserr = nfserr_inval;
+	if (lgp->lg_seg.length < lgp->lg_minlength ||
+	    (lgp->lg_minlength != NFS4_MAX_UINT64 &&
+	     lgp->lg_minlength > NFS4_MAX_UINT64 - lgp->lg_seg.offset) ||
+	    (lgp->lg_seg.length != NFS4_MAX_UINT64 &&
+	     lgp->lg_seg.length > NFS4_MAX_UINT64 - lgp->lg_seg.offset))
+		goto out;
+	if (lgp->lg_seg.length == 0)
+		goto out;
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lgp->lg_sid,
+						true, lgp->lg_layout_type, &ls);
+	if (nfserr)
+		goto out;
+
+	nfserr = ops->proc_layoutget(current_fh->fh_dentry->d_inode,
+				     current_fh, lgp);
+	if (nfserr)
+		goto out_put_stid;
+
+	nfserr = nfsd4_insert_layout(lgp, ls);
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutcommit(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutcommit *lcp)
+{
+	const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
+	struct svc_fh *current_fh = &cstate->current_fh;
+	const struct nfsd4_layout_ops *ops;
+	loff_t new_size = lcp->lc_last_wr + 1;
+	struct inode *inode;
+	struct nfs4_layout_stateid *ls;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	ops = nfsd4_layout_verify(current_fh->fh_export, lcp->lc_layout_type);
+	if (!ops)
+		goto out;
+	inode = current_fh->fh_dentry->d_inode;
+
+	nfserr = nfserr_inval;
+	if (new_size <= seg->offset) {
+		dprintk("pnfsd: last write before layout segment\n");
+		goto out;
+	}
+	if (new_size > seg->offset + seg->length) {
+		dprintk("pnfsd: last write beyond layout segment\n");
+		goto out;
+	}
+	if (!lcp->lc_newoffset && new_size > i_size_read(inode)) {
+		dprintk("pnfsd: layoutcommit beyond EOF\n");
+		goto out;
+	}
+
+	nfserr = nfsd4_preprocess_layout_stateid(rqstp, cstate, &lcp->lc_sid,
+						false, lcp->lc_layout_type,
+						&ls);
+	if (nfserr) {
+		/* fixup error code as per RFC5661 */
+		if (nfserr == nfserr_bad_stateid)
+			nfserr = nfserr_badlayout;
+		goto out;
+	}
+
+	nfserr = ops->proc_layoutcommit(inode, lcp);
+	if (nfserr)
+		goto out_put_stid;
+
+	if (new_size > i_size_read(inode)) {
+		lcp->lc_size_chg = 1;
+		lcp->lc_newsize = new_size;
+	} else {
+		lcp->lc_size_chg = 0;
+	}
+
+out_put_stid:
+	nfs4_put_stid(&ls->ls_stid);
+out:
+	return nfserr;
+}
+
+static __be32
+nfsd4_layoutreturn(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct svc_fh *current_fh = &cstate->current_fh;
+	__be32 nfserr;
+
+	nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_NOP);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_layoutunavailable;
+	if (!nfsd4_layout_verify(current_fh->fh_export, lrp->lr_layout_type))
+		goto out;
+
+	switch (lrp->lr_seg.iomode) {
+	case IOMODE_READ:
+	case IOMODE_RW:
+	case IOMODE_ANY:
+		break;
+	default:
+		dprintk("%s: invalid iomode %d\n", __func__,
+			lrp->lr_seg.iomode);
+		nfserr = nfserr_inval;
+		goto out;
+	}
+
+	switch (lrp->lr_return_type) {
+	case RETURN_FILE:
+		nfserr = nfsd4_return_file_layouts(rqstp, cstate, lrp);
+		break;
+	case RETURN_FSID:
+	case RETURN_ALL:
+		nfserr = nfsd4_return_client_layouts(rqstp, cstate, lrp);
+		break;
+	default:
+		dprintk("%s: invalid return_type %d\n", __func__,
+			lrp->lr_return_type);
+		nfserr = nfserr_inval;
+		break;
+	}
+out:
+	return nfserr;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 /*
  * NULL call.
  */
@@ -1679,6 +1926,36 @@ static inline u32 nfsd4_create_session_rsize(struct svc_rqst *rqstp, struct nfsd
 		op_encode_channel_attrs_maxsz) * sizeof(__be32);
 }
 
+#ifdef CONFIG_NFSD_PNFS
+/*
+ * At this stage we don't really know what layout driver will handle the request,
+ * so we need to define an arbitrary upper bound here.
+ */
+#define MAX_LAYOUT_SIZE		128
+static inline u32 nfsd4_layoutget_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* logr_return_on_close */ +
+		op_encode_stateid_maxsz +
+		1 /* nr of layouts */ +
+		MAX_LAYOUT_SIZE) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutcommit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* locr_newsize */ +
+		2 /* ns_size */) * sizeof(__be32);
+}
+
+static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size +
+		1 /* lrs_stateid */ +
+		op_encode_stateid_maxsz) * sizeof(__be32);
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
 		.op_func = (nfsd4op_func)nfsd4_access,
@@ -1966,6 +2243,31 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO] = {
+		.op_func = (nfsd4op_func)nfsd4_getdeviceinfo,
+		.op_flags = ALLOWED_WITHOUT_FH,
+		.op_name = "OP_GETDEVICEINFO",
+	},
+	[OP_LAYOUTGET] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutget,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTGET",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize,
+	},
+	[OP_LAYOUTCOMMIT] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutcommit,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTCOMMIT",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize,
+	},
+	[OP_LAYOUTRETURN] = {
+		.op_func = (nfsd4op_func)nfsd4_layoutreturn,
+		.op_flags = OP_MODIFIES_SOMETHING,
+		.op_name = "OP_LAYOUTRETURN",
+		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize,
+	},
+#endif /* CONFIG_NFSD_PNFS */
 
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE] = {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index eefd29ec43f..c89f79dc69e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -48,6 +48,7 @@
 #include "current_stateid.h"
 
 #include "netns.h"
+#include "pnfs.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -1539,6 +1540,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 	INIT_LIST_HEAD(&clp->cl_lru);
 	INIT_LIST_HEAD(&clp->cl_callbacks);
 	INIT_LIST_HEAD(&clp->cl_revoked);
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&clp->cl_lo_states);
+#endif
 	spin_lock_init(&clp->cl_lock);
 	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
@@ -1643,6 +1647,7 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
+	nfsd4_return_all_client_layouts(clp);
 	nfsd4_shutdown_callback(clp);
 	if (clp->cl_cb_conn.cb_xprt)
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@@ -2126,8 +2131,11 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 static void
 nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid)
 {
-	/* pNFS is not supported */
+#ifdef CONFIG_NFSD_PNFS
+	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS;
+#else
 	new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS;
+#endif
 
 	/* Referrals are supported, Migration is not. */
 	new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER;
@@ -3055,6 +3063,9 @@ static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval,
 	fp->fi_share_deny = 0;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
+#ifdef CONFIG_NFSD_PNFS
+	INIT_LIST_HEAD(&fp->fi_lo_states);
+#endif
 	hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]);
 }
 
@@ -4841,6 +4852,9 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	update_stateid(&stp->st_stid.sc_stateid);
 	memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
 
+	nfsd4_return_all_file_layouts(stp->st_stateowner->so_client,
+				      stp->st_stid.sc_file);
+
 	nfsd4_close_open_stateid(stp);
 
 	/* put reference from nfs4_preprocess_seqid_op */
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 974533e5a42..df5e66caf10 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -47,6 +47,7 @@
 #include "state.h"
 #include "cache.h"
 #include "netns.h"
+#include "pnfs.h"
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #include <linux/security.h>
@@ -1522,6 +1523,127 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_TAIL;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	DECODE_HEAD;
+	u32 num, i;
+
+	READ_BUF(sizeof(struct nfsd4_deviceid) + 3 * 4);
+	COPYMEM(&gdev->gd_devid, sizeof(struct nfsd4_deviceid));
+	gdev->gd_layout_type = be32_to_cpup(p++);
+	gdev->gd_maxcount = be32_to_cpup(p++);
+	num = be32_to_cpup(p++);
+	if (num) {
+		READ_BUF(4 * num);
+		gdev->gd_notify_types = be32_to_cpup(p++);
+		for (i = 1; i < num; i++) {
+			if (be32_to_cpup(p++)) {
+				status = nfserr_inval;
+				goto out;
+			}
+		}
+	}
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutget *lgp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(36);
+	lgp->lg_signal = be32_to_cpup(p++);
+	lgp->lg_layout_type = be32_to_cpup(p++);
+	lgp->lg_seg.iomode = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.offset);
+	p = xdr_decode_hyper(p, &lgp->lg_seg.length);
+	p = xdr_decode_hyper(p, &lgp->lg_minlength);
+	nfsd4_decode_stateid(argp, &lgp->lg_sid);
+	READ_BUF(4);
+	lgp->lg_maxcount = be32_to_cpup(p++);
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutcommit *lcp)
+{
+	DECODE_HEAD;
+	u32 timechange;
+
+	READ_BUF(20);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.offset);
+	p = xdr_decode_hyper(p, &lcp->lc_seg.length);
+	lcp->lc_reclaim = be32_to_cpup(p++);
+	nfsd4_decode_stateid(argp, &lcp->lc_sid);
+	READ_BUF(4);
+	lcp->lc_newoffset = be32_to_cpup(p++);
+	if (lcp->lc_newoffset) {
+		READ_BUF(8);
+		p = xdr_decode_hyper(p, &lcp->lc_last_wr);
+	} else
+		lcp->lc_last_wr = 0;
+	READ_BUF(4);
+	timechange = be32_to_cpup(p++);
+	if (timechange) {
+		status = nfsd4_decode_time(argp, &lcp->lc_mtime);
+		if (status)
+			return status;
+	} else {
+		lcp->lc_mtime.tv_nsec = UTIME_NOW;
+	}
+	READ_BUF(8);
+	lcp->lc_layout_type = be32_to_cpup(p++);
+
+	/*
+	 * Save the layout update in XDR format and let the layout driver deal
+	 * with it later.
+	 */
+	lcp->lc_up_len = be32_to_cpup(p++);
+	if (lcp->lc_up_len > 0) {
+		READ_BUF(lcp->lc_up_len);
+		READMEM(lcp->lc_up_layout, lcp->lc_up_len);
+	}
+
+	DECODE_TAIL;
+}
+
+static __be32
+nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp,
+		struct nfsd4_layoutreturn *lrp)
+{
+	DECODE_HEAD;
+
+	READ_BUF(16);
+	lrp->lr_reclaim = be32_to_cpup(p++);
+	lrp->lr_layout_type = be32_to_cpup(p++);
+	lrp->lr_seg.iomode = be32_to_cpup(p++);
+	lrp->lr_return_type = be32_to_cpup(p++);
+	if (lrp->lr_return_type == RETURN_FILE) {
+		READ_BUF(16);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.offset);
+		p = xdr_decode_hyper(p, &lrp->lr_seg.length);
+		nfsd4_decode_stateid(argp, &lrp->lr_sid);
+		READ_BUF(4);
+		lrp->lrf_body_len = be32_to_cpup(p++);
+		if (lrp->lrf_body_len > 0) {
+			READ_BUF(lrp->lrf_body_len);
+			READMEM(lrp->lrf_body, lrp->lrf_body_len);
+		}
+	} else {
+		lrp->lr_seg.offset = 0;
+		lrp->lr_seg.length = NFS4_MAX_UINT64;
+	}
+
+	DECODE_TAIL;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp,
 		       struct nfsd4_fallocate *fallocate)
@@ -1616,11 +1738,19 @@ static nfsd4_dec nfsd4_dec_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_dec)nfsd4_decode_destroy_session,
 	[OP_FREE_STATEID]	= (nfsd4_dec)nfsd4_decode_free_stateid,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_GETDEVICELIST]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTGET]		= (nfsd4_dec)nfsd4_decode_notsupp,
 	[OP_LAYOUTRETURN]	= (nfsd4_dec)nfsd4_decode_notsupp,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_dec)nfsd4_decode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_dec)nfsd4_decode_sequence,
 	[OP_SET_SSV]		= (nfsd4_dec)nfsd4_decode_notsupp,
@@ -2548,6 +2678,30 @@ out_acl:
 			get_parent_attributes(exp, &stat);
 		p = xdr_encode_hyper(p, stat.ino);
 	}
+#ifdef CONFIG_NFSD_PNFS
+	if ((bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) ||
+	    (bmval2 & FATTR4_WORD2_LAYOUT_TYPES)) {
+		if (exp->ex_layout_type) {
+			p = xdr_reserve_space(xdr, 8);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(1);
+			*p++ = cpu_to_be32(exp->ex_layout_type);
+		} else {
+			p = xdr_reserve_space(xdr, 4);
+			if (!p)
+				goto out_resource;
+			*p++ = cpu_to_be32(0);
+		}
+	}
+
+	if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out_resource;
+		*p++ = cpu_to_be32(stat.blksize);
+	}
+#endif /* CONFIG_NFSD_PNFS */
 	if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
 		status = nfsd4_encode_security_label(xdr, rqstp, context,
 								contextlen);
@@ -3824,6 +3978,156 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 	return nfserr;
 }
 
+#ifdef CONFIG_NFSD_PNFS
+static __be32
+nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_getdeviceinfo *gdev)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[gdev->gd_layout_type];
+	u32 starting_len = xdr->buf->len, needed_len;
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(gdev->gd_layout_type);
+
+	/* If maxcount is 0 then just update notifications */
+	if (gdev->gd_maxcount != 0) {
+		nfserr = ops->encode_getdeviceinfo(xdr, gdev);
+		if (nfserr) {
+			/*
+			 * We don't bother to burden the layout drivers with
+			 * enforcing gd_maxcount, just tell the client to
+			 * come back with a bigger buffer if it's not enough.
+			 */
+			if (xdr->buf->len + 4 > gdev->gd_maxcount)
+				goto toosmall;
+			goto out;
+		}
+	}
+
+	nfserr = nfserr_resource;
+	if (gdev->gd_notify_types) {
+		p = xdr_reserve_space(xdr, 4 + 4);
+		if (!p)
+			goto out;
+		*p++ = cpu_to_be32(1);			/* bitmap length */
+		*p++ = cpu_to_be32(gdev->gd_notify_types);
+	} else {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			goto out;
+		*p++ = 0;
+	}
+
+	nfserr = 0;
+out:
+	kfree(gdev->gd_device);
+	dprintk("%s: done: %d\n", __func__, be32_to_cpu(nfserr));
+	return nfserr;
+
+toosmall:
+	dprintk("%s: maxcount too small\n", __func__);
+	needed_len = xdr->buf->len + 4 /* notifications */;
+	xdr_truncate_encode(xdr, starting_len);
+	p = xdr_reserve_space(xdr, 4);
+	if (!p) {
+		nfserr = nfserr_resource;
+	} else {
+		*p++ = cpu_to_be32(needed_len);
+		nfserr = nfserr_toosmall;
+	}
+	goto out;
+}
+
+static __be32
+nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutget *lgp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	const struct nfsd4_layout_ops *ops =
+		nfsd4_layout_ops[lgp->lg_layout_type];
+	__be32 *p;
+
+	dprintk("%s: err %d\n", __func__, nfserr);
+	if (nfserr)
+		goto out;
+
+	nfserr = nfserr_resource;
+	p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t));
+	if (!p)
+		goto out;
+
+	*p++ = cpu_to_be32(1);	/* we always set return-on-close */
+	*p++ = cpu_to_be32(lgp->lg_sid.si_generation);
+	p = xdr_encode_opaque_fixed(p, &lgp->lg_sid.si_opaque,
+				    sizeof(stateid_opaque_t));
+
+	*p++ = cpu_to_be32(1);	/* we always return a single layout */
+	p = xdr_encode_hyper(p, lgp->lg_seg.offset);
+	p = xdr_encode_hyper(p, lgp->lg_seg.length);
+	*p++ = cpu_to_be32(lgp->lg_seg.iomode);
+	*p++ = cpu_to_be32(lgp->lg_layout_type);
+
+	nfserr = ops->encode_layoutget(xdr, lgp);
+out:
+	kfree(lgp->lg_content);
+	return nfserr;
+}
+
+static __be32
+nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr,
+			  struct nfsd4_layoutcommit *lcp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lcp->lc_size_chg);
+	if (lcp->lc_size_chg) {
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_hyper(p, lcp->lc_newsize);
+	}
+
+	return nfs_ok;
+}
+
+static __be32
+nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
+		struct nfsd4_layoutreturn *lrp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
+
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(lrp->lrs_present);
+	if (lrp->lrs_present)
+		nfsd4_encode_stateid(xdr, &lrp->lr_sid);
+	return nfs_ok;
+}
+#endif /* CONFIG_NFSD_PNFS */
+
 static __be32
 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
 		  struct nfsd4_seek *seek)
@@ -3900,11 +4204,19 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 	[OP_DESTROY_SESSION]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_FREE_STATEID]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GET_DIR_DELEGATION]	= (nfsd4_enc)nfsd4_encode_noop,
+#ifdef CONFIG_NFSD_PNFS
+	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_getdeviceinfo,
+	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
+	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_layoutcommit,
+	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_layoutget,
+	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_layoutreturn,
+#else
 	[OP_GETDEVICEINFO]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_GETDEVICELIST]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTCOMMIT]	= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTGET]		= (nfsd4_enc)nfsd4_encode_noop,
 	[OP_LAYOUTRETURN]	= (nfsd4_enc)nfsd4_encode_noop,
+#endif
 	[OP_SECINFO_NO_NAME]	= (nfsd4_enc)nfsd4_encode_secinfo_no_name,
 	[OP_SEQUENCE]		= (nfsd4_enc)nfsd4_encode_sequence,
 	[OP_SET_SSV]		= (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 19ace74d35f..aa47d75ddb2 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -21,6 +21,7 @@
 #include "cache.h"
 #include "state.h"
 #include "netns.h"
+#include "pnfs.h"
 
 /*
  *	We have a single directory with several nodes in it.
@@ -1258,9 +1259,12 @@ static int __init init_nfsd(void)
 	retval = nfsd4_init_slabs();
 	if (retval)
 		goto out_unregister_pernet;
-	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	retval = nfsd4_init_pnfs();
 	if (retval)
 		goto out_free_slabs;
+	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
+	if (retval)
+		goto out_exit_pnfs;
 	nfsd_stat_init();	/* Statistics */
 	retval = nfsd_reply_cache_init();
 	if (retval)
@@ -1282,6 +1286,8 @@ out_free_lockd:
 out_free_stat:
 	nfsd_stat_shutdown();
 	nfsd_fault_inject_cleanup();
+out_exit_pnfs:
+	nfsd4_exit_pnfs();
 out_free_slabs:
 	nfsd4_free_slabs();
 out_unregister_pernet:
@@ -1299,6 +1305,7 @@ static void __exit exit_nfsd(void)
 	nfsd_stat_shutdown();
 	nfsd_lockd_shutdown();
 	nfsd4_free_slabs();
+	nfsd4_exit_pnfs();
 	nfsd_fault_inject_cleanup();
 	unregister_filesystem(&nfsd_fs_type);
 	unregister_pernet_subsys(&nfsd_net_ops);
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 33a46a8dfaf..565c4da1a9e 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -325,15 +325,27 @@ void		nfsd_lockd_shutdown(void);
 
 #define NFSD4_SUPPORTED_ATTRS_WORD2 0
 
+/* 4.1 */
+#ifdef CONFIG_NFSD_PNFS
+#define PNFSD_SUPPORTED_ATTRS_WORD1	FATTR4_WORD1_FS_LAYOUT_TYPES
+#define PNFSD_SUPPORTED_ATTRS_WORD2 \
+(FATTR4_WORD2_LAYOUT_BLKSIZE	| FATTR4_WORD2_LAYOUT_TYPES)
+#else
+#define PNFSD_SUPPORTED_ATTRS_WORD1	0
+#define PNFSD_SUPPORTED_ATTRS_WORD2	0
+#endif /* CONFIG_NFSD_PNFS */
+
 #define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
 	NFSD4_SUPPORTED_ATTRS_WORD0
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
-	NFSD4_SUPPORTED_ATTRS_WORD1
+	(NFSD4_SUPPORTED_ATTRS_WORD1	| PNFSD_SUPPORTED_ATTRS_WORD1)
 
 #define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
-	(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+	(NFSD4_SUPPORTED_ATTRS_WORD2	| PNFSD_SUPPORTED_ATTRS_WORD2 | \
+	 FATTR4_WORD2_SUPPATTR_EXCLCREAT)
 
+/* 4.2 */
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 #define NFSD4_2_SECURITY_ATTRS		FATTR4_WORD2_SECURITY_LABEL
 #else
diff --git a/fs/nfsd/pnfs.h b/fs/nfsd/pnfs.h
new file mode 100644
index 00000000000..a9616a4e13c
--- /dev/null
+++ b/fs/nfsd/pnfs.h
@@ -0,0 +1,80 @@
+#ifndef _FS_NFSD_PNFS_H
+#define _FS_NFSD_PNFS_H 1
+
+#include <linux/exportfs.h>
+#include <linux/nfsd/export.h>
+
+#include "state.h"
+#include "xdr4.h"
+
+struct xdr_stream;
+
+struct nfsd4_deviceid_map {
+	struct list_head	hash;
+	u64			idx;
+	int			fsid_type;
+	u32			fsid[];
+};
+
+struct nfsd4_layout_ops {
+	u32		notify_types;
+
+	__be32 (*proc_getdeviceinfo)(struct super_block *sb,
+			struct nfsd4_getdeviceinfo *gdevp);
+	__be32 (*encode_getdeviceinfo)(struct xdr_stream *xdr,
+			struct nfsd4_getdeviceinfo *gdevp);
+
+	__be32 (*proc_layoutget)(struct inode *, const struct svc_fh *fhp,
+			struct nfsd4_layoutget *lgp);
+	__be32 (*encode_layoutget)(struct xdr_stream *,
+			struct nfsd4_layoutget *lgp);
+
+	__be32 (*proc_layoutcommit)(struct inode *inode,
+			struct nfsd4_layoutcommit *lcp);
+};
+
+extern const struct nfsd4_layout_ops *nfsd4_layout_ops[];
+
+__be32 nfsd4_preprocess_layout_stateid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, stateid_t *stateid,
+		bool create, u32 layout_type, struct nfs4_layout_stateid **lsp);
+__be32 nfsd4_insert_layout(struct nfsd4_layoutget *lgp,
+		struct nfs4_layout_stateid *ls);
+__be32 nfsd4_return_file_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+__be32 nfsd4_return_client_layouts(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		struct nfsd4_layoutreturn *lrp);
+int nfsd4_set_deviceid(struct nfsd4_deviceid *id, const struct svc_fh *fhp,
+		u32 device_generation);
+struct nfsd4_deviceid_map *nfsd4_find_devid_map(int idx);
+
+#ifdef CONFIG_NFSD_PNFS
+void nfsd4_setup_layout_type(struct svc_export *exp);
+void nfsd4_return_all_client_layouts(struct nfs4_client *);
+void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp);
+int nfsd4_init_pnfs(void);
+void nfsd4_exit_pnfs(void);
+#else
+static inline void nfsd4_setup_layout_type(struct svc_export *exp)
+{
+}
+
+static inline void nfsd4_return_all_client_layouts(struct nfs4_client *clp)
+{
+}
+static inline void nfsd4_return_all_file_layouts(struct nfs4_client *clp,
+		struct nfs4_file *fp)
+{
+}
+static inline void nfsd4_exit_pnfs(void)
+{
+}
+static inline int nfsd4_init_pnfs(void)
+{
+	return 0;
+}
+#endif /* CONFIG_NFSD_PNFS */
+#endif /* _FS_NFSD_PNFS_H */
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 38ebb1268b5..5f66b7fd029 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -92,6 +92,7 @@ struct nfs4_stid {
 /* For a deleg stateid kept around only to process free_stateid's: */
 #define NFS4_REVOKED_DELEG_STID 16
 #define NFS4_CLOSED_DELEG_STID 32
+#define NFS4_LAYOUT_STID 64
 	unsigned char sc_type;
 	stateid_t sc_stateid;
 	struct nfs4_client *sc_client;
@@ -297,6 +298,9 @@ struct nfs4_client {
 	struct list_head	cl_delegations;
 	struct list_head	cl_revoked;	/* unacknowledged, revoked 4.1 state */
 	struct list_head        cl_lru;         /* tail queue */
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	cl_lo_states;	/* outstanding layout states */
+#endif
 	struct xdr_netobj	cl_name; 	/* id generated by client */
 	nfs4_verifier		cl_verifier; 	/* generated by client */
 	time_t                  cl_time;        /* time of last lease renewal */
@@ -496,6 +500,9 @@ struct nfs4_file {
 	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;
+#ifdef CONFIG_NFSD_PNFS
+	struct list_head	fi_lo_states;
+#endif
 };
 
 /*
@@ -528,6 +535,20 @@ static inline struct nfs4_ol_stateid *openlockstateid(struct nfs4_stid *s)
 	return container_of(s, struct nfs4_ol_stateid, st_stid);
 }
 
+struct nfs4_layout_stateid {
+	struct nfs4_stid		ls_stid;
+	struct list_head		ls_perclnt;
+	struct list_head		ls_perfile;
+	spinlock_t			ls_lock;
+	struct list_head		ls_layouts;
+	u32				ls_layout_type;
+};
+
+static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s)
+{
+	return container_of(s, struct nfs4_layout_stateid, ls_stid);
+}
+
 /* flags for preprocess_seqid_op() */
 #define RD_STATE	        0x00000010
 #define WR_STATE	        0x00000020
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 90a5925bd6a..0bda93e58e1 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -428,6 +428,61 @@ struct nfsd4_reclaim_complete {
 	u32 rca_one_fs;
 };
 
+struct nfsd4_deviceid {
+	u64			fsid_idx;
+	u32			generation;
+	u32			pad;
+};
+
+struct nfsd4_layout_seg {
+	u32			iomode;
+	u64			offset;
+	u64			length;
+};
+
+struct nfsd4_getdeviceinfo {
+	struct nfsd4_deviceid	gd_devid;	/* request */
+	u32			gd_layout_type;	/* request */
+	u32			gd_maxcount;	/* request */
+	u32			gd_notify_types;/* request - response */
+	void			*gd_device;	/* response */
+};
+
+struct nfsd4_layoutget {
+	u64			lg_minlength;	/* request */
+	u32			lg_signal;	/* request */
+	u32			lg_layout_type;	/* request */
+	u32			lg_maxcount;	/* request */
+	stateid_t		lg_sid;		/* request/response */
+	struct nfsd4_layout_seg	lg_seg;		/* request/response */
+	void			*lg_content;	/* response */
+};
+
+struct nfsd4_layoutcommit {
+	stateid_t		lc_sid;		/* request */
+	struct nfsd4_layout_seg	lc_seg;		/* request */
+	u32			lc_reclaim;	/* request */
+	u32			lc_newoffset;	/* request */
+	u64			lc_last_wr;	/* request */
+	struct timespec		lc_mtime;	/* request */
+	u32			lc_layout_type;	/* request */
+	u32			lc_up_len;	/* layout length */
+	void			*lc_up_layout;	/* decoded by callback */
+	u32			lc_size_chg;	/* boolean for response */
+	u64			lc_newsize;	/* response */
+};
+
+struct nfsd4_layoutreturn {
+	u32			lr_return_type;	/* request */
+	u32			lr_layout_type;	/* request */
+	struct nfsd4_layout_seg	lr_seg;		/* request */
+	u32			lr_reclaim;	/* request */
+	u32			lrf_body_len;	/* request */
+	void			*lrf_body;	/* request */
+	stateid_t		lr_sid;		/* request/response */
+	u32			lrs_present;	/* response */
+};
+
 struct nfsd4_fallocate {
 	/* request */
 	stateid_t	falloc_stateid;
@@ -491,6 +546,10 @@ struct nfsd4_op {
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
 		struct nfsd4_free_stateid	free_stateid;
+		struct nfsd4_getdeviceinfo	getdeviceinfo;
+		struct nfsd4_layoutget		layoutget;
+		struct nfsd4_layoutcommit	layoutcommit;
+		struct nfsd4_layoutreturn	layoutreturn;
 
 		/* NFSv4.2 */
 		struct nfsd4_fallocate		allocate;
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 8a3589c2542..bc10d687f2c 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -411,6 +411,7 @@ enum lock_type4 {
 #define FATTR4_WORD1_TIME_MODIFY_SET    (1UL << 22)
 #define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
 #define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
+#define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
diff --git a/include/uapi/linux/nfsd/debug.h b/include/uapi/linux/nfsd/debug.h
index 1fdc95bb237..0bf130a1c58 100644
--- a/include/uapi/linux/nfsd/debug.h
+++ b/include/uapi/linux/nfsd/debug.h
@@ -32,6 +32,7 @@
 #define NFSDDBG_REPCACHE	0x0080
 #define NFSDDBG_XDR		0x0100
 #define NFSDDBG_LOCKD		0x0200
+#define NFSDDBG_PNFS		0x0400
 #define NFSDDBG_ALL		0x7FFF
 #define NFSDDBG_NOCHANGE	0xFFFF
 
diff --git a/include/uapi/linux/nfsd/export.h b/include/uapi/linux/nfsd/export.h
index 584b6ef3a5e..4742f2cb42f 100644
--- a/include/uapi/linux/nfsd/export.h
+++ b/include/uapi/linux/nfsd/export.h
@@ -47,8 +47,10 @@
  * exported filesystem.
  */
 #define	NFSEXP_V4ROOT		0x10000
+#define NFSEXP_NOPNFS		0x20000
+
 /* All flags that we claim to support.  (Note we don't support NOACL.) */
-#define NFSEXP_ALLFLAGS		0x1FE7F
+#define NFSEXP_ALLFLAGS		0x3FE7F
 
 /* The flags that may vary depending on security flavor: */
 #define NFSEXP_SECINFO_FLAGS	(NFSEXP_READONLY | NFSEXP_ROOTSQUASH \
-- 
cgit v1.2.3-70-g09d2


From 66f096f79166bcd56fe3c3607a51fb6aeff857b1 Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Mon, 2 Feb 2015 13:23:42 +0200
Subject: Bluetooth: Remove mgmt_rp_read_local_oob_ext_data struct

This extended return parameters struct conflicts with the new Read Local
OOB Extended Data command definition. To avoid the conflict simply
rename the old "extended" version to the normal one and update the code
appropriately to take into account the two possible response PDU sizes.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h |  4 ----
 net/bluetooth/mgmt.c         | 25 +++++++++----------------
 2 files changed, 9 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 95c34d5180f..e218a30f206 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -301,10 +301,6 @@ struct mgmt_cp_user_passkey_neg_reply {
 #define MGMT_OP_READ_LOCAL_OOB_DATA	0x0020
 #define MGMT_READ_LOCAL_OOB_DATA_SIZE	0
 struct mgmt_rp_read_local_oob_data {
-	__u8	hash[16];
-	__u8	rand[16];
-} __packed;
-struct mgmt_rp_read_local_oob_ext_data {
 	__u8	hash192[16];
 	__u8	rand192[16];
 	__u8	hash256[16];
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 9e50b5c09b0..9ec5390c85e 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7168,28 +7168,21 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
 		cmd_status(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA,
 			   mgmt_status(status));
 	} else {
-		if (bredr_sc_enabled(hdev) && hash256 && rand256) {
-			struct mgmt_rp_read_local_oob_ext_data rp;
+		struct mgmt_rp_read_local_oob_data rp;
+		size_t rp_size = sizeof(rp);
 
-			memcpy(rp.hash192, hash192, sizeof(rp.hash192));
-			memcpy(rp.rand192, rand192, sizeof(rp.rand192));
+		memcpy(rp.hash192, hash192, sizeof(rp.hash192));
+		memcpy(rp.rand192, rand192, sizeof(rp.rand192));
 
+		if (bredr_sc_enabled(hdev) && hash256 && rand256) {
 			memcpy(rp.hash256, hash256, sizeof(rp.hash256));
 			memcpy(rp.rand256, rand256, sizeof(rp.rand256));
-
-			cmd_complete(cmd->sk, hdev->id,
-				     MGMT_OP_READ_LOCAL_OOB_DATA, 0,
-				     &rp, sizeof(rp));
 		} else {
-			struct mgmt_rp_read_local_oob_data rp;
-
-			memcpy(rp.hash, hash192, sizeof(rp.hash));
-			memcpy(rp.rand, rand192, sizeof(rp.rand));
-
-			cmd_complete(cmd->sk, hdev->id,
-				     MGMT_OP_READ_LOCAL_OOB_DATA, 0,
-				     &rp, sizeof(rp));
+			rp_size -= sizeof(rp.hash256) + sizeof(rp.rand256);
 		}
+
+		cmd_complete(cmd->sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, 0,
+			     &rp, rp_size);
 	}
 
 	mgmt_pending_remove(cmd);
-- 
cgit v1.2.3-70-g09d2


From d29697dc3b92cb12a80632a5ade4fa26fd98225e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 30 Jan 2015 20:16:37 +0100
Subject: ASoC: Add sysfs entries via static attribute groups

Instead of calling device_create_file() manually, assign the static
attribute group entries at the device registration.  This simplifies
the error handling and avoids the possible races.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h |  2 +-
 sound/soc/soc-core.c     | 58 ++++++++++++++++++++++++++++--------------------
 sound/soc/soc-dapm.c     | 14 ++++--------
 3 files changed, 39 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index 89823cfe6f0..e8e0220404d 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -405,7 +405,7 @@ int snd_soc_dapm_mux_update_power(struct snd_soc_dapm_context *dapm,
 		struct snd_soc_dapm_update *update);
 
 /* dapm sys fs - used by the core */
-int snd_soc_dapm_sys_add(struct device *dev);
+extern struct attribute *soc_dapm_dev_attrs[];
 void snd_soc_dapm_debugfs_init(struct snd_soc_dapm_context *dapm,
 				struct dentry *parent);
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 985052b3fbe..54925dc84a9 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -191,6 +191,39 @@ static ssize_t pmdown_time_set(struct device *dev,
 
 static DEVICE_ATTR(pmdown_time, 0644, pmdown_time_show, pmdown_time_set);
 
+static struct attribute *soc_dev_attrs[] = {
+	&dev_attr_codec_reg.attr,
+	&dev_attr_pmdown_time.attr,
+	NULL
+};
+
+static umode_t soc_dev_attr_is_visible(struct kobject *kobj,
+				       struct attribute *attr, int idx)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct snd_soc_pcm_runtime *rtd = dev_get_drvdata(dev);
+
+	if (attr == &dev_attr_pmdown_time.attr)
+		return attr->mode; /* always visible */
+	return rtd->codec ? attr->mode : 0; /* enabled only with codec */
+}
+
+static const struct attribute_group soc_dapm_dev_group = {
+	.attrs = soc_dapm_dev_attrs,
+	.is_visible = soc_dev_attr_is_visible,
+};
+
+static const struct attribute_group soc_dev_roup = {
+	.attrs = soc_dev_attrs,
+	.is_visible = soc_dev_attr_is_visible,
+};
+
+static const struct attribute_group *soc_dev_attr_groups[] = {
+	&soc_dapm_dev_group,
+	&soc_dev_roup,
+	NULL
+};
+
 #ifdef CONFIG_DEBUG_FS
 static ssize_t codec_reg_read_file(struct file *file, char __user *user_buf,
 				   size_t count, loff_t *ppos)
@@ -949,8 +982,6 @@ static void soc_remove_link_dais(struct snd_soc_card *card, int num, int order)
 
 	/* unregister the rtd device */
 	if (rtd->dev_registered) {
-		device_remove_file(rtd->dev, &dev_attr_pmdown_time);
-		device_remove_file(rtd->dev, &dev_attr_codec_reg);
 		device_unregister(rtd->dev);
 		rtd->dev_registered = 0;
 	}
@@ -1120,6 +1151,7 @@ static int soc_post_component_init(struct snd_soc_pcm_runtime *rtd,
 	device_initialize(rtd->dev);
 	rtd->dev->parent = rtd->card->dev;
 	rtd->dev->release = rtd_release;
+	rtd->dev->groups = soc_dev_attr_groups;
 	dev_set_name(rtd->dev, "%s", name);
 	dev_set_drvdata(rtd->dev, rtd);
 	mutex_init(&rtd->pcm_mutex);
@@ -1136,23 +1168,6 @@ static int soc_post_component_init(struct snd_soc_pcm_runtime *rtd,
 		return ret;
 	}
 	rtd->dev_registered = 1;
-
-	if (rtd->codec) {
-		/* add DAPM sysfs entries for this codec */
-		ret = snd_soc_dapm_sys_add(rtd->dev);
-		if (ret < 0)
-			dev_err(rtd->dev,
-				"ASoC: failed to add codec dapm sysfs entries: %d\n",
-				ret);
-
-		/* add codec sysfs entries */
-		ret = device_create_file(rtd->dev, &dev_attr_codec_reg);
-		if (ret < 0)
-			dev_err(rtd->dev,
-				"ASoC: failed to add codec sysfs files: %d\n",
-				ret);
-	}
-
 	return 0;
 }
 
@@ -1308,11 +1323,6 @@ static int soc_probe_link_dais(struct snd_soc_card *card, int num, int order)
 	}
 #endif
 
-	ret = device_create_file(rtd->dev, &dev_attr_pmdown_time);
-	if (ret < 0)
-		dev_warn(rtd->dev, "ASoC: failed to add pmdown_time sysfs: %d\n",
-			ret);
-
 	if (cpu_dai->driver->compress_dai) {
 		/*create compress_device"*/
 		ret = soc_new_compress(rtd, num);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c5136bb1f98..6c5cf7d1ff5 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2127,15 +2127,10 @@ static ssize_t dapm_widget_show(struct device *dev,
 
 static DEVICE_ATTR(dapm_widget, 0444, dapm_widget_show, NULL);
 
-int snd_soc_dapm_sys_add(struct device *dev)
-{
-	return device_create_file(dev, &dev_attr_dapm_widget);
-}
-
-static void snd_soc_dapm_sys_remove(struct device *dev)
-{
-	device_remove_file(dev, &dev_attr_dapm_widget);
-}
+struct attribute *soc_dapm_dev_attrs[] = {
+	&dev_attr_dapm_widget.attr,
+	NULL
+};
 
 static void dapm_free_path(struct snd_soc_dapm_path *path)
 {
@@ -3903,7 +3898,6 @@ void snd_soc_dapm_auto_nc_pins(struct snd_soc_card *card)
  */
 void snd_soc_dapm_free(struct snd_soc_dapm_context *dapm)
 {
-	snd_soc_dapm_sys_remove(dapm->dev);
 	dapm_debugfs_cleanup(dapm);
 	dapm_free_widgets(dapm);
 	list_del(&dapm->list);
-- 
cgit v1.2.3-70-g09d2


From 4aeee6871e8c3b043ef02996db8ac70a1af8be92 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:08 +0100
Subject: NFC: nci: Add dynamic logical connections support

The current NCI core only support the RF static connection.
For other NFC features such as Secure Element communication, we
may need to create logical connections to the NFCEE (Execution
Environment.

In order to track each logical connection ID dynamically, we add a
linked list of connection info pointers to the nci_dev structure.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h | 32 ++++++++++++++++++++------
 net/nfc/nci/core.c         | 47 ++++++++++++++++++++++++++++++++------
 net/nfc/nci/data.c         | 56 +++++++++++++++++++++++++++++++++-------------
 net/nfc/nci/ntf.c          | 37 +++++++++++++++++++++---------
 net/nfc/nci/rsp.c          | 20 ++++++++++++++++-
 5 files changed, 152 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 9e51bb4d841..5e508741f20 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -82,6 +82,23 @@ struct nci_ops {
 
 #define NCI_MAX_SUPPORTED_RF_INTERFACES		4
 #define NCI_MAX_DISCOVERED_TARGETS		10
+#define NCI_MAX_NUM_NFCEE   255
+#define NCI_MAX_CONN_ID		7
+
+struct nci_conn_info {
+	struct list_head list;
+	__u8	id; /* can be an RF Discovery ID or an NFCEE ID */
+	__u8	conn_id;
+	__u8	max_pkt_payload_len;
+
+	atomic_t credits_cnt;
+	__u8	 initial_num_credits;
+
+	data_exchange_cb_t	data_exchange_cb;
+	void *data_exchange_cb_context;
+
+	struct sk_buff *rx_skb;
+};
 
 /* NCI Core structures */
 struct nci_dev {
@@ -95,7 +112,9 @@ struct nci_dev {
 	unsigned long		flags;
 
 	atomic_t		cmd_cnt;
-	atomic_t		credits_cnt;
+	__u8			cur_conn_id;
+
+	struct list_head	conn_info_list;
 
 	struct timer_list	cmd_timer;
 	struct timer_list	data_timer;
@@ -141,13 +160,10 @@ struct nci_dev {
 	__u8			manufact_id;
 	__u32			manufact_specific_info;
 
-	/* received during NCI_OP_RF_INTF_ACTIVATED_NTF */
-	__u8			max_data_pkt_payload_size;
-	__u8			initial_num_credits;
+	/* Save RF Discovery ID or NFCEE ID under conn_create */
+	__u8			cur_id;
 
 	/* stored during nci_data_exchange */
-	data_exchange_cb_t	data_exchange_cb;
-	void			*data_exchange_cb_context;
 	struct sk_buff		*rx_data_reassembly;
 
 	/* stored during intf_activated_ntf */
@@ -200,7 +216,7 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb);
 int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload);
 int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb);
 void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
-				int err);
+				__u8 conn_id, int err);
 void nci_clear_target_list(struct nci_dev *ndev);
 
 /* ----- NCI requests ----- */
@@ -209,6 +225,8 @@ void nci_clear_target_list(struct nci_dev *ndev);
 #define NCI_REQ_CANCELED	2
 
 void nci_req_complete(struct nci_dev *ndev, int result);
+struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev,
+						   int conn_id);
 
 /* ----- NCI status code ----- */
 int nci_to_errno(__u8 code);
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 51feb5e6300..eb607970bd5 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -45,6 +45,19 @@ static void nci_cmd_work(struct work_struct *work);
 static void nci_rx_work(struct work_struct *work);
 static void nci_tx_work(struct work_struct *work);
 
+struct nci_conn_info *nci_get_conn_info_by_conn_id(struct nci_dev *ndev,
+						   int conn_id)
+{
+	struct nci_conn_info *conn_info;
+
+	list_for_each_entry(conn_info, &ndev->conn_info_list, list) {
+		if (conn_info->conn_id == conn_id)
+			return conn_info;
+	}
+
+	return NULL;
+}
+
 /* ---- NCI requests ---- */
 
 void nci_req_complete(struct nci_dev *ndev, int result)
@@ -712,6 +725,11 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
 	int rc;
+	struct nci_conn_info    *conn_info;
+
+	conn_info = nci_get_conn_info_by_conn_id(ndev, NCI_STATIC_RF_CONN_ID);
+	if (!conn_info)
+		return -EPROTO;
 
 	pr_debug("target_idx %d, len %d\n", target->idx, skb->len);
 
@@ -724,8 +742,8 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 		return -EBUSY;
 
 	/* store cb and context to be used on receiving data */
-	ndev->data_exchange_cb = cb;
-	ndev->data_exchange_cb_context = cb_context;
+	conn_info->data_exchange_cb = cb;
+	conn_info->data_exchange_cb_context = cb_context;
 
 	rc = nci_send_data(ndev, NCI_STATIC_RF_CONN_ID, skb);
 	if (rc)
@@ -913,6 +931,7 @@ int nci_register_device(struct nci_dev *ndev)
 		    (unsigned long) ndev);
 
 	mutex_init(&ndev->req_lock);
+	INIT_LIST_HEAD(&ndev->conn_info_list);
 
 	rc = nfc_register_device(ndev->nfc_dev);
 	if (rc)
@@ -938,12 +957,19 @@ EXPORT_SYMBOL(nci_register_device);
  */
 void nci_unregister_device(struct nci_dev *ndev)
 {
+	struct nci_conn_info    *conn_info, *n;
+
 	nci_close_device(ndev);
 
 	destroy_workqueue(ndev->cmd_wq);
 	destroy_workqueue(ndev->rx_wq);
 	destroy_workqueue(ndev->tx_wq);
 
+	list_for_each_entry_safe(conn_info, n, &ndev->conn_info_list, list) {
+		list_del(&conn_info->list);
+		/* conn_info is allocated with devm_kzalloc */
+	}
+
 	nfc_unregister_device(ndev->nfc_dev);
 }
 EXPORT_SYMBOL(nci_unregister_device);
@@ -1027,20 +1053,25 @@ int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload)
 static void nci_tx_work(struct work_struct *work)
 {
 	struct nci_dev *ndev = container_of(work, struct nci_dev, tx_work);
+	struct nci_conn_info    *conn_info;
 	struct sk_buff *skb;
 
-	pr_debug("credits_cnt %d\n", atomic_read(&ndev->credits_cnt));
+	conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_conn_id);
+	if (!conn_info)
+		return;
+
+	pr_debug("credits_cnt %d\n", atomic_read(&conn_info->credits_cnt));
 
 	/* Send queued tx data */
-	while (atomic_read(&ndev->credits_cnt)) {
+	while (atomic_read(&conn_info->credits_cnt)) {
 		skb = skb_dequeue(&ndev->tx_q);
 		if (!skb)
 			return;
 
 		/* Check if data flow control is used */
-		if (atomic_read(&ndev->credits_cnt) !=
+		if (atomic_read(&conn_info->credits_cnt) !=
 		    NCI_DATA_FLOW_CONTROL_NOT_USED)
-			atomic_dec(&ndev->credits_cnt);
+			atomic_dec(&conn_info->credits_cnt);
 
 		pr_debug("NCI TX: MT=data, PBF=%d, conn_id=%d, plen=%d\n",
 			 nci_pbf(skb->data),
@@ -1092,7 +1123,9 @@ static void nci_rx_work(struct work_struct *work)
 	if (test_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags)) {
 		/* complete the data exchange transaction, if exists */
 		if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
-			nci_data_exchange_complete(ndev, NULL, -ETIMEDOUT);
+			nci_data_exchange_complete(ndev, NULL,
+						   ndev->cur_conn_id,
+						   -ETIMEDOUT);
 
 		clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags);
 	}
diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c
index a2de2a8cb00..566466d9004 100644
--- a/net/nfc/nci/data.c
+++ b/net/nfc/nci/data.c
@@ -36,10 +36,20 @@
 
 /* Complete data exchange transaction and forward skb to nfc core */
 void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
-				int err)
+				__u8 conn_id, int err)
 {
-	data_exchange_cb_t cb = ndev->data_exchange_cb;
-	void *cb_context = ndev->data_exchange_cb_context;
+	struct nci_conn_info    *conn_info;
+	data_exchange_cb_t cb;
+	void *cb_context;
+
+	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
+	if (!conn_info) {
+		kfree_skb(skb);
+		goto exit;
+	}
+
+	cb = conn_info->data_exchange_cb;
+	cb_context = conn_info->data_exchange_cb_context;
 
 	pr_debug("len %d, err %d\n", skb ? skb->len : 0, err);
 
@@ -48,9 +58,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 	clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags);
 
 	if (cb) {
-		ndev->data_exchange_cb = NULL;
-		ndev->data_exchange_cb_context = NULL;
-
 		/* forward skb to nfc core */
 		cb(cb_context, skb, err);
 	} else if (skb) {
@@ -60,6 +67,7 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 		kfree_skb(skb);
 	}
 
+exit:
 	clear_bit(NCI_DATA_EXCHANGE, &ndev->flags);
 }
 
@@ -85,6 +93,7 @@ static inline void nci_push_data_hdr(struct nci_dev *ndev,
 static int nci_queue_tx_data_frags(struct nci_dev *ndev,
 				   __u8 conn_id,
 				   struct sk_buff *skb) {
+	struct nci_conn_info    *conn_info;
 	int total_len = skb->len;
 	unsigned char *data = skb->data;
 	unsigned long flags;
@@ -95,11 +104,17 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev,
 
 	pr_debug("conn_id 0x%x, total_len %d\n", conn_id, total_len);
 
+	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
+	if (!conn_info) {
+		rc = -EPROTO;
+		goto free_exit;
+	}
+
 	__skb_queue_head_init(&frags_q);
 
 	while (total_len) {
 		frag_len =
-			min_t(int, total_len, ndev->max_data_pkt_payload_size);
+			min_t(int, total_len, conn_info->max_pkt_payload_len);
 
 		skb_frag = nci_skb_alloc(ndev,
 					 (NCI_DATA_HDR_SIZE + frag_len),
@@ -151,12 +166,19 @@ exit:
 /* Send NCI data */
 int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	int rc = 0;
 
 	pr_debug("conn_id 0x%x, plen %d\n", conn_id, skb->len);
 
+	conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id);
+	if (!conn_info) {
+		rc = -EPROTO;
+		goto free_exit;
+	}
+
 	/* check if the packet need to be fragmented */
-	if (skb->len <= ndev->max_data_pkt_payload_size) {
+	if (skb->len <= conn_info->max_pkt_payload_len) {
 		/* no need to fragment packet */
 		nci_push_data_hdr(ndev, conn_id, skb, NCI_PBF_LAST);
 
@@ -170,6 +192,7 @@ int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb)
 		}
 	}
 
+	ndev->cur_conn_id = conn_id;
 	queue_work(ndev->tx_wq, &ndev->tx_work);
 
 	goto exit;
@@ -185,7 +208,7 @@ exit:
 
 static void nci_add_rx_data_frag(struct nci_dev *ndev,
 				 struct sk_buff *skb,
-				 __u8 pbf, __u8 status)
+				 __u8 pbf, __u8 conn_id, __u8 status)
 {
 	int reassembly_len;
 	int err = 0;
@@ -229,16 +252,13 @@ static void nci_add_rx_data_frag(struct nci_dev *ndev,
 	}
 
 exit:
-	if (ndev->nfc_dev->rf_mode == NFC_RF_INITIATOR) {
-		nci_data_exchange_complete(ndev, skb, err);
-	} else if (ndev->nfc_dev->rf_mode == NFC_RF_TARGET) {
+	if (ndev->nfc_dev->rf_mode == NFC_RF_TARGET) {
 		/* Data received in Target mode, forward to nfc core */
 		err = nfc_tm_data_received(ndev->nfc_dev, skb);
 		if (err)
 			pr_err("unable to handle received data\n");
 	} else {
-		pr_err("rf mode unknown\n");
-		kfree_skb(skb);
+		nci_data_exchange_complete(ndev, skb, conn_id, err);
 	}
 }
 
@@ -247,6 +267,8 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u8 pbf = nci_pbf(skb->data);
 	__u8 status = 0;
+	__u8 conn_id = nci_conn_id(skb->data);
+	struct nci_conn_info    *conn_info;
 
 	pr_debug("len %d\n", skb->len);
 
@@ -255,6 +277,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		 nci_conn_id(skb->data),
 		 nci_plen(skb->data));
 
+	conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data));
+	if (!conn_info)
+		return;
+
 	/* strip the nci data header */
 	skb_pull(skb, NCI_DATA_HDR_SIZE);
 
@@ -268,5 +294,5 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		skb_trim(skb, (skb->len - 1));
 	}
 
-	nci_add_rx_data_frag(ndev, skb, pbf, nci_to_errno(status));
+	nci_add_rx_data_frag(ndev, skb, pbf, conn_id, nci_to_errno(status));
 }
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 22e453cb787..28fdbe234bd 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -43,6 +43,7 @@ static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev,
 					     struct sk_buff *skb)
 {
 	struct nci_core_conn_credit_ntf *ntf = (void *) skb->data;
+	struct nci_conn_info	*conn_info;
 	int i;
 
 	pr_debug("num_entries %d\n", ntf->num_entries);
@@ -59,11 +60,13 @@ static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev,
 			 i, ntf->conn_entries[i].conn_id,
 			 ntf->conn_entries[i].credits);
 
-		if (ntf->conn_entries[i].conn_id == NCI_STATIC_RF_CONN_ID) {
-			/* found static rf connection */
-			atomic_add(ntf->conn_entries[i].credits,
-				   &ndev->credits_cnt);
-		}
+		conn_info = nci_get_conn_info_by_conn_id(ndev,
+							 ntf->conn_entries[i].conn_id);
+		if (!conn_info)
+			return;
+
+		atomic_add(ntf->conn_entries[i].credits,
+			   &conn_info->credits_cnt);
 	}
 
 	/* trigger the next tx */
@@ -96,7 +99,7 @@ static void nci_core_conn_intf_error_ntf_packet(struct nci_dev *ndev,
 
 	/* complete the data exchange transaction, if exists */
 	if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
-		nci_data_exchange_complete(ndev, NULL, -EIO);
+		nci_data_exchange_complete(ndev, NULL, ntf->conn_id, -EIO);
 }
 
 static __u8 *nci_extract_rf_params_nfca_passive_poll(struct nci_dev *ndev,
@@ -513,6 +516,7 @@ static int nci_store_general_bytes_nfc_dep(struct nci_dev *ndev,
 static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 					     struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	struct nci_rf_intf_activated_ntf ntf;
 	__u8 *data = skb->data;
 	int err = NCI_STATUS_OK;
@@ -614,11 +618,17 @@ static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 
 exit:
 	if (err == NCI_STATUS_OK) {
-		ndev->max_data_pkt_payload_size = ntf.max_data_pkt_payload_size;
-		ndev->initial_num_credits = ntf.initial_num_credits;
+		conn_info = nci_get_conn_info_by_conn_id(ndev,
+							 NCI_STATIC_RF_CONN_ID);
+		if (!conn_info)
+			return;
+
+		conn_info->max_pkt_payload_len = ntf.max_data_pkt_payload_size;
+		conn_info->initial_num_credits = ntf.initial_num_credits;
 
 		/* set the available credits to initial value */
-		atomic_set(&ndev->credits_cnt, ndev->initial_num_credits);
+		atomic_set(&conn_info->credits_cnt,
+			   conn_info->initial_num_credits);
 
 		/* store general bytes to be reported later in dep_link_up */
 		if (ntf.rf_interface == NCI_RF_INTERFACE_NFC_DEP) {
@@ -661,10 +671,16 @@ exit:
 static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev,
 					 struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	struct nci_rf_deactivate_ntf *ntf = (void *) skb->data;
 
 	pr_debug("entry, type 0x%x, reason 0x%x\n", ntf->type, ntf->reason);
 
+	conn_info =
+		nci_get_conn_info_by_conn_id(ndev, NCI_STATIC_RF_CONN_ID);
+	if (!conn_info)
+		return;
+
 	/* drop tx data queue */
 	skb_queue_purge(&ndev->tx_q);
 
@@ -676,7 +692,8 @@ static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev,
 
 	/* complete the data exchange transaction, if exists */
 	if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags))
-		nci_data_exchange_complete(ndev, NULL, -EIO);
+		nci_data_exchange_complete(ndev, NULL, NCI_STATIC_RF_CONN_ID,
+					   -EIO);
 
 	switch (ntf->type) {
 	case NCI_DEACTIVATE_TYPE_IDLE_MODE:
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index 041de51ccdb..93b91493726 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -140,13 +140,31 @@ static void nci_rf_disc_map_rsp_packet(struct nci_dev *ndev,
 
 static void nci_rf_disc_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
+	struct nci_conn_info    *conn_info;
 	__u8 status = skb->data[0];
 
 	pr_debug("status 0x%x\n", status);
 
-	if (status == NCI_STATUS_OK)
+	if (status == NCI_STATUS_OK) {
 		atomic_set(&ndev->state, NCI_DISCOVERY);
 
+		conn_info = nci_get_conn_info_by_conn_id(ndev,
+							 NCI_STATIC_RF_CONN_ID);
+		if (!conn_info) {
+			conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
+						 sizeof(struct nci_conn_info),
+						 GFP_KERNEL);
+			if (!conn_info) {
+				status = NCI_STATUS_REJECTED;
+				goto exit;
+			}
+			conn_info->conn_id = NCI_STATIC_RF_CONN_ID;
+			INIT_LIST_HEAD(&conn_info->list);
+			list_add(&conn_info->list, &ndev->conn_info_list);
+		}
+	}
+
+exit:
 	nci_req_complete(ndev, status);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 8277f6937ae97c51ced5b54faa4934613c76999c Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:09 +0100
Subject: NFC: nci: Add NCI NFCEE constants

Add NFCEE NCI constant for:
- NFCEE Interface/Protocols
- Destination type
- Destination-specific parameters type
- NFCEE Discovery Action

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index e7257a4653b..6d99e8f7983 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -62,6 +62,25 @@
 #define NCI_STATUS_NFCEE_PROTOCOL_ERROR				0xc2
 #define NCI_STATUS_NFCEE_TIMEOUT_ERROR				0xc3
 
+/* NFCEE Interface/Protocols */
+#define NCI_NFCEE_INTERFACE_APDU           0x00
+#define NCI_NFCEE_INTERFACE_HCI_ACCESS     0x01
+#define NCI_NFCEE_INTERFACE_TYPE3_CMD_SET  0x02
+#define NCI_NFCEE_INTERFACE_TRANSPARENT        0x03
+
+/* Destination type */
+#define NCI_DESTINATION_NFCC_LOOPBACK      0x01
+#define NCI_DESTINATION_REMOTE_NFC_ENDPOINT    0x02
+#define NCI_DESTINATION_NFCEE              0x03
+
+/* Destination-specific parameters type */
+#define NCI_DESTINATION_SPECIFIC_PARAM_RF_TYPE     0x00
+#define NCI_DESTINATION_SPECIFIC_PARAM_NFCEE_TYPE  0x01
+
+/* NFCEE Discovery Action */
+#define NCI_NFCEE_DISCOVERY_ACTION_DISABLE			0x00
+#define NCI_NFCEE_DISCOVERY_ACTION_ENABLE			0x01
+
 /* NCI RF Technology and Mode */
 #define NCI_NFC_A_PASSIVE_POLL_MODE				0x00
 #define NCI_NFC_B_PASSIVE_POLL_MODE				0x01
@@ -260,6 +279,11 @@ struct nci_rf_deactivate_cmd {
 	__u8	type;
 } __packed;
 
+#define NCI_OP_NFCEE_DISCOVER_CMD nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x00)
+struct nci_nfcee_discover_cmd {
+	__u8	discovery_action;
+} __packed;
+
 /* ----------------------- */
 /* ---- NCI Responses ---- */
 /* ----------------------- */
@@ -303,6 +327,12 @@ struct nci_core_set_config_rsp {
 
 #define NCI_OP_RF_DEACTIVATE_RSP	nci_opcode_pack(NCI_GID_RF_MGMT, 0x06)
 
+#define NCI_OP_NFCEE_DISCOVER_RSP nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x00)
+struct nci_nfcee_discover_rsp {
+	__u8	status;
+	__u8	num_nfcee;
+} __packed;
+
 /* --------------------------- */
 /* ---- NCI Notifications ---- */
 /* --------------------------- */
@@ -430,4 +460,22 @@ struct nci_rf_deactivate_ntf {
 	__u8	reason;
 } __packed;
 
+#define NCI_OP_NFCEE_DISCOVER_NTF nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x00)
+struct nci_nfcee_supported_protocol {
+	__u8	num_protocol;
+	__u8	supported_protocol[0];
+} __packed;
+
+struct nci_nfcee_information_tlv {
+	__u8	num_tlv;
+	__u8	information_tlv[0];
+} __packed;
+
+struct nci_nfcee_discover_ntf {
+	__u8	nfcee_id;
+	__u8	nfcee_status;
+	struct nci_nfcee_supported_protocol supported_protocols;
+	struct nci_nfcee_information_tlv	information_tlv;
+} __packed;
+
 #endif /* __NCI_H */
-- 
cgit v1.2.3-70-g09d2


From af9c8aa67d07adcd3b41fb2934af7af056eabecf Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:10 +0100
Subject: NFC: nci: Add NFCEE discover support

NFCEEs (NFC Execution Environment) have to be explicitly
discovered by sending the NCI_OP_NFCEE_DISCOVER_CMD
command. The NFCC will respond to this command by telling
us how many NFCEEs are connected to it. Then the NFCC sends
a notification command for each and every NFCEE connected.
Here we implement support for sending
NCI_OP_NFCEE_DISCOVER_CMD command, receiving the response
and the potential notifications.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h |  4 ++++
 net/nfc/nci/core.c         | 17 +++++++++++++++++
 net/nfc/nci/ntf.c          | 30 ++++++++++++++++++++++++++++++
 net/nfc/nci/rsp.c          | 21 +++++++++++++++++++++
 4 files changed, 72 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 5e508741f20..31ad795aa4b 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -100,6 +100,8 @@ struct nci_conn_info {
 	struct sk_buff *rx_skb;
 };
 
+#define NCI_INVALID_CONN_ID 0x80
+
 /* NCI Core structures */
 struct nci_dev {
 	struct nfc_dev		*nfc_dev;
@@ -182,6 +184,8 @@ void nci_unregister_device(struct nci_dev *ndev);
 int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb);
 int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val);
 
+int nci_nfcee_discover(struct nci_dev *ndev, u8 action);
+
 static inline struct sk_buff *nci_skb_alloc(struct nci_dev *ndev,
 					    unsigned int len,
 					    gfp_t how)
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index eb607970bd5..a2585754852 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -469,6 +469,23 @@ int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val)
 }
 EXPORT_SYMBOL(nci_set_config);
 
+static void nci_nfcee_discover_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct nci_nfcee_discover_cmd cmd;
+	__u8 action = opt;
+
+	cmd.discovery_action = action;
+
+	nci_send_cmd(ndev, NCI_OP_NFCEE_DISCOVER_CMD, 1, &cmd);
+}
+
+int nci_nfcee_discover(struct nci_dev *ndev, u8 action)
+{
+	return nci_request(ndev, nci_nfcee_discover_req, action,
+				msecs_to_jiffies(NCI_CMD_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_nfcee_discover);
+
 static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 28fdbe234bd..4c0be7e82d2 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -713,6 +713,33 @@ static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev,
 	nci_req_complete(ndev, NCI_STATUS_OK);
 }
 
+static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev,
+					  struct sk_buff *skb)
+{
+	u8 status = NCI_STATUS_OK;
+	struct nci_conn_info    *conn_info;
+	struct nci_nfcee_discover_ntf   *nfcee_ntf =
+				(struct nci_nfcee_discover_ntf *)skb->data;
+
+	pr_debug("\n");
+
+	conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
+				 sizeof(struct nci_conn_info), GFP_KERNEL);
+	if (!conn_info) {
+		status = NCI_STATUS_REJECTED;
+		goto exit;
+	}
+
+	conn_info->id = nfcee_ntf->nfcee_id;
+	conn_info->conn_id = NCI_INVALID_CONN_ID;
+
+	INIT_LIST_HEAD(&conn_info->list);
+	list_add(&conn_info->list, &ndev->conn_info_list);
+
+exit:
+	nci_req_complete(ndev, status);
+}
+
 void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u16 ntf_opcode = nci_opcode(skb->data);
@@ -751,6 +778,9 @@ void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		nci_rf_deactivate_ntf_packet(ndev, skb);
 		break;
 
+	case NCI_OP_NFCEE_DISCOVER_NTF:
+		nci_nfcee_discover_ntf_packet(ndev, skb);
+		break;
 	default:
 		pr_err("unknown ntf opcode 0x%x\n", ntf_opcode);
 		break;
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index 93b91493726..ee094dfab2e 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -196,6 +196,23 @@ static void nci_rf_deactivate_rsp_packet(struct nci_dev *ndev,
 	}
 }
 
+static void nci_nfcee_discover_rsp_packet(struct nci_dev *ndev,
+					  struct sk_buff *skb)
+{
+	struct nci_nfcee_discover_rsp *discover_rsp;
+
+	if (skb->len != 2) {
+		nci_req_complete(ndev, NCI_STATUS_NFCEE_PROTOCOL_ERROR);
+		return;
+	}
+
+	discover_rsp = (struct nci_nfcee_discover_rsp *)skb->data;
+
+	if (discover_rsp->status != NCI_STATUS_OK ||
+	    discover_rsp->num_nfcee == 0)
+		nci_req_complete(ndev, discover_rsp->status);
+}
+
 void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u16 rsp_opcode = nci_opcode(skb->data);
@@ -241,6 +258,10 @@ void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		nci_rf_deactivate_rsp_packet(ndev, skb);
 		break;
 
+	case NCI_OP_NFCEE_DISCOVER_RSP:
+		nci_nfcee_discover_rsp_packet(ndev, skb);
+		break;
+
 	default:
 		pr_err("unknown rsp opcode 0x%x\n", rsp_opcode);
 		break;
-- 
cgit v1.2.3-70-g09d2


From f7f793f31378d5e83276871339c2a8374b0e8657 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:11 +0100
Subject: NFC: nci: Add NFCEE enabling and disabling support

NFCEEs can be enabled or disabled by sending the
NCI_OP_NFCEE_MODE_SET_CMD command to the NFCC. This patch
provides an API for drivers to enable and disable e.g. their
NCI discoveredd secure elements.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h      |  9 +++++++++
 include/net/nfc/nci_core.h |  1 +
 net/nfc/nci/core.c         | 21 +++++++++++++++++++++
 net/nfc/nci/rsp.c          | 13 +++++++++++++
 4 files changed, 44 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 6d99e8f7983..230f227bb31 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -284,6 +284,14 @@ struct nci_nfcee_discover_cmd {
 	__u8	discovery_action;
 } __packed;
 
+#define NCI_OP_NFCEE_MODE_SET_CMD nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x01)
+#define NCI_NFCEE_DISABLE	0x00
+#define NCI_NFCEE_ENABLE	0x01
+struct nci_nfcee_mode_set_cmd {
+	__u8	nfcee_id;
+	__u8	nfcee_mode;
+} __packed;
+
 /* ----------------------- */
 /* ---- NCI Responses ---- */
 /* ----------------------- */
@@ -333,6 +341,7 @@ struct nci_nfcee_discover_rsp {
 	__u8	num_nfcee;
 } __packed;
 
+#define NCI_OP_NFCEE_MODE_SET_RSP nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x01)
 /* --------------------------- */
 /* ---- NCI Notifications ---- */
 /* --------------------------- */
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 31ad795aa4b..6cf6ee2b696 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -185,6 +185,7 @@ int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb);
 int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val);
 
 int nci_nfcee_discover(struct nci_dev *ndev, u8 action);
+int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode);
 
 static inline struct sk_buff *nci_skb_alloc(struct nci_dev *ndev,
 					    unsigned int len,
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index a2585754852..e5fb8c8eed9 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -486,6 +486,27 @@ int nci_nfcee_discover(struct nci_dev *ndev, u8 action)
 }
 EXPORT_SYMBOL(nci_nfcee_discover);
 
+static void nci_nfcee_mode_set_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct nci_nfcee_mode_set_cmd *cmd =
+					(struct nci_nfcee_mode_set_cmd *)opt;
+
+	nci_send_cmd(ndev, NCI_OP_NFCEE_MODE_SET_CMD,
+		     sizeof(struct nci_nfcee_mode_set_cmd), cmd);
+}
+
+int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode)
+{
+	struct nci_nfcee_mode_set_cmd cmd;
+
+	cmd.nfcee_id = nfcee_id;
+	cmd.nfcee_mode = nfcee_mode;
+
+	return nci_request(ndev, nci_nfcee_mode_set_req, (unsigned long)&cmd,
+			   msecs_to_jiffies(NCI_CMD_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_nfcee_mode_set);
+
 static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index ee094dfab2e..0a3e98240dd 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -213,6 +213,15 @@ static void nci_nfcee_discover_rsp_packet(struct nci_dev *ndev,
 		nci_req_complete(ndev, discover_rsp->status);
 }
 
+static void nci_nfcee_mode_set_rsp_packet(struct nci_dev *ndev,
+					  struct sk_buff *skb)
+{
+	__u8 status = skb->data[0];
+
+	pr_debug("status 0x%x\n", status);
+	nci_req_complete(ndev, status);
+}
+
 void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u16 rsp_opcode = nci_opcode(skb->data);
@@ -262,6 +271,10 @@ void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		nci_nfcee_discover_rsp_packet(ndev, skb);
 		break;
 
+	case NCI_OP_NFCEE_MODE_SET_RSP:
+		nci_nfcee_mode_set_rsp_packet(ndev, skb);
+		break;
+
 	default:
 		pr_err("unknown rsp opcode 0x%x\n", rsp_opcode);
 		break;
-- 
cgit v1.2.3-70-g09d2


From 736bb9577407d3556d81c3c3cd57581cd3ae10ea Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:12 +0100
Subject: NFC: nci: Support logical connections management

In order to communicate with an NFCEE, we need to open a logical
connection to it, by sending the NCI_OP_CORE_CONN_CREATE_CMD
command to the NFCC. It's left up to the drivers to decide when
to close an already opened logical connection.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h      | 30 +++++++++++++++++++++++++++++
 include/net/nfc/nci_core.h |  3 +++
 net/nfc/nci/core.c         | 38 +++++++++++++++++++++++++++++++++++++
 net/nfc/nci/rsp.c          | 47 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 118 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 230f227bb31..deac78b9a53 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -243,6 +243,26 @@ struct nci_core_set_config_cmd {
 	struct	set_config_param param; /* support 1 param per cmd is enough */
 } __packed;
 
+#define NCI_OP_CORE_CONN_CREATE_CMD	nci_opcode_pack(NCI_GID_CORE, 0x04)
+struct dest_spec_params {
+	__u8	id;
+	__u8	protocol;
+} __packed;
+
+struct core_conn_create_dest_spec_params {
+	__u8	type;
+	__u8	length;
+	struct dest_spec_params value;
+} __packed;
+
+struct nci_core_conn_create_cmd {
+	__u8	destination_type;
+	__u8	number_destination_params;
+	struct core_conn_create_dest_spec_params params;
+} __packed;
+
+#define NCI_OP_CORE_CONN_CLOSE_CMD	nci_opcode_pack(NCI_GID_CORE, 0x05)
+
 #define NCI_OP_RF_DISCOVER_MAP_CMD	nci_opcode_pack(NCI_GID_RF_MGMT, 0x00)
 struct disc_map_config {
 	__u8	rf_protocol;
@@ -327,6 +347,16 @@ struct nci_core_set_config_rsp {
 	__u8	params_id[0];	/* variable size array */
 } __packed;
 
+#define NCI_OP_CORE_CONN_CREATE_RSP	nci_opcode_pack(NCI_GID_CORE, 0x04)
+struct nci_core_conn_create_rsp {
+	__u8	status;
+	__u8	max_ctrl_pkt_payload_len;
+	__u8    credits;
+	__u8	conn_id;
+} __packed;
+
+#define NCI_OP_CORE_CONN_CLOSE_RSP	nci_opcode_pack(NCI_GID_CORE, 0x05)
+
 #define NCI_OP_RF_DISCOVER_MAP_RSP	nci_opcode_pack(NCI_GID_RF_MGMT, 0x00)
 
 #define NCI_OP_RF_DISCOVER_RSP		nci_opcode_pack(NCI_GID_RF_MGMT, 0x03)
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 6cf6ee2b696..8ba3e38e416 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -186,6 +186,9 @@ int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val);
 
 int nci_nfcee_discover(struct nci_dev *ndev, u8 action);
 int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode);
+int nci_core_conn_create(struct nci_dev *ndev,
+			 struct core_conn_create_dest_spec_params *params);
+int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id);
 
 static inline struct sk_buff *nci_skb_alloc(struct nci_dev *ndev,
 					    unsigned int len,
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index e5fb8c8eed9..2a96ed68c7b 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -507,6 +507,44 @@ int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode)
 }
 EXPORT_SYMBOL(nci_nfcee_mode_set);
 
+static void nci_core_conn_create_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct nci_core_conn_create_cmd cmd;
+	struct core_conn_create_dest_spec_params *params =
+				(struct core_conn_create_dest_spec_params *)opt;
+
+	cmd.destination_type = NCI_DESTINATION_NFCEE;
+	cmd.number_destination_params = 1;
+	memcpy(&cmd.params.type, params,
+	       sizeof(struct core_conn_create_dest_spec_params));
+	nci_send_cmd(ndev, NCI_OP_CORE_CONN_CREATE_CMD,
+		     sizeof(struct nci_core_conn_create_cmd), &cmd);
+}
+
+int nci_core_conn_create(struct nci_dev *ndev,
+			 struct core_conn_create_dest_spec_params *params)
+{
+	ndev->cur_id = params->value.id;
+	return nci_request(ndev, nci_core_conn_create_req,
+			(unsigned long)params,
+			msecs_to_jiffies(NCI_CMD_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_core_conn_create);
+
+static void nci_core_conn_close_req(struct nci_dev *ndev, unsigned long opt)
+{
+	__u8 conn_id = opt;
+
+	nci_send_cmd(ndev, NCI_OP_CORE_CONN_CLOSE_CMD, 1, &conn_id);
+}
+
+int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id)
+{
+	return nci_request(ndev, nci_core_conn_close_req, conn_id,
+				msecs_to_jiffies(NCI_CMD_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_core_conn_close);
+
 static int nci_set_local_general_bytes(struct nfc_dev *nfc_dev)
 {
 	struct nci_dev *ndev = nfc_get_drvdata(nfc_dev);
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index 0a3e98240dd..31ccf7d05e8 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -222,6 +222,45 @@ static void nci_nfcee_mode_set_rsp_packet(struct nci_dev *ndev,
 	nci_req_complete(ndev, status);
 }
 
+static void nci_core_conn_create_rsp_packet(struct nci_dev *ndev,
+					    struct sk_buff *skb)
+{
+	__u8 status = skb->data[0];
+	struct nci_conn_info *conn_info;
+	struct nci_core_conn_create_rsp *rsp;
+
+	pr_debug("status 0x%x\n", status);
+
+	if (status == NCI_STATUS_OK) {
+		rsp = (struct nci_core_conn_create_rsp *)skb->data;
+		list_for_each_entry(conn_info, &ndev->conn_info_list, list) {
+			if (conn_info->id == ndev->cur_id)
+				break;
+		}
+
+		if (!conn_info || conn_info->id != ndev->cur_id) {
+			status = NCI_STATUS_REJECTED;
+			goto exit;
+		}
+
+		conn_info->conn_id = rsp->conn_id;
+		conn_info->max_pkt_payload_len = rsp->max_ctrl_pkt_payload_len;
+		atomic_set(&conn_info->credits_cnt, rsp->credits);
+	}
+
+exit:
+	nci_req_complete(ndev, status);
+}
+
+static void nci_core_conn_close_rsp_packet(struct nci_dev *ndev,
+					   struct sk_buff *skb)
+{
+	__u8 status = skb->data[0];
+
+	pr_debug("status 0x%x\n", status);
+	nci_req_complete(ndev, status);
+}
+
 void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u16 rsp_opcode = nci_opcode(skb->data);
@@ -251,6 +290,14 @@ void nci_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		nci_core_set_config_rsp_packet(ndev, skb);
 		break;
 
+	case NCI_OP_CORE_CONN_CREATE_RSP:
+		nci_core_conn_create_rsp_packet(ndev, skb);
+		break;
+
+	case NCI_OP_CORE_CONN_CLOSE_RSP:
+		nci_core_conn_close_rsp_packet(ndev, skb);
+		break;
+
 	case NCI_OP_RF_DISCOVER_MAP_RSP:
 		nci_rf_disc_map_rsp_packet(ndev, skb);
 		break;
-- 
cgit v1.2.3-70-g09d2


From 11f54f228643d0248ec00ce8c9fb8d872f87e7b8 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:14 +0100
Subject: NFC: nci: Add HCI over NCI protocol support

According to the NCI specification, one can use HCI over NCI
to talk with specific NFCEE. The HCI network is viewed as one
logical NFCEE.
This is needed to support secure element running HCI only
firmwares embedded on an NCI capable chipset, like e.g. the
st21nfcb.
There is some duplication between this piece of code and the
HCI core code, but the latter would need to be abstracted even
more to be able to use NCI as a logical transport for HCP packets.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h |  93 ++++++
 net/nfc/nci/Makefile       |   2 +-
 net/nfc/nci/core.c         |  20 +-
 net/nfc/nci/hci.c          | 686 +++++++++++++++++++++++++++++++++++++++++++++
 net/nfc/nci/ntf.c          |  32 ++-
 5 files changed, 815 insertions(+), 18 deletions(-)
 create mode 100644 net/nfc/nci/hci.c

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 8ba3e38e416..be858870dac 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -78,6 +78,11 @@ struct nci_ops {
 	int   (*se_io)(struct nci_dev *ndev, u32 se_idx,
 				u8 *apdu, size_t apdu_length,
 				se_io_cb_t cb, void *cb_context);
+	int   (*hci_load_session)(struct nci_dev *ndev);
+	void  (*hci_event_received)(struct nci_dev *ndev, u8 pipe, u8 event,
+				    struct sk_buff *skb);
+	void  (*hci_cmd_received)(struct nci_dev *ndev, u8 pipe, u8 cmd,
+				  struct sk_buff *skb);
 };
 
 #define NCI_MAX_SUPPORTED_RF_INTERFACES		4
@@ -102,10 +107,77 @@ struct nci_conn_info {
 
 #define NCI_INVALID_CONN_ID 0x80
 
+#define NCI_HCI_ANY_OPEN_PIPE      0x03
+
+/* Gates */
+#define NCI_HCI_ADMIN_GATE         0x00
+#define NCI_HCI_LINK_MGMT_GATE     0x06
+
+/* Pipes */
+#define NCI_HCI_LINK_MGMT_PIPE             0x00
+#define NCI_HCI_ADMIN_PIPE                 0x01
+
+/* Generic responses */
+#define NCI_HCI_ANY_OK                     0x00
+#define NCI_HCI_ANY_E_NOT_CONNECTED        0x01
+#define NCI_HCI_ANY_E_CMD_PAR_UNKNOWN      0x02
+#define NCI_HCI_ANY_E_NOK                  0x03
+#define NCI_HCI_ANY_E_PIPES_FULL           0x04
+#define NCI_HCI_ANY_E_REG_PAR_UNKNOWN      0x05
+#define NCI_HCI_ANY_E_PIPE_NOT_OPENED      0x06
+#define NCI_HCI_ANY_E_CMD_NOT_SUPPORTED    0x07
+#define NCI_HCI_ANY_E_INHIBITED            0x08
+#define NCI_HCI_ANY_E_TIMEOUT              0x09
+#define NCI_HCI_ANY_E_REG_ACCESS_DENIED    0x0a
+#define NCI_HCI_ANY_E_PIPE_ACCESS_DENIED   0x0b
+
+#define NCI_HCI_DO_NOT_OPEN_PIPE           0x81
+#define NCI_HCI_INVALID_PIPE               0x80
+#define NCI_HCI_INVALID_GATE               0xFF
+#define NCI_HCI_INVALID_HOST               0x80
+
+#define NCI_HCI_MAX_CUSTOM_GATES   50
+#define NCI_HCI_MAX_PIPES          127
+
+struct nci_hci_gate {
+	u8 gate;
+	u8 pipe;
+	u8 dest_host;
+} __packed;
+
+struct nci_hci_pipe {
+	u8 gate;
+	u8 host;
+} __packed;
+
+struct nci_hci_init_data {
+	u8 gate_count;
+	struct nci_hci_gate gates[NCI_HCI_MAX_CUSTOM_GATES];
+	char session_id[9];
+};
+
+#define NCI_HCI_MAX_GATES          256
+
+struct nci_hci_dev {
+	struct nci_dev *ndev;
+	struct nci_conn_info *conn_info;
+
+	struct nci_hci_init_data init_data;
+	struct nci_hci_pipe pipes[NCI_HCI_MAX_PIPES];
+	u8 gate2pipe[NCI_HCI_MAX_GATES];
+	int expected_pipes;
+	int count_pipes;
+
+	struct sk_buff_head rx_hcp_frags;
+	struct work_struct msg_rx_work;
+	struct sk_buff_head msg_rx_queue;
+};
+
 /* NCI Core structures */
 struct nci_dev {
 	struct nfc_dev		*nfc_dev;
 	struct nci_ops		*ops;
+	struct nci_hci_dev	*hci_dev;
 
 	int			tx_headroom;
 	int			tx_tailroom;
@@ -181,6 +253,10 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops,
 void nci_free_device(struct nci_dev *ndev);
 int nci_register_device(struct nci_dev *ndev);
 void nci_unregister_device(struct nci_dev *ndev);
+int nci_request(struct nci_dev *ndev,
+		void (*req)(struct nci_dev *ndev,
+			    unsigned long opt),
+		unsigned long opt, __u32 timeout);
 int nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb);
 int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val);
 
@@ -190,6 +266,21 @@ int nci_core_conn_create(struct nci_dev *ndev,
 			 struct core_conn_create_dest_spec_params *params);
 int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id);
 
+struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev);
+int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event,
+		       const u8 *param, size_t param_len);
+int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate,
+		     u8 cmd, const u8 *param, size_t param_len,
+		     struct sk_buff **skb);
+int nci_hci_open_pipe(struct nci_dev *ndev, u8 pipe);
+int nci_hci_connect_gate(struct nci_dev *ndev, u8 dest_host,
+			 u8 dest_gate, u8 pipe);
+int nci_hci_set_param(struct nci_dev *ndev, u8 gate, u8 idx,
+		      const u8 *param, size_t param_len);
+int nci_hci_get_param(struct nci_dev *ndev, u8 gate, u8 idx,
+		      struct sk_buff **skb);
+int nci_hci_dev_session_init(struct nci_dev *ndev);
+
 static inline struct sk_buff *nci_skb_alloc(struct nci_dev *ndev,
 					    unsigned int len,
 					    gfp_t how)
@@ -225,6 +316,8 @@ int nci_send_cmd(struct nci_dev *ndev, __u16 opcode, __u8 plen, void *payload);
 int nci_send_data(struct nci_dev *ndev, __u8 conn_id, struct sk_buff *skb);
 void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb,
 				__u8 conn_id, int err);
+void nci_hci_data_received_cb(void *context, struct sk_buff *skb, int err);
+
 void nci_clear_target_list(struct nci_dev *ndev);
 
 /* ----- NCI requests ----- */
diff --git a/net/nfc/nci/Makefile b/net/nfc/nci/Makefile
index 7aeedc43187..7ed8949266c 100644
--- a/net/nfc/nci/Makefile
+++ b/net/nfc/nci/Makefile
@@ -4,6 +4,6 @@
 
 obj-$(CONFIG_NFC_NCI) += nci.o
 
-nci-objs := core.o data.o lib.o ntf.o rsp.o
+nci-objs := core.o data.o lib.o ntf.o rsp.o hci.o
 
 nci-$(CONFIG_NFC_NCI_SPI) += spi.o
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 2a96ed68c7b..f74d420e2ea 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -122,10 +122,10 @@ static int __nci_request(struct nci_dev *ndev,
 	return rc;
 }
 
-static inline int nci_request(struct nci_dev *ndev,
-			      void (*req)(struct nci_dev *ndev,
-					  unsigned long opt),
-			      unsigned long opt, __u32 timeout)
+inline int nci_request(struct nci_dev *ndev,
+		       void (*req)(struct nci_dev *ndev,
+				   unsigned long opt),
+		       unsigned long opt, __u32 timeout)
 {
 	int rc;
 
@@ -901,7 +901,6 @@ static struct nfc_ops nci_nfc_ops = {
 };
 
 /* ---- Interface to NCI drivers ---- */
-
 /**
  * nci_allocate_device - allocate a new nci device
  *
@@ -936,13 +935,20 @@ struct nci_dev *nci_allocate_device(struct nci_ops *ops,
 					    tx_headroom + NCI_DATA_HDR_SIZE,
 					    tx_tailroom);
 	if (!ndev->nfc_dev)
-		goto free_exit;
+		goto free_nci;
+
+	ndev->hci_dev = nci_hci_allocate(ndev);
+	if (!ndev->hci_dev)
+		goto free_nfc;
 
 	nfc_set_drvdata(ndev->nfc_dev, ndev);
 
 	return ndev;
 
-free_exit:
+free_nfc:
+	kfree(ndev->nfc_dev);
+
+free_nci:
 	kfree(ndev);
 	return NULL;
 }
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
new file mode 100644
index 00000000000..ecf25394260
--- /dev/null
+++ b/net/nfc/nci/hci.c
@@ -0,0 +1,686 @@
+/*
+ *  The NFC Controller Interface is the communication protocol between an
+ *  NFC Controller (NFCC) and a Device Host (DH).
+ *  This is the HCI over NCI implementation, as specified in the 10.2
+ *  section of the NCI 1.1 specification.
+ *
+ *  Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include <linux/skbuff.h>
+
+#include "../nfc.h"
+#include <net/nfc/nci.h>
+#include <net/nfc/nci_core.h>
+#include <linux/nfc.h>
+
+struct nci_data {
+	u8              conn_id;
+	u8              pipe;
+	u8              cmd;
+	const u8        *data;
+	u32             data_len;
+} __packed;
+
+struct nci_hci_create_pipe_params {
+	u8 src_gate;
+	u8 dest_host;
+	u8 dest_gate;
+} __packed;
+
+struct nci_hci_create_pipe_resp {
+	u8 src_host;
+	u8 src_gate;
+	u8 dest_host;
+	u8 dest_gate;
+	u8 pipe;
+} __packed;
+
+struct nci_hci_delete_pipe_noti {
+	u8 pipe;
+} __packed;
+
+struct nci_hci_all_pipe_cleared_noti {
+	u8 host;
+} __packed;
+
+struct nci_hcp_message {
+	u8 header;      /* type -cmd,evt,rsp- + instruction */
+	u8 data[];
+} __packed;
+
+struct nci_hcp_packet {
+	u8 header;      /* cbit+pipe */
+	struct nci_hcp_message message;
+} __packed;
+
+#define NCI_HCI_ANY_SET_PARAMETER  0x01
+#define NCI_HCI_ANY_GET_PARAMETER  0x02
+#define NCI_HCI_ANY_CLOSE_PIPE     0x04
+
+#define NCI_HFP_NO_CHAINING        0x80
+
+#define NCI_NFCEE_ID_HCI                0x80
+
+#define NCI_EVT_HOT_PLUG           0x03
+
+#define NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY       0x01
+
+/* HCP headers */
+#define NCI_HCI_HCP_PACKET_HEADER_LEN      1
+#define NCI_HCI_HCP_MESSAGE_HEADER_LEN     1
+#define NCI_HCI_HCP_HEADER_LEN             2
+
+/* HCP types */
+#define NCI_HCI_HCP_COMMAND        0x00
+#define NCI_HCI_HCP_EVENT          0x01
+#define NCI_HCI_HCP_RESPONSE       0x02
+
+#define NCI_HCI_ADM_NOTIFY_PIPE_CREATED     0x12
+#define NCI_HCI_ADM_NOTIFY_PIPE_DELETED     0x13
+#define NCI_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED 0x15
+
+#define NCI_HCI_FRAGMENT           0x7f
+#define NCI_HCP_HEADER(type, instr) ((((type) & 0x03) << 6) |\
+				      ((instr) & 0x3f))
+
+#define NCI_HCP_MSG_GET_TYPE(header) ((header & 0xc0) >> 6)
+#define NCI_HCP_MSG_GET_CMD(header)  (header & 0x3f)
+#define NCI_HCP_MSG_GET_PIPE(header) (header & 0x7f)
+
+/* HCI core */
+static void nci_hci_reset_pipes(struct nci_hci_dev *hdev)
+{
+	int i;
+
+	for (i = 0; i < NCI_HCI_MAX_PIPES; i++) {
+		hdev->pipes[i].gate = NCI_HCI_INVALID_GATE;
+		hdev->pipes[i].host = NCI_HCI_INVALID_HOST;
+	}
+	memset(hdev->gate2pipe, NCI_HCI_INVALID_PIPE, sizeof(hdev->gate2pipe));
+}
+
+static void nci_hci_reset_pipes_per_host(struct nci_dev *ndev, u8 host)
+{
+	int i;
+
+	for (i = 0; i < NCI_HCI_MAX_PIPES; i++) {
+		if (ndev->hci_dev->pipes[i].host == host) {
+			ndev->hci_dev->pipes[i].gate = NCI_HCI_INVALID_GATE;
+			ndev->hci_dev->pipes[i].host = NCI_HCI_INVALID_HOST;
+		}
+	}
+}
+
+/* Fragment HCI data over NCI packet.
+ * NFC Forum NCI 10.2.2 Data Exchange:
+ * The payload of the Data Packets sent on the Logical Connection SHALL be
+ * valid HCP packets, as defined within [ETSI_102622]. Each Data Packet SHALL
+ * contain a single HCP packet. NCI Segmentation and Reassembly SHALL NOT be
+ * applied to Data Messages in either direction. The HCI fragmentation mechanism
+ * is used if required.
+ */
+static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe,
+			     const u8 data_type, const u8 *data,
+			     size_t data_len)
+{
+	struct nci_conn_info    *conn_info;
+	struct sk_buff *skb;
+	int len, i, r;
+	u8 cb = pipe;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	skb = nci_skb_alloc(ndev, 2 + conn_info->max_pkt_payload_len +
+			    NCI_DATA_HDR_SIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_reserve(skb, 2 + NCI_DATA_HDR_SIZE);
+	*skb_push(skb, 1) = data_type;
+
+	i = 0;
+	len = conn_info->max_pkt_payload_len;
+
+	do {
+		/* If last packet add NCI_HFP_NO_CHAINING */
+		if (i + conn_info->max_pkt_payload_len -
+		    (skb->len + 1) >= data_len) {
+			cb |= NCI_HFP_NO_CHAINING;
+			len = data_len - i;
+		} else {
+			len = conn_info->max_pkt_payload_len - skb->len - 1;
+		}
+
+		*skb_push(skb, 1) = cb;
+
+		if (len > 0)
+			memcpy(skb_put(skb, len), data + i, len);
+
+		r = nci_send_data(ndev, conn_info->conn_id, skb);
+		if (r < 0)
+			return r;
+
+		i += len;
+		if (i < data_len) {
+			skb_trim(skb, 0);
+			skb_pull(skb, len);
+		}
+	} while (i < data_len);
+
+	return i;
+}
+
+static void nci_hci_send_data_req(struct nci_dev *ndev, unsigned long opt)
+{
+	struct nci_data *data = (struct nci_data *)opt;
+
+	nci_hci_send_data(ndev, data->pipe, data->cmd,
+			  data->data, data->data_len);
+}
+
+int nci_hci_send_event(struct nci_dev *ndev, u8 gate, u8 event,
+		       const u8 *param, size_t param_len)
+{
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	return nci_hci_send_data(ndev, pipe,
+			NCI_HCP_HEADER(NCI_HCI_HCP_EVENT, event),
+			param, param_len);
+}
+EXPORT_SYMBOL(nci_hci_send_event);
+
+int nci_hci_send_cmd(struct nci_dev *ndev, u8 gate, u8 cmd,
+		     const u8 *param, size_t param_len,
+		     struct sk_buff **skb)
+{
+	struct nci_conn_info    *conn_info;
+	struct nci_data data;
+	int r;
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND, cmd);
+	data.data = param;
+	data.data_len = param_len;
+
+	r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+
+	if (r == NCI_STATUS_OK)
+		*skb = conn_info->rx_skb;
+
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_send_cmd);
+
+static void nci_hci_event_received(struct nci_dev *ndev, u8 pipe,
+				   u8 event, struct sk_buff *skb)
+{
+	if (ndev->ops->hci_event_received)
+		ndev->ops->hci_event_received(ndev, pipe, event, skb);
+}
+
+static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe,
+				 u8 cmd, struct sk_buff *skb)
+{
+	u8 gate = ndev->hci_dev->pipes[pipe].gate;
+	u8 status = NCI_HCI_ANY_OK | ~NCI_HCI_FRAGMENT;
+	u8 dest_gate, new_pipe;
+	struct nci_hci_create_pipe_resp *create_info;
+	struct nci_hci_delete_pipe_noti *delete_info;
+	struct nci_hci_all_pipe_cleared_noti *cleared_info;
+
+	pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd);
+
+	switch (cmd) {
+	case NCI_HCI_ADM_NOTIFY_PIPE_CREATED:
+		if (skb->len != 5) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		create_info = (struct nci_hci_create_pipe_resp *)skb->data;
+		dest_gate = create_info->dest_gate;
+		new_pipe = create_info->pipe;
+
+		/* Save the new created pipe and bind with local gate,
+		 * the description for skb->data[3] is destination gate id
+		 * but since we received this cmd from host controller, we
+		 * are the destination and it is our local gate
+		 */
+		ndev->hci_dev->gate2pipe[dest_gate] = new_pipe;
+		ndev->hci_dev->pipes[new_pipe].gate = dest_gate;
+		ndev->hci_dev->pipes[new_pipe].host =
+						create_info->src_host;
+		break;
+	case NCI_HCI_ANY_OPEN_PIPE:
+		/* If the pipe is not created report an error */
+		if (gate == NCI_HCI_INVALID_GATE) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		break;
+	case NCI_HCI_ADM_NOTIFY_PIPE_DELETED:
+		if (skb->len != 1) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+		delete_info = (struct nci_hci_delete_pipe_noti *)skb->data;
+
+		ndev->hci_dev->pipes[delete_info->pipe].gate =
+						NCI_HCI_INVALID_GATE;
+		ndev->hci_dev->pipes[delete_info->pipe].host =
+						NCI_HCI_INVALID_HOST;
+		break;
+	case NCI_HCI_ADM_NOTIFY_ALL_PIPE_CLEARED:
+		if (skb->len != 1) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
+
+		cleared_info =
+			(struct nci_hci_all_pipe_cleared_noti *)skb->data;
+		nci_hci_reset_pipes_per_host(ndev, cleared_info->host);
+		break;
+	default:
+		pr_debug("Discarded unknown cmd %x to gate %x\n", cmd, gate);
+		break;
+	}
+
+	if (ndev->ops->hci_cmd_received)
+		ndev->ops->hci_cmd_received(ndev, pipe, cmd, skb);
+
+exit:
+	nci_hci_send_data(ndev, pipe, status, NULL, 0);
+
+	kfree_skb(skb);
+}
+
+static void nci_hci_resp_received(struct nci_dev *ndev, u8 pipe,
+				  u8 result, struct sk_buff *skb)
+{
+	struct nci_conn_info    *conn_info;
+	u8 status = result;
+
+	if (result != NCI_HCI_ANY_OK)
+		goto exit;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info) {
+		status = NCI_STATUS_REJECTED;
+		goto exit;
+	}
+
+	conn_info->rx_skb = skb;
+
+exit:
+	nci_req_complete(ndev, status);
+}
+
+/* Receive hcp message for pipe, with type and cmd.
+ * skb contains optional message data only.
+ */
+static void nci_hci_hcp_message_rx(struct nci_dev *ndev, u8 pipe,
+				   u8 type, u8 instruction, struct sk_buff *skb)
+{
+	switch (type) {
+	case NCI_HCI_HCP_RESPONSE:
+		nci_hci_resp_received(ndev, pipe, instruction, skb);
+		break;
+	case NCI_HCI_HCP_COMMAND:
+		nci_hci_cmd_received(ndev, pipe, instruction, skb);
+		break;
+	case NCI_HCI_HCP_EVENT:
+		nci_hci_event_received(ndev, pipe, instruction, skb);
+		break;
+	default:
+		pr_err("UNKNOWN MSG Type %d, instruction=%d\n",
+		       type, instruction);
+		kfree_skb(skb);
+		break;
+	}
+
+	nci_req_complete(ndev, 0);
+}
+
+static void nci_hci_msg_rx_work(struct work_struct *work)
+{
+	struct nci_hci_dev *hdev =
+		container_of(work, struct nci_hci_dev, msg_rx_work);
+	struct sk_buff *skb;
+	struct nci_hcp_message *message;
+	u8 pipe, type, instruction;
+
+	while ((skb = skb_dequeue(&hdev->msg_rx_queue)) != NULL) {
+		pipe = skb->data[0];
+		skb_pull(skb, NCI_HCI_HCP_PACKET_HEADER_LEN);
+		message = (struct nci_hcp_message *)skb->data;
+		type = NCI_HCP_MSG_GET_TYPE(message->header);
+		instruction = NCI_HCP_MSG_GET_CMD(message->header);
+		skb_pull(skb, NCI_HCI_HCP_MESSAGE_HEADER_LEN);
+
+		nci_hci_hcp_message_rx(hdev->ndev, pipe,
+				       type, instruction, skb);
+	}
+}
+
+void nci_hci_data_received_cb(void *context,
+			      struct sk_buff *skb, int err)
+{
+	struct nci_dev *ndev = (struct nci_dev *)context;
+	struct nci_hcp_packet *packet;
+	u8 pipe, type, instruction;
+	struct sk_buff *hcp_skb;
+	struct sk_buff *frag_skb;
+	int msg_len;
+
+	pr_debug("\n");
+
+	if (err) {
+		nci_req_complete(ndev, err);
+		return;
+	}
+
+	packet = (struct nci_hcp_packet *)skb->data;
+	if ((packet->header & ~NCI_HCI_FRAGMENT) == 0) {
+		skb_queue_tail(&ndev->hci_dev->rx_hcp_frags, skb);
+		return;
+	}
+
+	/* it's the last fragment. Does it need re-aggregation? */
+	if (skb_queue_len(&ndev->hci_dev->rx_hcp_frags)) {
+		pipe = packet->header & NCI_HCI_FRAGMENT;
+		skb_queue_tail(&ndev->hci_dev->rx_hcp_frags, skb);
+
+		msg_len = 0;
+		skb_queue_walk(&ndev->hci_dev->rx_hcp_frags, frag_skb) {
+			msg_len += (frag_skb->len -
+				    NCI_HCI_HCP_PACKET_HEADER_LEN);
+		}
+
+		hcp_skb = nfc_alloc_recv_skb(NCI_HCI_HCP_PACKET_HEADER_LEN +
+					     msg_len, GFP_KERNEL);
+		if (!hcp_skb) {
+			nci_req_complete(ndev, -ENOMEM);
+			return;
+		}
+
+		*skb_put(hcp_skb, NCI_HCI_HCP_PACKET_HEADER_LEN) = pipe;
+
+		skb_queue_walk(&ndev->hci_dev->rx_hcp_frags, frag_skb) {
+		       msg_len = frag_skb->len - NCI_HCI_HCP_PACKET_HEADER_LEN;
+			memcpy(skb_put(hcp_skb, msg_len), frag_skb->data +
+			       NCI_HCI_HCP_PACKET_HEADER_LEN, msg_len);
+		}
+
+		skb_queue_purge(&ndev->hci_dev->rx_hcp_frags);
+	} else {
+		packet->header &= NCI_HCI_FRAGMENT;
+		hcp_skb = skb;
+	}
+
+	/* if this is a response, dispatch immediately to
+	 * unblock waiting cmd context. Otherwise, enqueue to dispatch
+	 * in separate context where handler can also execute command.
+	 */
+	packet = (struct nci_hcp_packet *)hcp_skb->data;
+	type = NCI_HCP_MSG_GET_TYPE(packet->message.header);
+	if (type == NCI_HCI_HCP_RESPONSE) {
+		pipe = packet->header;
+		instruction = NCI_HCP_MSG_GET_CMD(packet->message.header);
+		skb_pull(hcp_skb, NCI_HCI_HCP_PACKET_HEADER_LEN +
+			 NCI_HCI_HCP_MESSAGE_HEADER_LEN);
+		nci_hci_hcp_message_rx(ndev, pipe, type, instruction, hcp_skb);
+	} else {
+		skb_queue_tail(&ndev->hci_dev->msg_rx_queue, hcp_skb);
+		schedule_work(&ndev->hci_dev->msg_rx_work);
+	}
+}
+
+int nci_hci_open_pipe(struct nci_dev *ndev, u8 pipe)
+{
+	struct nci_data data;
+	struct nci_conn_info    *conn_info;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND,
+				       NCI_HCI_ANY_OPEN_PIPE);
+	data.data = NULL;
+	data.data_len = 0;
+
+	return nci_request(ndev, nci_hci_send_data_req,
+			(unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+}
+EXPORT_SYMBOL(nci_hci_open_pipe);
+
+int nci_hci_set_param(struct nci_dev *ndev, u8 gate, u8 idx,
+		      const u8 *param, size_t param_len)
+{
+	struct nci_conn_info *conn_info;
+	struct nci_data data;
+	int r;
+	u8 *tmp;
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	pr_debug("idx=%d to gate %d\n", idx, gate);
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	tmp = kmalloc(1 + param_len, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	*tmp = idx;
+	memcpy(tmp + 1, param, param_len);
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND,
+				       NCI_HCI_ANY_SET_PARAMETER);
+	data.data = tmp;
+	data.data_len = param_len + 1;
+
+	r = nci_request(ndev, nci_hci_send_data_req,
+			(unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+
+	kfree(tmp);
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_set_param);
+
+int nci_hci_get_param(struct nci_dev *ndev, u8 gate, u8 idx,
+		      struct sk_buff **skb)
+{
+	struct nci_conn_info    *conn_info;
+	struct nci_data data;
+	int r;
+	u8 pipe = ndev->hci_dev->gate2pipe[gate];
+
+	pr_debug("idx=%d to gate %d\n", idx, gate);
+
+	if (pipe == NCI_HCI_INVALID_PIPE)
+		return -EADDRNOTAVAIL;
+
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	data.conn_id = conn_info->conn_id;
+	data.pipe = pipe;
+	data.cmd = NCI_HCP_HEADER(NCI_HCI_HCP_COMMAND,
+				  NCI_HCI_ANY_GET_PARAMETER);
+	data.data = &idx;
+	data.data_len = 1;
+
+	r = nci_request(ndev, nci_hci_send_data_req, (unsigned long)&data,
+			msecs_to_jiffies(NCI_DATA_TIMEOUT));
+
+	if (r == NCI_STATUS_OK)
+		*skb = conn_info->rx_skb;
+
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_get_param);
+
+int nci_hci_connect_gate(struct nci_dev *ndev,
+			 u8 dest_host, u8 dest_gate, u8 pipe)
+{
+	int r;
+
+	if (pipe == NCI_HCI_DO_NOT_OPEN_PIPE)
+		return 0;
+
+	if (ndev->hci_dev->gate2pipe[dest_gate] != NCI_HCI_INVALID_PIPE)
+		return -EADDRINUSE;
+
+	if (pipe != NCI_HCI_INVALID_PIPE)
+		goto open_pipe;
+
+	switch (dest_gate) {
+	case NCI_HCI_LINK_MGMT_GATE:
+		pipe = NCI_HCI_LINK_MGMT_PIPE;
+	break;
+	case NCI_HCI_ADMIN_GATE:
+		pipe = NCI_HCI_ADMIN_PIPE;
+	break;
+	}
+
+open_pipe:
+	r = nci_hci_open_pipe(ndev, pipe);
+	if (r < 0)
+		return r;
+
+	ndev->hci_dev->pipes[pipe].gate = dest_gate;
+	ndev->hci_dev->pipes[pipe].host = dest_host;
+	ndev->hci_dev->gate2pipe[dest_gate] = pipe;
+
+	return 0;
+}
+EXPORT_SYMBOL(nci_hci_connect_gate);
+
+static int nci_hci_dev_connect_gates(struct nci_dev *ndev,
+				     u8 gate_count,
+				     struct nci_hci_gate *gates)
+{
+	int r;
+
+	while (gate_count--) {
+		r = nci_hci_connect_gate(ndev, gates->dest_host,
+					 gates->gate, gates->pipe);
+		if (r < 0)
+			return r;
+		gates++;
+	}
+
+	return 0;
+}
+
+int nci_hci_dev_session_init(struct nci_dev *ndev)
+{
+	struct sk_buff *skb;
+	int r;
+
+	ndev->hci_dev->count_pipes = 0;
+	ndev->hci_dev->expected_pipes = 0;
+
+	nci_hci_reset_pipes(ndev->hci_dev);
+
+	if (ndev->hci_dev->init_data.gates[0].gate != NCI_HCI_ADMIN_GATE)
+		return -EPROTO;
+
+	r = nci_hci_connect_gate(ndev,
+				 ndev->hci_dev->init_data.gates[0].dest_host,
+				 ndev->hci_dev->init_data.gates[0].gate,
+				 ndev->hci_dev->init_data.gates[0].pipe);
+	if (r < 0)
+		goto exit;
+
+	r = nci_hci_get_param(ndev, NCI_HCI_ADMIN_GATE,
+			      NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY, &skb);
+	if (r < 0)
+		goto exit;
+
+	if (skb->len &&
+	    skb->len == strlen(ndev->hci_dev->init_data.session_id) &&
+	    memcmp(ndev->hci_dev->init_data.session_id,
+		   skb->data, skb->len) == 0 &&
+	    ndev->ops->hci_load_session) {
+		/* Restore gate<->pipe table from some proprietary location. */
+		r = ndev->ops->hci_load_session(ndev);
+		if (r < 0)
+			goto exit;
+	} else {
+		r = nci_hci_dev_connect_gates(ndev,
+					      ndev->hci_dev->init_data.gate_count,
+					      ndev->hci_dev->init_data.gates);
+		if (r < 0)
+			goto exit;
+
+		r = nci_hci_set_param(ndev, NCI_HCI_ADMIN_GATE,
+				      NCI_HCI_ADMIN_PARAM_SESSION_IDENTITY,
+				      ndev->hci_dev->init_data.session_id,
+				      strlen(ndev->hci_dev->init_data.session_id));
+	}
+	if (r == 0)
+		goto exit;
+
+exit:
+	kfree_skb(skb);
+
+	return r;
+}
+EXPORT_SYMBOL(nci_hci_dev_session_init);
+
+struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev)
+{
+	struct nci_hci_dev *hdev;
+
+	hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
+	if (!hdev)
+		return NULL;
+
+	skb_queue_head_init(&hdev->rx_hcp_frags);
+	INIT_WORK(&hdev->msg_rx_work, nci_hci_msg_rx_work);
+	skb_queue_head_init(&hdev->msg_rx_queue);
+	hdev->ndev = ndev;
+
+	return hdev;
+}
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 4c0be7e82d2..6e041ac49e1 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -723,18 +723,30 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev,
 
 	pr_debug("\n");
 
-	conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
-				 sizeof(struct nci_conn_info), GFP_KERNEL);
-	if (!conn_info) {
-		status = NCI_STATUS_REJECTED;
-		goto exit;
-	}
+	/* NFCForum NCI 9.2.1 HCI Network Specific Handling
+	 * If the NFCC supports the HCI Network, it SHALL return one,
+	 * and only one, NFCEE_DISCOVER_NTF with a Protocol type of
+	 * “HCI Access”, even if the HCI Network contains multiple NFCEEs.
+	 */
+	if (!ndev->hci_dev->conn_info) {
+		conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
+					 sizeof(*conn_info), GFP_KERNEL);
+		if (!conn_info) {
+			status = NCI_STATUS_REJECTED;
+			goto exit;
+		}
 
-	conn_info->id = nfcee_ntf->nfcee_id;
-	conn_info->conn_id = NCI_INVALID_CONN_ID;
+		conn_info->id = nfcee_ntf->nfcee_id;
+		conn_info->conn_id = NCI_INVALID_CONN_ID;
 
-	INIT_LIST_HEAD(&conn_info->list);
-	list_add(&conn_info->list, &ndev->conn_info_list);
+		conn_info->data_exchange_cb = nci_hci_data_received_cb;
+		conn_info->data_exchange_cb_context = ndev;
+
+		INIT_LIST_HEAD(&conn_info->list);
+		list_add(&conn_info->list, &ndev->conn_info_list);
+
+		ndev->hci_dev->conn_info = conn_info;
+	}
 
 exit:
 	nci_req_complete(ndev, status);
-- 
cgit v1.2.3-70-g09d2


From 447b27c4f29b510b98e99395120d635f009ed563 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:16 +0100
Subject: NFC: Forward NFC_EVT_TRANSACTION to user space

NFC_EVT_TRANSACTION is sent through netlink in order for a
specific application running on a secure element to notify
userspace of an event. Typically the secure element application
counterpart on the host could interpret that event and act
upon it.

Forwarded information contains:
- SE host generating the event
- Application IDentifier doing the operation
- Applications parameters

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nfc.h    | 27 +++++++++++++++++++++++++++
 include/uapi/linux/nfc.h |  1 +
 net/nfc/core.c           | 21 +++++++++++++++++++++
 net/nfc/netlink.c        | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 net/nfc/nfc.h            |  2 ++
 5 files changed, 98 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index 12adb817c27..73190e65d5c 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -135,6 +135,31 @@ struct nfc_se {
 	u16 state;
 };
 
+/**
+ * nfc_evt_transaction - A struct for NFC secure element event transaction.
+ *
+ * @aid: The application identifier triggering the event
+ *
+ * @aid_len: The application identifier length [5:16]
+ *
+ * @params: The application parameters transmitted during the transaction
+ *
+ * @params_len: The applications parameters length [0:255]
+ *
+ */
+#define NFC_MIN_AID_LENGTH	5
+#define	NFC_MAX_AID_LENGTH	16
+#define NFC_MAX_PARAMS_LENGTH	255
+
+#define NFC_EVT_TRANSACTION_AID_TAG	0x81
+#define NFC_EVT_TRANSACTION_PARAMS_TAG	0x82
+struct nfc_evt_transaction {
+	u32 aid_len;
+	u8 aid[NFC_MAX_AID_LENGTH];
+	u8 params_len;
+	u8 params[NFC_MAX_PARAMS_LENGTH];
+} __packed;
+
 struct nfc_genl_data {
 	u32 poll_req_portid;
 	struct mutex genl_data_mutex;
@@ -262,6 +287,8 @@ int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb);
 
 void nfc_driver_failure(struct nfc_dev *dev, int err);
 
+int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx,
+		       struct nfc_evt_transaction *evt_transaction);
 int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type);
 int nfc_remove_se(struct nfc_dev *dev, u32 se_idx);
 struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx);
diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index 8119255feae..c1e2e63cf9b 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -183,6 +183,7 @@ enum nfc_attrs {
 	NFC_ATTR_SE_APDU,
 	NFC_ATTR_TARGET_ISO15693_DSFID,
 	NFC_ATTR_TARGET_ISO15693_UID,
+	NFC_ATTR_SE_PARAMS,
 /* private: internal use only */
 	__NFC_ATTR_AFTER_LAST
 };
diff --git a/net/nfc/core.c b/net/nfc/core.c
index 7f1b6351755..cff3f1614ad 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -932,6 +932,27 @@ int nfc_remove_se(struct nfc_dev *dev, u32 se_idx)
 }
 EXPORT_SYMBOL(nfc_remove_se);
 
+int nfc_se_transaction(struct nfc_dev *dev, u8 se_idx,
+		       struct nfc_evt_transaction *evt_transaction)
+{
+	int rc;
+
+	pr_debug("transaction: %x\n", se_idx);
+
+	device_lock(&dev->dev);
+
+	if (!evt_transaction) {
+		rc = -EPROTO;
+		goto out;
+	}
+
+	rc = nfc_genl_se_transaction(dev, se_idx, evt_transaction);
+out:
+	device_unlock(&dev->dev);
+	return rc;
+}
+EXPORT_SYMBOL(nfc_se_transaction);
+
 static void nfc_release(struct device *d)
 {
 	struct nfc_dev *dev = to_nfc_dev(d);
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index be387e6219a..14a2d11581d 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -497,6 +497,53 @@ free_msg:
 	return -EMSGSIZE;
 }
 
+int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx,
+			    struct nfc_evt_transaction *evt_transaction)
+{
+	struct nfc_se *se;
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0,
+			  NFC_EVENT_SE_TRANSACTION);
+	if (!hdr)
+		goto free_msg;
+
+	se = nfc_find_se(dev, se_idx);
+	if (!se)
+		goto free_msg;
+
+	if (nla_put_u32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx) ||
+	    nla_put_u32(msg, NFC_ATTR_SE_INDEX, se_idx) ||
+	    nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type) ||
+	    nla_put(msg, NFC_ATTR_SE_AID, evt_transaction->aid_len,
+		    evt_transaction->aid) ||
+	    nla_put(msg, NFC_ATTR_SE_PARAMS, evt_transaction->params_len,
+		    evt_transaction->params))
+		goto nla_put_failure;
+
+	/* evt_transaction is no more used */
+	devm_kfree(&dev->dev, evt_transaction);
+
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	/* evt_transaction is no more used */
+	devm_kfree(&dev->dev, evt_transaction);
+	nlmsg_free(msg);
+	return -EMSGSIZE;
+}
+
 static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev,
 				u32 portid, u32 seq,
 				struct netlink_callback *cb,
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index 88d60064890..a8ce80b4772 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -100,6 +100,8 @@ int nfc_genl_llc_send_sdres(struct nfc_dev *dev, struct hlist_head *sdres_list);
 
 int nfc_genl_se_added(struct nfc_dev *dev, u32 se_idx, u16 type);
 int nfc_genl_se_removed(struct nfc_dev *dev, u32 se_idx);
+int nfc_genl_se_transaction(struct nfc_dev *dev, u8 se_idx,
+			    struct nfc_evt_transaction *evt_transaction);
 
 struct nfc_dev *nfc_get_device(unsigned int idx);
 
-- 
cgit v1.2.3-70-g09d2


From a41bb8448ebaebe1d0d9a268d340fad73c247e09 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Sun, 1 Feb 2015 22:26:17 +0100
Subject: NFC: nci: Add RF NFCEE action notification support

The NFCC sends an NCI_OP_RF_NFCEE_ACTION_NTF notification
to the host (DH) to let it know that for example an RF
transaction with a payment reader is done.
For now the notification handler is empty.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h |  8 ++++++++
 net/nfc/nci/ntf.c     | 11 +++++++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index deac78b9a53..6c1beb2704b 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -499,6 +499,14 @@ struct nci_rf_deactivate_ntf {
 	__u8	reason;
 } __packed;
 
+#define NCI_OP_RF_NFCEE_ACTION_NTF	nci_opcode_pack(NCI_GID_RF_MGMT, 0x09)
+struct nci_rf_nfcee_action_ntf {
+	__u8 nfcee_id;
+	__u8 trigger;
+	__u8 supported_data_length;
+	__u8 supported_data[0];
+} __packed;
+
 #define NCI_OP_NFCEE_DISCOVER_NTF nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x00)
 struct nci_nfcee_supported_protocol {
 	__u8	num_protocol;
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 6e041ac49e1..5924b812fb6 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -752,6 +752,12 @@ exit:
 	nci_req_complete(ndev, status);
 }
 
+static void nci_nfcee_action_ntf_packet(struct nci_dev *ndev,
+					struct sk_buff *skb)
+{
+	pr_debug("\n");
+}
+
 void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	__u16 ntf_opcode = nci_opcode(skb->data);
@@ -793,6 +799,11 @@ void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb)
 	case NCI_OP_NFCEE_DISCOVER_NTF:
 		nci_nfcee_discover_ntf_packet(ndev, skb);
 		break;
+
+	case NCI_OP_RF_NFCEE_ACTION_NTF:
+		nci_nfcee_action_ntf_packet(ndev, skb);
+		break;
+
 	default:
 		pr_err("unknown ntf opcode 0x%x\n", ntf_opcode);
 		break;
-- 
cgit v1.2.3-70-g09d2


From 49ca0d8bfaf3bc46d5eef60ce67b00eb195bd392 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 30 Jan 2015 13:29:31 -0500
Subject: net-timestamp: no-payload option

Add timestamping option SOF_TIMESTAMPING_OPT_TSONLY. For transmit
timestamps, this loops timestamps on top of empty packets.

Doing so reduces the pressure on SO_RCVBUF. Payload inspection and
cmsg reception (aside from timestamps) are no longer possible. This
works together with a follow on patch that allows administrators to
only allow tx timestamping if it does not loop payload or metadata.

Signed-off-by: Willem de Bruijn <willemb@google.com>

----

Changes (rfc -> v1)
  - add documentation
  - remove unnecessary skb->len test (thanks to Richard Cochran)
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/timestamping.txt | 21 +++++++++++++++++++++
 include/uapi/linux/net_tstamp.h           |  3 ++-
 net/core/skbuff.c                         | 19 ++++++++++++++-----
 net/ipv4/ip_sockglue.c                    |  7 ++++---
 net/ipv6/datagram.c                       |  5 ++---
 net/rxrpc/ar-error.c                      |  5 +++++
 6 files changed, 48 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index a5c784c8931..5f0922613f1 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -162,6 +162,27 @@ SOF_TIMESTAMPING_OPT_CMSG:
   option IP_PKTINFO simultaneously.
 
 
+SOF_TIMESTAMPING_OPT_TSONLY:
+
+  Applies to transmit timestamps only. Makes the kernel return the
+  timestamp as a cmsg alongside an empty packet, as opposed to
+  alongside the original packet. This reduces the amount of memory
+  charged to the socket's receive budget (SO_RCVBUF) and delivers
+  the timestamp even if sysctl net.core.tstamp_allow_data is 0.
+  This option disables SOF_TIMESTAMPING_OPT_CMSG.
+
+
+New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to
+disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate
+regardless of the setting of sysctl net.core.tstamp_allow_data.
+
+An exception is when a process needs additional cmsg data, for
+instance SOL_IP/IP_PKTINFO to detect the egress network interface.
+Then pass option SOF_TIMESTAMPING_OPT_CMSG. This option depends on
+having access to the contents of the original packet, so cannot be
+combined with SOF_TIMESTAMPING_OPT_TSONLY.
+
+
 1.4 Bytestream Timestamps
 
 The SO_TIMESTAMPING interface supports timestamping of bytes in a
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index edbc888ceb5..6d1abea9746 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -24,8 +24,9 @@ enum {
 	SOF_TIMESTAMPING_TX_SCHED = (1<<8),
 	SOF_TIMESTAMPING_TX_ACK = (1<<9),
 	SOF_TIMESTAMPING_OPT_CMSG = (1<<10),
+	SOF_TIMESTAMPING_OPT_TSONLY = (1<<11),
 
-	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_CMSG,
+	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TSONLY,
 	SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
 				 SOF_TIMESTAMPING_LAST
 };
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 56db472e9b8..65a3798f43e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3710,19 +3710,28 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     struct sock *sk, int tstype)
 {
 	struct sk_buff *skb;
+	bool tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
 
 	if (!sk)
 		return;
 
-	if (hwtstamps)
-		*skb_hwtstamps(orig_skb) = *hwtstamps;
+	if (tsonly)
+		skb = alloc_skb(0, GFP_ATOMIC);
 	else
-		orig_skb->tstamp = ktime_get_real();
-
-	skb = skb_clone(orig_skb, GFP_ATOMIC);
+		skb = skb_clone(orig_skb, GFP_ATOMIC);
 	if (!skb)
 		return;
 
+	if (tsonly) {
+		skb_shinfo(skb)->tx_flags = skb_shinfo(orig_skb)->tx_flags;
+		skb_shinfo(skb)->tskey = skb_shinfo(orig_skb)->tskey;
+	}
+
+	if (hwtstamps)
+		*skb_hwtstamps(skb) = *hwtstamps;
+	else
+		skb->tstamp = ktime_get_real();
+
 	__skb_complete_tx_timestamp(skb, sk, tstype);
 }
 EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index db5e0f81ce0..31d8c71986b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -483,7 +483,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin) {
+	if (sin && skb->len) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) +
 						   serr->addr_offset);
@@ -496,8 +496,9 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	sin = &errhdr.offender;
 	memset(sin, 0, sizeof(*sin));
 
-	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
-	    ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin)) {
+	if (skb->len &&
+	    (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP ||
+	     ipv4_pktinfo_prepare_errqueue(sk, skb, serr->ee.ee_origin))) {
 		sin->sin_family = AF_INET;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		if (inet_sk(sk)->cmsg_flags)
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 49f5e73db12..c215be70cac 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -369,7 +369,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 	serr = SKB_EXT_ERR(skb);
 
-	if (sin) {
+	if (sin && skb->len) {
 		const unsigned char *nh = skb_network_header(skb);
 		sin->sin6_family = AF_INET6;
 		sin->sin6_flowinfo = 0;
@@ -394,8 +394,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 	memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err));
 	sin = &errhdr.offender;
 	memset(sin, 0, sizeof(*sin));
-
-	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL) {
+	if (serr->ee.ee_origin != SO_EE_ORIGIN_LOCAL && skb->len) {
 		sin->sin6_family = AF_INET6;
 		if (np->rxopt.all) {
 			if (serr->ee.ee_origin != SO_EE_ORIGIN_ICMP &&
diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c
index 74c0fcd3683..5394b6be46e 100644
--- a/net/rxrpc/ar-error.c
+++ b/net/rxrpc/ar-error.c
@@ -42,6 +42,11 @@ void rxrpc_UDP_error_report(struct sock *sk)
 		_leave("UDP socket errqueue empty");
 		return;
 	}
+	if (!skb->len) {
+		_leave("UDP empty message");
+		kfree_skb(skb);
+		return;
+	}
 
 	rxrpc_new_skb(skb);
 
-- 
cgit v1.2.3-70-g09d2


From b245be1f4db1a0394e4b6eb66059814b46670ac3 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 30 Jan 2015 13:29:32 -0500
Subject: net-timestamp: no-payload only sysctl

Tx timestamps are looped onto the error queue on top of an skb. This
mechanism leaks packet headers to processes unless the no-payload
options SOF_TIMESTAMPING_OPT_TSONLY is set.

Add a sysctl that optionally drops looped timestamp with data. This
only affects processes without CAP_NET_RAW.

The policy is checked when timestamps are generated in the stack.
It is possible for timestamps with data to be reported after the
sysctl is set, if these were queued internally earlier.

No vulnerability is immediately known that exploits knowledge
gleaned from packet headers, but it may still be preferable to allow
administrators to lock down this path at the cost of possible
breakage of legacy applications.

Signed-off-by: Willem de Bruijn <willemb@google.com>

----

Changes
  (v1 -> v2)
  - test socket CAP_NET_RAW instead of capable(CAP_NET_RAW)
  (rfc -> v1)
  - document the sysctl in Documentation/sysctl/net.txt
  - fix access control race: read .._OPT_TSONLY only once,
        use same value for permission check and skb generation.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/sysctl/net.txt |  8 ++++++++
 include/net/sock.h           |  1 +
 net/core/skbuff.c            | 21 ++++++++++++++++++++-
 net/core/sock.c              |  3 +++
 net/core/sysctl_net_core.c   |  9 +++++++++
 5 files changed, 41 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 666594b43cf..6294b5186ae 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -97,6 +97,14 @@ rmem_max
 
 The maximum receive socket buffer size in bytes.
 
+tstamp_allow_data
+-----------------
+Allow processes to receive tx timestamps looped together with the original
+packet contents. If disabled, transmit timestamp requests from unprivileged
+processes are dropped unless socket option SOF_TIMESTAMPING_OPT_TSONLY is set.
+Default: 1 (on)
+
+
 wmem_default
 ------------
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 15341499786..511ef7c8889 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2239,6 +2239,7 @@ bool sk_net_capable(const struct sock *sk, int cap);
 extern __u32 sysctl_wmem_max;
 extern __u32 sysctl_rmem_max;
 
+extern int sysctl_tstamp_allow_data;
 extern int sysctl_optmem_max;
 
 extern __u32 sysctl_wmem_default;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 65a3798f43e..a5bff2767f1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -74,6 +74,8 @@
 #include <asm/uaccess.h>
 #include <trace/events/skb.h>
 #include <linux/highmem.h>
+#include <linux/capability.h>
+#include <linux/user_namespace.h>
 
 struct kmem_cache *skbuff_head_cache __read_mostly;
 static struct kmem_cache *skbuff_fclone_cache __read_mostly;
@@ -3690,11 +3692,28 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 		kfree_skb(skb);
 }
 
+static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
+{
+	bool ret;
+
+	if (likely(sysctl_tstamp_allow_data || tsonly))
+		return true;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	ret = sk->sk_socket && sk->sk_socket->file &&
+	      file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW);
+	read_unlock_bh(&sk->sk_callback_lock);
+	return ret;
+}
+
 void skb_complete_tx_timestamp(struct sk_buff *skb,
 			       struct skb_shared_hwtstamps *hwtstamps)
 {
 	struct sock *sk = skb->sk;
 
+	if (!skb_may_tx_timestamp(sk, false))
+		return;
+
 	/* take a reference to prevent skb_orphan() from freeing the socket */
 	sock_hold(sk);
 
@@ -3712,7 +3731,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	struct sk_buff *skb;
 	bool tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
 
-	if (!sk)
+	if (!sk || !skb_may_tx_timestamp(sk, tsonly))
 		return;
 
 	if (tsonly)
diff --git a/net/core/sock.c b/net/core/sock.c
index 1c7a33db131..93c8b20c91e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -325,6 +325,8 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
+int sysctl_tstamp_allow_data __read_mostly = 1;
+
 struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE;
 EXPORT_SYMBOL_GPL(memalloc_socks);
 
@@ -840,6 +842,7 @@ set_rcvbuf:
 			ret = -EINVAL;
 			break;
 		}
+
 		if (val & SOF_TIMESTAMPING_OPT_ID &&
 		    !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) {
 			if (sk->sk_protocol == IPPROTO_TCP) {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 31baba2a71c..fde21d19e61 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -321,6 +321,15 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "tstamp_allow_data",
+		.data		= &sysctl_tstamp_allow_data,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one
+	},
 #ifdef CONFIG_RPS
 	{
 		.procname	= "rps_sock_flow_entries",
-- 
cgit v1.2.3-70-g09d2


From 366e41d9774d7010cb63112b6db2fce6dc7809c0 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Sat, 31 Jan 2015 10:40:13 -0500
Subject: ipv6: pull cork initialization into its own function.

Pull IPv6 cork initialization into its own function that
can be re-used.  IPv6 specific cork data did not have an
explicit data structure.  This patch creats eone so that
just ipv6 cork data can be as arguemts.  Also, since
IPv6 tries to save the flow label into inet_cork_full
tructure, pass the full cork.

Adjust ip6_cork_release() to take cork data structures.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ipv6.h  |  12 ++--
 net/ipv6/ip6_output.c | 158 ++++++++++++++++++++++++++++----------------------
 2 files changed, 96 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 2805062c013..4d5169f5d7d 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -125,6 +125,12 @@ struct ipv6_mc_socklist;
 struct ipv6_ac_socklist;
 struct ipv6_fl_socklist;
 
+struct inet6_cork {
+	struct ipv6_txoptions *opt;
+	u8 hop_limit;
+	u8 tclass;
+};
+
 /**
  * struct ipv6_pinfo - ipv6 private area
  *
@@ -217,11 +223,7 @@ struct ipv6_pinfo {
 	struct ipv6_txoptions	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
-	struct {
-		struct ipv6_txoptions *opt;
-		u8 hop_limit;
-		u8 tclass;
-	} cork;
+	struct inet6_cork	cork;
 };
 
 /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ce69a12ae48..f9f08c43c6e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1135,6 +1135,74 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 	}
 }
 
+static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
+			  struct inet6_cork *v6_cork,
+			  int hlimit, int tclass, struct ipv6_txoptions *opt,
+			  struct rt6_info *rt, struct flowi6 *fl6)
+{
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	unsigned int mtu;
+
+	/*
+	 * setup for corking
+	 */
+	if (opt) {
+		if (WARN_ON(v6_cork->opt))
+			return -EINVAL;
+
+		v6_cork->opt = kzalloc(opt->tot_len, sk->sk_allocation);
+		if (unlikely(v6_cork->opt == NULL))
+			return -ENOBUFS;
+
+		v6_cork->opt->tot_len = opt->tot_len;
+		v6_cork->opt->opt_flen = opt->opt_flen;
+		v6_cork->opt->opt_nflen = opt->opt_nflen;
+
+		v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt,
+						    sk->sk_allocation);
+		if (opt->dst0opt && !v6_cork->opt->dst0opt)
+			return -ENOBUFS;
+
+		v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt,
+						    sk->sk_allocation);
+		if (opt->dst1opt && !v6_cork->opt->dst1opt)
+			return -ENOBUFS;
+
+		v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt,
+						   sk->sk_allocation);
+		if (opt->hopopt && !v6_cork->opt->hopopt)
+			return -ENOBUFS;
+
+		v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt,
+						    sk->sk_allocation);
+		if (opt->srcrt && !v6_cork->opt->srcrt)
+			return -ENOBUFS;
+
+		/* need source address above miyazawa*/
+	}
+	dst_hold(&rt->dst);
+	cork->base.dst = &rt->dst;
+	cork->fl.u.ip6 = *fl6;
+	v6_cork->hop_limit = hlimit;
+	v6_cork->tclass = tclass;
+	if (rt->dst.flags & DST_XFRM_TUNNEL)
+		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		      rt->dst.dev->mtu : dst_mtu(&rt->dst);
+	else
+		mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
+		      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
+	if (np->frag_size < mtu) {
+		if (np->frag_size)
+			mtu = np->frag_size;
+	}
+	cork->base.fragsize = mtu;
+	if (dst_allfrag(rt->dst.path))
+		cork->base.flags |= IPCORK_ALLFRAG;
+	cork->base.length = 0;
+
+	return 0;
+}
+
 int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	int offset, int len, int odd, struct sk_buff *skb),
 	void *from, int length, int transhdrlen,
@@ -1162,59 +1230,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		/*
 		 * setup for corking
 		 */
-		if (opt) {
-			if (WARN_ON(np->cork.opt))
-				return -EINVAL;
-
-			np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
-			if (unlikely(np->cork.opt == NULL))
-				return -ENOBUFS;
-
-			np->cork.opt->tot_len = opt->tot_len;
-			np->cork.opt->opt_flen = opt->opt_flen;
-			np->cork.opt->opt_nflen = opt->opt_nflen;
-
-			np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
-							    sk->sk_allocation);
-			if (opt->dst0opt && !np->cork.opt->dst0opt)
-				return -ENOBUFS;
-
-			np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
-							    sk->sk_allocation);
-			if (opt->dst1opt && !np->cork.opt->dst1opt)
-				return -ENOBUFS;
-
-			np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
-							   sk->sk_allocation);
-			if (opt->hopopt && !np->cork.opt->hopopt)
-				return -ENOBUFS;
-
-			np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
-							    sk->sk_allocation);
-			if (opt->srcrt && !np->cork.opt->srcrt)
-				return -ENOBUFS;
-
-			/* need source address above miyazawa*/
-		}
-		dst_hold(&rt->dst);
-		cork->dst = &rt->dst;
-		inet->cork.fl.u.ip6 = *fl6;
-		np->cork.hop_limit = hlimit;
-		np->cork.tclass = tclass;
-		if (rt->dst.flags & DST_XFRM_TUNNEL)
-			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-			      rt->dst.dev->mtu : dst_mtu(&rt->dst);
-		else
-			mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ?
-			      rt->dst.dev->mtu : dst_mtu(rt->dst.path);
-		if (np->frag_size < mtu) {
-			if (np->frag_size)
-				mtu = np->frag_size;
-		}
-		cork->fragsize = mtu;
-		if (dst_allfrag(rt->dst.path))
-			cork->flags |= IPCORK_ALLFRAG;
-		cork->length = 0;
+		err = ip6_setup_cork(sk, &inet->cork, &np->cork, hlimit,
+				     tclass, opt, rt, fl6);
+		if (err)
+			return err;
 		exthdrlen = (opt ? opt->opt_flen : 0);
 		length += exthdrlen;
 		transhdrlen += exthdrlen;
@@ -1226,8 +1245,8 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		transhdrlen = 0;
 		exthdrlen = 0;
 		dst_exthdrlen = 0;
-		mtu = cork->fragsize;
 	}
+	mtu = cork->fragsize;
 	orig_mtu = mtu;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1503,23 +1522,24 @@ error:
 }
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
-static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
+static void ip6_cork_release(struct inet_cork_full *cork,
+			     struct inet6_cork *v6_cork)
 {
-	if (np->cork.opt) {
-		kfree(np->cork.opt->dst0opt);
-		kfree(np->cork.opt->dst1opt);
-		kfree(np->cork.opt->hopopt);
-		kfree(np->cork.opt->srcrt);
-		kfree(np->cork.opt);
-		np->cork.opt = NULL;
+	if (v6_cork->opt) {
+		kfree(v6_cork->opt->dst0opt);
+		kfree(v6_cork->opt->dst1opt);
+		kfree(v6_cork->opt->hopopt);
+		kfree(v6_cork->opt->srcrt);
+		kfree(v6_cork->opt);
+		v6_cork->opt = NULL;
 	}
 
-	if (inet->cork.base.dst) {
-		dst_release(inet->cork.base.dst);
-		inet->cork.base.dst = NULL;
-		inet->cork.base.flags &= ~IPCORK_ALLFRAG;
+	if (cork->base.dst) {
+		dst_release(cork->base.dst);
+		cork->base.dst = NULL;
+		cork->base.flags &= ~IPCORK_ALLFRAG;
 	}
-	memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
+	memset(&cork->fl, 0, sizeof(cork->fl));
 }
 
 int ip6_push_pending_frames(struct sock *sk)
@@ -1599,7 +1619,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	}
 
 out:
-	ip6_cork_release(inet, np);
+	ip6_cork_release(&inet->cork, &np->cork);
 	return err;
 error:
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
@@ -1618,6 +1638,6 @@ void ip6_flush_pending_frames(struct sock *sk)
 		kfree_skb(skb);
 	}
 
-	ip6_cork_release(inet_sk(sk), inet6_sk(sk));
+	ip6_cork_release(&inet_sk(sk)->cork, &inet6_sk(sk)->cork);
 }
 EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
-- 
cgit v1.2.3-70-g09d2


From 6422398c2ab09268a55112f98cbf96bbf0184328 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Sat, 31 Jan 2015 10:40:15 -0500
Subject: ipv6: introduce ipv6_make_skb

This commit is very similar to
commit 1c32c5ad6fac8cee1a77449f5abf211e911ff830
Author: Herbert Xu <herbert@gondor.apana.org.au>
Date:   Tue Mar 1 02:36:47 2011 +0000

    inet: Add ip_make_skb and ip_finish_skb

It adds IPv6 version of the helpers ip6_make_skb and ip6_finish_skb.

The job of ip6_make_skb is to collect messages into an ipv6 packet
and poplulate ipv6 eader.  The job of ip6_finish_skb is to transmit
the generated skb.  Together they replicated the job of
ip6_push_pending_frames() while also provide the capability to be
called independently.  This will be needed to add lockless UDP sendmsg
support.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h    |  19 ++++++++++
 net/ipv6/ip6_output.c | 103 ++++++++++++++++++++++++++++++++++++++++----------
 2 files changed, 103 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4292929392b..8027ca53e31 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -788,6 +788,25 @@ int ip6_push_pending_frames(struct sock *sk);
 
 void ip6_flush_pending_frames(struct sock *sk);
 
+int ip6_send_skb(struct sk_buff *skb);
+
+struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue,
+			       struct inet_cork_full *cork,
+			       struct inet6_cork *v6_cork);
+struct sk_buff *ip6_make_skb(struct sock *sk,
+			     int getfrag(void *from, char *to, int offset,
+					 int len, int odd, struct sk_buff *skb),
+			     void *from, int length, int transhdrlen,
+			     int hlimit, int tclass, struct ipv6_txoptions *opt,
+			     struct flowi6 *fl6, struct rt6_info *rt,
+			     unsigned int flags, int dontfrag);
+
+static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
+{
+	return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork,
+			      &inet6_sk(sk)->cork);
+}
+
 int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6);
 struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 				      const struct in6_addr *final_dst);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1b66453a695..b89d3c27dac 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1564,22 +1564,23 @@ static void ip6_cork_release(struct inet_cork_full *cork,
 	memset(&cork->fl, 0, sizeof(cork->fl));
 }
 
-int ip6_push_pending_frames(struct sock *sk)
+struct sk_buff *__ip6_make_skb(struct sock *sk,
+			       struct sk_buff_head *queue,
+			       struct inet_cork_full *cork,
+			       struct inet6_cork *v6_cork)
 {
 	struct sk_buff *skb, *tmp_skb;
 	struct sk_buff **tail_skb;
 	struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
-	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
 	struct ipv6hdr *hdr;
-	struct ipv6_txoptions *opt = np->cork.opt;
-	struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
-	struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
+	struct ipv6_txoptions *opt = v6_cork->opt;
+	struct rt6_info *rt = (struct rt6_info *)cork->base.dst;
+	struct flowi6 *fl6 = &cork->fl.u.ip6;
 	unsigned char proto = fl6->flowi6_proto;
-	int err = 0;
 
-	skb = __skb_dequeue(&sk->sk_write_queue);
+	skb = __skb_dequeue(queue);
 	if (skb == NULL)
 		goto out;
 	tail_skb = &(skb_shinfo(skb)->frag_list);
@@ -1587,7 +1588,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	/* move skb->data to ip header from ext header */
 	if (skb->data < skb_network_header(skb))
 		__skb_pull(skb, skb_network_offset(skb));
-	while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
+	while ((tmp_skb = __skb_dequeue(queue)) != NULL) {
 		__skb_pull(tmp_skb, skb_network_header_len(skb));
 		*tail_skb = tmp_skb;
 		tail_skb = &(tmp_skb->next);
@@ -1612,10 +1613,10 @@ int ip6_push_pending_frames(struct sock *sk)
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
 
-	ip6_flow_hdr(hdr, np->cork.tclass,
+	ip6_flow_hdr(hdr, v6_cork->tclass,
 		     ip6_make_flowlabel(net, skb, fl6->flowlabel,
 					np->autoflowlabel));
-	hdr->hop_limit = np->cork.hop_limit;
+	hdr->hop_limit = v6_cork->hop_limit;
 	hdr->nexthdr = proto;
 	hdr->saddr = fl6->saddr;
 	hdr->daddr = *final_dst;
@@ -1632,25 +1633,45 @@ int ip6_push_pending_frames(struct sock *sk)
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
 	}
 
+	ip6_cork_release(cork, v6_cork);
+out:
+	return skb;
+}
+
+int ip6_send_skb(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+	int err;
+
 	err = ip6_local_out(skb);
 	if (err) {
 		if (err > 0)
 			err = net_xmit_errno(err);
 		if (err)
-			goto error;
+			IP6_INC_STATS(net, rt->rt6i_idev,
+				      IPSTATS_MIB_OUTDISCARDS);
 	}
 
-out:
-	ip6_cork_release(&inet->cork, &np->cork);
 	return err;
-error:
-	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
-	goto out;
+}
+
+int ip6_push_pending_frames(struct sock *sk)
+{
+	struct sk_buff *skb;
+
+	skb = ip6_finish_skb(sk);
+	if (!skb)
+		return 0;
+
+	return ip6_send_skb(skb);
 }
 EXPORT_SYMBOL_GPL(ip6_push_pending_frames);
 
 static void __ip6_flush_pending_frames(struct sock *sk,
-				       struct sk_buff_head *queue)
+				       struct sk_buff_head *queue,
+				       struct inet_cork_full *cork,
+				       struct inet6_cork *v6_cork)
 {
 	struct sk_buff *skb;
 
@@ -1661,11 +1682,55 @@ static void __ip6_flush_pending_frames(struct sock *sk,
 		kfree_skb(skb);
 	}
 
-	ip6_cork_release(&inet_sk(sk)->cork, &inet6_sk(sk)->cork);
+	ip6_cork_release(cork, v6_cork);
 }
 
 void ip6_flush_pending_frames(struct sock *sk)
 {
-	__ip6_flush_pending_frames(sk, &sk->sk_write_queue);
+	__ip6_flush_pending_frames(sk, &sk->sk_write_queue,
+				   &inet_sk(sk)->cork, &inet6_sk(sk)->cork);
 }
 EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
+
+struct sk_buff *ip6_make_skb(struct sock *sk,
+			     int getfrag(void *from, char *to, int offset,
+					 int len, int odd, struct sk_buff *skb),
+			     void *from, int length, int transhdrlen,
+			     int hlimit, int tclass,
+			     struct ipv6_txoptions *opt, struct flowi6 *fl6,
+			     struct rt6_info *rt, unsigned int flags,
+			     int dontfrag)
+{
+	struct inet_cork_full cork;
+	struct inet6_cork v6_cork;
+	struct sk_buff_head queue;
+	int exthdrlen = (opt ? opt->opt_flen : 0);
+	int err;
+
+	if (flags & MSG_PROBE)
+		return NULL;
+
+	__skb_queue_head_init(&queue);
+
+	cork.base.flags = 0;
+	cork.base.addr = 0;
+	cork.base.opt = NULL;
+	v6_cork.opt = NULL;
+	err = ip6_setup_cork(sk, &cork, &v6_cork, hlimit, tclass, opt, rt, fl6);
+	if (err)
+		return ERR_PTR(err);
+
+	if (dontfrag < 0)
+		dontfrag = inet6_sk(sk)->dontfrag;
+
+	err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork,
+				&current->task_frag, getfrag, from,
+				length + exthdrlen, transhdrlen + exthdrlen,
+				flags, dontfrag);
+	if (err) {
+		__ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork);
+		return ERR_PTR(err);
+	}
+
+	return __ip6_make_skb(sk, &queue, &cork, &v6_cork);
+}
-- 
cgit v1.2.3-70-g09d2


From 5a2e87b16875f9b83b7e9494cf1fce8e17dc764a Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Mon, 2 Feb 2015 15:18:42 +0200
Subject: net/mlx4_core: Fix kernel Oops (mem corruption) when working with
 more than 80 VFs

Commit de966c592802 (net/mlx4_core: Support more than 64 VFs) was meant to
allow up to 126 VFs.  However, due to leaving MLX4_MFUNC_MAX too low, using
more than 80 VFs resulted in memory corruptions (and Oopses) when more than
80 VFs were requested. In addition, the number of slaves was left too high.

This commit fixes these issues.

Fixes: de966c592802 ("net/mlx4_core: Support more than 64 VFs")
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/mlx4.h | 3 ++-
 include/linux/mlx4/device.h               | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index bdd4eea2247..210691c89b6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -235,7 +235,8 @@ do {									\
 extern int mlx4_log_num_mgm_entry_size;
 extern int log_mtts_per_seg;
 
-#define MLX4_MAX_NUM_SLAVES	(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF)
+#define MLX4_MAX_NUM_SLAVES	(min(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF, \
+				     MLX4_MFUNC_MAX))
 #define ALL_SLAVES 0xff
 
 struct mlx4_bitmap {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 25c791e295f..5f3a9aa7225 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -97,7 +97,7 @@ enum {
 	MLX4_MAX_NUM_PF		= 16,
 	MLX4_MAX_NUM_VF		= 126,
 	MLX4_MAX_NUM_VF_P_PORT  = 64,
-	MLX4_MFUNC_MAX		= 80,
+	MLX4_MFUNC_MAX		= 128,
 	MLX4_MAX_EQ_NUM		= 1024,
 	MLX4_MFUNC_EQ_NUM	= 4,
 	MLX4_MFUNC_MAX_EQES     = 8,
-- 
cgit v1.2.3-70-g09d2


From 3e87523897e18a3e17fc8955ed795188be737ff1 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon, 2 Feb 2015 09:39:02 -0500
Subject: sched/wait: Remove might_sleep() from wait_event_cmd()

The patch e22b886a8a43 ("sched/wait: Add might_sleep() checks")
introduced a bug in the raid5 subsystem.

The function raid5_quiesce() (and resize_stripes()) uses the 'cmd'
part to release and acquire a spinlock (so we call the sleep
primitives in atomic context), and therefore we cannot do the
might_sleep() check.

Remove it.

Fixes: e22b886a8a43 ("sched/wait: Add might_sleep() checks")
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/alpine.LRH.2.02.1502020935580.13510@file01.intranet.prod.int.rdu2.redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2232ed16635..37423e0e137 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -363,7 +363,6 @@ do {									\
  */
 #define wait_event_cmd(wq, condition, cmd1, cmd2)			\
 do {									\
-	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
-- 
cgit v1.2.3-70-g09d2


From f0b66a2cf68ed3613fe72fe01ed309f998e2bbb3 Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Tue, 3 Feb 2015 09:29:52 -0600
Subject: PCI: Add pci_device_to_OF_node() stub for !CONFIG_OF

Add a stub for pci_device_to_OF_node() so drivers don't need to
use #ifdef CONFIG_OF around calls to it.

Signed-off-by: Kevin Hao <haokexin@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 360a966a97a..fbb5795a8d8 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1847,6 +1847,8 @@ static inline void pci_set_of_node(struct pci_dev *dev) { }
 static inline void pci_release_of_node(struct pci_dev *dev) { }
 static inline void pci_set_bus_of_node(struct pci_bus *bus) { }
 static inline void pci_release_bus_of_node(struct pci_bus *bus) { }
+static inline struct device_node *
+pci_device_to_OF_node(const struct pci_dev *pdev) { return NULL; }
 #endif  /* CONFIG_OF */
 
 #ifdef CONFIG_EEH
-- 
cgit v1.2.3-70-g09d2


From 344d635b9a41b19837ccf8083a99ea688027019c Mon Sep 17 00:00:00 2001
From: Brad Griffis <bgriffis@ti.com>
Date: Tue, 3 Feb 2015 11:44:12 -0800
Subject: Input: ti_am335x_tsc - remove udelay in interrupt handler

TSC interrupt handler had udelay to avoid reporting of false pen-up
interrupt to user space. This patch implements workaround suggesting in
Advisory 1.0.31 of silicon errata for am335x, thus eliminating udelay and
touchscreen lag. This also improves performance of touchscreen and
eliminates sudden jump of cursor at touch release.

IDLECONFIG and CHARGECONFIG registers are to be configured with same values
in order to eliminate false pen-up events. This workaround may result in
false pen-down to be detected, hence considerable charge step delay needs
to be added. The charge delay is set to 0xB000 (in terms of ADC clock
cycles) by default.

TSC steps are disabled at the end of every sampling cycle and EOS bit is
set. Once the EOS bit is set, the TSC steps need to be re-enabled to begin
next sampling cycle.

Signed-off-by: Brad Griffis <bgriffis@ti.com>
[vigneshr@ti.com: Ported the patch from v3.12 to v3.19rc1]
Signed-off-by: Vignesh R <vigneshr@ti.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/ti_am335x_tsc.c | 67 ++++++++++++++-----------------
 include/linux/mfd/ti_am335x_tscadc.h      |  3 +-
 2 files changed, 33 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
index dfbb9fe6a27..0625c102a1d 100644
--- a/drivers/input/touchscreen/ti_am335x_tsc.c
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -173,11 +173,9 @@ static void titsc_step_config(struct titsc *ts_dev)
 		titsc_writel(ts_dev, REG_STEPDELAY(i), STEPCONFIG_OPENDLY);
 	}
 
-	/* Charge step configuration */
-	config = ts_dev->bit_xp | ts_dev->bit_yn |
-			STEPCHARGE_RFP_XPUL | STEPCHARGE_RFM_XNUR |
-			STEPCHARGE_INM_AN1 | STEPCHARGE_INP(ts_dev->inp_yp);
+	/* Make CHARGECONFIG same as IDLECONFIG */
 
+	config = titsc_readl(ts_dev, REG_IDLECONFIG);
 	titsc_writel(ts_dev, REG_CHARGECONFIG, config);
 	titsc_writel(ts_dev, REG_CHARGEDELAY, CHARGEDLY_OPENDLY);
 
@@ -261,12 +259,34 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 {
 	struct titsc *ts_dev = dev;
 	struct input_dev *input_dev = ts_dev->input;
-	unsigned int status, irqclr = 0;
+	unsigned int fsm, status, irqclr = 0;
 	unsigned int x = 0, y = 0;
 	unsigned int z1, z2, z;
-	unsigned int fsm;
 
-	status = titsc_readl(ts_dev, REG_IRQSTATUS);
+	status = titsc_readl(ts_dev, REG_RAWIRQSTATUS);
+	if (status & IRQENB_HW_PEN) {
+		ts_dev->pen_down = true;
+		titsc_writel(ts_dev, REG_IRQWAKEUP, 0x00);
+		titsc_writel(ts_dev, REG_IRQCLR, IRQENB_HW_PEN);
+		irqclr |= IRQENB_HW_PEN;
+	}
+
+	if (status & IRQENB_PENUP) {
+		fsm = titsc_readl(ts_dev, REG_ADCFSM);
+		if (fsm == ADCFSM_STEPID) {
+			ts_dev->pen_down = false;
+			input_report_key(input_dev, BTN_TOUCH, 0);
+			input_report_abs(input_dev, ABS_PRESSURE, 0);
+			input_sync(input_dev);
+		} else {
+			ts_dev->pen_down = true;
+		}
+		irqclr |= IRQENB_PENUP;
+	}
+
+	if (status & IRQENB_EOS)
+		irqclr |= IRQENB_EOS;
+
 	/*
 	 * ADC and touchscreen share the IRQ line.
 	 * FIFO1 interrupts are used by ADC. Handle FIFO0 IRQs here only
@@ -297,37 +317,11 @@ static irqreturn_t titsc_irq(int irq, void *dev)
 		}
 		irqclr |= IRQENB_FIFO0THRES;
 	}
-
-	/*
-	 * Time for sequencer to settle, to read
-	 * correct state of the sequencer.
-	 */
-	udelay(SEQ_SETTLE);
-
-	status = titsc_readl(ts_dev, REG_RAWIRQSTATUS);
-	if (status & IRQENB_PENUP) {
-		/* Pen up event */
-		fsm = titsc_readl(ts_dev, REG_ADCFSM);
-		if (fsm == ADCFSM_STEPID) {
-			ts_dev->pen_down = false;
-			input_report_key(input_dev, BTN_TOUCH, 0);
-			input_report_abs(input_dev, ABS_PRESSURE, 0);
-			input_sync(input_dev);
-		} else {
-			ts_dev->pen_down = true;
-		}
-		irqclr |= IRQENB_PENUP;
-	}
-
-	if (status & IRQENB_HW_PEN) {
-
-		titsc_writel(ts_dev, REG_IRQWAKEUP, 0x00);
-		titsc_writel(ts_dev, REG_IRQCLR, IRQENB_HW_PEN);
-	}
-
 	if (irqclr) {
 		titsc_writel(ts_dev, REG_IRQSTATUS, irqclr);
-		am335x_tsc_se_set_cache(ts_dev->mfd_tscadc, ts_dev->step_mask);
+		if (status & IRQENB_EOS)
+			am335x_tsc_se_set_cache(ts_dev->mfd_tscadc,
+						ts_dev->step_mask);
 		return IRQ_HANDLED;
 	}
 	return IRQ_NONE;
@@ -417,6 +411,7 @@ static int titsc_probe(struct platform_device *pdev)
 	}
 
 	titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_FIFO0THRES);
+	titsc_writel(ts_dev, REG_IRQENABLE, IRQENB_EOS);
 	err = titsc_config_wires(ts_dev);
 	if (err) {
 		dev_err(&pdev->dev, "wrong i/p wire configuration\n");
diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h
index e2e70053470..3f4e994ace2 100644
--- a/include/linux/mfd/ti_am335x_tscadc.h
+++ b/include/linux/mfd/ti_am335x_tscadc.h
@@ -52,6 +52,7 @@
 
 /* IRQ enable */
 #define IRQENB_HW_PEN		BIT(0)
+#define IRQENB_EOS		BIT(1)
 #define IRQENB_FIFO0THRES	BIT(2)
 #define IRQENB_FIFO0OVRRUN	BIT(3)
 #define IRQENB_FIFO0UNDRFLW	BIT(4)
@@ -107,7 +108,7 @@
 /* Charge delay */
 #define CHARGEDLY_OPEN_MASK	(0x3FFFF << 0)
 #define CHARGEDLY_OPEN(val)	((val) << 0)
-#define CHARGEDLY_OPENDLY	CHARGEDLY_OPEN(1)
+#define CHARGEDLY_OPENDLY	CHARGEDLY_OPEN(0x400)
 
 /* Control register */
 #define CNTRLREG_TSCSSENB	BIT(0)
-- 
cgit v1.2.3-70-g09d2


From a49170b552423a3e85fc4f0d778c707402ee4863 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Mon, 2 Feb 2015 10:42:58 +0800
Subject: ACPI: Return translation offset when parsing ACPI address space
 resources

Change function acpi_dev_resource_address_space() and
acpi_dev_resource_ext_address_space() to return address space
translation offset.

It's based on a patch from Yinghai Lu <yinghai@kernel.org>.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/resource.c        | 58 +++++++++++++++++++++++-------------------
 drivers/pnp/pnpacpi/rsparser.c | 29 +++++++++++----------
 include/linux/acpi.h           |  9 +++++--
 3 files changed, 54 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 57891a621b9..c902c8eece8 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -184,13 +184,14 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res)
 }
 EXPORT_SYMBOL_GPL(acpi_dev_resource_io);
 
-static bool acpi_decode_space(struct resource *res,
+static bool acpi_decode_space(struct resource_win *win,
 			      struct acpi_resource_address *addr,
 			      struct acpi_address64_attribute *attr)
 {
 	u8 iodec = attr->granularity == 0xfff ? ACPI_DECODE_10 : ACPI_DECODE_16;
 	bool wp = addr->info.mem.write_protect;
 	u64 len = attr->address_length;
+	struct resource *res = &win->res;
 
 	/*
 	 * Filter out invalid descriptor according to ACPI Spec 5.0, section
@@ -218,6 +219,8 @@ static bool acpi_decode_space(struct resource *res,
 		return false;
 	}
 
+	win->offset = attr->translation_offset;
+
 	if (addr->producer_consumer == ACPI_PRODUCER)
 		res->flags |= IORESOURCE_WINDOW;
 
@@ -230,27 +233,28 @@ static bool acpi_decode_space(struct resource *res,
 /**
  * acpi_dev_resource_address_space - Extract ACPI address space information.
  * @ares: Input ACPI resource object.
- * @res: Output generic resource object.
+ * @win: Output generic resource object.
  *
  * Check if the given ACPI resource object represents an address space resource
  * and if that's the case, use the information in it to populate the generic
- * resource object pointed to by @res.
+ * resource object pointed to by @win.
  *
  * Return:
- * 1) false with res->flags setting to zero: not the expected resource type
- * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource
+ * 1) false with win->res.flags setting to zero: not the expected resource type
+ * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned
+ *    resource
  * 3) true: valid assigned resource
  */
 bool acpi_dev_resource_address_space(struct acpi_resource *ares,
-				     struct resource *res)
+				     struct resource_win *win)
 {
 	struct acpi_resource_address64 addr;
 
-	res->flags = 0;
+	win->res.flags = 0;
 	if (ACPI_FAILURE(acpi_resource_to_address64(ares, &addr)))
 		return false;
 
-	return acpi_decode_space(res, (struct acpi_resource_address *)&addr,
+	return acpi_decode_space(win, (struct acpi_resource_address *)&addr,
 				 &addr.address);
 }
 EXPORT_SYMBOL_GPL(acpi_dev_resource_address_space);
@@ -258,29 +262,30 @@ EXPORT_SYMBOL_GPL(acpi_dev_resource_address_space);
 /**
  * acpi_dev_resource_ext_address_space - Extract ACPI address space information.
  * @ares: Input ACPI resource object.
- * @res: Output generic resource object.
+ * @win: Output generic resource object.
  *
  * Check if the given ACPI resource object represents an extended address space
  * resource and if that's the case, use the information in it to populate the
- * generic resource object pointed to by @res.
+ * generic resource object pointed to by @win.
  *
  * Return:
- * 1) false with res->flags setting to zero: not the expected resource type
- * 2) false with IORESOURCE_DISABLED in res->flags: valid unassigned resource
+ * 1) false with win->res.flags setting to zero: not the expected resource type
+ * 2) false with IORESOURCE_DISABLED in win->res.flags: valid unassigned
+ *    resource
  * 3) true: valid assigned resource
  */
 bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares,
-					 struct resource *res)
+					 struct resource_win *win)
 {
 	struct acpi_resource_extended_address64 *ext_addr;
 
-	res->flags = 0;
+	win->res.flags = 0;
 	if (ares->type != ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64)
 		return false;
 
 	ext_addr = &ares->data.ext_address64;
 
-	return acpi_decode_space(res, (struct acpi_resource_address *)ext_addr,
+	return acpi_decode_space(win, (struct acpi_resource_address *)ext_addr,
 				 &ext_addr->address);
 }
 EXPORT_SYMBOL_GPL(acpi_dev_resource_ext_address_space);
@@ -441,7 +446,7 @@ struct res_proc_context {
 	int error;
 };
 
-static acpi_status acpi_dev_new_resource_entry(struct resource *r,
+static acpi_status acpi_dev_new_resource_entry(struct resource_win *win,
 					       struct res_proc_context *c)
 {
 	struct resource_list_entry *rentry;
@@ -451,7 +456,7 @@ static acpi_status acpi_dev_new_resource_entry(struct resource *r,
 		c->error = -ENOMEM;
 		return AE_NO_MEMORY;
 	}
-	rentry->res = *r;
+	rentry->res = win->res;
 	list_add_tail(&rentry->node, c->list);
 	c->count++;
 	return AE_OK;
@@ -461,7 +466,8 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares,
 					     void *context)
 {
 	struct res_proc_context *c = context;
-	struct resource r;
+	struct resource_win win;
+	struct resource *res = &win.res;
 	int i;
 
 	if (c->preproc) {
@@ -476,18 +482,18 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares,
 		}
 	}
 
-	memset(&r, 0, sizeof(r));
+	memset(&win, 0, sizeof(win));
 
-	if (acpi_dev_resource_memory(ares, &r)
-	    || acpi_dev_resource_io(ares, &r)
-	    || acpi_dev_resource_address_space(ares, &r)
-	    || acpi_dev_resource_ext_address_space(ares, &r))
-		return acpi_dev_new_resource_entry(&r, c);
+	if (acpi_dev_resource_memory(ares, res)
+	    || acpi_dev_resource_io(ares, res)
+	    || acpi_dev_resource_address_space(ares, &win)
+	    || acpi_dev_resource_ext_address_space(ares, &win))
+		return acpi_dev_new_resource_entry(&win, c);
 
-	for (i = 0; acpi_dev_resource_interrupt(ares, i, &r); i++) {
+	for (i = 0; acpi_dev_resource_interrupt(ares, i, res); i++) {
 		acpi_status status;
 
-		status = acpi_dev_new_resource_entry(&r, c);
+		status = acpi_dev_new_resource_entry(&win, c);
 		if (ACPI_FAILURE(status))
 			return status;
 	}
diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c
index 2d9bc789af0..ff0356fb378 100644
--- a/drivers/pnp/pnpacpi/rsparser.c
+++ b/drivers/pnp/pnpacpi/rsparser.c
@@ -180,20 +180,21 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 	struct pnp_dev *dev = data;
 	struct acpi_resource_dma *dma;
 	struct acpi_resource_vendor_typed *vendor_typed;
-	struct resource r = {0};
+	struct resource_win win = {{0}, 0};
+	struct resource *r = &win.res;
 	int i, flags;
 
-	if (acpi_dev_resource_address_space(res, &r)
-	    || acpi_dev_resource_ext_address_space(res, &r)) {
-		pnp_add_resource(dev, &r);
+	if (acpi_dev_resource_address_space(res, &win)
+	    || acpi_dev_resource_ext_address_space(res, &win)) {
+		pnp_add_resource(dev, &win.res);
 		return AE_OK;
 	}
 
-	r.flags = 0;
-	if (acpi_dev_resource_interrupt(res, 0, &r)) {
-		pnpacpi_add_irqresource(dev, &r);
-		for (i = 1; acpi_dev_resource_interrupt(res, i, &r); i++)
-			pnpacpi_add_irqresource(dev, &r);
+	r->flags = 0;
+	if (acpi_dev_resource_interrupt(res, 0, r)) {
+		pnpacpi_add_irqresource(dev, r);
+		for (i = 1; acpi_dev_resource_interrupt(res, i, r); i++)
+			pnpacpi_add_irqresource(dev, r);
 
 		if (i > 1) {
 			/*
@@ -209,7 +210,7 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 			}
 		}
 		return AE_OK;
-	} else if (r.flags & IORESOURCE_DISABLED) {
+	} else if (r->flags & IORESOURCE_DISABLED) {
 		pnp_add_irq_resource(dev, 0, IORESOURCE_DISABLED);
 		return AE_OK;
 	}
@@ -218,13 +219,13 @@ static acpi_status pnpacpi_allocated_resource(struct acpi_resource *res,
 	case ACPI_RESOURCE_TYPE_MEMORY24:
 	case ACPI_RESOURCE_TYPE_MEMORY32:
 	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
-		if (acpi_dev_resource_memory(res, &r))
-			pnp_add_resource(dev, &r);
+		if (acpi_dev_resource_memory(res, r))
+			pnp_add_resource(dev, r);
 		break;
 	case ACPI_RESOURCE_TYPE_IO:
 	case ACPI_RESOURCE_TYPE_FIXED_IO:
-		if (acpi_dev_resource_io(res, &r))
-			pnp_add_resource(dev, &r);
+		if (acpi_dev_resource_io(res, r))
+			pnp_add_resource(dev, r);
 		break;
 	case ACPI_RESOURCE_TYPE_DMA:
 		dma = &res->data.dma;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d459cd17b47..be9eaee8f4a 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -285,12 +285,17 @@ extern int pnpacpi_disabled;
 
 #define PXM_INVAL	(-1)
 
+struct resource_win {
+	struct resource res;
+	resource_size_t offset;
+};
+
 bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res);
 bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res);
 bool acpi_dev_resource_address_space(struct acpi_resource *ares,
-				     struct resource *res);
+				     struct resource_win *win);
 bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares,
-					 struct resource *res);
+					 struct resource_win *win);
 unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable);
 bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 				 struct resource *res);
-- 
cgit v1.2.3-70-g09d2


From 93286f4798590e711aa395503401f8632fb74f9a Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Mon, 2 Feb 2015 10:43:00 +0800
Subject: ACPI: Add field offset to struct resource_list_entry

Add field offset to struct resource_list_entry to host address space
translation offset so it could be used to represent bridge resources.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/resource.c | 1 +
 include/linux/acpi.h    | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 4dc8cfb2e94..1c3abae6f2f 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -472,6 +472,7 @@ static acpi_status acpi_dev_new_resource_entry(struct resource_win *win,
 		return AE_NO_MEMORY;
 	}
 	rentry->res = win->res;
+	rentry->offset = win->offset;
 	list_add_tail(&rentry->node, c->list);
 	c->count++;
 	return AE_OK;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index be9eaee8f4a..21dac3cb62d 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -303,6 +303,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 struct resource_list_entry {
 	struct list_head node;
 	struct resource res;
+	resource_size_t offset;
 };
 
 void acpi_dev_free_resource_list(struct list_head *list);
-- 
cgit v1.2.3-70-g09d2


From 62d1141ff34e35de496ba06491c8e854b23b3f3e Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Mon, 2 Feb 2015 10:43:01 +0800
Subject: ACPI: Introduce helper function acpi_dev_filter_resource_type()

Introduce helper function acpi_dev_filter_resource_type(), which may
be used by acpi_dev_get_resources() to filer out resource based on
resource type.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/resource.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/acpi.h    |  8 +++++++
 2 files changed, 63 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 1c3abae6f2f..3ea0d17eb95 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -569,3 +569,58 @@ int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list,
 	return c.count;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_get_resources);
+
+/**
+ * acpi_dev_filter_resource_type - Filter ACPI resource according to resource
+ *				   types
+ * @ares: Input ACPI resource object.
+ * @types: Valid resource types of IORESOURCE_XXX
+ *
+ * This is a hepler function to support acpi_dev_get_resources(), which filters
+ * ACPI resource objects according to resource types.
+ */
+int acpi_dev_filter_resource_type(struct acpi_resource *ares,
+				  unsigned long types)
+{
+	unsigned long type = 0;
+
+	switch (ares->type) {
+	case ACPI_RESOURCE_TYPE_MEMORY24:
+	case ACPI_RESOURCE_TYPE_MEMORY32:
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		type = IORESOURCE_MEM;
+		break;
+	case ACPI_RESOURCE_TYPE_IO:
+	case ACPI_RESOURCE_TYPE_FIXED_IO:
+		type = IORESOURCE_IO;
+		break;
+	case ACPI_RESOURCE_TYPE_IRQ:
+	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
+		type = IORESOURCE_IRQ;
+		break;
+	case ACPI_RESOURCE_TYPE_DMA:
+	case ACPI_RESOURCE_TYPE_FIXED_DMA:
+		type = IORESOURCE_DMA;
+		break;
+	case ACPI_RESOURCE_TYPE_GENERIC_REGISTER:
+		type = IORESOURCE_REG;
+		break;
+	case ACPI_RESOURCE_TYPE_ADDRESS16:
+	case ACPI_RESOURCE_TYPE_ADDRESS32:
+	case ACPI_RESOURCE_TYPE_ADDRESS64:
+	case ACPI_RESOURCE_TYPE_EXTENDED_ADDRESS64:
+		if (ares->data.address.resource_type == ACPI_MEMORY_RANGE)
+			type = IORESOURCE_MEM;
+		else if (ares->data.address.resource_type == ACPI_IO_RANGE)
+			type = IORESOURCE_IO;
+		else if (ares->data.address.resource_type ==
+			 ACPI_BUS_NUMBER_RANGE)
+			type = IORESOURCE_BUS;
+		break;
+	default:
+		break;
+	}
+
+	return (type & types) ? 0 : 1;
+}
+EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 21dac3cb62d..e818decb631 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -310,6 +310,14 @@ void acpi_dev_free_resource_list(struct list_head *list);
 int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list,
 			   int (*preproc)(struct acpi_resource *, void *),
 			   void *preproc_data);
+int acpi_dev_filter_resource_type(struct acpi_resource *ares,
+				  unsigned long types);
+
+static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares,
+						   void *arg)
+{
+	return acpi_dev_filter_resource_type(ares, (unsigned long)arg);
+}
 
 int acpi_check_resource_conflict(const struct resource *res);
 
-- 
cgit v1.2.3-70-g09d2


From c1dbe2fbb33ef425a81e1a7cffd17c113c87cdbc Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 27 Jan 2015 21:13:39 +0100
Subject: PM / Domains: Remove reference counting for the
 generic_pm_domain_data

The reference counting was needed when genpd supported PM domain device
callbacks. Since this option has been removed, let's also remove the
reference counting of the struct generic_pm_domain_data.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 10 ++--------
 include/linux/pm_domain.h   |  1 -
 2 files changed, 2 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index f9e7df554b2..351df5bbd9c 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1456,7 +1456,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 		gpd_data = gpd_data_new;
 		dev->power.subsys_data->domain_data = &gpd_data->base;
 	}
-	gpd_data->refcount++;
 	if (td)
 		gpd_data->td = *td;
 
@@ -1504,7 +1503,6 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 {
 	struct generic_pm_domain_data *gpd_data;
 	struct pm_domain_data *pdd;
-	bool remove = false;
 	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
@@ -1533,10 +1531,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	pdd = dev->power.subsys_data->domain_data;
 	list_del_init(&pdd->list_node);
 	gpd_data = to_gpd_data(pdd);
-	if (--gpd_data->refcount == 0) {
-		dev->power.subsys_data->domain_data = NULL;
-		remove = true;
-	}
+	dev->power.subsys_data->domain_data = NULL;
 
 	spin_unlock_irq(&dev->power.lock);
 
@@ -1547,8 +1542,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	genpd_release_lock(genpd);
 
 	dev_pm_put_subsys_data(dev);
-	if (remove)
-		genpd_free_dev_data(dev, gpd_data);
+	genpd_free_dev_data(dev, gpd_data);
 
 	return 0;
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index ed607760fc2..e160a0bba28 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -114,7 +114,6 @@ struct generic_pm_domain_data {
 	struct gpd_timing_data td;
 	struct notifier_block nb;
 	struct mutex lock;
-	unsigned int refcount;
 	int need_restore;
 };
 
-- 
cgit v1.2.3-70-g09d2


From c0356db7d1b66840882744cbd9d9c5960b2d88c7 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 27 Jan 2015 21:13:42 +0100
Subject: PM / Domains: Eliminate the mutex for the generic_pm_domain_data

While adding devices to their PM domains, dev_pm_qos_add_notifier() was
invoked while allocating the generic_pm_domain_data for the device.

Since the generic_pm_domain_data's device pointer will be assigned
after allocation, the ->genpd_dev_pm_qos_notifier() callback could be
called prior having a valid pointer to the device. Similar scenario
existed while removing a device from a genpd.

To cope with these scenarios a mutex was used to protect the pointer to
the device.

By re-order the sequence for when dev_pm_qos_add|remove_notifier() are
invoked, we make sure the ->genpd_dev_pm_qos_notifier() callback are
always called with a valid device pointer available.

In this way, we eliminate the need for protecting the pointer and thus
we can remove the mutex from the struct generic_pm_domain_data.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 37 ++++++++++++++-----------------------
 include/linux/pm_domain.h   |  1 -
 2 files changed, 14 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 88198ba919d..1f026c18bc5 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -344,14 +344,7 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 	struct device *dev;
 
 	gpd_data = container_of(nb, struct generic_pm_domain_data, nb);
-
-	mutex_lock(&gpd_data->lock);
 	dev = gpd_data->base.dev;
-	if (!dev) {
-		mutex_unlock(&gpd_data->lock);
-		return NOTIFY_DONE;
-	}
-	mutex_unlock(&gpd_data->lock);
 
 	for (;;) {
 		struct generic_pm_domain *genpd;
@@ -1392,16 +1385,12 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev)
 	if (!gpd_data)
 		return NULL;
 
-	mutex_init(&gpd_data->lock);
-	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
-	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 	return gpd_data;
 }
 
 static void genpd_free_dev_data(struct device *dev,
 				struct generic_pm_domain_data *gpd_data)
 {
-	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
 	kfree(gpd_data);
 }
 
@@ -1414,7 +1403,7 @@ static void genpd_free_dev_data(struct device *dev,
 int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 			  struct gpd_timing_data *td)
 {
-	struct generic_pm_domain_data *gpd_data_new, *gpd_data = NULL;
+	struct generic_pm_domain_data *gpd_data;
 	int ret = 0;
 
 	dev_dbg(dev, "%s()\n", __func__);
@@ -1422,8 +1411,8 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	gpd_data_new = genpd_alloc_dev_data(dev);
-	if (!gpd_data_new)
+	gpd_data = genpd_alloc_dev_data(dev);
+	if (!gpd_data)
 		return -ENOMEM;
 
 	genpd_acquire_lock(genpd);
@@ -1445,7 +1434,6 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 		goto out;
 	}
 
-	gpd_data = gpd_data_new;
 	dev->power.subsys_data->domain_data = &gpd_data->base;
 
 	if (td)
@@ -1461,19 +1449,20 @@ int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	genpd->device_count++;
 	genpd->max_off_time_changed = true;
 
-	mutex_lock(&gpd_data->lock);
 	gpd_data->base.dev = dev;
 	list_add_tail(&gpd_data->base.list_node, &genpd->dev_list);
 	gpd_data->need_restore = -1;
 	gpd_data->td.constraint_changed = true;
 	gpd_data->td.effective_constraint_ns = -1;
-	mutex_unlock(&gpd_data->lock);
+	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
 
  out:
 	genpd_release_lock(genpd);
 
-	if (gpd_data != gpd_data_new)
-		genpd_free_dev_data(dev, gpd_data_new);
+	if (ret)
+		genpd_free_dev_data(dev, gpd_data);
+	else
+		dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 
 	return ret;
 }
@@ -1509,6 +1498,11 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	    ||  pd_to_genpd(dev->pm_domain) != genpd)
 		return -EINVAL;
 
+	/* The above validation also means we have existing domain_data. */
+	pdd = dev->power.subsys_data->domain_data;
+	gpd_data = to_gpd_data(pdd);
+	dev_pm_qos_remove_notifier(dev, &gpd_data->nb);
+
 	genpd_acquire_lock(genpd);
 
 	if (genpd->prepared_count > 0) {
@@ -1525,16 +1519,12 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 	spin_lock_irq(&dev->power.lock);
 
 	dev->pm_domain = NULL;
-	pdd = dev->power.subsys_data->domain_data;
 	list_del_init(&pdd->list_node);
-	gpd_data = to_gpd_data(pdd);
 	dev->power.subsys_data->domain_data = NULL;
 
 	spin_unlock_irq(&dev->power.lock);
 
-	mutex_lock(&gpd_data->lock);
 	pdd->dev = NULL;
-	mutex_unlock(&gpd_data->lock);
 
 	genpd_release_lock(genpd);
 
@@ -1545,6 +1535,7 @@ int pm_genpd_remove_device(struct generic_pm_domain *genpd,
 
  out:
 	genpd_release_lock(genpd);
+	dev_pm_qos_add_notifier(dev, &gpd_data->nb);
 
 	return ret;
 }
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index e160a0bba28..080e778118b 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -113,7 +113,6 @@ struct generic_pm_domain_data {
 	struct pm_domain_data base;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
-	struct mutex lock;
 	int need_restore;
 };
 
-- 
cgit v1.2.3-70-g09d2


From 1e95e3b2da424db68d0a465273f1901a990c6277 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Thu, 29 Jan 2015 18:39:05 +0100
Subject: PM: Convert dev_pm_put_subsys_data() into a void function

Clients using the dev_pm_put_subsys_data() API isn't interested of a
return value. They care only of decreasing a reference to the device's
pm_subsys_data. So, let's convert the API to a void function, which
anyway seems like reasonable thing to do.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/common.c | 14 ++++----------
 include/linux/pm.h          |  2 +-
 2 files changed, 5 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index a1ee51d43da..f32b802b98f 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -56,13 +56,11 @@ EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data);
  * @dev: Device to handle.
  *
  * If the reference counter of power.subsys_data is zero after dropping the
- * reference, power.subsys_data is removed.  Return 1 if that happens or 0
- * otherwise.
+ * reference, power.subsys_data is removed.
  */
-int dev_pm_put_subsys_data(struct device *dev)
+void dev_pm_put_subsys_data(struct device *dev)
 {
 	struct pm_subsys_data *psd;
-	int ret = 1;
 
 	spin_lock_irq(&dev->power.lock);
 
@@ -70,18 +68,14 @@ int dev_pm_put_subsys_data(struct device *dev)
 	if (!psd)
 		goto out;
 
-	if (--psd->refcount == 0) {
+	if (--psd->refcount == 0)
 		dev->power.subsys_data = NULL;
-	} else {
+	else
 		psd = NULL;
-		ret = 0;
-	}
 
  out:
 	spin_unlock_irq(&dev->power.lock);
 	kfree(psd);
-
-	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
 
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 8b597636461..e2f1be6dd9d 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -597,7 +597,7 @@ struct dev_pm_info {
 
 extern void update_pm_runtime_accounting(struct device *dev);
 extern int dev_pm_get_subsys_data(struct device *dev);
-extern int dev_pm_put_subsys_data(struct device *dev);
+extern void dev_pm_put_subsys_data(struct device *dev);
 
 /*
  * Power domains provide callbacks that are executed during system suspend,
-- 
cgit v1.2.3-70-g09d2


From 851c63e3b381fdbf5aca1a797f37d8606b5588d2 Mon Sep 17 00:00:00 2001
From: Daniel Thompson <daniel.thompson@linaro.org>
Date: Mon, 5 Jan 2015 15:43:39 +0000
Subject: of: Fix brace position for struct of_device_id definition

Currently it is not easy to grep for the definition of struct of_device_id.
This is trivially fixed by moving the brace to the right place.

Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <robh+dt@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 include/linux/mod_devicetable.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 745def86258..bbf85d612be 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -220,8 +220,7 @@ struct serio_device_id {
 /*
  * Struct used for matching a device
  */
-struct of_device_id
-{
+struct of_device_id {
 	char	name[32];
 	char	type[32];
 	char	compatible[128];
-- 
cgit v1.2.3-70-g09d2


From 4c946d9c11d173c2ea6b9081b248f8072e6b46f1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 27 Nov 2014 19:52:04 -0500
Subject: vmci: propagate msghdr all way down to __qp_memcpy_to_queue()

Switch from passing msg->iov_iter.iov to passing msg itself

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/misc/vmw_vmci/vmci_queue_pair.c | 16 ++++++++--------
 include/linux/vmw_vmci_api.h            |  2 +-
 net/vmw_vsock/vmci_transport.c          |  3 +--
 3 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c
index 7aaaf51e159..35f19a68382 100644
--- a/drivers/misc/vmw_vmci/vmci_queue_pair.c
+++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c
@@ -370,12 +370,12 @@ static int __qp_memcpy_to_queue(struct vmci_queue *queue,
 			to_copy = size - bytes_copied;
 
 		if (is_iovec) {
-			struct iovec *iov = (struct iovec *)src;
+			struct msghdr *msg = (struct msghdr *)src;
 			int err;
 
 			/* The iovec will track bytes_copied internally. */
-			err = memcpy_fromiovec((u8 *)va + page_offset,
-					       iov, to_copy);
+			err = memcpy_from_msg((u8 *)va + page_offset,
+					      msg, to_copy);
 			if (err != 0) {
 				if (kernel_if->host)
 					kunmap(kernel_if->u.h.page[page_index]);
@@ -580,7 +580,7 @@ static int qp_memcpy_from_queue(void *dest,
  */
 static int qp_memcpy_to_queue_iov(struct vmci_queue *queue,
 				  u64 queue_offset,
-				  const void *src,
+				  const void *msg,
 				  size_t src_offset, size_t size)
 {
 
@@ -588,7 +588,7 @@ static int qp_memcpy_to_queue_iov(struct vmci_queue *queue,
 	 * We ignore src_offset because src is really a struct iovec * and will
 	 * maintain offset internally.
 	 */
-	return __qp_memcpy_to_queue(queue, queue_offset, src, size, true);
+	return __qp_memcpy_to_queue(queue, queue_offset, msg, size, true);
 }
 
 /*
@@ -3223,13 +3223,13 @@ EXPORT_SYMBOL_GPL(vmci_qpair_peek);
  * of bytes enqueued or < 0 on error.
  */
 ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
-			  void *iov,
+			  struct msghdr *msg,
 			  size_t iov_size,
 			  int buf_type)
 {
 	ssize_t result;
 
-	if (!qpair || !iov)
+	if (!qpair)
 		return VMCI_ERROR_INVALID_ARGS;
 
 	qp_lock(qpair);
@@ -3238,7 +3238,7 @@ ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
 		result = qp_enqueue_locked(qpair->produce_q,
 					   qpair->consume_q,
 					   qpair->produce_q_size,
-					   iov, iov_size,
+					   msg, iov_size,
 					   qp_memcpy_to_queue_iov);
 
 		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h
index 5691f752ce8..63df3a2a8ce 100644
--- a/include/linux/vmw_vmci_api.h
+++ b/include/linux/vmw_vmci_api.h
@@ -74,7 +74,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair,
 ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size,
 			int mode);
 ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
-			  void *iov, size_t iov_size, int mode);
+			  struct msghdr *msg, size_t iov_size, int mode);
 ssize_t vmci_qpair_dequev(struct vmci_qp *qpair,
 			  struct msghdr *msg, size_t iov_size, int mode);
 ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size,
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 02d2e522924..7f3255084a6 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -1850,8 +1850,7 @@ static ssize_t vmci_transport_stream_enqueue(
 	struct msghdr *msg,
 	size_t len)
 {
-	/* XXX: stripping const */
-	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, (struct iovec *)msg->msg_iter.iov, len, 0);
+	return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg, len, 0);
 }
 
 static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk)
-- 
cgit v1.2.3-70-g09d2


From af2b040e470b470bfc881981db3c796072853eae Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 27 Nov 2014 21:44:24 -0500
Subject: rxrpc: switch rxrpc_send_data() to iov_iter primitives

Convert skb_add_data() to iov_iter; allows to get rid of the explicit
messing with iovec in its only caller - skb_add_data() will keep advancing
->msg_iter for us, so there's no need to similate that manually.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/skbuff.h | 11 +++++------
 net/rxrpc/ar-output.c  | 43 ++++++++++---------------------------------
 2 files changed, 15 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 85ab7d72b54..9a8bafee1b6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2484,19 +2484,18 @@ static inline int skb_put_padto(struct sk_buff *skb, unsigned int len)
 }
 
 static inline int skb_add_data(struct sk_buff *skb,
-			       char __user *from, int copy)
+			       struct iov_iter *from, int copy)
 {
 	const int off = skb->len;
 
 	if (skb->ip_summed == CHECKSUM_NONE) {
-		int err = 0;
-		__wsum csum = csum_and_copy_from_user(from, skb_put(skb, copy),
-							    copy, 0, &err);
-		if (!err) {
+		__wsum csum = 0;
+		if (csum_and_copy_from_iter(skb_put(skb, copy), copy,
+					    &csum, from) == copy) {
 			skb->csum = csum_block_add(skb->csum, csum, off);
 			return 0;
 		}
-	} else if (!copy_from_user(skb_put(skb, copy), from, copy))
+	} else if (copy_from_iter(skb_put(skb, copy), copy, from) == copy)
 		return 0;
 
 	__skb_trim(skb, off);
diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c
index e1a9373e597..963a5b91f3e 100644
--- a/net/rxrpc/ar-output.c
+++ b/net/rxrpc/ar-output.c
@@ -529,13 +529,11 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			   struct msghdr *msg, size_t len)
 {
 	struct rxrpc_skb_priv *sp;
-	unsigned char __user *from;
 	struct sk_buff *skb;
-	const struct iovec *iov;
 	struct sock *sk = &rx->sk;
 	long timeo;
 	bool more;
-	int ret, ioc, segment, copied;
+	int ret, copied;
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
@@ -545,25 +543,17 @@ static int rxrpc_send_data(struct kiocb *iocb,
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		return -EPIPE;
 
-	iov = msg->msg_iter.iov;
-	ioc = msg->msg_iter.nr_segs - 1;
-	from = iov->iov_base;
-	segment = iov->iov_len;
-	iov++;
 	more = msg->msg_flags & MSG_MORE;
 
 	skb = call->tx_pending;
 	call->tx_pending = NULL;
 
 	copied = 0;
-	do {
+	if (len > iov_iter_count(&msg->msg_iter))
+		len = iov_iter_count(&msg->msg_iter);
+	while (len) {
 		int copy;
 
-		if (segment > len)
-			segment = len;
-
-		_debug("SEGMENT %d @%p", segment, from);
-
 		if (!skb) {
 			size_t size, chunk, max, space;
 
@@ -631,13 +621,13 @@ static int rxrpc_send_data(struct kiocb *iocb,
 		/* append next segment of data to the current buffer */
 		copy = skb_tailroom(skb);
 		ASSERTCMP(copy, >, 0);
-		if (copy > segment)
-			copy = segment;
+		if (copy > len)
+			copy = len;
 		if (copy > sp->remain)
 			copy = sp->remain;
 
 		_debug("add");
-		ret = skb_add_data(skb, from, copy);
+		ret = skb_add_data(skb, &msg->msg_iter, copy);
 		_debug("added");
 		if (ret < 0)
 			goto efault;
@@ -646,18 +636,6 @@ static int rxrpc_send_data(struct kiocb *iocb,
 		copied += copy;
 
 		len -= copy;
-		segment -= copy;
-		from += copy;
-		while (segment == 0 && ioc > 0) {
-			from = iov->iov_base;
-			segment = iov->iov_len;
-			iov++;
-			ioc--;
-		}
-		if (len == 0) {
-			segment = 0;
-			ioc = 0;
-		}
 
 		/* check for the far side aborting the call or a network error
 		 * occurring */
@@ -665,7 +643,7 @@ static int rxrpc_send_data(struct kiocb *iocb,
 			goto call_aborted;
 
 		/* add the packet to the send queue if it's now full */
-		if (sp->remain <= 0 || (segment == 0 && !more)) {
+		if (sp->remain <= 0 || (!len && !more)) {
 			struct rxrpc_connection *conn = call->conn;
 			uint32_t seq;
 			size_t pad;
@@ -711,11 +689,10 @@ static int rxrpc_send_data(struct kiocb *iocb,
 
 			memcpy(skb->head, &sp->hdr,
 			       sizeof(struct rxrpc_header));
-			rxrpc_queue_packet(call, skb, segment == 0 && !more);
+			rxrpc_queue_packet(call, skb, !iov_iter_count(&msg->msg_iter) && !more);
 			skb = NULL;
 		}
-
-	} while (segment > 0);
+	}
 
 success:
 	ret = copied;
-- 
cgit v1.2.3-70-g09d2


From cacdc7d2f9fa42e29b650e2879df42ea7d7833c1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 27 Nov 2014 20:34:16 -0500
Subject: ip: stash a pointer to msghdr in struct ping_fakehdr

... instead of storing its ->mgs_iter.iov there

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/ping.h | 2 +-
 net/ipv4/ping.c    | 7 +++----
 net/ipv6/ping.c    | 3 +--
 3 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ping.h b/include/net/ping.h
index f074060bc5d..cc16d413f68 100644
--- a/include/net/ping.h
+++ b/include/net/ping.h
@@ -59,7 +59,7 @@ extern struct pingv6_ops pingv6_ops;
 
 struct pingfakehdr {
 	struct icmphdr icmph;
-	struct iovec *iov;
+	struct msghdr *msg;
 	sa_family_t family;
 	__wsum wcheck;
 };
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2a3720fb5a5..9e15ba70140 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -602,14 +602,14 @@ int ping_getfrag(void *from, char *to,
 		if (fraglen < sizeof(struct icmphdr))
 			BUG();
 		if (csum_partial_copy_fromiovecend(to + sizeof(struct icmphdr),
-			    pfh->iov, 0, fraglen - sizeof(struct icmphdr),
+			    pfh->msg->msg_iter.iov, 0, fraglen - sizeof(struct icmphdr),
 			    &pfh->wcheck))
 			return -EFAULT;
 	} else if (offset < sizeof(struct icmphdr)) {
 			BUG();
 	} else {
 		if (csum_partial_copy_fromiovecend
-				(to, pfh->iov, offset - sizeof(struct icmphdr),
+				(to, pfh->msg->msg_iter.iov, offset - sizeof(struct icmphdr),
 				 fraglen, &pfh->wcheck))
 			return -EFAULT;
 	}
@@ -811,8 +811,7 @@ back_from_confirm:
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
-	/* XXX: stripping const */
-	pfh.iov = (struct iovec *)msg->msg_iter.iov;
+	pfh.msg = msg;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET;
 
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 2d3148378a1..bd46f736f61 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -163,8 +163,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	pfh.icmph.checksum = 0;
 	pfh.icmph.un.echo.id = inet->inet_sport;
 	pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence;
-	/* XXX: stripping const */
-	pfh.iov = (struct iovec *)msg->msg_iter.iov;
+	pfh.msg = msg;
 	pfh.wcheck = 0;
 	pfh.family = AF_INET6;
 
-- 
cgit v1.2.3-70-g09d2


From 57be5bdad759b9dde8b0d0cc630782a1a4ac4b9f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 28 Nov 2014 13:40:20 -0500
Subject: ip: convert tcp_sendmsg() to iov_iter primitives

patch is actually smaller than it seems to be - most of it is unindenting
the inner loop body in tcp_sendmsg() itself...

the bit in tcp_input.c is going to get reverted very soon - that's what
memcpy_from_msg() will become, but not in this commit; let's keep it
reasonably contained...

There's one potentially subtle change here: in case of short copy from
userland, mainline tcp_send_syn_data() discards the skb it has allocated
and falls back to normal path, where we'll send as much as possible after
rereading the same data again.  This patch trims SYN+data skb instead -
that way we don't need to copy from the same place twice.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/net/sock.h    |  18 ++--
 net/ipv4/tcp.c        | 233 +++++++++++++++++++++++---------------------------
 net/ipv4/tcp_input.c  |   2 +-
 net/ipv4/tcp_output.c |  11 ++-
 4 files changed, 123 insertions(+), 141 deletions(-)

(limited to 'include')

diff --git a/include/net/sock.h b/include/net/sock.h
index 15341499786..1e45e599a3a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1803,27 +1803,25 @@ static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
 }
 
 static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb,
-					   char __user *from, char *to,
+					   struct iov_iter *from, char *to,
 					   int copy, int offset)
 {
 	if (skb->ip_summed == CHECKSUM_NONE) {
-		int err = 0;
-		__wsum csum = csum_and_copy_from_user(from, to, copy, 0, &err);
-		if (err)
-			return err;
+		__wsum csum = 0;
+		if (csum_and_copy_from_iter(to, copy, &csum, from) != copy)
+			return -EFAULT;
 		skb->csum = csum_block_add(skb->csum, csum, offset);
 	} else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) {
-		if (!access_ok(VERIFY_READ, from, copy) ||
-		    __copy_from_user_nocache(to, from, copy))
+		if (copy_from_iter_nocache(to, copy, from) != copy)
 			return -EFAULT;
-	} else if (copy_from_user(to, from, copy))
+	} else if (copy_from_iter(to, copy, from) != copy)
 		return -EFAULT;
 
 	return 0;
 }
 
 static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
-				       char __user *from, int copy)
+				       struct iov_iter *from, int copy)
 {
 	int err, offset = skb->len;
 
@@ -1835,7 +1833,7 @@ static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb,
 	return err;
 }
 
-static inline int skb_copy_to_page_nocache(struct sock *sk, char __user *from,
+static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from,
 					   struct sk_buff *skb,
 					   struct page *page,
 					   int off, int copy)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3075723c729..9d72a0fcd92 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1067,11 +1067,10 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t size)
 {
-	const struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int iovlen, flags, err, copied = 0;
-	int mss_now = 0, size_goal, copied_syn = 0, offset = 0;
+	int flags, err, copied = 0;
+	int mss_now = 0, size_goal, copied_syn = 0;
 	bool sg;
 	long timeo;
 
@@ -1084,7 +1083,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			goto out;
 		else if (err)
 			goto out_err;
-		offset = copied_syn;
 	}
 
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
@@ -1118,8 +1116,6 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 
 	/* Ok commence sending. */
-	iovlen = msg->msg_iter.nr_segs;
-	iov = msg->msg_iter.iov;
 	copied = 0;
 
 	err = -EPIPE;
@@ -1128,151 +1124,134 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	sg = !!(sk->sk_route_caps & NETIF_F_SG);
 
-	while (--iovlen >= 0) {
-		size_t seglen = iov->iov_len;
-		unsigned char __user *from = iov->iov_base;
+	while (iov_iter_count(&msg->msg_iter)) {
+		int copy = 0;
+		int max = size_goal;
 
-		iov++;
-		if (unlikely(offset > 0)) {  /* Skip bytes copied in SYN */
-			if (offset >= seglen) {
-				offset -= seglen;
-				continue;
-			}
-			seglen -= offset;
-			from += offset;
-			offset = 0;
+		skb = tcp_write_queue_tail(sk);
+		if (tcp_send_head(sk)) {
+			if (skb->ip_summed == CHECKSUM_NONE)
+				max = mss_now;
+			copy = max - skb->len;
 		}
 
-		while (seglen > 0) {
-			int copy = 0;
-			int max = size_goal;
-
-			skb = tcp_write_queue_tail(sk);
-			if (tcp_send_head(sk)) {
-				if (skb->ip_summed == CHECKSUM_NONE)
-					max = mss_now;
-				copy = max - skb->len;
-			}
-
-			if (copy <= 0) {
+		if (copy <= 0) {
 new_segment:
-				/* Allocate new segment. If the interface is SG,
-				 * allocate skb fitting to single page.
-				 */
-				if (!sk_stream_memory_free(sk))
-					goto wait_for_sndbuf;
+			/* Allocate new segment. If the interface is SG,
+			 * allocate skb fitting to single page.
+			 */
+			if (!sk_stream_memory_free(sk))
+				goto wait_for_sndbuf;
 
-				skb = sk_stream_alloc_skb(sk,
-							  select_size(sk, sg),
-							  sk->sk_allocation);
-				if (!skb)
-					goto wait_for_memory;
+			skb = sk_stream_alloc_skb(sk,
+						  select_size(sk, sg),
+						  sk->sk_allocation);
+			if (!skb)
+				goto wait_for_memory;
 
-				/*
-				 * Check whether we can use HW checksum.
-				 */
-				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
-					skb->ip_summed = CHECKSUM_PARTIAL;
+			/*
+			 * Check whether we can use HW checksum.
+			 */
+			if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
+				skb->ip_summed = CHECKSUM_PARTIAL;
 
-				skb_entail(sk, skb);
-				copy = size_goal;
-				max = size_goal;
+			skb_entail(sk, skb);
+			copy = size_goal;
+			max = size_goal;
 
-				/* All packets are restored as if they have
-				 * already been sent. skb_mstamp isn't set to
-				 * avoid wrong rtt estimation.
-				 */
-				if (tp->repair)
-					TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
-			}
+			/* All packets are restored as if they have
+			 * already been sent. skb_mstamp isn't set to
+			 * avoid wrong rtt estimation.
+			 */
+			if (tp->repair)
+				TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED;
+		}
 
-			/* Try to append data to the end of skb. */
-			if (copy > seglen)
-				copy = seglen;
-
-			/* Where to copy to? */
-			if (skb_availroom(skb) > 0) {
-				/* We have some space in skb head. Superb! */
-				copy = min_t(int, copy, skb_availroom(skb));
-				err = skb_add_data_nocache(sk, skb, from, copy);
-				if (err)
-					goto do_fault;
-			} else {
-				bool merge = true;
-				int i = skb_shinfo(skb)->nr_frags;
-				struct page_frag *pfrag = sk_page_frag(sk);
-
-				if (!sk_page_frag_refill(sk, pfrag))
-					goto wait_for_memory;
-
-				if (!skb_can_coalesce(skb, i, pfrag->page,
-						      pfrag->offset)) {
-					if (i == MAX_SKB_FRAGS || !sg) {
-						tcp_mark_push(tp, skb);
-						goto new_segment;
-					}
-					merge = false;
-				}
+		/* Try to append data to the end of skb. */
+		if (copy > iov_iter_count(&msg->msg_iter))
+			copy = iov_iter_count(&msg->msg_iter);
+
+		/* Where to copy to? */
+		if (skb_availroom(skb) > 0) {
+			/* We have some space in skb head. Superb! */
+			copy = min_t(int, copy, skb_availroom(skb));
+			err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy);
+			if (err)
+				goto do_fault;
+		} else {
+			bool merge = true;
+			int i = skb_shinfo(skb)->nr_frags;
+			struct page_frag *pfrag = sk_page_frag(sk);
+
+			if (!sk_page_frag_refill(sk, pfrag))
+				goto wait_for_memory;
 
-				copy = min_t(int, copy, pfrag->size - pfrag->offset);
-
-				if (!sk_wmem_schedule(sk, copy))
-					goto wait_for_memory;
-
-				err = skb_copy_to_page_nocache(sk, from, skb,
-							       pfrag->page,
-							       pfrag->offset,
-							       copy);
-				if (err)
-					goto do_error;
-
-				/* Update the skb. */
-				if (merge) {
-					skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
-				} else {
-					skb_fill_page_desc(skb, i, pfrag->page,
-							   pfrag->offset, copy);
-					get_page(pfrag->page);
+			if (!skb_can_coalesce(skb, i, pfrag->page,
+					      pfrag->offset)) {
+				if (i == MAX_SKB_FRAGS || !sg) {
+					tcp_mark_push(tp, skb);
+					goto new_segment;
 				}
-				pfrag->offset += copy;
+				merge = false;
 			}
 
-			if (!copied)
-				TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
-			tp->write_seq += copy;
-			TCP_SKB_CB(skb)->end_seq += copy;
-			tcp_skb_pcount_set(skb, 0);
+			if (!sk_wmem_schedule(sk, copy))
+				goto wait_for_memory;
 
-			from += copy;
-			copied += copy;
-			if ((seglen -= copy) == 0 && iovlen == 0) {
-				tcp_tx_timestamp(sk, skb);
-				goto out;
+			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
+						       pfrag->page,
+						       pfrag->offset,
+						       copy);
+			if (err)
+				goto do_error;
+
+			/* Update the skb. */
+			if (merge) {
+				skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+			} else {
+				skb_fill_page_desc(skb, i, pfrag->page,
+						   pfrag->offset, copy);
+				get_page(pfrag->page);
 			}
+			pfrag->offset += copy;
+		}
 
-			if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
-				continue;
+		if (!copied)
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
+
+		tp->write_seq += copy;
+		TCP_SKB_CB(skb)->end_seq += copy;
+		tcp_skb_pcount_set(skb, 0);
+
+		copied += copy;
+		if (!iov_iter_count(&msg->msg_iter)) {
+			tcp_tx_timestamp(sk, skb);
+			goto out;
+		}
 
-			if (forced_push(tp)) {
-				tcp_mark_push(tp, skb);
-				__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
-			} else if (skb == tcp_send_head(sk))
-				tcp_push_one(sk, mss_now);
+		if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
 			continue;
 
+		if (forced_push(tp)) {
+			tcp_mark_push(tp, skb);
+			__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
+		} else if (skb == tcp_send_head(sk))
+			tcp_push_one(sk, mss_now);
+		continue;
+
 wait_for_sndbuf:
-			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-			if (copied)
-				tcp_push(sk, flags & ~MSG_MORE, mss_now,
-					 TCP_NAGLE_PUSH, size_goal);
+		if (copied)
+			tcp_push(sk, flags & ~MSG_MORE, mss_now,
+				 TCP_NAGLE_PUSH, size_goal);
 
-			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
-				goto do_error;
+		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
+			goto do_error;
 
-			mss_now = tcp_send_mss(sk, &size_goal, flags);
-		}
+		mss_now = tcp_send_mss(sk, &size_goal, flags);
 	}
 
 out:
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 71fb37c7058..93c74829cbc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4368,7 +4368,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (memcpy_from_msg(skb_put(skb, size), msg, size))
+	if (copy_from_iter(skb_put(skb, size), size, &msg->msg_iter) != size)
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 20ab06b228a..722c8bceaf9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3055,7 +3055,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_fastopen_request *fo = tp->fastopen_req;
-	int syn_loss = 0, space, err = 0;
+	int syn_loss = 0, space, err = 0, copied;
 	unsigned long last_syn_loss = 0;
 	struct sk_buff *syn_data;
 
@@ -3093,11 +3093,16 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 		goto fallback;
 	syn_data->ip_summed = CHECKSUM_PARTIAL;
 	memcpy(syn_data->cb, syn->cb, sizeof(syn->cb));
-	if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space),
-					 fo->data->msg_iter.iov, 0, space))) {
+	copied = copy_from_iter(skb_put(syn_data, space), space,
+				&fo->data->msg_iter);
+	if (unlikely(!copied)) {
 		kfree_skb(syn_data);
 		goto fallback;
 	}
+	if (copied != space) {
+		skb_trim(syn_data, copied);
+		space = copied;
+	}
 
 	/* No more data pending in inet_wait_for_connect() */
 	if (space == fo->size)
-- 
cgit v1.2.3-70-g09d2


From 21226abb4e9f14d88238964d89b279e461ddc30c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 28 Nov 2014 15:48:29 -0500
Subject: net: switch memcpy_fromiovec()/memcpy_fromiovecend() users to
 copy_from_iter()

That takes care of the majority of ->sendmsg() instances - most of them
via memcpy_to_msg() or assorted getfrag() callbacks.  One place where we
still keep memcpy_fromiovecend() is tipc - there we potentially read the
same data over and over; separate patch, that...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/skbuff.h |  3 +--
 include/net/udplite.h  |  3 +--
 net/ipv4/ip_output.c   |  6 ++----
 net/ipv4/ping.c        | 14 +++++++-------
 net/ipv4/raw.c         |  2 +-
 net/ipv4/tcp_input.c   |  2 +-
 net/ipv6/raw.c         |  2 +-
 7 files changed, 14 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9a8bafee1b6..b349c96dc80 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2692,8 +2692,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
 
 static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len)
 {
-	/* XXX: stripping const */
-	return memcpy_fromiovec(data, (struct iovec *)msg->msg_iter.iov, len);
+	return copy_from_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT;
 }
 
 static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len)
diff --git a/include/net/udplite.h b/include/net/udplite.h
index ae7c8d1fbca..80761938b9a 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -20,8 +20,7 @@ static __inline__ int udplite_getfrag(void *from, char *to, int  offset,
 				      int len, int odd, struct sk_buff *skb)
 {
 	struct msghdr *msg = from;
-	/* XXX: stripping const */
-	return memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len);
+	return copy_from_iter(to, len, &msg->msg_iter) != len ? -EFAULT : 0;
 }
 
 /* Designate sk as UDP-Lite socket */
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b50861b22b6..f998bc87ae3 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -755,13 +755,11 @@ ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk
 	struct msghdr *msg = from;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		/* XXX: stripping const */
-		if (memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len) < 0)
+		if (copy_from_iter(to, len, &msg->msg_iter) != len)
 			return -EFAULT;
 	} else {
 		__wsum csum = 0;
-		/* XXX: stripping const */
-		if (csum_partial_copy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len, &csum) < 0)
+		if (csum_and_copy_from_iter(to, len, &csum, &msg->msg_iter) != len)
 			return -EFAULT;
 		skb->csum = csum_block_add(skb->csum, csum, odd);
 	}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 9e15ba70140..e9f66e1cda5 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -599,18 +599,18 @@ int ping_getfrag(void *from, char *to,
 	struct pingfakehdr *pfh = (struct pingfakehdr *)from;
 
 	if (offset == 0) {
-		if (fraglen < sizeof(struct icmphdr))
+		fraglen -= sizeof(struct icmphdr);
+		if (fraglen < 0)
 			BUG();
-		if (csum_partial_copy_fromiovecend(to + sizeof(struct icmphdr),
-			    pfh->msg->msg_iter.iov, 0, fraglen - sizeof(struct icmphdr),
-			    &pfh->wcheck))
+		if (csum_and_copy_from_iter(to + sizeof(struct icmphdr),
+			    fraglen, &pfh->wcheck,
+			    &pfh->msg->msg_iter) != fraglen)
 			return -EFAULT;
 	} else if (offset < sizeof(struct icmphdr)) {
 			BUG();
 	} else {
-		if (csum_partial_copy_fromiovecend
-				(to, pfh->msg->msg_iter.iov, offset - sizeof(struct icmphdr),
-				 fraglen, &pfh->wcheck))
+		if (csum_and_copy_from_iter(to, fraglen, &pfh->wcheck,
+					    &pfh->msg->msg_iter) != fraglen)
 			return -EFAULT;
 	}
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 2c9d252072a..f027a708b7e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -382,7 +382,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 
 	skb->transport_header = skb->network_header;
 	err = -EFAULT;
-	if (memcpy_fromiovecend((void *)iph, msg->msg_iter.iov, 0, length))
+	if (memcpy_from_msg(iph, msg, length))
 		goto error_free;
 
 	iphlen = iph->ihl * 4;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 93c74829cbc..71fb37c7058 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4368,7 +4368,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
 		goto err_free;
 
-	if (copy_from_iter(skb_put(skb, size), size, &msg->msg_iter) != size)
+	if (memcpy_from_msg(skb_put(skb, size), msg, size))
 		goto err_free;
 
 	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 0dbb328fa68..dae7f1a1e46 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -648,7 +648,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	skb->transport_header = skb->network_header;
-	err = memcpy_fromiovecend((void *)iph, msg->msg_iter.iov, 0, length);
+	err = memcpy_from_msg(iph, msg, length);
 	if (err)
 		goto error_fault;
 
-- 
cgit v1.2.3-70-g09d2


From 31a25fae85956e3a9c778141d29e5e803fb0b124 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 28 Nov 2014 15:53:57 -0500
Subject: net: bury net/core/iovec.c - nothing in there is used anymore

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/socket.h |   7 ---
 net/core/Makefile      |   2 +-
 net/core/iovec.c       | 137 -------------------------------------------------
 3 files changed, 1 insertion(+), 145 deletions(-)
 delete mode 100644 net/core/iovec.c

(limited to 'include')

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6e49a14365d..5c19cba34dc 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -318,13 +318,6 @@ struct ucred {
 /* IPX options */
 #define IPX_TYPE	1
 
-extern int csum_partial_copy_fromiovecend(unsigned char *kdata, 
-					  struct iovec *iov, 
-					  int offset, 
-					  unsigned int len, __wsum *csump);
-extern unsigned long iov_pages(const struct iovec *iov, int offset,
-			       unsigned long nr_segs);
-
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
 
diff --git a/net/core/Makefile b/net/core/Makefile
index 235e6c50708..fec0856dd6c 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the Linux networking core.
 #
 
-obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
+obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \
 	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
diff --git a/net/core/iovec.c b/net/core/iovec.c
deleted file mode 100644
index dcbe98b3726..00000000000
--- a/net/core/iovec.c
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- *	iovec manipulation routines.
- *
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		as published by the Free Software Foundation; either version
- *		2 of the License, or (at your option) any later version.
- *
- *	Fixes:
- *		Andrew Lunn	:	Errors in iovec copying.
- *		Pedro Roque	:	Added memcpy_fromiovecend and
- *					csum_..._fromiovecend.
- *		Andi Kleen	:	fixed error handling for 2.1
- *		Alexey Kuznetsov:	2.1 optimisations
- *		Andi Kleen	:	Fix csum*fromiovecend for IPv6.
- */
-
-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/net.h>
-#include <linux/in6.h>
-#include <asm/uaccess.h>
-#include <asm/byteorder.h>
-#include <net/checksum.h>
-#include <net/sock.h>
-
-/*
- *	And now for the all-in-one: copy and checksum from a user iovec
- *	directly to a datagram
- *	Calls to csum_partial but the last must be in 32 bit chunks
- *
- *	ip_build_xmit must ensure that when fragmenting only the last
- *	call to this function will be unaligned also.
- */
-int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov,
-				 int offset, unsigned int len, __wsum *csump)
-{
-	__wsum csum = *csump;
-	int partial_cnt = 0, err = 0;
-
-	/* Skip over the finished iovecs */
-	while (offset >= iov->iov_len) {
-		offset -= iov->iov_len;
-		iov++;
-	}
-
-	while (len > 0) {
-		u8 __user *base = iov->iov_base + offset;
-		int copy = min_t(unsigned int, len, iov->iov_len - offset);
-
-		offset = 0;
-
-		/* There is a remnant from previous iov. */
-		if (partial_cnt) {
-			int par_len = 4 - partial_cnt;
-
-			/* iov component is too short ... */
-			if (par_len > copy) {
-				if (copy_from_user(kdata, base, copy))
-					goto out_fault;
-				kdata += copy;
-				base += copy;
-				partial_cnt += copy;
-				len -= copy;
-				iov++;
-				if (len)
-					continue;
-				*csump = csum_partial(kdata - partial_cnt,
-							 partial_cnt, csum);
-				goto out;
-			}
-			if (copy_from_user(kdata, base, par_len))
-				goto out_fault;
-			csum = csum_partial(kdata - partial_cnt, 4, csum);
-			kdata += par_len;
-			base  += par_len;
-			copy  -= par_len;
-			len   -= par_len;
-			partial_cnt = 0;
-		}
-
-		if (len > copy) {
-			partial_cnt = copy % 4;
-			if (partial_cnt) {
-				copy -= partial_cnt;
-				if (copy_from_user(kdata + copy, base + copy,
-						partial_cnt))
-					goto out_fault;
-			}
-		}
-
-		if (copy) {
-			csum = csum_and_copy_from_user(base, kdata, copy,
-							csum, &err);
-			if (err)
-				goto out;
-		}
-		len   -= copy + partial_cnt;
-		kdata += copy + partial_cnt;
-		iov++;
-	}
-	*csump = csum;
-out:
-	return err;
-
-out_fault:
-	err = -EFAULT;
-	goto out;
-}
-EXPORT_SYMBOL(csum_partial_copy_fromiovecend);
-
-unsigned long iov_pages(const struct iovec *iov, int offset,
-			unsigned long nr_segs)
-{
-	unsigned long seg, base;
-	int pages = 0, len, size;
-
-	while (nr_segs && (offset >= iov->iov_len)) {
-		offset -= iov->iov_len;
-		++iov;
-		--nr_segs;
-	}
-
-	for (seg = 0; seg < nr_segs; seg++) {
-		base = (unsigned long)iov[seg].iov_base + offset;
-		len = iov[seg].iov_len - offset;
-		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
-		pages += size;
-		offset = 0;
-	}
-
-	return pages;
-}
-EXPORT_SYMBOL(iov_pages);
-- 
cgit v1.2.3-70-g09d2


From 1d10eb2f156f5fc83cf6c7ce60441592e66eadb3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 28 Nov 2014 16:39:25 -0500
Subject: crypto: switch af_alg_make_sg() to iov_iter

With that, all ->sendmsg() instances are converted to iov_iter primitives
and are agnostic wrt the kind of iov_iter they are working with.
So's the last remaining ->recvmsg() instance that wasn't kind-agnostic yet.
All ->sendmsg() and ->recvmsg() advance ->msg_iter by the amount actually
copied and none of them modifies the underlying iovec, etc.

Cc: linux-crypto@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 crypto/af_alg.c         | 40 ++++++++------------------
 crypto/algif_hash.c     | 45 ++++++++++++------------------
 crypto/algif_skcipher.c | 74 ++++++++++++++++++++++---------------------------
 include/crypto/if_alg.h |  3 +-
 4 files changed, 62 insertions(+), 100 deletions(-)

(limited to 'include')

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 4665b79c729..eb78fe8a60c 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -338,49 +338,31 @@ static const struct net_proto_family alg_family = {
 	.owner	=	THIS_MODULE,
 };
 
-int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len,
-		   int write)
+int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len)
 {
-	unsigned long from = (unsigned long)addr;
-	unsigned long npages;
-	unsigned off;
-	int err;
-	int i;
-
-	err = -EFAULT;
-	if (!access_ok(write ? VERIFY_READ : VERIFY_WRITE, addr, len))
-		goto out;
-
-	off = from & ~PAGE_MASK;
-	npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (npages > ALG_MAX_PAGES)
-		npages = ALG_MAX_PAGES;
+	size_t off;
+	ssize_t n;
+	int npages, i;
 
-	err = get_user_pages_fast(from, npages, write, sgl->pages);
-	if (err < 0)
-		goto out;
+	n = iov_iter_get_pages(iter, sgl->pages, len, ALG_MAX_PAGES, &off);
+	if (n < 0)
+		return n;
 
-	npages = err;
-	err = -EINVAL;
+	npages = PAGE_ALIGN(off + n);
 	if (WARN_ON(npages == 0))
-		goto out;
-
-	err = 0;
+		return -EINVAL;
 
 	sg_init_table(sgl->sg, npages);
 
-	for (i = 0; i < npages; i++) {
+	for (i = 0, len = n; i < npages; i++) {
 		int plen = min_t(int, len, PAGE_SIZE - off);
 
 		sg_set_page(sgl->sg + i, sgl->pages[i], plen, off);
 
 		off = 0;
 		len -= plen;
-		err += plen;
 	}
-
-out:
-	return err;
+	return n;
 }
 EXPORT_SYMBOL_GPL(af_alg_make_sg);
 
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 01f56eb7816..01da360bdb5 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -41,8 +41,6 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
 	struct hash_ctx *ctx = ask->private;
-	unsigned long iovlen;
-	const struct iovec *iov;
 	long copied = 0;
 	int err;
 
@@ -58,37 +56,28 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
 
 	ctx->more = 0;
 
-	for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0;
-	     iovlen--, iov++) {
-		unsigned long seglen = iov->iov_len;
-		char __user *from = iov->iov_base;
+	while (iov_iter_count(&msg->msg_iter)) {
+		int len = iov_iter_count(&msg->msg_iter);
 
-		while (seglen) {
-			int len = min_t(unsigned long, seglen, limit);
-			int newlen;
+		if (len > limit)
+			len = limit;
 
-			newlen = af_alg_make_sg(&ctx->sgl, from, len, 0);
-			if (newlen < 0) {
-				err = copied ? 0 : newlen;
-				goto unlock;
-			}
-
-			ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL,
-						newlen);
-
-			err = af_alg_wait_for_completion(
-				crypto_ahash_update(&ctx->req),
-				&ctx->completion);
+		len = af_alg_make_sg(&ctx->sgl, &msg->msg_iter, len);
+		if (len < 0) {
+			err = copied ? 0 : len;
+			goto unlock;
+		}
 
-			af_alg_free_sg(&ctx->sgl);
+		ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL, len);
 
-			if (err)
-				goto unlock;
+		err = af_alg_wait_for_completion(crypto_ahash_update(&ctx->req),
+						 &ctx->completion);
+		af_alg_free_sg(&ctx->sgl);
+		if (err)
+			goto unlock;
 
-			seglen -= newlen;
-			from += newlen;
-			copied += newlen;
-		}
+		copied += len;
+		iov_iter_advance(&msg->msg_iter, len);
 	}
 
 	err = 0;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index c12207c8dde..37110fd68ad 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -426,67 +426,59 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
 		&ctx->req));
 	struct skcipher_sg_list *sgl;
 	struct scatterlist *sg;
-	unsigned long iovlen;
-	const struct iovec *iov;
 	int err = -EAGAIN;
 	int used;
 	long copied = 0;
 
 	lock_sock(sk);
-	for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0;
-	     iovlen--, iov++) {
-		unsigned long seglen = iov->iov_len;
-		char __user *from = iov->iov_base;
-
-		while (seglen) {
-			sgl = list_first_entry(&ctx->tsgl,
-					       struct skcipher_sg_list, list);
-			sg = sgl->sg;
-
-			while (!sg->length)
-				sg++;
-
-			if (!ctx->used) {
-				err = skcipher_wait_for_data(sk, flags);
-				if (err)
-					goto unlock;
-			}
+	while (iov_iter_count(&msg->msg_iter)) {
+		sgl = list_first_entry(&ctx->tsgl,
+				       struct skcipher_sg_list, list);
+		sg = sgl->sg;
 
-			used = min_t(unsigned long, ctx->used, seglen);
+		while (!sg->length)
+			sg++;
 
-			used = af_alg_make_sg(&ctx->rsgl, from, used, 1);
-			err = used;
-			if (err < 0)
+		used = ctx->used;
+		if (!used) {
+			err = skcipher_wait_for_data(sk, flags);
+			if (err)
 				goto unlock;
+		}
+
+		used = min_t(unsigned long, used, iov_iter_count(&msg->msg_iter));
+
+		used = af_alg_make_sg(&ctx->rsgl, &msg->msg_iter, used);
+		err = used;
+		if (err < 0)
+			goto unlock;
 
-			if (ctx->more || used < ctx->used)
-				used -= used % bs;
+		if (ctx->more || used < ctx->used)
+			used -= used % bs;
 
-			err = -EINVAL;
-			if (!used)
-				goto free;
+		err = -EINVAL;
+		if (!used)
+			goto free;
 
-			ablkcipher_request_set_crypt(&ctx->req, sg,
-						     ctx->rsgl.sg, used,
-						     ctx->iv);
+		ablkcipher_request_set_crypt(&ctx->req, sg,
+					     ctx->rsgl.sg, used,
+					     ctx->iv);
 
-			err = af_alg_wait_for_completion(
+		err = af_alg_wait_for_completion(
 				ctx->enc ?
 					crypto_ablkcipher_encrypt(&ctx->req) :
 					crypto_ablkcipher_decrypt(&ctx->req),
 				&ctx->completion);
 
 free:
-			af_alg_free_sg(&ctx->rsgl);
+		af_alg_free_sg(&ctx->rsgl);
 
-			if (err)
-				goto unlock;
+		if (err)
+			goto unlock;
 
-			copied += used;
-			from += used;
-			seglen -= used;
-			skcipher_pull_sgl(sk, used);
-		}
+		copied += used;
+		skcipher_pull_sgl(sk, used);
+		iov_iter_advance(&msg->msg_iter, used);
 	}
 
 	err = 0;
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index cd62bf4289e..88ea64e9a91 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -67,8 +67,7 @@ int af_alg_unregister_type(const struct af_alg_type *type);
 int af_alg_release(struct socket *sock);
 int af_alg_accept(struct sock *sk, struct socket *newsock);
 
-int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len,
-		   int write);
+int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len);
 void af_alg_free_sg(struct af_alg_sgl *sgl);
 
 int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con);
-- 
cgit v1.2.3-70-g09d2


From aad9a1cec7dcd1d45809b64643fce37061b17788 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2014 14:49:01 -0500
Subject: vhost: switch vhost get_indirect() to iov_iter, kill
 memcpy_fromiovec()

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/vhost/vhost.c |  6 ++++--
 include/linux/uio.h   |  1 -
 lib/iovec.c           | 25 -------------------------
 3 files changed, 4 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index cb807d0ea49..2ee28266fd0 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1125,6 +1125,7 @@ static int get_indirect(struct vhost_virtqueue *vq,
 	struct vring_desc desc;
 	unsigned int i = 0, count, found = 0;
 	u32 len = vhost32_to_cpu(vq, indirect->len);
+	struct iov_iter from;
 	int ret;
 
 	/* Sanity check */
@@ -1142,6 +1143,7 @@ static int get_indirect(struct vhost_virtqueue *vq,
 		vq_err(vq, "Translation failure %d in indirect.\n", ret);
 		return ret;
 	}
+	iov_iter_init(&from, READ, vq->indirect, ret, len);
 
 	/* We will use the result as an address to read from, so most
 	 * architectures only need a compiler barrier here. */
@@ -1164,8 +1166,8 @@ static int get_indirect(struct vhost_virtqueue *vq,
 			       i, count);
 			return -EINVAL;
 		}
-		if (unlikely(memcpy_fromiovec((unsigned char *)&desc,
-					      vq->indirect, sizeof desc))) {
+		if (unlikely(copy_from_iter(&desc, sizeof(desc), &from) !=
+			     sizeof(desc))) {
 			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
 			       i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
 			return -EINVAL;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 1c5e453f7ea..af3439f4ebf 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -135,7 +135,6 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 
-int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
 			int offset, int len);
 int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
diff --git a/lib/iovec.c b/lib/iovec.c
index 2d99cb4a500..4a90875c64a 100644
--- a/lib/iovec.c
+++ b/lib/iovec.c
@@ -2,31 +2,6 @@
 #include <linux/export.h>
 #include <linux/uio.h>
 
-/*
- *	Copy iovec to kernel. Returns -EFAULT on error.
- *
- *	Note: this modifies the original iovec.
- */
-
-int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len)
-{
-	while (len > 0) {
-		if (iov->iov_len) {
-			int copy = min_t(unsigned int, len, iov->iov_len);
-			if (copy_from_user(kdata, iov->iov_base, copy))
-				return -EFAULT;
-			len -= copy;
-			kdata += copy;
-			iov->iov_base += copy;
-			iov->iov_len -= copy;
-		}
-		iov++;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_fromiovec);
-
 /*
  *	Copy kernel to iovec. Returns -EFAULT on error.
  */
-- 
cgit v1.2.3-70-g09d2


From ba7438aed924133df54a60e4cd5499d359bcf2a8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2014 15:51:28 -0500
Subject: vhost: don't bother copying iovecs in handle_rx(), kill
 memcpy_toiovecend()

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/vhost/net.c | 82 +++++++++++++++--------------------------------------
 include/linux/uio.h |  3 --
 lib/iovec.c         | 26 -----------------
 3 files changed, 23 insertions(+), 88 deletions(-)

(limited to 'include')

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index d86cc9bb9ea..e022cc40303 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -84,10 +84,6 @@ struct vhost_net_ubuf_ref {
 
 struct vhost_net_virtqueue {
 	struct vhost_virtqueue vq;
-	/* hdr is used to store the virtio header.
-	 * Since each iovec has >= 1 byte length, we never need more than
-	 * header length entries to store the header. */
-	struct iovec hdr[sizeof(struct virtio_net_hdr_mrg_rxbuf)];
 	size_t vhost_hlen;
 	size_t sock_hlen;
 	/* vhost zerocopy support fields below: */
@@ -235,44 +231,6 @@ static bool vhost_sock_zcopy(struct socket *sock)
 		sock_flag(sock->sk, SOCK_ZEROCOPY);
 }
 
-/* Pop first len bytes from iovec. Return number of segments used. */
-static int move_iovec_hdr(struct iovec *from, struct iovec *to,
-			  size_t len, int iov_count)
-{
-	int seg = 0;
-	size_t size;
-
-	while (len && seg < iov_count) {
-		size = min(from->iov_len, len);
-		to->iov_base = from->iov_base;
-		to->iov_len = size;
-		from->iov_len -= size;
-		from->iov_base += size;
-		len -= size;
-		++from;
-		++to;
-		++seg;
-	}
-	return seg;
-}
-/* Copy iovec entries for len bytes from iovec. */
-static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
-			   size_t len, int iovcount)
-{
-	int seg = 0;
-	size_t size;
-
-	while (len && seg < iovcount) {
-		size = min(from->iov_len, len);
-		to->iov_base = from->iov_base;
-		to->iov_len = size;
-		len -= size;
-		++from;
-		++to;
-		++seg;
-	}
-}
-
 /* In case of DMA done not in order in lower device driver for some reason.
  * upend_idx is used to track end of used idx, done_idx is used to track head
  * of used idx. Once lower device DMA done contiguously, we will signal KVM
@@ -570,9 +528,9 @@ static void handle_rx(struct vhost_net *net)
 		.msg_controllen = 0,
 		.msg_flags = MSG_DONTWAIT,
 	};
-	struct virtio_net_hdr_mrg_rxbuf hdr = {
-		.hdr.flags = 0,
-		.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
+	struct virtio_net_hdr hdr = {
+		.flags = 0,
+		.gso_type = VIRTIO_NET_HDR_GSO_NONE
 	};
 	size_t total_len = 0;
 	int err, mergeable;
@@ -580,6 +538,7 @@ static void handle_rx(struct vhost_net *net)
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
 	struct socket *sock;
+	struct iov_iter fixup;
 
 	mutex_lock(&vq->mutex);
 	sock = vq->private_data;
@@ -624,14 +583,19 @@ static void handle_rx(struct vhost_net *net)
 			break;
 		}
 		/* We don't need to be notified again. */
-		if (unlikely((vhost_hlen)))
-			/* Skip header. TODO: support TSO. */
-			move_iovec_hdr(vq->iov, nvq->hdr, vhost_hlen, in);
-		else
-			/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
-			 * needed because recvmsg can modify msg_iov. */
-			copy_iovec_hdr(vq->iov, nvq->hdr, sock_hlen, in);
-		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, sock_len);
+		iov_iter_init(&msg.msg_iter, READ, vq->iov, in, vhost_len);
+		fixup = msg.msg_iter;
+		if (unlikely((vhost_hlen))) {
+			/* We will supply the header ourselves
+			 * TODO: support TSO.
+			 */
+			iov_iter_advance(&msg.msg_iter, vhost_hlen);
+		} else {
+			/* It'll come from socket; we'll need to patch
+			 * ->num_buffers over if VIRTIO_NET_F_MRG_RXBUF
+			 */
+			iov_iter_advance(&fixup, sizeof(hdr));
+		}
 		err = sock->ops->recvmsg(NULL, sock, &msg,
 					 sock_len, MSG_DONTWAIT | MSG_TRUNC);
 		/* Userspace might have consumed the packet meanwhile:
@@ -643,18 +607,18 @@ static void handle_rx(struct vhost_net *net)
 			vhost_discard_vq_desc(vq, headcount);
 			continue;
 		}
+		/* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */
 		if (unlikely(vhost_hlen) &&
-		    memcpy_toiovecend(nvq->hdr, (unsigned char *)&hdr, 0,
-				      vhost_hlen)) {
+		    copy_to_iter(&hdr, sizeof(hdr), &fixup) != sizeof(hdr)) {
 			vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
 			       vq->iov->iov_base);
 			break;
 		}
-		/* TODO: Should check and handle checksum. */
+		/* Supply (or replace) ->num_buffers if VIRTIO_NET_F_MRG_RXBUF
+		 * TODO: Should check and handle checksum.
+		 */
 		if (likely(mergeable) &&
-		    memcpy_toiovecend(nvq->hdr, (unsigned char *)&headcount,
-				      offsetof(typeof(hdr), num_buffers),
-				      sizeof hdr.num_buffers)) {
+		    copy_to_iter(&headcount, 2, &fixup) != 2) {
 			vq_err(vq, "Failed num_buffers write");
 			vhost_discard_vq_desc(vq, headcount);
 			break;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index af3439f4ebf..02bd8a92038 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -137,7 +137,4 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct io
 
 int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
 			int offset, int len);
-int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
-		      int offset, int len);
-
 #endif
diff --git a/lib/iovec.c b/lib/iovec.c
index 4a90875c64a..d8f17a9b1cc 100644
--- a/lib/iovec.c
+++ b/lib/iovec.c
@@ -2,32 +2,6 @@
 #include <linux/export.h>
 #include <linux/uio.h>
 
-/*
- *	Copy kernel to iovec. Returns -EFAULT on error.
- */
-
-int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
-		      int offset, int len)
-{
-	int copy;
-	for (; len > 0; ++iov) {
-		/* Skip over the finished iovecs */
-		if (unlikely(offset >= iov->iov_len)) {
-			offset -= iov->iov_len;
-			continue;
-		}
-		copy = min_t(unsigned int, iov->iov_len - offset, len);
-		if (copy_to_user(iov->iov_base + offset, kdata, copy))
-			return -EFAULT;
-		offset = 0;
-		kdata += copy;
-		len -= copy;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_toiovecend);
-
 /*
  *	Copy iovec to kernel. Returns -EFAULT on error.
  */
-- 
cgit v1.2.3-70-g09d2


From 57dd8a0735aabff4862025cf64ad94da3d80e620 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 10 Dec 2014 16:03:43 -0500
Subject: vhost: vhost_scsi_handle_vq() should just use copy_from_user()

it has just verified that it asks no more than the length of the
first segment of iovec.

And with that the last user of stuff in lib/iovec.c is gone.
RIP.

Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Nicholas A. Bellinger <nab@linux-iscsi.org>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/vhost/scsi.c |  2 +-
 include/linux/uio.h  |  2 --
 lib/Makefile         |  2 +-
 lib/iovec.c          | 36 ------------------------------------
 4 files changed, 2 insertions(+), 40 deletions(-)
 delete mode 100644 lib/iovec.c

(limited to 'include')

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index d695b1673ae..dc78d87e0fc 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1079,7 +1079,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			       req_size, vq->iov[0].iov_len);
 			break;
 		}
-		ret = memcpy_fromiovecend(req, &vq->iov[0], 0, req_size);
+		ret = copy_from_user(req, vq->iov[0].iov_base, req_size);
 		if (unlikely(ret)) {
 			vq_err(vq, "Faulted on virtio_scsi_cmd_req\n");
 			break;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 02bd8a92038..3e0cb4ea390 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -135,6 +135,4 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
 
-int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-			int offset, int len);
 #endif
diff --git a/lib/Makefile b/lib/Makefile
index 3c3b30b9e02..1071d06398c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -24,7 +24,7 @@ obj-y	+= lockref.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
-	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
+	 gcd.o lcm.o list_sort.o uuid.o flex_array.o clz_ctz.o \
 	 bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \
 	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o
 obj-y += string_helpers.o
diff --git a/lib/iovec.c b/lib/iovec.c
deleted file mode 100644
index d8f17a9b1cc..00000000000
--- a/lib/iovec.c
+++ /dev/null
@@ -1,36 +0,0 @@
-#include <linux/uaccess.h>
-#include <linux/export.h>
-#include <linux/uio.h>
-
-/*
- *	Copy iovec to kernel. Returns -EFAULT on error.
- */
-
-int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-			int offset, int len)
-{
-	/* No data? Done! */
-	if (len == 0)
-		return 0;
-
-	/* Skip over the finished iovecs */
-	while (offset >= iov->iov_len) {
-		offset -= iov->iov_len;
-		iov++;
-	}
-
-	while (len > 0) {
-		u8 __user *base = iov->iov_base + offset;
-		int copy = min_t(unsigned int, len, iov->iov_len - offset);
-
-		offset = 0;
-		if (copy_from_user(kdata, base, copy))
-			return -EFAULT;
-		len -= copy;
-		kdata += copy;
-		iov++;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_fromiovecend);
-- 
cgit v1.2.3-70-g09d2


From 44fc0e5eec00db5fba748803c95920098089c4cc Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Fri, 30 Jan 2015 13:14:36 +0200
Subject: sched/wait: Introduce wait_on_bit_timeout()

Add a new wait_on_bit_timeout() helper, basically the same as
wait_on_bit() except that it also takes a 'timeout' parameter.

All the building blocks like bit_wait_timeout() and
out_of_line_wait_on_bit_timeout() are already in place so the
addition is rather simple.

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: davem@davemloft.net
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1422616476-2917-2-git-send-email-johan.hedberg@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/wait.h | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 37423e0e137..537d58eea8a 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -989,6 +989,32 @@ wait_on_bit_io(void *word, int bit, unsigned mode)
 				       mode);
 }
 
+/**
+ * wait_on_bit_timeout - wait for a bit to be cleared or a timeout elapses
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ * @timeout: timeout, in jiffies
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared. This is similar to wait_on_bit(), except also takes a
+ * timeout parameter.
+ *
+ * Returned value will be zero if the bit was cleared before the
+ * @timeout elapsed, or non-zero if the @timeout elapsed or process
+ * received a signal and the mode permitted wakeup on that signal.
+ */
+static inline int
+wait_on_bit_timeout(void *word, int bit, unsigned mode, unsigned long timeout)
+{
+	might_sleep();
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_timeout(word, bit,
+					       bit_wait_timeout,
+					       mode, timeout);
+}
+
 /**
  * wait_on_bit_action - wait for a bit to be cleared
  * @word: the word being waited on, a kernel virtual address
-- 
cgit v1.2.3-70-g09d2


From 0508c07f5e0c94f38afd5434e8b2a55b84553077 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Tue, 3 Feb 2015 16:36:15 -0500
Subject: ipv6: Select fragment id during UFO segmentation if not set.

If the IPv6 fragment id has not been set and we perform
fragmentation due to UFO, select a new fragment id.
We now consider a fragment id of 0 as unset and if id selection
process returns 0 (after all the pertrubations), we set it to
0x80000000, thus giving us ample space not to create collisions
with the next packet we may have to fragment.

When doing UFO integrity checking, we also select the
fragment id if it has not be set yet.   This is stored into
the skb_shinfo() thus allowing UFO to function correclty.

This patch also removes duplicate fragment id generation code
and moves ipv6_select_ident() into the header as it may be
used during GSO.

Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h     |  3 +++
 net/ipv6/ip6_output.c  | 14 --------------
 net/ipv6/output_core.c | 41 +++++++++++++++++++++++++++++++++++------
 net/ipv6/udp_offload.c | 10 +++++++++-
 4 files changed, 47 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4292929392b..9bf85d34c02 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -671,6 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
+			struct in6_addr *src);
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 void ipv6_proxy_select_ident(struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ce69a12ae48..d28f2a2efb3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -537,20 +537,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
-static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static u32 ip6_idents_hashrnd __read_mostly;
-	u32 hash, id;
-
-	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
-
-	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
-
-	id = ip_idents_reserve(hash, 1);
-	fhdr->identification = htonl(id);
-}
-
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 97f41a3e68d..54520a0bd5e 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -9,6 +9,24 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src)
+{
+	u32 hash, id;
+
+	hash = __ipv6_addr_jhash(dst, hashrnd);
+	hash = __ipv6_addr_jhash(src, hash);
+
+	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
+	 * set the hight order instead thus minimizing possible future
+	 * collisions.
+	 */
+	id = ip_idents_reserve(hash, 1);
+	if (unlikely(!id))
+		id = 1 << 31;
+
+	return id;
+}
+
 /* This function exists only for tap drivers that must support broken
  * clients requesting UFO without specifying an IPv6 fragment ID.
  *
@@ -22,7 +40,7 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
-	u32 hash, id;
+	u32 id;
 
 	addrs = skb_header_pointer(skb,
 				   skb_network_offset(skb) +
@@ -34,14 +52,25 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
-	hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&addrs[0], hash);
-
-	id = ip_idents_reserve(hash, 1);
-	skb_shinfo(skb)->ip6_frag_id = htonl(id);
+	id = __ipv6_select_ident(ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
+	skb_shinfo(skb)->ip6_frag_id = id;
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr,
+				 &rt->rt6i_src.addr);
+	fhdr->identification = htonl(id);
+}
+EXPORT_SYMBOL(ipv6_select_ident);
+
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b6aa8ed1825..a56276996b7 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -52,6 +52,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 
+		/* Set the IPv6 fragment id if not set yet */
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(skb);
+
 		segs = NULL;
 		goto out;
 	}
@@ -108,7 +112,11 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		if (skb_shinfo(skb)->ip6_frag_id)
+			fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		else
+			ipv6_select_ident(fptr,
+					  (struct rt6_info *)skb_dst(skb));
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()
-- 
cgit v1.2.3-70-g09d2


From 2fde4f94e0a9531251e706fa57131b51b0df042e Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 7 Jan 2015 15:01:54 +0000
Subject: perf: Decouple unthrottling and rotating

Currently the adjusments made as part of perf_event_task_tick() use the
percpu rotation lists to iterate over any active PMU contexts, but these
are not used by the context rotation code, having been replaced by
separate (per-context) hrtimer callbacks. However, some manipulation of
the rotation lists (i.e. removal of contexts) has remained in
perf_rotate_context(). This leads to the following issues:

* Contexts are not always removed from the rotation lists. Removal of
  PMUs which have been placed in rotation lists, but have not been
  removed by a hrtimer callback can result in corruption of the rotation
  lists (when memory backing the context is freed).

  This has been observed to result in hangs when PMU drivers built as
  modules are inserted and removed around the creation of events for
  said PMUs.

* Contexts which do not require rotation may be removed from the
  rotation lists as a result of a hrtimer, and will not be considered by
  the unthrottling code in perf_event_task_tick.

This patch fixes the issue by updating the rotation ist when events are
scheduled in/out, ensuring that each rotation list stays in sync with
the HW state. As each event holds a refcount on the module of its PMU,
this ensures that when a PMU module is unloaded none of its CPU contexts
can be in a rotation list. By maintaining a list of perf_event_contexts
rather than perf_event_cpu_contexts, we don't need separate paths to
handle the cpu and task contexts, which also makes the code a little
simpler.

As the rotation_list variables are not used for rotation, these are
renamed to active_ctx_list, which better matches their current function.
perf_pmu_rotate_{start,stop} are renamed to
perf_pmu_ctx_{activate,deactivate}.

Reported-by: Johannes Jensen <johannes.jensen@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Will Deacon <Will.Deacon@arm.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150129134511.GR17721@leverpostej
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/perf_event.h |  2 +-
 kernel/events/core.c       | 81 +++++++++++++++++-----------------------------
 2 files changed, 30 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 216653466a6..5cad0e6f355 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -469,6 +469,7 @@ struct perf_event_context {
 	 */
 	struct mutex			mutex;
 
+	struct list_head		active_ctx_list;
 	struct list_head		pinned_groups;
 	struct list_head		flexible_groups;
 	struct list_head		event_list;
@@ -519,7 +520,6 @@ struct perf_cpu_context {
 	int				exclusive;
 	struct hrtimer			hrtimer;
 	ktime_t				hrtimer_interval;
-	struct list_head		rotation_list;
 	struct pmu			*unique_pmu;
 	struct perf_cgroup		*cgrp;
 };
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 37cc20e8aa3..7f2fbb8b506 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -872,22 +872,32 @@ void perf_pmu_enable(struct pmu *pmu)
 		pmu->pmu_enable(pmu);
 }
 
-static DEFINE_PER_CPU(struct list_head, rotation_list);
+static DEFINE_PER_CPU(struct list_head, active_ctx_list);
 
 /*
- * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
- * because they're strictly cpu affine and rotate_start is called with IRQs
- * disabled, while rotate_context is called from IRQ context.
+ * perf_event_ctx_activate(), perf_event_ctx_deactivate(), and
+ * perf_event_task_tick() are fully serialized because they're strictly cpu
+ * affine and perf_event_ctx{activate,deactivate} are called with IRQs
+ * disabled, while perf_event_task_tick is called from IRQ context.
  */
-static void perf_pmu_rotate_start(struct pmu *pmu)
+static void perf_event_ctx_activate(struct perf_event_context *ctx)
 {
-	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-	struct list_head *head = this_cpu_ptr(&rotation_list);
+	struct list_head *head = this_cpu_ptr(&active_ctx_list);
 
 	WARN_ON(!irqs_disabled());
 
-	if (list_empty(&cpuctx->rotation_list))
-		list_add(&cpuctx->rotation_list, head);
+	WARN_ON(!list_empty(&ctx->active_ctx_list));
+
+	list_add(&ctx->active_ctx_list, head);
+}
+
+static void perf_event_ctx_deactivate(struct perf_event_context *ctx)
+{
+	WARN_ON(!irqs_disabled());
+
+	WARN_ON(list_empty(&ctx->active_ctx_list));
+
+	list_del_init(&ctx->active_ctx_list);
 }
 
 static void get_ctx(struct perf_event_context *ctx)
@@ -1233,8 +1243,6 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 		ctx->nr_branch_stack++;
 
 	list_add_rcu(&event->event_entry, &ctx->event_list);
-	if (!ctx->nr_events)
-		perf_pmu_rotate_start(ctx->pmu);
 	ctx->nr_events++;
 	if (event->attr.inherit_stat)
 		ctx->nr_stat++;
@@ -1561,7 +1569,8 @@ event_sched_out(struct perf_event *event,
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu--;
-	ctx->nr_active--;
+	if (!--ctx->nr_active)
+		perf_event_ctx_deactivate(ctx);
 	if (event->attr.freq && event->attr.sample_freq)
 		ctx->nr_freq--;
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
@@ -1885,7 +1894,8 @@ event_sched_in(struct perf_event *event,
 
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
-	ctx->nr_active++;
+	if (!ctx->nr_active++)
+		perf_event_ctx_activate(ctx);
 	if (event->attr.freq && event->attr.sample_freq)
 		ctx->nr_freq++;
 
@@ -2742,12 +2752,6 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
-
-	/*
-	 * Since these rotations are per-cpu, we need to ensure the
-	 * cpu-context we got scheduled on is actually rotating.
-	 */
-	perf_pmu_rotate_start(ctx->pmu);
 }
 
 /*
@@ -3035,25 +3039,18 @@ static void rotate_ctx(struct perf_event_context *ctx)
 		list_rotate_left(&ctx->flexible_groups);
 }
 
-/*
- * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
- * because they're strictly cpu affine and rotate_start is called with IRQs
- * disabled, while rotate_context is called from IRQ context.
- */
 static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 {
 	struct perf_event_context *ctx = NULL;
-	int rotate = 0, remove = 1;
+	int rotate = 0;
 
 	if (cpuctx->ctx.nr_events) {
-		remove = 0;
 		if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
 			rotate = 1;
 	}
 
 	ctx = cpuctx->task_ctx;
 	if (ctx && ctx->nr_events) {
-		remove = 0;
 		if (ctx->nr_events != ctx->nr_active)
 			rotate = 1;
 	}
@@ -3077,8 +3074,6 @@ static int perf_rotate_context(struct perf_cpu_context *cpuctx)
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 done:
-	if (remove)
-		list_del_init(&cpuctx->rotation_list);
 
 	return rotate;
 }
@@ -3096,9 +3091,8 @@ bool perf_event_can_stop_tick(void)
 
 void perf_event_task_tick(void)
 {
-	struct list_head *head = this_cpu_ptr(&rotation_list);
-	struct perf_cpu_context *cpuctx, *tmp;
-	struct perf_event_context *ctx;
+	struct list_head *head = this_cpu_ptr(&active_ctx_list);
+	struct perf_event_context *ctx, *tmp;
 	int throttled;
 
 	WARN_ON(!irqs_disabled());
@@ -3106,14 +3100,8 @@ void perf_event_task_tick(void)
 	__this_cpu_inc(perf_throttled_seq);
 	throttled = __this_cpu_xchg(perf_throttled_count, 0);
 
-	list_for_each_entry_safe(cpuctx, tmp, head, rotation_list) {
-		ctx = &cpuctx->ctx;
+	list_for_each_entry_safe(ctx, tmp, head, active_ctx_list)
 		perf_adjust_freq_unthr_context(ctx, throttled);
-
-		ctx = cpuctx->task_ctx;
-		if (ctx)
-			perf_adjust_freq_unthr_context(ctx, throttled);
-	}
 }
 
 static int event_enable_on_exec(struct perf_event *event,
@@ -3272,6 +3260,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx)
 {
 	raw_spin_lock_init(&ctx->lock);
 	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->active_ctx_list);
 	INIT_LIST_HEAD(&ctx->pinned_groups);
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
@@ -6954,7 +6943,6 @@ skip_type:
 
 		__perf_cpu_hrtimer_init(cpuctx, cpu);
 
-		INIT_LIST_HEAD(&cpuctx->rotation_list);
 		cpuctx->unique_pmu = pmu;
 	}
 
@@ -8384,7 +8372,7 @@ static void __init perf_event_init_all_cpus(void)
 	for_each_possible_cpu(cpu) {
 		swhash = &per_cpu(swevent_htable, cpu);
 		mutex_init(&swhash->hlist_mutex);
-		INIT_LIST_HEAD(&per_cpu(rotation_list, cpu));
+		INIT_LIST_HEAD(&per_cpu(active_ctx_list, cpu));
 	}
 }
 
@@ -8405,22 +8393,11 @@ static void perf_event_init_cpu(int cpu)
 }
 
 #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
-static void perf_pmu_rotate_stop(struct pmu *pmu)
-{
-	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-
-	WARN_ON(!irqs_disabled());
-
-	list_del_init(&cpuctx->rotation_list);
-}
-
 static void __perf_event_exit_context(void *__info)
 {
 	struct remove_event re = { .detach_group = true };
 	struct perf_event_context *ctx = __info;
 
-	perf_pmu_rotate_stop(ctx->pmu);
-
 	rcu_read_lock();
 	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
 		__perf_remove_from_context(&re);
-- 
cgit v1.2.3-70-g09d2


From 12bdf27d46c9d5e490fa164551642e065105db78 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 3 Feb 2015 19:48:04 +0100
Subject: NFC: nci: Add reference to the RF logical connection

The NCI_STATIC_RF_CONN_ID logical connection is the most used
connection. Keeping it directly accessible in the nci_dev
structure will simplify and optimize the access.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci_core.h | 1 +
 net/nfc/nci/core.c         | 2 +-
 net/nfc/nci/ntf.c          | 6 ++----
 net/nfc/nci/rsp.c          | 4 ++--
 4 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index be858870dac..731fa5be998 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -189,6 +189,7 @@ struct nci_dev {
 	__u8			cur_conn_id;
 
 	struct list_head	conn_info_list;
+	struct nci_conn_info	*rf_conn_info;
 
 	struct timer_list	cmd_timer;
 	struct timer_list	data_timer;
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index f74d420e2ea..17ff5f83393 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -803,7 +803,7 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target,
 	int rc;
 	struct nci_conn_info    *conn_info;
 
-	conn_info = nci_get_conn_info_by_conn_id(ndev, NCI_STATIC_RF_CONN_ID);
+	conn_info = ndev->rf_conn_info;
 	if (!conn_info)
 		return -EPROTO;
 
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 33f5f00ecf4..6bbbf6fdacc 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -625,8 +625,7 @@ static void nci_rf_intf_activated_ntf_packet(struct nci_dev *ndev,
 
 exit:
 	if (err == NCI_STATUS_OK) {
-		conn_info = nci_get_conn_info_by_conn_id(ndev,
-							 NCI_STATIC_RF_CONN_ID);
+		conn_info = ndev->rf_conn_info;
 		if (!conn_info)
 			return;
 
@@ -684,8 +683,7 @@ static void nci_rf_deactivate_ntf_packet(struct nci_dev *ndev,
 
 	pr_debug("entry, type 0x%x, reason 0x%x\n", ntf->type, ntf->reason);
 
-	conn_info =
-		nci_get_conn_info_by_conn_id(ndev, NCI_STATIC_RF_CONN_ID);
+	conn_info = ndev->rf_conn_info;
 	if (!conn_info)
 		return;
 
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index 31ccf7d05e8..05268eb473d 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -148,8 +148,7 @@ static void nci_rf_disc_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 	if (status == NCI_STATUS_OK) {
 		atomic_set(&ndev->state, NCI_DISCOVERY);
 
-		conn_info = nci_get_conn_info_by_conn_id(ndev,
-							 NCI_STATIC_RF_CONN_ID);
+		conn_info = ndev->rf_conn_info;
 		if (!conn_info) {
 			conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
 						 sizeof(struct nci_conn_info),
@@ -161,6 +160,7 @@ static void nci_rf_disc_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 			conn_info->conn_id = NCI_STATIC_RF_CONN_ID;
 			INIT_LIST_HEAD(&conn_info->list);
 			list_add(&conn_info->list, &ndev->conn_info_list);
+			ndev->rf_conn_info = conn_info;
 		}
 	}
 
-- 
cgit v1.2.3-70-g09d2


From b16ae7160a836c4a1e443ea6efca31421e86bae1 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 3 Feb 2015 19:48:05 +0100
Subject: NFC: nci: Support all destinations type when creating a connection

The current implementation limits nci_core_conn_create_req()
to only manage NCI_DESTINATION_NFCEE.
Add new parameters to nci_core_conn_create() to support all
destination types described in the NCI specification.
Because there are some parameters with variable size dynamic
buffer allocation is needed.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/st21nfcb/st21nfcb_se.c | 38 ++++++++++++++++++++++--------
 include/net/nfc/nci.h              | 18 +++++++-------
 include/net/nfc/nci_core.h         |  4 +++-
 net/nfc/nci/core.c                 | 48 ++++++++++++++++++++++++++------------
 4 files changed, 74 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/st21nfcb/st21nfcb_se.c b/drivers/nfc/st21nfcb/st21nfcb_se.c
index 9f4d8b744f3..3b465e4c85e 100644
--- a/drivers/nfc/st21nfcb/st21nfcb_se.c
+++ b/drivers/nfc/st21nfcb/st21nfcb_se.c
@@ -494,7 +494,8 @@ EXPORT_SYMBOL_GPL(st21nfcb_nci_enable_se);
 
 static int st21nfcb_hci_network_init(struct nci_dev *ndev)
 {
-	struct core_conn_create_dest_spec_params dest_params;
+	struct core_conn_create_dest_spec_params *dest_params;
+	struct dest_spec_params spec_params;
 	struct nci_conn_info    *conn_info;
 	int r, dev_num;
 
@@ -502,17 +503,29 @@ static int st21nfcb_hci_network_init(struct nci_dev *ndev)
 	if (r != NCI_STATUS_OK)
 		goto exit;
 
-	dest_params.type = NCI_DESTINATION_SPECIFIC_PARAM_NFCEE_TYPE;
-	dest_params.length = sizeof(struct dest_spec_params);
-	dest_params.value.id = ndev->hci_dev->conn_info->id;
-	dest_params.value.protocol = NCI_NFCEE_INTERFACE_HCI_ACCESS;
-	r = nci_core_conn_create(ndev, &dest_params);
-	if (r != NCI_STATUS_OK)
+	dest_params =
+		kzalloc(sizeof(struct core_conn_create_dest_spec_params) +
+			sizeof(struct dest_spec_params), GFP_KERNEL);
+	if (dest_params == NULL) {
+		r = -ENOMEM;
 		goto exit;
+	}
+
+	dest_params->type = NCI_DESTINATION_SPECIFIC_PARAM_NFCEE_TYPE;
+	dest_params->length = sizeof(struct dest_spec_params);
+	spec_params.id = ndev->hci_dev->conn_info->id;
+	spec_params.protocol = NCI_NFCEE_INTERFACE_HCI_ACCESS;
+	memcpy(dest_params->value, &spec_params, sizeof(struct dest_spec_params));
+	r = nci_core_conn_create(ndev, NCI_DESTINATION_NFCEE, 1,
+				 sizeof(struct core_conn_create_dest_spec_params) +
+				 sizeof(struct dest_spec_params),
+				 dest_params);
+	if (r != NCI_STATUS_OK)
+		goto free_dest_params;
 
 	conn_info = ndev->hci_dev->conn_info;
 	if (!conn_info)
-		goto exit;
+		goto free_dest_params;
 
 	memcpy(ndev->hci_dev->init_data.gates, st21nfcb_gates,
 	       sizeof(st21nfcb_gates));
@@ -522,8 +535,10 @@ static int st21nfcb_hci_network_init(struct nci_dev *ndev)
 	 * persistent info to discriminate 2 identical chips
 	 */
 	dev_num = find_first_zero_bit(dev_mask, ST21NFCB_NUM_DEVICES);
-	if (dev_num >= ST21NFCB_NUM_DEVICES)
-		return -ENODEV;
+	if (dev_num >= ST21NFCB_NUM_DEVICES) {
+		r = -ENODEV;
+		goto free_dest_params;
+	}
 
 	scnprintf(ndev->hci_dev->init_data.session_id,
 		  sizeof(ndev->hci_dev->init_data.session_id),
@@ -540,6 +555,9 @@ static int st21nfcb_hci_network_init(struct nci_dev *ndev)
 
 	return 0;
 
+free_dest_params:
+	kfree(dest_params);
+
 exit:
 	return r;
 }
diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 6c1beb2704b..695d33cb75e 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -244,21 +244,23 @@ struct nci_core_set_config_cmd {
 } __packed;
 
 #define NCI_OP_CORE_CONN_CREATE_CMD	nci_opcode_pack(NCI_GID_CORE, 0x04)
+#define DEST_SPEC_PARAMS_ID_INDEX	0
+#define DEST_SPEC_PARAMS_PROTOCOL_INDEX	1
 struct dest_spec_params {
-	__u8	id;
-	__u8	protocol;
+	__u8    id;
+	__u8    protocol;
 } __packed;
 
 struct core_conn_create_dest_spec_params {
-	__u8	type;
-	__u8	length;
-	struct dest_spec_params value;
+	__u8    type;
+	__u8    length;
+	__u8    value[0];
 } __packed;
 
 struct nci_core_conn_create_cmd {
-	__u8	destination_type;
-	__u8	number_destination_params;
-	struct core_conn_create_dest_spec_params params;
+	__u8    destination_type;
+	__u8    number_destination_params;
+	struct core_conn_create_dest_spec_params params[0];
 } __packed;
 
 #define NCI_OP_CORE_CONN_CLOSE_CMD	nci_opcode_pack(NCI_GID_CORE, 0x05)
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 731fa5be998..d34c1b2295d 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -263,7 +263,9 @@ int nci_set_config(struct nci_dev *ndev, __u8 id, size_t len, __u8 *val);
 
 int nci_nfcee_discover(struct nci_dev *ndev, u8 action);
 int nci_nfcee_mode_set(struct nci_dev *ndev, u8 nfcee_id, u8 nfcee_mode);
-int nci_core_conn_create(struct nci_dev *ndev,
+int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type,
+			 u8 number_destination_params,
+			 size_t params_len,
 			 struct core_conn_create_dest_spec_params *params);
 int nci_core_conn_close(struct nci_dev *ndev, u8 conn_id);
 
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 17ff5f83393..ddfe91e43c8 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -41,6 +41,11 @@
 #include <net/nfc/nci_core.h>
 #include <linux/nfc.h>
 
+struct core_conn_create_data {
+	int length;
+	struct nci_core_conn_create_cmd *cmd;
+};
+
 static void nci_cmd_work(struct work_struct *work);
 static void nci_rx_work(struct work_struct *work);
 static void nci_tx_work(struct work_struct *work);
@@ -509,25 +514,38 @@ EXPORT_SYMBOL(nci_nfcee_mode_set);
 
 static void nci_core_conn_create_req(struct nci_dev *ndev, unsigned long opt)
 {
-	struct nci_core_conn_create_cmd cmd;
-	struct core_conn_create_dest_spec_params *params =
-				(struct core_conn_create_dest_spec_params *)opt;
-
-	cmd.destination_type = NCI_DESTINATION_NFCEE;
-	cmd.number_destination_params = 1;
-	memcpy(&cmd.params.type, params,
-	       sizeof(struct core_conn_create_dest_spec_params));
-	nci_send_cmd(ndev, NCI_OP_CORE_CONN_CREATE_CMD,
-		     sizeof(struct nci_core_conn_create_cmd), &cmd);
+	struct core_conn_create_data *data =
+					(struct core_conn_create_data *)opt;
+
+	nci_send_cmd(ndev, NCI_OP_CORE_CONN_CREATE_CMD, data->length, data->cmd);
 }
 
-int nci_core_conn_create(struct nci_dev *ndev,
+int nci_core_conn_create(struct nci_dev *ndev, u8 destination_type,
+			 u8 number_destination_params,
+			 size_t params_len,
 			 struct core_conn_create_dest_spec_params *params)
 {
-	ndev->cur_id = params->value.id;
-	return nci_request(ndev, nci_core_conn_create_req,
-			(unsigned long)params,
-			msecs_to_jiffies(NCI_CMD_TIMEOUT));
+	int r;
+	struct nci_core_conn_create_cmd *cmd;
+	struct core_conn_create_data data;
+
+	data.length = params_len + sizeof(struct nci_core_conn_create_cmd);
+	cmd = kzalloc(data.length, GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->destination_type = destination_type;
+	cmd->number_destination_params = number_destination_params;
+	memcpy(cmd->params, params, params_len);
+
+	data.cmd = cmd;
+	ndev->cur_id = params->value[DEST_SPEC_PARAMS_ID_INDEX];
+
+	r = __nci_request(ndev, nci_core_conn_create_req,
+			  (unsigned long)&data,
+			  msecs_to_jiffies(NCI_CMD_TIMEOUT));
+	kfree(cmd);
+	return r;
 }
 EXPORT_SYMBOL(nci_core_conn_create);
 
-- 
cgit v1.2.3-70-g09d2


From 3ba5c8466b320c3fd5d5861b34aa8a31dd0cf6b3 Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 3 Feb 2015 19:48:06 +0100
Subject: NFC: nci: Change credits field to credits_cnt

For consistency sake change nci_core_conn_create_rsp structure
credits field to credits_cnt.

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/net/nfc/nci.h | 2 +-
 net/nfc/nci/rsp.c     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index 695d33cb75e..a2f2f3d3196 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -353,7 +353,7 @@ struct nci_core_set_config_rsp {
 struct nci_core_conn_create_rsp {
 	__u8	status;
 	__u8	max_ctrl_pkt_payload_len;
-	__u8    credits;
+	__u8    credits_cnt;
 	__u8	conn_id;
 } __packed;
 
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index 05268eb473d..b419fed77ea 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -245,7 +245,7 @@ static void nci_core_conn_create_rsp_packet(struct nci_dev *ndev,
 
 		conn_info->conn_id = rsp->conn_id;
 		conn_info->max_pkt_payload_len = rsp->max_ctrl_pkt_payload_len;
-		atomic_set(&conn_info->credits_cnt, rsp->credits);
+		atomic_set(&conn_info->credits_cnt, rsp->credits_cnt);
 	}
 
 exit:
-- 
cgit v1.2.3-70-g09d2


From 15d4a8da0e440faf589a26346c8287e1ed0abe6c Mon Sep 17 00:00:00 2001
From: Christophe Ricard <christophe.ricard@gmail.com>
Date: Tue, 3 Feb 2015 19:48:07 +0100
Subject: NFC: nci: Move logical connection structure allocation

conn_info is currently allocated only after nfcee_discovery_ntf
which is not generic enough for logical connection other than
NFCEE. The corresponding conn_info is now created in
nci_core_conn_create_rsp().

Signed-off-by: Christophe Ricard <christophe-h.ricard@st.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/nfc/st21nfcb/st21nfcb_se.c |  2 +-
 include/net/nfc/nci_core.h         |  1 +
 net/nfc/nci/hci.c                  |  8 ++++++++
 net/nfc/nci/ntf.c                  | 23 ++---------------------
 net/nfc/nci/rsp.c                  | 29 ++++++++++++++++++++++++-----
 5 files changed, 36 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/nfc/st21nfcb/st21nfcb_se.c b/drivers/nfc/st21nfcb/st21nfcb_se.c
index 3b465e4c85e..d23e8f27c4a 100644
--- a/drivers/nfc/st21nfcb/st21nfcb_se.c
+++ b/drivers/nfc/st21nfcb/st21nfcb_se.c
@@ -513,7 +513,7 @@ static int st21nfcb_hci_network_init(struct nci_dev *ndev)
 
 	dest_params->type = NCI_DESTINATION_SPECIFIC_PARAM_NFCEE_TYPE;
 	dest_params->length = sizeof(struct dest_spec_params);
-	spec_params.id = ndev->hci_dev->conn_info->id;
+	spec_params.id = ndev->hci_dev->nfcee_id;
 	spec_params.protocol = NCI_NFCEE_INTERFACE_HCI_ACCESS;
 	memcpy(dest_params->value, &spec_params, sizeof(struct dest_spec_params));
 	r = nci_core_conn_create(ndev, NCI_DESTINATION_NFCEE, 1,
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index d34c1b2295d..ff87f8611fa 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -159,6 +159,7 @@ struct nci_hci_init_data {
 #define NCI_HCI_MAX_GATES          256
 
 struct nci_hci_dev {
+	u8 nfcee_id;
 	struct nci_dev *ndev;
 	struct nci_conn_info *conn_info;
 
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index ecf25394260..ed54ec53383 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -615,12 +615,20 @@ static int nci_hci_dev_connect_gates(struct nci_dev *ndev,
 
 int nci_hci_dev_session_init(struct nci_dev *ndev)
 {
+	struct nci_conn_info    *conn_info;
 	struct sk_buff *skb;
 	int r;
 
 	ndev->hci_dev->count_pipes = 0;
 	ndev->hci_dev->expected_pipes = 0;
 
+	conn_info = ndev->hci_dev->conn_info;
+	if (!conn_info)
+		return -EPROTO;
+
+	conn_info->data_exchange_cb = nci_hci_data_received_cb;
+	conn_info->data_exchange_cb_context = ndev;
+
 	nci_hci_reset_pipes(ndev->hci_dev);
 
 	if (ndev->hci_dev->init_data.gates[0].gate != NCI_HCI_ADMIN_GATE)
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 6bbbf6fdacc..3218071072a 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -723,7 +723,6 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev,
 					  struct sk_buff *skb)
 {
 	u8 status = NCI_STATUS_OK;
-	struct nci_conn_info    *conn_info;
 	struct nci_nfcee_discover_ntf   *nfcee_ntf =
 				(struct nci_nfcee_discover_ntf *)skb->data;
 
@@ -734,27 +733,9 @@ static void nci_nfcee_discover_ntf_packet(struct nci_dev *ndev,
 	 * and only one, NFCEE_DISCOVER_NTF with a Protocol type of
 	 * “HCI Access”, even if the HCI Network contains multiple NFCEEs.
 	 */
-	if (!ndev->hci_dev->conn_info) {
-		conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
-					 sizeof(*conn_info), GFP_KERNEL);
-		if (!conn_info) {
-			status = NCI_STATUS_REJECTED;
-			goto exit;
-		}
-
-		conn_info->id = nfcee_ntf->nfcee_id;
-		conn_info->conn_id = NCI_INVALID_CONN_ID;
-
-		conn_info->data_exchange_cb = nci_hci_data_received_cb;
-		conn_info->data_exchange_cb_context = ndev;
+	ndev->hci_dev->nfcee_id = nfcee_ntf->nfcee_id;
+	ndev->cur_id = nfcee_ntf->nfcee_id;
 
-		INIT_LIST_HEAD(&conn_info->list);
-		list_add(&conn_info->list, &ndev->conn_info_list);
-
-		ndev->hci_dev->conn_info = conn_info;
-	}
-
-exit:
 	nci_req_complete(ndev, status);
 }
 
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index b419fed77ea..02486bc2cee 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -233,16 +233,27 @@ static void nci_core_conn_create_rsp_packet(struct nci_dev *ndev,
 
 	if (status == NCI_STATUS_OK) {
 		rsp = (struct nci_core_conn_create_rsp *)skb->data;
-		list_for_each_entry(conn_info, &ndev->conn_info_list, list) {
-			if (conn_info->id == ndev->cur_id)
-				break;
-		}
 
-		if (!conn_info || conn_info->id != ndev->cur_id) {
+		conn_info = devm_kzalloc(&ndev->nfc_dev->dev,
+					 sizeof(*conn_info), GFP_KERNEL);
+		if (!conn_info) {
 			status = NCI_STATUS_REJECTED;
 			goto exit;
 		}
 
+		conn_info->id = ndev->cur_id;
+		conn_info->conn_id = rsp->conn_id;
+
+		/* Note: data_exchange_cb and data_exchange_cb_context need to
+		 * be specify out of nci_core_conn_create_rsp_packet
+		 */
+
+		INIT_LIST_HEAD(&conn_info->list);
+		list_add(&conn_info->list, &ndev->conn_info_list);
+
+		if (ndev->cur_id == ndev->hci_dev->nfcee_id)
+			ndev->hci_dev->conn_info = conn_info;
+
 		conn_info->conn_id = rsp->conn_id;
 		conn_info->max_pkt_payload_len = rsp->max_ctrl_pkt_payload_len;
 		atomic_set(&conn_info->credits_cnt, rsp->credits_cnt);
@@ -255,9 +266,17 @@ exit:
 static void nci_core_conn_close_rsp_packet(struct nci_dev *ndev,
 					   struct sk_buff *skb)
 {
+	struct nci_conn_info *conn_info;
 	__u8 status = skb->data[0];
 
 	pr_debug("status 0x%x\n", status);
+	if (status == NCI_STATUS_OK) {
+		conn_info = nci_get_conn_info_by_conn_id(ndev, ndev->cur_id);
+		if (conn_info) {
+			list_del(&conn_info->list);
+			devm_kfree(&ndev->nfc_dev->dev, conn_info);
+		}
+	}
 	nci_req_complete(ndev, status);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 12cf89b550d13eb7cb86ef182bd6c04345a33a1f Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 3 Feb 2015 16:45:18 -0600
Subject: livepatch: rename config to CONFIG_LIVEPATCH

Rename CONFIG_LIVE_PATCHING to CONFIG_LIVEPATCH to make the naming of
the config and the code more consistent.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Reviewed-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 arch/x86/Kconfig                 | 2 +-
 arch/x86/include/asm/livepatch.h | 4 ++--
 arch/x86/kernel/Makefile         | 2 +-
 include/linux/livepatch.h        | 4 ++--
 kernel/livepatch/Kconfig         | 6 +++---
 kernel/livepatch/Makefile        | 2 +-
 samples/Kconfig                  | 4 ++--
 samples/livepatch/Makefile       | 2 +-
 8 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 29b09523127..11970b07686 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -17,7 +17,7 @@ config X86_64
 	depends on 64BIT
 	select X86_DEV_DMA_OPS
 	select ARCH_USE_CMPXCHG_LOCKREF
-	select HAVE_LIVE_PATCHING
+	select HAVE_LIVEPATCH
 
 ### Arch settings
 config X86
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 26e58134c8c..a455a53d789 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -24,7 +24,7 @@
 #include <linux/module.h>
 #include <linux/ftrace.h>
 
-#ifdef CONFIG_LIVE_PATCHING
+#ifdef CONFIG_LIVEPATCH
 static inline int klp_check_compiler_support(void)
 {
 #ifndef CC_USING_FENTRY
@@ -40,7 +40,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 #else
-#error Live patching support is disabled; check CONFIG_LIVE_PATCHING
+#error Live patching support is disabled; check CONFIG_LIVEPATCH
 #endif
 
 #endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 316b34e74c1..73222349696 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -63,7 +63,7 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_LIVE_PATCHING)	+= livepatch.o
+obj-$(CONFIG_LIVEPATCH)		+= livepatch.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index f14c6fb262b..95023fd8b00 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -24,7 +24,7 @@
 #include <linux/module.h>
 #include <linux/ftrace.h>
 
-#if IS_ENABLED(CONFIG_LIVE_PATCHING)
+#if IS_ENABLED(CONFIG_LIVEPATCH)
 
 #include <asm/livepatch.h>
 
@@ -128,6 +128,6 @@ extern int klp_unregister_patch(struct klp_patch *);
 extern int klp_enable_patch(struct klp_patch *);
 extern int klp_disable_patch(struct klp_patch *);
 
-#endif /* CONFIG_LIVE_PATCHING */
+#endif /* CONFIG_LIVEPATCH */
 
 #endif /* _LINUX_LIVEPATCH_H_ */
diff --git a/kernel/livepatch/Kconfig b/kernel/livepatch/Kconfig
index 347ee222113..04502255793 100644
--- a/kernel/livepatch/Kconfig
+++ b/kernel/livepatch/Kconfig
@@ -1,15 +1,15 @@
-config HAVE_LIVE_PATCHING
+config HAVE_LIVEPATCH
 	bool
 	help
 	  Arch supports kernel live patching
 
-config LIVE_PATCHING
+config LIVEPATCH
 	bool "Kernel Live Patching"
 	depends on DYNAMIC_FTRACE_WITH_REGS
 	depends on MODULES
 	depends on SYSFS
 	depends on KALLSYMS_ALL
-	depends on HAVE_LIVE_PATCHING
+	depends on HAVE_LIVEPATCH
 	help
 	  Say Y here if you want to support kernel live patching.
 	  This option has no runtime impact until a kernel "patch"
diff --git a/kernel/livepatch/Makefile b/kernel/livepatch/Makefile
index 7c1f0086142..e8780c0901d 100644
--- a/kernel/livepatch/Makefile
+++ b/kernel/livepatch/Makefile
@@ -1,3 +1,3 @@
-obj-$(CONFIG_LIVE_PATCHING) += livepatch.o
+obj-$(CONFIG_LIVEPATCH) += livepatch.o
 
 livepatch-objs := core.o
diff --git a/samples/Kconfig b/samples/Kconfig
index 0aed20df5f0..224ebb46bed 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -63,9 +63,9 @@ config SAMPLE_RPMSG_CLIENT
 	  to communicate with an AMP-configured remote processor over
 	  the rpmsg bus.
 
-config SAMPLE_LIVE_PATCHING
+config SAMPLE_LIVEPATCH
 	tristate "Build live patching sample -- loadable modules only"
-	depends on LIVE_PATCHING && m
+	depends on LIVEPATCH && m
 	help
 	  Builds a sample live patch that replaces the procfs handler
 	  for /proc/cmdline to print "this has been live patched".
diff --git a/samples/livepatch/Makefile b/samples/livepatch/Makefile
index 7f1cdc131a0..10319d7ea0b 100644
--- a/samples/livepatch/Makefile
+++ b/samples/livepatch/Makefile
@@ -1 +1 @@
-obj-$(CONFIG_SAMPLE_LIVE_PATCHING) += livepatch-sample.o
+obj-$(CONFIG_SAMPLE_LIVEPATCH) += livepatch-sample.o
-- 
cgit v1.2.3-70-g09d2


From 472da57b1c6f26aa508e4b4dfaf4f8c562bfdbfb Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Thu, 11 Dec 2014 16:23:31 +0200
Subject: OMAPDSS: add define for DRA7xx HW version

Add define for DRA7xx DSS version.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/video/omapdss.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index 6a84498ea51..60de61fea8e 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -314,6 +314,7 @@ enum omapdss_version {
 	OMAPDSS_VER_OMAP4,		/* All other OMAP4s */
 	OMAPDSS_VER_OMAP5,
 	OMAPDSS_VER_AM43xx,
+	OMAPDSS_VER_DRA7xx,
 };
 
 /* Board specific data */
-- 
cgit v1.2.3-70-g09d2


From 509102760da3a21831e763560ba4715760e3fbda Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Wed, 4 Feb 2015 11:45:28 +0100
Subject: regulator: Fix build breakage on !REGULATOR

Add missing stubs for regulator_suspend_prepare() and
regulator_suspend_finish() to fix exynos_defconfig build without
REGULATOR:

arch/arm/mach-exynos/built-in.o: In function `exynos_suspend_finish':
arch/arm/mach-exynos/suspend.c:537: undefined reference to `regulator_suspend_finish'
arch/arm/mach-exynos/built-in.o: In function `exynos_suspend_prepare':
arch/arm/mach-exynos/suspend.c:520: undefined reference to `regulator_suspend_prepare'
make: *** [vmlinux] Error 1

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reported-by: Joerg Roedel <joro@8bytes.org>
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regulator/machine.h | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 0b08d05d470..b07562e082c 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -191,15 +191,22 @@ struct regulator_init_data {
 	void *driver_data;	/* core does not touch this */
 };
 
-int regulator_suspend_prepare(suspend_state_t state);
-int regulator_suspend_finish(void);
-
 #ifdef CONFIG_REGULATOR
 void regulator_has_full_constraints(void);
+int regulator_suspend_prepare(suspend_state_t state);
+int regulator_suspend_finish(void);
 #else
 static inline void regulator_has_full_constraints(void)
 {
 }
+static inline int regulator_suspend_prepare(suspend_state_t state)
+{
+	return 0;
+}
+static inline int regulator_suspend_finish(void)
+{
+	return 0;
+}
 #endif
 
 #endif
-- 
cgit v1.2.3-70-g09d2


From 9c4a6b1e42801343535ccab4c190019d9975cce8 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 4 Feb 2015 08:11:34 +0100
Subject: scsi_logging: return void for dev_printk() functions

dev_printk() is now a void function, so the related functions
scmd_printk() and sdev_prefix_printk() should be made void, too.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 drivers/scsi/scsi_logging.c | 22 +++++++++-------------
 include/scsi/scsi_device.h  |  4 ++--
 2 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c
index ecc5918e372..bd70339c124 100644
--- a/drivers/scsi/scsi_logging.c
+++ b/drivers/scsi/scsi_logging.c
@@ -93,20 +93,19 @@ static size_t sdev_format_header(char *logbuf, size_t logbuf_len,
 	return off;
 }
 
-int sdev_prefix_printk(const char *level, const struct scsi_device *sdev,
-		       const char *name, const char *fmt, ...)
+void sdev_prefix_printk(const char *level, const struct scsi_device *sdev,
+			const char *name, const char *fmt, ...)
 {
 	va_list args;
 	char *logbuf;
 	size_t off = 0, logbuf_len;
-	int ret;
 
 	if (!sdev)
-		return 0;
+		return;
 
 	logbuf = scsi_log_reserve_buffer(&logbuf_len);
 	if (!logbuf)
-		return 0;
+		return;
 
 	if (name)
 		off += scnprintf(logbuf + off, logbuf_len - off,
@@ -116,26 +115,24 @@ int sdev_prefix_printk(const char *level, const struct scsi_device *sdev,
 		off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
 		va_end(args);
 	}
-	ret = dev_printk(level, &sdev->sdev_gendev, "%s", logbuf);
+	dev_printk(level, &sdev->sdev_gendev, "%s", logbuf);
 	scsi_log_release_buffer(logbuf);
-	return ret;
 }
 EXPORT_SYMBOL(sdev_prefix_printk);
 
-int scmd_printk(const char *level, const struct scsi_cmnd *scmd,
+void scmd_printk(const char *level, const struct scsi_cmnd *scmd,
 		const char *fmt, ...)
 {
 	va_list args;
 	char *logbuf;
 	size_t off = 0, logbuf_len;
-	int ret;
 
 	if (!scmd || !scmd->cmnd)
-		return 0;
+		return;
 
 	logbuf = scsi_log_reserve_buffer(&logbuf_len);
 	if (!logbuf)
-		return 0;
+		return;
 	off = sdev_format_header(logbuf, logbuf_len, scmd_name(scmd),
 				 scmd->request->tag);
 	if (off < logbuf_len) {
@@ -143,9 +140,8 @@ int scmd_printk(const char *level, const struct scsi_cmnd *scmd,
 		off += vscnprintf(logbuf + off, logbuf_len - off, fmt, args);
 		va_end(args);
 	}
-	ret = dev_printk(level, &scmd->device->sdev_gendev, "%s", logbuf);
+	dev_printk(level, &scmd->device->sdev_gendev, "%s", logbuf);
 	scsi_log_release_buffer(logbuf);
-	return ret;
 }
 EXPORT_SYMBOL(scmd_printk);
 
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 2e0281ee719..a4c9336811d 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -237,14 +237,14 @@ struct scsi_dh_data {
  * like scmd_printk, but the device name is passed in
  * as a string pointer
  */
-__printf(4, 5) int
+__printf(4, 5) void
 sdev_prefix_printk(const char *, const struct scsi_device *, const char *,
 		const char *, ...);
 
 #define sdev_printk(l, sdev, fmt, a...)				\
 	sdev_prefix_printk(l, sdev, NULL, fmt, ##a)
 
-__printf(3, 4) int
+__printf(3, 4) void
 scmd_printk(const char *, const struct scsi_cmnd *, const char *, ...);
 
 #define scmd_dbg(scmd, fmt, a...)					   \
-- 
cgit v1.2.3-70-g09d2


From 9064bf3c3cdf92f6b9ac6634ff570dedf0035992 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 3 Feb 2015 17:03:35 -0600
Subject: spi: spi-pxa2xx: only include mach/dma.h for legacy DMA

Move the include of mach/dma.h to the legacy PXA DMA code where it is used.
This enables building spi-pxa2xx on ARM64.

Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-pxa2xx-pxadma.c | 1 +
 include/linux/spi/pxa2xx_spi.h  | 1 -
 2 files changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/spi/spi-pxa2xx-pxadma.c b/drivers/spi/spi-pxa2xx-pxadma.c
index 6c82d496b58..3fecaaa5b0a 100644
--- a/drivers/spi/spi-pxa2xx-pxadma.c
+++ b/drivers/spi/spi-pxa2xx-pxadma.c
@@ -25,6 +25,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/pxa2xx_spi.h>
 
+#include <mach/dma.h>
 #include "spi-pxa2xx.h"
 
 #define DMA_INT_MASK		(DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h
index d5a31655017..46d8fa94263 100644
--- a/include/linux/spi/pxa2xx_spi.h
+++ b/include/linux/spi/pxa2xx_spi.h
@@ -57,7 +57,6 @@ struct pxa2xx_spi_chip {
 #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP)
 
 #include <linux/clk.h>
-#include <mach/dma.h>
 
 extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info);
 
-- 
cgit v1.2.3-70-g09d2


From 2bd82484bb4c5db1d5dc983ac7c409b2782e0154 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 3 Feb 2015 23:48:24 -0800
Subject: xps: fix xps for stacked devices

A typical qdisc setup is the following :

bond0 : bonding device, using HTB hierarchy
eth1/eth2 : slaves, multiqueue NIC, using MQ + FQ qdisc

XPS allows to spread packets on specific tx queues, based on the cpu
doing the send.

Problem is that dequeues from bond0 qdisc can happen on random cpus,
due to the fact that qdisc_run() can dequeue a batch of packets.

CPUA -> queue packet P1 on bond0 qdisc, P1->ooo_okay=1
CPUA -> queue packet P2 on bond0 qdisc, P2->ooo_okay=0

CPUB -> dequeue packet P1 from bond0
        enqueue packet on eth1/eth2
CPUC -> dequeue packet P2 from bond0
        enqueue packet on eth1/eth2 using sk cache (ooo_okay is 0)

get_xps_queue() then might select wrong queue for P1, since current cpu
might be different than CPUA.

P2 might be sent on the old queue (stored in sk->sk_tx_queue_mapping),
if CPUC runs a bit faster (or CPUB spins a bit on qdisc lock)

Effect of this bug is TCP reorders, and more generally not optimal
TX queue placement. (A victim bulk flow can be migrated to the wrong TX
queue for a while)

To fix this, we have to record sender cpu number the first time
dev_queue_xmit() is called for one tx skb.

We can union napi_id (used on receive path) and sender_cpu,
granted we clear sender_cpu in skb_scrub_packet() (credit to Willem for
this union idea)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Nandita Dukkipati <nanditad@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    | 7 +++++--
 net/core/flow_dissector.c | 7 ++++++-
 net/core/skbuff.c         | 4 ++++
 3 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 85ab7d72b54..2748ff63914 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -626,8 +626,11 @@ struct sk_buff {
 	__u32			hash;
 	__be16			vlan_proto;
 	__u16			vlan_tci;
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	unsigned int	napi_id;
+#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS)
+	union {
+		unsigned int	napi_id;
+		unsigned int	sender_cpu;
+	};
 #endif
 #ifdef CONFIG_NETWORK_SECMARK
 	__u32			secmark;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index beb83d1ac1c..2c35c02a931 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -422,7 +422,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 	dev_maps = rcu_dereference(dev->xps_maps);
 	if (dev_maps) {
 		map = rcu_dereference(
-		    dev_maps->cpu_map[raw_smp_processor_id()]);
+		    dev_maps->cpu_map[skb->sender_cpu - 1]);
 		if (map) {
 			if (map->len == 1)
 				queue_index = map->queues[0];
@@ -468,6 +468,11 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 {
 	int queue_index = 0;
 
+#ifdef CONFIG_XPS
+	if (skb->sender_cpu == 0)
+		skb->sender_cpu = raw_smp_processor_id() + 1;
+#endif
+
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a5bff2767f1..88c613eab14 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -825,6 +825,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	CHECK_SKB_FIELD(napi_id);
 #endif
+#ifdef CONFIG_XPS
+	CHECK_SKB_FIELD(sender_cpu);
+#endif
 #ifdef CONFIG_NET_SCHED
 	CHECK_SKB_FIELD(tc_index);
 #ifdef CONFIG_NET_CLS_ACT
@@ -4169,6 +4172,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
 	skb->mark = 0;
+	skb->sender_cpu = 0;
 	skb_init_secmark(skb);
 	secpath_reset(skb);
 	nf_reset(skb);
-- 
cgit v1.2.3-70-g09d2


From dcdc8994697faa789669c3fdaca1a8bc27a8f356 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 2 Feb 2015 16:07:34 -0800
Subject: net: add skb functions to process remote checksum offload

This patch adds skb_remcsum_process and skb_gro_remcsum_process to
perform the appropriate adjustments to the skb when receiving
remote checksum offload.

Updated vxlan and gue to use these functions.

Tested: Ran TCP_RR and TCP_STREAM netperf for VXLAN and GUE, did
not see any change in performance.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c       | 18 ++----------------
 include/linux/netdevice.h | 15 +++++++++++++++
 include/linux/skbuff.h    | 21 +++++++++++++++++++++
 net/ipv4/fou.c            | 18 ++----------------
 4 files changed, 40 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 31bac2a21ce..c184717e8b2 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -558,7 +558,6 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 					  u32 data)
 {
 	size_t start, offset, plen;
-	__wsum delta;
 
 	if (skb->remcsum_offload)
 		return vh;
@@ -580,12 +579,7 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 			return NULL;
 	}
 
-	delta = remcsum_adjust((void *)vh + hdrlen,
-			       NAPI_GRO_CB(skb)->csum, start, offset);
-
-	/* Adjust skb->csum since we changed the packet */
-	skb->csum = csum_add(skb->csum, delta);
-	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+	skb_gro_remcsum_process(skb, (void *)vh + hdrlen, start, offset);
 
 	skb->remcsum_offload = 1;
 
@@ -1159,7 +1153,6 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
 				      size_t hdrlen, u32 data)
 {
 	size_t start, offset, plen;
-	__wsum delta;
 
 	if (skb->remcsum_offload) {
 		/* Already processed in GRO path */
@@ -1179,14 +1172,7 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
 
 	vh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
 
-	if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
-		__skb_checksum_complete(skb);
-
-	delta = remcsum_adjust((void *)vh + hdrlen,
-			       skb->csum, start, offset);
-
-	/* Adjust skb->csum since we changed the packet */
-	skb->csum = csum_add(skb->csum, delta);
+	skb_remcsum_process(skb, (void *)vh + hdrlen, start, offset);
 
 	return vh;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 16251e96e6a..1347ac50d2a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2318,6 +2318,21 @@ do {									\
 					   compute_pseudo(skb, proto));	\
 } while (0)
 
+static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
+					   int start, int offset)
+{
+	__wsum delta;
+
+	BUG_ON(!NAPI_GRO_CB(skb)->csum_valid);
+
+	delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset);
+
+	/* Adjust skb->csum since we changed the packet */
+	skb->csum = csum_add(skb->csum, delta);
+	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+}
+
+
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 				  unsigned short type,
 				  const void *daddr, const void *saddr,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2748ff63914..5405dfe0257 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3099,6 +3099,27 @@ do {									\
 				       compute_pseudo(skb, proto));	\
 } while (0)
 
+/* Update skbuf and packet to reflect the remote checksum offload operation.
+ * When called, ptr indicates the starting point for skb->csum when
+ * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete
+ * here, skb_postpull_rcsum is done so skb->csum start is ptr.
+ */
+static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr,
+				       int start, int offset)
+{
+	__wsum delta;
+
+	 if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) {
+		__skb_checksum_complete(skb);
+		skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data);
+	}
+
+	delta = remcsum_adjust(ptr, skb->csum, start, offset);
+
+	/* Adjust skb->csum since we changed the packet */
+	skb->csum = csum_add(skb->csum, delta);
+}
+
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 void nf_conntrack_destroy(struct nf_conntrack *nfct);
 static inline void nf_conntrack_put(struct nf_conntrack *nfct)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 3bc0cf07661..92ddea1e645 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -70,7 +70,6 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
 	size_t start = ntohs(pd[0]);
 	size_t offset = ntohs(pd[1]);
 	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
-	__wsum delta;
 
 	if (skb->remcsum_offload) {
 		/* Already processed in GRO path */
@@ -82,14 +81,7 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
 		return NULL;
 	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
 
-	if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
-		__skb_checksum_complete(skb);
-
-	delta = remcsum_adjust((void *)guehdr + hdrlen,
-			       skb->csum, start, offset);
-
-	/* Adjust skb->csum since we changed the packet */
-	skb->csum = csum_add(skb->csum, delta);
+	skb_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset);
 
 	return guehdr;
 }
@@ -228,7 +220,6 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 	size_t start = ntohs(pd[0]);
 	size_t offset = ntohs(pd[1]);
 	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
-	__wsum delta;
 
 	if (skb->remcsum_offload)
 		return guehdr;
@@ -243,12 +234,7 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 			return NULL;
 	}
 
-	delta = remcsum_adjust((void *)guehdr + hdrlen,
-			       NAPI_GRO_CB(skb)->csum, start, offset);
-
-	/* Adjust skb->csum since we changed the packet */
-	skb->csum = csum_add(skb->csum, delta);
-	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+	skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset);
 
 	skb->remcsum_offload = 1;
 
-- 
cgit v1.2.3-70-g09d2


From 61bd3857ff2c7daf756d49b41e6277bbdaa8f789 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Tue, 3 Feb 2015 16:48:29 +0200
Subject: net/core: Add event for a change in slave state

Add event which provides an indication on a change in the state
of a bonding slave. The event handler should cast the pointer to the
appropriate type (struct netdev_bonding_info) in order to get the
full info about the slave.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 15 +++++++++++++++
 net/core/dev.c            | 20 ++++++++++++++++++++
 net/core/rtnetlink.c      |  1 +
 3 files changed, 36 insertions(+)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1347ac50d2a..ce784d5018e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -51,6 +51,7 @@
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
 #include <uapi/linux/netdevice.h>
+#include <uapi/linux/if_bonding.h>
 
 struct netpoll_info;
 struct device;
@@ -2056,6 +2057,7 @@ struct pcpu_sw_netstats {
 #define NETDEV_RESEND_IGMP	0x0016
 #define NETDEV_PRECHANGEMTU	0x0017 /* notify before mtu change happened */
 #define NETDEV_CHANGEINFODATA	0x0018
+#define NETDEV_BONDING_INFO	0x0019
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -3494,6 +3496,19 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
 				    netdev_features_t features);
 
+struct netdev_bonding_info {
+	ifslave	slave;
+	ifbond	master;
+};
+
+struct netdev_notifier_bonding_info {
+	struct netdev_notifier_info info; /* must be first */
+	struct netdev_bonding_info  bonding_info;
+};
+
+void netdev_bonding_info_change(struct net_device *dev,
+				struct netdev_bonding_info *bonding_info);
+
 static inline
 struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 1d564d68e31..ede0b161b11 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5355,6 +5355,26 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
+/**
+ * netdev_bonding_info_change - Dispatch event about slave change
+ * @dev: device
+ * @netdev_bonding_info: info to dispatch
+ *
+ * Send NETDEV_BONDING_INFO to netdev notifiers with info.
+ * The caller must hold the RTNL lock.
+ */
+void netdev_bonding_info_change(struct net_device *dev,
+				struct netdev_bonding_info *bonding_info)
+{
+	struct netdev_notifier_bonding_info	info;
+
+	memcpy(&info.bonding_info, bonding_info,
+	       sizeof(struct netdev_bonding_info));
+	call_netdevice_notifiers_info(NETDEV_BONDING_INFO, dev,
+				      &info.info);
+}
+EXPORT_SYMBOL(netdev_bonding_info_change);
+
 void netdev_adjacent_add_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 673cb4c6f39..4cd5e350d12 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3180,6 +3180,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
 	case NETDEV_UNREGISTER_FINAL:
 	case NETDEV_RELEASE:
 	case NETDEV_JOIN:
+	case NETDEV_BONDING_INFO:
 		break;
 	default:
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
-- 
cgit v1.2.3-70-g09d2


From 69a2338e05995b10225b2a131f7540d1305980e4 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Tue, 3 Feb 2015 16:48:30 +0200
Subject: net/bonding: Move slave state changes to a helper function

Move slave state changes to a helper function, this is a pre-step for adding
functionality of dispatching an event when this helper is called.

This commit doesn't add new functionality.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 64 ++++++++++++++++++++++++-----------------
 include/net/bonding.h           |  5 ++++
 2 files changed, 43 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index c9e519cb921..92fe3a1bf52 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -790,7 +790,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 			}
 
 			new_active->delay = 0;
-			new_active->link = BOND_LINK_UP;
+			bond_set_slave_link_state(new_active, BOND_LINK_UP);
 
 			if (BOND_MODE(bond) == BOND_MODE_8023AD)
 				bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
@@ -1181,6 +1181,21 @@ static void bond_free_slave(struct slave *slave)
 	kfree(slave);
 }
 
+static void bond_fill_ifbond(struct bonding *bond, struct ifbond *info)
+{
+	info->bond_mode = BOND_MODE(bond);
+	info->miimon = bond->params.miimon;
+	info->num_slaves = bond->slave_cnt;
+}
+
+static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
+{
+	strcpy(info->slave_name, slave->dev->name);
+	info->link = slave->link;
+	info->state = bond_slave_state(slave);
+	info->link_failure_count = slave->link_failure_count;
+}
+
 /* enslave device <slave> to bond device <master> */
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 {
@@ -1444,19 +1459,22 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	if (bond->params.miimon) {
 		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
 			if (bond->params.updelay) {
-				new_slave->link = BOND_LINK_BACK;
+				bond_set_slave_link_state(new_slave,
+							  BOND_LINK_BACK);
 				new_slave->delay = bond->params.updelay;
 			} else {
-				new_slave->link = BOND_LINK_UP;
+				bond_set_slave_link_state(new_slave,
+							  BOND_LINK_UP);
 			}
 		} else {
-			new_slave->link = BOND_LINK_DOWN;
+			bond_set_slave_link_state(new_slave, BOND_LINK_DOWN);
 		}
 	} else if (bond->params.arp_interval) {
-		new_slave->link = (netif_carrier_ok(slave_dev) ?
-			BOND_LINK_UP : BOND_LINK_DOWN);
+		bond_set_slave_link_state(new_slave,
+					  (netif_carrier_ok(slave_dev) ?
+					  BOND_LINK_UP : BOND_LINK_DOWN));
 	} else {
-		new_slave->link = BOND_LINK_UP;
+		bond_set_slave_link_state(new_slave, BOND_LINK_UP);
 	}
 
 	if (new_slave->link != BOND_LINK_DOWN)
@@ -1821,11 +1839,7 @@ static int  bond_release_and_destroy(struct net_device *bond_dev,
 static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-
-	info->bond_mode = BOND_MODE(bond);
-	info->miimon = bond->params.miimon;
-	info->num_slaves = bond->slave_cnt;
-
+	bond_fill_ifbond(bond, info);
 	return 0;
 }
 
@@ -1839,10 +1853,7 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in
 	bond_for_each_slave(bond, slave, iter) {
 		if (i++ == (int)info->slave_id) {
 			res = 0;
-			strcpy(info->slave_name, slave->dev->name);
-			info->link = slave->link;
-			info->state = bond_slave_state(slave);
-			info->link_failure_count = slave->link_failure_count;
+			bond_fill_ifslave(slave, info);
 			break;
 		}
 	}
@@ -1872,7 +1883,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (link_state)
 				continue;
 
-			slave->link = BOND_LINK_FAIL;
+			bond_set_slave_link_state(slave, BOND_LINK_FAIL);
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -1887,7 +1898,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_FAIL:
 			if (link_state) {
 				/* recovered before downdelay expired */
-				slave->link = BOND_LINK_UP;
+				bond_set_slave_link_state(slave, BOND_LINK_UP);
 				slave->last_link_up = jiffies;
 				netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
 					    (bond->params.downdelay - slave->delay) *
@@ -1909,7 +1920,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (!link_state)
 				continue;
 
-			slave->link = BOND_LINK_BACK;
+			bond_set_slave_link_state(slave, BOND_LINK_BACK);
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
@@ -1922,7 +1933,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 			/*FALLTHRU*/
 		case BOND_LINK_BACK:
 			if (!link_state) {
-				slave->link = BOND_LINK_DOWN;
+				bond_set_slave_link_state(slave,
+							  BOND_LINK_DOWN);
 				netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
 					    (bond->params.updelay - slave->delay) *
 					    bond->params.miimon,
@@ -1960,7 +1972,7 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
-			slave->link = BOND_LINK_UP;
+			bond_set_slave_link_state(slave, BOND_LINK_UP);
 			slave->last_link_up = jiffies;
 
 			primary = rtnl_dereference(bond->primary_slave);
@@ -2000,7 +2012,7 @@ static void bond_miimon_commit(struct bonding *bond)
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			slave->link = BOND_LINK_DOWN;
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
 
 			if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
 			    BOND_MODE(bond) == BOND_MODE_8023AD)
@@ -2583,7 +2595,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 				struct slave *current_arp_slave;
 
 				current_arp_slave = rtnl_dereference(bond->current_arp_slave);
-				slave->link = BOND_LINK_UP;
+				bond_set_slave_link_state(slave, BOND_LINK_UP);
 				if (current_arp_slave) {
 					bond_set_slave_inactive_flags(
 						current_arp_slave,
@@ -2606,7 +2618,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			slave->link = BOND_LINK_DOWN;
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
 			bond_set_slave_inactive_flags(slave,
 						      BOND_SLAVE_NOTIFY_NOW);
 
@@ -2685,7 +2697,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 		 * up when it is actually down
 		 */
 		if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
-			slave->link = BOND_LINK_DOWN;
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
@@ -2705,7 +2717,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 	if (!new_slave)
 		goto check_state;
 
-	new_slave->link = BOND_LINK_BACK;
+	bond_set_slave_link_state(new_slave, BOND_LINK_BACK);
 	bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
 	bond_arp_send_all(bond, new_slave);
 	new_slave->last_link_up = jiffies;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 29f53eacac0..d1367ec7493 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -490,6 +490,11 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
 	return slave->inactive;
 }
 
+static inline void bond_set_slave_link_state(struct slave *slave, int state)
+{
+	slave->link = state;
+}
+
 static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)
 {
 	struct in_device *in_dev;
-- 
cgit v1.2.3-70-g09d2


From 69e6113343cfe983511904ffca0d7a1466460b67 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Tue, 3 Feb 2015 16:48:31 +0200
Subject: net/bonding: Notify state change on slaves

Use notifier chain to dispatch an event upon a change in slave state.
Event is dispatched with slave specific info.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 42 +++++++++++++++++++++++++++++++++++++++++
 include/net/bonding.h           | 12 ++++++++++++
 2 files changed, 54 insertions(+)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 92fe3a1bf52..679ef00d6b1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1196,6 +1196,47 @@ static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
 	info->link_failure_count = slave->link_failure_count;
 }
 
+static void bond_netdev_notify(struct slave *slave, struct net_device *dev)
+{
+	struct bonding *bond = slave->bond;
+	struct netdev_bonding_info bonding_info;
+
+	rtnl_lock();
+	/* make sure that slave is still valid */
+	if (dev->priv_flags & IFF_BONDING) {
+		bond_fill_ifslave(slave, &bonding_info.slave);
+		bond_fill_ifbond(bond, &bonding_info.master);
+		netdev_bonding_info_change(slave->dev, &bonding_info);
+	}
+	rtnl_unlock();
+}
+
+static void bond_netdev_notify_work(struct work_struct *_work)
+{
+	struct netdev_notify_work *w =
+		container_of(_work, struct netdev_notify_work, work.work);
+
+	bond_netdev_notify(w->slave, w->dev);
+	dev_put(w->dev);
+}
+
+void bond_queue_slave_event(struct slave *slave)
+{
+	struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC);
+
+	if (!nnw)
+		return;
+
+	INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work);
+	nnw->slave = slave;
+	nnw->dev = slave->dev;
+
+	if (queue_delayed_work(slave->bond->wq, &nnw->work, 0))
+		dev_hold(slave->dev);
+	else
+		kfree(nnw);
+}
+
 /* enslave device <slave> to bond device <master> */
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 {
@@ -1590,6 +1631,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		    new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");
 
 	/* enslave is successful */
+	bond_queue_slave_event(new_slave);
 	return 0;
 
 /* Undo stages on error */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index d1367ec7493..4e17095ad46 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -150,6 +150,12 @@ struct bond_parm_tbl {
 	int mode;
 };
 
+struct netdev_notify_work {
+	struct delayed_work	work;
+	struct slave		*slave;
+	struct net_device	*dev;
+};
+
 struct slave {
 	struct net_device *dev; /* first - useful for panic debug */
 	struct bonding *bond; /* our master */
@@ -243,6 +249,8 @@ struct bonding {
 #define bond_slave_get_rtnl(dev) \
 	((struct slave *) rtnl_dereference(dev->rx_handler_data))
 
+void bond_queue_slave_event(struct slave *slave);
+
 struct bond_vlan_tag {
 	__be16		vlan_proto;
 	unsigned short	vlan_id;
@@ -315,6 +323,7 @@ static inline void bond_set_active_slave(struct slave *slave)
 {
 	if (slave->backup) {
 		slave->backup = 0;
+		bond_queue_slave_event(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
@@ -323,6 +332,7 @@ static inline void bond_set_backup_slave(struct slave *slave)
 {
 	if (!slave->backup) {
 		slave->backup = 1;
+		bond_queue_slave_event(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
@@ -336,6 +346,7 @@ static inline void bond_set_slave_state(struct slave *slave,
 	slave->backup = slave_state;
 	if (notify) {
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
+		bond_queue_slave_event(slave);
 		slave->should_notify = 0;
 	} else {
 		if (slave->should_notify)
@@ -493,6 +504,7 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
 static inline void bond_set_slave_link_state(struct slave *slave, int state)
 {
 	slave->link = state;
+	bond_queue_slave_event(slave);
 }
 
 static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)
-- 
cgit v1.2.3-70-g09d2


From 59e14e325066be49b49b6c2503337c69a9ee29fc Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Tue, 3 Feb 2015 16:48:32 +0200
Subject: net/mlx4_core: Port aggregation low level interface

Implement the hardware interface required for port aggregation.

1. Disable RX port check on receive - don't perform a validity check
that matches to QP's port and the port where the packet is received.

2. Virtual to physical port remap - configure virtual to physical port
mapping. Port remap capability for virtual functions.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c |  9 +++++
 drivers/net/ethernet/mellanox/mlx4/fw.c  | 56 +++++++++++++++++++++++++++++---
 include/linux/mlx4/cmd.h                 |  7 ++++
 include/linux/mlx4/device.h              | 10 +++++-
 include/linux/mlx4/qp.h                  |  1 +
 5 files changed, 77 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 154effbfd8b..a681d7c0bb9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1583,6 +1583,15 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.verify = NULL,
 		.wrapper = mlx4_CMD_EPERM_wrapper
 	},
+	{
+		.opcode = MLX4_CMD_VIRT_PORT_MAP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_CMD_EPERM_wrapper
+	},
 };
 
 static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index dbabfae3a3d..4b08a393ebc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -142,7 +142,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[17] = "Asymmetric EQs support",
 		[18] = "More than 80 VFs support",
 		[19] = "Performance optimized for limited rule configuration flow steering support",
-		[20] = "Recoverable error events support"
+		[20] = "Recoverable error events support",
+		[21] = "Port Remap support"
 	};
 	int i;
 
@@ -863,6 +864,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_EQE_STRIDE;
 	MLX4_GET(dev_cap->bmme_flags, outbox,
 		 QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
+	if (dev_cap->bmme_flags & MLX4_FLAG_PORT_REMAP)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_PORT_REMAP;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_CONFIG_DEV_OFFSET);
 	if (field & 0x20)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CONFIG_DEV;
@@ -1120,9 +1123,10 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
 	field &= 0x7f;
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_BF_OFFSET);
 
-	/* For guests, disable mw type 2 */
+	/* For guests, disable mw type 2 and port remap*/
 	MLX4_GET(bmme_flags, outbox->buf, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 	bmme_flags &= ~MLX4_BMME_FLAG_TYPE_2_WIN;
+	bmme_flags &= ~MLX4_FLAG_PORT_REMAP;
 	MLX4_PUT(outbox->buf, bmme_flags, QUERY_DEV_CAP_BMME_FLAGS_OFFSET);
 
 	/* turn off device-managed steering capability if not enabled */
@@ -2100,13 +2104,16 @@ struct mlx4_config_dev {
 	__be32	rsvd1[3];
 	__be16	vxlan_udp_dport;
 	__be16	rsvd2;
-	__be32	rsvd3[27];
-	__be16	rsvd4;
-	u8	rsvd5;
+	__be32	rsvd3;
+	__be32	roce_flags;
+	__be32	rsvd4[25];
+	__be16	rsvd5;
+	u8	rsvd6;
 	u8	rx_checksum_val;
 };
 
 #define MLX4_VXLAN_UDP_DPORT (1 << 0)
+#define MLX4_DISABLE_RX_PORT BIT(18)
 
 static int mlx4_CONFIG_DEV_set(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
 {
@@ -2209,6 +2216,45 @@ int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
 }
 EXPORT_SYMBOL_GPL(mlx4_config_vxlan_port);
 
+#define CONFIG_DISABLE_RX_PORT BIT(15)
+int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis)
+{
+	struct mlx4_config_dev config_dev;
+
+	memset(&config_dev, 0, sizeof(config_dev));
+	config_dev.update_flags = cpu_to_be32(MLX4_DISABLE_RX_PORT);
+	if (dis)
+		config_dev.roce_flags =
+			cpu_to_be32(CONFIG_DISABLE_RX_PORT);
+
+	return mlx4_CONFIG_DEV_set(dev, &config_dev);
+}
+
+int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	struct {
+		__be32 v_port1;
+		__be32 v_port2;
+	} *v2p;
+	int err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return -ENOMEM;
+
+	v2p = mailbox->buf;
+	v2p->v_port1 = cpu_to_be32(port1);
+	v2p->v_port2 = cpu_to_be32(port2);
+
+	err = mlx4_cmd(dev, mailbox->dma, 0,
+		       MLX4_SET_PORT_VIRT2PHY, MLX4_CMD_VIRT_PORT_MAP,
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
 
 int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
 {
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index ae95adc7850..7b6d4e9ff60 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -71,6 +71,7 @@ enum {
 
 	/*master notify fw on finish for slave's flr*/
 	MLX4_CMD_INFORM_FLR_DONE = 0x5b,
+	MLX4_CMD_VIRT_PORT_MAP   = 0x5c,
 	MLX4_CMD_GET_OP_REQ      = 0x59,
 
 	/* TPT commands */
@@ -170,6 +171,12 @@ enum {
 	MLX4_CMD_TIME_CLASS_C	= 60000,
 };
 
+enum {
+	/* virtual to physical port mapping opcode modifiers */
+	MLX4_GET_PORT_VIRT2PHY = 0x0,
+	MLX4_SET_PORT_VIRT2PHY = 0x1,
+};
+
 enum {
 	MLX4_MAILBOX_SIZE	= 4096,
 	MLX4_ACCESS_MEM_ALIGN	= 256,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index c95d659a39f..d9afd99dde3 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -201,7 +201,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_SYS_EQS		= 1LL <<  17,
 	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18,
 	MLX4_DEV_CAP_FLAG2_FS_A0		= 1LL <<  19,
-	MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20
+	MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT = 1LL << 20,
+	MLX4_DEV_CAP_FLAG2_PORT_REMAP		= 1LL <<  21
 };
 
 enum {
@@ -253,9 +254,14 @@ enum {
 	MLX4_BMME_FLAG_TYPE_2_WIN	= 1 <<  9,
 	MLX4_BMME_FLAG_RESERVED_LKEY	= 1 << 10,
 	MLX4_BMME_FLAG_FAST_REG_WR	= 1 << 11,
+	MLX4_BMME_FLAG_PORT_REMAP	= 1 << 24,
 	MLX4_BMME_FLAG_VSD_INIT2RTR	= 1 << 28,
 };
 
+enum {
+	MLX4_FLAG_PORT_REMAP		= MLX4_BMME_FLAG_PORT_REMAP
+};
+
 enum mlx4_event {
 	MLX4_EVENT_TYPE_COMP		   = 0x00,
 	MLX4_EVENT_TYPE_PATH_MIG	   = 0x01,
@@ -1378,6 +1384,8 @@ int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port);
 int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port);
 
 int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port);
+int mlx4_disable_rx_port_check(struct mlx4_dev *dev, bool dis);
+int mlx4_virt2phy_port_map(struct mlx4_dev *dev, u32 port1, u32 port2);
 int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port);
 int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port);
 int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 467ccdf94c9..2bbc62aa818 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -96,6 +96,7 @@ enum {
 	MLX4_QP_BIT_RRE				= 1 << 15,
 	MLX4_QP_BIT_RWE				= 1 << 14,
 	MLX4_QP_BIT_RAE				= 1 << 13,
+	MLX4_QP_BIT_FPP				= 1 <<	3,
 	MLX4_QP_BIT_RIC				= 1 <<	4,
 };
 
-- 
cgit v1.2.3-70-g09d2


From 53f33ae295a5098f12218da1400f55ad7df7447c Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Tue, 3 Feb 2015 16:48:33 +0200
Subject: net/mlx4_core: Port aggregation upper layer interface

Supply interface functions to bond and unbond ports of a mlx4 internal
interfaces. Example for such an interface is the one registered by the
mlx4 IB driver under RoCE.

There are

1. Functions to go in/out to/from bonded mode
2. Function to remap virtual ports to physical ports

The bond_mutex prevents simultaneous access to data that keep status of
the device in bonded mode.

The upper mlx4 interface marks to the mlx4 core module that they
want to be subject for such bonding by setting the MLX4_INTFF_BONDING
flag. Interface which goes to/from bonded mode is re-created.

The mlx4 Ethernet driver does not set this flag when registering the
interface, the IB driver does.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_resources.c  |  8 +-
 drivers/net/ethernet/mellanox/mlx4/intf.c          | 54 +++++++++++++
 drivers/net/ethernet/mellanox/mlx4/main.c          | 89 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |  3 +
 drivers/net/ethernet/mellanox/mlx4/qp.c            |  2 +
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |  3 +
 include/linux/mlx4/device.h                        |  1 +
 include/linux/mlx4/driver.h                        | 19 +++++
 8 files changed, 177 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index f1a5500ff72..34f2fdf4fe5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -50,10 +50,14 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	context->mtu_msgmax = 0xff;
 	if (!is_tx && !rss)
 		context->rq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
-	if (is_tx)
+	if (is_tx) {
 		context->sq_size_stride = ilog2(size) << 3 | (ilog2(stride) - 4);
-	else
+		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP)
+			context->params2 |= MLX4_QP_BIT_FPP;
+
+	} else {
 		context->sq_size_stride = ilog2(TXBB_SIZE) - 4;
+	}
 	context->usr_page = cpu_to_be32(mdev->priv_uar.index);
 	context->local_qpn = cpu_to_be32(qpn);
 	context->pri_path.ackto = 1 & 0x07;
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 68d2bad325d..6fce5871883 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -33,11 +33,13 @@
 
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/errno.h>
 
 #include "mlx4.h"
 
 struct mlx4_device_context {
 	struct list_head	list;
+	struct list_head	bond_list;
 	struct mlx4_interface  *intf;
 	void		       *context;
 };
@@ -115,6 +117,58 @@ void mlx4_unregister_interface(struct mlx4_interface *intf)
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_interface);
 
+int mlx4_do_bond(struct mlx4_dev *dev, bool enable)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_device_context *dev_ctx = NULL, *temp_dev_ctx;
+	unsigned long flags;
+	int ret;
+	LIST_HEAD(bond_list);
+
+	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
+		return -ENOTSUPP;
+
+	ret = mlx4_disable_rx_port_check(dev, enable);
+	if (ret) {
+		mlx4_err(dev, "Fail to %s rx port check\n",
+			 enable ? "enable" : "disable");
+		return ret;
+	}
+	if (enable) {
+		dev->flags |= MLX4_FLAG_BONDED;
+	} else {
+		 ret = mlx4_virt2phy_port_map(dev, 1, 2);
+		if (ret) {
+			mlx4_err(dev, "Fail to reset port map\n");
+			return ret;
+		}
+		dev->flags &= ~MLX4_FLAG_BONDED;
+	}
+
+	spin_lock_irqsave(&priv->ctx_lock, flags);
+	list_for_each_entry_safe(dev_ctx, temp_dev_ctx, &priv->ctx_list, list) {
+		if (dev_ctx->intf->flags & MLX4_INTFF_BONDING) {
+			list_add_tail(&dev_ctx->bond_list, &bond_list);
+			list_del(&dev_ctx->list);
+		}
+	}
+	spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+	list_for_each_entry(dev_ctx, &bond_list, bond_list) {
+		dev_ctx->intf->remove(dev, dev_ctx->context);
+		dev_ctx->context =  dev_ctx->intf->add(dev);
+
+		spin_lock_irqsave(&priv->ctx_lock, flags);
+		list_add_tail(&dev_ctx->list, &priv->ctx_list);
+		spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+		mlx4_dbg(dev, "Inrerface for protocol %d restarted with when bonded mode is %s\n",
+			 dev_ctx->intf->protocol, enable ?
+			 "enabled" : "disabled");
+	}
+	return 0;
+}
+
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
 			 unsigned long param)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index cc9f4843924..f3245fe0f44 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1160,6 +1160,91 @@ err_set_port:
 	return err ? err : count;
 }
 
+int mlx4_bond(struct mlx4_dev *dev)
+{
+	int ret = 0;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	mutex_lock(&priv->bond_mutex);
+
+	if (!mlx4_is_bonded(dev))
+		ret = mlx4_do_bond(dev, true);
+	else
+		ret = 0;
+
+	mutex_unlock(&priv->bond_mutex);
+	if (ret)
+		mlx4_err(dev, "Failed to bond device: %d\n", ret);
+	else
+		mlx4_dbg(dev, "Device is bonded\n");
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_bond);
+
+int mlx4_unbond(struct mlx4_dev *dev)
+{
+	int ret = 0;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	mutex_lock(&priv->bond_mutex);
+
+	if (mlx4_is_bonded(dev))
+		ret = mlx4_do_bond(dev, false);
+
+	mutex_unlock(&priv->bond_mutex);
+	if (ret)
+		mlx4_err(dev, "Failed to unbond device: %d\n", ret);
+	else
+		mlx4_dbg(dev, "Device is unbonded\n");
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_unbond);
+
+
+int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p)
+{
+	u8 port1 = v2p->port1;
+	u8 port2 = v2p->port2;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int err;
+
+	if (!(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PORT_REMAP))
+		return -ENOTSUPP;
+
+	mutex_lock(&priv->bond_mutex);
+
+	/* zero means keep current mapping for this port */
+	if (port1 == 0)
+		port1 = priv->v2p.port1;
+	if (port2 == 0)
+		port2 = priv->v2p.port2;
+
+	if ((port1 < 1) || (port1 > MLX4_MAX_PORTS) ||
+	    (port2 < 1) || (port2 > MLX4_MAX_PORTS) ||
+	    (port1 == 2 && port2 == 1)) {
+		/* besides boundary checks cross mapping makes
+		 * no sense and therefore not allowed */
+		err = -EINVAL;
+	} else if ((port1 == priv->v2p.port1) &&
+		 (port2 == priv->v2p.port2)) {
+		err = 0;
+	} else {
+		err = mlx4_virt2phy_port_map(dev, port1, port2);
+		if (!err) {
+			mlx4_dbg(dev, "port map changed: [%d][%d]\n",
+				 port1, port2);
+			priv->v2p.port1 = port1;
+			priv->v2p.port2 = port2;
+		} else {
+			mlx4_err(dev, "Failed to change port mape: %d\n", err);
+		}
+	}
+
+	mutex_unlock(&priv->bond_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_port_map_set);
+
 static int mlx4_load_fw(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2638,6 +2723,7 @@ static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data,
 	spin_lock_init(&priv->ctx_lock);
 
 	mutex_init(&priv->port_mutex);
+	mutex_init(&priv->bond_mutex);
 
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
@@ -2934,6 +3020,9 @@ slave_start:
 			goto err_port;
 	}
 
+	priv->v2p.port1 = 1;
+	priv->v2p.port2 = 2;
+
 	err = mlx4_register_device(dev);
 	if (err)
 		goto err_port;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 148dc0945aa..803f17653da 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -885,6 +885,8 @@ struct mlx4_priv {
 	int			reserved_mtts;
 	int			fs_hash_mode;
 	u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS];
+	struct mlx4_port_map	v2p; /* cached port mapping configuration */
+	struct mutex		bond_mutex; /* for bond mode */
 	__be64			slave_node_guids[MLX4_MFUNC_MAX];
 
 	atomic_t		opreq_count;
@@ -1364,6 +1366,7 @@ int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
 /* Returns the VF index of slave */
 int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
 int mlx4_config_mad_demux(struct mlx4_dev *dev);
+int mlx4_do_bond(struct mlx4_dev *dev, bool enable);
 
 enum mlx4_zone_flags {
 	MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO	= 1UL << 0,
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 1586ecce13c..2bb8553bd90 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -882,6 +882,8 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 	for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
 		context->flags &= cpu_to_be32(~(0xf << 28));
 		context->flags |= cpu_to_be32(states[i + 1] << 28);
+		if (states[i + 1] != MLX4_QP_STATE_RTR)
+			context->params2 &= ~MLX4_QP_BIT_FPP;
 		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
 				     context, 0, 0, qp);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 79feeb6b0d8..c5f3dfca226 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2944,6 +2944,9 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 	qp_type	= (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
 	optpar	= be32_to_cpu(*(__be32 *) inbox->buf);
 
+	if (slave != mlx4_master_func_num(dev))
+		qp_ctx->params2 &= ~MLX4_QP_BIT_FPP;
+
 	switch (qp_type) {
 	case MLX4_QP_ST_RC:
 	case MLX4_QP_ST_XRC:
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d9afd99dde3..977b0b16443 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -70,6 +70,7 @@ enum {
 	MLX4_FLAG_SLAVE		= 1 << 3,
 	MLX4_FLAG_SRIOV		= 1 << 4,
 	MLX4_FLAG_OLD_REG_MAC	= 1 << 6,
+	MLX4_FLAG_BONDED	= 1 << 7
 };
 
 enum {
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 022055c8fb2..9553a73d204 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -49,6 +49,10 @@ enum mlx4_dev_event {
 	MLX4_DEV_EVENT_SLAVE_SHUTDOWN,
 };
 
+enum {
+	MLX4_INTFF_BONDING	= 1 << 0
+};
+
 struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
@@ -57,11 +61,26 @@ struct mlx4_interface {
 	void *			(*get_dev)(struct mlx4_dev *dev, void *context, u8 port);
 	struct list_head	list;
 	enum mlx4_protocol	protocol;
+	int			flags;
 };
 
 int mlx4_register_interface(struct mlx4_interface *intf);
 void mlx4_unregister_interface(struct mlx4_interface *intf);
 
+int mlx4_bond(struct mlx4_dev *dev);
+int mlx4_unbond(struct mlx4_dev *dev);
+static inline int mlx4_is_bonded(struct mlx4_dev *dev)
+{
+	return !!(dev->flags & MLX4_FLAG_BONDED);
+}
+
+struct mlx4_port_map {
+	u8	port1;
+	u8	port2;
+};
+
+int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
+
 void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
 
 static inline u64 mlx4_mac_to_u64(u8 *addr)
-- 
cgit v1.2.3-70-g09d2


From f2dba9c6ff0d9a515b4c3f1b037cd65c8b2a868c Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 4 Feb 2015 07:33:23 +1100
Subject: rhashtable: Introduce rhashtable_walk_*

Some existing rhashtable users get too intimate with it by walking
the buckets directly.  This prevents us from easily changing the
internals of rhashtable.

This patch adds the helpers rhashtable_walk_init/exit/start/next/stop
which will replace these custom walkers.

They are meant to be usable for both procfs seq_file walks as well
as walking by a netlink dump.  The iterator structure should fit
inside a netlink dump cb structure, with at least one element to
spare.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  35 ++++++++++
 lib/rhashtable.c           | 163 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 198 insertions(+)

(limited to 'include')

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index e0337844358..58851275fed 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -18,6 +18,7 @@
 #ifndef _LINUX_RHASHTABLE_H
 #define _LINUX_RHASHTABLE_H
 
+#include <linux/compiler.h>
 #include <linux/list_nulls.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
@@ -111,6 +112,7 @@ struct rhashtable_params {
  * @p: Configuration parameters
  * @run_work: Deferred worker to expand/shrink asynchronously
  * @mutex: Mutex to protect current/future table swapping
+ * @walkers: List of active walkers
  * @being_destroyed: True if table is set up for destruction
  */
 struct rhashtable {
@@ -121,9 +123,36 @@ struct rhashtable {
 	struct rhashtable_params	p;
 	struct work_struct		run_work;
 	struct mutex                    mutex;
+	struct list_head		walkers;
 	bool                            being_destroyed;
 };
 
+/**
+ * struct rhashtable_walker - Hash table walker
+ * @list: List entry on list of walkers
+ * @resize: Resize event occured
+ */
+struct rhashtable_walker {
+	struct list_head list;
+	bool resize;
+};
+
+/**
+ * struct rhashtable_iter - Hash table iterator, fits into netlink cb
+ * @ht: Table to iterate through
+ * @p: Current pointer
+ * @walker: Associated rhashtable walker
+ * @slot: Current slot
+ * @skip: Number of entries to skip in slot
+ */
+struct rhashtable_iter {
+	struct rhashtable *ht;
+	struct rhash_head *p;
+	struct rhashtable_walker *walker;
+	unsigned int slot;
+	unsigned int skip;
+};
+
 static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash)
 {
 	return NULLS_MARKER(ht->p.nulls_base + hash);
@@ -179,6 +208,12 @@ bool rhashtable_lookup_compare_insert(struct rhashtable *ht,
 				      bool (*compare)(void *, void *),
 				      void *arg);
 
+int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter);
+void rhashtable_walk_exit(struct rhashtable_iter *iter);
+int rhashtable_walk_start(struct rhashtable_iter *iter) __acquires(RCU);
+void *rhashtable_walk_next(struct rhashtable_iter *iter);
+void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU);
+
 void rhashtable_destroy(struct rhashtable *ht);
 
 #define rht_dereference(p, ht) \
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 904b419b72f..057919164e2 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -484,6 +484,7 @@ static void rht_deferred_worker(struct work_struct *work)
 {
 	struct rhashtable *ht;
 	struct bucket_table *tbl;
+	struct rhashtable_walker *walker;
 
 	ht = container_of(work, struct rhashtable, run_work);
 	mutex_lock(&ht->mutex);
@@ -492,6 +493,9 @@ static void rht_deferred_worker(struct work_struct *work)
 
 	tbl = rht_dereference(ht->tbl, ht);
 
+	list_for_each_entry(walker, &ht->walkers, list)
+		walker->resize = true;
+
 	if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size))
 		rhashtable_expand(ht);
 	else if (ht->p.shrink_decision && ht->p.shrink_decision(ht, tbl->size))
@@ -822,6 +826,164 @@ exit:
 }
 EXPORT_SYMBOL_GPL(rhashtable_lookup_compare_insert);
 
+/**
+ * rhashtable_walk_init - Initialise an iterator
+ * @ht:		Table to walk over
+ * @iter:	Hash table Iterator
+ *
+ * This function prepares a hash table walk.
+ *
+ * Note that if you restart a walk after rhashtable_walk_stop you
+ * may see the same object twice.  Also, you may miss objects if
+ * there are removals in between rhashtable_walk_stop and the next
+ * call to rhashtable_walk_start.
+ *
+ * For a completely stable walk you should construct your own data
+ * structure outside the hash table.
+ *
+ * This function may sleep so you must not call it from interrupt
+ * context or with spin locks held.
+ *
+ * You must call rhashtable_walk_exit if this function returns
+ * successfully.
+ */
+int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter)
+{
+	iter->ht = ht;
+	iter->p = NULL;
+	iter->slot = 0;
+	iter->skip = 0;
+
+	iter->walker = kmalloc(sizeof(*iter->walker), GFP_KERNEL);
+	if (!iter->walker)
+		return -ENOMEM;
+
+	mutex_lock(&ht->mutex);
+	list_add(&iter->walker->list, &ht->walkers);
+	mutex_unlock(&ht->mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rhashtable_walk_init);
+
+/**
+ * rhashtable_walk_exit - Free an iterator
+ * @iter:	Hash table Iterator
+ *
+ * This function frees resources allocated by rhashtable_walk_init.
+ */
+void rhashtable_walk_exit(struct rhashtable_iter *iter)
+{
+	mutex_lock(&iter->ht->mutex);
+	list_del(&iter->walker->list);
+	mutex_unlock(&iter->ht->mutex);
+	kfree(iter->walker);
+}
+EXPORT_SYMBOL_GPL(rhashtable_walk_exit);
+
+/**
+ * rhashtable_walk_start - Start a hash table walk
+ * @iter:	Hash table iterator
+ *
+ * Start a hash table walk.  Note that we take the RCU lock in all
+ * cases including when we return an error.  So you must always call
+ * rhashtable_walk_stop to clean up.
+ *
+ * Returns zero if successful.
+ *
+ * Returns -EAGAIN if resize event occured.  Note that the iterator
+ * will rewind back to the beginning and you may use it immediately
+ * by calling rhashtable_walk_next.
+ */
+int rhashtable_walk_start(struct rhashtable_iter *iter)
+{
+	rcu_read_lock();
+
+	if (iter->walker->resize) {
+		iter->slot = 0;
+		iter->skip = 0;
+		iter->walker->resize = false;
+		return -EAGAIN;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rhashtable_walk_start);
+
+/**
+ * rhashtable_walk_next - Return the next object and advance the iterator
+ * @iter:	Hash table iterator
+ *
+ * Note that you must call rhashtable_walk_stop when you are finished
+ * with the walk.
+ *
+ * Returns the next object or NULL when the end of the table is reached.
+ *
+ * Returns -EAGAIN if resize event occured.  Note that the iterator
+ * will rewind back to the beginning and you may continue to use it.
+ */
+void *rhashtable_walk_next(struct rhashtable_iter *iter)
+{
+	const struct bucket_table *tbl;
+	struct rhashtable *ht = iter->ht;
+	struct rhash_head *p = iter->p;
+	void *obj = NULL;
+
+	tbl = rht_dereference_rcu(ht->tbl, ht);
+
+	if (p) {
+		p = rht_dereference_bucket_rcu(p->next, tbl, iter->slot);
+		goto next;
+	}
+
+	for (; iter->slot < tbl->size; iter->slot++) {
+		int skip = iter->skip;
+
+		rht_for_each_rcu(p, tbl, iter->slot) {
+			if (!skip)
+				break;
+			skip--;
+		}
+
+next:
+		if (!rht_is_a_nulls(p)) {
+			iter->skip++;
+			iter->p = p;
+			obj = rht_obj(ht, p);
+			goto out;
+		}
+
+		iter->skip = 0;
+	}
+
+	iter->p = NULL;
+
+out:
+	if (iter->walker->resize) {
+		iter->p = NULL;
+		iter->slot = 0;
+		iter->skip = 0;
+		iter->walker->resize = false;
+		return ERR_PTR(-EAGAIN);
+	}
+
+	return obj;
+}
+EXPORT_SYMBOL_GPL(rhashtable_walk_next);
+
+/**
+ * rhashtable_walk_stop - Finish a hash table walk
+ * @iter:	Hash table iterator
+ *
+ * Finish a hash table walk.
+ */
+void rhashtable_walk_stop(struct rhashtable_iter *iter)
+{
+	rcu_read_unlock();
+	iter->p = NULL;
+}
+EXPORT_SYMBOL_GPL(rhashtable_walk_stop);
+
 static size_t rounded_hashtable_size(struct rhashtable_params *params)
 {
 	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
@@ -894,6 +1056,7 @@ int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params)
 	memset(ht, 0, sizeof(*ht));
 	mutex_init(&ht->mutex);
 	memcpy(&ht->p, params, sizeof(*params));
+	INIT_LIST_HEAD(&ht->walkers);
 
 	if (params->locks_mul)
 		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
-- 
cgit v1.2.3-70-g09d2


From 9878196578286c5ed494778ada01da094377a686 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 3 Feb 2015 18:31:53 -0800
Subject: tcp: do not pace pure ack packets

When we added pacing to TCP, we decided to let sch_fq take care
of actual pacing.

All TCP had to do was to compute sk->pacing_rate using simple formula:

sk->pacing_rate = 2 * cwnd * mss / rtt

It works well for senders (bulk flows), but not very well for receivers
or even RPC :

cwnd on the receiver can be less than 10, rtt can be around 100ms, so we
can end up pacing ACK packets, slowing down the sender.

Really, only the sender should pace, according to its own logic.

Instead of adding a new bit in skb, or call yet another flow
dissection, we tweak skb->truesize to a small value (2), and
we instruct sch_fq to use new helper and not pace pure ack.

Note this also helps TCP small queue, as ack packets present
in qdisc/NIC do not prevent sending a data packet (RPC workload)

This helps to reduce tx completion overhead, ack packets can use regular
sock_wfree() instead of tcp_wfree() which is a bit more expensive.

This has no impact in the case packets are sent to loopback interface,
as we do not coalesce ack packets (were we would detect skb->truesize
lie)

In case netem (with a delay) is used, skb_orphan_partial() also sets
skb->truesize to 1.

This patch is a combination of two patches we used for about one year at
Google.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 15 +++++++++++++++
 net/ipv4/tcp_output.c | 10 +++++++++-
 net/sched/sch_fq.c    | 10 ++++++++--
 3 files changed, 32 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b8fdc6bab3f..637ee490ec8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1713,4 +1713,19 @@ static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb)
 	return dopt;
 }
 
+/* locally generated TCP pure ACKs have skb->truesize == 2
+ * (check tcp_send_ack() in net/ipv4/tcp_output.c )
+ * This is much faster than dissecting the packet to find out.
+ * (Think of GRE encapsulations, IPv4, IPv6, ...)
+ */
+static inline bool skb_is_tcp_pure_ack(const struct sk_buff *skb)
+{
+	return skb->truesize == 2;
+}
+
+static inline void skb_set_tcp_pure_ack(struct sk_buff *skb)
+{
+	skb->truesize = 2;
+}
+
 #endif	/* _TCP_H */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 20ab06b228a..1b326ed46f7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -948,7 +948,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	skb_orphan(skb);
 	skb->sk = sk;
-	skb->destructor = tcp_wfree;
+	skb->destructor = skb_is_tcp_pure_ack(skb) ? sock_wfree : tcp_wfree;
 	skb_set_hash_from_sk(skb, sk);
 	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 
@@ -3265,6 +3265,14 @@ void tcp_send_ack(struct sock *sk)
 	skb_reserve(buff, MAX_TCP_HEADER);
 	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
 
+	/* We do not want pure acks influencing TCP Small Queues or fq/pacing
+	 * too much.
+	 * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784
+	 * We also avoid tcp_wfree() overhead (cache line miss accessing
+	 * tp->tsq_flags) by using regular sock_wfree()
+	 */
+	skb_set_tcp_pure_ack(buff);
+
 	/* Send it off, this clears delayed acks for us. */
 	skb_mstamp_get(&buff->skb_mstamp);
 	tcp_transmit_skb(sk, buff, 0, sk_gfp_atomic(sk, GFP_ATOMIC));
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 2a50f5c6207..69a3dbf55c6 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -52,6 +52,7 @@
 #include <net/pkt_sched.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
+#include <net/tcp.h>
 
 /*
  * Per flow structure, dynamically allocated
@@ -445,7 +446,9 @@ begin:
 		goto begin;
 	}
 
-	if (unlikely(f->head && now < f->time_next_packet)) {
+	skb = f->head;
+	if (unlikely(skb && now < f->time_next_packet &&
+		     !skb_is_tcp_pure_ack(skb))) {
 		head->first = f->next;
 		fq_flow_set_throttled(q, f);
 		goto begin;
@@ -464,12 +467,15 @@ begin:
 		goto begin;
 	}
 	prefetch(&skb->end);
-	f->time_next_packet = now;
 	f->credit -= qdisc_pkt_len(skb);
 
 	if (f->credit > 0 || !q->rate_enable)
 		goto out;
 
+	/* Do not pace locally generated ack packets */
+	if (skb_is_tcp_pure_ack(skb))
+		goto out;
+
 	rate = q->flow_max_rate;
 	if (skb->sk)
 		rate = min(skb->sk->sk_pacing_rate, rate);
-- 
cgit v1.2.3-70-g09d2


From 06eb395fa9856b5a87cf7d80baee2a0ed3cdb9d7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Feb 2015 21:30:40 -0800
Subject: pkt_sched: fq: better control of DDOS traffic

FQ has a fast path for skb attached to a socket, as it does not
have to compute a flow hash. But for other packets, FQ being non
stochastic means that hosts exposed to random Internet traffic
can allocate million of flows structure (104 bytes each) pretty
easily. Not only host can OOM, but lookup in RB trees can take
too much cpu and memory resources.

This patch adds a new attribute, orphan_mask, that is adding
possibility of having a stochastic hash for orphaned skb.

Its default value is 1024 slots, to mimic SFQ behavior.

Note: This does not apply to locally generated TCP traffic,
and no locally generated traffic will share a flow structure
with another perfect or stochastic flow.

This patch also handles the specific case of SYNACK messages:

They are attached to the listener socket, and therefore all map
to a single hash bucket. If listener have set SO_MAX_PACING_RATE,
hoping to have new accepted socket inherit this rate, SYNACK
might be paced and even dropped.

This is very similar to an internal patch Google have used more
than one year.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  2 ++
 net/sched/sch_fq.c             | 19 +++++++++++++++++--
 2 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index d62316baae9..534b8471074 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -774,6 +774,8 @@ enum {
 
 	TCA_FQ_FLOW_REFILL_DELAY,	/* flow credit refill delay in usec */
 
+	TCA_FQ_ORPHAN_MASK,	/* mask applied to orphaned skb hashes */
+
 	__TCA_FQ_MAX
 };
 
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 69a3dbf55c6..a00c4304300 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -93,6 +93,7 @@ struct fq_sched_data {
 	u32		flow_refill_delay;
 	u32		flow_max_rate;	/* optional max rate per flow */
 	u32		flow_plimit;	/* max packets per flow */
+	u32		orphan_mask;	/* mask for orphaned skb */
 	struct rb_root	*fq_root;
 	u8		rate_enable;
 	u8		fq_trees_log;
@@ -223,11 +224,20 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q)
 	if (unlikely((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL))
 		return &q->internal;
 
-	if (unlikely(!sk)) {
+	/* SYNACK messages are attached to a listener socket.
+	 * 1) They are not part of a 'flow' yet
+	 * 2) We do not want to rate limit them (eg SYNFLOOD attack),
+	 *    especially if the listener set SO_MAX_PACING_RATE
+	 * 3) We pretend they are orphaned
+	 */
+	if (!sk || sk->sk_state == TCP_LISTEN) {
+		unsigned long hash = skb_get_hash(skb) & q->orphan_mask;
+
 		/* By forcing low order bit to 1, we make sure to not
 		 * collide with a local flow (socket pointers are word aligned)
 		 */
-		sk = (struct sock *)(skb_get_hash(skb) | 1L);
+		sk = (struct sock *)((hash << 1) | 1UL);
+		skb_orphan(skb);
 	}
 
 	root = &q->fq_root[hash_32((u32)(long)sk, q->fq_trees_log)];
@@ -704,6 +714,9 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt)
 		q->flow_refill_delay = usecs_to_jiffies(usecs_delay);
 	}
 
+	if (tb[TCA_FQ_ORPHAN_MASK])
+		q->orphan_mask = nla_get_u32(tb[TCA_FQ_ORPHAN_MASK]);
+
 	if (!err) {
 		sch_tree_unlock(sch);
 		err = fq_resize(sch, fq_log);
@@ -749,6 +762,7 @@ static int fq_init(struct Qdisc *sch, struct nlattr *opt)
 	q->delayed		= RB_ROOT;
 	q->fq_root		= NULL;
 	q->fq_trees_log		= ilog2(1024);
+	q->orphan_mask		= 1024 - 1;
 	qdisc_watchdog_init(&q->watchdog, sch);
 
 	if (opt)
@@ -778,6 +792,7 @@ static int fq_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    nla_put_u32(skb, TCA_FQ_FLOW_MAX_RATE, q->flow_max_rate) ||
 	    nla_put_u32(skb, TCA_FQ_FLOW_REFILL_DELAY,
 			jiffies_to_usecs(q->flow_refill_delay)) ||
+	    nla_put_u32(skb, TCA_FQ_ORPHAN_MASK, q->orphan_mask) ||
 	    nla_put_u32(skb, TCA_FQ_BUCKETS_LOG, q->fq_trees_log))
 		goto nla_put_failure;
 
-- 
cgit v1.2.3-70-g09d2


From f4575d3534617eec98c7eb8701185cec96b4374b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Feb 2015 13:31:54 -0800
Subject: flow_keys: n_proto type should be __be16

(struct flow_keys)->n_proto is in network order, use
proper type for this.

Fixes following sparse errors :

net/core/flow_dissector.c:139:39: warning: incorrect type in assignment (different base types)
net/core/flow_dissector.c:139:39:    expected unsigned short [unsigned] [usertype] n_proto
net/core/flow_dissector.c:139:39:    got restricted __be16 [assigned] [usertype] proto
net/core/flow_dissector.c:237:23: warning: incorrect type in assignment (different base types)
net/core/flow_dissector.c:237:23:    expected unsigned short [unsigned] [usertype] n_proto
net/core/flow_dissector.c:237:23:    got restricted __be16 [assigned] [usertype] proto

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: e0f31d849867 ("flow_keys: Record IP layer protocol in skb_flow_dissect()")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_keys.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 7ee2df08354..dc8fd81412b 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -22,9 +22,9 @@ struct flow_keys {
 		__be32 ports;
 		__be16 port16[2];
 	};
-	u16 thoff;
-	u16 n_proto;
-	u8 ip_proto;
+	u16	thoff;
+	__be16	n_proto;
+	u8	ip_proto;
 };
 
 bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
-- 
cgit v1.2.3-70-g09d2


From 677651462c774b5866be2bc42601303a76b021a0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 4 Feb 2015 15:03:25 -0800
Subject: ipv6: fix sparse errors in ip6_make_flowlabel()

include/net/ipv6.h:713:22: warning: incorrect type in assignment (different base types)
include/net/ipv6.h:713:22:    expected restricted __be32 [usertype] hash
include/net/ipv6.h:713:22:    got unsigned int
include/net/ipv6.h:719:25: warning: restricted __be32 degrades to integer
include/net/ipv6.h:719:22: warning: invalid assignment: ^=
include/net/ipv6.h:719:22:    left side has type restricted __be32
include/net/ipv6.h:719:22:    right side has type unsigned int

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 9bf85d34c02..6e416f6d3e3 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -711,7 +711,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 					__be32 flowlabel, bool autolabel)
 {
 	if (!flowlabel && (autolabel || net->ipv6.sysctl.auto_flowlabels)) {
-		__be32 hash;
+		u32 hash;
 
 		hash = skb_get_hash(skb);
 
@@ -721,7 +721,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 		 */
 		hash ^= hash >> 12;
 
-		flowlabel = hash & IPV6_FLOWLABEL_MASK;
+		flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 	}
 
 	return flowlabel;
-- 
cgit v1.2.3-70-g09d2


From 7fbc1067f06098c6b674e672fbb17e758fcc9402 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 28 Oct 2013 10:32:35 +0100
Subject: exportfs: add methods for block layout exports

Add three methods to allow exporting pnfs block layout volumes:

 - get_uuid: get a filesystem unique signature exposed to clients
 - map_blocks: map and if nessecary allocate blocks for a layout
 - commit_blocks: commit blocks in a layout once the client is done with them

For now we stick the external pnfs block layout interfaces into s_export_op to
avoid mixing them up with the internal interface between the NFS server and
the layout drivers.  Once we've fully internalized the latter interface we
can redecide if these methods should stay in s_export_ops.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/exportfs.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 41b223a59a6..fa05e04c553 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 
 struct dentry;
+struct iattr;
 struct inode;
 struct super_block;
 struct vfsmount;
@@ -180,6 +181,21 @@ struct fid {
  *    get_name is not (which is possibly inconsistent)
  */
 
+/* types of block ranges for multipage write mappings. */
+#define IOMAP_HOLE	0x01	/* no blocks allocated, need allocation */
+#define IOMAP_DELALLOC	0x02	/* delayed allocation blocks */
+#define IOMAP_MAPPED	0x03	/* blocks allocated @blkno */
+#define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
+
+#define IOMAP_NULL_BLOCK -1LL	/* blkno is not valid */
+
+struct iomap {
+	sector_t	blkno;	/* first sector of mapping */
+	loff_t		offset;	/* file offset of mapping, bytes */
+	u64		length;	/* length of mapping, bytes */
+	int		type;	/* type of mapping */
+};
+
 struct export_operations {
 	int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len,
 			struct inode *parent);
@@ -191,6 +207,13 @@ struct export_operations {
 			struct dentry *child);
 	struct dentry * (*get_parent)(struct dentry *child);
 	int (*commit_metadata)(struct inode *inode);
+
+	int (*get_uuid)(struct super_block *sb, u8 *buf, u32 *len, u64 *offset);
+	int (*map_blocks)(struct inode *inode, loff_t offset,
+			  u64 len, struct iomap *iomap,
+			  bool write, u32 *device_generation);
+	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
+			     int nr_iomaps, struct iattr *iattr);
 };
 
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
-- 
cgit v1.2.3-70-g09d2


From 90e97820619dc912b52cc9d103272819d8b51259 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 5 Feb 2015 13:44:43 +0800
Subject: resources: Move struct resource_list_entry from ACPI into resource
 core

Currently ACPI, PCI and pnp all implement the same resource list
management with different data structure. We need to transfer from
one data structure into another when passing resources from one
subsystem into another subsystem. So move struct resource_list_entry
from ACPI into resource core and rename it as resource_entry,
then it could be reused by different subystems and avoid the data
structure conversion.

Introduce dedicated header file resource_ext.h instead of embedding
it into ioport.h to avoid header file inclusion order issues.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_lpss.c     |  8 ++---
 drivers/acpi/acpi_platform.c |  4 +--
 drivers/acpi/resource.c      | 17 ++++------
 drivers/dma/acpi-dma.c       | 10 +++---
 include/linux/acpi.h         | 12 +------
 include/linux/resource_ext.h | 77 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/resource.c            | 25 ++++++++++++++
 7 files changed, 120 insertions(+), 33 deletions(-)
 create mode 100644 include/linux/resource_ext.h

(limited to 'include')

diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 4f3febf8a58..dfd1b8095da 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -313,7 +313,7 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 {
 	struct lpss_device_desc *dev_desc;
 	struct lpss_private_data *pdata;
-	struct resource_list_entry *rentry;
+	struct resource_entry *rentry;
 	struct list_head resource_list;
 	struct platform_device *pdev;
 	int ret;
@@ -333,12 +333,12 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 		goto err_out;
 
 	list_for_each_entry(rentry, &resource_list, node)
-		if (resource_type(&rentry->res) == IORESOURCE_MEM) {
+		if (resource_type(rentry->res) == IORESOURCE_MEM) {
 			if (dev_desc->prv_size_override)
 				pdata->mmio_size = dev_desc->prv_size_override;
 			else
-				pdata->mmio_size = resource_size(&rentry->res);
-			pdata->mmio_base = ioremap(rentry->res.start,
+				pdata->mmio_size = resource_size(rentry->res);
+			pdata->mmio_base = ioremap(rentry->res->start,
 						   pdata->mmio_size);
 			break;
 		}
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index 6ba8beb6b9d..1284138e42a 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -45,7 +45,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 	struct platform_device *pdev = NULL;
 	struct acpi_device *acpi_parent;
 	struct platform_device_info pdevinfo;
-	struct resource_list_entry *rentry;
+	struct resource_entry *rentry;
 	struct list_head resource_list;
 	struct resource *resources = NULL;
 	int count;
@@ -71,7 +71,7 @@ struct platform_device *acpi_create_platform_device(struct acpi_device *adev)
 		}
 		count = 0;
 		list_for_each_entry(rentry, &resource_list, node)
-			resources[count++] = rentry->res;
+			resources[count++] = *rentry->res;
 
 		acpi_dev_free_resource_list(&resource_list);
 	}
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 3ea0d17eb95..4752b993998 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -444,12 +444,7 @@ EXPORT_SYMBOL_GPL(acpi_dev_resource_interrupt);
  */
 void acpi_dev_free_resource_list(struct list_head *list)
 {
-	struct resource_list_entry *rentry, *re;
-
-	list_for_each_entry_safe(rentry, re, list, node) {
-		list_del(&rentry->node);
-		kfree(rentry);
-	}
+	resource_list_free(list);
 }
 EXPORT_SYMBOL_GPL(acpi_dev_free_resource_list);
 
@@ -464,16 +459,16 @@ struct res_proc_context {
 static acpi_status acpi_dev_new_resource_entry(struct resource_win *win,
 					       struct res_proc_context *c)
 {
-	struct resource_list_entry *rentry;
+	struct resource_entry *rentry;
 
-	rentry = kmalloc(sizeof(*rentry), GFP_KERNEL);
+	rentry = resource_list_create_entry(NULL, 0);
 	if (!rentry) {
 		c->error = -ENOMEM;
 		return AE_NO_MEMORY;
 	}
-	rentry->res = win->res;
+	*rentry->res = win->res;
 	rentry->offset = win->offset;
-	list_add_tail(&rentry->node, c->list);
+	resource_list_add_tail(rentry, c->list);
 	c->count++;
 	return AE_OK;
 }
@@ -534,7 +529,7 @@ static acpi_status acpi_dev_process_resource(struct acpi_resource *ares,
  * returned as the final error code.
  *
  * The resultant struct resource objects are put on the list pointed to by
- * @list, that must be empty initially, as members of struct resource_list_entry
+ * @list, that must be empty initially, as members of struct resource_entry
  * objects.  Callers of this routine should use %acpi_dev_free_resource_list() to
  * free that list.
  *
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index de361a156b3..5a635646e05 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -43,7 +43,7 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 {
 	const struct acpi_csrt_shared_info *si;
 	struct list_head resource_list;
-	struct resource_list_entry *rentry;
+	struct resource_entry *rentry;
 	resource_size_t mem = 0, irq = 0;
 	int ret;
 
@@ -56,10 +56,10 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 		return 0;
 
 	list_for_each_entry(rentry, &resource_list, node) {
-		if (resource_type(&rentry->res) == IORESOURCE_MEM)
-			mem = rentry->res.start;
-		else if (resource_type(&rentry->res) == IORESOURCE_IRQ)
-			irq = rentry->res.start;
+		if (resource_type(rentry->res) == IORESOURCE_MEM)
+			mem = rentry->res->start;
+		else if (resource_type(rentry->res) == IORESOURCE_IRQ)
+			irq = rentry->res->start;
 	}
 
 	acpi_dev_free_resource_list(&resource_list);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index e818decb631..e53822148b6 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -27,6 +27,7 @@
 
 #include <linux/errno.h>
 #include <linux/ioport.h>	/* for struct resource */
+#include <linux/resource_ext.h>
 #include <linux/device.h>
 #include <linux/property.h>
 
@@ -285,11 +286,6 @@ extern int pnpacpi_disabled;
 
 #define PXM_INVAL	(-1)
 
-struct resource_win {
-	struct resource res;
-	resource_size_t offset;
-};
-
 bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res);
 bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res);
 bool acpi_dev_resource_address_space(struct acpi_resource *ares,
@@ -300,12 +296,6 @@ unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable);
 bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 				 struct resource *res);
 
-struct resource_list_entry {
-	struct list_head node;
-	struct resource res;
-	resource_size_t offset;
-};
-
 void acpi_dev_free_resource_list(struct list_head *list);
 int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list,
 			   int (*preproc)(struct acpi_resource *, void *),
diff --git a/include/linux/resource_ext.h b/include/linux/resource_ext.h
new file mode 100644
index 00000000000..e2bf63d881d
--- /dev/null
+++ b/include/linux/resource_ext.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2015, Intel Corporation
+ * Author: Jiang Liu <jiang.liu@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#ifndef _LINUX_RESOURCE_EXT_H
+#define _LINUX_RESOURCE_EXT_H
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+
+/* Represent resource window for bridge devices */
+struct resource_win {
+	struct resource res;		/* In master (CPU) address space */
+	resource_size_t offset;		/* Translation offset for bridge */
+};
+
+/*
+ * Common resource list management data structure and interfaces to support
+ * ACPI, PNP and PCI host bridge etc.
+ */
+struct resource_entry {
+	struct list_head	node;
+	struct resource		*res;	/* In master (CPU) address space */
+	resource_size_t		offset;	/* Translation offset for bridge */
+	struct resource		__res;	/* Default storage for res */
+};
+
+extern struct resource_entry *
+resource_list_create_entry(struct resource *res, size_t extra_size);
+extern void resource_list_free(struct list_head *head);
+
+static inline void resource_list_add(struct resource_entry *entry,
+				     struct list_head *head)
+{
+	list_add(&entry->node, head);
+}
+
+static inline void resource_list_add_tail(struct resource_entry *entry,
+					  struct list_head *head)
+{
+	list_add_tail(&entry->node, head);
+}
+
+static inline void resource_list_del(struct resource_entry *entry)
+{
+	list_del(&entry->node);
+}
+
+static inline void resource_list_free_entry(struct resource_entry *entry)
+{
+	kfree(entry);
+}
+
+static inline void
+resource_list_destroy_entry(struct resource_entry *entry)
+{
+	resource_list_del(entry);
+	resource_list_free_entry(entry);
+}
+
+#define resource_list_for_each_entry(entry, list)	\
+	list_for_each_entry((entry), (list), node)
+
+#define resource_list_for_each_entry_safe(entry, tmp, list)	\
+	list_for_each_entry_safe((entry), (tmp), (list), node)
+
+#endif /* _LINUX_RESOURCE_EXT_H */
diff --git a/kernel/resource.c b/kernel/resource.c
index 0bcebffc4e7..19f2357dfda 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -22,6 +22,7 @@
 #include <linux/device.h>
 #include <linux/pfn.h>
 #include <linux/mm.h>
+#include <linux/resource_ext.h>
 #include <asm/io.h>
 
 
@@ -1529,6 +1530,30 @@ int iomem_is_exclusive(u64 addr)
 	return err;
 }
 
+struct resource_entry *resource_list_create_entry(struct resource *res,
+						  size_t extra_size)
+{
+	struct resource_entry *entry;
+
+	entry = kzalloc(sizeof(*entry) + extra_size, GFP_KERNEL);
+	if (entry) {
+		INIT_LIST_HEAD(&entry->node);
+		entry->res = res ? res : &entry->__res;
+	}
+
+	return entry;
+}
+EXPORT_SYMBOL(resource_list_create_entry);
+
+void resource_list_free(struct list_head *head)
+{
+	struct resource_entry *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, head, node)
+		resource_list_destroy_entry(entry);
+}
+EXPORT_SYMBOL(resource_list_free);
+
 static int __init strict_iomem(char *str)
 {
 	if (strstr(str, "relaxed"))
-- 
cgit v1.2.3-70-g09d2


From 14d76b68f2819a1d0b50236a7e9e9f2ea69869d9 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 5 Feb 2015 13:44:44 +0800
Subject: PCI: Use common resource list management code instead of private
 implementation

Use common resource list management data structure and interfaces
instead of private implementation.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm/kernel/bios32.c            |  5 ++---
 arch/x86/pci/bus_numa.c             |  4 ++--
 drivers/pci/bus.c                   | 18 ++++++------------
 drivers/pci/host-bridge.c           |  8 ++++----
 drivers/pci/host/pci-host-generic.c |  4 ++--
 drivers/pci/host/pci-xgene.c        |  4 ++--
 drivers/pci/host/pcie-xilinx.c      |  4 ++--
 drivers/pci/probe.c                 | 10 +++++-----
 include/linux/pci.h                 |  9 ++-------
 9 files changed, 27 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index a4effd6d8f2..016991792b0 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -422,17 +422,16 @@ static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 static int pcibios_init_resources(int busnr, struct pci_sys_data *sys)
 {
 	int ret;
-	struct pci_host_bridge_window *window;
+	struct resource_entry *window;
 
 	if (list_empty(&sys->resources)) {
 		pci_add_resource_offset(&sys->resources,
 			 &iomem_resource, sys->mem_offset);
 	}
 
-	list_for_each_entry(window, &sys->resources, list) {
+	resource_list_for_each_entry(window, &sys->resources)
 		if (resource_type(window->res) == IORESOURCE_IO)
 			return 0;
-	}
 
 	sys->io_res.start = (busnr * SZ_64K) ?  : pcibios_min_io;
 	sys->io_res.end = (busnr + 1) * SZ_64K - 1;
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index f3a2cfc1412..7bcf06a7cd1 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -31,7 +31,7 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources)
 {
 	struct pci_root_info *info = x86_find_pci_root_info(bus);
 	struct pci_root_res *root_res;
-	struct pci_host_bridge_window *window;
+	struct resource_entry *window;
 	bool found = false;
 
 	if (!info)
@@ -41,7 +41,7 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources)
 	       bus);
 
 	/* already added by acpi ? */
-	list_for_each_entry(window, resources, list)
+	resource_list_for_each_entry(window, resources)
 		if (window->res->flags & IORESOURCE_BUS) {
 			found = true;
 			break;
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 8fb16188cd8..90fa3a78fb7 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -20,17 +20,16 @@
 void pci_add_resource_offset(struct list_head *resources, struct resource *res,
 			     resource_size_t offset)
 {
-	struct pci_host_bridge_window *window;
+	struct resource_entry *entry;
 
-	window = kzalloc(sizeof(struct pci_host_bridge_window), GFP_KERNEL);
-	if (!window) {
+	entry = resource_list_create_entry(res, 0);
+	if (!entry) {
 		printk(KERN_ERR "PCI: can't add host bridge window %pR\n", res);
 		return;
 	}
 
-	window->res = res;
-	window->offset = offset;
-	list_add_tail(&window->list, resources);
+	entry->offset = offset;
+	resource_list_add_tail(entry, resources);
 }
 EXPORT_SYMBOL(pci_add_resource_offset);
 
@@ -42,12 +41,7 @@ EXPORT_SYMBOL(pci_add_resource);
 
 void pci_free_resource_list(struct list_head *resources)
 {
-	struct pci_host_bridge_window *window, *tmp;
-
-	list_for_each_entry_safe(window, tmp, resources, list) {
-		list_del(&window->list);
-		kfree(window);
-	}
+	resource_list_free(resources);
 }
 EXPORT_SYMBOL(pci_free_resource_list);
 
diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c
index 0e5f3c95af5..39b2dbe585a 100644
--- a/drivers/pci/host-bridge.c
+++ b/drivers/pci/host-bridge.c
@@ -35,10 +35,10 @@ void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region,
 			     struct resource *res)
 {
 	struct pci_host_bridge *bridge = find_pci_host_bridge(bus);
-	struct pci_host_bridge_window *window;
+	struct resource_entry *window;
 	resource_size_t offset = 0;
 
-	list_for_each_entry(window, &bridge->windows, list) {
+	resource_list_for_each_entry(window, &bridge->windows) {
 		if (resource_contains(window->res, res)) {
 			offset = window->offset;
 			break;
@@ -60,10 +60,10 @@ void pcibios_bus_to_resource(struct pci_bus *bus, struct resource *res,
 			     struct pci_bus_region *region)
 {
 	struct pci_host_bridge *bridge = find_pci_host_bridge(bus);
-	struct pci_host_bridge_window *window;
+	struct resource_entry *window;
 	resource_size_t offset = 0;
 
-	list_for_each_entry(window, &bridge->windows, list) {
+	resource_list_for_each_entry(window, &bridge->windows) {
 		struct pci_bus_region bus_region;
 
 		if (resource_type(res) != resource_type(window->res))
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index 6eb1aa75bd3..aee3c620ecf 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -149,14 +149,14 @@ static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
 	struct device *dev = pci->host.dev.parent;
 	struct device_node *np = dev->of_node;
 	resource_size_t iobase;
-	struct pci_host_bridge_window *win;
+	struct resource_entry *win;
 
 	err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pci->resources,
 					       &iobase);
 	if (err)
 		return err;
 
-	list_for_each_entry(win, &pci->resources, list) {
+	resource_list_for_each_entry(win, &pci->resources) {
 		struct resource *parent, *res = win->res;
 
 		switch (resource_type(res)) {
diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c
index b1d0596457c..a704257bab7 100644
--- a/drivers/pci/host/pci-xgene.c
+++ b/drivers/pci/host/pci-xgene.c
@@ -401,11 +401,11 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port,
 				 struct list_head *res,
 				 resource_size_t io_base)
 {
-	struct pci_host_bridge_window *window;
+	struct resource_entry *window;
 	struct device *dev = port->dev;
 	int ret;
 
-	list_for_each_entry(window, res, list) {
+	resource_list_for_each_entry(window, res) {
 		struct resource *res = window->res;
 		u64 restype = resource_type(res);
 
diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c
index ef3ebaf9a73..601261df766 100644
--- a/drivers/pci/host/pcie-xilinx.c
+++ b/drivers/pci/host/pcie-xilinx.c
@@ -737,7 +737,7 @@ static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port)
 	resource_size_t offset;
 	struct of_pci_range_parser parser;
 	struct of_pci_range range;
-	struct pci_host_bridge_window *win;
+	struct resource_entry *win;
 	int err = 0, mem_resno = 0;
 
 	/* Get the ranges */
@@ -807,7 +807,7 @@ static int xilinx_pcie_parse_and_add_res(struct xilinx_pcie_port *port)
 
 free_resources:
 	release_child_resources(&iomem_resource);
-	list_for_each_entry(win, &port->resources, list)
+	resource_list_for_each_entry(win, &port->resources)
 		devm_kfree(dev, win->res);
 	pci_free_resource_list(&port->resources);
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 23212f8ae09..8d2f400e96c 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1895,7 +1895,7 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 	int error;
 	struct pci_host_bridge *bridge;
 	struct pci_bus *b, *b2;
-	struct pci_host_bridge_window *window, *n;
+	struct resource_entry *window, *n;
 	struct resource *res;
 	resource_size_t offset;
 	char bus_addr[64];
@@ -1959,8 +1959,8 @@ struct pci_bus *pci_create_root_bus(struct device *parent, int bus,
 		printk(KERN_INFO "PCI host bridge to bus %s\n", dev_name(&b->dev));
 
 	/* Add initial resources to the bus */
-	list_for_each_entry_safe(window, n, resources, list) {
-		list_move_tail(&window->list, &bridge->windows);
+	resource_list_for_each_entry_safe(window, n, resources) {
+		list_move_tail(&window->node, &bridge->windows);
 		res = window->res;
 		offset = window->offset;
 		if (res->flags & IORESOURCE_BUS)
@@ -2060,12 +2060,12 @@ void pci_bus_release_busn_res(struct pci_bus *b)
 struct pci_bus *pci_scan_root_bus(struct device *parent, int bus,
 		struct pci_ops *ops, void *sysdata, struct list_head *resources)
 {
-	struct pci_host_bridge_window *window;
+	struct resource_entry *window;
 	bool found = false;
 	struct pci_bus *b;
 	int max;
 
-	list_for_each_entry(window, resources, list)
+	resource_list_for_each_entry(window, resources)
 		if (window->res->flags & IORESOURCE_BUS) {
 			found = true;
 			break;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 9603094ed59..faa60fa2631 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -29,6 +29,7 @@
 #include <linux/atomic.h>
 #include <linux/device.h>
 #include <linux/io.h>
+#include <linux/resource_ext.h>
 #include <uapi/linux/pci.h>
 
 #include <linux/pci_ids.h>
@@ -397,16 +398,10 @@ static inline int pci_channel_offline(struct pci_dev *pdev)
 	return (pdev->error_state != pci_channel_io_normal);
 }
 
-struct pci_host_bridge_window {
-	struct list_head list;
-	struct resource *res;		/* host bridge aperture (CPU address) */
-	resource_size_t offset;		/* bus address + offset = CPU address */
-};
-
 struct pci_host_bridge {
 	struct device dev;
 	struct pci_bus *bus;		/* root bus */
-	struct list_head windows;	/* pci_host_bridge_windows */
+	struct list_head windows;	/* resource_entry */
 	void (*release_fn)(struct pci_host_bridge *);
 	void *release_data;
 };
-- 
cgit v1.2.3-70-g09d2


From ecf5636dcd59cd5508641f995cc4c2bafedbb995 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Thu, 5 Feb 2015 13:44:48 +0800
Subject: ACPI: Add interfaces to parse IOAPIC ID for IOAPIC hotplug

We need to parse APIC ID for IOAPIC registration for IOAPIC hotplug.
ACPI _MAT method and MADT table are used to figure out IOAPIC ID, just
like parsing CPU APIC ID for CPU hotplug.

[ tglx: Fixed docbook comment ]

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Len Brown <lenb@kernel.org>
Link: http://lkml.kernel.org/r/1414387308-27148-8-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/processor_core.c | 123 ++++++++++++++++++++++++++++++++++++++----
 include/linux/acpi.h          |   4 ++
 2 files changed, 118 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 02e48394276..7962651cdbd 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -4,6 +4,10 @@
  *
  *	Alex Chiang <achiang@hp.com>
  *	- Unified x86/ia64 implementations
+ *
+ * I/O APIC hotplug support
+ *	Yinghai Lu <yinghai@kernel.org>
+ *	Jiang Liu <jiang.liu@intel.com>
  */
 #include <linux/export.h>
 #include <linux/acpi.h>
@@ -12,6 +16,21 @@
 #define _COMPONENT		ACPI_PROCESSOR_COMPONENT
 ACPI_MODULE_NAME("processor_core");
 
+static struct acpi_table_madt *get_madt_table(void)
+{
+	static struct acpi_table_madt *madt;
+	static int read_madt;
+
+	if (!read_madt) {
+		if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0,
+					(struct acpi_table_header **)&madt)))
+			madt = NULL;
+		read_madt++;
+	}
+
+	return madt;
+}
+
 static int map_lapic_id(struct acpi_subtable_header *entry,
 		 u32 acpi_id, int *apic_id)
 {
@@ -67,17 +86,10 @@ static int map_lsapic_id(struct acpi_subtable_header *entry,
 static int map_madt_entry(int type, u32 acpi_id)
 {
 	unsigned long madt_end, entry;
-	static struct acpi_table_madt *madt;
-	static int read_madt;
 	int phys_id = -1;	/* CPU hardware ID */
+	struct acpi_table_madt *madt;
 
-	if (!read_madt) {
-		if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_MADT, 0,
-					(struct acpi_table_header **)&madt)))
-			madt = NULL;
-		read_madt++;
-	}
-
+	madt = get_madt_table();
 	if (!madt)
 		return phys_id;
 
@@ -203,3 +215,96 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 	return acpi_map_cpuid(phys_id, acpi_id);
 }
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+static int get_ioapic_id(struct acpi_subtable_header *entry, u32 gsi_base,
+			 u64 *phys_addr, int *ioapic_id)
+{
+	struct acpi_madt_io_apic *ioapic = (struct acpi_madt_io_apic *)entry;
+
+	if (ioapic->global_irq_base != gsi_base)
+		return 0;
+
+	*phys_addr = ioapic->address;
+	*ioapic_id = ioapic->id;
+	return 1;
+}
+
+static int parse_madt_ioapic_entry(u32 gsi_base, u64 *phys_addr)
+{
+	struct acpi_subtable_header *hdr;
+	unsigned long madt_end, entry;
+	struct acpi_table_madt *madt;
+	int apic_id = -1;
+
+	madt = get_madt_table();
+	if (!madt)
+		return apic_id;
+
+	entry = (unsigned long)madt;
+	madt_end = entry + madt->header.length;
+
+	/* Parse all entries looking for a match. */
+	entry += sizeof(struct acpi_table_madt);
+	while (entry + sizeof(struct acpi_subtable_header) < madt_end) {
+		hdr = (struct acpi_subtable_header *)entry;
+		if (hdr->type == ACPI_MADT_TYPE_IO_APIC &&
+		    get_ioapic_id(hdr, gsi_base, phys_addr, &apic_id))
+			break;
+		else
+			entry += hdr->length;
+	}
+
+	return apic_id;
+}
+
+static int parse_mat_ioapic_entry(acpi_handle handle, u32 gsi_base,
+				  u64 *phys_addr)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_subtable_header *header;
+	union acpi_object *obj;
+	int apic_id = -1;
+
+	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
+		goto exit;
+
+	if (!buffer.length || !buffer.pointer)
+		goto exit;
+
+	obj = buffer.pointer;
+	if (obj->type != ACPI_TYPE_BUFFER ||
+	    obj->buffer.length < sizeof(struct acpi_subtable_header))
+		goto exit;
+
+	header = (struct acpi_subtable_header *)obj->buffer.pointer;
+	if (header->type == ACPI_MADT_TYPE_IO_APIC)
+		get_ioapic_id(header, gsi_base, phys_addr, &apic_id);
+
+exit:
+	kfree(buffer.pointer);
+	return apic_id;
+}
+
+/**
+ * acpi_get_ioapic_id - Get IOAPIC ID and physical address matching @gsi_base
+ * @handle:	ACPI object for IOAPIC device
+ * @gsi_base:	GSI base to match with
+ * @phys_addr:	Pointer to store physical address of matching IOAPIC record
+ *
+ * Walk resources returned by ACPI_MAT method, then ACPI MADT table, to search
+ * for an ACPI IOAPIC record matching @gsi_base.
+ * Return IOAPIC id and store physical address in @phys_addr if found a match,
+ * otherwise return <0.
+ */
+int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr)
+{
+	int apic_id;
+
+	apic_id = parse_mat_ioapic_entry(handle, gsi_base, phys_addr);
+	if (apic_id == -1)
+		apic_id = parse_madt_ioapic_entry(gsi_base, phys_addr);
+
+	return apic_id;
+}
+#endif /* CONFIG_ACPI_HOTPLUG_IOAPIC */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index e53822148b6..24c7aa8b1d2 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -152,6 +152,10 @@ int acpi_map_cpu(acpi_handle handle, int physid, int *pcpu);
 int acpi_unmap_cpu(int cpu);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr);
+#endif
+
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base);
 int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base);
 int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base);
-- 
cgit v1.2.3-70-g09d2


From 7c43312af8b363b679d1e7840858ff8d204a4d91 Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 5 Feb 2015 15:20:29 +0800
Subject: ACPICA: Events: Cleanup GPE dispatcher type obtaining code

ACPICA commit 7926d5ca9452c87f866938dcea8f12e1efb58f89

There is an issue in acpi_install_gpe_handler() and acpi_remove_gpe_handler().
The code to obtain the GPE dispatcher type from the Handler->original_flags
is wrong:
    if (((Handler->original_flags & ACPI_GPE_DISPATCH_METHOD) ||
         (Handler->original_flags & ACPI_GPE_DISPATCH_NOTIFY)) &&
ACPI_GPE_DISPATCH_NOTIFY is 0x03 and ACPI_GPE_DISPATCH_METHOD is 0x02, thus
this statement is TRUE for the following dispatcher types:
    0x01 (ACPI_GPE_DISPATCH_HANDLER): not expected
    0x02 (ACPI_GPE_DISPATCH_METHOD): expected
    0x03 (ACPI_GPE_DISPATCH_NOTIFY): expected

There is no functional issue due to this because Handler->original_flags is
only set in acpi_install_gpe_handler(), and an earlier checker has excluded
the ACPI_GPE_DISPATCH_HANDLER:
    if ((gpe_event_info->Flags & ACPI_GPE_DISPATCH_MASK) ==
            ACPI_GPE_DISPATCH_HANDLER)
    {
        Status = AE_ALREADY_EXISTS;
        goto free_and_exit;
    }
    ...
    Handler->original_flags = (u8) (gpe_event_info->Flags &
        (ACPI_GPE_XRUPT_TYPE_MASK | ACPI_GPE_DISPATCH_MASK));

We need to clean this up before modifying the GPE dispatcher type values.

In order to prevent such issue from happening in the future, this patch
introduces ACPI_GPE_DISPATCH_TYPE() macro to be used to obtain the GPE
dispatcher types. Lv Zheng.

Link: https://github.com/acpica/acpica/commit/7926d5ca
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/evgpe.c     |  4 ++--
 drivers/acpi/acpica/evgpeblk.c  |  6 +++---
 drivers/acpi/acpica/evgpeinit.c |  4 ++--
 drivers/acpi/acpica/evgpeutil.c |  8 +++-----
 drivers/acpi/acpica/evxface.c   | 18 ++++++++++--------
 drivers/acpi/acpica/evxfgpe.c   |  6 +++---
 drivers/acpi/acpica/hwgpe.c     |  2 +-
 include/acpi/actypes.h          |  1 +
 8 files changed, 25 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index 4a4f41a2822..fccdfb2f73d 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -503,7 +503,7 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context)
 
 	/* Do the correct dispatch - normal method or implicit notify */
 
-	switch (gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) {
+	switch (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags)) {
 	case ACPI_GPE_DISPATCH_NOTIFY:
 		/*
 		 * Implicit notify.
@@ -707,7 +707,7 @@ acpi_ev_gpe_dispatch(struct acpi_namespace_node *gpe_device,
 	 * If there is neither a handler nor a method, leave the GPE
 	 * disabled.
 	 */
-	switch (gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) {
+	switch (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags)) {
 	case ACPI_GPE_DISPATCH_HANDLER:
 
 		/* Invoke the installed handler (at interrupt level) */
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index d86699eea33..d0a6024ae62 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -474,10 +474,10 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 			 * Ignore GPEs that have no corresponding _Lxx/_Exx method
 			 * and GPEs that are used to wake the system
 			 */
-			if (((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
+			if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 			     ACPI_GPE_DISPATCH_NONE)
-			    || ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK)
-				== ACPI_GPE_DISPATCH_HANDLER)
+			    || (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+				ACPI_GPE_DISPATCH_HANDLER)
 			    || (gpe_event_info->flags & ACPI_GPE_CAN_WAKE)) {
 				continue;
 			}
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 7be92837987..ebfd40d77d1 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -401,7 +401,7 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 		return_ACPI_STATUS(AE_OK);
 	}
 
-	if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
+	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 	    ACPI_GPE_DISPATCH_HANDLER) {
 
 		/* If there is already a handler, ignore this GPE method */
@@ -409,7 +409,7 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 		return_ACPI_STATUS(AE_OK);
 	}
 
-	if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
+	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 	    ACPI_GPE_DISPATCH_METHOD) {
 		/*
 		 * If there is already a method, ignore this method. But check
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index 3f1c5aa682a..b1978122f6a 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -324,7 +324,7 @@ acpi_ev_delete_gpe_handlers(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 								 ACPI_GPE_REGISTER_WIDTH)
 								+ j];
 
-			if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
+			if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 			    ACPI_GPE_DISPATCH_HANDLER) {
 
 				/* Delete an installed handler block */
@@ -333,10 +333,8 @@ acpi_ev_delete_gpe_handlers(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 				gpe_event_info->dispatch.handler = NULL;
 				gpe_event_info->flags &=
 				    ~ACPI_GPE_DISPATCH_MASK;
-			} else
-			    if ((gpe_event_info->
-				 flags & ACPI_GPE_DISPATCH_MASK) ==
-				ACPI_GPE_DISPATCH_NOTIFY) {
+			} else if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags)
+				   == ACPI_GPE_DISPATCH_NOTIFY) {
 
 				/* Delete the implicit notification device list */
 
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index b6b0c2341d2..61b0261dd13 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -775,7 +775,7 @@ acpi_install_gpe_handler(acpi_handle gpe_device,
 
 	/* Make sure that there isn't a handler there already */
 
-	if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
+	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 	    ACPI_GPE_DISPATCH_HANDLER) {
 		status = AE_ALREADY_EXISTS;
 		goto free_and_exit;
@@ -793,9 +793,10 @@ acpi_install_gpe_handler(acpi_handle gpe_device,
 	 * automatically during initialization, in which case it has to be
 	 * disabled now to avoid spurious execution of the handler.
 	 */
-	if (((handler->original_flags & ACPI_GPE_DISPATCH_METHOD) ||
-	     (handler->original_flags & ACPI_GPE_DISPATCH_NOTIFY)) &&
-	    gpe_event_info->runtime_count) {
+	if (((ACPI_GPE_DISPATCH_TYPE(handler->original_flags) ==
+	      ACPI_GPE_DISPATCH_METHOD) ||
+	     (ACPI_GPE_DISPATCH_TYPE(handler->original_flags) ==
+	      ACPI_GPE_DISPATCH_NOTIFY)) && gpe_event_info->runtime_count) {
 		handler->originally_enabled = TRUE;
 		(void)acpi_ev_remove_gpe_reference(gpe_event_info);
 
@@ -880,7 +881,7 @@ acpi_remove_gpe_handler(acpi_handle gpe_device,
 
 	/* Make sure that a handler is indeed installed */
 
-	if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) !=
+	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) !=
 	    ACPI_GPE_DISPATCH_HANDLER) {
 		status = AE_NOT_EXIST;
 		goto unlock_and_exit;
@@ -910,9 +911,10 @@ acpi_remove_gpe_handler(acpi_handle gpe_device,
 	 * enabled, it should be enabled at this point to restore the
 	 * post-initialization configuration.
 	 */
-	if (((handler->original_flags & ACPI_GPE_DISPATCH_METHOD) ||
-	     (handler->original_flags & ACPI_GPE_DISPATCH_NOTIFY)) &&
-	    handler->originally_enabled) {
+	if (((ACPI_GPE_DISPATCH_TYPE(handler->original_flags) ==
+	      ACPI_GPE_DISPATCH_METHOD) ||
+	     (ACPI_GPE_DISPATCH_TYPE(handler->original_flags) ==
+	      ACPI_GPE_DISPATCH_NOTIFY)) && handler->originally_enabled) {
 		(void)acpi_ev_add_gpe_reference(gpe_event_info);
 	}
 
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index c637666e717..b836139e13b 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -132,7 +132,7 @@ acpi_status acpi_enable_gpe(acpi_handle gpe_device, u32 gpe_number)
 	 */
 	gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number);
 	if (gpe_event_info) {
-		if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) !=
+		if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) !=
 		    ACPI_GPE_DISPATCH_NONE) {
 			status = acpi_ev_add_gpe_reference(gpe_event_info);
 		} else {
@@ -313,7 +313,7 @@ acpi_setup_gpe_for_wake(acpi_handle wake_device,
 	 * known as an "implicit notify". Note: The GPE is assumed to be
 	 * level-triggered (for windows compatibility).
 	 */
-	if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
+	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 	    ACPI_GPE_DISPATCH_NONE) {
 		/*
 		 * This is the first device for implicit notify on this GPE.
@@ -327,7 +327,7 @@ acpi_setup_gpe_for_wake(acpi_handle wake_device,
 	 * If we already have an implicit notify on this GPE, add
 	 * this device to the notify list.
 	 */
-	if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) ==
+	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 	    ACPI_GPE_DISPATCH_NOTIFY) {
 
 		/* Ensure that the device is not already in the list */
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index 6a955a93984..ed85fe7494a 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -225,7 +225,7 @@ acpi_hw_get_gpe_status(struct acpi_gpe_event_info * gpe_event_info,
 
 	/* GPE currently handled? */
 
-	if ((gpe_event_info->flags & ACPI_GPE_DISPATCH_MASK) !=
+	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) !=
 	    ACPI_GPE_DISPATCH_NONE) {
 		local_event_status |= ACPI_EVENT_FLAG_HAS_HANDLER;
 	}
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index bbef17368e4..401705df516 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -757,6 +757,7 @@ typedef u32 acpi_event_status;
 #define ACPI_GPE_DISPATCH_HANDLER       (u8) 0x02
 #define ACPI_GPE_DISPATCH_NOTIFY        (u8) 0x03
 #define ACPI_GPE_DISPATCH_MASK          (u8) 0x03
+#define ACPI_GPE_DISPATCH_TYPE(flags)   ((u8) ((flags) & ACPI_GPE_DISPATCH_MASK))
 
 #define ACPI_GPE_LEVEL_TRIGGERED        (u8) 0x04
 #define ACPI_GPE_EDGE_TRIGGERED         (u8) 0x00
-- 
cgit v1.2.3-70-g09d2


From 82a809419429f2e6142d2c5d88d91661f8aecb87 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Thu, 5 Feb 2015 15:20:45 +0800
Subject: ACPICA: Update Copyright headers to 2015

ACPICA commit 8990e73ab2aa15d6a0068b860ab54feff25bee36

Link: https://github.com/acpica/acpica/commit/8990e73a
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/acapps.h                             | 4 ++--
 drivers/acpi/acpica/accommon.h                           | 2 +-
 drivers/acpi/acpica/acdebug.h                            | 2 +-
 drivers/acpi/acpica/acdispat.h                           | 2 +-
 drivers/acpi/acpica/acevents.h                           | 2 +-
 drivers/acpi/acpica/acglobal.h                           | 2 +-
 drivers/acpi/acpica/achware.h                            | 2 +-
 drivers/acpi/acpica/acinterp.h                           | 2 +-
 drivers/acpi/acpica/aclocal.h                            | 2 +-
 drivers/acpi/acpica/acmacros.h                           | 2 +-
 drivers/acpi/acpica/acnamesp.h                           | 2 +-
 drivers/acpi/acpica/acobject.h                           | 2 +-
 drivers/acpi/acpica/acopcode.h                           | 2 +-
 drivers/acpi/acpica/acparser.h                           | 2 +-
 drivers/acpi/acpica/acpredef.h                           | 2 +-
 drivers/acpi/acpica/acresrc.h                            | 2 +-
 drivers/acpi/acpica/acstruct.h                           | 2 +-
 drivers/acpi/acpica/actables.h                           | 2 +-
 drivers/acpi/acpica/acutils.h                            | 2 +-
 drivers/acpi/acpica/amlcode.h                            | 2 +-
 drivers/acpi/acpica/amlresrc.h                           | 2 +-
 drivers/acpi/acpica/dsargs.c                             | 2 +-
 drivers/acpi/acpica/dscontrol.c                          | 2 +-
 drivers/acpi/acpica/dsfield.c                            | 2 +-
 drivers/acpi/acpica/dsinit.c                             | 2 +-
 drivers/acpi/acpica/dsmethod.c                           | 2 +-
 drivers/acpi/acpica/dsmthdat.c                           | 2 +-
 drivers/acpi/acpica/dsobject.c                           | 2 +-
 drivers/acpi/acpica/dsopcode.c                           | 2 +-
 drivers/acpi/acpica/dsutils.c                            | 2 +-
 drivers/acpi/acpica/dswexec.c                            | 2 +-
 drivers/acpi/acpica/dswload.c                            | 2 +-
 drivers/acpi/acpica/dswload2.c                           | 2 +-
 drivers/acpi/acpica/dswscope.c                           | 2 +-
 drivers/acpi/acpica/dswstate.c                           | 2 +-
 drivers/acpi/acpica/evevent.c                            | 2 +-
 drivers/acpi/acpica/evglock.c                            | 2 +-
 drivers/acpi/acpica/evgpe.c                              | 2 +-
 drivers/acpi/acpica/evgpeblk.c                           | 2 +-
 drivers/acpi/acpica/evgpeinit.c                          | 2 +-
 drivers/acpi/acpica/evgpeutil.c                          | 2 +-
 drivers/acpi/acpica/evhandler.c                          | 2 +-
 drivers/acpi/acpica/evmisc.c                             | 2 +-
 drivers/acpi/acpica/evregion.c                           | 2 +-
 drivers/acpi/acpica/evrgnini.c                           | 2 +-
 drivers/acpi/acpica/evsci.c                              | 2 +-
 drivers/acpi/acpica/evxface.c                            | 2 +-
 drivers/acpi/acpica/evxfevnt.c                           | 2 +-
 drivers/acpi/acpica/evxfgpe.c                            | 2 +-
 drivers/acpi/acpica/evxfregn.c                           | 2 +-
 drivers/acpi/acpica/exconfig.c                           | 2 +-
 drivers/acpi/acpica/exconvrt.c                           | 2 +-
 drivers/acpi/acpica/excreate.c                           | 2 +-
 drivers/acpi/acpica/exdebug.c                            | 2 +-
 drivers/acpi/acpica/exdump.c                             | 2 +-
 drivers/acpi/acpica/exfield.c                            | 2 +-
 drivers/acpi/acpica/exfldio.c                            | 2 +-
 drivers/acpi/acpica/exmisc.c                             | 2 +-
 drivers/acpi/acpica/exmutex.c                            | 2 +-
 drivers/acpi/acpica/exnames.c                            | 2 +-
 drivers/acpi/acpica/exoparg1.c                           | 2 +-
 drivers/acpi/acpica/exoparg2.c                           | 2 +-
 drivers/acpi/acpica/exoparg3.c                           | 2 +-
 drivers/acpi/acpica/exoparg6.c                           | 2 +-
 drivers/acpi/acpica/exprep.c                             | 2 +-
 drivers/acpi/acpica/exregion.c                           | 2 +-
 drivers/acpi/acpica/exresnte.c                           | 2 +-
 drivers/acpi/acpica/exresolv.c                           | 2 +-
 drivers/acpi/acpica/exresop.c                            | 2 +-
 drivers/acpi/acpica/exstore.c                            | 2 +-
 drivers/acpi/acpica/exstoren.c                           | 2 +-
 drivers/acpi/acpica/exstorob.c                           | 2 +-
 drivers/acpi/acpica/exsystem.c                           | 2 +-
 drivers/acpi/acpica/exutils.c                            | 2 +-
 drivers/acpi/acpica/hwacpi.c                             | 2 +-
 drivers/acpi/acpica/hwesleep.c                           | 2 +-
 drivers/acpi/acpica/hwgpe.c                              | 2 +-
 drivers/acpi/acpica/hwpci.c                              | 2 +-
 drivers/acpi/acpica/hwregs.c                             | 2 +-
 drivers/acpi/acpica/hwsleep.c                            | 2 +-
 drivers/acpi/acpica/hwtimer.c                            | 2 +-
 drivers/acpi/acpica/hwvalid.c                            | 2 +-
 drivers/acpi/acpica/hwxface.c                            | 2 +-
 drivers/acpi/acpica/hwxfsleep.c                          | 2 +-
 drivers/acpi/acpica/nsaccess.c                           | 2 +-
 drivers/acpi/acpica/nsalloc.c                            | 2 +-
 drivers/acpi/acpica/nsarguments.c                        | 2 +-
 drivers/acpi/acpica/nsconvert.c                          | 2 +-
 drivers/acpi/acpica/nsdump.c                             | 2 +-
 drivers/acpi/acpica/nsdumpdv.c                           | 2 +-
 drivers/acpi/acpica/nseval.c                             | 2 +-
 drivers/acpi/acpica/nsinit.c                             | 2 +-
 drivers/acpi/acpica/nsload.c                             | 2 +-
 drivers/acpi/acpica/nsnames.c                            | 2 +-
 drivers/acpi/acpica/nsobject.c                           | 2 +-
 drivers/acpi/acpica/nsparse.c                            | 2 +-
 drivers/acpi/acpica/nspredef.c                           | 2 +-
 drivers/acpi/acpica/nsprepkg.c                           | 2 +-
 drivers/acpi/acpica/nsrepair.c                           | 2 +-
 drivers/acpi/acpica/nsrepair2.c                          | 2 +-
 drivers/acpi/acpica/nssearch.c                           | 2 +-
 drivers/acpi/acpica/nsutils.c                            | 2 +-
 drivers/acpi/acpica/nswalk.c                             | 2 +-
 drivers/acpi/acpica/nsxfeval.c                           | 2 +-
 drivers/acpi/acpica/nsxfname.c                           | 2 +-
 drivers/acpi/acpica/nsxfobj.c                            | 2 +-
 drivers/acpi/acpica/psargs.c                             | 2 +-
 drivers/acpi/acpica/psloop.c                             | 2 +-
 drivers/acpi/acpica/psobject.c                           | 2 +-
 drivers/acpi/acpica/psopcode.c                           | 2 +-
 drivers/acpi/acpica/psopinfo.c                           | 2 +-
 drivers/acpi/acpica/psparse.c                            | 2 +-
 drivers/acpi/acpica/psscope.c                            | 2 +-
 drivers/acpi/acpica/pstree.c                             | 2 +-
 drivers/acpi/acpica/psutils.c                            | 2 +-
 drivers/acpi/acpica/pswalk.c                             | 2 +-
 drivers/acpi/acpica/psxface.c                            | 2 +-
 drivers/acpi/acpica/rsaddr.c                             | 2 +-
 drivers/acpi/acpica/rscalc.c                             | 2 +-
 drivers/acpi/acpica/rscreate.c                           | 2 +-
 drivers/acpi/acpica/rsdump.c                             | 2 +-
 drivers/acpi/acpica/rsdumpinfo.c                         | 2 +-
 drivers/acpi/acpica/rsinfo.c                             | 2 +-
 drivers/acpi/acpica/rsio.c                               | 2 +-
 drivers/acpi/acpica/rsirq.c                              | 2 +-
 drivers/acpi/acpica/rslist.c                             | 2 +-
 drivers/acpi/acpica/rsmemory.c                           | 2 +-
 drivers/acpi/acpica/rsmisc.c                             | 2 +-
 drivers/acpi/acpica/rsserial.c                           | 2 +-
 drivers/acpi/acpica/rsutils.c                            | 2 +-
 drivers/acpi/acpica/rsxface.c                            | 2 +-
 drivers/acpi/acpica/tbdata.c                             | 2 +-
 drivers/acpi/acpica/tbfadt.c                             | 2 +-
 drivers/acpi/acpica/tbfind.c                             | 2 +-
 drivers/acpi/acpica/tbinstal.c                           | 2 +-
 drivers/acpi/acpica/tbprint.c                            | 2 +-
 drivers/acpi/acpica/tbutils.c                            | 2 +-
 drivers/acpi/acpica/tbxface.c                            | 2 +-
 drivers/acpi/acpica/tbxfload.c                           | 2 +-
 drivers/acpi/acpica/tbxfroot.c                           | 2 +-
 drivers/acpi/acpica/utaddress.c                          | 2 +-
 drivers/acpi/acpica/utalloc.c                            | 2 +-
 drivers/acpi/acpica/utbuffer.c                           | 2 +-
 drivers/acpi/acpica/utcache.c                            | 2 +-
 drivers/acpi/acpica/utcopy.c                             | 2 +-
 drivers/acpi/acpica/utdebug.c                            | 2 +-
 drivers/acpi/acpica/utdecode.c                           | 2 +-
 drivers/acpi/acpica/utdelete.c                           | 2 +-
 drivers/acpi/acpica/uterror.c                            | 2 +-
 drivers/acpi/acpica/uteval.c                             | 2 +-
 drivers/acpi/acpica/utexcep.c                            | 2 +-
 drivers/acpi/acpica/utfileio.c                           | 2 +-
 drivers/acpi/acpica/utglobal.c                           | 2 +-
 drivers/acpi/acpica/uthex.c                              | 2 +-
 drivers/acpi/acpica/utids.c                              | 2 +-
 drivers/acpi/acpica/utinit.c                             | 2 +-
 drivers/acpi/acpica/utlock.c                             | 2 +-
 drivers/acpi/acpica/utmath.c                             | 2 +-
 drivers/acpi/acpica/utmisc.c                             | 2 +-
 drivers/acpi/acpica/utmutex.c                            | 2 +-
 drivers/acpi/acpica/utobject.c                           | 2 +-
 drivers/acpi/acpica/utosi.c                              | 2 +-
 drivers/acpi/acpica/utownerid.c                          | 2 +-
 drivers/acpi/acpica/utpredef.c                           | 2 +-
 drivers/acpi/acpica/utprint.c                            | 2 +-
 drivers/acpi/acpica/utresrc.c                            | 2 +-
 drivers/acpi/acpica/utstate.c                            | 2 +-
 drivers/acpi/acpica/utstring.c                           | 2 +-
 drivers/acpi/acpica/uttrack.c                            | 2 +-
 drivers/acpi/acpica/utuuid.c                             | 2 +-
 drivers/acpi/acpica/utxface.c                            | 2 +-
 drivers/acpi/acpica/utxferror.c                          | 2 +-
 drivers/acpi/acpica/utxfinit.c                           | 2 +-
 drivers/acpi/acpica/utxfmutex.c                          | 2 +-
 include/acpi/acbuffer.h                                  | 2 +-
 include/acpi/acconfig.h                                  | 2 +-
 include/acpi/acexcep.h                                   | 2 +-
 include/acpi/acnames.h                                   | 2 +-
 include/acpi/acoutput.h                                  | 2 +-
 include/acpi/acpi.h                                      | 2 +-
 include/acpi/acpiosxf.h                                  | 2 +-
 include/acpi/acpixf.h                                    | 2 +-
 include/acpi/acrestyp.h                                  | 2 +-
 include/acpi/actbl.h                                     | 2 +-
 include/acpi/actbl1.h                                    | 2 +-
 include/acpi/actbl2.h                                    | 2 +-
 include/acpi/actbl3.h                                    | 2 +-
 include/acpi/actypes.h                                   | 2 +-
 include/acpi/platform/acenv.h                            | 2 +-
 include/acpi/platform/acenvex.h                          | 2 +-
 include/acpi/platform/acgcc.h                            | 2 +-
 include/acpi/platform/aclinux.h                          | 2 +-
 include/acpi/platform/aclinuxex.h                        | 2 +-
 tools/power/acpi/common/cmfsize.c                        | 2 +-
 tools/power/acpi/common/getopt.c                         | 2 +-
 tools/power/acpi/os_specific/service_layers/oslibcfs.c   | 2 +-
 tools/power/acpi/os_specific/service_layers/oslinuxtbl.c | 2 +-
 tools/power/acpi/os_specific/service_layers/osunixdir.c  | 2 +-
 tools/power/acpi/os_specific/service_layers/osunixmap.c  | 2 +-
 tools/power/acpi/os_specific/service_layers/osunixxf.c   | 2 +-
 tools/power/acpi/tools/acpidump/acpidump.h               | 2 +-
 tools/power/acpi/tools/acpidump/apdump.c                 | 2 +-
 tools/power/acpi/tools/acpidump/apfiles.c                | 2 +-
 tools/power/acpi/tools/acpidump/apmain.c                 | 2 +-
 204 files changed, 205 insertions(+), 205 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h
index 3d2c88289da..d863016565b 100644
--- a/drivers/acpi/acpica/acapps.h
+++ b/drivers/acpi/acpica/acapps.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -47,7 +47,7 @@
 /* Common info for tool signons */
 
 #define ACPICA_NAME                 "Intel ACPI Component Architecture"
-#define ACPICA_COPYRIGHT            "Copyright (c) 2000 - 2014 Intel Corporation"
+#define ACPICA_COPYRIGHT            "Copyright (c) 2000 - 2015 Intel Corporation"
 
 #if ACPI_MACHINE_WIDTH == 64
 #define ACPI_WIDTH          "-64"
diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h
index 6f1c616910a..853aa2dbdb6 100644
--- a/drivers/acpi/acpica/accommon.h
+++ b/drivers/acpi/acpica/accommon.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 1d026ff1683..4169bb87a99 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h
index d3e2cc395d7..408f04bcaab 100644
--- a/drivers/acpi/acpica/acdispat.h
+++ b/drivers/acpi/acpica/acdispat.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index 38b94a1a5cf..228704b7865 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 7f60582d0c8..a165d25343e 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index c318d3e2789..196a5524455 100644
--- a/drivers/acpi/acpica/achware.h
+++ b/drivers/acpi/acpica/achware.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h
index b01f71ce052..1886bde54b5 100644
--- a/drivers/acpi/acpica/acinterp.h
+++ b/drivers/acpi/acpica/acinterp.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 680d23bbae7..7add32e5d8c 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index 4bceb11c738..cf607fe69db 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index ee1c040f321..952fbe0b723 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index 8abb393dafa..3e9720e1f34 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h
index dda0e6affcf..a5f17de45ac 100644
--- a/drivers/acpi/acpica/acopcode.h
+++ b/drivers/acpi/acpica/acopcode.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h
index 6168b85463e..74a390c6db1 100644
--- a/drivers/acpi/acpica/acparser.h
+++ b/drivers/acpi/acpica/acparser.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index bd3908d26c4..a972d11c97c 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h
index 4b008e8884a..efc4c7124cc 100644
--- a/drivers/acpi/acpica/acresrc.h
+++ b/drivers/acpi/acpica/acresrc.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h
index cf7346110bd..d14b547b7cd 100644
--- a/drivers/acpi/acpica/acstruct.h
+++ b/drivers/acpi/acpica/acstruct.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h
index 1afe46e44da..1c127a43017 100644
--- a/drivers/acpi/acpica/actables.h
+++ b/drivers/acpi/acpica/actables.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 486d342e74b..c2f03e8774a 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h
index 5908ccec6ae..3a95068fc11 100644
--- a/drivers/acpi/acpica/amlcode.h
+++ b/drivers/acpi/acpica/amlcode.h
@@ -7,7 +7,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h
index 3a0beeb86ba..ee0cdd60b93 100644
--- a/drivers/acpi/acpica/amlresrc.h
+++ b/drivers/acpi/acpica/amlresrc.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c
index 720b1cdda71..3e6989738e8 100644
--- a/drivers/acpi/acpica/dsargs.c
+++ b/drivers/acpi/acpica/dsargs.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index 8daf9de82b7..39da9da62bb 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index c5766619667..43b40de9048 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index aee5e45f6d3..bbe74bcebba 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index 3c7f7378b94..d72565a3c64 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsmthdat.c b/drivers/acpi/acpica/dsmthdat.c
index b67522df01a..2e4c42b377e 100644
--- a/drivers/acpi/acpica/dsmthdat.c
+++ b/drivers/acpi/acpica/dsmthdat.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index a1e7e6b6fcf..8a7b07b6adc 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index 6c0759c0db4..77244182ff0 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index 9f74795e226..e5ff89bcb3f 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index f7f5107e754..df54d46225c 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index 15623da2620..843942fb4be 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 2ac28d29730..fcaa30c611f 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c
index 9d6e2c1de1f..43b3ea40c0b 100644
--- a/drivers/acpi/acpica/dswscope.c
+++ b/drivers/acpi/acpica/dswscope.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c
index 24f7d5ea678..89ac2022465 100644
--- a/drivers/acpi/acpica/dswstate.c
+++ b/drivers/acpi/acpica/dswstate.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c
index c7bffff9ed3..bf6873f95e7 100644
--- a/drivers/acpi/acpica/evevent.c
+++ b/drivers/acpi/acpica/evevent.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c
index 3393a73ca0d..b78dc7c6d5d 100644
--- a/drivers/acpi/acpica/evglock.c
+++ b/drivers/acpi/acpica/evglock.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index fccdfb2f73d..836c79b8cd1 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index d0a6024ae62..ce2a7cf3a23 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index ebfd40d77d1..76705082b3d 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index b1978122f6a..c369b199763 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c
index 78ac29351c9..74e8595f5a2 100644
--- a/drivers/acpi/acpica/evhandler.c
+++ b/drivers/acpi/acpica/evhandler.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index 24ea3424981..f7c9dfe7b99 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 8eb8575e8c1..9abace3401f 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 1b148a440d6..da323390bb7 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c
index 29630e30382..0366703d297 100644
--- a/drivers/acpi/acpica/evsci.c
+++ b/drivers/acpi/acpica/evsci.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index 61b0261dd13..6d04ae944bd 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c
index bb8cbf5961b..df06a23c419 100644
--- a/drivers/acpi/acpica/evxfevnt.c
+++ b/drivers/acpi/acpica/evxfevnt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index b836139e13b..b8af53bce74 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index 2d6f187939c..f21afbab03f 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index 7d2949420db..6e0df2b9d5a 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c
index c545386fee9..89a976b4ccf 100644
--- a/drivers/acpi/acpica/exconvrt.c
+++ b/drivers/acpi/acpica/exconvrt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index 95d23dabcfb..aaeea4840aa 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c
index 6fbfad47518..e67d0aca3fe 100644
--- a/drivers/acpi/acpica/exdebug.c
+++ b/drivers/acpi/acpica/exdebug.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index 0f23c3f2678..7c213b6b647 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index b994845ed35..c161dd974f7 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index 1d1b27a96c5..49479927e7f 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index 2207e624f53..b56fc9d6f48 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c
index b49ea2a95f4..472030f2b5b 100644
--- a/drivers/acpi/acpica/exmutex.c
+++ b/drivers/acpi/acpica/exmutex.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index dbb03b544e8..453b00c3017 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index 1b8e9410440..77930683ab7 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c
index 2ede656ee26..fcc618aa206 100644
--- a/drivers/acpi/acpica/exoparg2.c
+++ b/drivers/acpi/acpica/exoparg2.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index 363767cf01e..b813fed95e5 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c
index 29e9e99f7fe..c930edda3f6 100644
--- a/drivers/acpi/acpica/exoparg6.c
+++ b/drivers/acpi/acpica/exoparg6.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index 118e942005e..4c2836dc825 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index cd5288a257a..0fe188e238e 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c
index ab060261b43..c7e3b929aa8 100644
--- a/drivers/acpi/acpica/exresnte.c
+++ b/drivers/acpi/acpica/exresnte.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c
index 3cde553bcbe..b6b7f3af29e 100644
--- a/drivers/acpi/acpica/exresolv.c
+++ b/drivers/acpi/acpica/exresolv.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index 3af8de3fcea..d2964af9ad4 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index daf49f7ea31..a7eee2400ce 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c
index 04bd16c08f9..3101607b4ef 100644
--- a/drivers/acpi/acpica/exstoren.c
+++ b/drivers/acpi/acpica/exstoren.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c
index fd11018b016..6fa3c8d8fc5 100644
--- a/drivers/acpi/acpica/exstorob.c
+++ b/drivers/acpi/acpica/exstorob.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c
index f7da64123ed..05450656fe3 100644
--- a/drivers/acpi/acpica/exsystem.c
+++ b/drivers/acpi/acpica/exsystem.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index d9d72dff2a7..3f4225e95d9 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c
index 1e66d960fc1..e5c5949f908 100644
--- a/drivers/acpi/acpica/hwacpi.c
+++ b/drivers/acpi/acpica/hwacpi.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c
index 858fdd6be59..e5599f61080 100644
--- a/drivers/acpi/acpica/hwesleep.c
+++ b/drivers/acpi/acpica/hwesleep.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index b7fb00d8e4c..84bc550f4f1 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwpci.c b/drivers/acpi/acpica/hwpci.c
index 6aade8e1d2a..c5214dec498 100644
--- a/drivers/acpi/acpica/hwpci.c
+++ b/drivers/acpi/acpica/hwpci.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index a4c34d2c556..3cf77afd142 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
index d590693eb54..7d21cae6d60 100644
--- a/drivers/acpi/acpica/hwsleep.c
+++ b/drivers/acpi/acpica/hwsleep.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 76ab5c1a814..675c709a300 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index 6b919127cd9..2bd33fe56cb 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 96d007df65e..5f97468df8f 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index 6921c7f3d20..3b376769882 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index f1249e3463b..24fa19a76d7 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsalloc.c b/drivers/acpi/acpica/nsalloc.c
index 607eb9e5150..e107f929d9c 100644
--- a/drivers/acpi/acpica/nsalloc.c
+++ b/drivers/acpi/acpica/nsalloc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c
index 80fcfc8c9c1..5d347a71bd0 100644
--- a/drivers/acpi/acpica/nsarguments.c
+++ b/drivers/acpi/acpica/nsarguments.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index b55642c4ee5..1a8b39c8d96 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 3d88ef4a3e0..80f097eb738 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c
index 42d37109aa5..7dc367e6fe0 100644
--- a/drivers/acpi/acpica/nsdumpdv.c
+++ b/drivers/acpi/acpica/nsdumpdv.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c
index e634a05974d..7bcc68f57af 100644
--- a/drivers/acpi/acpica/nseval.c
+++ b/drivers/acpi/acpica/nseval.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index a3fb7e4c080..4a85c451798 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index 7c9d0181f34..bd6cd4a8131 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index 7eee0a6f02f..d293d974803 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c
index a42ee9d6970..677bc9330e6 100644
--- a/drivers/acpi/acpica/nsobject.c
+++ b/drivers/acpi/acpica/nsobject.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index e83cff31754..c95a119767b 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c
index 392910ffbed..0eb54315b4b 100644
--- a/drivers/acpi/acpica/nspredef.c
+++ b/drivers/acpi/acpica/nspredef.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c
index 1b13b921dda..8b79958b7ac 100644
--- a/drivers/acpi/acpica/nsprepkg.c
+++ b/drivers/acpi/acpica/nsprepkg.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 7e417aa5c91..151fcd95ba8 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index b09e6bef72b..c30672d2387 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c
index af1cc42a8aa..4a9d4a66016 100644
--- a/drivers/acpi/acpica/nssearch.c
+++ b/drivers/acpi/acpica/nssearch.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index 4a5e3f5c0ff..6ad02008c0c 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c
index 4758a1f2ce2..c68609a2bc1 100644
--- a/drivers/acpi/acpica/nswalk.c
+++ b/drivers/acpi/acpica/nswalk.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index 4bd558bf10d..b6030a2deee 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index 8c6c11ce976..d66c326485d 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c
index 51a83298c18..793383501f8 100644
--- a/drivers/acpi/acpica/nsxfobj.c
+++ b/drivers/acpi/acpica/nsxfobj.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 314d314340a..6d038770577 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c
index b058e2390fd..90437227d79 100644
--- a/drivers/acpi/acpica/psloop.c
+++ b/drivers/acpi/acpica/psloop.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index a6885077d59..2f5ddd806c5 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c
index 1755d2ac565..1af4a405e35 100644
--- a/drivers/acpi/acpica/psopcode.c
+++ b/drivers/acpi/acpica/psopcode.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c
index 0d8d37ffd04..e18e7c47f48 100644
--- a/drivers/acpi/acpica/psopinfo.c
+++ b/drivers/acpi/acpica/psopinfo.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c
index 6d27b597394..a555f7f7b9a 100644
--- a/drivers/acpi/acpica/psparse.c
+++ b/drivers/acpi/acpica/psparse.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c
index 32d250feea2..9d669cc6cb6 100644
--- a/drivers/acpi/acpica/psscope.c
+++ b/drivers/acpi/acpica/psscope.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c
index 0b64181e772..89984f30add 100644
--- a/drivers/acpi/acpica/pstree.c
+++ b/drivers/acpi/acpica/pstree.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index 3cd48802eed..960505ab409 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c
index 9cb07e1e76d..ba5f6917128 100644
--- a/drivers/acpi/acpica/pswalk.c
+++ b/drivers/acpi/acpica/pswalk.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c
index e135acaa5e1..841a5ea0609 100644
--- a/drivers/acpi/acpica/psxface.c
+++ b/drivers/acpi/acpica/psxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c
index 94a3a057042..66d406e8fe3 100644
--- a/drivers/acpi/acpica/rsaddr.c
+++ b/drivers/acpi/acpica/rsaddr.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c
index 689556744b0..cb739a69493 100644
--- a/drivers/acpi/acpica/rscalc.c
+++ b/drivers/acpi/acpica/rscalc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rscreate.c b/drivers/acpi/acpica/rscreate.c
index 049d9c22a0f..15434e4c9b3 100644
--- a/drivers/acpi/acpica/rscreate.c
+++ b/drivers/acpi/acpica/rscreate.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsdump.c b/drivers/acpi/acpica/rsdump.c
index c3c56b5a978..1539394c8c5 100644
--- a/drivers/acpi/acpica/rsdump.c
+++ b/drivers/acpi/acpica/rsdump.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsdumpinfo.c b/drivers/acpi/acpica/rsdumpinfo.c
index 6ba7ad5faa9..b29d9ec63d1 100644
--- a/drivers/acpi/acpica/rsdumpinfo.c
+++ b/drivers/acpi/acpica/rsdumpinfo.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsinfo.c b/drivers/acpi/acpica/rsinfo.c
index 9d3f8a9a24b..edecfc67597 100644
--- a/drivers/acpi/acpica/rsinfo.c
+++ b/drivers/acpi/acpica/rsinfo.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsio.c b/drivers/acpi/acpica/rsio.c
index 19d64873290..5adba018bab 100644
--- a/drivers/acpi/acpica/rsio.c
+++ b/drivers/acpi/acpica/rsio.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsirq.c b/drivers/acpi/acpica/rsirq.c
index 3461f7db26d..07cfa70a475 100644
--- a/drivers/acpi/acpica/rsirq.c
+++ b/drivers/acpi/acpica/rsirq.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rslist.c b/drivers/acpi/acpica/rslist.c
index 77291293af6..50d5be2ee06 100644
--- a/drivers/acpi/acpica/rslist.c
+++ b/drivers/acpi/acpica/rslist.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsmemory.c b/drivers/acpi/acpica/rsmemory.c
index eab4483ff5f..c6b80862030 100644
--- a/drivers/acpi/acpica/rsmemory.c
+++ b/drivers/acpi/acpica/rsmemory.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsmisc.c b/drivers/acpi/acpica/rsmisc.c
index 41eea4bc089..1fe49d22366 100644
--- a/drivers/acpi/acpica/rsmisc.c
+++ b/drivers/acpi/acpica/rsmisc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsserial.c b/drivers/acpi/acpica/rsserial.c
index 9e8407223d9..4c8c6fe6ea7 100644
--- a/drivers/acpi/acpica/rsserial.c
+++ b/drivers/acpi/acpica/rsserial.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsutils.c b/drivers/acpi/acpica/rsutils.c
index 897a5ceb042..ece3cd60cc6 100644
--- a/drivers/acpi/acpica/rsutils.c
+++ b/drivers/acpi/acpica/rsutils.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c
index 29528789117..8e6276df022 100644
--- a/drivers/acpi/acpica/rsxface.c
+++ b/drivers/acpi/acpica/rsxface.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index f499c10ceb4..6a144957aad 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 41519a95808..7d2486005e3 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index cb947700206..0b879fcfef6 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 755b90c40dd..9bad45e63a4 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index df3bb20ea32..ef16c06e509 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 6b1ca9991b9..6559a58439c 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 0f9dd80b1cd..60e94f87f27 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index ab5308b81aa..aadb3002a2d 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 43a54af2b54..eac52cf14f1 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c
index a1acec9d2ef..1279f50da75 100644
--- a/drivers/acpi/acpica/utaddress.c
+++ b/drivers/acpi/acpica/utaddress.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c
index efac83c606d..61d8f6d186d 100644
--- a/drivers/acpi/acpica/utalloc.c
+++ b/drivers/acpi/acpica/utalloc.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index 038ea887f56..242bd071f00 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index 78fde0aac48..eacc5eee362 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index ff601c0f7c7..c37ec5035f4 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index e516254c63b..57078e3ea9b 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index 40e923e675f..988e23b7795 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c
index a3516de213f..71fce389fd4 100644
--- a/drivers/acpi/acpica/utdelete.c
+++ b/drivers/acpi/acpica/utdelete.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c
index 8e544d4688c..9ef80f2828e 100644
--- a/drivers/acpi/acpica/uterror.c
+++ b/drivers/acpi/acpica/uterror.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c
index 8fed1482d22..6c738fa0cd4 100644
--- a/drivers/acpi/acpica/uteval.c
+++ b/drivers/acpi/acpica/uteval.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utexcep.c b/drivers/acpi/acpica/utexcep.c
index 0403dcaabaf..743a0ae9fb1 100644
--- a/drivers/acpi/acpica/utexcep.c
+++ b/drivers/acpi/acpica/utexcep.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utfileio.c b/drivers/acpi/acpica/utfileio.c
index 4e263a8cc6f..7e1168be39f 100644
--- a/drivers/acpi/acpica/utfileio.c
+++ b/drivers/acpi/acpica/utfileio.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index 77ceac715f2..5e8df9177da 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c
index 9afa9441b18..aa448278ba2 100644
--- a/drivers/acpi/acpica/uthex.c
+++ b/drivers/acpi/acpica/uthex.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index 4b12880e5b1..27431cfc1c4 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c
index 77120ec9ea8..e402e07b484 100644
--- a/drivers/acpi/acpica/utinit.c
+++ b/drivers/acpi/acpica/utinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c
index dc6e96547f1..089f78bbd59 100644
--- a/drivers/acpi/acpica/utlock.c
+++ b/drivers/acpi/acpica/utlock.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utmath.c b/drivers/acpi/acpica/utmath.c
index d44dee6ee10..f9ff100f015 100644
--- a/drivers/acpi/acpica/utmath.c
+++ b/drivers/acpi/acpica/utmath.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c
index 2e2bb14e109..56bbacd576f 100644
--- a/drivers/acpi/acpica/utmisc.c
+++ b/drivers/acpi/acpica/utmisc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index 82717fff9ff..37b8b58fcd5 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c
index dfa9009bfc8..7d83efe1ea2 100644
--- a/drivers/acpi/acpica/utobject.c
+++ b/drivers/acpi/acpica/utobject.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c
index 685766fc6ca..574cd311831 100644
--- a/drivers/acpi/acpica/utosi.c
+++ b/drivers/acpi/acpica/utosi.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utownerid.c b/drivers/acpi/acpica/utownerid.c
index 36bec57ebd2..2959217067c 100644
--- a/drivers/acpi/acpica/utownerid.c
+++ b/drivers/acpi/acpica/utownerid.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c
index db30caff130..29e449935a8 100644
--- a/drivers/acpi/acpica/utpredef.c
+++ b/drivers/acpi/acpica/utpredef.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 0ce3f5a0dd6..82ca9142e10 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c
index bc1ff820c7d..b3505dbc715 100644
--- a/drivers/acpi/acpica/utresrc.c
+++ b/drivers/acpi/acpica/utresrc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utstate.c b/drivers/acpi/acpica/utstate.c
index 1cc97a752c1..8274cc16edc 100644
--- a/drivers/acpi/acpica/utstate.c
+++ b/drivers/acpi/acpica/utstate.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 6dc54b3c28b..83b6c52490d 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index 7d0ee969d78..130dd9f96f0 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c
index 4dc33130f13..c6149a21214 100644
--- a/drivers/acpi/acpica/utuuid.c
+++ b/drivers/acpi/acpica/utuuid.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index 49c873c6875..0929187bdce 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c
index 88ef77f3cf8..306e785f941 100644
--- a/drivers/acpi/acpica/utxferror.c
+++ b/drivers/acpi/acpica/utxferror.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index b1fd6886e43..083a7689188 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxfmutex.c b/drivers/acpi/acpica/utxfmutex.c
index 2a0f9e04d3a..f2606af3364 100644
--- a/drivers/acpi/acpica/utxfmutex.c
+++ b/drivers/acpi/acpica/utxfmutex.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h
index d5ec6c87810..6b040f4ddfa 100644
--- a/include/acpi/acbuffer.h
+++ b/include/acpi/acbuffer.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 5a0a3e5daf8..03aacfb3e98 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index 8b06e4c1dd5..11c3a011dcb 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index 7461327e14e..273de709495 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
index 1baae6edda8..9318a87ee39 100644
--- a/include/acpi/acoutput.h
+++ b/include/acpi/acoutput.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h
index a08e55a263c..b0bb30ebb80 100644
--- a/include/acpi/acpi.h
+++ b/include/acpi/acpi.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 03b3e6d405f..0bc78df66d4 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -7,7 +7,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 5dd21bc18ce..f81e530ae52 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h
index 0b75e01212c..ebe24263859 100644
--- a/include/acpi/acrestyp.h
+++ b/include/acpi/acrestyp.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index bee19d8170c..d4081fef109 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h
index 29e79370641..b80b0e6dabc 100644
--- a/include/acpi/actbl1.h
+++ b/include/acpi/actbl1.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index ecff62405f1..f06d75e5fa5 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h
index 5480cb2236b..440ca8104b4 100644
--- a/include/acpi/actbl3.h
+++ b/include/acpi/actbl3.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 401705df516..453cebb430f 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index 5f8cc1fa327..ad74dc51d5b 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h
index 2b612384c99..71e5ec5b07a 100644
--- a/include/acpi/platform/acenvex.h
+++ b/include/acpi/platform/acenvex.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h
index 384875da371..f54de0a6355 100644
--- a/include/acpi/platform/acgcc.h
+++ b/include/acpi/platform/acgcc.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 1ba7c190c2c..74ba46c8157 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h
index 568d4b88671..acedc3f026d 100644
--- a/include/acpi/platform/aclinuxex.h
+++ b/include/acpi/platform/aclinuxex.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c
index f4b953354ff..eec68804150 100644
--- a/tools/power/acpi/common/cmfsize.c
+++ b/tools/power/acpi/common/cmfsize.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c
index 2f0f34a36db..5da129e10aa 100644
--- a/tools/power/acpi/common/getopt.c
+++ b/tools/power/acpi/common/getopt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/oslibcfs.c b/tools/power/acpi/os_specific/service_layers/oslibcfs.c
index c13ff9c51d7..b51e40a9a12 100644
--- a/tools/power/acpi/os_specific/service_layers/oslibcfs.c
+++ b/tools/power/acpi/os_specific/service_layers/oslibcfs.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index 0dc2485dedf..92f1fd70034 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c
index 733f9e490fc..e153fcb12b1 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixdir.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c
index 99b47b6194a..3853a735044 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixmap.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c
index 7ccb073f831..6858c0893c9 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixxf.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h
index a2d37d61063..84bdef0136c 100644
--- a/tools/power/acpi/tools/acpidump/acpidump.h
+++ b/tools/power/acpi/tools/acpidump/acpidump.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index 24d32968802..c736adf5fb5 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index d470046a6d8..8f2fe168228 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index 853b4da22c3..d0ba6535f5a 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2014, Intel Corp.
+ * Copyright (C) 2000 - 2015, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
-- 
cgit v1.2.3-70-g09d2


From 121b7d91e902f19d21a669618f6b8966180e5131 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Thu, 5 Feb 2015 15:20:54 +0800
Subject: ACPICA: Update version to 20150204

ACPICA commit e06b1624b02dc8317d144e9a6fe9d684c5fa2f90

Version 20150204.

Link: https://github.com/acpica/acpica/commit/e06b1624
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index f81e530ae52..96e4ef3668d 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20141107
+#define ACPI_CA_VERSION                 0x20150204
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit v1.2.3-70-g09d2


From 0d0988af81ac809b30f818f0c0f065327ff6423b Mon Sep 17 00:00:00 2001
From: Lv Zheng <lv.zheng@intel.com>
Date: Thu, 5 Feb 2015 16:27:03 +0800
Subject: ACPICA: Events: Introduce ACPI_GPE_DISPATCH_RAW_HANDLER to fix 2
 issues for the current GPE APIs

ACPICA commit 199cad16530a45aea2bec98e528866e20c5927e1

Since whether the GPE should be disabled/enabled/cleared should only be
determined by the GPE driver's state machine:
1. GPE should be disabled if the driver wants to switch to the GPE polling
   mode when a GPE storm condition is indicated and should be enabled if
   the driver wants to switch back to the GPE interrupt mode when all of
   the storm conditions are cleared. The conditions should be protected by
   the driver's specific lock.
2. GPE should be enabled if the driver has accepted more than one request
   and should be disabled if the driver has completed all of the requests.
   The request count should be protected by the driver's specific lock.
3. GPE should be cleared either when the driver is about to handle an edge
   triggered GPE or when the driver has completed to handle a level
   triggered GPE. The handling code should be protected by the driver's
   specific lock.
Thus the GPE enabling/disabling/clearing operations are likely to be
performed with the driver's specific lock held while we currently cannot do
this. This is because:
1. We have the acpi_gbl_gpe_lock held before invoking the GPE driver's
   handler. Driver's specific lock is likely to be held inside of the
   handler, thus we can see some dead lock issues due to the reversed
   locking order or recursive locking. In order to solve such dead lock
   issues, we need to unlock the acpi_gbl_gpe_lock before invoking the
   handler. BZ 1100.
2. Since GPE disabling/enabling/clearing should be determined by the GPE
   driver's state machine, we shouldn't perform such operations inside of
   ACPICA for a GPE handler to mess up the driver's state machine. BZ 1101.

Originally this patch includes a logic to flush GPE handlers, it is dropped
due to the following reasons:
1. This is a different issue;
2. Linux OSL has fixed this by flushing SCI in acpi_os_wait_events_complete().
We will pick up this topic when the Linux OSL fix turns out to be not
sufficient.

Note that currently the internal operations and the acpi_gbl_gpe_lock are
also used by ACPI_GPE_DISPATCH_METHOD and ACPI_GPE_DISPATCH_NOTIFY. In
order not to introduce regressions, we add one
ACPI_GPE_DISPATCH_RAW_HANDLER type to be distiguished from
ACPI_GPE_DISPATCH_HANDLER. For which the acpi_gbl_gpe_lock is unlocked before
invoking the GPE handler and the internal enabling/disabling operations are
bypassed to allow drivers to perform them at a proper position using the
GPE APIs and ACPI_GPE_DISPATCH_RAW_HANDLER users should invoke acpi_set_gpe()
instead of acpi_enable_gpe()/acpi_disable_gpe() to bypass the internal GPE
clearing code in acpi_enable_gpe(). Lv Zheng.

Known issues:
1. Edge-triggered GPE lost for frequent enablings
   On some buggy silicon platforms, GPE enable line may not be directly
   wired to the GPE trigger line. In that case, when GPE enabling is
   frequently performed for edge-triggered GPEs, GPE status may stay set
   without being triggered.
   This patch may maginify this problem as it allows GPE enabling to be
   parallel performed during the process the GPEs are handled.
   This is an existing issue, because:
   1. For task context:
      Current ACPI_GPE_DISPATCH_METHOD practices have proven that this
      isn't a real issue - we can re-enable edge-triggered GPE in a work
      queue where the GPE status bit might already be set.
   2. For IRQ context:
      This can even happen when the GPE enabling occurs before returning
      from the GPE handler and after unlocking the GPE lock.
   Thus currently no code is included to protect this.

Link: https://github.com/acpica/acpica/commit/199cad16
Signed-off-by: Lv Zheng <lv.zheng@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/evgpe.c     |  52 +++++++++++++++---
 drivers/acpi/acpica/evgpeblk.c  |   2 +
 drivers/acpi/acpica/evgpeinit.c |   6 ++-
 drivers/acpi/acpica/evgpeutil.c |   6 ++-
 drivers/acpi/acpica/evxface.c   | 115 +++++++++++++++++++++++++++++++++++-----
 include/acpi/acpixf.h           |   8 +++
 include/acpi/actypes.h          |  11 ++--
 7 files changed, 171 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index 836c79b8cd1..5ed064e8673 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -332,6 +332,7 @@ u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info *gpe_xrupt_list)
 	struct acpi_gpe_register_info *gpe_register_info;
 	struct acpi_gpe_event_info *gpe_event_info;
 	u32 gpe_number;
+	struct acpi_gpe_handler_info *gpe_handler_info;
 	u32 int_status = ACPI_INTERRUPT_NOT_HANDLED;
 	u8 enabled_status_byte;
 	u32 status_reg;
@@ -455,14 +456,49 @@ u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info *gpe_xrupt_list)
 						     acpi_gbl_global_event_handler_context);
 					}
 
-					/*
-					 * Found an active GPE. Dispatch the event to a handler
-					 * or method.
-					 */
-					int_status |=
-					    acpi_ev_gpe_dispatch(gpe_device,
-								 gpe_event_info,
-								 gpe_number);
+					/* Found an active GPE */
+
+					if (ACPI_GPE_DISPATCH_TYPE
+					    (gpe_event_info->flags) ==
+					    ACPI_GPE_DISPATCH_RAW_HANDLER) {
+
+						/* Dispatch the event to a raw handler */
+
+						gpe_handler_info =
+						    gpe_event_info->dispatch.
+						    handler;
+
+						/*
+						 * There is no protection around the namespace node
+						 * and the GPE handler to ensure a safe destruction
+						 * because:
+						 * 1. The namespace node is expected to always
+						 *    exist after loading a table.
+						 * 2. The GPE handler is expected to be flushed by
+						 *    acpi_os_wait_events_complete() before the
+						 *    destruction.
+						 */
+						acpi_os_release_lock
+						    (acpi_gbl_gpe_lock, flags);
+						int_status |=
+						    gpe_handler_info->
+						    address(gpe_device,
+							    gpe_number,
+							    gpe_handler_info->
+							    context);
+						flags =
+						    acpi_os_acquire_lock
+						    (acpi_gbl_gpe_lock);
+					} else {
+						/*
+						 * Dispatch the event to a standard handler or
+						 * method.
+						 */
+						int_status |=
+						    acpi_ev_gpe_dispatch
+						    (gpe_device, gpe_event_info,
+						     gpe_number);
+					}
 				}
 			}
 		}
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index ce2a7cf3a23..e0f24c50451 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -478,6 +478,8 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 			     ACPI_GPE_DISPATCH_NONE)
 			    || (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
 				ACPI_GPE_DISPATCH_HANDLER)
+			    || (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+				ACPI_GPE_DISPATCH_RAW_HANDLER)
 			    || (gpe_event_info->flags & ACPI_GPE_CAN_WAKE)) {
 				continue;
 			}
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 76705082b3d..8840296d5b2 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -401,8 +401,10 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 		return_ACPI_STATUS(AE_OK);
 	}
 
-	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
-	    ACPI_GPE_DISPATCH_HANDLER) {
+	if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+	     ACPI_GPE_DISPATCH_HANDLER) ||
+	    (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+	     ACPI_GPE_DISPATCH_RAW_HANDLER)) {
 
 		/* If there is already a handler, ignore this GPE method */
 
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index c369b199763..3a958f3612f 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -324,8 +324,10 @@ acpi_ev_delete_gpe_handlers(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
 								 ACPI_GPE_REGISTER_WIDTH)
 								+ j];
 
-			if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
-			    ACPI_GPE_DISPATCH_HANDLER) {
+			if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+			     ACPI_GPE_DISPATCH_HANDLER) ||
+			    (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+			     ACPI_GPE_DISPATCH_RAW_HANDLER)) {
 
 				/* Delete an installed handler block */
 
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index 6d04ae944bd..81f2d9e87fa 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -51,6 +51,16 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evxface")
+#if (!ACPI_REDUCED_HARDWARE)
+/* Local prototypes */
+static acpi_status
+acpi_ev_install_gpe_handler(acpi_handle gpe_device,
+			    u32 gpe_number,
+			    u32 type,
+			    u8 is_raw_handler,
+			    acpi_gpe_handler address, void *context);
+
+#endif
 
 
 /*******************************************************************************
@@ -76,6 +86,7 @@ ACPI_MODULE_NAME("evxface")
  *              handlers.
  *
  ******************************************************************************/
+
 acpi_status
 acpi_install_notify_handler(acpi_handle device,
 			    u32 handler_type,
@@ -717,32 +728,37 @@ ACPI_EXPORT_SYMBOL(acpi_remove_fixed_event_handler)
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_install_gpe_handler
+ * FUNCTION:    acpi_ev_install_gpe_handler
  *
  * PARAMETERS:  gpe_device      - Namespace node for the GPE (NULL for FADT
  *                                defined GPEs)
  *              gpe_number      - The GPE number within the GPE block
  *              type            - Whether this GPE should be treated as an
  *                                edge- or level-triggered interrupt.
+ *              is_raw_handler  - Whether this GPE should be handled using
+ *                                the special GPE handler mode.
  *              address         - Address of the handler
  *              context         - Value passed to the handler on each GPE
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Install a handler for a General Purpose Event.
+ * DESCRIPTION: Internal function to install a handler for a General Purpose
+ *              Event.
  *
  ******************************************************************************/
-acpi_status
-acpi_install_gpe_handler(acpi_handle gpe_device,
-			 u32 gpe_number,
-			 u32 type, acpi_gpe_handler address, void *context)
+static acpi_status
+acpi_ev_install_gpe_handler(acpi_handle gpe_device,
+			    u32 gpe_number,
+			    u32 type,
+			    u8 is_raw_handler,
+			    acpi_gpe_handler address, void *context)
 {
 	struct acpi_gpe_event_info *gpe_event_info;
 	struct acpi_gpe_handler_info *handler;
 	acpi_status status;
 	acpi_cpu_flags flags;
 
-	ACPI_FUNCTION_TRACE(acpi_install_gpe_handler);
+	ACPI_FUNCTION_TRACE(ev_install_gpe_handler);
 
 	/* Parameter validation */
 
@@ -775,8 +791,10 @@ acpi_install_gpe_handler(acpi_handle gpe_device,
 
 	/* Make sure that there isn't a handler there already */
 
-	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
-	    ACPI_GPE_DISPATCH_HANDLER) {
+	if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+	     ACPI_GPE_DISPATCH_HANDLER) ||
+	    (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) ==
+	     ACPI_GPE_DISPATCH_RAW_HANDLER)) {
 		status = AE_ALREADY_EXISTS;
 		goto free_and_exit;
 	}
@@ -817,7 +835,10 @@ acpi_install_gpe_handler(acpi_handle gpe_device,
 
 	gpe_event_info->flags &=
 	    ~(ACPI_GPE_XRUPT_TYPE_MASK | ACPI_GPE_DISPATCH_MASK);
-	gpe_event_info->flags |= (u8)(type | ACPI_GPE_DISPATCH_HANDLER);
+	gpe_event_info->flags |=
+	    (u8)(type |
+		 (is_raw_handler ? ACPI_GPE_DISPATCH_RAW_HANDLER :
+		  ACPI_GPE_DISPATCH_HANDLER));
 
 	acpi_os_release_lock(acpi_gbl_gpe_lock, flags);
 
@@ -831,8 +852,76 @@ free_and_exit:
 	goto unlock_and_exit;
 }
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_install_gpe_handler
+ *
+ * PARAMETERS:  gpe_device      - Namespace node for the GPE (NULL for FADT
+ *                                defined GPEs)
+ *              gpe_number      - The GPE number within the GPE block
+ *              type            - Whether this GPE should be treated as an
+ *                                edge- or level-triggered interrupt.
+ *              address         - Address of the handler
+ *              context         - Value passed to the handler on each GPE
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Install a handler for a General Purpose Event.
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_install_gpe_handler(acpi_handle gpe_device,
+			 u32 gpe_number,
+			 u32 type, acpi_gpe_handler address, void *context)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_install_gpe_handler);
+
+	status =
+	    acpi_ev_install_gpe_handler(gpe_device, gpe_number, type, FALSE,
+					address, context);
+
+	return_ACPI_STATUS(status);
+}
+
 ACPI_EXPORT_SYMBOL(acpi_install_gpe_handler)
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_install_gpe_raw_handler
+ *
+ * PARAMETERS:  gpe_device      - Namespace node for the GPE (NULL for FADT
+ *                                defined GPEs)
+ *              gpe_number      - The GPE number within the GPE block
+ *              type            - Whether this GPE should be treated as an
+ *                                edge- or level-triggered interrupt.
+ *              address         - Address of the handler
+ *              context         - Value passed to the handler on each GPE
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Install a handler for a General Purpose Event.
+ *
+ ******************************************************************************/
+acpi_status
+acpi_install_gpe_raw_handler(acpi_handle gpe_device,
+			     u32 gpe_number,
+			     u32 type, acpi_gpe_handler address, void *context)
+{
+	acpi_status status;
+
+	ACPI_FUNCTION_TRACE(acpi_install_gpe_raw_handler);
+
+	status = acpi_ev_install_gpe_handler(gpe_device, gpe_number, type, TRUE,
+					     address, context);
+
+	return_ACPI_STATUS(status);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_install_gpe_raw_handler)
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_remove_gpe_handler
@@ -881,8 +970,10 @@ acpi_remove_gpe_handler(acpi_handle gpe_device,
 
 	/* Make sure that a handler is indeed installed */
 
-	if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) !=
-	    ACPI_GPE_DISPATCH_HANDLER) {
+	if ((ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) !=
+	     ACPI_GPE_DISPATCH_HANDLER) &&
+	    (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) !=
+	     ACPI_GPE_DISPATCH_RAW_HANDLER)) {
 		status = AE_NOT_EXIST;
 		goto unlock_and_exit;
 	}
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 96e4ef3668d..d56f5d72213 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -568,6 +568,14 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 							  acpi_gpe_handler
 							  address,
 							  void *context))
+ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
+				 acpi_install_gpe_raw_handler(acpi_handle
+							      gpe_device,
+							      u32 gpe_number,
+							      u32 type,
+							      acpi_gpe_handler
+							      address,
+							      void *context))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				 acpi_remove_gpe_handler(acpi_handle gpe_device,
 							 u32 gpe_number,
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 453cebb430f..b034f1068df 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -744,7 +744,7 @@ typedef u32 acpi_event_status;
 /*
  * GPE info flags - Per GPE
  * +-------+-+-+---+
- * |  7:4  |3|2|1:0|
+ * |  7:5  |4|3|2:0|
  * +-------+-+-+---+
  *     |    | |  |
  *     |    | |  +-- Type of dispatch:to method, handler, notify, or none
@@ -756,14 +756,15 @@ typedef u32 acpi_event_status;
 #define ACPI_GPE_DISPATCH_METHOD        (u8) 0x01
 #define ACPI_GPE_DISPATCH_HANDLER       (u8) 0x02
 #define ACPI_GPE_DISPATCH_NOTIFY        (u8) 0x03
-#define ACPI_GPE_DISPATCH_MASK          (u8) 0x03
+#define ACPI_GPE_DISPATCH_RAW_HANDLER   (u8) 0x04
+#define ACPI_GPE_DISPATCH_MASK          (u8) 0x07
 #define ACPI_GPE_DISPATCH_TYPE(flags)   ((u8) ((flags) & ACPI_GPE_DISPATCH_MASK))
 
-#define ACPI_GPE_LEVEL_TRIGGERED        (u8) 0x04
+#define ACPI_GPE_LEVEL_TRIGGERED        (u8) 0x08
 #define ACPI_GPE_EDGE_TRIGGERED         (u8) 0x00
-#define ACPI_GPE_XRUPT_TYPE_MASK        (u8) 0x04
+#define ACPI_GPE_XRUPT_TYPE_MASK        (u8) 0x08
 
-#define ACPI_GPE_CAN_WAKE               (u8) 0x08
+#define ACPI_GPE_CAN_WAKE               (u8) 0x10
 
 /*
  * Flags for GPE and Lock interfaces
-- 
cgit v1.2.3-70-g09d2


From c58da4c659803ac12eca5275c8a7064222adb4c7 Mon Sep 17 00:00:00 2001
From: Erik Kline <ek@google.com>
Date: Wed, 4 Feb 2015 20:01:23 +0900
Subject: net: ipv6: allow explicitly choosing optimistic addresses

RFC 4429 ("Optimistic DAD") states that optimistic addresses
should be treated as deprecated addresses.  From section 2.1:

   Unless noted otherwise, components of the IPv6 protocol stack
   should treat addresses in the Optimistic state equivalently to
   those in the Deprecated state, indicating that the address is
   available for use but should not be used if another suitable
   address is available.

Optimistic addresses are indeed avoided when other addresses are
available (i.e. at source address selection time), but they have
not heretofore been available for things like explicit bind() and
sendmsg() with struct in6_pktinfo, etc.

This change makes optimistic addresses treated more like
deprecated addresses than tentative ones.

Signed-off-by: Erik Kline <ek@google.com>
Acked-by: Lorenzo Colitti <lorenzo@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h |  3 +++
 net/ipv6/addrconf.c    | 19 +++++++++++++++++--
 net/ipv6/ndisc.c       |  4 +++-
 3 files changed, 23 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index d13573bb879..80456f72d70 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -62,6 +62,9 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg);
 
 int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		  const struct net_device *dev, int strict);
+int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+			    const struct net_device *dev, int strict,
+			    u32 banned_flags);
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
 int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f7c8bbeb27b..62900aee4c5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1518,16 +1518,31 @@ static int ipv6_count_addresses(struct inet6_dev *idev)
 
 int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 		  const struct net_device *dev, int strict)
+{
+	return ipv6_chk_addr_and_flags(net, addr, dev, strict, IFA_F_TENTATIVE);
+}
+EXPORT_SYMBOL(ipv6_chk_addr);
+
+int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr,
+			    const struct net_device *dev, int strict,
+			    u32 banned_flags)
 {
 	struct inet6_ifaddr *ifp;
 	unsigned int hash = inet6_addr_hash(addr);
+	u32 ifp_flags;
 
 	rcu_read_lock_bh();
 	hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) {
 		if (!net_eq(dev_net(ifp->idev->dev), net))
 			continue;
+		/* Decouple optimistic from tentative for evaluation here.
+		 * Ban optimistic addresses explicitly, when required.
+		 */
+		ifp_flags = (ifp->flags&IFA_F_OPTIMISTIC)
+			    ? (ifp->flags&~IFA_F_TENTATIVE)
+			    : ifp->flags;
 		if (ipv6_addr_equal(&ifp->addr, addr) &&
-		    !(ifp->flags&IFA_F_TENTATIVE) &&
+		    !(ifp_flags&banned_flags) &&
 		    (dev == NULL || ifp->idev->dev == dev ||
 		     !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) {
 			rcu_read_unlock_bh();
@@ -1538,7 +1553,7 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
 	rcu_read_unlock_bh();
 	return 0;
 }
-EXPORT_SYMBOL(ipv6_chk_addr);
+EXPORT_SYMBOL(ipv6_chk_addr_and_flags);
 
 static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 			       struct net_device *dev)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 682866777d5..113fc6cd5a0 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -655,7 +655,9 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
 	struct in6_addr *target = (struct in6_addr *)&neigh->primary_key;
 	int probes = atomic_read(&neigh->probes);
 
-	if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1))
+	if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr,
+					   dev, 1,
+					   IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))
 		saddr = &ipv6_hdr(skb)->saddr;
 	probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
 	if (probes < 0) {
-- 
cgit v1.2.3-70-g09d2


From 43c6116573ca0f9fc907e6b46861f2f142acb33b Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Thu, 5 Feb 2015 22:10:18 +0100
Subject: Revert "IB/core: Add support for extended query device caps"

While commit 7e36ef8205ff ("IB/core: Temporarily disable
ex_query_device uverb") is correct as it makes the extended
QUERY_DEVICE uverb (which came as part of commit 5a77abf9a97a
("IB/core: Add support for extended query device caps") and commit
860f10a799c8 ("IB/core: Add flags for on demand paging support")) not
available to userspace, it doesn't address the initial issue regarding
ib_copy_to_udata() [1][2].

Additionally, further discussions around this new uverb seems to
conclude it would require a different data structure than the one
currently described in <rdma/ib_user_verbs.h> [3].

Both of these issues require a revert of the changes, so this patch
partially reverts commit 8cdd312cfed7 ("IB/mlx5: Implement the ODP
capability query verb") and commit 860f10a799c8 ("IB/core: Add flags
for on demand paging support") and fully reverts commit 5a77abf9a97a
("IB/core: Add support for extended query device caps").

[1] "Re: [PATCH v3 06/17] IB/core: Add support for extended query device caps"
    http://mid.gmane.org/1418733236.2779.26.camel@opteya.com

[2] "Re: [PATCH] IB/core: Temporarily disable ex_query_device uverb"
    http://mid.gmane.org/1423067503.3030.83.camel@opteya.com

[3] "RE: [PATCH v1 1/5] IB/uverbs: ex_query_device: answer must not depend on request's comp_mask"
    http://mid.gmane.org/2807E5FD2F6FDA4886F6618EAC48510E0CC12C30@CRSMSX101.amr.corp.intel.com

Cc: Eli Cohen <eli@mellanox.com>
Cc: Haggai Eran <haggaie@mellanox.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/core/uverbs.h     |   1 -
 drivers/infiniband/core/uverbs_cmd.c | 137 +++++++++++------------------------
 drivers/infiniband/hw/mlx5/main.c    |   2 -
 include/rdma/ib_verbs.h              |   5 +-
 include/uapi/rdma/ib_user_verbs.h    |  27 -------
 5 files changed, 42 insertions(+), 130 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index b716b081564..643c08a025a 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -258,6 +258,5 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
 
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
-IB_UVERBS_DECLARE_EX_CMD(query_device);
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 532d8eba8b0..b7943ff16ed 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -400,52 +400,6 @@ err:
 	return ret;
 }
 
-static void copy_query_dev_fields(struct ib_uverbs_file *file,
-				  struct ib_uverbs_query_device_resp *resp,
-				  struct ib_device_attr *attr)
-{
-	resp->fw_ver		= attr->fw_ver;
-	resp->node_guid		= file->device->ib_dev->node_guid;
-	resp->sys_image_guid	= attr->sys_image_guid;
-	resp->max_mr_size	= attr->max_mr_size;
-	resp->page_size_cap	= attr->page_size_cap;
-	resp->vendor_id		= attr->vendor_id;
-	resp->vendor_part_id	= attr->vendor_part_id;
-	resp->hw_ver		= attr->hw_ver;
-	resp->max_qp		= attr->max_qp;
-	resp->max_qp_wr		= attr->max_qp_wr;
-	resp->device_cap_flags	= attr->device_cap_flags;
-	resp->max_sge		= attr->max_sge;
-	resp->max_sge_rd	= attr->max_sge_rd;
-	resp->max_cq		= attr->max_cq;
-	resp->max_cqe		= attr->max_cqe;
-	resp->max_mr		= attr->max_mr;
-	resp->max_pd		= attr->max_pd;
-	resp->max_qp_rd_atom	= attr->max_qp_rd_atom;
-	resp->max_ee_rd_atom	= attr->max_ee_rd_atom;
-	resp->max_res_rd_atom	= attr->max_res_rd_atom;
-	resp->max_qp_init_rd_atom	= attr->max_qp_init_rd_atom;
-	resp->max_ee_init_rd_atom	= attr->max_ee_init_rd_atom;
-	resp->atomic_cap		= attr->atomic_cap;
-	resp->max_ee			= attr->max_ee;
-	resp->max_rdd			= attr->max_rdd;
-	resp->max_mw			= attr->max_mw;
-	resp->max_raw_ipv6_qp		= attr->max_raw_ipv6_qp;
-	resp->max_raw_ethy_qp		= attr->max_raw_ethy_qp;
-	resp->max_mcast_grp		= attr->max_mcast_grp;
-	resp->max_mcast_qp_attach	= attr->max_mcast_qp_attach;
-	resp->max_total_mcast_qp_attach	= attr->max_total_mcast_qp_attach;
-	resp->max_ah			= attr->max_ah;
-	resp->max_fmr			= attr->max_fmr;
-	resp->max_map_per_fmr		= attr->max_map_per_fmr;
-	resp->max_srq			= attr->max_srq;
-	resp->max_srq_wr		= attr->max_srq_wr;
-	resp->max_srq_sge		= attr->max_srq_sge;
-	resp->max_pkeys			= attr->max_pkeys;
-	resp->local_ca_ack_delay	= attr->local_ca_ack_delay;
-	resp->phys_port_cnt		= file->device->ib_dev->phys_port_cnt;
-}
-
 ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 			       const char __user *buf,
 			       int in_len, int out_len)
@@ -466,7 +420,47 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 		return ret;
 
 	memset(&resp, 0, sizeof resp);
-	copy_query_dev_fields(file, &resp, &attr);
+
+	resp.fw_ver 		       = attr.fw_ver;
+	resp.node_guid 		       = file->device->ib_dev->node_guid;
+	resp.sys_image_guid 	       = attr.sys_image_guid;
+	resp.max_mr_size 	       = attr.max_mr_size;
+	resp.page_size_cap 	       = attr.page_size_cap;
+	resp.vendor_id 		       = attr.vendor_id;
+	resp.vendor_part_id 	       = attr.vendor_part_id;
+	resp.hw_ver 		       = attr.hw_ver;
+	resp.max_qp 		       = attr.max_qp;
+	resp.max_qp_wr 		       = attr.max_qp_wr;
+	resp.device_cap_flags 	       = attr.device_cap_flags;
+	resp.max_sge 		       = attr.max_sge;
+	resp.max_sge_rd 	       = attr.max_sge_rd;
+	resp.max_cq 		       = attr.max_cq;
+	resp.max_cqe 		       = attr.max_cqe;
+	resp.max_mr 		       = attr.max_mr;
+	resp.max_pd 		       = attr.max_pd;
+	resp.max_qp_rd_atom 	       = attr.max_qp_rd_atom;
+	resp.max_ee_rd_atom 	       = attr.max_ee_rd_atom;
+	resp.max_res_rd_atom 	       = attr.max_res_rd_atom;
+	resp.max_qp_init_rd_atom       = attr.max_qp_init_rd_atom;
+	resp.max_ee_init_rd_atom       = attr.max_ee_init_rd_atom;
+	resp.atomic_cap 	       = attr.atomic_cap;
+	resp.max_ee 		       = attr.max_ee;
+	resp.max_rdd 		       = attr.max_rdd;
+	resp.max_mw 		       = attr.max_mw;
+	resp.max_raw_ipv6_qp 	       = attr.max_raw_ipv6_qp;
+	resp.max_raw_ethy_qp 	       = attr.max_raw_ethy_qp;
+	resp.max_mcast_grp 	       = attr.max_mcast_grp;
+	resp.max_mcast_qp_attach       = attr.max_mcast_qp_attach;
+	resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach;
+	resp.max_ah 		       = attr.max_ah;
+	resp.max_fmr 		       = attr.max_fmr;
+	resp.max_map_per_fmr 	       = attr.max_map_per_fmr;
+	resp.max_srq 		       = attr.max_srq;
+	resp.max_srq_wr 	       = attr.max_srq_wr;
+	resp.max_srq_sge 	       = attr.max_srq_sge;
+	resp.max_pkeys 		       = attr.max_pkeys;
+	resp.local_ca_ack_delay        = attr.local_ca_ack_delay;
+	resp.phys_port_cnt	       = file->device->ib_dev->phys_port_cnt;
 
 	if (copy_to_user((void __user *) (unsigned long) cmd.response,
 			 &resp, sizeof resp))
@@ -3293,52 +3287,3 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file,
 
 	return ret ? ret : in_len;
 }
-
-int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
-			      struct ib_udata *ucore,
-			      struct ib_udata *uhw)
-{
-	struct ib_uverbs_ex_query_device_resp resp;
-	struct ib_uverbs_ex_query_device  cmd;
-	struct ib_device_attr attr;
-	struct ib_device *device;
-	int err;
-
-	device = file->device->ib_dev;
-	if (ucore->inlen < sizeof(cmd))
-		return -EINVAL;
-
-	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
-	if (err)
-		return err;
-
-	if (cmd.reserved)
-		return -EINVAL;
-
-	err = device->query_device(device, &attr);
-	if (err)
-		return err;
-
-	memset(&resp, 0, sizeof(resp));
-	copy_query_dev_fields(file, &resp.base, &attr);
-	resp.comp_mask = 0;
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (cmd.comp_mask & IB_USER_VERBS_EX_QUERY_DEVICE_ODP) {
-		resp.odp_caps.general_caps = attr.odp_caps.general_caps;
-		resp.odp_caps.per_transport_caps.rc_odp_caps =
-			attr.odp_caps.per_transport_caps.rc_odp_caps;
-		resp.odp_caps.per_transport_caps.uc_odp_caps =
-			attr.odp_caps.per_transport_caps.uc_odp_caps;
-		resp.odp_caps.per_transport_caps.ud_odp_caps =
-			attr.odp_caps.per_transport_caps.ud_odp_caps;
-		resp.comp_mask |= IB_USER_VERBS_EX_QUERY_DEVICE_ODP;
-	}
-#endif
-
-	err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
-	if (err)
-		return err;
-
-	return 0;
-}
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8a87404e9c7..03bf81211a5 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1331,8 +1331,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 		(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ)		|
 		(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ)		|
 		(1ull << IB_USER_VERBS_CMD_OPEN_QP);
-	dev->ib_dev.uverbs_ex_cmd_mask =
-		(1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE);
 
 	dev->ib_dev.query_device	= mlx5_ib_query_device;
 	dev->ib_dev.query_port		= mlx5_ib_query_port;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0d74f1de99a..65994a19e84 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1707,10 +1707,7 @@ static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t
 
 static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
 {
-	size_t copy_sz;
-
-	copy_sz = min_t(size_t, len, udata->outlen);
-	return copy_to_user(udata->outbuf, src, copy_sz) ? -EFAULT : 0;
+	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
 }
 
 /**
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 4275b961bf6..867cc5084af 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -90,7 +90,6 @@ enum {
 };
 
 enum {
-	IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE,
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
 	IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
 };
@@ -202,32 +201,6 @@ struct ib_uverbs_query_device_resp {
 	__u8  reserved[4];
 };
 
-enum {
-	IB_USER_VERBS_EX_QUERY_DEVICE_ODP =		1ULL << 0,
-};
-
-struct ib_uverbs_ex_query_device {
-	__u32 comp_mask;
-	__u32 reserved;
-};
-
-struct ib_uverbs_odp_caps {
-	__u64 general_caps;
-	struct {
-		__u32 rc_odp_caps;
-		__u32 uc_odp_caps;
-		__u32 ud_odp_caps;
-	} per_transport_caps;
-	__u32 reserved;
-};
-
-struct ib_uverbs_ex_query_device_resp {
-	struct ib_uverbs_query_device_resp base;
-	__u32 comp_mask;
-	__u32 reserved;
-	struct ib_uverbs_odp_caps odp_caps;
-};
-
 struct ib_uverbs_query_port {
 	__u64 response;
 	__u8  port_num;
-- 
cgit v1.2.3-70-g09d2


From 6bbc7fed849597ec35ffdcaf677910dd11d71d08 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 30 Jan 2015 12:27:43 +0100
Subject: ALSA: Add a helper to add a new attribute group to card

For assigning sysfs entries for a card device from the driver,
introduce a new helper function, snd_card_add_dev_attr().  In this
way, we can avoid the possible race between the device registration
and the sysfs addition / removal.

The driver can pass a new attribute group to add freely.  This has to
be called before snd_card_register().

Currently, up to two extra groups can be added.  More than that, it'll
return an error.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/core.h |  3 +++
 sound/core/init.c    | 31 +++++++++++++++++++++++++------
 2 files changed, 28 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/sound/core.h b/include/sound/core.h
index 58882bfacdd..da574828996 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -132,6 +132,7 @@ struct snd_card {
 	struct completion *release_completion;
 	struct device *dev;		/* device assigned to this card */
 	struct device card_dev;		/* cardX object for sysfs */
+	const struct attribute_group *dev_groups[4]; /* assigned sysfs attr */
 	bool registered;		/* card_dev is registered? */
 
 #ifdef CONFIG_PM
@@ -262,6 +263,8 @@ void snd_card_set_id(struct snd_card *card, const char *id);
 int snd_card_register(struct snd_card *card);
 int snd_card_info_init(void);
 int snd_card_info_done(void);
+int snd_card_add_dev_attr(struct snd_card *card,
+			  const struct attribute_group *group);
 int snd_component_add(struct snd_card *card, const char *component);
 int snd_card_file_add(struct snd_card *card, struct file *file);
 int snd_card_file_remove(struct snd_card *card, struct file *file);
diff --git a/sound/core/init.c b/sound/core/init.c
index 96194599e82..35419054821 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -181,7 +181,7 @@ void snd_device_initialize(struct device *dev, struct snd_card *card)
 EXPORT_SYMBOL_GPL(snd_device_initialize);
 
 static int snd_card_do_free(struct snd_card *card);
-static const struct attribute_group *card_dev_attr_groups[];
+static const struct attribute_group card_dev_attr_group;
 
 static void release_card_device(struct device *dev)
 {
@@ -269,7 +269,8 @@ int snd_card_new(struct device *parent, int idx, const char *xid,
 	card->card_dev.parent = parent;
 	card->card_dev.class = sound_class;
 	card->card_dev.release = release_card_device;
-	card->card_dev.groups = card_dev_attr_groups;
+	card->card_dev.groups = card->dev_groups;
+	card->dev_groups[0] = &card_dev_attr_group;
 	err = kobject_set_name(&card->card_dev.kobj, "card%d", idx);
 	if (err < 0)
 		goto __error;
@@ -700,14 +701,32 @@ static struct attribute *card_dev_attrs[] = {
 	NULL
 };
 
-static struct attribute_group card_dev_attr_group = {
+static const struct attribute_group card_dev_attr_group = {
 	.attrs	= card_dev_attrs,
 };
 
-static const struct attribute_group *card_dev_attr_groups[] = {
-	&card_dev_attr_group,
-	NULL
+/**
+ * snd_card_add_dev_attr - Append a new sysfs attribute group to card
+ * @card: card instance
+ * @group: attribute group to append
+ */
+int snd_card_add_dev_attr(struct snd_card *card,
+			  const struct attribute_group *group)
+{
+	int i;
+
+	/* loop for (arraysize-1) here to keep NULL at the last entry */
+	for (i = 0; i < ARRAY_SIZE(card->dev_groups) - 1; i++) {
+		if (!card->dev_groups[i]) {
+			card->dev_groups[i] = group;
+			return 0;
+		}
+	}
+
+	dev_err(card->dev, "Too many groups assigned\n");
+	return -ENOSPC;
 };
+EXPORT_SYMBOL_GPL(snd_card_add_dev_attr);
 
 /**
  *  snd_card_register - register the soundcard
-- 
cgit v1.2.3-70-g09d2


From a05d59a5673339ef6936d6940cdf68172ce75b9f Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 6 Feb 2015 14:30:50 -0500
Subject: tracing: Add condition check to RCU lockdep checks

The trace_tlb_flush() tracepoint can be called when a CPU is going offline.
When a CPU is offline, RCU is no longer watching that CPU and since the
tracepoint is protected by RCU, it must not be called. To prevent the
tlb_flush tracepoint from being called when the CPU is offline, it was
converted to a TRACE_EVENT_CONDITION where the condition checks if the
CPU is online before calling the tracepoint.

Unfortunately, this was not enough to stop lockdep from complaining about
it. Even though the RCU protected code of the tracepoint will never be
called, the condition is hidden within the tracepoint, and even though the
condition prevents RCU code from being called, the lockdep checks are
outside the tracepoint (this is to test tracepoints even when they are not
enabled).

Even though tracepoints should be checked to be RCU safe when they are not
enabled, the condition should still be considered when checking RCU.

Link: http://lkml.kernel.org/r/CA+icZUUGiGDoL5NU8RuxKzFjoLjEKRtUWx=JB8B9a0EQv-eGzQ@mail.gmail.com

Fixes: 3a630178fd5f "tracing: generate RCU warnings even when tracepoints are disabled"
Cc: stable@vger.kernel.org # 3.18+
Acked-by: Dave Hansen <dave@sr71.net>
Reported-by: Sedat Dilek <sedat.dilek@gmail.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/tracepoint.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index e08e21e5f60..c72851328ca 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -173,7 +173,7 @@ extern void syscall_unregfunc(void);
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),,);			\
-		if (IS_ENABLED(CONFIG_LOCKDEP)) {			\
+		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			rcu_read_lock_sched_notrace();			\
 			rcu_dereference_sched(__tracepoint_##name.funcs);\
 			rcu_read_unlock_sched_notrace();		\
-- 
cgit v1.2.3-70-g09d2


From 6c8465a82a605bc692304bab42703017dcfff013 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 6 Feb 2015 14:18:19 -0500
Subject: x86/tlb/trace: Do not trace on CPU that is offline

When taking a CPU down for suspend and resume, a tracepoint may be called
when the CPU has been designated offline. As tracepoints require RCU for
protection, they must not be called if the current CPU is offline.

Unfortunately, trace_tlb_flush() is called in this scenario as was noted
by LOCKDEP:

...

 Disabling non-boot CPUs ...
 intel_pstate CPU 1 exiting

 ===============================
 smpboot: CPU 1 didn't die...
 [ INFO: suspicious RCU usage. ]
 3.19.0-rc7-next-20150204.1-iniza-small #1 Not tainted
 -------------------------------
 include/trace/events/tlb.h:35 suspicious rcu_dereference_check() usage!

 other info that might help us debug this:

 RCU used illegally from offline CPU!
 rcu_scheduler_active = 1, debug_locks = 0
 no locks held by swapper/1/0.

 stack backtrace:
 CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.19.0-rc7-next-20150204.1-iniza-small #1
 Hardware name: SAMSUNG ELECTRONICS CO., LTD. 530U3BI/530U4BI/530U4BH/530U3BI/530U4BI/530U4BH, BIOS 13XK 03/28/2013
  0000000000000001 ffff88011a44fe18 ffffffff817e370d 0000000000000011
  ffff88011a448290 ffff88011a44fe48 ffffffff810d6847 ffff8800c66b9600
  0000000000000001 ffff88011a44c000 ffffffff81cb3900 ffff88011a44fe78
 Call Trace:
  [<ffffffff817e370d>] dump_stack+0x4c/0x65
  [<ffffffff810d6847>] lockdep_rcu_suspicious+0xe7/0x120
  [<ffffffff810b71a5>] idle_task_exit+0x205/0x2c0
  [<ffffffff81054c4e>] play_dead_common+0xe/0x50
  [<ffffffff81054ca5>] native_play_dead+0x15/0x140
  [<ffffffff8102963f>] arch_cpu_idle_dead+0xf/0x20
  [<ffffffff810cd89e>] cpu_startup_entry+0x37e/0x580
  [<ffffffff81053e20>] start_secondary+0x140/0x150
 intel_pstate CPU 2 exiting

...

By converting the tlb_flush tracepoint to a TRACE_EVENT_CONDITION where the
condition is cpu_online(smp_processor_id()), we can avoid calling RCU protected
code when the CPU is offline.

Link: http://lkml.kernel.org/r/CA+icZUUGiGDoL5NU8RuxKzFjoLjEKRtUWx=JB8B9a0EQv-eGzQ@mail.gmail.com

Cc: stable@vger.kernel.org # 3.17+
Fixes: d17d8f9dedb9 "x86/mm: Add tracepoints for TLB flushes"
Reported-by: Sedat Dilek <sedat.dilek@gmail.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Hansen <dave@sr71.net>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/tlb.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h
index 13391d28810..0e763576515 100644
--- a/include/trace/events/tlb.h
+++ b/include/trace/events/tlb.h
@@ -13,11 +13,13 @@
 	{ TLB_LOCAL_SHOOTDOWN,		"local shootdown" },		\
 	{ TLB_LOCAL_MM_SHOOTDOWN,	"local mm shootdown" }
 
-TRACE_EVENT(tlb_flush,
+TRACE_EVENT_CONDITION(tlb_flush,
 
 	TP_PROTO(int reason, unsigned long pages),
 	TP_ARGS(reason, pages),
 
+	TP_CONDITION(cpu_online(smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(	  int, reason)
 		__field(unsigned long,  pages)
-- 
cgit v1.2.3-70-g09d2


From 83d2b9ba1abca241df44a502b6da950a25856b5b Mon Sep 17 00:00:00 2001
From: Jarno Rajahalme <jrajahalme@nicira.com>
Date: Thu, 5 Feb 2015 13:40:49 -0800
Subject: net: openvswitch: Support masked set actions.

OVS userspace already probes the openvswitch kernel module for
OVS_ACTION_ATTR_SET_MASKED support.  This patch adds the kernel module
implementation of masked set actions.

The existing set action sets many fields at once.  When only a subset
of the IP header fields, for example, should be modified, all the IP
fields need to be exact matched so that the other field values can be
copied to the set action.  A masked set action allows modification of
an arbitrary subset of the supported header bits without requiring the
rest to be matched.

Masked set action is now supported for all writeable key types, except
for the tunnel key.  The set tunnel action is an exception as any
input tunnel info is cleared before action processing starts, so there
is no tunnel info to mask.

The kernel module converts all (non-tunnel) set actions to masked set
actions.  This makes action processing more uniform, and results in
less branching and duplicating the action processing code.  When
returning actions to userspace, the fully masked set actions are
converted back to normal set actions.  We use a kernel internal action
code to be able to tell the userspace provided and converted masked
set actions apart.

Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/openvswitch.h |  22 ++-
 net/openvswitch/actions.c        | 373 ++++++++++++++++++++++++---------------
 net/openvswitch/flow_netlink.c   | 161 +++++++++++++----
 3 files changed, 383 insertions(+), 173 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 7a8785a9924..bbd49a0c46c 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -599,6 +599,12 @@ struct ovs_action_hash {
  * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header.  The
  * single nested %OVS_KEY_ATTR_* attribute specifies a header to modify and its
  * value.
+ * @OVS_ACTION_ATTR_SET_MASKED: Replaces the contents of an existing header.  A
+ * nested %OVS_KEY_ATTR_* attribute specifies a header to modify, its value,
+ * and a mask.  For every bit set in the mask, the corresponding bit value
+ * is copied from the value to the packet header field, rest of the bits are
+ * left unchanged.  The non-masked value bits must be passed in as zeroes.
+ * Masking is not supported for the %OVS_KEY_ATTR_TUNNEL attribute.
  * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q header onto the
  * packet.
  * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet.
@@ -617,6 +623,9 @@ struct ovs_action_hash {
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
  * type may not be changed.
+ *
+ * @OVS_ACTION_ATTR_SET_TO_MASKED: Kernel internal masked set action translated
+ * from the @OVS_ACTION_ATTR_SET.
  */
 
 enum ovs_action_attr {
@@ -631,8 +640,19 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_HASH,	      /* struct ovs_action_hash. */
 	OVS_ACTION_ATTR_PUSH_MPLS,    /* struct ovs_action_push_mpls. */
 	OVS_ACTION_ATTR_POP_MPLS,     /* __be16 ethertype. */
+	OVS_ACTION_ATTR_SET_MASKED,   /* One nested OVS_KEY_ATTR_* including
+				       * data immediately followed by a mask.
+				       * The data must be zero for the unmasked
+				       * bits. */
+
+	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
+				       * from userspace. */
 
-	__OVS_ACTION_ATTR_MAX
+#ifdef __KERNEL__
+	OVS_ACTION_ATTR_SET_TO_MASKED, /* Kernel module internal masked
+					* set action converted from
+					* OVS_ACTION_ATTR_SET. */
+#endif
 };
 
 #define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1)
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index b4cffe68612..b491c1c296f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -185,10 +185,15 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	return 0;
 }
 
-static int set_mpls(struct sk_buff *skb, struct sw_flow_key *key,
-		    const __be32 *mpls_lse)
+/* 'KEY' must not have any bits set outside of the 'MASK' */
+#define MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK)))
+#define SET_MASKED(OLD, KEY, MASK) ((OLD) = MASKED(OLD, KEY, MASK))
+
+static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const __be32 *mpls_lse, const __be32 *mask)
 {
 	__be32 *stack;
+	__be32 lse;
 	int err;
 
 	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
@@ -196,14 +201,16 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 		return err;
 
 	stack = (__be32 *)skb_mpls_header(skb);
+	lse = MASKED(*stack, *mpls_lse, *mask);
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		__be32 diff[] = { ~(*stack), *mpls_lse };
+		__be32 diff[] = { ~(*stack), lse };
+
 		skb->csum = ~csum_partial((char *)diff, sizeof(diff),
 					  ~skb->csum);
 	}
 
-	*stack = *mpls_lse;
-	key->mpls.top_lse = *mpls_lse;
+	*stack = lse;
+	flow_key->mpls.top_lse = lse;
 	return 0;
 }
 
@@ -230,23 +237,39 @@ static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 			     ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
 }
 
-static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *key,
-			const struct ovs_key_ethernet *eth_key)
+/* 'src' is already properly masked. */
+static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
+{
+	u16 *dst = (u16 *)dst_;
+	const u16 *src = (const u16 *)src_;
+	const u16 *mask = (const u16 *)mask_;
+
+	SET_MASKED(dst[0], src[0], mask[0]);
+	SET_MASKED(dst[1], src[1], mask[1]);
+	SET_MASKED(dst[2], src[2], mask[2]);
+}
+
+static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
+			const struct ovs_key_ethernet *key,
+			const struct ovs_key_ethernet *mask)
 {
 	int err;
+
 	err = skb_ensure_writable(skb, ETH_HLEN);
 	if (unlikely(err))
 		return err;
 
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
-	ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
-	ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
+	ether_addr_copy_masked(eth_hdr(skb)->h_source, key->eth_src,
+			       mask->eth_src);
+	ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
+			       mask->eth_dst);
 
 	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
-	ether_addr_copy(key->eth.src, eth_key->eth_src);
-	ether_addr_copy(key->eth.dst, eth_key->eth_dst);
+	ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);
+	ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);
 	return 0;
 }
 
@@ -304,6 +327,15 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
 	}
 }
 
+static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4],
+			   const __be32 mask[4], __be32 masked[4])
+{
+	masked[0] = MASKED(old[0], addr[0], mask[0]);
+	masked[1] = MASKED(old[1], addr[1], mask[1]);
+	masked[2] = MASKED(old[2], addr[2], mask[2]);
+	masked[3] = MASKED(old[3], addr[3], mask[3]);
+}
+
 static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 			  __be32 addr[4], const __be32 new_addr[4],
 			  bool recalculate_csum)
@@ -315,29 +347,29 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 	memcpy(addr, new_addr, sizeof(__be32[4]));
 }
 
-static void set_ipv6_tc(struct ipv6hdr *nh, u8 tc)
+static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
 {
-	nh->priority = tc >> 4;
-	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0x0F) | ((tc & 0x0F) << 4);
+	/* Bits 21-24 are always unmasked, so this retains their values. */
+	SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
+	SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
+	SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
 }
 
-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl)
+static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
+		       u8 mask)
 {
-	nh->flow_lbl[0] = (nh->flow_lbl[0] & 0xF0) | (fl & 0x000F0000) >> 16;
-	nh->flow_lbl[1] = (fl & 0x0000FF00) >> 8;
-	nh->flow_lbl[2] = fl & 0x000000FF;
-}
+	new_ttl = MASKED(nh->ttl, new_ttl, mask);
 
-static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
-{
 	csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
 	nh->ttl = new_ttl;
 }
 
-static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *key,
-		    const struct ovs_key_ipv4 *ipv4_key)
+static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const struct ovs_key_ipv4 *key,
+		    const struct ovs_key_ipv4 *mask)
 {
 	struct iphdr *nh;
+	__be32 new_addr;
 	int err;
 
 	err = skb_ensure_writable(skb, skb_network_offset(skb) +
@@ -347,36 +379,49 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *key,
 
 	nh = ip_hdr(skb);
 
-	if (ipv4_key->ipv4_src != nh->saddr) {
-		set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
-		key->ipv4.addr.src = ipv4_key->ipv4_src;
-	}
+	/* Setting an IP addresses is typically only a side effect of
+	 * matching on them in the current userspace implementation, so it
+	 * makes sense to check if the value actually changed.
+	 */
+	if (mask->ipv4_src) {
+		new_addr = MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src);
 
-	if (ipv4_key->ipv4_dst != nh->daddr) {
-		set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
-		key->ipv4.addr.dst = ipv4_key->ipv4_dst;
+		if (unlikely(new_addr != nh->saddr)) {
+			set_ip_addr(skb, nh, &nh->saddr, new_addr);
+			flow_key->ipv4.addr.src = new_addr;
+		}
 	}
+	if (mask->ipv4_dst) {
+		new_addr = MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst);
 
-	if (ipv4_key->ipv4_tos != nh->tos) {
-		ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
-		key->ip.tos = nh->tos;
+		if (unlikely(new_addr != nh->daddr)) {
+			set_ip_addr(skb, nh, &nh->daddr, new_addr);
+			flow_key->ipv4.addr.dst = new_addr;
+		}
 	}
-
-	if (ipv4_key->ipv4_ttl != nh->ttl) {
-		set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
-		key->ip.ttl = ipv4_key->ipv4_ttl;
+	if (mask->ipv4_tos) {
+		ipv4_change_dsfield(nh, ~mask->ipv4_tos, key->ipv4_tos);
+		flow_key->ip.tos = nh->tos;
+	}
+	if (mask->ipv4_ttl) {
+		set_ip_ttl(skb, nh, key->ipv4_ttl, mask->ipv4_ttl);
+		flow_key->ip.ttl = nh->ttl;
 	}
 
 	return 0;
 }
 
-static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *key,
-		    const struct ovs_key_ipv6 *ipv6_key)
+static bool is_ipv6_mask_nonzero(const __be32 addr[4])
+{
+	return !!(addr[0] | addr[1] | addr[2] | addr[3]);
+}
+
+static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const struct ovs_key_ipv6 *key,
+		    const struct ovs_key_ipv6 *mask)
 {
 	struct ipv6hdr *nh;
 	int err;
-	__be32 *saddr;
-	__be32 *daddr;
 
 	err = skb_ensure_writable(skb, skb_network_offset(skb) +
 				  sizeof(struct ipv6hdr));
@@ -384,71 +429,77 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *key,
 		return err;
 
 	nh = ipv6_hdr(skb);
-	saddr = (__be32 *)&nh->saddr;
-	daddr = (__be32 *)&nh->daddr;
-
-	if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src))) {
-		set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr,
-			      ipv6_key->ipv6_src, true);
-		memcpy(&key->ipv6.addr.src, ipv6_key->ipv6_src,
-		       sizeof(ipv6_key->ipv6_src));
-	}
 
-	if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) {
+	/* Setting an IP addresses is typically only a side effect of
+	 * matching on them in the current userspace implementation, so it
+	 * makes sense to check if the value actually changed.
+	 */
+	if (is_ipv6_mask_nonzero(mask->ipv6_src)) {
+		__be32 *saddr = (__be32 *)&nh->saddr;
+		__be32 masked[4];
+
+		mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
+
+		if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
+			set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+				      true);
+			memcpy(&flow_key->ipv6.addr.src, masked,
+			       sizeof(flow_key->ipv6.addr.src));
+		}
+	}
+	if (is_ipv6_mask_nonzero(mask->ipv6_dst)) {
 		unsigned int offset = 0;
 		int flags = IP6_FH_F_SKIP_RH;
 		bool recalc_csum = true;
-
-		if (ipv6_ext_hdr(nh->nexthdr))
-			recalc_csum = ipv6_find_hdr(skb, &offset,
-						    NEXTHDR_ROUTING, NULL,
-						    &flags) != NEXTHDR_ROUTING;
-
-		set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr,
-			      ipv6_key->ipv6_dst, recalc_csum);
-		memcpy(&key->ipv6.addr.dst, ipv6_key->ipv6_dst,
-		       sizeof(ipv6_key->ipv6_dst));
+		__be32 *daddr = (__be32 *)&nh->daddr;
+		__be32 masked[4];
+
+		mask_ipv6_addr(daddr, key->ipv6_dst, mask->ipv6_dst, masked);
+
+		if (unlikely(memcmp(daddr, masked, sizeof(masked)))) {
+			if (ipv6_ext_hdr(nh->nexthdr))
+				recalc_csum = (ipv6_find_hdr(skb, &offset,
+							     NEXTHDR_ROUTING,
+							     NULL, &flags)
+					       != NEXTHDR_ROUTING);
+
+			set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+				      recalc_csum);
+			memcpy(&flow_key->ipv6.addr.dst, masked,
+			       sizeof(flow_key->ipv6.addr.dst));
+		}
+	}
+	if (mask->ipv6_tclass) {
+		ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
+		flow_key->ip.tos = ipv6_get_dsfield(nh);
+	}
+	if (mask->ipv6_label) {
+		set_ipv6_fl(nh, ntohl(key->ipv6_label),
+			    ntohl(mask->ipv6_label));
+		flow_key->ipv6.label =
+		    *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
+	}
+	if (mask->ipv6_hlimit) {
+		SET_MASKED(nh->hop_limit, key->ipv6_hlimit, mask->ipv6_hlimit);
+		flow_key->ip.ttl = nh->hop_limit;
 	}
-
-	set_ipv6_tc(nh, ipv6_key->ipv6_tclass);
-	key->ip.tos = ipv6_get_dsfield(nh);
-
-	set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label));
-	key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
-
-	nh->hop_limit = ipv6_key->ipv6_hlimit;
-	key->ip.ttl = ipv6_key->ipv6_hlimit;
 	return 0;
 }
 
 /* Must follow skb_ensure_writable() since that can move the skb data. */
 static void set_tp_port(struct sk_buff *skb, __be16 *port,
-			 __be16 new_port, __sum16 *check)
+			__be16 new_port, __sum16 *check)
 {
 	inet_proto_csum_replace2(check, skb, *port, new_port, 0);
 	*port = new_port;
-	skb_clear_hash(skb);
-}
-
-static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
-{
-	struct udphdr *uh = udp_hdr(skb);
-
-	if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
-		set_tp_port(skb, port, new_port, &uh->check);
-
-		if (!uh->check)
-			uh->check = CSUM_MANGLED_0;
-	} else {
-		*port = new_port;
-		skb_clear_hash(skb);
-	}
 }
 
-static int set_udp(struct sk_buff *skb, struct sw_flow_key *key,
-		   const struct ovs_key_udp *udp_port_key)
+static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		   const struct ovs_key_udp *key,
+		   const struct ovs_key_udp *mask)
 {
 	struct udphdr *uh;
+	__be16 src, dst;
 	int err;
 
 	err = skb_ensure_writable(skb, skb_transport_offset(skb) +
@@ -457,23 +508,40 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *key,
 		return err;
 
 	uh = udp_hdr(skb);
-	if (udp_port_key->udp_src != uh->source) {
-		set_udp_port(skb, &uh->source, udp_port_key->udp_src);
-		key->tp.src = udp_port_key->udp_src;
-	}
+	/* Either of the masks is non-zero, so do not bother checking them. */
+	src = MASKED(uh->source, key->udp_src, mask->udp_src);
+	dst = MASKED(uh->dest, key->udp_dst, mask->udp_dst);
 
-	if (udp_port_key->udp_dst != uh->dest) {
-		set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
-		key->tp.dst = udp_port_key->udp_dst;
+	if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
+		if (likely(src != uh->source)) {
+			set_tp_port(skb, &uh->source, src, &uh->check);
+			flow_key->tp.src = src;
+		}
+		if (likely(dst != uh->dest)) {
+			set_tp_port(skb, &uh->dest, dst, &uh->check);
+			flow_key->tp.dst = dst;
+		}
+
+		if (unlikely(!uh->check))
+			uh->check = CSUM_MANGLED_0;
+	} else {
+		uh->source = src;
+		uh->dest = dst;
+		flow_key->tp.src = src;
+		flow_key->tp.dst = dst;
 	}
 
+	skb_clear_hash(skb);
+
 	return 0;
 }
 
-static int set_tcp(struct sk_buff *skb, struct sw_flow_key *key,
-		   const struct ovs_key_tcp *tcp_port_key)
+static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		   const struct ovs_key_tcp *key,
+		   const struct ovs_key_tcp *mask)
 {
 	struct tcphdr *th;
+	__be16 src, dst;
 	int err;
 
 	err = skb_ensure_writable(skb, skb_transport_offset(skb) +
@@ -482,50 +550,49 @@ static int set_tcp(struct sk_buff *skb, struct sw_flow_key *key,
 		return err;
 
 	th = tcp_hdr(skb);
-	if (tcp_port_key->tcp_src != th->source) {
-		set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check);
-		key->tp.src = tcp_port_key->tcp_src;
+	src = MASKED(th->source, key->tcp_src, mask->tcp_src);
+	if (likely(src != th->source)) {
+		set_tp_port(skb, &th->source, src, &th->check);
+		flow_key->tp.src = src;
 	}
-
-	if (tcp_port_key->tcp_dst != th->dest) {
-		set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
-		key->tp.dst = tcp_port_key->tcp_dst;
+	dst = MASKED(th->dest, key->tcp_dst, mask->tcp_dst);
+	if (likely(dst != th->dest)) {
+		set_tp_port(skb, &th->dest, dst, &th->check);
+		flow_key->tp.dst = dst;
 	}
+	skb_clear_hash(skb);
 
 	return 0;
 }
 
-static int set_sctp(struct sk_buff *skb, struct sw_flow_key *key,
-		    const struct ovs_key_sctp *sctp_port_key)
+static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+		    const struct ovs_key_sctp *key,
+		    const struct ovs_key_sctp *mask)
 {
+	unsigned int sctphoff = skb_transport_offset(skb);
 	struct sctphdr *sh;
+	__le32 old_correct_csum, new_csum, old_csum;
 	int err;
-	unsigned int sctphoff = skb_transport_offset(skb);
 
 	err = skb_ensure_writable(skb, sctphoff + sizeof(struct sctphdr));
 	if (unlikely(err))
 		return err;
 
 	sh = sctp_hdr(skb);
-	if (sctp_port_key->sctp_src != sh->source ||
-	    sctp_port_key->sctp_dst != sh->dest) {
-		__le32 old_correct_csum, new_csum, old_csum;
+	old_csum = sh->checksum;
+	old_correct_csum = sctp_compute_cksum(skb, sctphoff);
 
-		old_csum = sh->checksum;
-		old_correct_csum = sctp_compute_cksum(skb, sctphoff);
+	sh->source = MASKED(sh->source, key->sctp_src, mask->sctp_src);
+	sh->dest = MASKED(sh->dest, key->sctp_dst, mask->sctp_dst);
 
-		sh->source = sctp_port_key->sctp_src;
-		sh->dest = sctp_port_key->sctp_dst;
+	new_csum = sctp_compute_cksum(skb, sctphoff);
 
-		new_csum = sctp_compute_cksum(skb, sctphoff);
+	/* Carry any checksum errors through. */
+	sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
 
-		/* Carry any checksum errors through. */
-		sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
-
-		skb_clear_hash(skb);
-		key->tp.src = sctp_port_key->sctp_src;
-		key->tp.dst = sctp_port_key->sctp_dst;
-	}
+	skb_clear_hash(skb);
+	flow_key->tp.src = sh->source;
+	flow_key->tp.dst = sh->dest;
 
 	return 0;
 }
@@ -653,52 +720,77 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
 	key->ovs_flow_hash = hash;
 }
 
-static int execute_set_action(struct sk_buff *skb, struct sw_flow_key *key,
-			      const struct nlattr *nested_attr)
+static int execute_set_action(struct sk_buff *skb,
+			      struct sw_flow_key *flow_key,
+			      const struct nlattr *a)
+{
+	/* Only tunnel set execution is supported without a mask. */
+	if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) {
+		OVS_CB(skb)->egress_tun_info = nla_data(a);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+/* Mask is at the midpoint of the data. */
+#define get_mask(a, type) ((const type)nla_data(a) + 1)
+
+static int execute_masked_set_action(struct sk_buff *skb,
+				     struct sw_flow_key *flow_key,
+				     const struct nlattr *a)
 {
 	int err = 0;
 
-	switch (nla_type(nested_attr)) {
+	switch (nla_type(a)) {
 	case OVS_KEY_ATTR_PRIORITY:
-		skb->priority = nla_get_u32(nested_attr);
-		key->phy.priority = skb->priority;
+		SET_MASKED(skb->priority, nla_get_u32(a), *get_mask(a, u32 *));
+		flow_key->phy.priority = skb->priority;
 		break;
 
 	case OVS_KEY_ATTR_SKB_MARK:
-		skb->mark = nla_get_u32(nested_attr);
-		key->phy.skb_mark = skb->mark;
+		SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *));
+		flow_key->phy.skb_mark = skb->mark;
 		break;
 
 	case OVS_KEY_ATTR_TUNNEL_INFO:
-		OVS_CB(skb)->egress_tun_info = nla_data(nested_attr);
+		/* Masked data not supported for tunnel. */
+		err = -EINVAL;
 		break;
 
 	case OVS_KEY_ATTR_ETHERNET:
-		err = set_eth_addr(skb, key, nla_data(nested_attr));
+		err = set_eth_addr(skb, flow_key, nla_data(a),
+				   get_mask(a, struct ovs_key_ethernet *));
 		break;
 
 	case OVS_KEY_ATTR_IPV4:
-		err = set_ipv4(skb, key, nla_data(nested_attr));
+		err = set_ipv4(skb, flow_key, nla_data(a),
+			       get_mask(a, struct ovs_key_ipv4 *));
 		break;
 
 	case OVS_KEY_ATTR_IPV6:
-		err = set_ipv6(skb, key, nla_data(nested_attr));
+		err = set_ipv6(skb, flow_key, nla_data(a),
+			       get_mask(a, struct ovs_key_ipv6 *));
 		break;
 
 	case OVS_KEY_ATTR_TCP:
-		err = set_tcp(skb, key, nla_data(nested_attr));
+		err = set_tcp(skb, flow_key, nla_data(a),
+			      get_mask(a, struct ovs_key_tcp *));
 		break;
 
 	case OVS_KEY_ATTR_UDP:
-		err = set_udp(skb, key, nla_data(nested_attr));
+		err = set_udp(skb, flow_key, nla_data(a),
+			      get_mask(a, struct ovs_key_udp *));
 		break;
 
 	case OVS_KEY_ATTR_SCTP:
-		err = set_sctp(skb, key, nla_data(nested_attr));
+		err = set_sctp(skb, flow_key, nla_data(a),
+			       get_mask(a, struct ovs_key_sctp *));
 		break;
 
 	case OVS_KEY_ATTR_MPLS:
-		err = set_mpls(skb, key, nla_data(nested_attr));
+		err = set_mpls(skb, flow_key, nla_data(a), get_mask(a,
+								    __be32 *));
 		break;
 	}
 
@@ -818,6 +910,11 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			err = execute_set_action(skb, key, nla_data(a));
 			break;
 
+		case OVS_ACTION_ATTR_SET_MASKED:
+		case OVS_ACTION_ATTR_SET_TO_MASKED:
+			err = execute_masked_set_action(skb, key, nla_data(a));
+			break;
+
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = sample(dp, skb, key, a);
 			break;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 8b9a612b39d..993281e6278 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1695,16 +1695,6 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 	return 0;
 }
 
-static int validate_tp_port(const struct sw_flow_key *flow_key,
-			    __be16 eth_type)
-{
-	if ((eth_type == htons(ETH_P_IP) || eth_type == htons(ETH_P_IPV6)) &&
-	    (flow_key->tp.src || flow_key->tp.dst))
-		return 0;
-
-	return -EINVAL;
-}
-
 void ovs_match_init(struct sw_flow_match *match,
 		    struct sw_flow_key *key,
 		    struct sw_flow_mask *mask)
@@ -1805,23 +1795,45 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	return err;
 }
 
+/* Return false if there are any non-masked bits set.
+ * Mask follows data immediately, before any netlink padding.
+ */
+static bool validate_masked(u8 *data, int len)
+{
+	u8 *mask = data + len;
+
+	while (len--)
+		if (*data++ & ~*mask++)
+			return false;
+
+	return true;
+}
+
 static int validate_set(const struct nlattr *a,
 			const struct sw_flow_key *flow_key,
 			struct sw_flow_actions **sfa,
-			bool *set_tun, __be16 eth_type, bool log)
+			bool *skip_copy, __be16 eth_type, bool masked, bool log)
 {
 	const struct nlattr *ovs_key = nla_data(a);
 	int key_type = nla_type(ovs_key);
+	size_t key_len;
 
 	/* There can be only one key in a action */
 	if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
 		return -EINVAL;
 
+	key_len = nla_len(ovs_key);
+	if (masked)
+		key_len /= 2;
+
 	if (key_type > OVS_KEY_ATTR_MAX ||
-	    (ovs_key_lens[key_type].len != nla_len(ovs_key) &&
+	    (ovs_key_lens[key_type].len != key_len &&
 	     ovs_key_lens[key_type].len != OVS_ATTR_NESTED))
 		return -EINVAL;
 
+	if (masked && !validate_masked(nla_data(ovs_key), key_len))
+		return -EINVAL;
+
 	switch (key_type) {
 	const struct ovs_key_ipv4 *ipv4_key;
 	const struct ovs_key_ipv6 *ipv6_key;
@@ -1836,7 +1848,10 @@ static int validate_set(const struct nlattr *a,
 		if (eth_p_mpls(eth_type))
 			return -EINVAL;
 
-		*set_tun = true;
+		if (masked)
+			return -EINVAL; /* Masked tunnel set not supported. */
+
+		*skip_copy = true;
 		err = validate_and_copy_set_tun(a, sfa, log);
 		if (err)
 			return err;
@@ -1846,48 +1861,66 @@ static int validate_set(const struct nlattr *a,
 		if (eth_type != htons(ETH_P_IP))
 			return -EINVAL;
 
-		if (!flow_key->ip.proto)
-			return -EINVAL;
-
 		ipv4_key = nla_data(ovs_key);
-		if (ipv4_key->ipv4_proto != flow_key->ip.proto)
-			return -EINVAL;
 
-		if (ipv4_key->ipv4_frag != flow_key->ip.frag)
-			return -EINVAL;
+		if (masked) {
+			const struct ovs_key_ipv4 *mask = ipv4_key + 1;
 
+			/* Non-writeable fields. */
+			if (mask->ipv4_proto || mask->ipv4_frag)
+				return -EINVAL;
+		} else {
+			if (ipv4_key->ipv4_proto != flow_key->ip.proto)
+				return -EINVAL;
+
+			if (ipv4_key->ipv4_frag != flow_key->ip.frag)
+				return -EINVAL;
+		}
 		break;
 
 	case OVS_KEY_ATTR_IPV6:
 		if (eth_type != htons(ETH_P_IPV6))
 			return -EINVAL;
 
-		if (!flow_key->ip.proto)
-			return -EINVAL;
-
 		ipv6_key = nla_data(ovs_key);
-		if (ipv6_key->ipv6_proto != flow_key->ip.proto)
-			return -EINVAL;
 
-		if (ipv6_key->ipv6_frag != flow_key->ip.frag)
-			return -EINVAL;
+		if (masked) {
+			const struct ovs_key_ipv6 *mask = ipv6_key + 1;
+
+			/* Non-writeable fields. */
+			if (mask->ipv6_proto || mask->ipv6_frag)
+				return -EINVAL;
+
+			/* Invalid bits in the flow label mask? */
+			if (ntohl(mask->ipv6_label) & 0xFFF00000)
+				return -EINVAL;
+		} else {
+			if (ipv6_key->ipv6_proto != flow_key->ip.proto)
+				return -EINVAL;
 
+			if (ipv6_key->ipv6_frag != flow_key->ip.frag)
+				return -EINVAL;
+		}
 		if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
 			return -EINVAL;
 
 		break;
 
 	case OVS_KEY_ATTR_TCP:
-		if (flow_key->ip.proto != IPPROTO_TCP)
+		if ((eth_type != htons(ETH_P_IP) &&
+		     eth_type != htons(ETH_P_IPV6)) ||
+		    flow_key->ip.proto != IPPROTO_TCP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key, eth_type);
+		break;
 
 	case OVS_KEY_ATTR_UDP:
-		if (flow_key->ip.proto != IPPROTO_UDP)
+		if ((eth_type != htons(ETH_P_IP) &&
+		     eth_type != htons(ETH_P_IPV6)) ||
+		    flow_key->ip.proto != IPPROTO_UDP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key, eth_type);
+		break;
 
 	case OVS_KEY_ATTR_MPLS:
 		if (!eth_p_mpls(eth_type))
@@ -1895,15 +1928,45 @@ static int validate_set(const struct nlattr *a,
 		break;
 
 	case OVS_KEY_ATTR_SCTP:
-		if (flow_key->ip.proto != IPPROTO_SCTP)
+		if ((eth_type != htons(ETH_P_IP) &&
+		     eth_type != htons(ETH_P_IPV6)) ||
+		    flow_key->ip.proto != IPPROTO_SCTP)
 			return -EINVAL;
 
-		return validate_tp_port(flow_key, eth_type);
+		break;
 
 	default:
 		return -EINVAL;
 	}
 
+	/* Convert non-masked non-tunnel set actions to masked set actions. */
+	if (!masked && key_type != OVS_KEY_ATTR_TUNNEL) {
+		int start, len = key_len * 2;
+		struct nlattr *at;
+
+		*skip_copy = true;
+
+		start = add_nested_action_start(sfa,
+						OVS_ACTION_ATTR_SET_TO_MASKED,
+						log);
+		if (start < 0)
+			return start;
+
+		at = __add_action(sfa, key_type, NULL, len, log);
+		if (IS_ERR(at))
+			return PTR_ERR(at);
+
+		memcpy(nla_data(at), nla_data(ovs_key), key_len); /* Key. */
+		memset(nla_data(at) + key_len, 0xff, key_len);    /* Mask. */
+		/* Clear non-writeable bits from otherwise writeable fields. */
+		if (key_type == OVS_KEY_ATTR_IPV6) {
+			struct ovs_key_ipv6 *mask = nla_data(at) + key_len;
+
+			mask->ipv6_label &= htonl(0x000FFFFF);
+		}
+		add_nested_action_end(*sfa, start);
+	}
+
 	return 0;
 }
 
@@ -1965,6 +2028,7 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr,
 			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
 			[OVS_ACTION_ATTR_POP_VLAN] = 0,
 			[OVS_ACTION_ATTR_SET] = (u32)-1,
+			[OVS_ACTION_ATTR_SET_MASKED] = (u32)-1,
 			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
 			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash)
 		};
@@ -2060,7 +2124,14 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr,
 
 		case OVS_ACTION_ATTR_SET:
 			err = validate_set(a, key, sfa,
-					   &skip_copy, eth_type, log);
+					   &skip_copy, eth_type, false, log);
+			if (err)
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_SET_MASKED:
+			err = validate_set(a, key, sfa,
+					   &skip_copy, eth_type, true, log);
 			if (err)
 				return err;
 			break;
@@ -2090,6 +2161,7 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr,
 	return 0;
 }
 
+/* 'key' must be the masked key. */
 int ovs_nla_copy_actions(const struct nlattr *attr,
 			 const struct sw_flow_key *key,
 			 struct sw_flow_actions **sfa, bool log)
@@ -2177,6 +2249,21 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 	return 0;
 }
 
+static int masked_set_action_to_set_action_attr(const struct nlattr *a,
+						struct sk_buff *skb)
+{
+	const struct nlattr *ovs_key = nla_data(a);
+	size_t key_len = nla_len(ovs_key) / 2;
+
+	/* Revert the conversion we did from a non-masked set action to
+	 * masked set action.
+	 */
+	if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a) - key_len, ovs_key))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
 {
 	const struct nlattr *a;
@@ -2192,6 +2279,12 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
 				return err;
 			break;
 
+		case OVS_ACTION_ATTR_SET_TO_MASKED:
+			err = masked_set_action_to_set_action_attr(a, skb);
+			if (err)
+				return err;
+			break;
+
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = sample_action_to_attr(a, skb);
 			if (err)
-- 
cgit v1.2.3-70-g09d2


From 032ee4236954eb214651cb9bfc1b38ffa8fd7a01 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 6 Feb 2015 16:04:38 -0500
Subject: tcp: helpers to mitigate ACK loops by rate-limiting out-of-window
 dupacks

Helpers for mitigating ACK loops by rate-limiting dupacks sent in
response to incoming out-of-window packets.

This patch includes:

- rate-limiting logic
- sysctl to control how often we allow dupacks to out-of-window packets
- SNMP counter for cases where we rate-limited our dupack sending

The rate-limiting logic in this patch decides to not send dupacks in
response to out-of-window segments if (a) they are SYNs or pure ACKs
and (b) the remote endpoint is sending them faster than the configured
rate limit.

We rate-limit our responses rather than blocking them entirely or
resetting the connection, because legitimate connections can rely on
dupacks in response to some out-of-window segments. For example, zero
window probes are typically sent with a sequence number that is below
the current window, and ZWPs thus expect to thus elicit a dupack in
response.

We allow dupacks in response to TCP segments with data, because these
may be spurious retransmissions for which the remote endpoint wants to
receive DSACKs. This is safe because segments with data can't
realistically be part of ACK loops, which by their nature consist of
each side sending pure/data-less ACKs to each other.

The dupack interval is controlled by a new sysctl knob,
tcp_invalid_ratelimit, given in milliseconds, in case an administrator
needs to dial this upward in the face of a high-rate DoS attack. The
name and units are chosen to be analogous to the existing analogous
knob for ICMP, icmp_ratelimit.

The default value for tcp_invalid_ratelimit is 500ms, which allows at
most one such dupack per 500ms. This is chosen to be 2x faster than
the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule
2.4). We allow the extra 2x factor because network delay variations
can cause packets sent at 1 second intervals to be compressed and
arrive much closer.

Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 22 ++++++++++++++++++++++
 include/net/tcp.h                      | 32 ++++++++++++++++++++++++++++++++
 include/uapi/linux/snmp.h              |  6 ++++++
 net/ipv4/proc.c                        |  6 ++++++
 net/ipv4/sysctl_net_ipv4.c             |  7 +++++++
 net/ipv4/tcp_input.c                   |  1 +
 6 files changed, 74 insertions(+)

(limited to 'include')

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a5e4c813f17..1b8c964b0d1 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -290,6 +290,28 @@ tcp_frto - INTEGER
 
 	By default it's enabled with a non-zero value. 0 disables F-RTO.
 
+tcp_invalid_ratelimit - INTEGER
+	Limit the maximal rate for sending duplicate acknowledgments
+	in response to incoming TCP packets that are for an existing
+	connection but that are invalid due to any of these reasons:
+
+	  (a) out-of-window sequence number,
+	  (b) out-of-window acknowledgment number, or
+	  (c) PAWS (Protection Against Wrapped Sequence numbers) check failure
+
+	This can help mitigate simple "ack loop" DoS attacks, wherein
+	a buggy or malicious middlebox or man-in-the-middle can
+	rewrite TCP header fields in manner that causes each endpoint
+	to think that the other is sending invalid TCP segments, thus
+	causing each side to send an unterminating stream of duplicate
+	acknowledgments for invalid segments.
+
+	Using 0 disables rate-limiting of dupacks in response to
+	invalid segments; otherwise this value specifies the minimal
+	space between sending such dupacks, in milliseconds.
+
+	Default: 500 (milliseconds).
+
 tcp_keepalive_time - INTEGER
 	How often TCP sends out keepalive messages when keepalive is enabled.
 	Default: 2hours.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 28e9bd3abce..b81f45c67b2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -274,6 +274,7 @@ extern int sysctl_tcp_challenge_ack_limit;
 extern unsigned int sysctl_tcp_notsent_lowat;
 extern int sysctl_tcp_min_tso_segs;
 extern int sysctl_tcp_autocorking;
+extern int sysctl_tcp_invalid_ratelimit;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -1236,6 +1237,37 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
 	return true;
 }
 
+/* Return true if we're currently rate-limiting out-of-window ACKs and
+ * thus shouldn't send a dupack right now. We rate-limit dupacks in
+ * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
+ * attacks that send repeated SYNs or ACKs for the same connection. To
+ * do this, we do not send a duplicate SYNACK or ACK if the remote
+ * endpoint is sending out-of-window SYNs or pure ACKs at a high rate.
+ */
+static inline bool tcp_oow_rate_limited(struct net *net,
+					const struct sk_buff *skb,
+					int mib_idx, u32 *last_oow_ack_time)
+{
+	/* Data packets without SYNs are not likely part of an ACK loop. */
+	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
+	    !tcp_hdr(skb)->syn)
+		goto not_rate_limited;
+
+	if (*last_oow_ack_time) {
+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+			NET_INC_STATS_BH(net, mib_idx);
+			return true;	/* rate-limited: don't send yet! */
+		}
+	}
+
+	*last_oow_ack_time = tcp_time_stamp;
+
+not_rate_limited:
+	return false;	/* not rate-limited: go ahead, send dupack now! */
+}
+
 static inline void tcp_mib_init(struct net *net)
 {
 	/* See RFC 2012 */
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index b2222410001..6a6fb747c78 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -270,6 +270,12 @@ enum
 	LINUX_MIB_TCPHYSTARTTRAINCWND,		/* TCPHystartTrainCwnd */
 	LINUX_MIB_TCPHYSTARTDELAYDETECT,	/* TCPHystartDelayDetect */
 	LINUX_MIB_TCPHYSTARTDELAYCWND,		/* TCPHystartDelayCwnd */
+	LINUX_MIB_TCPACKSKIPPEDSYNRECV,		/* TCPACKSkippedSynRecv */
+	LINUX_MIB_TCPACKSKIPPEDPAWS,		/* TCPACKSkippedPAWS */
+	LINUX_MIB_TCPACKSKIPPEDSEQ,		/* TCPACKSkippedSeq */
+	LINUX_MIB_TCPACKSKIPPEDFINWAIT2,	/* TCPACKSkippedFinWait2 */
+	LINUX_MIB_TCPACKSKIPPEDTIMEWAIT,	/* TCPACKSkippedTimeWait */
+	LINUX_MIB_TCPACKSKIPPEDCHALLENGE,	/* TCPACKSkippedChallenge */
 	__LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8f9cd200ce2..d8953ef0770 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -292,6 +292,12 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPHystartTrainCwnd", LINUX_MIB_TCPHYSTARTTRAINCWND),
 	SNMP_MIB_ITEM("TCPHystartDelayDetect", LINUX_MIB_TCPHYSTARTDELAYDETECT),
 	SNMP_MIB_ITEM("TCPHystartDelayCwnd", LINUX_MIB_TCPHYSTARTDELAYCWND),
+	SNMP_MIB_ITEM("TCPACKSkippedSynRecv", LINUX_MIB_TCPACKSKIPPEDSYNRECV),
+	SNMP_MIB_ITEM("TCPACKSkippedPAWS", LINUX_MIB_TCPACKSKIPPEDPAWS),
+	SNMP_MIB_ITEM("TCPACKSkippedSeq", LINUX_MIB_TCPACKSKIPPEDSEQ),
+	SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2),
+	SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT),
+	SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e0ee384a448..82601a68cf9 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -728,6 +728,13 @@ static struct ctl_table ipv4_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+	{
+		.procname	= "tcp_invalid_ratelimit",
+		.data		= &sysctl_tcp_invalid_ratelimit,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_ms_jiffies,
+	},
 	{
 		.procname	= "icmp_msgs_per_sec",
 		.data		= &sysctl_icmp_msgs_per_sec,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d3dfff78fa1..9401aa43b81 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -100,6 +100,7 @@ int sysctl_tcp_thin_dupack __read_mostly;
 
 int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
 int sysctl_tcp_early_retrans __read_mostly = 3;
+int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 
 #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
 #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
-- 
cgit v1.2.3-70-g09d2


From a9b2c06dbef48ed31cff1764c5ce824829106f4f Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 6 Feb 2015 16:04:39 -0500
Subject: tcp: mitigate ACK loops for connections as tcp_request_sock

In the SYN_RECV state, where the TCP connection is represented by
tcp_request_sock, we now rate-limit SYNACKs in response to a client's
retransmitted SYNs: we do not send a SYNACK in response to client SYN
if it has been less than sysctl_tcp_invalid_ratelimit (default 500ms)
since we last sent a SYNACK in response to a client's retransmitted
SYN.

This allows the vast majority of legitimate client connections to
proceed unimpeded, even for the most aggressive platforms, iOS and
MacOS, which actually retransmit SYNs 1-second intervals for several
times in a row. They use SYN RTO timeouts following the progression:
1,1,1,1,1,2,4,8,16,32.

Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      | 1 +
 include/net/tcp.h        | 1 +
 net/ipv4/tcp_minisocks.c | 6 +++++-
 3 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 67309ece077..bcc828d3b9b 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -115,6 +115,7 @@ struct tcp_request_sock {
 	u32				rcv_isn;
 	u32				snt_isn;
 	u32				snt_synack; /* synack sent time */
+	u32				last_oow_ack_time; /* last SYNACK */
 	u32				rcv_nxt; /* the ack # by SYNACK. For
 						  * FastOpen it's the seq#
 						  * after data-in-SYN.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b81f45c67b2..da4196fb78d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1145,6 +1145,7 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
 	tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 	tcp_rsk(req)->snt_synack = tcp_time_stamp;
+	tcp_rsk(req)->last_oow_ack_time = 0;
 	req->mss = rx_opt->mss_clamp;
 	req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
 	ireq->tstamp_ok = rx_opt->tstamp_ok;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index bc9216dc9de..131aa4950d1 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -605,7 +605,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		 * Reset timer after retransmitting SYNACK, similar to
 		 * the idea of fast retransmit in recovery.
 		 */
-		if (!inet_rtx_syn_ack(sk, req))
+		if (!tcp_oow_rate_limited(sock_net(sk), skb,
+					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
+					  &tcp_rsk(req)->last_oow_ack_time) &&
+
+		    !inet_rtx_syn_ack(sk, req))
 			req->expires = min(TCP_TIMEOUT_INIT << req->num_timeout,
 					   TCP_RTO_MAX) + jiffies;
 		return NULL;
-- 
cgit v1.2.3-70-g09d2


From f2b2c582e82429270d5818fbabe653f4359d7024 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 6 Feb 2015 16:04:40 -0500
Subject: tcp: mitigate ACK loops for connections as tcp_sock

Ensure that in state ESTABLISHED, where the connection is represented
by a tcp_sock, we rate limit dupacks in response to incoming packets
(a) with TCP timestamps that fail PAWS checks, or (b) with sequence
numbers or ACK numbers that are out of the acceptable window.

We do not send a dupack in response to out-of-window packets if it has
been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we
last sent a dupack in response to an out-of-window packet.

There is already a similar (although global) rate-limiting mechanism
for "challenge ACKs". When deciding whether to send a challence ACK,
we first consult the new per-connection rate limit, and then the
global rate limit.

Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      |  1 +
 net/ipv4/tcp_input.c     | 29 ++++++++++++++++++++++-------
 net/ipv4/tcp_minisocks.c |  1 +
 3 files changed, 24 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index bcc828d3b9b..66d85a80a1e 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -153,6 +153,7 @@ struct tcp_sock {
  	u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
 	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
 	u32	lsndtime;	/* timestamp of last sent data packet (for restart window) */
+	u32	last_oow_ack_time;  /* timestamp of last out-of-window ACK */
 
 	u32	tsoffset;	/* timestamp offset */
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9401aa43b81..8fdd27b1730 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3322,13 +3322,22 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
 }
 
 /* RFC 5961 7 [ACK Throttling] */
-static void tcp_send_challenge_ack(struct sock *sk)
+static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 {
 	/* unprotected vars, we dont care of overwrites */
 	static u32 challenge_timestamp;
 	static unsigned int challenge_count;
-	u32 now = jiffies / HZ;
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 now;
+
+	/* First check our per-socket dupack rate limit. */
+	if (tcp_oow_rate_limited(sock_net(sk), skb,
+				 LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
+				 &tp->last_oow_ack_time))
+		return;
 
+	/* Then check the check host-wide RFC 5961 rate limit. */
+	now = jiffies / HZ;
 	if (now != challenge_timestamp) {
 		challenge_timestamp = now;
 		challenge_count = 0;
@@ -3424,7 +3433,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (before(ack, prior_snd_una)) {
 		/* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */
 		if (before(ack, prior_snd_una - tp->max_window)) {
-			tcp_send_challenge_ack(sk);
+			tcp_send_challenge_ack(sk, skb);
 			return -1;
 		}
 		goto old_ack;
@@ -4993,7 +5002,10 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	    tcp_paws_discard(sk, skb)) {
 		if (!th->rst) {
 			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
-			tcp_send_dupack(sk, skb);
+			if (!tcp_oow_rate_limited(sock_net(sk), skb,
+						  LINUX_MIB_TCPACKSKIPPEDPAWS,
+						  &tp->last_oow_ack_time))
+				tcp_send_dupack(sk, skb);
 			goto discard;
 		}
 		/* Reset is accepted even if it did not pass PAWS. */
@@ -5010,7 +5022,10 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		if (!th->rst) {
 			if (th->syn)
 				goto syn_challenge;
-			tcp_send_dupack(sk, skb);
+			if (!tcp_oow_rate_limited(sock_net(sk), skb,
+						  LINUX_MIB_TCPACKSKIPPEDSEQ,
+						  &tp->last_oow_ack_time))
+				tcp_send_dupack(sk, skb);
 		}
 		goto discard;
 	}
@@ -5026,7 +5041,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt)
 			tcp_reset(sk);
 		else
-			tcp_send_challenge_ack(sk);
+			tcp_send_challenge_ack(sk, skb);
 		goto discard;
 	}
 
@@ -5040,7 +5055,7 @@ syn_challenge:
 		if (syn_inerr)
 			TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNCHALLENGE);
-		tcp_send_challenge_ack(sk);
+		tcp_send_challenge_ack(sk, skb);
 		goto discard;
 	}
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 131aa4950d1..98a840561ec 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -467,6 +467,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		tcp_enable_early_retrans(newtp);
 		newtp->tlp_high_seq = 0;
 		newtp->lsndtime = treq->snt_synack;
+		newtp->last_oow_ack_time = 0;
 		newtp->total_retrans = req->num_retrans;
 
 		/* So many TCP implementations out there (incorrectly) count the
-- 
cgit v1.2.3-70-g09d2


From 4fb17a6091674f469e8ac85dc770fbf9a9ba7cc8 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 6 Feb 2015 16:04:41 -0500
Subject: tcp: mitigate ACK loops for connections as tcp_timewait_sock

Ensure that in state FIN_WAIT2 or TIME_WAIT, where the connection is
represented by a tcp_timewait_sock, we rate limit dupacks in response
to incoming packets (a) with TCP timestamps that fail PAWS checks, or
(b) with sequence numbers that are out of the acceptable window.

We do not send a dupack in response to out-of-window packets if it has
been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we
last sent a dupack in response to an out-of-window packet.

Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      |  4 ++++
 net/ipv4/tcp_minisocks.c | 29 ++++++++++++++++++++++++-----
 2 files changed, 28 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 66d85a80a1e..1a7adb41164 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -342,6 +342,10 @@ struct tcp_timewait_sock {
 	u32			  tw_rcv_wnd;
 	u32			  tw_ts_offset;
 	u32			  tw_ts_recent;
+
+	/* The time we sent the last out-of-window ACK: */
+	u32			  tw_last_oow_ack_time;
+
 	long			  tw_ts_recent_stamp;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key	  *tw_md5_key;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 98a840561ec..dd11ac7798c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -58,6 +58,25 @@ static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
 	return seq == e_win && seq == end_seq;
 }
 
+static enum tcp_tw_status
+tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
+				  const struct sk_buff *skb, int mib_idx)
+{
+	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
+
+	if (!tcp_oow_rate_limited(twsk_net(tw), skb, mib_idx,
+				  &tcptw->tw_last_oow_ack_time)) {
+		/* Send ACK. Note, we do not put the bucket,
+		 * it will be released by caller.
+		 */
+		return TCP_TW_ACK;
+	}
+
+	/* We are rate-limiting, so just release the tw sock and drop skb. */
+	inet_twsk_put(tw);
+	return TCP_TW_SUCCESS;
+}
+
 /*
  * * Main purpose of TIME-WAIT state is to close connection gracefully,
  *   when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
@@ -116,7 +135,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
 				   tcptw->tw_rcv_nxt,
 				   tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd))
-			return TCP_TW_ACK;
+			return tcp_timewait_check_oow_rate_limit(
+				tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2);
 
 		if (th->rst)
 			goto kill;
@@ -250,10 +270,8 @@ kill:
 			inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
 					   TCP_TIMEWAIT_LEN);
 
-		/* Send ACK. Note, we do not put the bucket,
-		 * it will be released by caller.
-		 */
-		return TCP_TW_ACK;
+		return tcp_timewait_check_oow_rate_limit(
+			tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT);
 	}
 	inet_twsk_put(tw);
 	return TCP_TW_SUCCESS;
@@ -289,6 +307,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		tcptw->tw_ts_recent	= tp->rx_opt.ts_recent;
 		tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
 		tcptw->tw_ts_offset	= tp->tsoffset;
+		tcptw->tw_last_oow_ack_time = 0;
 
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
-- 
cgit v1.2.3-70-g09d2


From 096a4cfa5807aa89c78ce12309c0b1c10cf88184 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 6 Feb 2015 18:54:19 +0100
Subject: net: fix a typo in skb_checksum_validate_zero_check

Remove trailing underscore.

Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 111e665455c..1bb36edb66b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3072,7 +3072,7 @@ static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto)
 
 #define skb_checksum_validate_zero_check(skb, proto, check,		\
 					 compute_pseudo)		\
-	__skb_checksum_validate_(skb, proto, true, true, check, compute_pseudo)
+	__skb_checksum_validate(skb, proto, true, true, check, compute_pseudo)
 
 #define skb_checksum_simple_validate(skb)				\
 	__skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo)
-- 
cgit v1.2.3-70-g09d2


From 567e4b79731c352a17d73c483959f795d3593e03 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 6 Feb 2015 12:59:01 -0800
Subject: net: rfs: add hash collision detection

Receive Flow Steering is a nice solution but suffers from
hash collisions when a mix of connected and unconnected traffic
is received on the host, when flow hash table is populated.

Also, clearing flow in inet_release() makes RFS not very good
for short lived flows, as many packets can follow close().
(FIN , ACK packets, ...)

This patch extends the information stored into global hash table
to not only include cpu number, but upper part of the hash value.

I use a 32bit value, and dynamically split it in two parts.

For host with less than 64 possible cpus, this gives 6 bits for the
cpu number, and 26 (32-6) bits for the upper part of the hash.

Since hash bucket selection use low order bits of the hash, we have
a full hash match, if /proc/sys/net/core/rps_sock_flow_entries is big
enough.

If the hash found in flow table does not match, we fallback to RPS (if
it is enabled for the rxqueue).

This means that a packet for an non connected flow can avoid the
IPI through a unrelated/victim CPU.

This also means we no longer have to clear the table at socket
close time, and this helps short lived flows performance.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c          |  5 +----
 include/linux/netdevice.h  | 34 ++++++++++++++++----------------
 include/net/sock.h         | 24 +----------------------
 net/core/dev.c             | 48 ++++++++++++++++++++++++++--------------------
 net/core/sysctl_net_core.c |  2 +-
 net/ipv4/af_inet.c         |  2 --
 6 files changed, 47 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ad7d3d5f3ee..857dca47bf8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -256,7 +256,6 @@ static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e)
 {
 	tun_debug(KERN_INFO, tun, "delete flow: hash %u index %u\n",
 		  e->rxhash, e->queue_index);
-	sock_rps_reset_flow_hash(e->rps_rxhash);
 	hlist_del_rcu(&e->hash_link);
 	kfree_rcu(e, rcu);
 	--tun->flow_count;
@@ -373,10 +372,8 @@ unlock:
  */
 static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
 {
-	if (unlikely(e->rps_rxhash != hash)) {
-		sock_rps_reset_flow_hash(e->rps_rxhash);
+	if (unlikely(e->rps_rxhash != hash))
 		e->rps_rxhash = hash;
-	}
 }
 
 /* We try to identify a flow through its rxhash first. The reason that
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ce784d5018e..ab3b7cef463 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -644,39 +644,39 @@ struct rps_dev_flow_table {
 /*
  * The rps_sock_flow_table contains mappings of flows to the last CPU
  * on which they were processed by the application (set in recvmsg).
+ * Each entry is a 32bit value. Upper part is the high order bits
+ * of flow hash, lower part is cpu number.
+ * rps_cpu_mask is used to partition the space, depending on number of
+ * possible cpus : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1
+ * For example, if 64 cpus are possible, rps_cpu_mask = 0x3f,
+ * meaning we use 32-6=26 bits for the hash.
  */
 struct rps_sock_flow_table {
-	unsigned int mask;
-	u16 ents[0];
+	u32	mask;
+	u32	ents[0];
 };
-#define	RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \
-    ((_num) * sizeof(u16)))
+#define	RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
 
 #define RPS_NO_CPU 0xffff
 
+extern u32 rps_cpu_mask;
+extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
+
 static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
 					u32 hash)
 {
 	if (table && hash) {
-		unsigned int cpu, index = hash & table->mask;
+		unsigned int index = hash & table->mask;
+		u32 val = hash & ~rps_cpu_mask;
 
 		/* We only give a hint, preemption can change cpu under us */
-		cpu = raw_smp_processor_id();
+		val |= raw_smp_processor_id();
 
-		if (table->ents[index] != cpu)
-			table->ents[index] = cpu;
+		if (table->ents[index] != val)
+			table->ents[index] = val;
 	}
 }
 
-static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table,
-				       u32 hash)
-{
-	if (table && hash)
-		table->ents[hash & table->mask] = RPS_NO_CPU;
-}
-
-extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
-
 #ifdef CONFIG_RFS_ACCEL
 bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
 			 u16 filter_id);
diff --git a/include/net/sock.h b/include/net/sock.h
index d28b8fededd..e13824570b0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -857,18 +857,6 @@ static inline void sock_rps_record_flow_hash(__u32 hash)
 #endif
 }
 
-static inline void sock_rps_reset_flow_hash(__u32 hash)
-{
-#ifdef CONFIG_RPS
-	struct rps_sock_flow_table *sock_flow_table;
-
-	rcu_read_lock();
-	sock_flow_table = rcu_dereference(rps_sock_flow_table);
-	rps_reset_sock_flow(sock_flow_table, hash);
-	rcu_read_unlock();
-#endif
-}
-
 static inline void sock_rps_record_flow(const struct sock *sk)
 {
 #ifdef CONFIG_RPS
@@ -876,28 +864,18 @@ static inline void sock_rps_record_flow(const struct sock *sk)
 #endif
 }
 
-static inline void sock_rps_reset_flow(const struct sock *sk)
-{
-#ifdef CONFIG_RPS
-	sock_rps_reset_flow_hash(sk->sk_rxhash);
-#endif
-}
-
 static inline void sock_rps_save_rxhash(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_RPS
-	if (unlikely(sk->sk_rxhash != skb->hash)) {
-		sock_rps_reset_flow(sk);
+	if (unlikely(sk->sk_rxhash != skb->hash))
 		sk->sk_rxhash = skb->hash;
-	}
 #endif
 }
 
 static inline void sock_rps_reset_rxhash(struct sock *sk)
 {
 #ifdef CONFIG_RPS
-	sock_rps_reset_flow(sk);
 	sk->sk_rxhash = 0;
 #endif
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index a3a96ffc67f..8be38675e1a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3030,6 +3030,8 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 /* One global table that all flow-based protocols share. */
 struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
 EXPORT_SYMBOL(rps_sock_flow_table);
+u32 rps_cpu_mask __read_mostly;
+EXPORT_SYMBOL(rps_cpu_mask);
 
 struct static_key rps_needed __read_mostly;
 
@@ -3086,16 +3088,17 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		       struct rps_dev_flow **rflowp)
 {
-	struct netdev_rx_queue *rxqueue;
-	struct rps_map *map;
+	const struct rps_sock_flow_table *sock_flow_table;
+	struct netdev_rx_queue *rxqueue = dev->_rx;
 	struct rps_dev_flow_table *flow_table;
-	struct rps_sock_flow_table *sock_flow_table;
+	struct rps_map *map;
 	int cpu = -1;
-	u16 tcpu;
+	u32 tcpu;
 	u32 hash;
 
 	if (skb_rx_queue_recorded(skb)) {
 		u16 index = skb_get_rx_queue(skb);
+
 		if (unlikely(index >= dev->real_num_rx_queues)) {
 			WARN_ONCE(dev->real_num_rx_queues > 1,
 				  "%s received packet on queue %u, but number "
@@ -3103,39 +3106,40 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 				  dev->name, index, dev->real_num_rx_queues);
 			goto done;
 		}
-		rxqueue = dev->_rx + index;
-	} else
-		rxqueue = dev->_rx;
+		rxqueue += index;
+	}
 
+	/* Avoid computing hash if RFS/RPS is not active for this rxqueue */
+
+	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	map = rcu_dereference(rxqueue->rps_map);
-	if (map) {
-		if (map->len == 1 &&
-		    !rcu_access_pointer(rxqueue->rps_flow_table)) {
-			tcpu = map->cpus[0];
-			if (cpu_online(tcpu))
-				cpu = tcpu;
-			goto done;
-		}
-	} else if (!rcu_access_pointer(rxqueue->rps_flow_table)) {
+	if (!flow_table && !map)
 		goto done;
-	}
 
 	skb_reset_network_header(skb);
 	hash = skb_get_hash(skb);
 	if (!hash)
 		goto done;
 
-	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	sock_flow_table = rcu_dereference(rps_sock_flow_table);
 	if (flow_table && sock_flow_table) {
-		u16 next_cpu;
 		struct rps_dev_flow *rflow;
+		u32 next_cpu;
+		u32 ident;
+
+		/* First check into global flow table if there is a match */
+		ident = sock_flow_table->ents[hash & sock_flow_table->mask];
+		if ((ident ^ hash) & ~rps_cpu_mask)
+			goto try_rps;
 
+		next_cpu = ident & rps_cpu_mask;
+
+		/* OK, now we know there is a match,
+		 * we can look at the local (per receive queue) flow table
+		 */
 		rflow = &flow_table->flows[hash & flow_table->mask];
 		tcpu = rflow->cpu;
 
-		next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
-
 		/*
 		 * If the desired CPU (where last recvmsg was done) is
 		 * different from current CPU (one in the rx-queue flow
@@ -3162,6 +3166,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		}
 	}
 
+try_rps:
+
 	if (map) {
 		tcpu = map->cpus[reciprocal_scale(hash, map->len)];
 		if (cpu_online(tcpu)) {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index fde21d19e61..7a31be5e361 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -65,7 +65,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 					mutex_unlock(&sock_flow_mutex);
 					return -ENOMEM;
 				}
-
+				rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1;
 				sock_table->mask = size - 1;
 			} else
 				sock_table = orig_sock_table;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a44773c8346..d2e49baaff6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -395,8 +395,6 @@ int inet_release(struct socket *sock)
 	if (sk) {
 		long timeout;
 
-		sock_rps_reset_flow(sk);
-
 		/* Applications forget to leave groups before exiting */
 		ip_mc_drop_socket(sk);
 
-- 
cgit v1.2.3-70-g09d2


From 93c1af6ca94c1e763efba76a127b5c135e3d23a6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 8 Feb 2015 20:39:13 -0800
Subject: net:rfs: adjust table size checking

Make sure root user does not try something stupid.

Also make sure mask field in struct rps_sock_flow_table
does not share a cache line with the potentially often dirtied
flow table.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 567e4b79731c ("net: rfs: add hash collision detection")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h  | 3 ++-
 net/core/sysctl_net_core.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ab3b7cef463..d115256ed5a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -653,7 +653,8 @@ struct rps_dev_flow_table {
  */
 struct rps_sock_flow_table {
 	u32	mask;
-	u32	ents[0];
+
+	u32	ents[0] ____cacheline_aligned_in_smp;
 };
 #define	RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
 
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 7a31be5e361..eaa51ddf236 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -52,7 +52,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
 
 	if (write) {
 		if (size) {
-			if (size > 1<<30) {
+			if (size > 1<<29) {
 				/* Enforce limit to prevent overflow */
 				mutex_unlock(&sock_flow_mutex);
 				return -EINVAL;
-- 
cgit v1.2.3-70-g09d2


From 2b79d7a6bf341ebeffb85fc2b3577d0cfa810c49 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Fri, 6 Feb 2015 15:55:51 -0600
Subject: ALSA: pcm: allow for trigger_tstamp snapshot in .trigger

Don't use generic snapshot of trigger_tstamp if low-level driver or
hardware can get a more precise value for better audio/system time
synchronization.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h     | 1 +
 sound/core/pcm_native.c | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 07299b29523..c0ddb7e69c2 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -285,6 +285,7 @@ struct snd_pcm_runtime {
 	/* -- Status -- */
 	struct snd_pcm_substream *trigger_master;
 	struct timespec trigger_tstamp;	/* trigger timestamp */
+	bool trigger_tstamp_latched;     /* trigger timestamp latched in low-level driver/hardware */
 	int overrange;
 	snd_pcm_uframes_t avail_max;
 	snd_pcm_uframes_t hw_ptr_base;	/* Position at buffer restart */
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 4ecd35fbfe3..b03a638b420 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -810,7 +810,8 @@ static void snd_pcm_trigger_tstamp(struct snd_pcm_substream *substream)
 	if (runtime->trigger_master == NULL)
 		return;
 	if (runtime->trigger_master == substream) {
-		snd_pcm_gettime(runtime, &runtime->trigger_tstamp);
+		if (!runtime->trigger_tstamp_latched)
+			snd_pcm_gettime(runtime, &runtime->trigger_tstamp);
 	} else {
 		snd_pcm_trigger_tstamp(runtime->trigger_master);
 		runtime->trigger_tstamp = runtime->trigger_master->runtime->trigger_tstamp;
@@ -979,6 +980,7 @@ static int snd_pcm_pre_start(struct snd_pcm_substream *substream, int state)
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
 	    !snd_pcm_playback_data(substream))
 		return -EPIPE;
+	runtime->trigger_tstamp_latched = false;
 	runtime->trigger_master = substream;
 	return 0;
 }
-- 
cgit v1.2.3-70-g09d2


From d0796d1ef63deb38147729664691ba3090930b26 Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Mon, 9 Feb 2015 09:50:04 +0100
Subject: tipc: convert legacy nl bearer dump to nl compat

Introduce a framework for dumping netlink data from the new netlink
API and formatting it to the old legacy API format. This is done by
looping the dump data and calling a format handler for each entity, in
this case a bearer.

We dump until either all data is dumped or we reach the limited buffer
size of the legacy API. Remember, the legacy API doesn't scale.

In this commit we convert TIPC_CMD_GET_BEARER_NAMES to use the compat
layer.

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_config.h |   5 +
 net/tipc/bearer.c                |  29 -----
 net/tipc/bearer.h                |   1 -
 net/tipc/config.c                |   3 -
 net/tipc/netlink_compat.c        | 274 ++++++++++++++++++++++++++++++++++++++-
 5 files changed, 278 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h
index 876d0a14863..e1f4f05f4c5 100644
--- a/include/uapi/linux/tipc_config.h
+++ b/include/uapi/linux/tipc_config.h
@@ -272,6 +272,11 @@ static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type)
 		(ntohs(((struct tlv_desc *)tlv)->tlv_type) == exp_type);
 }
 
+static inline int TLV_GET_LEN(struct tlv_desc *tlv)
+{
+	return ntohs(tlv->tlv_len);
+}
+
 static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len)
 {
 	struct tlv_desc *tlv_ptr;
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 35d400e8c2e..7a9e29641e6 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -205,35 +205,6 @@ struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name)
 	return NULL;
 }
 
-/**
- * tipc_bearer_get_names - record names of bearers in buffer
- */
-struct sk_buff *tipc_bearer_get_names(struct net *net)
-{
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	struct sk_buff *buf;
-	struct tipc_bearer *b;
-	int i, j;
-
-	buf = tipc_cfg_reply_alloc(MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME));
-	if (!buf)
-		return NULL;
-
-	for (i = 0; media_info_array[i] != NULL; i++) {
-		for (j = 0; j < MAX_BEARERS; j++) {
-			b = rtnl_dereference(tn->bearer_list[j]);
-			if (!b)
-				continue;
-			if (b->media == media_info_array[i]) {
-				tipc_cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME,
-						    b->name,
-						    strlen(b->name) + 1);
-			}
-		}
-	}
-	return buf;
-}
-
 void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index c035e3e2476..956858276d9 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -205,7 +205,6 @@ void tipc_disable_l2_media(struct tipc_bearer *b);
 int tipc_l2_send_msg(struct net *net, struct sk_buff *buf,
 		     struct tipc_bearer *b, struct tipc_media_addr *dest);
 
-struct sk_buff *tipc_bearer_get_names(struct net *net);
 void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest);
 void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest);
 struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name);
diff --git a/net/tipc/config.c b/net/tipc/config.c
index 6873360cda5..52e84b0ac48 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -252,9 +252,6 @@ struct sk_buff *tipc_cfg_do_cmd(struct net *net, u32 orig_node, u16 cmd,
 		rep_tlv_buf = tipc_nametbl_get(net, req_tlv_area,
 					       req_tlv_space);
 		break;
-	case TIPC_CMD_GET_BEARER_NAMES:
-		rep_tlv_buf = tipc_bearer_get_names(net);
-		break;
 	case TIPC_CMD_GET_MEDIA_NAMES:
 		rep_tlv_buf = tipc_media_get_names();
 		break;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index f752854c8b1..bd75ea290e3 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -33,9 +33,265 @@
 
 #include "core.h"
 #include "config.h"
+#include "bearer.h"
 #include <net/genetlink.h>
 #include <linux/tipc_config.h>
 
+/* The legacy API had an artificial message length limit called
+ * ULTRA_STRING_MAX_LEN.
+ */
+#define ULTRA_STRING_MAX_LEN 32768
+
+#define TIPC_SKB_MAX TLV_SPACE(ULTRA_STRING_MAX_LEN)
+
+#define REPLY_TRUNCATED "<truncated>\n"
+
+struct tipc_nl_compat_msg {
+	u16 cmd;
+	int rep_size;
+	struct sk_buff *rep;
+	struct tlv_desc *req;
+	struct sock *dst_sk;
+};
+
+struct tipc_nl_compat_cmd_dump {
+	int (*dumpit)(struct sk_buff *, struct netlink_callback *);
+	int (*format)(struct tipc_nl_compat_msg *msg, struct nlattr **attrs);
+};
+
+static int tipc_skb_tailroom(struct sk_buff *skb)
+{
+	int tailroom;
+	int limit;
+
+	tailroom = skb_tailroom(skb);
+	limit = TIPC_SKB_MAX - skb->len;
+
+	if (tailroom < limit)
+		return tailroom;
+
+	return limit;
+}
+
+static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
+{
+	struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb);
+
+	if (tipc_skb_tailroom(skb) < TLV_SPACE(len))
+		return -EMSGSIZE;
+
+	skb_put(skb, TLV_SPACE(len));
+	tlv->tlv_type = htons(type);
+	tlv->tlv_len = htons(TLV_LENGTH(len));
+	if (len && data)
+		memcpy(TLV_DATA(tlv), data, len);
+
+	return 0;
+}
+
+static struct sk_buff *tipc_tlv_alloc(int size)
+{
+	int hdr_len;
+	struct sk_buff *buf;
+
+	size = TLV_SPACE(size);
+	hdr_len = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
+
+	buf = alloc_skb(hdr_len + size, GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	skb_reserve(buf, hdr_len);
+
+	return buf;
+}
+
+static struct sk_buff *tipc_get_err_tlv(char *str)
+{
+	int str_len = strlen(str) + 1;
+	struct sk_buff *buf;
+
+	buf = tipc_tlv_alloc(TLV_SPACE(str_len));
+	if (buf)
+		tipc_add_tlv(buf, TIPC_TLV_ERROR_STRING, str, str_len);
+
+	return buf;
+}
+
+static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
+				   struct tipc_nl_compat_msg *msg,
+				   struct sk_buff *arg)
+{
+	int len = 0;
+	int err;
+	struct sk_buff *buf;
+	struct nlmsghdr *nlmsg;
+	struct netlink_callback cb;
+
+	memset(&cb, 0, sizeof(cb));
+	cb.nlh = (struct nlmsghdr *)arg->data;
+	cb.skb = arg;
+
+	buf = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf->sk = msg->dst_sk;
+
+	do {
+		int rem;
+
+		len = (*cmd->dumpit)(buf, &cb);
+
+		nlmsg_for_each_msg(nlmsg, nlmsg_hdr(buf), len, rem) {
+			struct nlattr **attrs;
+
+			err = tipc_nlmsg_parse(nlmsg, &attrs);
+			if (err)
+				goto err_out;
+
+			err = (*cmd->format)(msg, attrs);
+			if (err)
+				goto err_out;
+
+			if (tipc_skb_tailroom(msg->rep) <= 1) {
+				err = -EMSGSIZE;
+				goto err_out;
+			}
+		}
+
+		skb_reset_tail_pointer(buf);
+		buf->len = 0;
+
+	} while (len);
+
+	err = 0;
+
+err_out:
+	kfree_skb(buf);
+
+	if (err == -EMSGSIZE) {
+		/* The legacy API only considered messages filling
+		 * "ULTRA_STRING_MAX_LEN" to be truncated.
+		 */
+		if ((TIPC_SKB_MAX - msg->rep->len) <= 1) {
+			char *tail = skb_tail_pointer(msg->rep);
+
+			if (*tail != '\0')
+				sprintf(tail - sizeof(REPLY_TRUNCATED) - 1,
+					REPLY_TRUNCATED);
+		}
+
+		return 0;
+	}
+
+	return err;
+}
+
+static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
+				 struct tipc_nl_compat_msg *msg)
+{
+	int err;
+	struct sk_buff *arg;
+
+	msg->rep = tipc_tlv_alloc(msg->rep_size);
+	if (!msg->rep)
+		return -ENOMEM;
+
+	arg = nlmsg_new(0, GFP_KERNEL);
+	if (!arg) {
+		kfree_skb(msg->rep);
+		return -ENOMEM;
+	}
+
+	err = __tipc_nl_compat_dumpit(cmd, msg, arg);
+	if (err)
+		kfree_skb(msg->rep);
+
+	kfree_skb(arg);
+
+	return err;
+}
+
+static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
+				      struct nlattr **attrs)
+{
+	struct nlattr *bearer[TIPC_NLA_BEARER_MAX + 1];
+
+	nla_parse_nested(bearer, TIPC_NLA_BEARER_MAX, attrs[TIPC_NLA_BEARER],
+			 NULL);
+
+	return tipc_add_tlv(msg->rep, TIPC_TLV_BEARER_NAME,
+			    nla_data(bearer[TIPC_NLA_BEARER_NAME]),
+			    nla_len(bearer[TIPC_NLA_BEARER_NAME]));
+}
+
+static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg)
+{
+	struct tipc_nl_compat_cmd_dump dump;
+
+	memset(&dump, 0, sizeof(dump));
+
+	switch (msg->cmd) {
+	case TIPC_CMD_GET_BEARER_NAMES:
+		msg->rep_size = MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME);
+		dump.dumpit = tipc_nl_bearer_dump;
+		dump.format = tipc_nl_compat_bearer_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info)
+{
+	int err;
+	int len;
+	struct tipc_nl_compat_msg msg;
+	struct nlmsghdr *req_nlh;
+	struct nlmsghdr *rep_nlh;
+	struct tipc_genlmsghdr *req_userhdr = info->userhdr;
+	struct net *net = genl_info_net(info);
+
+	memset(&msg, 0, sizeof(msg));
+
+	req_nlh = (struct nlmsghdr *)skb->data;
+	msg.req = nlmsg_data(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN;
+	msg.cmd = req_userhdr->cmd;
+	msg.dst_sk = info->dst_sk;
+
+	if ((msg.cmd & 0xC000) && (!netlink_net_capable(skb, CAP_NET_ADMIN))) {
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_NET_ADMIN);
+		err = -EACCES;
+		goto send;
+	}
+
+	len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	if (TLV_GET_LEN(msg.req) && !TLV_OK(msg.req, len)) {
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
+		err = -EOPNOTSUPP;
+		goto send;
+	}
+
+	err = tipc_nl_compat_handle(&msg);
+	if (err == -EOPNOTSUPP)
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
+	else if (err == -EINVAL)
+		msg.rep = tipc_get_err_tlv(TIPC_CFG_TLV_ERROR);
+send:
+	if (!msg.rep)
+		return err;
+
+	len = nlmsg_total_size(GENL_HDRLEN + TIPC_GENL_HDRLEN);
+	skb_push(msg.rep, len);
+	rep_nlh = nlmsg_hdr(msg.rep);
+	memcpy(rep_nlh, info->nlhdr, len);
+	rep_nlh->nlmsg_len = msg.rep->len;
+	genlmsg_unicast(net, msg.rep, NETLINK_CB(skb).portid);
+
+	return err;
+}
+
 static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
@@ -69,6 +325,22 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+/* Temporary function to keep functionality throughout the patchset
+ * without having to mess with the global variables and other trickery
+ * of the old API.
+ */
+static int tipc_nl_compat_tmp_wrap(struct sk_buff *skb, struct genl_info *info)
+{
+	struct tipc_genlmsghdr *req = info->userhdr;
+
+	switch (req->cmd) {
+	case TIPC_CMD_GET_BEARER_NAMES:
+		return tipc_nl_compat_recv(skb, info);
+	}
+
+	return handle_cmd(skb, info);
+}
+
 static struct genl_family tipc_genl_compat_family = {
 	.id		= GENL_ID_GENERATE,
 	.name		= TIPC_GENL_NAME,
@@ -81,7 +353,7 @@ static struct genl_family tipc_genl_compat_family = {
 static struct genl_ops tipc_genl_compat_ops[] = {
 	{
 		.cmd		= TIPC_GENL_CMD,
-		.doit		= handle_cmd,
+		.doit		= tipc_nl_compat_tmp_wrap,
 	},
 };
 
-- 
cgit v1.2.3-70-g09d2


From 9ab154658a7ff2c5076607e02f18581c6859fc2a Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Mon, 9 Feb 2015 09:50:05 +0100
Subject: tipc: convert legacy nl bearer enable/disable to nl compat

Introduce a framework for transcoding legacy nl action into actions
(.doit) calls from the new nl API. This is done by converting the
incoming TLV data into netlink data with nested netlink attributes.
Unfortunately due to the randomness of the legacy API we can't do this
generically so each legacy netlink command requires a specific
transcoding recipe. In this case for bearer enable and bearer disable.

Convert TIPC_CMD_ENABLE_BEARER and TIPC_CMD_DISABLE_BEARER into doit
compat calls.

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_config.h |   5 ++
 net/tipc/bearer.c                |  26 ++-----
 net/tipc/bearer.h                |   3 -
 net/tipc/config.c                |  33 ---------
 net/tipc/netlink_compat.c        | 144 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 154 insertions(+), 57 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h
index e1f4f05f4c5..f9226566c1b 100644
--- a/include/uapi/linux/tipc_config.h
+++ b/include/uapi/linux/tipc_config.h
@@ -277,6 +277,11 @@ static inline int TLV_GET_LEN(struct tlv_desc *tlv)
 	return ntohs(tlv->tlv_len);
 }
 
+static inline int TLV_CHECK_TYPE(struct tlv_desc *tlv,  __u16 type)
+{
+	return (ntohs(tlv->tlv_type) == type);
+}
+
 static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len)
 {
 	struct tlv_desc *tlv_ptr;
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 7a9e29641e6..de1c800ef80 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -236,8 +236,8 @@ void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest)
 /**
  * tipc_enable_bearer - enable bearer with the given name
  */
-int tipc_enable_bearer(struct net *net, const char *name, u32 disc_domain,
-		       u32 priority)
+static int tipc_enable_bearer(struct net *net, const char *name,
+			      u32 disc_domain, u32 priority)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_bearer *b_ptr;
@@ -393,22 +393,6 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr,
 	kfree_rcu(b_ptr, rcu);
 }
 
-int tipc_disable_bearer(struct net *net, const char *name)
-{
-	struct tipc_bearer *b_ptr;
-	int res;
-
-	b_ptr = tipc_bearer_find(net, name);
-	if (b_ptr == NULL) {
-		pr_warn("Attempt to disable unknown bearer <%s>\n", name);
-		res = -EINVAL;
-	} else {
-		bearer_disable(net, b_ptr, false);
-		res = 0;
-	}
-	return res;
-}
-
 int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b)
 {
 	struct net_device *dev;
@@ -756,7 +740,7 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
 	char *name;
 	struct tipc_bearer *bearer;
 	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
-	struct net *net = genl_info_net(info);
+	struct net *net = sock_net(skb->sk);
 
 	if (!info->attrs[TIPC_NLA_BEARER])
 		return -EINVAL;
@@ -787,11 +771,11 @@ int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info)
 
 int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info)
 {
-	struct net *net = genl_info_net(info);
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	int err;
 	char *bearer;
 	struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1];
+	struct net *net = sock_net(skb->sk);
+	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	u32 domain;
 	u32 prio;
 
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index 956858276d9..06f25d14487 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -173,9 +173,6 @@ struct tipc_bearer_names {
  */
 
 void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr);
-int tipc_enable_bearer(struct net *net, const char *bearer_name,
-		       u32 disc_domain, u32 priority);
-int tipc_disable_bearer(struct net *net, const char *name);
 
 /*
  * Routines made available to TIPC by supported media types
diff --git a/net/tipc/config.c b/net/tipc/config.c
index 52e84b0ac48..f8cd5e1b545 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -134,33 +134,6 @@ static struct sk_buff *tipc_show_stats(void)
 	return buf;
 }
 
-static struct sk_buff *cfg_enable_bearer(struct net *net)
-{
-	struct tipc_bearer_config *args;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_BEARER_CONFIG))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	args = (struct tipc_bearer_config *)TLV_DATA(req_tlv_area);
-	if (tipc_enable_bearer(net, args->name,
-			       ntohl(args->disc_domain),
-			       ntohl(args->priority)))
-		return tipc_cfg_reply_error_string("unable to enable bearer");
-
-	return tipc_cfg_reply_none();
-}
-
-static struct sk_buff *cfg_disable_bearer(struct net *net)
-{
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_BEARER_NAME))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	if (tipc_disable_bearer(net, (char *)TLV_DATA(req_tlv_area)))
-		return tipc_cfg_reply_error_string("unable to disable bearer");
-
-	return tipc_cfg_reply_none();
-}
-
 static struct sk_buff *cfg_set_own_addr(struct net *net)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
@@ -267,12 +240,6 @@ struct sk_buff *tipc_cfg_do_cmd(struct net *net, u32 orig_node, u16 cmd,
 		rep_tlv_buf = tipc_link_cmd_config(net, req_tlv_area,
 						   req_tlv_space, cmd);
 		break;
-	case TIPC_CMD_ENABLE_BEARER:
-		rep_tlv_buf = cfg_enable_bearer(net);
-		break;
-	case TIPC_CMD_DISABLE_BEARER:
-		rep_tlv_buf = cfg_disable_bearer(net);
-		break;
 	case TIPC_CMD_SET_NODE_ADDR:
 		rep_tlv_buf = cfg_set_own_addr(net);
 		break;
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index bd75ea290e3..12b0f442479 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -49,6 +49,7 @@
 struct tipc_nl_compat_msg {
 	u16 cmd;
 	int rep_size;
+	int req_type;
 	struct sk_buff *rep;
 	struct tlv_desc *req;
 	struct sock *dst_sk;
@@ -59,6 +60,11 @@ struct tipc_nl_compat_cmd_dump {
 	int (*format)(struct tipc_nl_compat_msg *msg, struct nlattr **attrs);
 };
 
+struct tipc_nl_compat_cmd_doit {
+	int (*doit)(struct sk_buff *skb, struct genl_info *info);
+	int (*transcode)(struct sk_buff *skb, struct tipc_nl_compat_msg *msg);
+};
+
 static int tipc_skb_tailroom(struct sk_buff *skb)
 {
 	int tailroom;
@@ -213,6 +219,78 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	return err;
 }
 
+static int __tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
+				 struct tipc_nl_compat_msg *msg)
+{
+	int err;
+	struct sk_buff *doit_buf;
+	struct sk_buff *trans_buf;
+	struct nlattr **attrbuf;
+	struct genl_info info;
+
+	trans_buf = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!trans_buf)
+		return -ENOMEM;
+
+	err = (*cmd->transcode)(trans_buf, msg);
+	if (err)
+		goto trans_out;
+
+	attrbuf = kmalloc((tipc_genl_family.maxattr + 1) *
+			sizeof(struct nlattr *), GFP_KERNEL);
+	if (!attrbuf) {
+		err = -ENOMEM;
+		goto trans_out;
+	}
+
+	err = nla_parse(attrbuf, tipc_genl_family.maxattr,
+			(const struct nlattr *)trans_buf->data,
+			trans_buf->len, NULL);
+	if (err)
+		goto parse_out;
+
+	doit_buf = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!doit_buf) {
+		err = -ENOMEM;
+		goto parse_out;
+	}
+
+	doit_buf->sk = msg->dst_sk;
+
+	memset(&info, 0, sizeof(info));
+	info.attrs = attrbuf;
+
+	err = (*cmd->doit)(doit_buf, &info);
+
+	kfree_skb(doit_buf);
+parse_out:
+	kfree(attrbuf);
+trans_out:
+	kfree_skb(trans_buf);
+
+	return err;
+}
+
+static int tipc_nl_compat_doit(struct tipc_nl_compat_cmd_doit *cmd,
+			       struct tipc_nl_compat_msg *msg)
+{
+	int err;
+
+	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+		return -EINVAL;
+
+	err = __tipc_nl_compat_doit(cmd, msg);
+	if (err)
+		return err;
+
+	/* The legacy API considered an empty message a success message */
+	msg->rep = tipc_tlv_alloc(0);
+	if (!msg->rep)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
 				      struct nlattr **attrs)
 {
@@ -226,11 +304,65 @@ static int tipc_nl_compat_bearer_dump(struct tipc_nl_compat_msg *msg,
 			    nla_len(bearer[TIPC_NLA_BEARER_NAME]));
 }
 
+static int tipc_nl_compat_bearer_enable(struct sk_buff *skb,
+					struct tipc_nl_compat_msg *msg)
+{
+	struct nlattr *prop;
+	struct nlattr *bearer;
+	struct tipc_bearer_config *b;
+
+	b = (struct tipc_bearer_config *)TLV_DATA(msg->req);
+
+	bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+	if (!bearer)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name))
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, TIPC_NLA_BEARER_DOMAIN, ntohl(b->disc_domain)))
+		return -EMSGSIZE;
+
+	if (ntohl(b->priority) <= TIPC_MAX_LINK_PRI) {
+		prop = nla_nest_start(skb, TIPC_NLA_BEARER_PROP);
+		if (!prop)
+			return -EMSGSIZE;
+		if (nla_put_u32(skb, TIPC_NLA_PROP_PRIO, ntohl(b->priority)))
+			return -EMSGSIZE;
+		nla_nest_end(skb, prop);
+	}
+	nla_nest_end(skb, bearer);
+
+	return 0;
+}
+
+static int tipc_nl_compat_bearer_disable(struct sk_buff *skb,
+					 struct tipc_nl_compat_msg *msg)
+{
+	char *name;
+	struct nlattr *bearer;
+
+	name = (char *)TLV_DATA(msg->req);
+
+	bearer = nla_nest_start(skb, TIPC_NLA_BEARER);
+	if (!bearer)
+		return -EMSGSIZE;
+
+	if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name))
+		return -EMSGSIZE;
+
+	nla_nest_end(skb, bearer);
+
+	return 0;
+}
+
 static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg)
 {
 	struct tipc_nl_compat_cmd_dump dump;
+	struct tipc_nl_compat_cmd_doit doit;
 
 	memset(&dump, 0, sizeof(dump));
+	memset(&doit, 0, sizeof(doit));
 
 	switch (msg->cmd) {
 	case TIPC_CMD_GET_BEARER_NAMES:
@@ -238,6 +370,16 @@ static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg)
 		dump.dumpit = tipc_nl_bearer_dump;
 		dump.format = tipc_nl_compat_bearer_dump;
 		return tipc_nl_compat_dumpit(&dump, msg);
+	case TIPC_CMD_ENABLE_BEARER:
+		msg->req_type = TIPC_TLV_BEARER_CONFIG;
+		doit.doit = tipc_nl_bearer_enable;
+		doit.transcode = tipc_nl_compat_bearer_enable;
+		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_DISABLE_BEARER:
+		msg->req_type = TIPC_TLV_BEARER_NAME;
+		doit.doit = tipc_nl_bearer_disable;
+		doit.transcode = tipc_nl_compat_bearer_disable;
+		return tipc_nl_compat_doit(&doit, msg);
 	}
 
 	return -EOPNOTSUPP;
@@ -335,6 +477,8 @@ static int tipc_nl_compat_tmp_wrap(struct sk_buff *skb, struct genl_info *info)
 
 	switch (req->cmd) {
 	case TIPC_CMD_GET_BEARER_NAMES:
+	case TIPC_CMD_ENABLE_BEARER:
+	case TIPC_CMD_DISABLE_BEARER:
 		return tipc_nl_compat_recv(skb, info);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From f2b3b2d4ccbf9666f5f42a21347cd1aaa532b2fa Mon Sep 17 00:00:00 2001
From: Richard Alpe <richard.alpe@ericsson.com>
Date: Mon, 9 Feb 2015 09:50:06 +0100
Subject: tipc: convert legacy nl link stat to nl compat

Add functionality for safely appending string data to a TLV without
keeping write count in the caller.

Convert TIPC_CMD_SHOW_LINK_STATS to compat dumpit.

Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_config.h |  10 ++
 net/tipc/bcast.c                 |  43 --------
 net/tipc/bcast.h                 |   1 -
 net/tipc/config.c                |   4 -
 net/tipc/link.c                  | 141 ---------------------------
 net/tipc/link.h                  |   3 -
 net/tipc/netlink_compat.c        | 205 +++++++++++++++++++++++++++++++++++++++
 7 files changed, 215 insertions(+), 192 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h
index f9226566c1b..087b0ef82c0 100644
--- a/include/uapi/linux/tipc_config.h
+++ b/include/uapi/linux/tipc_config.h
@@ -277,11 +277,21 @@ static inline int TLV_GET_LEN(struct tlv_desc *tlv)
 	return ntohs(tlv->tlv_len);
 }
 
+static inline void TLV_SET_LEN(struct tlv_desc *tlv, __u16 len)
+{
+	tlv->tlv_len = htons(len);
+}
+
 static inline int TLV_CHECK_TYPE(struct tlv_desc *tlv,  __u16 type)
 {
 	return (ntohs(tlv->tlv_type) == type);
 }
 
+static inline void TLV_SET_TYPE(struct tlv_desc *tlv, __u16 type)
+{
+	tlv->tlv_type = htons(type);
+}
+
 static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len)
 {
 	struct tlv_desc *tlv_ptr;
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index e96fd6a6d5c..3e41704832d 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -860,49 +860,6 @@ msg_full:
 	return -EMSGSIZE;
 }
 
-int tipc_bclink_stats(struct net *net, char *buf, const u32 buf_size)
-{
-	int ret;
-	struct tipc_stats *s;
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	struct tipc_link *bcl = tn->bcl;
-
-	if (!bcl)
-		return 0;
-
-	tipc_bclink_lock(net);
-
-	s = &bcl->stats;
-
-	ret = tipc_snprintf(buf, buf_size, "Link <%s>\n"
-			    "  Window:%u packets\n",
-			    bcl->name, bcl->queue_limit[0]);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     s->recv_info, s->recv_fragments,
-			     s->recv_fragmented, s->recv_bundles,
-			     s->recv_bundled);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     s->sent_info, s->sent_fragments,
-			     s->sent_fragmented, s->sent_bundles,
-			     s->sent_bundled);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX naks:%u defs:%u dups:%u\n",
-			     s->recv_nacks, s->deferred_recv, s->duplicates);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX naks:%u acks:%u dups:%u\n",
-			     s->sent_nacks, s->sent_acks, s->retransmitted);
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  Congestion link:%u  Send queue max:%u avg:%u\n",
-			     s->link_congs, s->max_queue_sz,
-			     s->queue_sz_counts ?
-			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
-
-	tipc_bclink_unlock(net);
-	return ret;
-}
-
 int tipc_bclink_reset_stats(struct net *net)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index a910c0b9f24..43f397fbac5 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -127,7 +127,6 @@ u32  tipc_bclink_get_last_sent(struct net *net);
 u32  tipc_bclink_acks_missing(struct tipc_node *n_ptr);
 void tipc_bclink_update_link_state(struct tipc_node *node,
 				   u32 last_sent);
-int  tipc_bclink_stats(struct net *net, char *stats_buf, const u32 buf_size);
 int  tipc_bclink_reset_stats(struct net *net);
 int  tipc_bclink_set_queue_limits(struct net *net, u32 limit);
 void tipc_bcbearer_sort(struct net *net, struct tipc_node_map *nm_ptr,
diff --git a/net/tipc/config.c b/net/tipc/config.c
index f8cd5e1b545..67b76ee847f 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -213,10 +213,6 @@ struct sk_buff *tipc_cfg_do_cmd(struct net *net, u32 orig_node, u16 cmd,
 		rep_tlv_buf = tipc_node_get_links(net, req_tlv_area,
 						  req_tlv_space);
 		break;
-	case TIPC_CMD_SHOW_LINK_STATS:
-		rep_tlv_buf = tipc_link_cmd_show_stats(net, req_tlv_area,
-						       req_tlv_space);
-		break;
 	case TIPC_CMD_RESET_LINK_STATS:
 		rep_tlv_buf = tipc_link_cmd_reset_stats(net, req_tlv_area,
 							req_tlv_space);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 466f28fcf21..2622fb99344 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -2146,147 +2146,6 @@ struct sk_buff *tipc_link_cmd_reset_stats(struct net *net,
 	return tipc_cfg_reply_none();
 }
 
-/**
- * percent - convert count to a percentage of total (rounding up or down)
- */
-static u32 percent(u32 count, u32 total)
-{
-	return (count * 100 + (total / 2)) / total;
-}
-
-/**
- * tipc_link_stats - print link statistics
- * @net: the applicable net namespace
- * @name: link name
- * @buf: print buffer area
- * @buf_size: size of print buffer area
- *
- * Returns length of print buffer data string (or 0 if error)
- */
-static int tipc_link_stats(struct net *net, const char *name, char *buf,
-			   const u32 buf_size)
-{
-	struct tipc_link *l;
-	struct tipc_stats *s;
-	struct tipc_node *node;
-	char *status;
-	u32 profile_total = 0;
-	unsigned int bearer_id;
-	int ret;
-
-	if (!strcmp(name, tipc_bclink_name))
-		return tipc_bclink_stats(net, buf, buf_size);
-
-	node = tipc_link_find_owner(net, name, &bearer_id);
-	if (!node)
-		return 0;
-
-	tipc_node_lock(node);
-
-	l = node->links[bearer_id];
-	if (!l) {
-		tipc_node_unlock(node);
-		return 0;
-	}
-
-	s = &l->stats;
-
-	if (tipc_link_is_active(l))
-		status = "ACTIVE";
-	else if (tipc_link_is_up(l))
-		status = "STANDBY";
-	else
-		status = "DEFUNCT";
-
-	ret = tipc_snprintf(buf, buf_size, "Link <%s>\n"
-			    "  %s  MTU:%u  Priority:%u  Tolerance:%u ms"
-			    "  Window:%u packets\n",
-			    l->name, status, l->max_pkt, l->priority,
-			    l->tolerance, l->queue_limit[0]);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     l->next_in_no - s->recv_info, s->recv_fragments,
-			     s->recv_fragmented, s->recv_bundles,
-			     s->recv_bundled);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
-			     l->next_out_no - s->sent_info, s->sent_fragments,
-			     s->sent_fragmented, s->sent_bundles,
-			     s->sent_bundled);
-
-	profile_total = s->msg_length_counts;
-	if (!profile_total)
-		profile_total = 1;
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX profile sample:%u packets  average:%u octets\n"
-			     "  0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% "
-			     "-16384:%u%% -32768:%u%% -66000:%u%%\n",
-			     s->msg_length_counts,
-			     s->msg_lengths_total / profile_total,
-			     percent(s->msg_length_profile[0], profile_total),
-			     percent(s->msg_length_profile[1], profile_total),
-			     percent(s->msg_length_profile[2], profile_total),
-			     percent(s->msg_length_profile[3], profile_total),
-			     percent(s->msg_length_profile[4], profile_total),
-			     percent(s->msg_length_profile[5], profile_total),
-			     percent(s->msg_length_profile[6], profile_total));
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  RX states:%u probes:%u naks:%u defs:%u"
-			     " dups:%u\n", s->recv_states, s->recv_probes,
-			     s->recv_nacks, s->deferred_recv, s->duplicates);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  TX states:%u probes:%u naks:%u acks:%u"
-			     " dups:%u\n", s->sent_states, s->sent_probes,
-			     s->sent_nacks, s->sent_acks, s->retransmitted);
-
-	ret += tipc_snprintf(buf + ret, buf_size - ret,
-			     "  Congestion link:%u  Send queue"
-			     " max:%u avg:%u\n", s->link_congs,
-			     s->max_queue_sz, s->queue_sz_counts ?
-			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
-
-	tipc_node_unlock(node);
-	return ret;
-}
-
-struct sk_buff *tipc_link_cmd_show_stats(struct net *net,
-					 const void *req_tlv_area,
-					 int req_tlv_space)
-{
-	struct sk_buff *buf;
-	struct tlv_desc *rep_tlv;
-	int str_len;
-	int pb_len;
-	char *pb;
-
-	if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME))
-		return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR);
-
-	buf = tipc_cfg_reply_alloc(TLV_SPACE(ULTRA_STRING_MAX_LEN));
-	if (!buf)
-		return NULL;
-
-	rep_tlv = (struct tlv_desc *)buf->data;
-	pb = TLV_DATA(rep_tlv);
-	pb_len = ULTRA_STRING_MAX_LEN;
-	str_len = tipc_link_stats(net, (char *)TLV_DATA(req_tlv_area),
-				  pb, pb_len);
-	if (!str_len) {
-		kfree_skb(buf);
-		return tipc_cfg_reply_error_string("link not found");
-	}
-	str_len += 1;	/* for "\0" */
-	skb_put(buf, TLV_SPACE(str_len));
-	TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len);
-
-	return buf;
-}
-
 static void link_print(struct tipc_link *l_ptr, const char *str)
 {
 	struct tipc_net *tn = net_generic(l_ptr->owner->net, tipc_net_id);
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 34d3f55c4ce..8c8340cf991 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -217,9 +217,6 @@ int tipc_link_is_active(struct tipc_link *l_ptr);
 void tipc_link_purge_queues(struct tipc_link *l_ptr);
 struct sk_buff *tipc_link_cmd_config(struct net *net, const void *req_tlv_area,
 				     int req_tlv_space, u16 cmd);
-struct sk_buff *tipc_link_cmd_show_stats(struct net *net,
-					 const void *req_tlv_area,
-					 int req_tlv_space);
 struct sk_buff *tipc_link_cmd_reset_stats(struct net *net,
 					  const void *req_tlv_area,
 					  int req_tlv_space);
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 12b0f442479..899bd94da46 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -34,6 +34,7 @@
 #include "core.h"
 #include "config.h"
 #include "bearer.h"
+#include "link.h"
 #include <net/genetlink.h>
 #include <linux/tipc_config.h>
 
@@ -48,6 +49,7 @@
 
 struct tipc_nl_compat_msg {
 	u16 cmd;
+	int rep_type;
 	int rep_size;
 	int req_type;
 	struct sk_buff *rep;
@@ -95,6 +97,40 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len)
 	return 0;
 }
 
+static void tipc_tlv_init(struct sk_buff *skb, u16 type)
+{
+	struct tlv_desc *tlv = (struct tlv_desc *)skb->data;
+
+	TLV_SET_LEN(tlv, 0);
+	TLV_SET_TYPE(tlv, type);
+	skb_put(skb, sizeof(struct tlv_desc));
+}
+
+static int tipc_tlv_sprintf(struct sk_buff *skb, const char *fmt, ...)
+{
+	int n;
+	u16 len;
+	u32 rem;
+	char *buf;
+	struct tlv_desc *tlv;
+	va_list args;
+
+	rem = tipc_skb_tailroom(skb);
+
+	tlv = (struct tlv_desc *)skb->data;
+	len = TLV_GET_LEN(tlv);
+	buf = TLV_DATA(tlv) + len;
+
+	va_start(args, fmt);
+	n = vscnprintf(buf, rem, fmt, args);
+	va_end(args);
+
+	TLV_SET_LEN(tlv, n + len);
+	skb_put(skb, n);
+
+	return n;
+}
+
 static struct sk_buff *tipc_tlv_alloc(int size)
 {
 	int hdr_len;
@@ -200,10 +236,16 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	int err;
 	struct sk_buff *arg;
 
+	if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+		return -EINVAL;
+
 	msg->rep = tipc_tlv_alloc(msg->rep_size);
 	if (!msg->rep)
 		return -ENOMEM;
 
+	if (msg->rep_type)
+		tipc_tlv_init(msg->rep, msg->rep_type);
+
 	arg = nlmsg_new(0, GFP_KERNEL);
 	if (!arg) {
 		kfree_skb(msg->rep);
@@ -356,6 +398,161 @@ static int tipc_nl_compat_bearer_disable(struct sk_buff *skb,
 	return 0;
 }
 
+static inline u32 perc(u32 count, u32 total)
+{
+	return (count * 100 + (total / 2)) / total;
+}
+
+static void __fill_bc_link_stat(struct tipc_nl_compat_msg *msg,
+				struct nlattr *prop[], struct nlattr *stats[])
+{
+	tipc_tlv_sprintf(msg->rep, "  Window:%u packets\n",
+			 nla_get_u32(prop[TIPC_NLA_PROP_WIN]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep, "  RX naks:%u defs:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_DEFERRED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_DUPLICATES]));
+
+	tipc_tlv_sprintf(msg->rep, "  TX naks:%u acks:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_ACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RETRANSMITTED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  Congestion link:%u  Send queue max:%u avg:%u",
+			 nla_get_u32(stats[TIPC_NLA_STATS_LINK_CONGS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_MAX_QUEUE]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_AVG_QUEUE]));
+}
+
+static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
+					 struct nlattr **attrs)
+{
+	char *name;
+	struct nlattr *link[TIPC_NLA_LINK_MAX + 1];
+	struct nlattr *prop[TIPC_NLA_PROP_MAX + 1];
+	struct nlattr *stats[TIPC_NLA_STATS_MAX + 1];
+
+	nla_parse_nested(link, TIPC_NLA_LINK_MAX, attrs[TIPC_NLA_LINK], NULL);
+
+	nla_parse_nested(prop, TIPC_NLA_PROP_MAX, link[TIPC_NLA_LINK_PROP],
+			 NULL);
+
+	nla_parse_nested(stats, TIPC_NLA_STATS_MAX, link[TIPC_NLA_LINK_STATS],
+			 NULL);
+
+	name = (char *)TLV_DATA(msg->req);
+	if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0)
+		return 0;
+
+	tipc_tlv_sprintf(msg->rep, "\nLink <%s>\n",
+			 nla_data(link[TIPC_NLA_LINK_NAME]));
+
+	if (link[TIPC_NLA_LINK_BROADCAST]) {
+		__fill_bc_link_stat(msg, prop, stats);
+		return 0;
+	}
+
+	if (link[TIPC_NLA_LINK_ACTIVE])
+		tipc_tlv_sprintf(msg->rep, "  ACTIVE");
+	else if (link[TIPC_NLA_LINK_UP])
+		tipc_tlv_sprintf(msg->rep, "  STANDBY");
+	else
+		tipc_tlv_sprintf(msg->rep, "  DEFUNCT");
+
+	tipc_tlv_sprintf(msg->rep, "  MTU:%u  Priority:%u",
+			 nla_get_u32(link[TIPC_NLA_LINK_MTU]),
+			 nla_get_u32(prop[TIPC_NLA_PROP_PRIO]));
+
+	tipc_tlv_sprintf(msg->rep, "  Tolerance:%u ms  Window:%u packets\n",
+			 nla_get_u32(prop[TIPC_NLA_PROP_TOL]),
+			 nla_get_u32(prop[TIPC_NLA_PROP_WIN]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  RX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(link[TIPC_NLA_LINK_RX]) -
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX packets:%u fragments:%u/%u bundles:%u/%u\n",
+			 nla_get_u32(link[TIPC_NLA_LINK_TX]) -
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_INFO]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_FRAGMENTED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_BUNDLED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX profile sample:%u packets  average:%u octets\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_CNT]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_TOT]) /
+			 nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% ",
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P0]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P1]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P2]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P3]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])));
+
+	tipc_tlv_sprintf(msg->rep, "-16384:%u%% -32768:%u%% -66000:%u%%\n",
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P4]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P5]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])),
+			 perc(nla_get_u32(stats[TIPC_NLA_STATS_MSG_LEN_P6]),
+			      nla_get_u32(stats[TIPC_NLA_STATS_MSG_PROF_TOT])));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  RX states:%u probes:%u naks:%u defs:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_STATES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_PROBES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RX_DEFERRED]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_DUPLICATES]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  TX states:%u probes:%u naks:%u acks:%u dups:%u\n",
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_STATES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_PROBES]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_NACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_TX_ACKS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_RETRANSMITTED]));
+
+	tipc_tlv_sprintf(msg->rep,
+			 "  Congestion link:%u  Send queue max:%u avg:%u",
+			 nla_get_u32(stats[TIPC_NLA_STATS_LINK_CONGS]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_MAX_QUEUE]),
+			 nla_get_u32(stats[TIPC_NLA_STATS_AVG_QUEUE]));
+
+	return 0;
+}
+
 static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg)
 {
 	struct tipc_nl_compat_cmd_dump dump;
@@ -380,6 +577,13 @@ static int tipc_nl_compat_handle(struct tipc_nl_compat_msg *msg)
 		doit.doit = tipc_nl_bearer_disable;
 		doit.transcode = tipc_nl_compat_bearer_disable;
 		return tipc_nl_compat_doit(&doit, msg);
+	case TIPC_CMD_SHOW_LINK_STATS:
+		msg->req_type = TIPC_TLV_LINK_NAME;
+		msg->rep_size = ULTRA_STRING_MAX_LEN;
+		msg->rep_type = TIPC_TLV_ULTRA_STRING;
+		dump.dumpit = tipc_nl_link_dump;
+		dump.format = tipc_nl_compat_link_stat_dump;
+		return tipc_nl_compat_dumpit(&dump, msg);
 	}
 
 	return -EOPNOTSUPP;
@@ -479,6 +683,7 @@ static int tipc_nl_compat_tmp_wrap(struct sk_buff *skb, struct genl_info *info)
 	case TIPC_CMD_GET_BEARER_NAMES:
 	case TIPC_CMD_ENABLE_BEARER:
 	case TIPC_CMD_DISABLE_BEARER:
+	case TIPC_CMD_SHOW_LINK_STATS:
 		return tipc_nl_compat_recv(skb, info);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From 92e584fe443995bbb84069a4d13ea8ebedb5c5c8 Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Sun, 8 Feb 2015 11:49:32 +0200
Subject: net/bonding: Fix potential bad memory access during bonding events

When queuing work to send the NETDEV_BONDING_INFO netdev event, it's
possible that when the work is executed, the pointer to the slave
becomes invalid. This can happen if between queuing the event and the
execution of the work, the net-device was un-ensvaled and re-enslaved.

Fix that by queuing a work with the data of the slave instead of the
slave structure.

Fixes: 69e6113343cf ('net/bonding: Notify state change on slaves')
Reported-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 28 +++++++++++-----------------
 include/net/bonding.h           |  2 +-
 2 files changed, 12 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 679ef00d6b1..b979c265fc5 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1196,18 +1196,11 @@ static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
 	info->link_failure_count = slave->link_failure_count;
 }
 
-static void bond_netdev_notify(struct slave *slave, struct net_device *dev)
+static void bond_netdev_notify(struct net_device *dev,
+			       struct netdev_bonding_info *info)
 {
-	struct bonding *bond = slave->bond;
-	struct netdev_bonding_info bonding_info;
-
 	rtnl_lock();
-	/* make sure that slave is still valid */
-	if (dev->priv_flags & IFF_BONDING) {
-		bond_fill_ifslave(slave, &bonding_info.slave);
-		bond_fill_ifbond(bond, &bonding_info.master);
-		netdev_bonding_info_change(slave->dev, &bonding_info);
-	}
+	netdev_bonding_info_change(dev, info);
 	rtnl_unlock();
 }
 
@@ -1216,25 +1209,26 @@ static void bond_netdev_notify_work(struct work_struct *_work)
 	struct netdev_notify_work *w =
 		container_of(_work, struct netdev_notify_work, work.work);
 
-	bond_netdev_notify(w->slave, w->dev);
+	bond_netdev_notify(w->dev, &w->bonding_info);
 	dev_put(w->dev);
+	kfree(w);
 }
 
 void bond_queue_slave_event(struct slave *slave)
 {
+	struct bonding *bond = slave->bond;
 	struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC);
 
 	if (!nnw)
 		return;
 
-	INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work);
-	nnw->slave = slave;
+	dev_hold(slave->dev);
 	nnw->dev = slave->dev;
+	bond_fill_ifslave(slave, &nnw->bonding_info.slave);
+	bond_fill_ifbond(bond, &nnw->bonding_info.master);
+	INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work);
 
-	if (queue_delayed_work(slave->bond->wq, &nnw->work, 0))
-		dev_hold(slave->dev);
-	else
-		kfree(nnw);
+	queue_delayed_work(slave->bond->wq, &nnw->work, 0);
 }
 
 /* enslave device <slave> to bond device <master> */
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 4e17095ad46..fda6feeb6c1 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -152,8 +152,8 @@ struct bond_parm_tbl {
 
 struct netdev_notify_work {
 	struct delayed_work	work;
-	struct slave		*slave;
 	struct net_device	*dev;
+	struct netdev_bonding_info bonding_info;
 };
 
 struct slave {
-- 
cgit v1.2.3-70-g09d2


From 35f05dabf95ac3ebc4c15bafd6833f7a3046e66f Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Sun, 8 Feb 2015 11:49:34 +0200
Subject: IB/mlx4: Reset flow support for IB kernel ULPs

The driver exposes interfaces that directly relate to HW state. Upon fatal
error, consumers of these interfaces (ULPs) that rely on completion of
all their posted work-request could hang, thereby introducing dependencies
in shutdown order.  To prevent this from happening, we manage the
relevant resources (CQs, QPs) that are used by the device. Upon a fatal error,
we now generate simulated completions for outstanding WQEs that were not
completed at the time the HW was reset.

It includes invoking the completion event handler for all involved CQs so that
the ULPs will poll those CQs. When polled we return simulated CQEs with
IB_WC_WR_FLUSH_ERR return code enabling ULPs to clean up their resources and
not wait forever for completions upon receiving remove_one.

The above change requires an extra check in the data path to make sure that when
device is in error state, the simulated CQEs will be returned and no further
WQEs will be posted.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/cq.c      | 57 ++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx4/main.c    | 64 ++++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx4/mlx4_ib.h |  9 +++++
 drivers/infiniband/hw/mlx4/qp.c      | 59 +++++++++++++++++++++++++++++----
 drivers/infiniband/hw/mlx4/srq.c     |  8 +++++
 include/linux/mlx4/device.h          |  2 ++
 6 files changed, 193 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index a3b70f6c403..543ecdd8667 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -188,6 +188,8 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	spin_lock_init(&cq->lock);
 	cq->resize_buf = NULL;
 	cq->resize_umem = NULL;
+	INIT_LIST_HEAD(&cq->send_qp_list);
+	INIT_LIST_HEAD(&cq->recv_qp_list);
 
 	if (context) {
 		struct mlx4_ib_create_cq ucmd;
@@ -594,6 +596,55 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct
 	return 0;
 }
 
+static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries,
+			       struct ib_wc *wc, int *npolled, int is_send)
+{
+	struct mlx4_ib_wq *wq;
+	unsigned cur;
+	int i;
+
+	wq = is_send ? &qp->sq : &qp->rq;
+	cur = wq->head - wq->tail;
+
+	if (cur == 0)
+		return;
+
+	for (i = 0;  i < cur && *npolled < num_entries; i++) {
+		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
+		wc->status = IB_WC_WR_FLUSH_ERR;
+		wc->vendor_err = MLX4_CQE_SYNDROME_WR_FLUSH_ERR;
+		wq->tail++;
+		(*npolled)++;
+		wc->qp = &qp->ibqp;
+		wc++;
+	}
+}
+
+static void mlx4_ib_poll_sw_comp(struct mlx4_ib_cq *cq, int num_entries,
+				 struct ib_wc *wc, int *npolled)
+{
+	struct mlx4_ib_qp *qp;
+
+	*npolled = 0;
+	/* Find uncompleted WQEs belonging to that cq and retrun
+	 * simulated FLUSH_ERR completions
+	 */
+	list_for_each_entry(qp, &cq->send_qp_list, cq_send_list) {
+		mlx4_ib_qp_sw_comp(qp, num_entries, wc, npolled, 1);
+		if (*npolled >= num_entries)
+			goto out;
+	}
+
+	list_for_each_entry(qp, &cq->recv_qp_list, cq_recv_list) {
+		mlx4_ib_qp_sw_comp(qp, num_entries, wc + *npolled, npolled, 0);
+		if (*npolled >= num_entries)
+			goto out;
+	}
+
+out:
+	return;
+}
+
 static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
 			    struct mlx4_ib_qp **cur_qp,
 			    struct ib_wc *wc)
@@ -836,8 +887,13 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	unsigned long flags;
 	int npolled;
 	int err = 0;
+	struct mlx4_ib_dev *mdev = to_mdev(cq->ibcq.device);
 
 	spin_lock_irqsave(&cq->lock, flags);
+	if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
+		mlx4_ib_poll_sw_comp(cq, num_entries, wc, &npolled);
+		goto out;
+	}
 
 	for (npolled = 0; npolled < num_entries; ++npolled) {
 		err = mlx4_ib_poll_one(cq, &cur_qp, wc + npolled);
@@ -847,6 +903,7 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 
 	mlx4_cq_set_ci(&cq->mcq);
 
+out:
 	spin_unlock_irqrestore(&cq->lock, flags);
 
 	if (err == 0 || err == -EAGAIN)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 3140da518a0..eb8e215f161 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2308,6 +2308,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	spin_lock_init(&ibdev->sm_lock);
 	mutex_init(&ibdev->cap_mask_mutex);
+	INIT_LIST_HEAD(&ibdev->qp_list);
+	spin_lock_init(&ibdev->reset_flow_resource_lock);
 
 	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED &&
 	    ib_num_ports) {
@@ -2622,6 +2624,67 @@ out:
 	return;
 }
 
+static void mlx4_ib_handle_catas_error(struct mlx4_ib_dev *ibdev)
+{
+	struct mlx4_ib_qp *mqp;
+	unsigned long flags_qp;
+	unsigned long flags_cq;
+	struct mlx4_ib_cq *send_mcq, *recv_mcq;
+	struct list_head    cq_notify_list;
+	struct mlx4_cq *mcq;
+	unsigned long flags;
+
+	pr_warn("mlx4_ib_handle_catas_error was started\n");
+	INIT_LIST_HEAD(&cq_notify_list);
+
+	/* Go over qp list reside on that ibdev, sync with create/destroy qp.*/
+	spin_lock_irqsave(&ibdev->reset_flow_resource_lock, flags);
+
+	list_for_each_entry(mqp, &ibdev->qp_list, qps_list) {
+		spin_lock_irqsave(&mqp->sq.lock, flags_qp);
+		if (mqp->sq.tail != mqp->sq.head) {
+			send_mcq = to_mcq(mqp->ibqp.send_cq);
+			spin_lock_irqsave(&send_mcq->lock, flags_cq);
+			if (send_mcq->mcq.comp &&
+			    mqp->ibqp.send_cq->comp_handler) {
+				if (!send_mcq->mcq.reset_notify_added) {
+					send_mcq->mcq.reset_notify_added = 1;
+					list_add_tail(&send_mcq->mcq.reset_notify,
+						      &cq_notify_list);
+				}
+			}
+			spin_unlock_irqrestore(&send_mcq->lock, flags_cq);
+		}
+		spin_unlock_irqrestore(&mqp->sq.lock, flags_qp);
+		/* Now, handle the QP's receive queue */
+		spin_lock_irqsave(&mqp->rq.lock, flags_qp);
+		/* no handling is needed for SRQ */
+		if (!mqp->ibqp.srq) {
+			if (mqp->rq.tail != mqp->rq.head) {
+				recv_mcq = to_mcq(mqp->ibqp.recv_cq);
+				spin_lock_irqsave(&recv_mcq->lock, flags_cq);
+				if (recv_mcq->mcq.comp &&
+				    mqp->ibqp.recv_cq->comp_handler) {
+					if (!recv_mcq->mcq.reset_notify_added) {
+						recv_mcq->mcq.reset_notify_added = 1;
+						list_add_tail(&recv_mcq->mcq.reset_notify,
+							      &cq_notify_list);
+					}
+				}
+				spin_unlock_irqrestore(&recv_mcq->lock,
+						       flags_cq);
+			}
+		}
+		spin_unlock_irqrestore(&mqp->rq.lock, flags_qp);
+	}
+
+	list_for_each_entry(mcq, &cq_notify_list, reset_notify) {
+		mcq->comp(mcq);
+	}
+	spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags);
+	pr_warn("mlx4_ib_handle_catas_error ended\n");
+}
+
 static void handle_bonded_port_state_event(struct work_struct *work)
 {
 	struct ib_event_work *ew =
@@ -2701,6 +2764,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 	case MLX4_DEV_EVENT_CATASTROPHIC_ERROR:
 		ibdev->ib_active = false;
 		ibev.event = IB_EVENT_DEVICE_FATAL;
+		mlx4_ib_handle_catas_error(ibdev);
 		break;
 
 	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 721540c9163..f829fd935b7 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -110,6 +110,9 @@ struct mlx4_ib_cq {
 	struct mutex		resize_mutex;
 	struct ib_umem	       *umem;
 	struct ib_umem	       *resize_umem;
+	/* List of qps that it serves.*/
+	struct list_head		send_qp_list;
+	struct list_head		recv_qp_list;
 };
 
 struct mlx4_ib_mr {
@@ -300,6 +303,9 @@ struct mlx4_ib_qp {
 	struct mlx4_roce_smac_vlan_info pri;
 	struct mlx4_roce_smac_vlan_info alt;
 	u64			reg_id;
+	struct list_head	qps_list;
+	struct list_head	cq_recv_list;
+	struct list_head	cq_send_list;
 };
 
 struct mlx4_ib_srq {
@@ -535,6 +541,9 @@ struct mlx4_ib_dev {
 	/* lock when destroying qp1_proxy and getting netdev events */
 	struct mutex		qp1_proxy_lock[MLX4_MAX_PORTS];
 	u8			bond_next_port;
+	/* protect resources needed as part of reset flow */
+	spinlock_t		reset_flow_resource_lock;
+	struct list_head		qp_list;
 };
 
 struct ib_event_work {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 792f9dc86ad..dfc6ca128a7 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -46,6 +46,11 @@
 #include "mlx4_ib.h"
 #include "user.h"
 
+static void mlx4_ib_lock_cqs(struct mlx4_ib_cq *send_cq,
+			     struct mlx4_ib_cq *recv_cq);
+static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq,
+			       struct mlx4_ib_cq *recv_cq);
+
 enum {
 	MLX4_IB_ACK_REQ_FREQ	= 8,
 };
@@ -618,6 +623,8 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	struct mlx4_ib_sqp *sqp;
 	struct mlx4_ib_qp *qp;
 	enum mlx4_ib_qp_type qp_type = (enum mlx4_ib_qp_type) init_attr->qp_type;
+	struct mlx4_ib_cq *mcq;
+	unsigned long flags;
 
 	/* When tunneling special qps, we use a plain UD qp */
 	if (sqpn) {
@@ -828,6 +835,24 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	qp->mqp.event = mlx4_ib_qp_event;
 	if (!*caller_qp)
 		*caller_qp = qp;
+
+	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
+	mlx4_ib_lock_cqs(to_mcq(init_attr->send_cq),
+			 to_mcq(init_attr->recv_cq));
+	/* Maintain device to QPs access, needed for further handling
+	 * via reset flow
+	 */
+	list_add_tail(&qp->qps_list, &dev->qp_list);
+	/* Maintain CQ to QPs access, needed for further handling
+	 * via reset flow
+	 */
+	mcq = to_mcq(init_attr->send_cq);
+	list_add_tail(&qp->cq_send_list, &mcq->send_qp_list);
+	mcq = to_mcq(init_attr->recv_cq);
+	list_add_tail(&qp->cq_recv_list, &mcq->recv_qp_list);
+	mlx4_ib_unlock_cqs(to_mcq(init_attr->send_cq),
+			   to_mcq(init_attr->recv_cq));
+	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
 	return 0;
 
 err_qpn:
@@ -886,13 +911,13 @@ static void mlx4_ib_lock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *recv
 	__acquires(&send_cq->lock) __acquires(&recv_cq->lock)
 {
 	if (send_cq == recv_cq) {
-		spin_lock_irq(&send_cq->lock);
+		spin_lock(&send_cq->lock);
 		__acquire(&recv_cq->lock);
 	} else if (send_cq->mcq.cqn < recv_cq->mcq.cqn) {
-		spin_lock_irq(&send_cq->lock);
+		spin_lock(&send_cq->lock);
 		spin_lock_nested(&recv_cq->lock, SINGLE_DEPTH_NESTING);
 	} else {
-		spin_lock_irq(&recv_cq->lock);
+		spin_lock(&recv_cq->lock);
 		spin_lock_nested(&send_cq->lock, SINGLE_DEPTH_NESTING);
 	}
 }
@@ -902,13 +927,13 @@ static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *re
 {
 	if (send_cq == recv_cq) {
 		__release(&recv_cq->lock);
-		spin_unlock_irq(&send_cq->lock);
+		spin_unlock(&send_cq->lock);
 	} else if (send_cq->mcq.cqn < recv_cq->mcq.cqn) {
 		spin_unlock(&recv_cq->lock);
-		spin_unlock_irq(&send_cq->lock);
+		spin_unlock(&send_cq->lock);
 	} else {
 		spin_unlock(&send_cq->lock);
-		spin_unlock_irq(&recv_cq->lock);
+		spin_unlock(&recv_cq->lock);
 	}
 }
 
@@ -953,6 +978,7 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 			      int is_user)
 {
 	struct mlx4_ib_cq *send_cq, *recv_cq;
+	unsigned long flags;
 
 	if (qp->state != IB_QPS_RESET) {
 		if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state),
@@ -984,8 +1010,13 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 
 	get_cqs(qp, &send_cq, &recv_cq);
 
+	spin_lock_irqsave(&dev->reset_flow_resource_lock, flags);
 	mlx4_ib_lock_cqs(send_cq, recv_cq);
 
+	/* del from lists under both locks above to protect reset flow paths */
+	list_del(&qp->qps_list);
+	list_del(&qp->cq_send_list);
+	list_del(&qp->cq_recv_list);
 	if (!is_user) {
 		__mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn,
 				 qp->ibqp.srq ? to_msrq(qp->ibqp.srq): NULL);
@@ -996,6 +1027,7 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 	mlx4_qp_remove(dev->dev, &qp->mqp);
 
 	mlx4_ib_unlock_cqs(send_cq, recv_cq);
+	spin_unlock_irqrestore(&dev->reset_flow_resource_lock, flags);
 
 	mlx4_qp_free(dev->dev, &qp->mqp);
 
@@ -2618,8 +2650,15 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	__be32 uninitialized_var(lso_hdr_sz);
 	__be32 blh;
 	int i;
+	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
+	if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
+		err = -EIO;
+		*bad_wr = wr;
+		nreq = 0;
+		goto out;
+	}
 
 	ind = qp->sq_next_wqe;
 
@@ -2917,10 +2956,18 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 	int ind;
 	int max_gs;
 	int i;
+	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
 
 	max_gs = qp->rq.max_gs;
 	spin_lock_irqsave(&qp->rq.lock, flags);
 
+	if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
+		err = -EIO;
+		*bad_wr = wr;
+		nreq = 0;
+		goto out;
+	}
+
 	ind = qp->rq.head & (qp->rq.wqe_cnt - 1);
 
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 62d9285300a..dce5dfe3a70 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -316,8 +316,15 @@ int mlx4_ib_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 	int err = 0;
 	int nreq;
 	int i;
+	struct mlx4_ib_dev *mdev = to_mdev(ibsrq->device);
 
 	spin_lock_irqsave(&srq->lock, flags);
+	if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
+		err = -EIO;
+		*bad_wr = wr;
+		nreq = 0;
+		goto out;
+	}
 
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
 		if (unlikely(wr->num_sge > srq->msrq.max_gs)) {
@@ -362,6 +369,7 @@ int mlx4_ib_post_srq_recv(struct ib_srq *ibsrq, struct ib_recv_wr *wr,
 
 		*srq->db.db = cpu_to_be32(srq->wqe_ctr);
 	}
+out:
 
 	spin_unlock_irqrestore(&srq->lock, flags);
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index c116cb02475..e4ebff7e9d0 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -689,6 +689,8 @@ struct mlx4_cq {
 		void (*comp)(struct mlx4_cq *);
 		void		*priv;
 	} tasklet_ctx;
+	int		reset_notify_added;
+	struct list_head	reset_notify;
 };
 
 struct mlx4_qp {
-- 
cgit v1.2.3-70-g09d2


From a4505152044c31f7b8e108a87ab2009901d96d0e Mon Sep 17 00:00:00 2001
From: Hariprasad Shenai <hariprasad@chelsio.com>
Date: Mon, 9 Feb 2015 12:07:29 +0530
Subject: ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion
 ROM version

Renamed the reserved1 member of struct ethtool_drvinfo to erom_version to get
expansion/option ROM version of the adapter if present.

Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 5f66d9c2889..2e49fc880d2 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -139,6 +139,7 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep)
 
 #define ETHTOOL_FWVERS_LEN	32
 #define ETHTOOL_BUSINFO_LEN	32
+#define ETHTOOL_EROMVERS_LEN	32
 
 /**
  * struct ethtool_drvinfo - general driver and device information
@@ -148,6 +149,7 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep)
  *	not be an empty string.
  * @version: Driver version string; may be an empty string
  * @fw_version: Firmware version string; may be an empty string
+ * @erom_version: Expansion ROM version string; may be an empty string
  * @bus_info: Device bus address.  This should match the dev_name()
  *	string for the underlying bus device, if there is one.  May be
  *	an empty string.
@@ -176,7 +178,7 @@ struct ethtool_drvinfo {
 	char	version[32];
 	char	fw_version[ETHTOOL_FWVERS_LEN];
 	char	bus_info[ETHTOOL_BUSINFO_LEN];
-	char	reserved1[32];
+	char	erom_version[ETHTOOL_EROMVERS_LEN];
 	char	reserved2[12];
 	__u32	n_priv_flags;
 	__u32	n_stats;
-- 
cgit v1.2.3-70-g09d2


From 8381eacf5c3b35cf7755f4bc521c4d56d24c1cd9 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Mon, 9 Feb 2015 09:38:21 -0500
Subject: ipv6: Make __ipv6_select_ident static

Make __ipv6_select_ident() static as it isn't used outside
the file.

Fixes: 0508c07f5e0c9 (ipv6: Select fragment id during UFO segmentation if not set.)
Signed-off-by: Vladislav Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h     | 2 --
 net/ipv6/output_core.c | 3 ++-
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6e416f6d3e3..fde3b593c3f 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -671,8 +671,6 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
-u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
-			struct in6_addr *src);
 void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 void ipv6_proxy_select_ident(struct sk_buff *skb);
 
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index a86cf60f0ca..74581f706c4 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -9,7 +9,8 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
-u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src)
+static u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
+			       struct in6_addr *src)
 {
 	u32 hash, id;
 
-- 
cgit v1.2.3-70-g09d2


From b0f9ca53cbb103e9240a29a974e0b6085e58f9f7 Mon Sep 17 00:00:00 2001
From: Fan Du <fan.du@intel.com>
Date: Tue, 10 Feb 2015 09:53:16 +0800
Subject: ipv4: Namespecify TCP PMTU mechanism

Packetization Layer Path MTU Discovery works separately beside
Path MTU Discovery at IP level, different net namespace has
various requirements on which one to chose, e.g., a virutalized
container instance would require TCP PMTU to probe an usable
effective mtu for underlying tunnel, while the host would
employ classical ICMP based PMTU to function.

Hence making TCP PMTU mechanism per net namespace to decouple
two functionality. Furthermore the probe base MSS should also
be configured separately for each namespace.

Signed-off-by: Fan Du <fan.du@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/ipv4.h   |  2 ++
 include/net/tcp.h          |  2 --
 net/ipv4/sysctl_net_ipv4.c | 28 ++++++++++++++--------------
 net/ipv4/tcp_ipv4.c        |  1 +
 net/ipv4/tcp_output.c      |  8 +++-----
 net/ipv4/tcp_timer.c       |  7 +++++--
 6 files changed, 25 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index e0bdcb14732..dbe225478ad 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -82,6 +82,8 @@ struct netns_ipv4 {
 
 	int sysctl_fwmark_reflect;
 	int sysctl_tcp_fwmark_accept;
+	int sysctl_tcp_mtu_probing;
+	int sysctl_tcp_base_mss;
 
 	struct ping_group_range ping_group_range;
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index da4196fb78d..8d6b983d509 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -262,8 +262,6 @@ extern int sysctl_tcp_low_latency;
 extern int sysctl_tcp_nometrics_save;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
-extern int sysctl_tcp_mtu_probing;
-extern int sysctl_tcp_base_mss;
 extern int sysctl_tcp_workaround_signed_windows;
 extern int sysctl_tcp_slow_start_after_idle;
 extern int sysctl_tcp_thin_linear_timeouts;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 82601a68cf9..d151539da8e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -603,20 +603,6 @@ static struct ctl_table ipv4_table[] = {
 		.maxlen		= TCP_CA_NAME_MAX,
 		.proc_handler	= proc_tcp_congestion_control,
 	},
-	{
-		.procname	= "tcp_mtu_probing",
-		.data		= &sysctl_tcp_mtu_probing,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "tcp_base_mss",
-		.data		= &sysctl_tcp_base_mss,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "tcp_workaround_signed_windows",
 		.data		= &sysctl_tcp_workaround_signed_windows,
@@ -883,6 +869,20 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "tcp_mtu_probing",
+		.data		= &init_net.ipv4.sysctl_tcp_mtu_probing,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_base_mss",
+		.data		= &init_net.ipv4.sysctl_tcp_base_mss,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 67bc95fb5d9..5a2dfed4783 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2459,6 +2459,7 @@ static int __net_init tcp_sk_init(struct net *net)
 		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
 	}
 	net->ipv4.sysctl_tcp_ecn = 2;
+	net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS;
 	return 0;
 
 fail:
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4fcc9a76884..a2a796c5536 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -59,9 +59,6 @@ int sysctl_tcp_limit_output_bytes __read_mostly = 131072;
  */
 int sysctl_tcp_tso_win_divisor __read_mostly = 3;
 
-int sysctl_tcp_mtu_probing __read_mostly = 0;
-int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
-
 /* By default, RFC2861 behavior.  */
 int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
 
@@ -1350,11 +1347,12 @@ void tcp_mtup_init(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct net *net = sock_net(sk);
 
-	icsk->icsk_mtup.enabled = sysctl_tcp_mtu_probing > 1;
+	icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1;
 	icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
 			       icsk->icsk_af_ops->net_header_len;
-	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss);
+	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
 	icsk->icsk_mtup.probe_size = 0;
 }
 EXPORT_SYMBOL(tcp_mtup_init);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 1829c7fbc77..0732b787904 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -101,17 +101,20 @@ static int tcp_orphan_retries(struct sock *sk, int alive)
 
 static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 {
+	struct net *net = sock_net(sk);
+
 	/* Black hole detection */
-	if (sysctl_tcp_mtu_probing) {
+	if (net->ipv4.sysctl_tcp_mtu_probing) {
 		if (!icsk->icsk_mtup.enabled) {
 			icsk->icsk_mtup.enabled = 1;
 			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 		} else {
+			struct net *net = sock_net(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
 			int mss;
 
 			mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
-			mss = min(sysctl_tcp_base_mss, mss);
+			mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
 			mss = max(mss, 68 - tp->tcp_header_len);
 			icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
-- 
cgit v1.2.3-70-g09d2


From 3cf385713460eb2bb4cb7ceb8ed89833b00b594b Mon Sep 17 00:00:00 2001
From: Antonios Motakis <a.motakis@virtualopensystems.com>
Date: Tue, 6 Jan 2015 11:15:11 +0100
Subject: ARM: 8256/1: driver coamba: add device binding path 'driver_override'

As already demonstrated with PCI [1] and the platform bus [2], a
driver_override property in sysfs can be used to bypass the id
matching of a device to a AMBA driver. This can be used by VFIO to
bind to any AMBA device requested by the user.

[1] http://lists-archives.com/linux-kernel/28030441-pci-introduce-new-device-binding-path-using-pci_dev-driver_override.html
[2] https://www.redhat.com/archives/libvir-list/2014-April/msg00382.html

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Reviewed-by: Kim Phillips <kim.phillips@freescale.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 Documentation/ABI/testing/sysfs-bus-amba | 20 ++++++++++++++
 drivers/amba/bus.c                       | 47 ++++++++++++++++++++++++++++++++
 include/linux/amba/bus.h                 |  1 +
 3 files changed, 68 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-bus-amba

(limited to 'include')

diff --git a/Documentation/ABI/testing/sysfs-bus-amba b/Documentation/ABI/testing/sysfs-bus-amba
new file mode 100644
index 00000000000..e7b54677cfb
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-amba
@@ -0,0 +1,20 @@
+What:		/sys/bus/amba/devices/.../driver_override
+Date:		September 2014
+Contact:	Antonios Motakis <a.motakis@virtualopensystems.com>
+Description:
+		This file allows the driver for a device to be specified which
+		will override standard OF, ACPI, ID table, and name matching.
+		When specified, only a driver with a name matching the value
+		written to driver_override will have an opportunity to bind to
+		the device. The override is specified by writing a string to the
+		driver_override file (echo vfio-amba > driver_override)	and may
+		be cleared with an empty string (echo > driver_override).
+		This returns the device to standard matching rules binding.
+		Writing to driver_override does not automatically unbind the
+		device from its current driver or make any attempt to
+		automatically load the specified driver. If no driver with a
+		matching name is currently loaded in the kernel, the device will
+		not bind to any driver. This also allows devices to opt-out of
+		driver binding using a driver_override name such as "none".
+		Only a single driver may be specified in the override, there is
+		no support for parsing delimiters.
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 52ddd9fbb55..f0099360039 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -18,6 +18,7 @@
 #include <linux/pm_domain.h>
 #include <linux/amba/bus.h>
 #include <linux/sizes.h>
+#include <linux/limits.h>
 
 #include <asm/irq.h>
 
@@ -43,6 +44,10 @@ static int amba_match(struct device *dev, struct device_driver *drv)
 	struct amba_device *pcdev = to_amba_device(dev);
 	struct amba_driver *pcdrv = to_amba_driver(drv);
 
+	/* When driver_override is set, only bind to the matching driver */
+	if (pcdev->driver_override)
+		return !strcmp(pcdev->driver_override, drv->name);
+
 	return amba_lookup(pcdrv->id_table, pcdev) != NULL;
 }
 
@@ -59,6 +64,47 @@ static int amba_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return retval;
 }
 
+static ssize_t driver_override_show(struct device *_dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct amba_device *dev = to_amba_device(_dev);
+
+	if (!dev->driver_override)
+		return 0;
+
+	return sprintf(buf, "%s\n", dev->driver_override);
+}
+
+static ssize_t driver_override_store(struct device *_dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct amba_device *dev = to_amba_device(_dev);
+	char *driver_override, *old = dev->driver_override, *cp;
+
+	if (count > PATH_MAX)
+		return -EINVAL;
+
+	driver_override = kstrndup(buf, count, GFP_KERNEL);
+	if (!driver_override)
+		return -ENOMEM;
+
+	cp = strchr(driver_override, '\n');
+	if (cp)
+		*cp = '\0';
+
+	if (strlen(driver_override)) {
+		dev->driver_override = driver_override;
+	} else {
+	       kfree(driver_override);
+	       dev->driver_override = NULL;
+	}
+
+	kfree(old);
+
+	return count;
+}
+
 #define amba_attr_func(name,fmt,arg...)					\
 static ssize_t name##_show(struct device *_dev,				\
 			   struct device_attribute *attr, char *buf)	\
@@ -81,6 +127,7 @@ amba_attr_func(resource, "\t%016llx\t%016llx\t%016lx\n",
 static struct device_attribute amba_dev_attrs[] = {
 	__ATTR_RO(id),
 	__ATTR_RO(resource),
+	__ATTR_RW(driver_override),
 	__ATTR_NULL,
 };
 
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 0ab5f8e0dea..50fc6686840 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -33,6 +33,7 @@ struct amba_device {
 	struct clk		*pclk;
 	unsigned int		periphid;
 	unsigned int		irq[AMBA_NR_IRQS];
+	char			*driver_override;
 };
 
 struct amba_driver {
-- 
cgit v1.2.3-70-g09d2


From 6ee8e25fc3e916193bce4ebb43d5439e1e2144ab Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 10 Feb 2015 14:08:32 -0800
Subject: fsnotify: fix handling of renames in audit

Commit e9fd702a58c4 ("audit: convert audit watches to use fsnotify
instead of inotify") broke handling of renames in audit.  Audit code
wants to update inode number of an inode corresponding to watched name
in a directory.  When something gets renamed into a directory to a
watched name, inotify previously passed moved inode to audit code
however new fsnotify code passes directory inode where the change
happened.  That confuses audit and it starts watching parent directory
instead of a file in a directory.

This can be observed for example by doing:

  cd /tmp
  touch foo bar
  auditctl -w /tmp/foo
  touch foo
  mv bar foo
  touch foo

In audit log we see events like:

  type=CONFIG_CHANGE msg=audit(1423563584.155:90): auid=1000 ses=2 op="updated rules" path="/tmp/foo" key=(null) list=4 res=1
  ...
  type=PATH msg=audit(1423563584.155:91): item=2 name="bar" inode=1046884 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=DELETE
  type=PATH msg=audit(1423563584.155:91): item=3 name="foo" inode=1046842 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=DELETE
  type=PATH msg=audit(1423563584.155:91): item=4 name="foo" inode=1046884 dev=08:0 2 mode=0100644 ouid=0 ogid=0 rdev=00:00 nametype=CREATE
  ...

and that's it - we see event for the first touch after creating the
audit rule, we see events for rename but we don't see any event for the
last touch.  However we start seeing events for unrelated stuff
happening in /tmp.

Fix the problem by passing moved inode as data in the FS_MOVED_FROM and
FS_MOVED_TO events instead of the directory where the change happens.
This doesn't introduce any new problems because noone besides
audit_watch.c cares about the passed value:

  fs/notify/fanotify/fanotify.c cares only about FSNOTIFY_EVENT_PATH events.
  fs/notify/dnotify/dnotify.c doesn't care about passed 'data' value at all.
  fs/notify/inotify/inotify_fsnotify.c uses 'data' only for FSNOTIFY_EVENT_PATH.
  kernel/audit_tree.c doesn't care about passed 'data' at all.
  kernel/audit_watch.c expects moved inode as 'data'.

Fixes: e9fd702a58c49db ("audit: convert audit watches to use fsnotify instead of inotify")
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Eric Paris <eparis@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fsnotify.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 1c804b057fb..7ee1774edee 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -101,8 +101,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		new_dir_mask |= FS_ISDIR;
 	}
 
-	fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
-	fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie);
+	fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name,
+		 fs_cookie);
+	fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name,
+		 fs_cookie);
 
 	if (target)
 		fsnotify_link_count(target);
-- 
cgit v1.2.3-70-g09d2


From ccaafd7fd039aebc9359a9799f8558b01f1c2adc Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Tue, 10 Feb 2015 14:09:35 -0800
Subject: mm: don't use compound_head() in virt_to_head_page()

compound_head() is implemented with assumption that there would be race
condition when checking tail flag.  This assumption is only true when we
try to access arbitrary positioned struct page.

The situation that virt_to_head_page() is called is different case.  We
call virt_to_head_page() only in the range of allocated pages, so there
is no race condition on tail flag.  In this case, we don't need to
handle race condition and we can reduce overhead slightly.  This patch
implements compound_head_fast() which is similar with compound_head()
except tail flag race handling.  And then, virt_to_head_page() uses this
optimized function to improve performance.

I saw 1.8% win in a fast-path loop over kmem_cache_alloc/free, (14.063
ns -> 13.810 ns) if target object is on tail page.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index dd5ea3016fc..2c6fd3c5424 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -446,6 +446,12 @@ static inline struct page *compound_head_by_tail(struct page *tail)
 	return tail;
 }
 
+/*
+ * Since either compound page could be dismantled asynchronously in THP
+ * or we access asynchronously arbitrary positioned struct page, there
+ * would be tail flag race. To handle this race, we should call
+ * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
+ */
 static inline struct page *compound_head(struct page *page)
 {
 	if (unlikely(PageTail(page)))
@@ -453,6 +459,18 @@ static inline struct page *compound_head(struct page *page)
 	return page;
 }
 
+/*
+ * If we access compound page synchronously such as access to
+ * allocated page, there is no need to handle tail flag race, so we can
+ * check tail flag directly without any synchronization primitive.
+ */
+static inline struct page *compound_head_fast(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		return page->first_page;
+	return page;
+}
+
 /*
  * The atomic page->_mapcount, starts from -1: so that transitions
  * both from it and to it can be tracked, using atomic_inc_and_test
@@ -531,7 +549,14 @@ static inline void get_page(struct page *page)
 static inline struct page *virt_to_head_page(const void *x)
 {
 	struct page *page = virt_to_page(x);
-	return compound_head(page);
+
+	/*
+	 * We don't need to worry about synchronization of tail flag
+	 * when we call virt_to_head_page() since it is only called for
+	 * already allocated page and this page won't be freed until
+	 * this virt_to_head_page() is finished. So use _fast variant.
+	 */
+	return compound_head_fast(page);
 }
 
 /*
-- 
cgit v1.2.3-70-g09d2


From c8d78c1823f46519473949d33f0d1d33fe21ea16 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:09:46 -0800
Subject: mm: replace remap_file_pages() syscall with emulation

remap_file_pages(2) was invented to be able efficiently map parts of
huge file into limited 32-bit virtual address space such as in database
workloads.

Nonlinear mappings are pain to support and it seems there's no
legitimate use-cases nowadays since 64-bit systems are widely available.

Let's drop it and get rid of all these special-cased code.

The patch replaces the syscall with emulation which creates new VMA on
each remap_file_pages(), unless they it can be merged with an adjacent
one.

I didn't find *any* real code that uses remap_file_pages(2) to test
emulation impact on.  I've checked Debian code search and source of all
packages in ALT Linux.  No real users: libc wrappers, mentions in
strace, gdb, valgrind and this kind of stuff.

There are few basic tests in LTP for the syscall.  They work just fine
with emulation.

To test performance impact, I've written small test case which
demonstrate pretty much worst case scenario: map 4G shmfs file, write to
begin of every page pgoff of the page, remap pages in reverse order,
read every page.

The test creates 1 million of VMAs if emulation is in use, so I had to
set vm.max_map_count to 1100000 to avoid -ENOMEM.

Before:		23.3 ( +-  4.31% ) seconds
After:		43.9 ( +-  0.85% ) seconds
Slowdown:	1.88x

I believe we can live with that.

Test case:

        #define _GNU_SOURCE
        #include <assert.h>
        #include <stdlib.h>
        #include <stdio.h>
        #include <sys/mman.h>

        #define MB	(1024UL * 1024)
        #define SIZE	(4096 * MB)

        int main(int argc, char **argv)
        {
                unsigned long *p;
                long i, pass;

                for (pass = 0; pass < 10; pass++) {
                        p = mmap(NULL, SIZE, PROT_READ|PROT_WRITE,
                                        MAP_SHARED | MAP_ANONYMOUS, -1, 0);
                        if (p == MAP_FAILED) {
                                perror("mmap");
                                return -1;
                        }

                        for (i = 0; i < SIZE / 4096; i++)
                                p[i * 4096 / sizeof(*p)] = i;

                        for (i = 0; i < SIZE / 4096; i++) {
                                if (remap_file_pages(p + i * 4096 / sizeof(*p), 4096,
                                                0, (SIZE - 4096 * (i + 1)) >> 12, 0)) {
                                        perror("remap_file_pages");
                                        return -1;
                                }
                        }

                        for (i = SIZE / 4096 - 1; i >= 0; i--)
                                assert(p[i * 4096 / sizeof(*p)] == SIZE / 4096 - i - 1);

                        munmap(p, SIZE);
                }

                return 0;
        }

[akpm@linux-foundation.org: fix spello]
[sasha.levin@oracle.com: initialize populate before usage]
[sasha.levin@oracle.com: grab file ref to prevent race while mmaping]
Signed-off-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Armin Rigo <arigo@tunes.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/remap_file_pages.txt |   7 +-
 include/linux/fs.h                    |   8 +-
 mm/Makefile                           |   2 +-
 mm/fremap.c                           | 283 ----------------------------------
 mm/mmap.c                             |  69 +++++++++
 mm/nommu.c                            |   8 -
 6 files changed, 79 insertions(+), 298 deletions(-)
 delete mode 100644 mm/fremap.c

(limited to 'include')

diff --git a/Documentation/vm/remap_file_pages.txt b/Documentation/vm/remap_file_pages.txt
index 560e4363a55..f609142f406 100644
--- a/Documentation/vm/remap_file_pages.txt
+++ b/Documentation/vm/remap_file_pages.txt
@@ -18,10 +18,9 @@ on 32-bit systems to map files bigger than can linearly fit into 32-bit
 virtual address space. This use-case is not critical anymore since 64-bit
 systems are widely available.
 
-The plan is to deprecate the syscall and replace it with an emulation.
-The emulation will create new VMAs instead of nonlinear mappings. It's
-going to work slower for rare users of remap_file_pages() but ABI is
-preserved.
+The syscall is deprecated and replaced it with an emulation now. The
+emulation creates new VMAs instead of nonlinear mappings. It's going to
+work slower for rare users of remap_file_pages() but ABI is preserved.
 
 One side effect of emulation (apart from performance) is that user can hit
 vm.max_map_count limit more easily due to additional VMAs. See comment for
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42efe13077b..60c4996df7f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2481,8 +2481,12 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
-		unsigned long size, pgoff_t pgoff);
+static inline int generic_file_remap_pages(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long size, pgoff_t pgoff)
+{
+	BUG();
+	return 0;
+}
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/mm/Makefile b/mm/Makefile
index 4bf586e6637..3548460ab7b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -3,7 +3,7 @@
 #
 
 mmu-y			:= nommu.o
-mmu-$(CONFIG_MMU)	:= fremap.o gup.o highmem.o memory.o mincore.o \
+mmu-$(CONFIG_MMU)	:= gup.o highmem.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
 			   vmalloc.o pagewalk.o pgtable-generic.o
 
diff --git a/mm/fremap.c b/mm/fremap.c
deleted file mode 100644
index 2805d71cf47..00000000000
--- a/mm/fremap.c
+++ /dev/null
@@ -1,283 +0,0 @@
-/*
- *   linux/mm/fremap.c
- * 
- * Explicit pagetable population and nonlinear (random) mappings support.
- *
- * started by Ingo Molnar, Copyright (C) 2002, 2003
- */
-#include <linux/export.h>
-#include <linux/backing-dev.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/file.h>
-#include <linux/mman.h>
-#include <linux/pagemap.h>
-#include <linux/swapops.h>
-#include <linux/rmap.h>
-#include <linux/syscalls.h>
-#include <linux/mmu_notifier.h>
-
-#include <asm/mmu_context.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-#include "internal.h"
-
-static int mm_counter(struct page *page)
-{
-	return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
-}
-
-static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
-			unsigned long addr, pte_t *ptep)
-{
-	pte_t pte = *ptep;
-	struct page *page;
-	swp_entry_t entry;
-
-	if (pte_present(pte)) {
-		flush_cache_page(vma, addr, pte_pfn(pte));
-		pte = ptep_clear_flush_notify(vma, addr, ptep);
-		page = vm_normal_page(vma, addr, pte);
-		if (page) {
-			if (pte_dirty(pte))
-				set_page_dirty(page);
-			update_hiwater_rss(mm);
-			dec_mm_counter(mm, mm_counter(page));
-			page_remove_rmap(page);
-			page_cache_release(page);
-		}
-	} else {	/* zap_pte() is not called when pte_none() */
-		if (!pte_file(pte)) {
-			update_hiwater_rss(mm);
-			entry = pte_to_swp_entry(pte);
-			if (non_swap_entry(entry)) {
-				if (is_migration_entry(entry)) {
-					page = migration_entry_to_page(entry);
-					dec_mm_counter(mm, mm_counter(page));
-				}
-			} else {
-				free_swap_and_cache(entry);
-				dec_mm_counter(mm, MM_SWAPENTS);
-			}
-		}
-		pte_clear_not_present_full(mm, addr, ptep, 0);
-	}
-}
-
-/*
- * Install a file pte to a given virtual memory address, release any
- * previously existing mapping.
- */
-static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long pgoff, pgprot_t prot)
-{
-	int err = -ENOMEM;
-	pte_t *pte, ptfile;
-	spinlock_t *ptl;
-
-	pte = get_locked_pte(mm, addr, &ptl);
-	if (!pte)
-		goto out;
-
-	ptfile = pgoff_to_pte(pgoff);
-
-	if (!pte_none(*pte))
-		zap_pte(mm, vma, addr, pte);
-
-	set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile));
-	/*
-	 * We don't need to run update_mmu_cache() here because the "file pte"
-	 * being installed by install_file_pte() is not a real pte - it's a
-	 * non-present entry (like a swap entry), noting what file offset should
-	 * be mapped there when there's a fault (in a non-linear vma where
-	 * that's not obvious).
-	 */
-	pte_unmap_unlock(pte, ptl);
-	err = 0;
-out:
-	return err;
-}
-
-int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
-			     unsigned long size, pgoff_t pgoff)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	int err;
-
-	do {
-		err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
-		if (err)
-			return err;
-
-		size -= PAGE_SIZE;
-		addr += PAGE_SIZE;
-		pgoff++;
-	} while (size);
-
-	return 0;
-}
-EXPORT_SYMBOL(generic_file_remap_pages);
-
-/**
- * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma
- * @start: start of the remapped virtual memory range
- * @size: size of the remapped virtual memory range
- * @prot: new protection bits of the range (see NOTE)
- * @pgoff: to-be-mapped page of the backing store file
- * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
- *
- * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma
- * (shared backing store file).
- *
- * This syscall works purely via pagetables, so it's the most efficient
- * way to map the same (large) file into a given virtual window. Unlike
- * mmap()/mremap() it does not create any new vmas. The new mappings are
- * also safe across swapout.
- *
- * NOTE: the @prot parameter right now is ignored (but must be zero),
- * and the vma's default protection is used. Arbitrary protections
- * might be implemented in the future.
- */
-SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
-		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
-{
-	struct mm_struct *mm = current->mm;
-	struct address_space *mapping;
-	struct vm_area_struct *vma;
-	int err = -EINVAL;
-	int has_write_lock = 0;
-	vm_flags_t vm_flags = 0;
-
-	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
-			"See Documentation/vm/remap_file_pages.txt.\n",
-			current->comm, current->pid);
-
-	if (prot)
-		return err;
-	/*
-	 * Sanitize the syscall parameters:
-	 */
-	start = start & PAGE_MASK;
-	size = size & PAGE_MASK;
-
-	/* Does the address range wrap, or is the span zero-sized? */
-	if (start + size <= start)
-		return err;
-
-	/* Does pgoff wrap? */
-	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
-		return err;
-
-	/* Can we represent this offset inside this architecture's pte's? */
-#if PTE_FILE_MAX_BITS < BITS_PER_LONG
-	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
-		return err;
-#endif
-
-	/* We need down_write() to change vma->vm_flags. */
-	down_read(&mm->mmap_sem);
- retry:
-	vma = find_vma(mm, start);
-
-	/*
-	 * Make sure the vma is shared, that it supports prefaulting,
-	 * and that the remapped range is valid and fully within
-	 * the single existing vma.
-	 */
-	if (!vma || !(vma->vm_flags & VM_SHARED))
-		goto out;
-
-	if (!vma->vm_ops || !vma->vm_ops->remap_pages)
-		goto out;
-
-	if (start < vma->vm_start || start + size > vma->vm_end)
-		goto out;
-
-	/* Must set VM_NONLINEAR before any pages are populated. */
-	if (!(vma->vm_flags & VM_NONLINEAR)) {
-		/*
-		 * vm_private_data is used as a swapout cursor
-		 * in a VM_NONLINEAR vma.
-		 */
-		if (vma->vm_private_data)
-			goto out;
-
-		/* Don't need a nonlinear mapping, exit success */
-		if (pgoff == linear_page_index(vma, start)) {
-			err = 0;
-			goto out;
-		}
-
-		if (!has_write_lock) {
-get_write_lock:
-			up_read(&mm->mmap_sem);
-			down_write(&mm->mmap_sem);
-			has_write_lock = 1;
-			goto retry;
-		}
-		mapping = vma->vm_file->f_mapping;
-		/*
-		 * page_mkclean doesn't work on nonlinear vmas, so if
-		 * dirty pages need to be accounted, emulate with linear
-		 * vmas.
-		 */
-		if (mapping_cap_account_dirty(mapping)) {
-			unsigned long addr;
-			struct file *file = get_file(vma->vm_file);
-			/* mmap_region may free vma; grab the info now */
-			vm_flags = vma->vm_flags;
-
-			addr = mmap_region(file, start, size, vm_flags, pgoff);
-			fput(file);
-			if (IS_ERR_VALUE(addr)) {
-				err = addr;
-			} else {
-				BUG_ON(addr != start);
-				err = 0;
-			}
-			goto out_freed;
-		}
-		i_mmap_lock_write(mapping);
-		flush_dcache_mmap_lock(mapping);
-		vma->vm_flags |= VM_NONLINEAR;
-		vma_interval_tree_remove(vma, &mapping->i_mmap);
-		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
-		flush_dcache_mmap_unlock(mapping);
-		i_mmap_unlock_write(mapping);
-	}
-
-	if (vma->vm_flags & VM_LOCKED) {
-		/*
-		 * drop PG_Mlocked flag for over-mapped range
-		 */
-		if (!has_write_lock)
-			goto get_write_lock;
-		vm_flags = vma->vm_flags;
-		munlock_vma_pages_range(vma, start, start + size);
-		vma->vm_flags = vm_flags;
-	}
-
-	mmu_notifier_invalidate_range_start(mm, start, start + size);
-	err = vma->vm_ops->remap_pages(vma, start, size, pgoff);
-	mmu_notifier_invalidate_range_end(mm, start, start + size);
-
-	/*
-	 * We can't clear VM_NONLINEAR because we'd have to do
-	 * it after ->populate completes, and that would prevent
-	 * downgrading the lock.  (Locks can't be upgraded).
-	 */
-
-out:
-	if (vma)
-		vm_flags = vma->vm_flags;
-out_freed:
-	if (likely(!has_write_lock))
-		up_read(&mm->mmap_sem);
-	else
-		up_write(&mm->mmap_sem);
-	if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK)))
-		mm_populate(start, size);
-
-	return err;
-}
diff --git a/mm/mmap.c b/mm/mmap.c
index 7f684d5a808..e023dc5e59a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2634,6 +2634,75 @@ SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 	return vm_munmap(addr, len);
 }
 
+
+/*
+ * Emulation of deprecated remap_file_pages() syscall.
+ */
+SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
+{
+
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long populate = 0;
+	unsigned long ret = -EINVAL;
+	struct file *file;
+
+	pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. "
+			"See Documentation/vm/remap_file_pages.txt.\n",
+			current->comm, current->pid);
+
+	if (prot)
+		return ret;
+	start = start & PAGE_MASK;
+	size = size & PAGE_MASK;
+
+	if (start + size <= start)
+		return ret;
+
+	/* Does pgoff wrap? */
+	if (pgoff + (size >> PAGE_SHIFT) < pgoff)
+		return ret;
+
+	down_write(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+
+	if (!vma || !(vma->vm_flags & VM_SHARED))
+		goto out;
+
+	if (start < vma->vm_start || start + size > vma->vm_end)
+		goto out;
+
+	if (pgoff == linear_page_index(vma, start)) {
+		ret = 0;
+		goto out;
+	}
+
+	prot |= vma->vm_flags & VM_READ ? PROT_READ : 0;
+	prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0;
+	prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0;
+
+	flags &= MAP_NONBLOCK;
+	flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE;
+	if (vma->vm_flags & VM_LOCKED) {
+		flags |= MAP_LOCKED;
+		/* drop PG_Mlocked flag for over-mapped range */
+		munlock_vma_pages_range(vma, start, start + size);
+	}
+
+	file = get_file(vma->vm_file);
+	ret = do_mmap_pgoff(vma->vm_file, start, size,
+			prot, flags, pgoff, &populate);
+	fput(file);
+out:
+	up_write(&mm->mmap_sem);
+	if (populate)
+		mm_populate(ret, populate);
+	if (!IS_ERR_VALUE(ret))
+		ret = 0;
+	return ret;
+}
+
 static inline void verify_mm_writelocked(struct mm_struct *mm)
 {
 #ifdef CONFIG_DEBUG_VM
diff --git a/mm/nommu.c b/mm/nommu.c
index 28bd8c4dff6..541bed64e34 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1984,14 +1984,6 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_map_pages);
 
-int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
-			     unsigned long size, pgoff_t pgoff)
-{
-	BUG();
-	return 0;
-}
-EXPORT_SYMBOL(generic_file_remap_pages);
-
 static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long addr, void *buf, int len, int write)
 {
-- 
cgit v1.2.3-70-g09d2


From 8a5f14a23177061ec11daeaa3d09d0765d785c47 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:09:49 -0800
Subject: mm: drop support of non-linear mapping from unmap/zap codepath

We have remap_file_pages(2) emulation in -mm tree for few release cycles
and we plan to have it mainline in v3.20. This patchset removes rest of
VM_NONLINEAR infrastructure.

Patches 1-8 take care about generic code. They are pretty
straight-forward and can be applied without other of patches.

Rest patches removes pte_file()-related stuff from architecture-specific
code. It usually frees up one bit in non-present pte. I've tried to reuse
that bit for swap offset, where I was able to figure out how to do that.

For obvious reason I cannot test all that arch-specific code and would
like to see acks from maintainers.

In total, remap_file_pages(2) required about 1.4K lines of not-so-trivial
kernel code. That's too much for functionality nobody uses.

Tested-by: Felipe Balbi <balbi@ti.com>

This patch (of 38):

We don't create non-linear mappings anymore. Let's drop code which
handles them on unmap/zap.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  1 -
 mm/madvise.c       |  9 +-----
 mm/memory.c        | 82 ++++++++++++++----------------------------------------
 3 files changed, 22 insertions(+), 70 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2c6fd3c5424..600ef5ed469 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1146,7 +1146,6 @@ extern void user_shm_unlock(size_t, struct user_struct *);
  * Parameter block passed down to zap_pte_range in exceptional cases.
  */
 struct zap_details {
-	struct vm_area_struct *nonlinear_vma;	/* Check page->index if set */
 	struct address_space *check_mapping;	/* Check page->mapping if set */
 	pgoff_t	first_index;			/* Lowest page->index to unmap */
 	pgoff_t last_index;			/* Highest page->index to unmap */
diff --git a/mm/madvise.c b/mm/madvise.c
index a271adc9328..917754d26c1 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -278,14 +278,7 @@ static long madvise_dontneed(struct vm_area_struct *vma,
 	if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
 		return -EINVAL;
 
-	if (unlikely(vma->vm_flags & VM_NONLINEAR)) {
-		struct zap_details details = {
-			.nonlinear_vma = vma,
-			.last_index = ULONG_MAX,
-		};
-		zap_page_range(vma, start, end - start, &details);
-	} else
-		zap_page_range(vma, start, end - start, NULL);
+	zap_page_range(vma, start, end - start, NULL);
 	return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 2c3536cc6c6..9a3e73b69da 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1082,6 +1082,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
+	swp_entry_t entry;
 
 again:
 	init_rss_vec(rss);
@@ -1107,28 +1108,12 @@ again:
 				if (details->check_mapping &&
 				    details->check_mapping != page->mapping)
 					continue;
-				/*
-				 * Each page->index must be checked when
-				 * invalidating or truncating nonlinear.
-				 */
-				if (details->nonlinear_vma &&
-				    (page->index < details->first_index ||
-				     page->index > details->last_index))
-					continue;
 			}
 			ptent = ptep_get_and_clear_full(mm, addr, pte,
 							tlb->fullmm);
 			tlb_remove_tlb_entry(tlb, pte, addr);
 			if (unlikely(!page))
 				continue;
-			if (unlikely(details) && details->nonlinear_vma
-			    && linear_page_index(details->nonlinear_vma,
-						addr) != page->index) {
-				pte_t ptfile = pgoff_to_pte(page->index);
-				if (pte_soft_dirty(ptent))
-					ptfile = pte_file_mksoft_dirty(ptfile);
-				set_pte_at(mm, addr, pte, ptfile);
-			}
 			if (PageAnon(page))
 				rss[MM_ANONPAGES]--;
 			else {
@@ -1151,33 +1136,25 @@ again:
 			}
 			continue;
 		}
-		/*
-		 * If details->check_mapping, we leave swap entries;
-		 * if details->nonlinear_vma, we leave file entries.
-		 */
+		/* If details->check_mapping, we leave swap entries. */
 		if (unlikely(details))
 			continue;
-		if (pte_file(ptent)) {
-			if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
-				print_bad_pte(vma, addr, ptent, NULL);
-		} else {
-			swp_entry_t entry = pte_to_swp_entry(ptent);
 
-			if (!non_swap_entry(entry))
-				rss[MM_SWAPENTS]--;
-			else if (is_migration_entry(entry)) {
-				struct page *page;
+		entry = pte_to_swp_entry(ptent);
+		if (!non_swap_entry(entry))
+			rss[MM_SWAPENTS]--;
+		else if (is_migration_entry(entry)) {
+			struct page *page;
 
-				page = migration_entry_to_page(entry);
+			page = migration_entry_to_page(entry);
 
-				if (PageAnon(page))
-					rss[MM_ANONPAGES]--;
-				else
-					rss[MM_FILEPAGES]--;
-			}
-			if (unlikely(!free_swap_and_cache(entry)))
-				print_bad_pte(vma, addr, ptent, NULL);
+			if (PageAnon(page))
+				rss[MM_ANONPAGES]--;
+			else
+				rss[MM_FILEPAGES]--;
 		}
+		if (unlikely(!free_swap_and_cache(entry)))
+			print_bad_pte(vma, addr, ptent, NULL);
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
@@ -1277,7 +1254,7 @@ static void unmap_page_range(struct mmu_gather *tlb,
 	pgd_t *pgd;
 	unsigned long next;
 
-	if (details && !details->check_mapping && !details->nonlinear_vma)
+	if (details && !details->check_mapping)
 		details = NULL;
 
 	BUG_ON(addr >= end);
@@ -1371,7 +1348,7 @@ void unmap_vmas(struct mmu_gather *tlb,
  * @vma: vm_area_struct holding the applicable pages
  * @start: starting address of pages to zap
  * @size: number of bytes to zap
- * @details: details of nonlinear truncation or shared cache invalidation
+ * @details: details of shared cache invalidation
  *
  * Caller must protect the VMA list
  */
@@ -1397,7 +1374,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start,
  * @vma: vm_area_struct holding the applicable pages
  * @address: starting address of pages to zap
  * @size: number of bytes to zap
- * @details: details of nonlinear truncation or shared cache invalidation
+ * @details: details of shared cache invalidation
  *
  * The range must fit into one VMA.
  */
@@ -2331,25 +2308,11 @@ static inline void unmap_mapping_range_tree(struct rb_root *root,
 	}
 }
 
-static inline void unmap_mapping_range_list(struct list_head *head,
-					    struct zap_details *details)
-{
-	struct vm_area_struct *vma;
-
-	/*
-	 * In nonlinear VMAs there is no correspondence between virtual address
-	 * offset and file offset.  So we must perform an exhaustive search
-	 * across *all* the pages in each nonlinear VMA, not just the pages
-	 * whose virtual address lies outside the file truncation point.
-	 */
-	list_for_each_entry(vma, head, shared.nonlinear) {
-		details->nonlinear_vma = vma;
-		unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
-	}
-}
-
 /**
- * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file.
+ * unmap_mapping_range - unmap the portion of all mmaps in the specified
+ * address_space corresponding to the specified page range in the underlying
+ * file.
+ *
  * @mapping: the address space containing mmaps to be unmapped.
  * @holebegin: byte in first page to unmap, relative to the start of
  * the underlying file.  This will be rounded down to a PAGE_SIZE
@@ -2378,7 +2341,6 @@ void unmap_mapping_range(struct address_space *mapping,
 	}
 
 	details.check_mapping = even_cows? NULL: mapping;
-	details.nonlinear_vma = NULL;
 	details.first_index = hba;
 	details.last_index = hba + hlen - 1;
 	if (details.last_index < details.first_index)
@@ -2388,8 +2350,6 @@ void unmap_mapping_range(struct address_space *mapping,
 	i_mmap_lock_write(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
-	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
-		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
 	i_mmap_unlock_write(mapping);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
-- 
cgit v1.2.3-70-g09d2


From 9b4bdd2ffab9557ac43af7dff02e7dab1c8c58bd Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:09:51 -0800
Subject: mm: drop support of non-linear mapping from fault codepath

We don't create non-linear mappings anymore.  Let's drop code which
handles them on page fault.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 16 ++++++--------
 mm/memory.c        | 65 ++++++++----------------------------------------------
 2 files changed, 16 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 600ef5ed469..376e5c325de 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -206,21 +206,19 @@ extern unsigned int kobjsize(const void *objp);
 extern pgprot_t protection_map[16];
 
 #define FAULT_FLAG_WRITE	0x01	/* Fault was a write access */
-#define FAULT_FLAG_NONLINEAR	0x02	/* Fault was via a nonlinear mapping */
-#define FAULT_FLAG_MKWRITE	0x04	/* Fault was mkwrite of existing pte */
-#define FAULT_FLAG_ALLOW_RETRY	0x08	/* Retry fault if blocking */
-#define FAULT_FLAG_RETRY_NOWAIT	0x10	/* Don't drop mmap_sem and wait when retrying */
-#define FAULT_FLAG_KILLABLE	0x20	/* The fault task is in SIGKILL killable region */
-#define FAULT_FLAG_TRIED	0x40	/* second try */
-#define FAULT_FLAG_USER		0x80	/* The fault originated in userspace */
+#define FAULT_FLAG_MKWRITE	0x02	/* Fault was mkwrite of existing pte */
+#define FAULT_FLAG_ALLOW_RETRY	0x04	/* Retry fault if blocking */
+#define FAULT_FLAG_RETRY_NOWAIT	0x08	/* Don't drop mmap_sem and wait when retrying */
+#define FAULT_FLAG_KILLABLE	0x10	/* The fault task is in SIGKILL killable region */
+#define FAULT_FLAG_TRIED	0x20	/* Second try */
+#define FAULT_FLAG_USER		0x40	/* The fault originated in userspace */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
- * pgoff should be used in favour of virtual_address, if possible. If pgoff
- * is used, one may implement ->remap_pages to get nonlinear mapping support.
+ * pgoff should be used in favour of virtual_address, if possible.
  */
 struct vm_fault {
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
diff --git a/mm/memory.c b/mm/memory.c
index 9a3e73b69da..43a53743cbb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1899,12 +1899,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 EXPORT_SYMBOL_GPL(apply_to_page_range);
 
 /*
- * handle_pte_fault chooses page fault handler according to an entry
- * which was read non-atomically.  Before making any commitment, on
- * those architectures or configurations (e.g. i386 with PAE) which
- * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault
- * must check under lock before unmapping the pte and proceeding
- * (but do_wp_page is only called after already making such a check;
+ * handle_pte_fault chooses page fault handler according to an entry which was
+ * read non-atomically.  Before making any commitment, on those architectures
+ * or configurations (e.g. i386 with PAE) which might give a mix of unmatched
+ * parts, do_swap_page must check under lock before unmapping the pte and
+ * proceeding (but do_wp_page is only called after already making such a check;
  * and do_anonymous_page can safely check later on).
  */
 static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
@@ -2710,8 +2709,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 	entry = mk_pte(page, vma->vm_page_prot);
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-	else if (pte_file(*pte) && pte_file_soft_dirty(*pte))
-		entry = pte_mksoft_dirty(entry);
 	if (anon) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
 		page_add_new_anon_rmap(page, vma, address);
@@ -2846,8 +2843,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * if page by the offset is not ready to be mapped (cold cache or
 	 * something).
 	 */
-	if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) &&
-	    fault_around_bytes >> PAGE_SHIFT > 1) {
+	if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) {
 		pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 		do_fault_around(vma, address, pte, pgoff, flags);
 		if (!pte_same(*pte, orig_pte))
@@ -2992,7 +2988,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
  * The mmap_sem may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
  */
-static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
 		unsigned int flags, pte_t orig_pte)
 {
@@ -3009,46 +3005,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
-/*
- * Fault of a previously existing named mapping. Repopulate the pte
- * from the encoded file_pte if possible. This enables swappable
- * nonlinear vmas.
- *
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with pte unmapped and unlocked.
- * The mmap_sem may have been released depending on flags and our
- * return value.  See filemap_fault() and __lock_page_or_retry().
- */
-static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
-		unsigned long address, pte_t *page_table, pmd_t *pmd,
-		unsigned int flags, pte_t orig_pte)
-{
-	pgoff_t pgoff;
-
-	flags |= FAULT_FLAG_NONLINEAR;
-
-	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
-		return 0;
-
-	if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
-		/*
-		 * Page table corrupted: show pte and kill process.
-		 */
-		print_bad_pte(vma, address, orig_pte, NULL);
-		return VM_FAULT_SIGBUS;
-	}
-
-	pgoff = pte_to_pgoff(orig_pte);
-	if (!(flags & FAULT_FLAG_WRITE))
-		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
-				orig_pte);
-	if (!(vma->vm_flags & VM_SHARED))
-		return do_cow_fault(mm, vma, address, pmd, pgoff, flags,
-				orig_pte);
-	return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
-}
-
 static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma,
 				unsigned long addr, int page_nid,
 				int *flags)
@@ -3176,15 +3132,12 @@ static int handle_pte_fault(struct mm_struct *mm,
 		if (pte_none(entry)) {
 			if (vma->vm_ops) {
 				if (likely(vma->vm_ops->fault))
-					return do_linear_fault(mm, vma, address,
-						pte, pmd, flags, entry);
+					return do_fault(mm, vma, address, pte,
+							pmd, flags, entry);
 			}
 			return do_anonymous_page(mm, vma, address,
 						 pte, pmd, flags);
 		}
-		if (pte_file(entry))
-			return do_nonlinear_fault(mm, vma, address,
-					pte, pmd, flags, entry);
 		return do_swap_page(mm, vma, address,
 					pte, pmd, flags, entry);
 	}
-- 
cgit v1.2.3-70-g09d2


From d83a08db5ba6072caa658745881f4baa9bad6a08 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:09:54 -0800
Subject: mm: drop vm_ops->remap_pages and generic_file_remap_pages() stub

Nobody uses it anymore.

[akpm@linux-foundation.org: fix filemap_xip.c]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/9p/vfs_file.c   | 2 --
 fs/btrfs/file.c    | 1 -
 fs/ceph/addr.c     | 1 -
 fs/cifs/file.c     | 1 -
 fs/ext4/file.c     | 1 -
 fs/f2fs/file.c     | 1 -
 fs/fuse/file.c     | 1 -
 fs/gfs2/file.c     | 1 -
 fs/nfs/file.c      | 1 -
 fs/nilfs2/file.c   | 1 -
 fs/ocfs2/mmap.c    | 1 -
 fs/ubifs/file.c    | 1 -
 fs/xfs/xfs_file.c  | 1 -
 include/linux/fs.h | 6 ------
 include/linux/mm.h | 3 ---
 mm/filemap.c       | 1 -
 mm/filemap_xip.c   | 1 -
 mm/shmem.c         | 1 -
 18 files changed, 26 deletions(-)

(limited to 'include')

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 5594505e6e7..b40133796b8 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -831,7 +831,6 @@ static const struct vm_operations_struct v9fs_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
@@ -839,7 +838,6 @@ static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e4090259569..a606ab55129 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2081,7 +2081,6 @@ static const struct vm_operations_struct btrfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= btrfs_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c81c0e00458..24be059fd1f 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1569,7 +1569,6 @@ out:
 static struct vm_operations_struct ceph_vmops = {
 	.fault		= ceph_filemap_fault,
 	.page_mkwrite	= ceph_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 int ceph_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 74f12877493..294ff302a23 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3248,7 +3248,6 @@ static struct vm_operations_struct cifs_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = cifs_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8131be8c0af..7cb59238612 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -195,7 +195,6 @@ static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 3c27e0ecb3b..5674ba13102 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -92,7 +92,6 @@ static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= f2fs_vm_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int get_parent_ino(struct inode *inode, nid_t *pino)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 760b2c55219..d769e594855 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2062,7 +2062,6 @@ static const struct vm_operations_struct fuse_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= fuse_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 6e600abf694..ec9c2d33477 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -498,7 +498,6 @@ static const struct vm_operations_struct gfs2_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = gfs2_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 /**
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 2ab6f00dba5..94712fc781f 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -646,7 +646,6 @@ static const struct vm_operations_struct nfs_file_vm_ops = {
 	.fault = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = nfs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 static int nfs_need_sync_write(struct file *filp, struct inode *inode)
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 3a03e0aea1f..a8c728acb7a 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -128,7 +128,6 @@ static const struct vm_operations_struct nilfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= nilfs_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 10d66c75cec..9581d190f6e 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -173,7 +173,6 @@ out:
 static const struct vm_operations_struct ocfs2_file_vm_ops = {
 	.fault		= ocfs2_fault,
 	.page_mkwrite	= ocfs2_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 int ocfs2_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 538519ee37d..035e5101144 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1536,7 +1536,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = {
 	.fault        = filemap_fault,
 	.map_pages = filemap_map_pages,
 	.page_mkwrite = ubifs_vm_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 13e974e6a88..ac7f1e8f92b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1384,5 +1384,4 @@ static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_vm_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 60c4996df7f..47f557c7ef7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2481,12 +2481,6 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-static inline int generic_file_remap_pages(struct vm_area_struct *vma,
-		unsigned long addr, unsigned long size, pgoff_t pgoff)
-{
-	BUG();
-	return 0;
-}
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 376e5c325de..2ddd9d1d626 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -285,9 +285,6 @@ struct vm_operations_struct {
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
 					unsigned long addr);
 #endif
-	/* called by sys_remap_file_pages() to populate non-linear mapping */
-	int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,
-			   unsigned long size, pgoff_t pgoff);
 };
 
 struct mmu_gather;
diff --git a/mm/filemap.c b/mm/filemap.c
index 673e4581a2e..bf7a2714270 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2087,7 +2087,6 @@ const struct vm_operations_struct generic_file_vm_ops = {
 	.fault		= filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= filemap_page_mkwrite,
-	.remap_pages	= generic_file_remap_pages,
 };
 
 /* This is used for a general mmap of a disk file */
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 0d105aeff82..70c09da1a41 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -301,7 +301,6 @@ out:
 static const struct vm_operations_struct xip_file_vm_ops = {
 	.fault	= xip_file_fault,
 	.page_mkwrite	= filemap_page_mkwrite,
-	.remap_pages = generic_file_remap_pages,
 };
 
 int xip_file_mmap(struct file * file, struct vm_area_struct * vma)
diff --git a/mm/shmem.c b/mm/shmem.c
index 993e6ba689c..b3e40318198 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3201,7 +3201,6 @@ static const struct vm_operations_struct shmem_vm_ops = {
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
 #endif
-	.remap_pages	= generic_file_remap_pages,
 };
 
 static struct dentry *shmem_mount(struct file_system_type *fs_type,
-- 
cgit v1.2.3-70-g09d2


From 27ba0644ea9dfe6e7693abc85837b60e40583b96 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:09:59 -0800
Subject: rmap: drop support of non-linear mappings

We don't create non-linear mappings anymore.  Let's drop code which
handles them in rmap.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cachetlb.txt |   8 +-
 fs/inode.c                 |   1 -
 include/linux/fs.h         |   4 +-
 include/linux/mm.h         |   6 --
 include/linux/mm_types.h   |   4 +-
 include/linux/rmap.h       |   2 -
 kernel/fork.c              |   8 +-
 mm/migrate.c               |  32 -------
 mm/mmap.c                  |  24 ++---
 mm/rmap.c                  | 225 +--------------------------------------------
 mm/swap.c                  |   4 +-
 11 files changed, 18 insertions(+), 300 deletions(-)

(limited to 'include')

diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index d79b008e4a3..3f9f808b511 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -317,10 +317,10 @@ maps this page at its virtual address.
 	about doing this.
 
 	The idea is, first at flush_dcache_page() time, if
-	page->mapping->i_mmap is an empty tree and ->i_mmap_nonlinear
-	an empty list, just mark the architecture private page flag bit.
-	Later, in update_mmu_cache(), a check is made of this flag bit,
-	and if set the flush is done and the flag bit is cleared.
+	page->mapping->i_mmap is an empty tree, just mark the architecture
+	private page flag bit.  Later, in update_mmu_cache(), a check is
+	made of this flag bit, and if set the flush is done and the flag
+	bit is cleared.
 
 	IMPORTANT NOTE: It is often important, if you defer the flush,
 			that the actual flush occurs on the same CPU
diff --git a/fs/inode.c b/fs/inode.c
index aa149e7262a..c760fac33c9 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -355,7 +355,6 @@ void address_space_init_once(struct address_space *mapping)
 	INIT_LIST_HEAD(&mapping->private_list);
 	spin_lock_init(&mapping->private_lock);
 	mapping->i_mmap = RB_ROOT;
-	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
 }
 EXPORT_SYMBOL(address_space_init_once);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 47f557c7ef7..60acab20970 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -401,7 +401,6 @@ struct address_space {
 	spinlock_t		tree_lock;	/* and lock protecting it */
 	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
 	struct rb_root		i_mmap;		/* tree of private and shared mappings */
-	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
 	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
@@ -493,8 +492,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
  */
 static inline int mapping_mapped(struct address_space *mapping)
 {
-	return	!RB_EMPTY_ROOT(&mapping->i_mmap) ||
-		!list_empty(&mapping->i_mmap_nonlinear);
+	return	!RB_EMPTY_ROOT(&mapping->i_mmap);
 }
 
 /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2ddd9d1d626..18391eec486 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1796,12 +1796,6 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node,
 	for (vma = vma_interval_tree_iter_first(root, start, last);	\
 	     vma; vma = vma_interval_tree_iter_next(vma, start, last))
 
-static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
-					struct list_head *list)
-{
-	list_add_tail(&vma->shared.nonlinear, list);
-}
-
 void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
 				   struct rb_root *root);
 void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6d34aa266a8..3b1d20fb084 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -273,15 +273,13 @@ struct vm_area_struct {
 
 	/*
 	 * For areas with an address space and backing store,
-	 * linkage into the address_space->i_mmap interval tree, or
-	 * linkage of vma in the address_space->i_mmap_nonlinear list.
+	 * linkage into the address_space->i_mmap interval tree.
 	 */
 	union {
 		struct {
 			struct rb_node rb;
 			unsigned long rb_subtree_last;
 		} linear;
-		struct list_head nonlinear;
 	} shared;
 
 	/*
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index d9d7e7e5635..b38f559130d 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -246,7 +246,6 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
  * arg: passed to rmap_one() and invalid_vma()
  * rmap_one: executed on each vma where page is mapped
  * done: for checking traversing termination condition
- * file_nonlinear: for handling file nonlinear mapping
  * anon_lock: for getting anon_lock by optimized way rather than default
  * invalid_vma: for skipping uninterested vma
  */
@@ -255,7 +254,6 @@ struct rmap_walk_control {
 	int (*rmap_one)(struct page *page, struct vm_area_struct *vma,
 					unsigned long addr, void *arg);
 	int (*done)(struct page *page);
-	int (*file_nonlinear)(struct page *, struct address_space *, void *arg);
 	struct anon_vma *(*anon_lock)(struct page *page);
 	bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
 };
diff --git a/kernel/fork.c b/kernel/fork.c
index 4dc2ddade9f..b379d9abddc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -438,12 +438,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 				atomic_inc(&mapping->i_mmap_writable);
 			flush_dcache_mmap_lock(mapping);
 			/* insert tmp into the share list, just after mpnt */
-			if (unlikely(tmp->vm_flags & VM_NONLINEAR))
-				vma_nonlinear_insert(tmp,
-						&mapping->i_mmap_nonlinear);
-			else
-				vma_interval_tree_insert_after(tmp, mpnt,
-							&mapping->i_mmap);
+			vma_interval_tree_insert_after(tmp, mpnt,
+					&mapping->i_mmap);
 			flush_dcache_mmap_unlock(mapping);
 			i_mmap_unlock_write(mapping);
 		}
diff --git a/mm/migrate.c b/mm/migrate.c
index 344cdf692fc..6e284bcca8b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -178,37 +178,6 @@ out:
 	return SWAP_AGAIN;
 }
 
-/*
- * Congratulations to trinity for discovering this bug.
- * mm/fremap.c's remap_file_pages() accepts any range within a single vma to
- * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then
- * replace the specified range by file ptes throughout (maybe populated after).
- * If page migration finds a page within that range, while it's still located
- * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem:
- * zap_pte() clears the temporary migration entry before mmap_sem is dropped.
- * But if the migrating page is in a part of the vma outside the range to be
- * remapped, then it will not be cleared, and remove_migration_ptes() needs to
- * deal with it.  Fortunately, this part of the vma is of course still linear,
- * so we just need to use linear location on the nonlinear list.
- */
-static int remove_linear_migration_ptes_from_nonlinear(struct page *page,
-		struct address_space *mapping, void *arg)
-{
-	struct vm_area_struct *vma;
-	/* hugetlbfs does not support remap_pages, so no huge pgoff worries */
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-	unsigned long addr;
-
-	list_for_each_entry(vma,
-		&mapping->i_mmap_nonlinear, shared.nonlinear) {
-
-		addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
-		if (addr >= vma->vm_start && addr < vma->vm_end)
-			remove_migration_pte(page, vma, addr, arg);
-	}
-	return SWAP_AGAIN;
-}
-
 /*
  * Get rid of all migration entries and replace them by
  * references to the indicated page.
@@ -218,7 +187,6 @@ static void remove_migration_ptes(struct page *old, struct page *new)
 	struct rmap_walk_control rwc = {
 		.rmap_one = remove_migration_pte,
 		.arg = old,
-		.file_nonlinear = remove_linear_migration_ptes_from_nonlinear,
 	};
 
 	rmap_walk(new, &rwc);
diff --git a/mm/mmap.c b/mm/mmap.c
index e023dc5e59a..14d84666e8b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -243,10 +243,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 		mapping_unmap_writable(mapping);
 
 	flush_dcache_mmap_lock(mapping);
-	if (unlikely(vma->vm_flags & VM_NONLINEAR))
-		list_del_init(&vma->shared.nonlinear);
-	else
-		vma_interval_tree_remove(vma, &mapping->i_mmap);
+	vma_interval_tree_remove(vma, &mapping->i_mmap);
 	flush_dcache_mmap_unlock(mapping);
 }
 
@@ -649,10 +646,7 @@ static void __vma_link_file(struct vm_area_struct *vma)
 			atomic_inc(&mapping->i_mmap_writable);
 
 		flush_dcache_mmap_lock(mapping);
-		if (unlikely(vma->vm_flags & VM_NONLINEAR))
-			vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
-		else
-			vma_interval_tree_insert(vma, &mapping->i_mmap);
+		vma_interval_tree_insert(vma, &mapping->i_mmap);
 		flush_dcache_mmap_unlock(mapping);
 	}
 }
@@ -789,14 +783,11 @@ again:			remove_next = 1 + (end > next->vm_end);
 
 	if (file) {
 		mapping = file->f_mapping;
-		if (!(vma->vm_flags & VM_NONLINEAR)) {
-			root = &mapping->i_mmap;
-			uprobe_munmap(vma, vma->vm_start, vma->vm_end);
+		root = &mapping->i_mmap;
+		uprobe_munmap(vma, vma->vm_start, vma->vm_end);
 
-			if (adjust_next)
-				uprobe_munmap(next, next->vm_start,
-							next->vm_end);
-		}
+		if (adjust_next)
+			uprobe_munmap(next, next->vm_start, next->vm_end);
 
 		i_mmap_lock_write(mapping);
 		if (insert) {
@@ -3177,8 +3168,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
  *
  * mmap_sem in write mode is required in order to block all operations
  * that could modify pagetables and free pages without need of
- * altering the vma layout (for example populate_range() with
- * nonlinear vmas). It's also needed in write mode to avoid new
+ * altering the vma layout. It's also needed in write mode to avoid new
  * anon_vmas to be associated with existing vmas.
  *
  * A single task can't take more than one mm_take_all_locks() in a row
diff --git a/mm/rmap.c b/mm/rmap.c
index 71cd5bd0c17..70b32498d4f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -590,9 +590,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 		if (!vma->anon_vma || !page__anon_vma ||
 		    vma->anon_vma->root != page__anon_vma->root)
 			return -EFAULT;
-	} else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
-		if (!vma->vm_file ||
-		    vma->vm_file->f_mapping != page->mapping)
+	} else if (page->mapping) {
+		if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping)
 			return -EFAULT;
 	} else
 		return -EFAULT;
@@ -1274,7 +1273,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 		if (pte_soft_dirty(pteval))
 			swp_pte = pte_swp_mksoft_dirty(swp_pte);
 		set_pte_at(mm, address, pte, swp_pte);
-		BUG_ON(pte_file(*pte));
 	} else if (IS_ENABLED(CONFIG_MIGRATION) &&
 		   (flags & TTU_MIGRATION)) {
 		/* Establish migration entry for a file page */
@@ -1316,211 +1314,6 @@ out_mlock:
 	return ret;
 }
 
-/*
- * objrmap doesn't work for nonlinear VMAs because the assumption that
- * offset-into-file correlates with offset-into-virtual-addresses does not hold.
- * Consequently, given a particular page and its ->index, we cannot locate the
- * ptes which are mapping that page without an exhaustive linear search.
- *
- * So what this code does is a mini "virtual scan" of each nonlinear VMA which
- * maps the file to which the target page belongs.  The ->vm_private_data field
- * holds the current cursor into that scan.  Successive searches will circulate
- * around the vma's virtual address space.
- *
- * So as more replacement pressure is applied to the pages in a nonlinear VMA,
- * more scanning pressure is placed against them as well.   Eventually pages
- * will become fully unmapped and are eligible for eviction.
- *
- * For very sparsely populated VMAs this is a little inefficient - chances are
- * there there won't be many ptes located within the scan cluster.  In this case
- * maybe we could scan further - to the end of the pte page, perhaps.
- *
- * Mlocked pages:  check VM_LOCKED under mmap_sem held for read, if we can
- * acquire it without blocking.  If vma locked, mlock the pages in the cluster,
- * rather than unmapping them.  If we encounter the "check_page" that vmscan is
- * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN.
- */
-#define CLUSTER_SIZE	min(32*PAGE_SIZE, PMD_SIZE)
-#define CLUSTER_MASK	(~(CLUSTER_SIZE - 1))
-
-static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
-		struct vm_area_struct *vma, struct page *check_page)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	pmd_t *pmd;
-	pte_t *pte;
-	pte_t pteval;
-	spinlock_t *ptl;
-	struct page *page;
-	unsigned long address;
-	unsigned long mmun_start;	/* For mmu_notifiers */
-	unsigned long mmun_end;		/* For mmu_notifiers */
-	unsigned long end;
-	int ret = SWAP_AGAIN;
-	int locked_vma = 0;
-
-	address = (vma->vm_start + cursor) & CLUSTER_MASK;
-	end = address + CLUSTER_SIZE;
-	if (address < vma->vm_start)
-		address = vma->vm_start;
-	if (end > vma->vm_end)
-		end = vma->vm_end;
-
-	pmd = mm_find_pmd(mm, address);
-	if (!pmd)
-		return ret;
-
-	mmun_start = address;
-	mmun_end   = end;
-	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
-
-	/*
-	 * If we can acquire the mmap_sem for read, and vma is VM_LOCKED,
-	 * keep the sem while scanning the cluster for mlocking pages.
-	 */
-	if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
-		locked_vma = (vma->vm_flags & VM_LOCKED);
-		if (!locked_vma)
-			up_read(&vma->vm_mm->mmap_sem); /* don't need it */
-	}
-
-	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
-
-	/* Update high watermark before we lower rss */
-	update_hiwater_rss(mm);
-
-	for (; address < end; pte++, address += PAGE_SIZE) {
-		if (!pte_present(*pte))
-			continue;
-		page = vm_normal_page(vma, address, *pte);
-		BUG_ON(!page || PageAnon(page));
-
-		if (locked_vma) {
-			if (page == check_page) {
-				/* we know we have check_page locked */
-				mlock_vma_page(page);
-				ret = SWAP_MLOCK;
-			} else if (trylock_page(page)) {
-				/*
-				 * If we can lock the page, perform mlock.
-				 * Otherwise leave the page alone, it will be
-				 * eventually encountered again later.
-				 */
-				mlock_vma_page(page);
-				unlock_page(page);
-			}
-			continue;	/* don't unmap */
-		}
-
-		/*
-		 * No need for _notify because we're within an
-		 * mmu_notifier_invalidate_range_ {start|end} scope.
-		 */
-		if (ptep_clear_flush_young(vma, address, pte))
-			continue;
-
-		/* Nuke the page table entry. */
-		flush_cache_page(vma, address, pte_pfn(*pte));
-		pteval = ptep_clear_flush_notify(vma, address, pte);
-
-		/* If nonlinear, store the file page offset in the pte. */
-		if (page->index != linear_page_index(vma, address)) {
-			pte_t ptfile = pgoff_to_pte(page->index);
-			if (pte_soft_dirty(pteval))
-				ptfile = pte_file_mksoft_dirty(ptfile);
-			set_pte_at(mm, address, pte, ptfile);
-		}
-
-		/* Move the dirty bit to the physical page now the pte is gone. */
-		if (pte_dirty(pteval))
-			set_page_dirty(page);
-
-		page_remove_rmap(page);
-		page_cache_release(page);
-		dec_mm_counter(mm, MM_FILEPAGES);
-		(*mapcount)--;
-	}
-	pte_unmap_unlock(pte - 1, ptl);
-	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
-	if (locked_vma)
-		up_read(&vma->vm_mm->mmap_sem);
-	return ret;
-}
-
-static int try_to_unmap_nonlinear(struct page *page,
-		struct address_space *mapping, void *arg)
-{
-	struct vm_area_struct *vma;
-	int ret = SWAP_AGAIN;
-	unsigned long cursor;
-	unsigned long max_nl_cursor = 0;
-	unsigned long max_nl_size = 0;
-	unsigned int mapcount;
-
-	list_for_each_entry(vma,
-		&mapping->i_mmap_nonlinear, shared.nonlinear) {
-
-		cursor = (unsigned long) vma->vm_private_data;
-		if (cursor > max_nl_cursor)
-			max_nl_cursor = cursor;
-		cursor = vma->vm_end - vma->vm_start;
-		if (cursor > max_nl_size)
-			max_nl_size = cursor;
-	}
-
-	if (max_nl_size == 0) {	/* all nonlinears locked or reserved ? */
-		return SWAP_FAIL;
-	}
-
-	/*
-	 * We don't try to search for this page in the nonlinear vmas,
-	 * and page_referenced wouldn't have found it anyway.  Instead
-	 * just walk the nonlinear vmas trying to age and unmap some.
-	 * The mapcount of the page we came in with is irrelevant,
-	 * but even so use it as a guide to how hard we should try?
-	 */
-	mapcount = page_mapcount(page);
-	if (!mapcount)
-		return ret;
-
-	cond_resched();
-
-	max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
-	if (max_nl_cursor == 0)
-		max_nl_cursor = CLUSTER_SIZE;
-
-	do {
-		list_for_each_entry(vma,
-			&mapping->i_mmap_nonlinear, shared.nonlinear) {
-
-			cursor = (unsigned long) vma->vm_private_data;
-			while (cursor < max_nl_cursor &&
-				cursor < vma->vm_end - vma->vm_start) {
-				if (try_to_unmap_cluster(cursor, &mapcount,
-						vma, page) == SWAP_MLOCK)
-					ret = SWAP_MLOCK;
-				cursor += CLUSTER_SIZE;
-				vma->vm_private_data = (void *) cursor;
-				if ((int)mapcount <= 0)
-					return ret;
-			}
-			vma->vm_private_data = (void *) max_nl_cursor;
-		}
-		cond_resched();
-		max_nl_cursor += CLUSTER_SIZE;
-	} while (max_nl_cursor <= max_nl_size);
-
-	/*
-	 * Don't loop forever (perhaps all the remaining pages are
-	 * in locked vmas).  Reset cursor on all unreserved nonlinear
-	 * vmas, now forgetting on which ones it had fallen behind.
-	 */
-	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear)
-		vma->vm_private_data = NULL;
-
-	return ret;
-}
-
 bool is_vma_temporary_stack(struct vm_area_struct *vma)
 {
 	int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
@@ -1566,7 +1359,6 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
 		.rmap_one = try_to_unmap_one,
 		.arg = (void *)flags,
 		.done = page_not_mapped,
-		.file_nonlinear = try_to_unmap_nonlinear,
 		.anon_lock = page_lock_anon_vma_read,
 	};
 
@@ -1612,12 +1404,6 @@ int try_to_munlock(struct page *page)
 		.rmap_one = try_to_unmap_one,
 		.arg = (void *)TTU_MUNLOCK,
 		.done = page_not_mapped,
-		/*
-		 * We don't bother to try to find the munlocked page in
-		 * nonlinears. It's costly. Instead, later, page reclaim logic
-		 * may call try_to_unmap() and recover PG_mlocked lazily.
-		 */
-		.file_nonlinear = NULL,
 		.anon_lock = page_lock_anon_vma_read,
 
 	};
@@ -1748,13 +1534,6 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 			goto done;
 	}
 
-	if (!rwc->file_nonlinear)
-		goto done;
-
-	if (list_empty(&mapping->i_mmap_nonlinear))
-		goto done;
-
-	ret = rwc->file_nonlinear(page, mapping, rwc->arg);
 done:
 	i_mmap_unlock_read(mapping);
 	return ret;
diff --git a/mm/swap.c b/mm/swap.c
index 8a12b33936b..5b3087228b9 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1140,10 +1140,8 @@ void __init swap_setup(void)
 
 	if (bdi_init(swapper_spaces[0].backing_dev_info))
 		panic("Failed to init swap bdi");
-	for (i = 0; i < MAX_SWAPFILES; i++) {
+	for (i = 0; i < MAX_SWAPFILES; i++)
 		spin_lock_init(&swapper_spaces[i].tree_lock);
-		INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear);
-	}
 #endif
 
 	/* Use a smaller cluster for small-memory machines */
-- 
cgit v1.2.3-70-g09d2


From ac51b934f3912582d3c897c6c4d09b32ea57b2c7 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:10:02 -0800
Subject: mm: replace vma->sharead.linear with vma->shared

After removing vma->shared.nonlinear we have only one member of
vma->shared union, which doesn't make much sense.

This patch drops the union and move struct vma->shared.linear to
vma->shared.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_types.h |  8 +++-----
 mm/interval_tree.c       | 34 +++++++++++++++++-----------------
 2 files changed, 20 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3b1d20fb084..07c8bd3f7b4 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -275,11 +275,9 @@ struct vm_area_struct {
 	 * For areas with an address space and backing store,
 	 * linkage into the address_space->i_mmap interval tree.
 	 */
-	union {
-		struct {
-			struct rb_node rb;
-			unsigned long rb_subtree_last;
-		} linear;
+	struct {
+		struct rb_node rb;
+		unsigned long rb_subtree_last;
 	} shared;
 
 	/*
diff --git a/mm/interval_tree.c b/mm/interval_tree.c
index 8da581fa906..f2c2492681b 100644
--- a/mm/interval_tree.c
+++ b/mm/interval_tree.c
@@ -21,8 +21,8 @@ static inline unsigned long vma_last_pgoff(struct vm_area_struct *v)
 	return v->vm_pgoff + ((v->vm_end - v->vm_start) >> PAGE_SHIFT) - 1;
 }
 
-INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.linear.rb,
-		     unsigned long, shared.linear.rb_subtree_last,
+INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb,
+		     unsigned long, shared.rb_subtree_last,
 		     vma_start_pgoff, vma_last_pgoff,, vma_interval_tree)
 
 /* Insert node immediately after prev in the interval tree */
@@ -36,26 +36,26 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node,
 
 	VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node);
 
-	if (!prev->shared.linear.rb.rb_right) {
+	if (!prev->shared.rb.rb_right) {
 		parent = prev;
-		link = &prev->shared.linear.rb.rb_right;
+		link = &prev->shared.rb.rb_right;
 	} else {
-		parent = rb_entry(prev->shared.linear.rb.rb_right,
-				  struct vm_area_struct, shared.linear.rb);
-		if (parent->shared.linear.rb_subtree_last < last)
-			parent->shared.linear.rb_subtree_last = last;
-		while (parent->shared.linear.rb.rb_left) {
-			parent = rb_entry(parent->shared.linear.rb.rb_left,
-				struct vm_area_struct, shared.linear.rb);
-			if (parent->shared.linear.rb_subtree_last < last)
-				parent->shared.linear.rb_subtree_last = last;
+		parent = rb_entry(prev->shared.rb.rb_right,
+				  struct vm_area_struct, shared.rb);
+		if (parent->shared.rb_subtree_last < last)
+			parent->shared.rb_subtree_last = last;
+		while (parent->shared.rb.rb_left) {
+			parent = rb_entry(parent->shared.rb.rb_left,
+				struct vm_area_struct, shared.rb);
+			if (parent->shared.rb_subtree_last < last)
+				parent->shared.rb_subtree_last = last;
 		}
-		link = &parent->shared.linear.rb.rb_left;
+		link = &parent->shared.rb.rb_left;
 	}
 
-	node->shared.linear.rb_subtree_last = last;
-	rb_link_node(&node->shared.linear.rb, &parent->shared.linear.rb, link);
-	rb_insert_augmented(&node->shared.linear.rb, root,
+	node->shared.rb_subtree_last = last;
+	rb_link_node(&node->shared.rb, &parent->shared.rb, link);
+	rb_insert_augmented(&node->shared.rb, root,
 			    &vma_interval_tree_augment);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 0661a33611fca12570cba48d9344ce68834ee86c Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:10:04 -0800
Subject: mm: remove rest usage of VM_NONLINEAR and pte_file()

One bit in ->vm_flags is unused now!

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/gpu/drm/drm_vma_manager.c |  3 +-
 include/linux/mm.h                |  1 -
 include/linux/swapops.h           |  4 +-
 mm/debug.c                        |  1 -
 mm/gup.c                          |  2 +-
 mm/ksm.c                          |  2 +-
 mm/madvise.c                      |  4 +-
 mm/memcontrol.c                   |  7 +---
 mm/memory.c                       | 78 +++++++++++++++++++--------------------
 mm/mincore.c                      |  9 +----
 mm/mprotect.c                     |  2 +-
 mm/mremap.c                       |  2 -
 mm/msync.c                        |  5 +--
 13 files changed, 49 insertions(+), 71 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c
index 63b47120507..68c1f32fb08 100644
--- a/drivers/gpu/drm/drm_vma_manager.c
+++ b/drivers/gpu/drm/drm_vma_manager.c
@@ -50,8 +50,7 @@
  *
  * You must not use multiple offset managers on a single address_space.
  * Otherwise, mm-core will be unable to tear down memory mappings as the VM will
- * no longer be linear. Please use VM_NONLINEAR in that case and implement your
- * own offset managers.
+ * no longer be linear.
  *
  * This offset manager works on page-based addresses. That is, every argument
  * and return code (with the exception of drm_vma_node_offset_addr()) is given
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 18391eec486..a0da685bdb8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -138,7 +138,6 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
-#define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
 #define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
 #define VM_ARCH_2	0x02000000
 #define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 6adfb7bfbf4..50cbc876be5 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -54,7 +54,7 @@ static inline pgoff_t swp_offset(swp_entry_t entry)
 /* check whether a pte points to a swap entry */
 static inline int is_swap_pte(pte_t pte)
 {
-	return !pte_none(pte) && !pte_present_nonuma(pte) && !pte_file(pte);
+	return !pte_none(pte) && !pte_present_nonuma(pte);
 }
 #endif
 
@@ -66,7 +66,6 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
 {
 	swp_entry_t arch_entry;
 
-	BUG_ON(pte_file(pte));
 	if (pte_swp_soft_dirty(pte))
 		pte = pte_swp_clear_soft_dirty(pte);
 	arch_entry = __pte_to_swp_entry(pte);
@@ -82,7 +81,6 @@ static inline pte_t swp_entry_to_pte(swp_entry_t entry)
 	swp_entry_t arch_entry;
 
 	arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
-	BUG_ON(pte_file(__swp_entry_to_pte(arch_entry)));
 	return __swp_entry_to_pte(arch_entry);
 }
 
diff --git a/mm/debug.c b/mm/debug.c
index 0e58f3211f8..d69cb5a7ba9 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -130,7 +130,6 @@ static const struct trace_print_flags vmaflags_names[] = {
 	{VM_ACCOUNT,			"account"	},
 	{VM_NORESERVE,			"noreserve"	},
 	{VM_HUGETLB,			"hugetlb"	},
-	{VM_NONLINEAR,			"nonlinear"	},
 #if defined(CONFIG_X86)
 	{VM_PAT,			"pat"		},
 #elif defined(CONFIG_PPC)
diff --git a/mm/gup.c b/mm/gup.c
index 8dd50ce6326..12bc2bc33da 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -55,7 +55,7 @@ retry:
 		 */
 		if (likely(!(flags & FOLL_MIGRATION)))
 			goto no_page;
-		if (pte_none(pte) || pte_file(pte))
+		if (pte_none(pte))
 			goto no_page;
 		entry = pte_to_swp_entry(pte);
 		if (!is_migration_entry(entry))
diff --git a/mm/ksm.c b/mm/ksm.c
index 15647fb0394..4162dce2eb4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1748,7 +1748,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		 */
 		if (*vm_flags & (VM_MERGEABLE | VM_SHARED  | VM_MAYSHARE   |
 				 VM_PFNMAP    | VM_IO      | VM_DONTEXPAND |
-				 VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP))
+				 VM_HUGETLB | VM_MIXEDMAP))
 			return 0;		/* just ignore the advice */
 
 #ifdef VM_SAO
diff --git a/mm/madvise.c b/mm/madvise.c
index 917754d26c1..d79fb5e8f80 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -155,7 +155,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
 		pte = *(orig_pte + ((index - start) / PAGE_SIZE));
 		pte_unmap_unlock(orig_pte, ptl);
 
-		if (pte_present(pte) || pte_none(pte) || pte_file(pte))
+		if (pte_present(pte) || pte_none(pte))
 			continue;
 		entry = pte_to_swp_entry(pte);
 		if (unlikely(non_swap_entry(entry)))
@@ -296,7 +296,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
-	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
+	if (vma->vm_flags & (VM_LOCKED | VM_HUGETLB))
 		return -EINVAL;
 
 	f = vma->vm_file;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2f6893c2f01..8b58701b964 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4926,10 +4926,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 		return NULL;
 
 	mapping = vma->vm_file->f_mapping;
-	if (pte_none(ptent))
-		pgoff = linear_page_index(vma, addr);
-	else /* pte_file(ptent) is true */
-		pgoff = pte_to_pgoff(ptent);
+	pgoff = linear_page_index(vma, addr);
 
 	/* page is moved even if it's not RSS of this task(page-faulted). */
 #ifdef CONFIG_SWAP
@@ -4961,7 +4958,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		page = mc_handle_present_pte(vma, addr, ptent);
 	else if (is_swap_pte(ptent))
 		page = mc_handle_swap_pte(vma, addr, ptent, &ent);
-	else if (pte_none(ptent) || pte_file(ptent))
+	else if (pte_none(ptent))
 		page = mc_handle_file_pte(vma, addr, ptent, &ent);
 
 	if (!page && !ent.val)
diff --git a/mm/memory.c b/mm/memory.c
index 43a53743cbb..9aa09217fe2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -811,42 +811,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	/* pte contains position in swap or file, so copy. */
 	if (unlikely(!pte_present(pte))) {
-		if (!pte_file(pte)) {
-			swp_entry_t entry = pte_to_swp_entry(pte);
-
-			if (likely(!non_swap_entry(entry))) {
-				if (swap_duplicate(entry) < 0)
-					return entry.val;
-
-				/* make sure dst_mm is on swapoff's mmlist. */
-				if (unlikely(list_empty(&dst_mm->mmlist))) {
-					spin_lock(&mmlist_lock);
-					if (list_empty(&dst_mm->mmlist))
-						list_add(&dst_mm->mmlist,
-							 &src_mm->mmlist);
-					spin_unlock(&mmlist_lock);
-				}
-				rss[MM_SWAPENTS]++;
-			} else if (is_migration_entry(entry)) {
-				page = migration_entry_to_page(entry);
-
-				if (PageAnon(page))
-					rss[MM_ANONPAGES]++;
-				else
-					rss[MM_FILEPAGES]++;
-
-				if (is_write_migration_entry(entry) &&
-				    is_cow_mapping(vm_flags)) {
-					/*
-					 * COW mappings require pages in both
-					 * parent and child to be set to read.
-					 */
-					make_migration_entry_read(&entry);
-					pte = swp_entry_to_pte(entry);
-					if (pte_swp_soft_dirty(*src_pte))
-						pte = pte_swp_mksoft_dirty(pte);
-					set_pte_at(src_mm, addr, src_pte, pte);
-				}
+		swp_entry_t entry = pte_to_swp_entry(pte);
+
+		if (likely(!non_swap_entry(entry))) {
+			if (swap_duplicate(entry) < 0)
+				return entry.val;
+
+			/* make sure dst_mm is on swapoff's mmlist. */
+			if (unlikely(list_empty(&dst_mm->mmlist))) {
+				spin_lock(&mmlist_lock);
+				if (list_empty(&dst_mm->mmlist))
+					list_add(&dst_mm->mmlist,
+							&src_mm->mmlist);
+				spin_unlock(&mmlist_lock);
+			}
+			rss[MM_SWAPENTS]++;
+		} else if (is_migration_entry(entry)) {
+			page = migration_entry_to_page(entry);
+
+			if (PageAnon(page))
+				rss[MM_ANONPAGES]++;
+			else
+				rss[MM_FILEPAGES]++;
+
+			if (is_write_migration_entry(entry) &&
+					is_cow_mapping(vm_flags)) {
+				/*
+				 * COW mappings require pages in both
+				 * parent and child to be set to read.
+				 */
+				make_migration_entry_read(&entry);
+				pte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(*src_pte))
+					pte = pte_swp_mksoft_dirty(pte);
+				set_pte_at(src_mm, addr, src_pte, pte);
 			}
 		}
 		goto out_set_pte;
@@ -1020,11 +1018,9 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * readonly mappings. The tradeoff is that copy_page_range is more
 	 * efficient than faulting.
 	 */
-	if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR |
-			       VM_PFNMAP | VM_MIXEDMAP))) {
-		if (!vma->anon_vma)
-			return 0;
-	}
+	if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) &&
+			!vma->anon_vma)
+		return 0;
 
 	if (is_vm_hugetlb_page(vma))
 		return copy_hugetlb_page_range(dst_mm, src_mm, vma);
diff --git a/mm/mincore.c b/mm/mincore.c
index c8c528b3664..46527c023e0 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -124,17 +124,13 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	do {
 		pte_t pte = *ptep;
-		pgoff_t pgoff;
 
 		next = addr + PAGE_SIZE;
 		if (pte_none(pte))
 			mincore_unmapped_range(vma, addr, next, vec);
 		else if (pte_present(pte))
 			*vec = 1;
-		else if (pte_file(pte)) {
-			pgoff = pte_to_pgoff(pte);
-			*vec = mincore_page(vma->vm_file->f_mapping, pgoff);
-		} else { /* pte is a swap entry */
+		else { /* pte is a swap entry */
 			swp_entry_t entry = pte_to_swp_entry(pte);
 
 			if (non_swap_entry(entry)) {
@@ -145,9 +141,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				*vec = 1;
 			} else {
 #ifdef CONFIG_SWAP
-				pgoff = entry.val;
 				*vec = mincore_page(swap_address_space(entry),
-					pgoff);
+					entry.val);
 #else
 				WARN_ON(1);
 				*vec = 1;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ace93454ce8..33121662f08 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -105,7 +105,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			}
 			if (updated)
 				pages++;
-		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
+		} else if (IS_ENABLED(CONFIG_MIGRATION)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
 			if (is_write_migration_entry(entry)) {
diff --git a/mm/mremap.c b/mm/mremap.c
index 17fa018f5f3..57dadc025c6 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -81,8 +81,6 @@ static pte_t move_soft_dirty_pte(pte_t pte)
 		pte = pte_mksoft_dirty(pte);
 	else if (is_swap_pte(pte))
 		pte = pte_swp_mksoft_dirty(pte);
-	else if (pte_file(pte))
-		pte = pte_file_mksoft_dirty(pte);
 #endif
 	return pte;
 }
diff --git a/mm/msync.c b/mm/msync.c
index 992a1673d48..bb04d53ae85 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -86,10 +86,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 				(vma->vm_flags & VM_SHARED)) {
 			get_file(file);
 			up_read(&mm->mmap_sem);
-			if (vma->vm_flags & VM_NONLINEAR)
-				error = vfs_fsync(file, 1);
-			else
-				error = vfs_fsync_range(file, fstart, fend, 1);
+			error = vfs_fsync_range(file, fstart, fend, 1);
 			fput(file);
 			if (error || start >= end)
 				goto out;
-- 
cgit v1.2.3-70-g09d2


From 5064c8e19dc215afae8ffae95570e7f22062d49c Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 10 Feb 2015 14:10:07 -0800
Subject: asm-generic: drop unused pte_file* helpers

All users are gone.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/pgtable.h | 15 ---------------
 1 file changed, 15 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 177d5973b13..129de9204d1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -474,21 +474,6 @@ static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
 	return pte;
 }
-
-static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
-{
-       return pte;
-}
-
-static inline pte_t pte_file_mksoft_dirty(pte_t pte)
-{
-       return pte;
-}
-
-static inline int pte_file_soft_dirty(pte_t pte)
-{
-       return 0;
-}
 #endif
 
 #ifndef __HAVE_PFNMAP_TRACKING
-- 
cgit v1.2.3-70-g09d2


From 753162cd849c45580fb5aaa7f3597c81e74e391c Mon Sep 17 00:00:00 2001
From: Andrey Ryabinin <a.ryabinin@samsung.com>
Date: Tue, 10 Feb 2015 14:11:36 -0800
Subject: mm: hugetlb: fix type of hugetlb_treat_as_movable variable

hugetlb_treat_as_movable declared as unsigned long, but
proc_dointvec() used for parsing it:

static struct ctl_table vm_table[] = {
...
        {
                .procname	= "hugepages_treat_as_movable",
                .data		= &hugepages_treat_as_movable,
                .maxlen		= sizeof(int),
                .mode		= 0644,
                .proc_handler	= proc_dointvec,
        },

This seems harmless, but it's better to use int type here.

Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h | 2 +-
 mm/hugetlb.c            | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 431b7fc605c..7d785635992 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -86,7 +86,7 @@ void free_huge_page(struct page *page);
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
 #endif
 
-extern unsigned long hugepages_treat_as_movable;
+extern int hugepages_treat_as_movable;
 extern int sysctl_hugetlb_shm_group;
 extern struct list_head huge_boot_pages;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 85032de5e20..be0e5d0db5e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -35,7 +35,7 @@
 #include <linux/node.h>
 #include "internal.h"
 
-unsigned long hugepages_treat_as_movable;
+int hugepages_treat_as_movable;
 
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
-- 
cgit v1.2.3-70-g09d2


From dbf22eb6d8675fc173154d9f1bd1bd0fda53a001 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Tue, 10 Feb 2015 14:11:41 -0800
Subject: memcg: zap __memcg_{charge,uncharge}_slab

They are simple wrappers around memcg_{charge,uncharge}_kmem, so let's
zap them and call these functions directly.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  5 +++--
 mm/memcontrol.c            | 21 +++------------------
 mm/slab.h                  |  4 ++--
 3 files changed, 8 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7c95af8d552..18ccb298897 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -403,8 +403,9 @@ void memcg_update_array_size(int num_groups);
 struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep);
 void __memcg_kmem_put_cache(struct kmem_cache *cachep);
 
-int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order);
-void __memcg_uncharge_slab(struct kmem_cache *cachep, int order);
+int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
+		      unsigned long nr_pages);
+void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
 
 int __memcg_cleanup_cache_params(struct kmem_cache *s);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8b58701b964..e229e3ad615 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2495,8 +2495,8 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
 	return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg));
 }
 
-static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
-			     unsigned long nr_pages)
+int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
+		      unsigned long nr_pages)
 {
 	struct page_counter *counter;
 	int ret = 0;
@@ -2533,8 +2533,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 	return ret;
 }
 
-static void memcg_uncharge_kmem(struct mem_cgroup *memcg,
-				unsigned long nr_pages)
+void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages)
 {
 	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
@@ -2767,20 +2766,6 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
 	current->memcg_kmem_skip_account = 0;
 }
 
-int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order)
-{
-	unsigned int nr_pages = 1 << order;
-
-	return memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages);
-}
-
-void __memcg_uncharge_slab(struct kmem_cache *cachep, int order)
-{
-	unsigned int nr_pages = 1 << order;
-
-	memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages);
-}
-
 /*
  * Return the kmem_cache we're supposed to use for a slab allocation.
  * We try to use the current memcg's version of the cache.
diff --git a/mm/slab.h b/mm/slab.h
index 1cf4005482d..90430d6f665 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -235,7 +235,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s,
 		return 0;
 	if (is_root_cache(s))
 		return 0;
-	return __memcg_charge_slab(s, gfp, order);
+	return memcg_charge_kmem(s->memcg_params->memcg, gfp, 1 << order);
 }
 
 static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
@@ -244,7 +244,7 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order)
 		return;
 	if (is_root_cache(s))
 		return;
-	__memcg_uncharge_slab(s, order);
+	memcg_uncharge_kmem(s->memcg_params->memcg, 1 << order);
 }
 #else
 static inline bool is_root_cache(struct kmem_cache *s)
-- 
cgit v1.2.3-70-g09d2


From 3e0350a36414a73c5c2d1e354f8c0ab4ace1296d Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Tue, 10 Feb 2015 14:11:44 -0800
Subject: memcg: zap memcg_name argument of memcg_create_kmem_cache

Instead of passing the name of the memory cgroup which the cache is
created for in the memcg_name_argument, let's obtain it immediately in
memcg_create_kmem_cache.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slab.h | 3 +--
 mm/memcontrol.c      | 5 +----
 mm/slab_common.c     | 9 +++++----
 3 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9a139b63706..eca9ed303a1 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -117,8 +117,7 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			void (*)(void *));
 #ifdef CONFIG_MEMCG_KMEM
 struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *,
-					   struct kmem_cache *,
-					   const char *);
+					   struct kmem_cache *);
 #endif
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e229e3ad615..baf7eb27e3a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2607,8 +2607,6 @@ void memcg_update_array_size(int num)
 static void memcg_register_cache(struct mem_cgroup *memcg,
 				 struct kmem_cache *root_cache)
 {
-	static char memcg_name_buf[NAME_MAX + 1]; /* protected by
-						     memcg_slab_mutex */
 	struct kmem_cache *cachep;
 	int id;
 
@@ -2624,8 +2622,7 @@ static void memcg_register_cache(struct mem_cgroup *memcg,
 	if (cache_from_memcg_idx(root_cache, id))
 		return;
 
-	cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1);
-	cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf);
+	cachep = memcg_create_kmem_cache(memcg, root_cache);
 	/*
 	 * If we could not create a memcg cache, do not complain, because
 	 * that's not critical at all as we can always proceed with the root
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 67f182c10f2..1b782a2d3b3 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -430,16 +430,15 @@ EXPORT_SYMBOL(kmem_cache_create);
  * memcg_create_kmem_cache - Create a cache for a memory cgroup.
  * @memcg: The memory cgroup the new cache is for.
  * @root_cache: The parent of the new cache.
- * @memcg_name: The name of the memory cgroup (used for naming the new cache).
  *
  * This function attempts to create a kmem cache that will serve allocation
  * requests going from @memcg to @root_cache. The new cache inherits properties
  * from its parent.
  */
 struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
-					   struct kmem_cache *root_cache,
-					   const char *memcg_name)
+					   struct kmem_cache *root_cache)
 {
+	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
 	struct kmem_cache *s = NULL;
 	char *cache_name;
 
@@ -448,8 +447,10 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 
 	mutex_lock(&slab_mutex);
 
+	cgroup_name(mem_cgroup_css(memcg)->cgroup,
+		    memcg_name_buf, sizeof(memcg_name_buf));
 	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
-			       memcg_cache_id(memcg), memcg_name);
+			       memcg_cache_id(memcg), memcg_name_buf);
 	if (!cache_name)
 		goto out_unlock;
 
-- 
cgit v1.2.3-70-g09d2


From d5b3cf7139b8770af4ed8bb36a1ab9d290ac39e9 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Tue, 10 Feb 2015 14:11:47 -0800
Subject: memcg: zap memcg_slab_caches and memcg_slab_mutex

mem_cgroup->memcg_slab_caches is a list of kmem caches corresponding to
the given cgroup.  Currently, it is only used on css free in order to
destroy all caches corresponding to the memory cgroup being freed.  The
list is protected by memcg_slab_mutex.  The mutex is also used to protect
kmem_cache->memcg_params->memcg_caches arrays and synchronizes
kmem_cache_destroy vs memcg_unregister_all_caches.

However, we can perfectly get on without these two.  To destroy all caches
corresponding to a memory cgroup, we can walk over the global list of kmem
caches, slab_caches, and we can do all the synchronization stuff using the
slab_mutex instead of the memcg_slab_mutex.  This patch therefore gets rid
of the memcg_slab_caches and memcg_slab_mutex.

Apart from this nice cleanup, it also:

 - assures that rcu_barrier() is called once at max when a root cache is
   destroyed or a memory cgroup is freed, no matter how many caches have
   SLAB_DESTROY_BY_RCU flag set;

 - fixes the race between kmem_cache_destroy and kmem_cache_create that
   exists, because memcg_cleanup_cache_params, which is called from
   kmem_cache_destroy after checking that kmem_cache->refcount=0,
   releases the slab_mutex, which gives kmem_cache_create a chance to
   make an alias to a cache doomed to be destroyed.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |   2 -
 include/linux/slab.h       |   6 +-
 mm/memcontrol.c            | 156 +++++----------------------------------------
 mm/slab_common.c           | 142 +++++++++++++++++++++++++++++------------
 4 files changed, 120 insertions(+), 186 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 18ccb298897..fb212e1d700 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -407,8 +407,6 @@ int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 		      unsigned long nr_pages);
 void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages);
 
-int __memcg_cleanup_cache_params(struct kmem_cache *s);
-
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
  * @gfp: the gfp allocation flags.
diff --git a/include/linux/slab.h b/include/linux/slab.h
index eca9ed303a1..2e3b448cfa2 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -116,8 +116,8 @@ struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
 			void (*)(void *));
 #ifdef CONFIG_MEMCG_KMEM
-struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *,
-					   struct kmem_cache *);
+void memcg_create_kmem_cache(struct mem_cgroup *, struct kmem_cache *);
+void memcg_destroy_kmem_caches(struct mem_cgroup *);
 #endif
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
@@ -490,7 +490,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
  * Child caches will hold extra metadata needed for its operation. Fields are:
  *
  * @memcg: pointer to the memcg this cache belongs to
- * @list: list_head for the list of all caches in this memcg
  * @root_cache: pointer to the global, root cache, this cache was derived from
  */
 struct memcg_cache_params {
@@ -502,7 +501,6 @@ struct memcg_cache_params {
 		};
 		struct {
 			struct mem_cgroup *memcg;
-			struct list_head list;
 			struct kmem_cache *root_cache;
 		};
 	};
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index baf7eb27e3a..f3f8a4f52a0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -343,9 +343,6 @@ struct mem_cgroup {
 	struct cg_proto tcp_mem;
 #endif
 #if defined(CONFIG_MEMCG_KMEM)
-	/* analogous to slab_common's slab_caches list, but per-memcg;
-	 * protected by memcg_slab_mutex */
-	struct list_head memcg_slab_caches;
         /* Index in the kmem_cache->memcg_params->memcg_caches array */
 	int kmemcg_id;
 #endif
@@ -2476,25 +2473,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-/*
- * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or
- * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists.
- */
-static DEFINE_MUTEX(memcg_slab_mutex);
-
-/*
- * This is a bit cumbersome, but it is rarely used and avoids a backpointer
- * in the memcg_cache_params struct.
- */
-static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
-{
-	struct kmem_cache *cachep;
-
-	VM_BUG_ON(p->is_root_cache);
-	cachep = p->root_cache;
-	return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg));
-}
-
 int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
 		      unsigned long nr_pages)
 {
@@ -2578,10 +2556,7 @@ static int memcg_alloc_cache_id(void)
 	else if (size > MEMCG_CACHES_MAX_SIZE)
 		size = MEMCG_CACHES_MAX_SIZE;
 
-	mutex_lock(&memcg_slab_mutex);
 	err = memcg_update_all_caches(size);
-	mutex_unlock(&memcg_slab_mutex);
-
 	if (err) {
 		ida_simple_remove(&kmem_limited_groups, id);
 		return err;
@@ -2604,120 +2579,20 @@ void memcg_update_array_size(int num)
 	memcg_limited_groups_array_size = num;
 }
 
-static void memcg_register_cache(struct mem_cgroup *memcg,
-				 struct kmem_cache *root_cache)
-{
-	struct kmem_cache *cachep;
-	int id;
-
-	lockdep_assert_held(&memcg_slab_mutex);
-
-	id = memcg_cache_id(memcg);
-
-	/*
-	 * Since per-memcg caches are created asynchronously on first
-	 * allocation (see memcg_kmem_get_cache()), several threads can try to
-	 * create the same cache, but only one of them may succeed.
-	 */
-	if (cache_from_memcg_idx(root_cache, id))
-		return;
-
-	cachep = memcg_create_kmem_cache(memcg, root_cache);
-	/*
-	 * If we could not create a memcg cache, do not complain, because
-	 * that's not critical at all as we can always proceed with the root
-	 * cache.
-	 */
-	if (!cachep)
-		return;
-
-	list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
-
-	/*
-	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
-	 * barrier here to ensure nobody will see the kmem_cache partially
-	 * initialized.
-	 */
-	smp_wmb();
-
-	BUG_ON(root_cache->memcg_params->memcg_caches[id]);
-	root_cache->memcg_params->memcg_caches[id] = cachep;
-}
-
-static void memcg_unregister_cache(struct kmem_cache *cachep)
-{
-	struct kmem_cache *root_cache;
-	struct mem_cgroup *memcg;
-	int id;
-
-	lockdep_assert_held(&memcg_slab_mutex);
-
-	BUG_ON(is_root_cache(cachep));
-
-	root_cache = cachep->memcg_params->root_cache;
-	memcg = cachep->memcg_params->memcg;
-	id = memcg_cache_id(memcg);
-
-	BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep);
-	root_cache->memcg_params->memcg_caches[id] = NULL;
-
-	list_del(&cachep->memcg_params->list);
-
-	kmem_cache_destroy(cachep);
-}
-
-int __memcg_cleanup_cache_params(struct kmem_cache *s)
-{
-	struct kmem_cache *c;
-	int i, failed = 0;
-
-	mutex_lock(&memcg_slab_mutex);
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg_idx(s, i);
-		if (!c)
-			continue;
-
-		memcg_unregister_cache(c);
-
-		if (cache_from_memcg_idx(s, i))
-			failed++;
-	}
-	mutex_unlock(&memcg_slab_mutex);
-	return failed;
-}
-
-static void memcg_unregister_all_caches(struct mem_cgroup *memcg)
-{
-	struct kmem_cache *cachep;
-	struct memcg_cache_params *params, *tmp;
-
-	if (!memcg_kmem_is_active(memcg))
-		return;
-
-	mutex_lock(&memcg_slab_mutex);
-	list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) {
-		cachep = memcg_params_to_cache(params);
-		memcg_unregister_cache(cachep);
-	}
-	mutex_unlock(&memcg_slab_mutex);
-}
-
-struct memcg_register_cache_work {
+struct memcg_kmem_cache_create_work {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *cachep;
 	struct work_struct work;
 };
 
-static void memcg_register_cache_func(struct work_struct *w)
+static void memcg_kmem_cache_create_func(struct work_struct *w)
 {
-	struct memcg_register_cache_work *cw =
-		container_of(w, struct memcg_register_cache_work, work);
+	struct memcg_kmem_cache_create_work *cw =
+		container_of(w, struct memcg_kmem_cache_create_work, work);
 	struct mem_cgroup *memcg = cw->memcg;
 	struct kmem_cache *cachep = cw->cachep;
 
-	mutex_lock(&memcg_slab_mutex);
-	memcg_register_cache(memcg, cachep);
-	mutex_unlock(&memcg_slab_mutex);
+	memcg_create_kmem_cache(memcg, cachep);
 
 	css_put(&memcg->css);
 	kfree(cw);
@@ -2726,10 +2601,10 @@ static void memcg_register_cache_func(struct work_struct *w)
 /*
  * Enqueue the creation of a per-memcg kmem_cache.
  */
-static void __memcg_schedule_register_cache(struct mem_cgroup *memcg,
-					    struct kmem_cache *cachep)
+static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
+					       struct kmem_cache *cachep)
 {
-	struct memcg_register_cache_work *cw;
+	struct memcg_kmem_cache_create_work *cw;
 
 	cw = kmalloc(sizeof(*cw), GFP_NOWAIT);
 	if (!cw)
@@ -2739,18 +2614,18 @@ static void __memcg_schedule_register_cache(struct mem_cgroup *memcg,
 
 	cw->memcg = memcg;
 	cw->cachep = cachep;
+	INIT_WORK(&cw->work, memcg_kmem_cache_create_func);
 
-	INIT_WORK(&cw->work, memcg_register_cache_func);
 	schedule_work(&cw->work);
 }
 
-static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
-					  struct kmem_cache *cachep)
+static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
+					     struct kmem_cache *cachep)
 {
 	/*
 	 * We need to stop accounting when we kmalloc, because if the
 	 * corresponding kmalloc cache is not yet created, the first allocation
-	 * in __memcg_schedule_register_cache will recurse.
+	 * in __memcg_schedule_kmem_cache_create will recurse.
 	 *
 	 * However, it is better to enclose the whole function. Depending on
 	 * the debugging options enabled, INIT_WORK(), for instance, can
@@ -2759,7 +2634,7 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
 	 * the safest choice is to do it like this, wrapping the whole function.
 	 */
 	current->memcg_kmem_skip_account = 1;
-	__memcg_schedule_register_cache(memcg, cachep);
+	__memcg_schedule_kmem_cache_create(memcg, cachep);
 	current->memcg_kmem_skip_account = 0;
 }
 
@@ -2807,7 +2682,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep)
 	 * could happen with the slab_mutex held. So it's better to
 	 * defer everything.
 	 */
-	memcg_schedule_register_cache(memcg, cachep);
+	memcg_schedule_kmem_cache_create(memcg, cachep);
 out:
 	css_put(&memcg->css);
 	return cachep;
@@ -4136,7 +4011,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
-	memcg_unregister_all_caches(memcg);
+	memcg_destroy_kmem_caches(memcg);
 	mem_cgroup_sockets_destroy(memcg);
 }
 #else
@@ -4664,7 +4539,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	spin_lock_init(&memcg->event_list_lock);
 #ifdef CONFIG_MEMCG_KMEM
 	memcg->kmemcg_id = -1;
-	INIT_LIST_HEAD(&memcg->memcg_slab_caches);
 #endif
 
 	return &memcg->css;
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 1b782a2d3b3..6e1e4cf6583 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -425,6 +425,49 @@ out_unlock:
 }
 EXPORT_SYMBOL(kmem_cache_create);
 
+static int do_kmem_cache_shutdown(struct kmem_cache *s,
+		struct list_head *release, bool *need_rcu_barrier)
+{
+	if (__kmem_cache_shutdown(s) != 0) {
+		printk(KERN_ERR "kmem_cache_destroy %s: "
+		       "Slab cache still has objects\n", s->name);
+		dump_stack();
+		return -EBUSY;
+	}
+
+	if (s->flags & SLAB_DESTROY_BY_RCU)
+		*need_rcu_barrier = true;
+
+#ifdef CONFIG_MEMCG_KMEM
+	if (!is_root_cache(s)) {
+		struct kmem_cache *root_cache = s->memcg_params->root_cache;
+		int memcg_id = memcg_cache_id(s->memcg_params->memcg);
+
+		BUG_ON(root_cache->memcg_params->memcg_caches[memcg_id] != s);
+		root_cache->memcg_params->memcg_caches[memcg_id] = NULL;
+	}
+#endif
+	list_move(&s->list, release);
+	return 0;
+}
+
+static void do_kmem_cache_release(struct list_head *release,
+				  bool need_rcu_barrier)
+{
+	struct kmem_cache *s, *s2;
+
+	if (need_rcu_barrier)
+		rcu_barrier();
+
+	list_for_each_entry_safe(s, s2, release, list) {
+#ifdef SLAB_SUPPORTS_SYSFS
+		sysfs_slab_remove(s);
+#else
+		slab_kmem_cache_release(s);
+#endif
+	}
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * memcg_create_kmem_cache - Create a cache for a memory cgroup.
@@ -435,10 +478,11 @@ EXPORT_SYMBOL(kmem_cache_create);
  * requests going from @memcg to @root_cache. The new cache inherits properties
  * from its parent.
  */
-struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
-					   struct kmem_cache *root_cache)
+void memcg_create_kmem_cache(struct mem_cgroup *memcg,
+			     struct kmem_cache *root_cache)
 {
 	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
+	int memcg_id = memcg_cache_id(memcg);
 	struct kmem_cache *s = NULL;
 	char *cache_name;
 
@@ -447,6 +491,14 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 
 	mutex_lock(&slab_mutex);
 
+	/*
+	 * Since per-memcg caches are created asynchronously on first
+	 * allocation (see memcg_kmem_get_cache()), several threads can try to
+	 * create the same cache, but only one of them may succeed.
+	 */
+	if (cache_from_memcg_idx(root_cache, memcg_id))
+		goto out_unlock;
+
 	cgroup_name(mem_cgroup_css(memcg)->cgroup,
 		    memcg_name_buf, sizeof(memcg_name_buf));
 	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
@@ -458,49 +510,73 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 				 root_cache->size, root_cache->align,
 				 root_cache->flags, root_cache->ctor,
 				 memcg, root_cache);
+	/*
+	 * If we could not create a memcg cache, do not complain, because
+	 * that's not critical at all as we can always proceed with the root
+	 * cache.
+	 */
 	if (IS_ERR(s)) {
 		kfree(cache_name);
-		s = NULL;
+		goto out_unlock;
 	}
 
+	/*
+	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
+	 * barrier here to ensure nobody will see the kmem_cache partially
+	 * initialized.
+	 */
+	smp_wmb();
+	root_cache->memcg_params->memcg_caches[memcg_id] = s;
+
 out_unlock:
 	mutex_unlock(&slab_mutex);
 
 	put_online_mems();
 	put_online_cpus();
-
-	return s;
 }
 
-static int memcg_cleanup_cache_params(struct kmem_cache *s)
+void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
 {
-	int rc;
+	LIST_HEAD(release);
+	bool need_rcu_barrier = false;
+	struct kmem_cache *s, *s2;
 
-	if (!s->memcg_params ||
-	    !s->memcg_params->is_root_cache)
-		return 0;
+	get_online_cpus();
+	get_online_mems();
 
-	mutex_unlock(&slab_mutex);
-	rc = __memcg_cleanup_cache_params(s);
 	mutex_lock(&slab_mutex);
+	list_for_each_entry_safe(s, s2, &slab_caches, list) {
+		if (is_root_cache(s) || s->memcg_params->memcg != memcg)
+			continue;
+		/*
+		 * The cgroup is about to be freed and therefore has no charges
+		 * left. Hence, all its caches must be empty by now.
+		 */
+		BUG_ON(do_kmem_cache_shutdown(s, &release, &need_rcu_barrier));
+	}
+	mutex_unlock(&slab_mutex);
 
-	return rc;
-}
-#else
-static int memcg_cleanup_cache_params(struct kmem_cache *s)
-{
-	return 0;
+	put_online_mems();
+	put_online_cpus();
+
+	do_kmem_cache_release(&release, need_rcu_barrier);
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
+	memcg_free_cache_params(s);
 	kfree(s->name);
 	kmem_cache_free(kmem_cache, s);
 }
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
+	int i;
+	LIST_HEAD(release);
+	bool need_rcu_barrier = false;
+	bool busy = false;
+
 	get_online_cpus();
 	get_online_mems();
 
@@ -510,35 +586,23 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (s->refcount)
 		goto out_unlock;
 
-	if (memcg_cleanup_cache_params(s) != 0)
-		goto out_unlock;
+	for_each_memcg_cache_index(i) {
+		struct kmem_cache *c = cache_from_memcg_idx(s, i);
 
-	if (__kmem_cache_shutdown(s) != 0) {
-		printk(KERN_ERR "kmem_cache_destroy %s: "
-		       "Slab cache still has objects\n", s->name);
-		dump_stack();
-		goto out_unlock;
+		if (c && do_kmem_cache_shutdown(c, &release, &need_rcu_barrier))
+			busy = true;
 	}
 
-	list_del(&s->list);
-
-	mutex_unlock(&slab_mutex);
-	if (s->flags & SLAB_DESTROY_BY_RCU)
-		rcu_barrier();
-
-	memcg_free_cache_params(s);
-#ifdef SLAB_SUPPORTS_SYSFS
-	sysfs_slab_remove(s);
-#else
-	slab_kmem_cache_release(s);
-#endif
-	goto out;
+	if (!busy)
+		do_kmem_cache_shutdown(s, &release, &need_rcu_barrier);
 
 out_unlock:
 	mutex_unlock(&slab_mutex);
-out:
+
 	put_online_mems();
 	put_online_cpus();
+
+	do_kmem_cache_release(&release, need_rcu_barrier);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
-- 
cgit v1.2.3-70-g09d2


From 04f81f0154e4bf002be6f4d85668ce1257efa4d9 Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Wed, 11 Feb 2015 14:46:37 -0500
Subject: cipso: don't use IPCB() to locate the CIPSO IP option

Using the IPCB() macro to get the IPv4 options is convenient, but
unfortunately NetLabel often needs to examine the CIPSO option outside
of the scope of the IP layer in the stack.  While historically IPCB()
worked above the IP layer, due to the inclusion of the inet_skb_param
struct at the head of the {tcp,udp}_skb_cb structs, recent commit
971f10ec ("tcp: better TCP_SKB_CB layout to reduce cache line misses")
reordered the tcp_skb_cb struct and invalidated this IPCB() trick.

This patch fixes the problem by creating a new function,
cipso_v4_optptr(), which locates the CIPSO option inside the IP header
without calling IPCB().  Unfortunately, this isn't as fast as a simple
lookup so some additional tweaks were made to limit the use of this
new function.

Cc: <stable@vger.kernel.org> # 3.18
Reported-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Paul Moore <pmoore@redhat.com>
Tested-by: Casey Schaufler <casey@schaufler-ca.com>
---
 include/net/cipso_ipv4.h     | 25 ++++++++++++++--------
 net/ipv4/cipso_ipv4.c        | 51 ++++++++++++++++++++++++++------------------
 net/netlabel/netlabel_kapi.c | 15 ++++++++-----
 3 files changed, 56 insertions(+), 35 deletions(-)

(limited to 'include')

diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index a6fd939f202..3ebb168b9af 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -120,13 +120,6 @@ extern int cipso_v4_rbm_optfmt;
 extern int cipso_v4_rbm_strictvalid;
 #endif
 
-/*
- * Helper Functions
- */
-
-#define CIPSO_V4_OPTEXIST(x) (IPCB(x)->opt.cipso != 0)
-#define CIPSO_V4_OPTPTR(x) (skb_network_header(x) + IPCB(x)->opt.cipso)
-
 /*
  * DOI List Functions
  */
@@ -190,7 +183,7 @@ static inline int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def,
 
 #ifdef CONFIG_NETLABEL
 void cipso_v4_cache_invalidate(void);
-int cipso_v4_cache_add(const struct sk_buff *skb,
+int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 		       const struct netlbl_lsm_secattr *secattr);
 #else
 static inline void cipso_v4_cache_invalidate(void)
@@ -198,7 +191,7 @@ static inline void cipso_v4_cache_invalidate(void)
 	return;
 }
 
-static inline int cipso_v4_cache_add(const struct sk_buff *skb,
+static inline int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 				     const struct netlbl_lsm_secattr *secattr)
 {
 	return 0;
@@ -211,6 +204,8 @@ static inline int cipso_v4_cache_add(const struct sk_buff *skb,
 
 #ifdef CONFIG_NETLABEL
 void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway);
+int cipso_v4_getattr(const unsigned char *cipso,
+		     struct netlbl_lsm_secattr *secattr);
 int cipso_v4_sock_setattr(struct sock *sk,
 			  const struct cipso_v4_doi *doi_def,
 			  const struct netlbl_lsm_secattr *secattr);
@@ -226,6 +221,7 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb,
 int cipso_v4_skbuff_delattr(struct sk_buff *skb);
 int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
 			    struct netlbl_lsm_secattr *secattr);
+unsigned char *cipso_v4_optptr(const struct sk_buff *skb);
 int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option);
 #else
 static inline void cipso_v4_error(struct sk_buff *skb,
@@ -235,6 +231,12 @@ static inline void cipso_v4_error(struct sk_buff *skb,
 	return;
 }
 
+static inline int cipso_v4_getattr(const unsigned char *cipso,
+				   struct netlbl_lsm_secattr *secattr)
+{
+	return -ENOSYS;
+}
+
 static inline int cipso_v4_sock_setattr(struct sock *sk,
 				      const struct cipso_v4_doi *doi_def,
 				      const struct netlbl_lsm_secattr *secattr)
@@ -282,6 +284,11 @@ static inline int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
 	return -ENOSYS;
 }
 
+static inline unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
+{
+	return NULL;
+}
+
 static inline int cipso_v4_validate(const struct sk_buff *skb,
 				    unsigned char **option)
 {
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 5160c710f2e..e361ea6f3fc 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -378,20 +378,18 @@ static int cipso_v4_cache_check(const unsigned char *key,
  * negative values on failure.
  *
  */
-int cipso_v4_cache_add(const struct sk_buff *skb,
+int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 		       const struct netlbl_lsm_secattr *secattr)
 {
 	int ret_val = -EPERM;
 	u32 bkt;
 	struct cipso_v4_map_cache_entry *entry = NULL;
 	struct cipso_v4_map_cache_entry *old_entry = NULL;
-	unsigned char *cipso_ptr;
 	u32 cipso_ptr_len;
 
 	if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
 		return 0;
 
-	cipso_ptr = CIPSO_V4_OPTPTR(skb);
 	cipso_ptr_len = cipso_ptr[1];
 
 	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
@@ -1578,6 +1576,33 @@ static int cipso_v4_parsetag_loc(const struct cipso_v4_doi *doi_def,
 	return 0;
 }
 
+/**
+ * cipso_v4_optptr - Find the CIPSO option in the packet
+ * @skb: the packet
+ *
+ * Description:
+ * Parse the packet's IP header looking for a CIPSO option.  Returns a pointer
+ * to the start of the CIPSO option on success, NULL if one if not found.
+ *
+ */
+unsigned char *cipso_v4_optptr(const struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	unsigned char *optptr = (unsigned char *)&(ip_hdr(skb)[1]);
+	int optlen;
+	int taglen;
+
+	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) {
+		if (optptr[0] == IPOPT_CIPSO)
+			return optptr;
+		taglen = optptr[1];
+		optlen -= taglen;
+		optptr += taglen;
+	}
+
+	return NULL;
+}
+
 /**
  * cipso_v4_validate - Validate a CIPSO option
  * @option: the start of the option, on error it is set to point to the error
@@ -2119,8 +2144,8 @@ void cipso_v4_req_delattr(struct request_sock *req)
  * on success and negative values on failure.
  *
  */
-static int cipso_v4_getattr(const unsigned char *cipso,
-			    struct netlbl_lsm_secattr *secattr)
+int cipso_v4_getattr(const unsigned char *cipso,
+		     struct netlbl_lsm_secattr *secattr)
 {
 	int ret_val = -ENOMSG;
 	u32 doi;
@@ -2305,22 +2330,6 @@ int cipso_v4_skbuff_delattr(struct sk_buff *skb)
 	return 0;
 }
 
-/**
- * cipso_v4_skbuff_getattr - Get the security attributes from the CIPSO option
- * @skb: the packet
- * @secattr: the security attributes
- *
- * Description:
- * Parse the given packet's CIPSO option and return the security attributes.
- * Returns zero on success and negative values on failure.
- *
- */
-int cipso_v4_skbuff_getattr(const struct sk_buff *skb,
-			    struct netlbl_lsm_secattr *secattr)
-{
-	return cipso_v4_getattr(CIPSO_V4_OPTPTR(skb), secattr);
-}
-
 /*
  * Setup Functions
  */
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index a845cd4cf21..28cddc85b70 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -1065,10 +1065,12 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb,
 			  u16 family,
 			  struct netlbl_lsm_secattr *secattr)
 {
+	unsigned char *ptr;
+
 	switch (family) {
 	case AF_INET:
-		if (CIPSO_V4_OPTEXIST(skb) &&
-		    cipso_v4_skbuff_getattr(skb, secattr) == 0)
+		ptr = cipso_v4_optptr(skb);
+		if (ptr && cipso_v4_getattr(ptr, secattr) == 0)
 			return 0;
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1094,7 +1096,7 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb,
  */
 void netlbl_skbuff_err(struct sk_buff *skb, int error, int gateway)
 {
-	if (CIPSO_V4_OPTEXIST(skb))
+	if (cipso_v4_optptr(skb))
 		cipso_v4_error(skb, error, gateway);
 }
 
@@ -1126,11 +1128,14 @@ void netlbl_cache_invalidate(void)
 int netlbl_cache_add(const struct sk_buff *skb,
 		     const struct netlbl_lsm_secattr *secattr)
 {
+	unsigned char *ptr;
+
 	if ((secattr->flags & NETLBL_SECATTR_CACHE) == 0)
 		return -ENOMSG;
 
-	if (CIPSO_V4_OPTEXIST(skb))
-		return cipso_v4_cache_add(skb, secattr);
+	ptr = cipso_v4_optptr(skb);
+	if (ptr)
+		return cipso_v4_cache_add(ptr, secattr);
 
 	return -ENOMSG;
 }
-- 
cgit v1.2.3-70-g09d2


From e4b294c2d8f73af4cd41ff30638ad0e4769dc56a Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 11 Feb 2015 15:24:46 -0800
Subject: mm: add fields for compound destructor and order into struct page

Currently, we use lru.next/lru.prev plus cast to access or set
destructor and order of compound page.

Let's replace it with explicit fields in struct page.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h       | 9 ++++-----
 include/linux/mm_types.h | 8 ++++++++
 2 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 65db4aee738..8dd4fde9d2e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -627,29 +627,28 @@ int split_free_page(struct page *page);
  * prototype for that function and accessor functions.
  * These are _only_ valid on the head of a PG_compound page.
  */
-typedef void compound_page_dtor(struct page *);
 
 static inline void set_compound_page_dtor(struct page *page,
 						compound_page_dtor *dtor)
 {
-	page[1].lru.next = (void *)dtor;
+	page[1].compound_dtor = dtor;
 }
 
 static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
 {
-	return (compound_page_dtor *)page[1].lru.next;
+	return page[1].compound_dtor;
 }
 
 static inline int compound_order(struct page *page)
 {
 	if (!PageHead(page))
 		return 0;
-	return (unsigned long)page[1].lru.prev;
+	return page[1].compound_order;
 }
 
 static inline void set_compound_order(struct page *page, unsigned long order)
 {
-	page[1].lru.prev = (void *)order;
+	page[1].compound_order = order;
 }
 
 #ifdef CONFIG_MMU
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 07c8bd3f7b4..20ff2105b56 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -28,6 +28,8 @@ struct mem_cgroup;
 		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
 #define ALLOC_SPLIT_PTLOCKS	(SPINLOCK_SIZE > BITS_PER_LONG/8)
 
+typedef void compound_page_dtor(struct page *);
+
 /*
  * Each physical page in the system has a struct page associated with
  * it to keep track of whatever it is we are using the page for at the
@@ -142,6 +144,12 @@ struct page {
 		struct rcu_head rcu_head;	/* Used by SLAB
 						 * when destroying via RCU
 						 */
+		/* First tail page of compound page */
+		struct {
+			compound_page_dtor *compound_dtor;
+			unsigned long compound_order;
+		};
+
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
 		pgtable_t pmd_huge_pte; /* protected by page->ptl */
 #endif
-- 
cgit v1.2.3-70-g09d2


From 1d148e218a0d0566b1c06f2f45f1436d53b049b2 Mon Sep 17 00:00:00 2001
From: "Wang, Yalin" <Yalin.Wang@sonymobile.com>
Date: Wed, 11 Feb 2015 15:24:48 -0800
Subject: mm: add VM_BUG_ON_PAGE() to page_mapcount()

Add VM_BUG_ON_PAGE() for slab pages.  _mapcount is an union with slab
struct in struct page, so we must avoid accessing _mapcount if this page
is a slab page.  Also remove the unneeded bracket.

Signed-off-by: Yalin Wang <yalin.wang@sonymobile.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8dd4fde9d2e..c6bf813a6b3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -484,7 +484,8 @@ static inline void page_mapcount_reset(struct page *page)
 
 static inline int page_mapcount(struct page *page)
 {
-	return atomic_read(&(page)->_mapcount) + 1;
+	VM_BUG_ON_PAGE(PageSlab(page), page);
+	return atomic_read(&page->_mapcount) + 1;
 }
 
 static inline int page_count(struct page *page)
-- 
cgit v1.2.3-70-g09d2


From 56873f43abdcd574b25105867a990f067747b2f4 Mon Sep 17 00:00:00 2001
From: "Wang, Yalin" <Yalin.Wang@sonymobile.com>
Date: Wed, 11 Feb 2015 15:24:51 -0800
Subject: mm:add KPF_ZERO_PAGE flag for /proc/kpageflags

Add KPF_ZERO_PAGE flag for zero_page, so that userspace processes can
detect zero_page in /proc/kpageflags, and then do memory analysis more
accurately.

Signed-off-by: Yalin Wang <yalin.wang@sonymobile.com>
Acked-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/vm/pagemap.txt           |  8 ++++++++
 fs/proc/page.c                         | 16 +++++++++++++---
 include/linux/huge_mm.h                | 12 ++++++++++++
 include/uapi/linux/kernel-page-flags.h |  1 +
 mm/huge_memory.c                       |  7 +------
 tools/vm/page-types.c                  |  1 +
 6 files changed, 36 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index 5948e455c4d..6fbd55ef6b4 100644
--- a/Documentation/vm/pagemap.txt
+++ b/Documentation/vm/pagemap.txt
@@ -62,6 +62,8 @@ There are three components to pagemap:
     20. NOPAGE
     21. KSM
     22. THP
+    23. BALLOON
+    24. ZERO_PAGE
 
 Short descriptions to the page flags:
 
@@ -102,6 +104,12 @@ Short descriptions to the page flags:
 22. THP
     contiguous pages which construct transparent hugepages
 
+23. BALLOON
+    balloon compaction page
+
+24. ZERO_PAGE
+    zero page for pfn_zero or huge_zero page
+
     [IO related page flags]
  1. ERROR     IO error occurred
  3. UPTODATE  page has up-to-date data
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 1e3187da1fe..7eee2d8b97d 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -5,6 +5,7 @@
 #include <linux/ksm.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
+#include <linux/huge_mm.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
@@ -121,9 +122,18 @@ u64 stable_page_flags(struct page *page)
 	 * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
 	 * to make sure a given page is a thp, not a non-huge compound page.
 	 */
-	else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
-					     PageAnon(compound_head(page))))
-		u |= 1 << KPF_THP;
+	else if (PageTransCompound(page)) {
+		struct page *head = compound_head(page);
+
+		if (PageLRU(head) || PageAnon(head))
+			u |= 1 << KPF_THP;
+		else if (is_huge_zero_page(head)) {
+			u |= 1 << KPF_ZERO_PAGE;
+			u |= 1 << KPF_THP;
+		}
+	} else if (is_zero_pfn(page_to_pfn(page)))
+		u |= 1 << KPF_ZERO_PAGE;
+
 
 	/*
 	 * Caveats on high order pages: page->_count will only be set
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ad9051bab26..f10b20f0515 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -157,6 +157,13 @@ static inline int hpage_nr_pages(struct page *page)
 extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp);
 
+extern struct page *huge_zero_page;
+
+static inline bool is_huge_zero_page(struct page *page)
+{
+	return ACCESS_ONCE(huge_zero_page) == page;
+}
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
@@ -206,6 +213,11 @@ static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_str
 	return 0;
 }
 
+static inline bool is_huge_zero_page(struct page *page)
+{
+	return false;
+}
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h
index 2f96d233c98..a6c4962e5d4 100644
--- a/include/uapi/linux/kernel-page-flags.h
+++ b/include/uapi/linux/kernel-page-flags.h
@@ -32,6 +32,7 @@
 #define KPF_KSM			21
 #define KPF_THP			22
 #define KPF_BALLOON		23
+#define KPF_ZERO_PAGE		24
 
 
 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 817a875f2b8..88971318098 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -171,12 +171,7 @@ static int start_khugepaged(void)
 }
 
 static atomic_t huge_zero_refcount;
-static struct page *huge_zero_page __read_mostly;
-
-static inline bool is_huge_zero_page(struct page *page)
-{
-	return ACCESS_ONCE(huge_zero_page) == page;
-}
+struct page *huge_zero_page __read_mostly;
 
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 264fbc297e0..8bdf16b8ba6 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -133,6 +133,7 @@ static const char * const page_flag_names[] = {
 	[KPF_KSM]		= "x:ksm",
 	[KPF_THP]		= "t:thp",
 	[KPF_BALLOON]		= "o:balloon",
+	[KPF_ZERO_PAGE]		= "z:zero_page",
 
 	[KPF_RESERVED]		= "r:reserved",
 	[KPF_MLOCKED]		= "m:mlocked",
-- 
cgit v1.2.3-70-g09d2


From 93aa7d95248d04b934eb8e89717c7b8d6400bf2b Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Wed, 11 Feb 2015 15:24:59 -0800
Subject: swap: remove unused mem_cgroup_uncharge_swapcache declaration

The body of this function was removed by commit 0a31bc97c80c ("mm:
memcontrol: rewrite uncharge API").

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h | 15 ---------------
 mm/shmem.c           |  2 +-
 2 files changed, 1 insertion(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 34e8b60ab97..7067eca501e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -437,16 +437,6 @@ extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 
-#ifdef CONFIG_MEMCG
-extern void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
-#else
-static inline void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
-{
-}
-#endif
-
 #else /* CONFIG_SWAP */
 
 #define swap_address_space(entry)		(NULL)
@@ -547,11 +537,6 @@ static inline swp_entry_t get_swap_page(void)
 	return entry;
 }
 
-static inline void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
-{
-}
-
 #endif /* CONFIG_SWAP */
 #endif /* __KERNEL__*/
 #endif /* _LINUX_SWAP_H */
diff --git a/mm/shmem.c b/mm/shmem.c
index b3e40318198..864c878401e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1131,7 +1131,7 @@ repeat:
 			 * truncated or holepunched since swap was confirmed.
 			 * shmem_undo_range() will have done some of the
 			 * unaccounting, now delete_from_swap_cache() will do
-			 * the rest (including mem_cgroup_uncharge_swapcache).
+			 * the rest.
 			 * Reset swap.val? No, leave it so "failed" goes back to
 			 * "repeat": reading a hole and writing should succeed.
 			 */
-- 
cgit v1.2.3-70-g09d2


From 6de226191d12fce30331ebf024ca3ed24834f0ee Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 11 Feb 2015 15:25:01 -0800
Subject: mm: memcontrol: track move_lock state internally

The complexity of memcg page stat synchronization is currently leaking
into the callsites, forcing them to keep track of the move_lock state and
the IRQ flags.  Simplify the API by tracking it in the memcg.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 12 +++-----
 mm/memcontrol.c            | 68 ++++++++++++++++++++++++++--------------------
 mm/page-writeback.c        | 12 +++-----
 mm/rmap.c                  | 12 +++-----
 4 files changed, 51 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index fb212e1d700..76b4084b8d0 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -138,12 +138,10 @@ static inline bool mem_cgroup_disabled(void)
 	return false;
 }
 
-struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked,
-					      unsigned long *flags);
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
-			      unsigned long *flags);
+struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page);
 void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
 				 enum mem_cgroup_stat_index idx, int val);
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg);
 
 static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg,
 					    enum mem_cgroup_stat_index idx)
@@ -285,14 +283,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
-static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
-					bool *locked, unsigned long *flags)
+static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
 {
 	return NULL;
 }
 
-static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg,
-					bool *locked, unsigned long *flags)
+static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 {
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f3f8a4f52a0..028d07c7910 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -325,9 +325,11 @@ struct mem_cgroup {
 	/*
 	 * set > 0 if pages under this cgroup are moving to other cgroup.
 	 */
-	atomic_t	moving_account;
+	atomic_t		moving_account;
 	/* taken only while moving_account > 0 */
-	spinlock_t	move_lock;
+	spinlock_t		move_lock;
+	struct task_struct	*move_lock_task;
+	unsigned long		move_lock_flags;
 	/*
 	 * percpu counter.
 	 */
@@ -1977,34 +1979,33 @@ cleanup:
 /**
  * mem_cgroup_begin_page_stat - begin a page state statistics transaction
  * @page: page that is going to change accounted state
- * @locked: &memcg->move_lock slowpath was taken
- * @flags: IRQ-state flags for &memcg->move_lock
  *
  * This function must mark the beginning of an accounted page state
  * change to prevent double accounting when the page is concurrently
  * being moved to another memcg:
  *
- *   memcg = mem_cgroup_begin_page_stat(page, &locked, &flags);
+ *   memcg = mem_cgroup_begin_page_stat(page);
  *   if (TestClearPageState(page))
  *     mem_cgroup_update_page_stat(memcg, state, -1);
- *   mem_cgroup_end_page_stat(memcg, locked, flags);
- *
- * The RCU lock is held throughout the transaction.  The fast path can
- * get away without acquiring the memcg->move_lock (@locked is false)
- * because page moving starts with an RCU grace period.
- *
- * The RCU lock also protects the memcg from being freed when the page
- * state that is going to change is the only thing preventing the page
- * from being uncharged.  E.g. end-writeback clearing PageWriteback(),
- * which allows migration to go ahead and uncharge the page before the
- * account transaction might be complete.
+ *   mem_cgroup_end_page_stat(memcg);
  */
-struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
-					      bool *locked,
-					      unsigned long *flags)
+struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page)
 {
 	struct mem_cgroup *memcg;
+	unsigned long flags;
 
+	/*
+	 * The RCU lock is held throughout the transaction.  The fast
+	 * path can get away without acquiring the memcg->move_lock
+	 * because page moving starts with an RCU grace period.
+	 *
+	 * The RCU lock also protects the memcg from being freed when
+	 * the page state that is going to change is the only thing
+	 * preventing the page from being uncharged.
+	 * E.g. end-writeback clearing PageWriteback(), which allows
+	 * migration to go ahead and uncharge the page before the
+	 * account transaction might be complete.
+	 */
 	rcu_read_lock();
 
 	if (mem_cgroup_disabled())
@@ -2014,16 +2015,22 @@ again:
 	if (unlikely(!memcg))
 		return NULL;
 
-	*locked = false;
 	if (atomic_read(&memcg->moving_account) <= 0)
 		return memcg;
 
-	spin_lock_irqsave(&memcg->move_lock, *flags);
+	spin_lock_irqsave(&memcg->move_lock, flags);
 	if (memcg != page->mem_cgroup) {
-		spin_unlock_irqrestore(&memcg->move_lock, *flags);
+		spin_unlock_irqrestore(&memcg->move_lock, flags);
 		goto again;
 	}
-	*locked = true;
+
+	/*
+	 * When charge migration first begins, we can have locked and
+	 * unlocked page stat updates happening concurrently.  Track
+	 * the task who has the lock for mem_cgroup_end_page_stat().
+	 */
+	memcg->move_lock_task = current;
+	memcg->move_lock_flags = flags;
 
 	return memcg;
 }
@@ -2031,14 +2038,17 @@ again:
 /**
  * mem_cgroup_end_page_stat - finish a page state statistics transaction
  * @memcg: the memcg that was accounted against
- * @locked: value received from mem_cgroup_begin_page_stat()
- * @flags: value received from mem_cgroup_begin_page_stat()
  */
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
-			      unsigned long *flags)
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 {
-	if (memcg && *locked)
-		spin_unlock_irqrestore(&memcg->move_lock, *flags);
+	if (memcg && memcg->move_lock_task == current) {
+		unsigned long flags = memcg->move_lock_flags;
+
+		memcg->move_lock_task = NULL;
+		memcg->move_lock_flags = 0;
+
+		spin_unlock_irqrestore(&memcg->move_lock, flags);
+	}
 
 	rcu_read_unlock();
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6f4335238e3..fb71e9deca8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2308,12 +2308,10 @@ EXPORT_SYMBOL(clear_page_dirty_for_io);
 int test_clear_page_writeback(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
-	unsigned long memcg_flags;
 	struct mem_cgroup *memcg;
-	bool locked;
 	int ret;
 
-	memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
+	memcg = mem_cgroup_begin_page_stat(page);
 	if (mapping) {
 		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		unsigned long flags;
@@ -2338,19 +2336,17 @@ int test_clear_page_writeback(struct page *page)
 		dec_zone_page_state(page, NR_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITTEN);
 	}
-	mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags);
+	mem_cgroup_end_page_stat(memcg);
 	return ret;
 }
 
 int __test_set_page_writeback(struct page *page, bool keep_write)
 {
 	struct address_space *mapping = page_mapping(page);
-	unsigned long memcg_flags;
 	struct mem_cgroup *memcg;
-	bool locked;
 	int ret;
 
-	memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags);
+	memcg = mem_cgroup_begin_page_stat(page);
 	if (mapping) {
 		struct backing_dev_info *bdi = mapping->backing_dev_info;
 		unsigned long flags;
@@ -2380,7 +2376,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITEBACK);
 	}
-	mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags);
+	mem_cgroup_end_page_stat(memcg);
 	return ret;
 
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 70b32498d4f..5e3e0908116 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1085,24 +1085,20 @@ void page_add_new_anon_rmap(struct page *page,
 void page_add_file_rmap(struct page *page)
 {
 	struct mem_cgroup *memcg;
-	unsigned long flags;
-	bool locked;
 
-	memcg = mem_cgroup_begin_page_stat(page, &locked, &flags);
+	memcg = mem_cgroup_begin_page_stat(page);
 	if (atomic_inc_and_test(&page->_mapcount)) {
 		__inc_zone_page_state(page, NR_FILE_MAPPED);
 		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
 	}
-	mem_cgroup_end_page_stat(memcg, &locked, &flags);
+	mem_cgroup_end_page_stat(memcg);
 }
 
 static void page_remove_file_rmap(struct page *page)
 {
 	struct mem_cgroup *memcg;
-	unsigned long flags;
-	bool locked;
 
-	memcg = mem_cgroup_begin_page_stat(page, &locked, &flags);
+	memcg = mem_cgroup_begin_page_stat(page);
 
 	/* page still mapped by someone else? */
 	if (!atomic_add_negative(-1, &page->_mapcount))
@@ -1123,7 +1119,7 @@ static void page_remove_file_rmap(struct page *page)
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
 out:
-	mem_cgroup_end_page_stat(memcg, &locked, &flags);
+	mem_cgroup_end_page_stat(memcg);
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 44628d9755e249aab9a6e1a17407d2f4278047ee Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Wed, 11 Feb 2015 15:25:10 -0800
Subject: mm: fix typo of MIGRATE_RESERVE in comment

Found it when I want to jump to the definition of MIGRATE_RESERVE ctags.

Signed-off-by: Baoquan He <bhe@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2f0856d14b2..b4182970133 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -426,7 +426,7 @@ struct zone {
 	const char		*name;
 
 	/*
-	 * Number of MIGRATE_RESEVE page block. To maintain for just
+	 * Number of MIGRATE_RESERVE page block. To maintain for just
 	 * optimization. Protected by zone->lock.
 	 */
 	int			nr_migrate_reserve_block;
-- 
cgit v1.2.3-70-g09d2


From e66f17ff71772b209eed39de35aaa99ba819c93d Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Wed, 11 Feb 2015 15:25:22 -0800
Subject: mm/hugetlb: take page table lock in follow_huge_pmd()

We have a race condition between move_pages() and freeing hugepages, where
move_pages() calls follow_page(FOLL_GET) for hugepages internally and
tries to get its refcount without preventing concurrent freeing.  This
race crashes the kernel, so this patch fixes it by moving FOLL_GET code
for hugepages into follow_huge_pmd() with taking the page table lock.

This patch intentionally removes page==NULL check after pte_page.
This is justified because pte_page() never returns NULL for any
architectures or configurations.

This patch changes the behavior of follow_huge_pmd() for tail pages and
then tail pages can be pinned/returned.  So the caller must be changed to
properly handle the returned tail pages.

We could have a choice to add the similar locking to
follow_huge_(addr|pud) for consistency, but it's not necessary because
currently these functions don't support FOLL_GET flag, so let's leave it
for future development.

Here is the reproducer:

  $ cat movepages.c
  #include <stdio.h>
  #include <stdlib.h>
  #include <numaif.h>

  #define ADDR_INPUT      0x700000000000UL
  #define HPS             0x200000
  #define PS              0x1000

  int main(int argc, char *argv[]) {
          int i;
          int nr_hp = strtol(argv[1], NULL, 0);
          int nr_p  = nr_hp * HPS / PS;
          int ret;
          void **addrs;
          int *status;
          int *nodes;
          pid_t pid;

          pid = strtol(argv[2], NULL, 0);
          addrs  = malloc(sizeof(char *) * nr_p + 1);
          status = malloc(sizeof(char *) * nr_p + 1);
          nodes  = malloc(sizeof(char *) * nr_p + 1);

          while (1) {
                  for (i = 0; i < nr_p; i++) {
                          addrs[i] = (void *)ADDR_INPUT + i * PS;
                          nodes[i] = 1;
                          status[i] = 0;
                  }
                  ret = numa_move_pages(pid, nr_p, addrs, nodes, status,
                                        MPOL_MF_MOVE_ALL);
                  if (ret == -1)
                          err("move_pages");

                  for (i = 0; i < nr_p; i++) {
                          addrs[i] = (void *)ADDR_INPUT + i * PS;
                          nodes[i] = 0;
                          status[i] = 0;
                  }
                  ret = numa_move_pages(pid, nr_p, addrs, nodes, status,
                                        MPOL_MF_MOVE_ALL);
                  if (ret == -1)
                          err("move_pages");
          }
          return 0;
  }

  $ cat hugepage.c
  #include <stdio.h>
  #include <sys/mman.h>
  #include <string.h>

  #define ADDR_INPUT      0x700000000000UL
  #define HPS             0x200000

  int main(int argc, char *argv[]) {
          int nr_hp = strtol(argv[1], NULL, 0);
          char *p;

          while (1) {
                  p = mmap((void *)ADDR_INPUT, nr_hp * HPS, PROT_READ | PROT_WRITE,
                           MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0);
                  if (p != (void *)ADDR_INPUT) {
                          perror("mmap");
                          break;
                  }
                  memset(p, 0, nr_hp * HPS);
                  munmap(p, nr_hp * HPS);
          }
  }

  $ sysctl vm.nr_hugepages=40
  $ ./hugepage 10 &
  $ ./movepages 10 $(pgrep -f hugepage)

Fixes: e632a938d914 ("mm: migrate: add hugepage migration code to move_pages()")
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reported-by: Hugh Dickins <hughd@google.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Luiz Capitulino <lcapitulino@redhat.com>
Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: <stable@vger.kernel.org>	[3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  8 ++++----
 include/linux/swapops.h |  4 ++++
 mm/gup.c                | 25 ++++++++-----------------
 mm/hugetlb.c            | 48 ++++++++++++++++++++++++++++++++++--------------
 mm/migrate.c            |  5 +++--
 5 files changed, 53 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 7d785635992..7b578503204 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -99,9 +99,9 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write);
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-				pmd_t *pmd, int write);
+				pmd_t *pmd, int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
-				pud_t *pud, int write);
+				pud_t *pud, int flags);
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pmd);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
@@ -133,8 +133,8 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 static inline void hugetlb_show_meminfo(void)
 {
 }
-#define follow_huge_pmd(mm, addr, pmd, write)	NULL
-#define follow_huge_pud(mm, addr, pud, write)	NULL
+#define follow_huge_pmd(mm, addr, pmd, flags)	NULL
+#define follow_huge_pud(mm, addr, pud, flags)	NULL
 #define prepare_hugepage_range(file, addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
 #define pud_huge(x)	0
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 50cbc876be5..831a3168ab3 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -135,6 +135,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
 	*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
 }
 
+extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+					spinlock_t *ptl);
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
 extern void migration_entry_wait_huge(struct vm_area_struct *vma,
@@ -148,6 +150,8 @@ static inline int is_migration_entry(swp_entry_t swp)
 }
 #define migration_entry_to_page(swp) NULL
 static inline void make_migration_entry_read(swp_entry_t *entryp) { }
+static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+					spinlock_t *ptl) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
 static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
diff --git a/mm/gup.c b/mm/gup.c
index 12bc2bc33da..1a8ab05918e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -167,10 +167,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
 	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
-		if (flags & FOLL_GET)
-			return NULL;
-		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
-		return page;
+		page = follow_huge_pud(mm, address, pud, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
 	if (unlikely(pud_bad(*pud)))
 		return no_page_table(vma, flags);
@@ -179,19 +179,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
 	if (pmd_none(*pmd))
 		return no_page_table(vma, flags);
 	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
-		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
-		if (flags & FOLL_GET) {
-			/*
-			 * Refcount on tail pages are not well-defined and
-			 * shouldn't be taken. The caller should handle a NULL
-			 * return when trying to follow tail pages.
-			 */
-			if (PageHead(page))
-				get_page(page);
-			else
-				page = NULL;
-		}
-		return page;
+		page = follow_huge_pmd(mm, address, pmd, flags);
+		if (page)
+			return page;
+		return no_page_table(vma, flags);
 	}
 	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
 		return no_page_table(vma, flags);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d96b8bfa748..5aca3707450 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3675,28 +3675,48 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address,
 
 struct page * __weak
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
+		pmd_t *pmd, int flags)
 {
-	struct page *page;
-
-	if (!pmd_present(*pmd))
-		return NULL;
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+	struct page *page = NULL;
+	spinlock_t *ptl;
+retry:
+	ptl = pmd_lockptr(mm, pmd);
+	spin_lock(ptl);
+	/*
+	 * make sure that the address range covered by this pmd is not
+	 * unmapped from other threads.
+	 */
+	if (!pmd_huge(*pmd))
+		goto out;
+	if (pmd_present(*pmd)) {
+		page = pte_page(*(pte_t *)pmd) +
+			((address & ~PMD_MASK) >> PAGE_SHIFT);
+		if (flags & FOLL_GET)
+			get_page(page);
+	} else {
+		if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) {
+			spin_unlock(ptl);
+			__migration_entry_wait(mm, (pte_t *)pmd, ptl);
+			goto retry;
+		}
+		/*
+		 * hwpoisoned entry is treated as no_page_table in
+		 * follow_page_mask().
+		 */
+	}
+out:
+	spin_unlock(ptl);
 	return page;
 }
 
 struct page * __weak
 follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int write)
+		pud_t *pud, int flags)
 {
-	struct page *page;
+	if (flags & FOLL_GET)
+		return NULL;
 
-	page = pte_page(*(pte_t *)pud);
-	if (page)
-		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
-	return page;
+	return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
 }
 
 #ifdef CONFIG_MEMORY_FAILURE
diff --git a/mm/migrate.c b/mm/migrate.c
index 6e284bcca8b..f98067e5d35 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -197,7 +197,7 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  * get to the page and wait until migration is finished.
  * When we return from this function the fault will be retried.
  */
-static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 				spinlock_t *ptl)
 {
 	pte_t pte;
@@ -1236,7 +1236,8 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 			goto put_and_set;
 
 		if (PageHuge(page)) {
-			isolate_huge_page(page, &pagelist);
+			if (PageHead(page))
+				isolate_huge_page(page, &pagelist);
 			goto put_and_set;
 		}
 
-- 
cgit v1.2.3-70-g09d2


From 1a6d53a105406d97396c87511afd6f09b4dc8ad2 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 11 Feb 2015 15:25:44 -0800
Subject: mm: reduce try_to_compact_pages parameters

Expand the usage of the struct alloc_context introduced in the previous
patch also for calling try_to_compact_pages(), to reduce the number of its
parameters.  Since the function is in different compilation unit, we need
to move alloc_context definition in the shared mm/internal.h header.

With this change we get simpler code and small savings of code size and stack
usage:

add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-27 (-27)
function                                     old     new   delta
__alloc_pages_direct_compact                 283     256     -27
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-13 (-13)
function                                     old     new   delta
try_to_compact_pages                         582     569     -13

Stack usage of __alloc_pages_direct_compact goes from 24 to none (per
scripts/checkstack.pl).

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h | 17 +++++++++--------
 mm/compaction.c            | 23 +++++++++++------------
 mm/internal.h              | 22 ++++++++++++++++++++++
 mm/page_alloc.c            | 27 ++-------------------------
 4 files changed, 44 insertions(+), 45 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 3238ffa33f6..f2efda2e6ac 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -21,6 +21,8 @@
 /* Zone lock or lru_lock was contended in async compaction */
 #define COMPACT_CONTENDED_LOCK	2
 
+struct alloc_context; /* in mm/internal.h */
+
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
@@ -30,10 +32,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 			void __user *buffer, size_t *length, loff_t *ppos);
 
 extern int fragmentation_index(struct zone *zone, unsigned int order);
-extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
-			int order, gfp_t gfp_mask, nodemask_t *mask,
-			enum migrate_mode mode, int *contended,
-			int alloc_flags, int classzone_idx);
+extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
+			int alloc_flags, const struct alloc_context *ac,
+			enum migrate_mode mode, int *contended);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order,
@@ -101,10 +102,10 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 }
 
 #else
-static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
-			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, int *contended,
-			int alloc_flags, int classzone_idx)
+static inline unsigned long try_to_compact_pages(gfp_t gfp_mask,
+			unsigned int order, int alloc_flags,
+			const struct alloc_context *ac,
+			enum migrate_mode mode, int *contended)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 546e571e9d6..9c7e6909dd2 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1335,22 +1335,20 @@ int sysctl_extfrag_threshold = 500;
 
 /**
  * try_to_compact_pages - Direct compact to satisfy a high-order allocation
- * @zonelist: The zonelist used for the current allocation
- * @order: The order of the current allocation
  * @gfp_mask: The GFP mask of the current allocation
- * @nodemask: The allowed nodes to allocate from
+ * @order: The order of the current allocation
+ * @alloc_flags: The allocation flags of the current allocation
+ * @ac: The context of current allocation
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that determines if compaction was aborted due to
  *	       need_resched() or lock contention
  *
  * This is the main entry point for direct page compaction.
  */
-unsigned long try_to_compact_pages(struct zonelist *zonelist,
-			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			enum migrate_mode mode, int *contended,
-			int alloc_flags, int classzone_idx)
+unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
+			int alloc_flags, const struct alloc_context *ac,
+			enum migrate_mode mode, int *contended)
 {
-	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
 	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
@@ -1365,8 +1363,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		return COMPACT_SKIPPED;
 
 	/* Compact each zone in the list */
-	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
-								nodemask) {
+	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
+								ac->nodemask) {
 		int status;
 		int zone_contended;
 
@@ -1374,7 +1372,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-				&zone_contended, alloc_flags, classzone_idx);
+				&zone_contended, alloc_flags,
+				ac->classzone_idx);
 		rc = max(status, rc);
 		/*
 		 * It takes at least one zone that wasn't lock contended
@@ -1384,7 +1383,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
-					classzone_idx, alloc_flags)) {
+					ac->classzone_idx, alloc_flags)) {
 			/*
 			 * We think the allocation will succeed in this zone,
 			 * but it is not certain, hence the false. The caller
diff --git a/mm/internal.h b/mm/internal.h
index efad241f701..c4d6c9b4349 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -109,6 +109,28 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
  * in mm/page_alloc.c
  */
 
+/*
+ * Structure for holding the mostly immutable allocation parameters passed
+ * between functions involved in allocations, including the alloc_pages*
+ * family of functions.
+ *
+ * nodemask, migratetype and high_zoneidx are initialized only once in
+ * __alloc_pages_nodemask() and then never change.
+ *
+ * zonelist, preferred_zone and classzone_idx are set first in
+ * __alloc_pages_nodemask() for the fast path, and might be later changed
+ * in __alloc_pages_slowpath(). All other functions pass the whole strucure
+ * by a const pointer.
+ */
+struct alloc_context {
+	struct zonelist *zonelist;
+	nodemask_t *nodemask;
+	struct zone *preferred_zone;
+	int classzone_idx;
+	int migratetype;
+	enum zone_type high_zoneidx;
+};
+
 /*
  * Locate the struct page for both the matching buddy in our
  * pair (buddy1) and the combined O(n+1) page they form (page).
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4aead0bd8d4..d664eb922a7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -232,27 +232,6 @@ EXPORT_SYMBOL(nr_node_ids);
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
-/*
- * Structure for holding the mostly immutable allocation parameters passed
- * between alloc_pages* family of functions.
- *
- * nodemask, migratetype and high_zoneidx are initialized only once in
- * __alloc_pages_nodemask() and then never change.
- *
- * zonelist, preferred_zone and classzone_idx are set first in
- * __alloc_pages_nodemask() for the fast path, and might be later changed
- * in __alloc_pages_slowpath(). All other functions pass the whole strucure
- * by a const pointer.
- */
-struct alloc_context {
-	struct zonelist *zonelist;
-	nodemask_t *nodemask;
-	struct zone *preferred_zone;
-	int classzone_idx;
-	int migratetype;
-	enum zone_type high_zoneidx;
-};
-
 int page_group_by_mobility_disabled __read_mostly;
 
 void set_pageblock_migratetype(struct page *page, int migratetype)
@@ -2429,10 +2408,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 	current->flags |= PF_MEMALLOC;
-	compact_result = try_to_compact_pages(ac->zonelist, order, gfp_mask,
-						ac->nodemask, mode,
-						contended_compaction,
-						alloc_flags, ac->classzone_idx);
+	compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
+						mode, contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 
 	switch (compact_result) {
-- 
cgit v1.2.3-70-g09d2


From 05891fb06517d19ae5357c9dc44e96bbe0300a3c Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 11 Feb 2015 15:25:47 -0800
Subject: mm: microoptimize zonelist operations

next_zones_zonelist() returns a zoneref pointer, as well as a zone pointer
via extra parameter.  Since the latter can be trivially obtained by
dereferencing the former, the overhead of the extra parameter is
unjustified.

This patch thus removes the zone parameter from next_zones_zonelist().
Both callers happen to be in the same header file, so it's simple to add
the zoneref dereference inline.  We save some bytes of code size.

add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-105 (-105)
function                                     old     new   delta
nr_free_zone_pages                           129     115     -14
__alloc_pages_nodemask                      2300    2285     -15
get_page_from_freelist                      2652    2576     -76

add/remove: 0/0 grow/shrink: 1/0 up/down: 10/0 (10)
function                                     old     new   delta
try_to_compact_pages                         569     579     +10

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h | 13 +++++++------
 mm/mmzone.c            |  4 +---
 2 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b4182970133..f279d9c158c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -970,7 +970,6 @@ static inline int zonelist_node_idx(struct zoneref *zoneref)
  * @z - The cursor used as a starting point for the search
  * @highest_zoneidx - The zone index of the highest zone to return
  * @nodes - An optional nodemask to filter the zonelist with
- * @zone - The first suitable zone found is returned via this parameter
  *
  * This function returns the next zone at or below a given zone index that is
  * within the allowed nodemask using a cursor as the starting point for the
@@ -980,8 +979,7 @@ static inline int zonelist_node_idx(struct zoneref *zoneref)
  */
 struct zoneref *next_zones_zonelist(struct zoneref *z,
 					enum zone_type highest_zoneidx,
-					nodemask_t *nodes,
-					struct zone **zone);
+					nodemask_t *nodes);
 
 /**
  * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist
@@ -1000,8 +998,10 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 					nodemask_t *nodes,
 					struct zone **zone)
 {
-	return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes,
-								zone);
+	struct zoneref *z = next_zones_zonelist(zonelist->_zonerefs,
+							highest_zoneidx, nodes);
+	*zone = zonelist_zone(z);
+	return z;
 }
 
 /**
@@ -1018,7 +1018,8 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
 	for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone);	\
 		zone;							\
-		z = next_zones_zonelist(++z, highidx, nodemask, &zone))	\
+		z = next_zones_zonelist(++z, highidx, nodemask),	\
+			zone = zonelist_zone(z))			\
 
 /**
  * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index
diff --git a/mm/mmzone.c b/mm/mmzone.c
index bf34fb8556d..7d87ebb0d63 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -54,8 +54,7 @@ static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes)
 /* Returns the next zone at or below highest_zoneidx in a zonelist */
 struct zoneref *next_zones_zonelist(struct zoneref *z,
 					enum zone_type highest_zoneidx,
-					nodemask_t *nodes,
-					struct zone **zone)
+					nodemask_t *nodes)
 {
 	/*
 	 * Find the next suitable zone to use for the allocation.
@@ -69,7 +68,6 @@ struct zoneref *next_zones_zonelist(struct zoneref *z,
 				(z->zone && !zref_in_nodemask(z, nodes)))
 			z++;
 
-	*zone = zonelist_zone(z);
 	return z;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 90cbc2508827e1e15dca23361c33cc26dd2b9e99 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Wed, 11 Feb 2015 15:25:55 -0800
Subject: vmscan: force scan offline memory cgroups

Since commit b2052564e66d ("mm: memcontrol: continue cache reclaim from
offlined groups") pages charged to a memory cgroup are not reparented when
the cgroup is removed.  Instead, they are supposed to be reclaimed in a
regular way, along with pages accounted to online memory cgroups.

However, an lruvec of an offline memory cgroup will sooner or later get so
small that it will be scanned only at low scan priorities (see
get_scan_count()).  Therefore, if there are enough reclaimable pages in
big lruvecs, pages accounted to offline memory cgroups will never be
scanned at all, wasting memory.

Fix this by unconditionally forcing scanning dead lruvecs from kswapd.

[akpm@linux-foundation.org: fix build]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  6 ++++++
 mm/memcontrol.c            | 14 ++++++++++++++
 mm/vmscan.c                |  8 ++++++--
 3 files changed, 26 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 76b4084b8d0..353537a5981 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -102,6 +102,7 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
  * For memory reclaim.
  */
 int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec);
+bool mem_cgroup_lruvec_online(struct lruvec *lruvec);
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
 void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
@@ -266,6 +267,11 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return 1;
 }
 
+static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+{
+	return true;
+}
+
 static inline unsigned long
 mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 028d07c7910..6187ca4d5dc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1367,6 +1367,20 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
+bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+{
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return true;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	memcg = mz->memcg;
+
+	return !!(memcg->css.flags & CSS_ONLINE);
+}
+
 #define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f756a202d5d..b6dfa0081a8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1903,8 +1903,12 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness,
 	 * latencies, so it's better to scan a minimum amount there as
 	 * well.
 	 */
-	if (current_is_kswapd() && !zone_reclaimable(zone))
-		force_scan = true;
+	if (current_is_kswapd()) {
+		if (!zone_reclaimable(zone))
+			force_scan = true;
+		if (!mem_cgroup_lruvec_online(lruvec))
+			force_scan = true;
+	}
 	if (!global_reclaim(sc))
 		force_scan = true;
 
-- 
cgit v1.2.3-70-g09d2


From 650c5e565492f9092552bfe4d65935196c7d9567 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 11 Feb 2015 15:26:03 -0800
Subject: mm: page_counter: pull "-1" handling out of page_counter_memparse()

The unified hierarchy interface for memory cgroups will no longer use "-1"
to mean maximum possible resource value.  In preparation for this, make
the string an argument and let the caller supply it.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_counter.h | 3 ++-
 mm/hugetlb_cgroup.c          | 2 +-
 mm/memcontrol.c              | 4 ++--
 mm/page_counter.c            | 7 ++++---
 net/ipv4/tcp_memcontrol.c    | 2 +-
 5 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 955421575d1..17fa4f8de3a 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -41,7 +41,8 @@ int page_counter_try_charge(struct page_counter *counter,
 			    struct page_counter **fail);
 void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
 int page_counter_limit(struct page_counter *counter, unsigned long limit);
-int page_counter_memparse(const char *buf, unsigned long *nr_pages);
+int page_counter_memparse(const char *buf, const char *max,
+			  unsigned long *nr_pages);
 
 static inline void page_counter_reset_watermark(struct page_counter *counter)
 {
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 037e1c00a5b..6e0057439a4 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -279,7 +279,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 		return -EINVAL;
 
 	buf = strstrip(buf);
-	ret = page_counter_memparse(buf, &nr_pages);
+	ret = page_counter_memparse(buf, "-1", &nr_pages);
 	if (ret)
 		return ret;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dc5c4cd0afd..6453ea5a27a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3414,7 +3414,7 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 	int ret;
 
 	buf = strstrip(buf);
-	ret = page_counter_memparse(buf, &nr_pages);
+	ret = page_counter_memparse(buf, "-1", &nr_pages);
 	if (ret)
 		return ret;
 
@@ -3786,7 +3786,7 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 	unsigned long usage;
 	int i, size, ret;
 
-	ret = page_counter_memparse(args, &threshold);
+	ret = page_counter_memparse(args, "-1", &threshold);
 	if (ret)
 		return ret;
 
diff --git a/mm/page_counter.c b/mm/page_counter.c
index a009574fbba..11b4beda14b 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -166,18 +166,19 @@ int page_counter_limit(struct page_counter *counter, unsigned long limit)
 /**
  * page_counter_memparse - memparse() for page counter limits
  * @buf: string to parse
+ * @max: string meaning maximum possible value
  * @nr_pages: returns the result in number of pages
  *
  * Returns -EINVAL, or 0 and @nr_pages on success.  @nr_pages will be
  * limited to %PAGE_COUNTER_MAX.
  */
-int page_counter_memparse(const char *buf, unsigned long *nr_pages)
+int page_counter_memparse(const char *buf, const char *max,
+			  unsigned long *nr_pages)
 {
-	char unlimited[] = "-1";
 	char *end;
 	u64 bytes;
 
-	if (!strncmp(buf, unlimited, sizeof(unlimited))) {
+	if (!strcmp(buf, max)) {
 		*nr_pages = PAGE_COUNTER_MAX;
 		return 0;
 	}
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 272327134a1..c2a75c6957a 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -120,7 +120,7 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = page_counter_memparse(buf, &nr_pages);
+		ret = page_counter_memparse(buf, "-1", &nr_pages);
 		if (ret)
 			break;
 		mutex_lock(&tcp_limit_mutex);
-- 
cgit v1.2.3-70-g09d2


From 241994ed8649f7300667be8b13a9e04ae04e05a1 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Wed, 11 Feb 2015 15:26:06 -0800
Subject: mm: memcontrol: default hierarchy interface for memory

Introduce the basic control files to account, partition, and limit
memory using cgroups in default hierarchy mode.

This interface versioning allows us to address fundamental design
issues in the existing memory cgroup interface, further explained
below.  The old interface will be maintained indefinitely, but a
clearer model and improved workload performance should encourage
existing users to switch over to the new one eventually.

The control files are thus:

  - memory.current shows the current consumption of the cgroup and its
    descendants, in bytes.

  - memory.low configures the lower end of the cgroup's expected
    memory consumption range.  The kernel considers memory below that
    boundary to be a reserve - the minimum that the workload needs in
    order to make forward progress - and generally avoids reclaiming
    it, unless there is an imminent risk of entering an OOM situation.

  - memory.high configures the upper end of the cgroup's expected
    memory consumption range.  A cgroup whose consumption grows beyond
    this threshold is forced into direct reclaim, to work off the
    excess and to throttle new allocations heavily, but is generally
    allowed to continue and the OOM killer is not invoked.

  - memory.max configures the hard maximum amount of memory that the
    cgroup is allowed to consume before the OOM killer is invoked.

  - memory.events shows event counters that indicate how often the
    cgroup was reclaimed while below memory.low, how often it was
    forced to reclaim excess beyond memory.high, how often it hit
    memory.max, and how often it entered OOM due to memory.max.  This
    allows users to identify configuration problems when observing a
    degradation in workload performance.  An overcommitted system will
    have an increased rate of low boundary breaches, whereas increased
    rates of high limit breaches, maximum hits, or even OOM situations
    will indicate internally overcommitted cgroups.

For existing users of memory cgroups, the following deviations from
the current interface are worth pointing out and explaining:

  - The original lower boundary, the soft limit, is defined as a limit
    that is per default unset.  As a result, the set of cgroups that
    global reclaim prefers is opt-in, rather than opt-out.  The costs
    for optimizing these mostly negative lookups are so high that the
    implementation, despite its enormous size, does not even provide
    the basic desirable behavior.  First off, the soft limit has no
    hierarchical meaning.  All configured groups are organized in a
    global rbtree and treated like equal peers, regardless where they
    are located in the hierarchy.  This makes subtree delegation
    impossible.  Second, the soft limit reclaim pass is so aggressive
    that it not just introduces high allocation latencies into the
    system, but also impacts system performance due to overreclaim, to
    the point where the feature becomes self-defeating.

    The memory.low boundary on the other hand is a top-down allocated
    reserve.  A cgroup enjoys reclaim protection when it and all its
    ancestors are below their low boundaries, which makes delegation
    of subtrees possible.  Secondly, new cgroups have no reserve per
    default and in the common case most cgroups are eligible for the
    preferred reclaim pass.  This allows the new low boundary to be
    efficiently implemented with just a minor addition to the generic
    reclaim code, without the need for out-of-band data structures and
    reclaim passes.  Because the generic reclaim code considers all
    cgroups except for the ones running low in the preferred first
    reclaim pass, overreclaim of individual groups is eliminated as
    well, resulting in much better overall workload performance.

  - The original high boundary, the hard limit, is defined as a strict
    limit that can not budge, even if the OOM killer has to be called.
    But this generally goes against the goal of making the most out of
    the available memory.  The memory consumption of workloads varies
    during runtime, and that requires users to overcommit.  But doing
    that with a strict upper limit requires either a fairly accurate
    prediction of the working set size or adding slack to the limit.
    Since working set size estimation is hard and error prone, and
    getting it wrong results in OOM kills, most users tend to err on
    the side of a looser limit and end up wasting precious resources.

    The memory.high boundary on the other hand can be set much more
    conservatively.  When hit, it throttles allocations by forcing
    them into direct reclaim to work off the excess, but it never
    invokes the OOM killer.  As a result, a high boundary that is
    chosen too aggressively will not terminate the processes, but
    instead it will lead to gradual performance degradation.  The user
    can monitor this and make corrections until the minimal memory
    footprint that still gives acceptable performance is found.

    In extreme cases, with many concurrent allocations and a complete
    breakdown of reclaim progress within the group, the high boundary
    can be exceeded.  But even then it's mostly better to satisfy the
    allocation from the slack available in other groups or the rest of
    the system than killing the group.  Otherwise, memory.max is there
    to limit this type of spillover and ultimately contain buggy or
    even malicious applications.

  - The original control file names are unwieldy and inconsistent in
    many different ways.  For example, the upper boundary hit count is
    exported in the memory.failcnt file, but an OOM event count has to
    be manually counted by listening to memory.oom_control events, and
    lower boundary / soft limit events have to be counted by first
    setting a threshold for that value and then counting those events.
    Also, usage and limit files encode their units in the filename.
    That makes the filenames very long, even though this is not
    information that a user needs to be reminded of every time they
    type out those names.

    To address these naming issues, as well as to signal clearly that
    the new interface carries a new configuration model, the naming
    conventions in it necessarily differ from the old interface.

  - The original limit files indicate the state of an unset limit with
    a very high number, and a configured limit can be unset by echoing
    -1 into those files.  But that very high number is implementation
    and architecture dependent and not very descriptive.  And while -1
    can be understood as an underflow into the highest possible value,
    -2 or -10M etc. do not work, so it's not inconsistent.

    memory.low, memory.high, and memory.max will use the string
    "infinity" to indicate and set the highest possible value.

[akpm@linux-foundation.org: use seq_puts() for basic strings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/unified-hierarchy.txt |  79 ++++++++++
 include/linux/memcontrol.h                  |  32 ++++
 mm/memcontrol.c                             | 229 ++++++++++++++++++++++++++--
 mm/vmscan.c                                 |  22 ++-
 4 files changed, 348 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt
index 4f456327786..71daa35ec2d 100644
--- a/Documentation/cgroups/unified-hierarchy.txt
+++ b/Documentation/cgroups/unified-hierarchy.txt
@@ -327,6 +327,85 @@ supported and the interface files "release_agent" and
 - use_hierarchy is on by default and the cgroup file for the flag is
   not created.
 
+- The original lower boundary, the soft limit, is defined as a limit
+  that is per default unset.  As a result, the set of cgroups that
+  global reclaim prefers is opt-in, rather than opt-out.  The costs
+  for optimizing these mostly negative lookups are so high that the
+  implementation, despite its enormous size, does not even provide the
+  basic desirable behavior.  First off, the soft limit has no
+  hierarchical meaning.  All configured groups are organized in a
+  global rbtree and treated like equal peers, regardless where they
+  are located in the hierarchy.  This makes subtree delegation
+  impossible.  Second, the soft limit reclaim pass is so aggressive
+  that it not just introduces high allocation latencies into the
+  system, but also impacts system performance due to overreclaim, to
+  the point where the feature becomes self-defeating.
+
+  The memory.low boundary on the other hand is a top-down allocated
+  reserve.  A cgroup enjoys reclaim protection when it and all its
+  ancestors are below their low boundaries, which makes delegation of
+  subtrees possible.  Secondly, new cgroups have no reserve per
+  default and in the common case most cgroups are eligible for the
+  preferred reclaim pass.  This allows the new low boundary to be
+  efficiently implemented with just a minor addition to the generic
+  reclaim code, without the need for out-of-band data structures and
+  reclaim passes.  Because the generic reclaim code considers all
+  cgroups except for the ones running low in the preferred first
+  reclaim pass, overreclaim of individual groups is eliminated as
+  well, resulting in much better overall workload performance.
+
+- The original high boundary, the hard limit, is defined as a strict
+  limit that can not budge, even if the OOM killer has to be called.
+  But this generally goes against the goal of making the most out of
+  the available memory.  The memory consumption of workloads varies
+  during runtime, and that requires users to overcommit.  But doing
+  that with a strict upper limit requires either a fairly accurate
+  prediction of the working set size or adding slack to the limit.
+  Since working set size estimation is hard and error prone, and
+  getting it wrong results in OOM kills, most users tend to err on the
+  side of a looser limit and end up wasting precious resources.
+
+  The memory.high boundary on the other hand can be set much more
+  conservatively.  When hit, it throttles allocations by forcing them
+  into direct reclaim to work off the excess, but it never invokes the
+  OOM killer.  As a result, a high boundary that is chosen too
+  aggressively will not terminate the processes, but instead it will
+  lead to gradual performance degradation.  The user can monitor this
+  and make corrections until the minimal memory footprint that still
+  gives acceptable performance is found.
+
+  In extreme cases, with many concurrent allocations and a complete
+  breakdown of reclaim progress within the group, the high boundary
+  can be exceeded.  But even then it's mostly better to satisfy the
+  allocation from the slack available in other groups or the rest of
+  the system than killing the group.  Otherwise, memory.max is there
+  to limit this type of spillover and ultimately contain buggy or even
+  malicious applications.
+
+- The original control file names are unwieldy and inconsistent in
+  many different ways.  For example, the upper boundary hit count is
+  exported in the memory.failcnt file, but an OOM event count has to
+  be manually counted by listening to memory.oom_control events, and
+  lower boundary / soft limit events have to be counted by first
+  setting a threshold for that value and then counting those events.
+  Also, usage and limit files encode their units in the filename.
+  That makes the filenames very long, even though this is not
+  information that a user needs to be reminded of every time they type
+  out those names.
+
+  To address these naming issues, as well as to signal clearly that
+  the new interface carries a new configuration model, the naming
+  conventions in it necessarily differ from the old interface.
+
+- The original limit files indicate the state of an unset limit with a
+  Very High Number, and a configured limit can be unset by echoing -1
+  into those files.  But that very high number is implementation and
+  architecture dependent and not very descriptive.  And while -1 can
+  be understood as an underflow into the highest possible value, -2 or
+  -10M etc. do not work, so it's not consistent.
+
+  memory.low, memory.high, and memory.max will use the string
+  "infinity" to indicate and set the highest possible value.
 
 5. Planned Changes
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 353537a5981..6cfd934c7c9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -52,7 +52,27 @@ struct mem_cgroup_reclaim_cookie {
 	unsigned int generation;
 };
 
+enum mem_cgroup_events_index {
+	MEM_CGROUP_EVENTS_PGPGIN,	/* # of pages paged in */
+	MEM_CGROUP_EVENTS_PGPGOUT,	/* # of pages paged out */
+	MEM_CGROUP_EVENTS_PGFAULT,	/* # of page-faults */
+	MEM_CGROUP_EVENTS_PGMAJFAULT,	/* # of major page-faults */
+	MEM_CGROUP_EVENTS_NSTATS,
+	/* default hierarchy events */
+	MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS,
+	MEMCG_HIGH,
+	MEMCG_MAX,
+	MEMCG_OOM,
+	MEMCG_NR_EVENTS,
+};
+
 #ifdef CONFIG_MEMCG
+void mem_cgroup_events(struct mem_cgroup *memcg,
+		       enum mem_cgroup_events_index idx,
+		       unsigned int nr);
+
+bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
+
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 			  gfp_t gfp_mask, struct mem_cgroup **memcgp);
 void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -175,6 +195,18 @@ void mem_cgroup_split_huge_fixup(struct page *head);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
+static inline void mem_cgroup_events(struct mem_cgroup *memcg,
+				     enum mem_cgroup_events_index idx,
+				     unsigned int nr)
+{
+}
+
+static inline bool mem_cgroup_low(struct mem_cgroup *root,
+				  struct mem_cgroup *memcg)
+{
+	return false;
+}
+
 static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask,
 					struct mem_cgroup **memcgp)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6453ea5a27a..ee97c9ac62c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -97,14 +97,6 @@ static const char * const mem_cgroup_stat_names[] = {
 	"swap",
 };
 
-enum mem_cgroup_events_index {
-	MEM_CGROUP_EVENTS_PGPGIN,	/* # of pages paged in */
-	MEM_CGROUP_EVENTS_PGPGOUT,	/* # of pages paged out */
-	MEM_CGROUP_EVENTS_PGFAULT,	/* # of page-faults */
-	MEM_CGROUP_EVENTS_PGMAJFAULT,	/* # of major page-faults */
-	MEM_CGROUP_EVENTS_NSTATS,
-};
-
 static const char * const mem_cgroup_events_names[] = {
 	"pgpgin",
 	"pgpgout",
@@ -138,7 +130,7 @@ enum mem_cgroup_events_target {
 
 struct mem_cgroup_stat_cpu {
 	long count[MEM_CGROUP_STAT_NSTATS];
-	unsigned long events[MEM_CGROUP_EVENTS_NSTATS];
+	unsigned long events[MEMCG_NR_EVENTS];
 	unsigned long nr_page_events;
 	unsigned long targets[MEM_CGROUP_NTARGETS];
 };
@@ -284,6 +276,10 @@ struct mem_cgroup {
 	struct page_counter memsw;
 	struct page_counter kmem;
 
+	/* Normal memory consumption range */
+	unsigned long low;
+	unsigned long high;
+
 	unsigned long soft_limit;
 
 	/* vmpressure notifications */
@@ -2315,6 +2311,8 @@ retry:
 	if (!(gfp_mask & __GFP_WAIT))
 		goto nomem;
 
+	mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1);
+
 	nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
 						    gfp_mask, may_swap);
 
@@ -2356,6 +2354,8 @@ retry:
 	if (fatal_signal_pending(current))
 		goto bypass;
 
+	mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1);
+
 	mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages));
 nomem:
 	if (!(gfp_mask & __GFP_NOFAIL))
@@ -2367,6 +2367,16 @@ done_restock:
 	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
+	/*
+	 * If the hierarchy is above the normal consumption range,
+	 * make the charging task trim their excess contribution.
+	 */
+	do {
+		if (page_counter_read(&memcg->memory) <= memcg->high)
+			continue;
+		mem_cgroup_events(memcg, MEMCG_HIGH, 1);
+		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
+	} while ((memcg = parent_mem_cgroup(memcg)));
 done:
 	return ret;
 }
@@ -4276,7 +4286,7 @@ out_kfree:
 	return ret;
 }
 
-static struct cftype mem_cgroup_files[] = {
+static struct cftype mem_cgroup_legacy_files[] = {
 	{
 		.name = "usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
@@ -4552,6 +4562,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (parent_css == NULL) {
 		root_mem_cgroup = memcg;
 		page_counter_init(&memcg->memory, NULL);
+		memcg->high = PAGE_COUNTER_MAX;
 		memcg->soft_limit = PAGE_COUNTER_MAX;
 		page_counter_init(&memcg->memsw, NULL);
 		page_counter_init(&memcg->kmem, NULL);
@@ -4597,6 +4608,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 
 	if (parent->use_hierarchy) {
 		page_counter_init(&memcg->memory, &parent->memory);
+		memcg->high = PAGE_COUNTER_MAX;
 		memcg->soft_limit = PAGE_COUNTER_MAX;
 		page_counter_init(&memcg->memsw, &parent->memsw);
 		page_counter_init(&memcg->kmem, &parent->kmem);
@@ -4607,6 +4619,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		 */
 	} else {
 		page_counter_init(&memcg->memory, NULL);
+		memcg->high = PAGE_COUNTER_MAX;
 		memcg->soft_limit = PAGE_COUNTER_MAX;
 		page_counter_init(&memcg->memsw, NULL);
 		page_counter_init(&memcg->kmem, NULL);
@@ -4682,6 +4695,8 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 	mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX);
 	mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX);
 	memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX);
+	memcg->low = 0;
+	memcg->high = PAGE_COUNTER_MAX;
 	memcg->soft_limit = PAGE_COUNTER_MAX;
 }
 
@@ -5267,6 +5282,147 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 		mem_cgroup_from_css(root_css)->use_hierarchy = true;
 }
 
+static u64 memory_current_read(struct cgroup_subsys_state *css,
+			       struct cftype *cft)
+{
+	return mem_cgroup_usage(mem_cgroup_from_css(css), false);
+}
+
+static int memory_low_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	unsigned long low = ACCESS_ONCE(memcg->low);
+
+	if (low == PAGE_COUNTER_MAX)
+		seq_puts(m, "infinity\n");
+	else
+		seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE);
+
+	return 0;
+}
+
+static ssize_t memory_low_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned long low;
+	int err;
+
+	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "infinity", &low);
+	if (err)
+		return err;
+
+	memcg->low = low;
+
+	return nbytes;
+}
+
+static int memory_high_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	unsigned long high = ACCESS_ONCE(memcg->high);
+
+	if (high == PAGE_COUNTER_MAX)
+		seq_puts(m, "infinity\n");
+	else
+		seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE);
+
+	return 0;
+}
+
+static ssize_t memory_high_write(struct kernfs_open_file *of,
+				 char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned long high;
+	int err;
+
+	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "infinity", &high);
+	if (err)
+		return err;
+
+	memcg->high = high;
+
+	return nbytes;
+}
+
+static int memory_max_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	unsigned long max = ACCESS_ONCE(memcg->memory.limit);
+
+	if (max == PAGE_COUNTER_MAX)
+		seq_puts(m, "infinity\n");
+	else
+		seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
+
+	return 0;
+}
+
+static ssize_t memory_max_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned long max;
+	int err;
+
+	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "infinity", &max);
+	if (err)
+		return err;
+
+	err = mem_cgroup_resize_limit(memcg, max);
+	if (err)
+		return err;
+
+	return nbytes;
+}
+
+static int memory_events_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	seq_printf(m, "low %lu\n", mem_cgroup_read_events(memcg, MEMCG_LOW));
+	seq_printf(m, "high %lu\n", mem_cgroup_read_events(memcg, MEMCG_HIGH));
+	seq_printf(m, "max %lu\n", mem_cgroup_read_events(memcg, MEMCG_MAX));
+	seq_printf(m, "oom %lu\n", mem_cgroup_read_events(memcg, MEMCG_OOM));
+
+	return 0;
+}
+
+static struct cftype memory_files[] = {
+	{
+		.name = "current",
+		.read_u64 = memory_current_read,
+	},
+	{
+		.name = "low",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = memory_low_show,
+		.write = memory_low_write,
+	},
+	{
+		.name = "high",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = memory_high_show,
+		.write = memory_high_write,
+	},
+	{
+		.name = "max",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = memory_max_show,
+		.write = memory_max_write,
+	},
+	{
+		.name = "events",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = memory_events_show,
+	},
+	{ }	/* terminate */
+};
+
 struct cgroup_subsys memory_cgrp_subsys = {
 	.css_alloc = mem_cgroup_css_alloc,
 	.css_online = mem_cgroup_css_online,
@@ -5277,7 +5433,8 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
 	.bind = mem_cgroup_bind,
-	.legacy_cftypes = mem_cgroup_files,
+	.dfl_cftypes = memory_files,
+	.legacy_cftypes = mem_cgroup_legacy_files,
 	.early_init = 0,
 };
 
@@ -5312,6 +5469,56 @@ static void __init enable_swap_cgroup(void)
 }
 #endif
 
+/**
+ * mem_cgroup_events - count memory events against a cgroup
+ * @memcg: the memory cgroup
+ * @idx: the event index
+ * @nr: the number of events to account for
+ */
+void mem_cgroup_events(struct mem_cgroup *memcg,
+		       enum mem_cgroup_events_index idx,
+		       unsigned int nr)
+{
+	this_cpu_add(memcg->stat->events[idx], nr);
+}
+
+/**
+ * mem_cgroup_low - check if memory consumption is below the normal range
+ * @root: the highest ancestor to consider
+ * @memcg: the memory cgroup to check
+ *
+ * Returns %true if memory consumption of @memcg, and that of all
+ * configurable ancestors up to @root, is below the normal range.
+ */
+bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return false;
+
+	/*
+	 * The toplevel group doesn't have a configurable range, so
+	 * it's never low when looked at directly, and it is not
+	 * considered an ancestor when assessing the hierarchy.
+	 */
+
+	if (memcg == root_mem_cgroup)
+		return false;
+
+	if (page_counter_read(&memcg->memory) > memcg->low)
+		return false;
+
+	while (memcg != root) {
+		memcg = parent_mem_cgroup(memcg);
+
+		if (memcg == root_mem_cgroup)
+			break;
+
+		if (page_counter_read(&memcg->memory) > memcg->low)
+			return false;
+	}
+	return true;
+}
+
 #ifdef CONFIG_MEMCG_SWAP
 /**
  * mem_cgroup_swapout - transfer a memsw charge to swap
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b6dfa0081a8..8e645ee5204 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -91,6 +91,9 @@ struct scan_control {
 	/* Can pages be swapped as part of reclaim? */
 	unsigned int may_swap:1;
 
+	/* Can cgroups be reclaimed below their normal consumption range? */
+	unsigned int may_thrash:1;
+
 	unsigned int hibernation_mode:1;
 
 	/* One of the zones is ready for compaction */
@@ -2294,6 +2297,12 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 			struct lruvec *lruvec;
 			int swappiness;
 
+			if (mem_cgroup_low(root, memcg)) {
+				if (!sc->may_thrash)
+					continue;
+				mem_cgroup_events(memcg, MEMCG_LOW, 1);
+			}
+
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 			swappiness = mem_cgroup_swappiness(memcg);
 
@@ -2315,8 +2324,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 				mem_cgroup_iter_break(root, memcg);
 				break;
 			}
-			memcg = mem_cgroup_iter(root, memcg, &reclaim);
-		} while (memcg);
+		} while ((memcg = mem_cgroup_iter(root, memcg, &reclaim)));
 
 		/*
 		 * Shrink the slab caches in the same proportion that
@@ -2519,10 +2527,11 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 					  struct scan_control *sc)
 {
+	int initial_priority = sc->priority;
 	unsigned long total_scanned = 0;
 	unsigned long writeback_threshold;
 	bool zones_reclaimable;
-
+retry:
 	delayacct_freepages_start();
 
 	if (global_reclaim(sc))
@@ -2572,6 +2581,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	if (sc->compaction_ready)
 		return 1;
 
+	/* Untapped cgroup reserves?  Don't OOM, retry. */
+	if (!sc->may_thrash) {
+		sc->priority = initial_priority;
+		sc->may_thrash = 1;
+		goto retry;
+	}
+
 	/* Any of the zones still reclaimable?  Don't OOM. */
 	if (zones_reclaimable)
 		return 1;
-- 
cgit v1.2.3-70-g09d2


From 49550b605587924b3336386caae53200c68969d3 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.cz>
Date: Wed, 11 Feb 2015 15:26:12 -0800
Subject: oom: add helpers for setting and clearing TIF_MEMDIE

This patchset addresses a race which was described in the changelog for
5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM suspend"):

: PM freezer relies on having all tasks frozen by the time devices are
: getting frozen so that no task will touch them while they are getting
: frozen.  But OOM killer is allowed to kill an already frozen task in order
: to handle OOM situtation.  In order to protect from late wake ups OOM
: killer is disabled after all tasks are frozen.  This, however, still keeps
: a window open when a killed task didn't manage to die by the time
: freeze_processes finishes.

The original patch hasn't closed the race window completely because that
would require a more complex solution as it can be seen by this patchset.

The primary motivation was to close the race condition between OOM killer
and PM freezer _completely_.  As Tejun pointed out, even though the race
condition is unlikely the harder it would be to debug weird bugs deep in
the PM freezer when the debugging options are reduced considerably.  I can
only speculate what might happen when a task is still runnable
unexpectedly.

On a plus side and as a side effect the oom enable/disable has a better
(full barrier) semantic without polluting hot paths.

I have tested the series in KVM with 100M RAM:
- many small tasks (20M anon mmap) which are triggering OOM continually
- s2ram which resumes automatically is triggered in a loop
	echo processors > /sys/power/pm_test
	while true
	do
		echo mem > /sys/power/state
		sleep 1s
	done
- simple module which allocates and frees 20M in 8K chunks. If it sees
  freezing(current) then it tries another round of allocation before calling
  try_to_freeze
- debugging messages of PM stages and OOM killer enable/disable/fail added
  and unmark_oom_victim is delayed by 1s after it clears TIF_MEMDIE and before
  it wakes up waiters.
- rebased on top of the current mmotm which means some necessary updates
  in mm/oom_kill.c. mark_tsk_oom_victim is now called under task_lock but
  I think this should be OK because __thaw_task shouldn't interfere with any
  locking down wake_up_process. Oleg?

As expected there are no OOM killed tasks after oom is disabled and
allocations requested by the kernel thread are failing after all the tasks
are frozen and OOM disabled.  I wasn't able to catch a race where
oom_killer_disable would really have to wait but I kinda expected the race
is really unlikely.

[  242.609330] Killed process 2992 (mem_eater) total-vm:24412kB, anon-rss:2164kB, file-rss:4kB
[  243.628071] Unmarking 2992 OOM victim. oom_victims: 1
[  243.636072] (elapsed 2.837 seconds) done.
[  243.641985] Trying to disable OOM killer
[  243.643032] Waiting for concurent OOM victims
[  243.644342] OOM killer disabled
[  243.645447] Freezing remaining freezable tasks ... (elapsed 0.005 seconds) done.
[  243.652983] Suspending console(s) (use no_console_suspend to debug)
[  243.903299] kmem_eater: page allocation failure: order:1, mode:0x204010
[...]
[  243.992600] PM: suspend of devices complete after 336.667 msecs
[  243.993264] PM: late suspend of devices complete after 0.660 msecs
[  243.994713] PM: noirq suspend of devices complete after 1.446 msecs
[  243.994717] ACPI: Preparing to enter system sleep state S3
[  243.994795] PM: Saving platform NVS memory
[  243.994796] Disabling non-boot CPUs ...

The first 2 patches are simple cleanups for OOM.  They should go in
regardless the rest IMO.

Patches 3 and 4 are trivial printk -> pr_info conversion and they should
go in ditto.

The main patch is the last one and I would appreciate acks from Tejun and
Rafael.  I think the OOM part should be OK (except for __thaw_task vs.
task_lock where a look from Oleg would appreciated) but I am not so sure I
haven't screwed anything in the freezer code.  I have found several
surprises there.

This patch (of 5):

This patch is just a preparatory and it doesn't introduce any functional
change.

Note:
I am utterly unhappy about lowmemory killer abusing TIF_MEMDIE just to
wait for the oom victim and to prevent from new killing. This is
just a side effect of the flag. The primary meaning is to give the oom
victim access to the memory reserves and that shouldn't be necessary
here.

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/staging/android/lowmemorykiller.c |  7 ++++++-
 include/linux/oom.h                       |  4 ++++
 kernel/exit.c                             |  2 +-
 mm/memcontrol.c                           |  2 +-
 mm/oom_kill.c                             | 23 ++++++++++++++++++++---
 5 files changed, 32 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index b545d3d1da3..feafa172b15 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -160,7 +160,12 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc)
 			     selected->pid, selected->comm,
 			     selected_oom_score_adj, selected_tasksize);
 		lowmem_deathpending_timeout = jiffies + HZ;
-		set_tsk_thread_flag(selected, TIF_MEMDIE);
+		/*
+		 * FIXME: lowmemorykiller shouldn't abuse global OOM killer
+		 * infrastructure. There is no real reason why the selected
+		 * task should have access to the memory reserves.
+		 */
+		mark_tsk_oom_victim(selected);
 		send_sig(SIGKILL, selected, 0);
 		rem += selected_tasksize;
 	}
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 76200984d1e..b42b80f88c3 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -47,6 +47,10 @@ static inline bool oom_task_origin(const struct task_struct *p)
 	return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN);
 }
 
+extern void mark_tsk_oom_victim(struct task_struct *tsk);
+
+extern void unmark_oom_victim(void);
+
 extern unsigned long oom_badness(struct task_struct *p,
 		struct mem_cgroup *memcg, const nodemask_t *nodemask,
 		unsigned long totalpages);
diff --git a/kernel/exit.c b/kernel/exit.c
index 6806c55475e..02b3d1ab2ec 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -435,7 +435,7 @@ static void exit_mm(struct task_struct *tsk)
 	task_unlock(tsk);
 	mm_update_next_owner(mm);
 	mmput(mm);
-	clear_thread_flag(TIF_MEMDIE);
+	unmark_oom_victim();
 }
 
 static struct task_struct *find_alive_thread(struct task_struct *p)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 11c9e6a1dad..fe4d258ef32 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1556,7 +1556,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * quickly exit and free its memory.
 	 */
 	if (fatal_signal_pending(current) || task_will_free_mem(current)) {
-		set_thread_flag(TIF_MEMDIE);
+		mark_tsk_oom_victim(current);
 		return;
 	}
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 294493a7ae4..80b34e285f9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -416,6 +416,23 @@ void note_oom_kill(void)
 	atomic_inc(&oom_kills);
 }
 
+/**
+ * mark_tsk_oom_victim - marks the given taks as OOM victim.
+ * @tsk: task to mark
+ */
+void mark_tsk_oom_victim(struct task_struct *tsk)
+{
+	set_tsk_thread_flag(tsk, TIF_MEMDIE);
+}
+
+/**
+ * unmark_oom_victim - unmarks the current task as OOM victim.
+ */
+void unmark_oom_victim(void)
+{
+	clear_thread_flag(TIF_MEMDIE);
+}
+
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /*
  * Must be called while holding a reference to p, which will be released upon
@@ -440,7 +457,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	 */
 	task_lock(p);
 	if (p->mm && task_will_free_mem(p)) {
-		set_tsk_thread_flag(p, TIF_MEMDIE);
+		mark_tsk_oom_victim(p);
 		task_unlock(p);
 		put_task_struct(p);
 		return;
@@ -495,7 +512,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 
 	/* mm cannot safely be dereferenced after task_unlock(victim) */
 	mm = victim->mm;
-	set_tsk_thread_flag(victim, TIF_MEMDIE);
+	mark_tsk_oom_victim(victim);
 	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
 		task_pid_nr(victim), victim->comm, K(victim->mm->total_vm),
 		K(get_mm_counter(victim->mm, MM_ANONPAGES)),
@@ -652,7 +669,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	 */
 	if (current->mm &&
 	    (fatal_signal_pending(current) || task_will_free_mem(current))) {
-		set_thread_flag(TIF_MEMDIE);
+		mark_tsk_oom_victim(current);
 		return;
 	}
 
-- 
cgit v1.2.3-70-g09d2


From c32b3cbe0d067a9cfae85aa70ba1e97ceba0ced7 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.cz>
Date: Wed, 11 Feb 2015 15:26:24 -0800
Subject: oom, PM: make OOM detection in the freezer path raceless

Commit 5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM
suspend") has left a race window when OOM killer manages to
note_oom_kill after freeze_processes checks the counter.  The race
window is quite small and really unlikely and partial solution deemed
sufficient at the time of submission.

Tejun wasn't happy about this partial solution though and insisted on a
full solution.  That requires the full OOM and freezer's task freezing
exclusion, though.  This is done by this patch which introduces oom_sem
RW lock and turns oom_killer_disable() into a full OOM barrier.

oom_killer_disabled check is moved from the allocation path to the OOM
level and we take oom_sem for reading for both the check and the whole
OOM invocation.

oom_killer_disable() takes oom_sem for writing so it waits for all
currently running OOM killer invocations.  Then it disable all the further
OOMs by setting oom_killer_disabled and checks for any oom victims.
Victims are counted via mark_tsk_oom_victim resp.  unmark_oom_victim.  The
last victim wakes up all waiters enqueued by oom_killer_disable().
Therefore this function acts as the full OOM barrier.

The page fault path is covered now as well although it was assumed to be
safe before.  As per Tejun, "We used to have freezing points deep in file
system code which may be reacheable from page fault." so it would be
better and more robust to not rely on freezing points here.  Same applies
to the memcg OOM killer.

out_of_memory tells the caller whether the OOM was allowed to trigger and
the callers are supposed to handle the situation.  The page allocation
path simply fails the allocation same as before.  The page fault path will
retry the fault (more on that later) and Sysrq OOM trigger will simply
complain to the log.

Normally there wouldn't be any unfrozen user tasks after
try_to_freeze_tasks so the function will not block. But if there was an
OOM killer racing with try_to_freeze_tasks and the OOM victim didn't
finish yet then we have to wait for it. This should complete in a finite
time, though, because

	- the victim cannot loop in the page fault handler (it would die
	  on the way out from the exception)
	- it cannot loop in the page allocator because all the further
	  allocation would fail and __GFP_NOFAIL allocations are not
	  acceptable at this stage
	- it shouldn't be blocked on any locks held by frozen tasks
	  (try_to_freeze expects lockless context) and kernel threads and
	  work queues are not frozen yet

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Suggested-by: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/tty/sysrq.c    |   5 +-
 include/linux/oom.h    |  14 ++----
 kernel/exit.c          |   3 +-
 kernel/power/process.c |  50 ++++---------------
 mm/memcontrol.c        |   2 +-
 mm/oom_kill.c          | 132 +++++++++++++++++++++++++++++++++++++++++--------
 mm/page_alloc.c        |  17 +------
 7 files changed, 132 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 0071469ecbf..259a4d5a4e8 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -355,8 +355,9 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
-	out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), GFP_KERNEL,
-		      0, NULL, true);
+	if (!out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL),
+			   GFP_KERNEL, 0, NULL, true))
+		pr_info("OOM request ignored because killer is disabled\n");
 }
 
 static DECLARE_WORK(moom_work, moom_callback);
diff --git a/include/linux/oom.h b/include/linux/oom.h
index b42b80f88c3..d5771bed59c 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -72,22 +72,14 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 		unsigned long totalpages, const nodemask_t *nodemask,
 		bool force_kill);
 
-extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *mask, bool force_kill);
 extern int register_oom_notifier(struct notifier_block *nb);
 extern int unregister_oom_notifier(struct notifier_block *nb);
 
 extern bool oom_killer_disabled;
-
-static inline void oom_killer_disable(void)
-{
-	oom_killer_disabled = true;
-}
-
-static inline void oom_killer_enable(void)
-{
-	oom_killer_disabled = false;
-}
+extern bool oom_killer_disable(void);
+extern void oom_killer_enable(void);
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 02b3d1ab2ec..feff10bbb30 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -435,7 +435,8 @@ static void exit_mm(struct task_struct *tsk)
 	task_unlock(tsk);
 	mm_update_next_owner(mm);
 	mmput(mm);
-	unmark_oom_victim();
+	if (test_thread_flag(TIF_MEMDIE))
+		unmark_oom_victim();
 }
 
 static struct task_struct *find_alive_thread(struct task_struct *p)
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 3ac45f192e9..564f786df47 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -108,30 +108,6 @@ static int try_to_freeze_tasks(bool user_only)
 	return todo ? -EBUSY : 0;
 }
 
-static bool __check_frozen_processes(void)
-{
-	struct task_struct *g, *p;
-
-	for_each_process_thread(g, p)
-		if (p != current && !freezer_should_skip(p) && !frozen(p))
-			return false;
-
-	return true;
-}
-
-/*
- * Returns true if all freezable tasks (except for current) are frozen already
- */
-static bool check_frozen_processes(void)
-{
-	bool ret;
-
-	read_lock(&tasklist_lock);
-	ret = __check_frozen_processes();
-	read_unlock(&tasklist_lock);
-	return ret;
-}
-
 /**
  * freeze_processes - Signal user space processes to enter the refrigerator.
  * The current thread will not be frozen.  The same process that calls
@@ -142,7 +118,6 @@ static bool check_frozen_processes(void)
 int freeze_processes(void)
 {
 	int error;
-	int oom_kills_saved;
 
 	error = __usermodehelper_disable(UMH_FREEZING);
 	if (error)
@@ -157,29 +132,22 @@ int freeze_processes(void)
 	pm_wakeup_clear();
 	pr_info("Freezing user space processes ... ");
 	pm_freezing = true;
-	oom_kills_saved = oom_kills_count();
 	error = try_to_freeze_tasks(true);
 	if (!error) {
 		__usermodehelper_set_disable_depth(UMH_DISABLED);
-		oom_killer_disable();
-
-		/*
-		 * There might have been an OOM kill while we were
-		 * freezing tasks and the killed task might be still
-		 * on the way out so we have to double check for race.
-		 */
-		if (oom_kills_count() != oom_kills_saved &&
-		    !check_frozen_processes()) {
-			__usermodehelper_set_disable_depth(UMH_ENABLED);
-			pr_cont("OOM in progress.");
-			error = -EBUSY;
-		} else {
-			pr_cont("done.");
-		}
+		pr_cont("done.");
 	}
 	pr_cont("\n");
 	BUG_ON(in_atomic());
 
+	/*
+	 * Now that the whole userspace is frozen we need to disbale
+	 * the OOM killer to disallow any further interference with
+	 * killable tasks.
+	 */
+	if (!error && !oom_killer_disable())
+		error = -EBUSY;
+
 	if (error)
 		thaw_processes();
 	return error;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index fe4d258ef32..fbf64e6f64e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1930,7 +1930,7 @@ bool mem_cgroup_oom_synchronize(bool handle)
 	if (!memcg)
 		return false;
 
-	if (!handle)
+	if (!handle || oom_killer_disabled)
 		goto cleanup;
 
 	owait.memcg = memcg;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3cbd76b8c13..b8df76ee2be 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -398,30 +398,27 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 }
 
 /*
- * Number of OOM killer invocations (including memcg OOM killer).
- * Primarily used by PM freezer to check for potential races with
- * OOM killed frozen task.
+ * Number of OOM victims in flight
  */
-static atomic_t oom_kills = ATOMIC_INIT(0);
+static atomic_t oom_victims = ATOMIC_INIT(0);
+static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait);
 
-int oom_kills_count(void)
-{
-	return atomic_read(&oom_kills);
-}
-
-void note_oom_kill(void)
-{
-	atomic_inc(&oom_kills);
-}
+bool oom_killer_disabled __read_mostly;
+static DECLARE_RWSEM(oom_sem);
 
 /**
  * mark_tsk_oom_victim - marks the given taks as OOM victim.
  * @tsk: task to mark
+ *
+ * Has to be called with oom_sem taken for read and never after
+ * oom has been disabled already.
  */
 void mark_tsk_oom_victim(struct task_struct *tsk)
 {
-	set_tsk_thread_flag(tsk, TIF_MEMDIE);
-
+	WARN_ON(oom_killer_disabled);
+	/* OOM killer might race with memcg OOM */
+	if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE))
+		return;
 	/*
 	 * Make sure that the task is woken up from uninterruptible sleep
 	 * if it is frozen because OOM killer wouldn't be able to free
@@ -429,14 +426,70 @@ void mark_tsk_oom_victim(struct task_struct *tsk)
 	 * that TIF_MEMDIE tasks should be ignored.
 	 */
 	__thaw_task(tsk);
+	atomic_inc(&oom_victims);
 }
 
 /**
  * unmark_oom_victim - unmarks the current task as OOM victim.
+ *
+ * Wakes up all waiters in oom_killer_disable()
  */
 void unmark_oom_victim(void)
 {
-	clear_thread_flag(TIF_MEMDIE);
+	if (!test_and_clear_thread_flag(TIF_MEMDIE))
+		return;
+
+	down_read(&oom_sem);
+	/*
+	 * There is no need to signal the lasst oom_victim if there
+	 * is nobody who cares.
+	 */
+	if (!atomic_dec_return(&oom_victims) && oom_killer_disabled)
+		wake_up_all(&oom_victims_wait);
+	up_read(&oom_sem);
+}
+
+/**
+ * oom_killer_disable - disable OOM killer
+ *
+ * Forces all page allocations to fail rather than trigger OOM killer.
+ * Will block and wait until all OOM victims are killed.
+ *
+ * The function cannot be called when there are runnable user tasks because
+ * the userspace would see unexpected allocation failures as a result. Any
+ * new usage of this function should be consulted with MM people.
+ *
+ * Returns true if successful and false if the OOM killer cannot be
+ * disabled.
+ */
+bool oom_killer_disable(void)
+{
+	/*
+	 * Make sure to not race with an ongoing OOM killer
+	 * and that the current is not the victim.
+	 */
+	down_write(&oom_sem);
+	if (test_thread_flag(TIF_MEMDIE)) {
+		up_write(&oom_sem);
+		return false;
+	}
+
+	oom_killer_disabled = true;
+	up_write(&oom_sem);
+
+	wait_event(oom_victims_wait, !atomic_read(&oom_victims));
+
+	return true;
+}
+
+/**
+ * oom_killer_enable - enable OOM killer
+ */
+void oom_killer_enable(void)
+{
+	down_write(&oom_sem);
+	oom_killer_disabled = false;
+	up_write(&oom_sem);
 }
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
@@ -637,7 +690,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
 }
 
 /**
- * out_of_memory - kill the "best" process when we run out of memory
+ * __out_of_memory - kill the "best" process when we run out of memory
  * @zonelist: zonelist pointer
  * @gfp_mask: memory allocation flags
  * @order: amount of memory being requested as a power of 2
@@ -649,7 +702,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask)
  * OR try to be smart about which process to kill. Note that we
  * don't have to be perfect here, we just have to be good.
  */
-void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		int order, nodemask_t *nodemask, bool force_kill)
 {
 	const nodemask_t *mpol_mask;
@@ -718,6 +771,32 @@ out:
 		schedule_timeout_killable(1);
 }
 
+/**
+ * out_of_memory -  tries to invoke OOM killer.
+ * @zonelist: zonelist pointer
+ * @gfp_mask: memory allocation flags
+ * @order: amount of memory being requested as a power of 2
+ * @nodemask: nodemask passed to page allocator
+ * @force_kill: true if a task must be killed, even if others are exiting
+ *
+ * invokes __out_of_memory if the OOM is not disabled by oom_killer_disable()
+ * when it returns false. Otherwise returns true.
+ */
+bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
+		int order, nodemask_t *nodemask, bool force_kill)
+{
+	bool ret = false;
+
+	down_read(&oom_sem);
+	if (!oom_killer_disabled) {
+		__out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill);
+		ret = true;
+	}
+	up_read(&oom_sem);
+
+	return ret;
+}
+
 /*
  * The pagefault handler calls here because it is out of memory, so kill a
  * memory-hogging task.  If any populated zone has ZONE_OOM_LOCKED set, a
@@ -727,12 +806,25 @@ void pagefault_out_of_memory(void)
 {
 	struct zonelist *zonelist;
 
+	down_read(&oom_sem);
 	if (mem_cgroup_oom_synchronize(true))
-		return;
+		goto unlock;
 
 	zonelist = node_zonelist(first_memory_node, GFP_KERNEL);
 	if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) {
-		out_of_memory(NULL, 0, 0, NULL, false);
+		if (!oom_killer_disabled)
+			__out_of_memory(NULL, 0, 0, NULL, false);
+		else
+			/*
+			 * There shouldn't be any user tasks runable while the
+			 * OOM killer is disabled so the current task has to
+			 * be a racing OOM victim for which oom_killer_disable()
+			 * is waiting for.
+			 */
+			WARN_ON(test_thread_flag(TIF_MEMDIE));
+
 		oom_zonelist_unlock(zonelist, GFP_KERNEL);
 	}
+unlock:
+	up_read(&oom_sem);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 641d5a9a861..134e2552504 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -244,8 +244,6 @@ void set_pageblock_migratetype(struct page *page, int migratetype)
 					PB_migrate, PB_migrate_end);
 }
 
-bool oom_killer_disabled __read_mostly;
-
 #ifdef CONFIG_DEBUG_VM
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 {
@@ -2317,9 +2315,6 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 
 	*did_some_progress = 0;
 
-	if (oom_killer_disabled)
-		return NULL;
-
 	/*
 	 * Acquire the per-zone oom lock for each zone.  If that
 	 * fails, somebody else is making progress for us.
@@ -2330,14 +2325,6 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 	}
 
-	/*
-	 * PM-freezer should be notified that there might be an OOM killer on
-	 * its way to kill and wake somebody up. This is too early and we might
-	 * end up not killing anything but false positives are acceptable.
-	 * See freeze_processes.
-	 */
-	note_oom_kill();
-
 	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
@@ -2372,8 +2359,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 			goto out;
 	}
 	/* Exhausted what can be done so it's blamo time */
-	out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false);
-	*did_some_progress = 1;
+	if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false))
+		*did_some_progress = 1;
 out:
 	oom_zonelist_unlock(ac->zonelist, gfp_mask);
 	return page;
-- 
cgit v1.2.3-70-g09d2


From 4155b8e0a79570d41ae77b5bf7df375bd4c36610 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 11 Feb 2015 15:26:44 -0800
Subject: mm, asm-generic: define PUD_SHIFT in <asm-generic/4level-fixup.h>

If an architecure uses <asm-generic/4level-fixup.h>, build fails if we
try to use PUD_SHIFT in generic code:

   In file included from arch/microblaze/include/asm/bug.h:1:0,
                    from include/linux/bug.h:4,
                    from include/linux/thread_info.h:11,
                    from include/asm-generic/preempt.h:4,
                    from arch/microblaze/include/generated/asm/preempt.h:1,
                    from include/linux/preempt.h:18,
                    from include/linux/spinlock.h:50,
                    from include/linux/mmzone.h:7,
                    from include/linux/gfp.h:5,
                    from include/linux/slab.h:14,
                    from mm/mmap.c:12:
   mm/mmap.c: In function 'exit_mmap':
>> mm/mmap.c:2858:46: error: 'PUD_SHIFT' undeclared (first use in this function)
       round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT);
                                                 ^
   include/asm-generic/bug.h:86:25: note: in definition of macro 'WARN_ON'
     int __ret_warn_on = !!(condition);    \
                            ^
   mm/mmap.c:2858:46: note: each undeclared identifier is reported only once for each function it appears in
       round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT);
                                                 ^
   include/asm-generic/bug.h:86:25: note: in definition of macro 'WARN_ON'
     int __ret_warn_on = !!(condition);    \
                            ^
As with <asm-generic/pgtable-nopud.h>, let's define PUD_SHIFT to
PGDIR_SHIFT.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/4level-fixup.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 77ff547730a..5bdab6bffd2 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -4,6 +4,7 @@
 #define __ARCH_HAS_4LEVEL_HACK
 #define __PAGETABLE_PUD_FOLDED
 
+#define PUD_SHIFT			PGDIR_SHIFT
 #define PUD_SIZE			PGDIR_SIZE
 #define PUD_MASK			PGDIR_MASK
 #define PTRS_PER_PUD			1
-- 
cgit v1.2.3-70-g09d2


From dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 11 Feb 2015 15:26:50 -0800
Subject: mm: account pmd page tables to the process

Dave noticed that unprivileged process can allocate significant amount of
memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and
memory cgroup.  The trick is to allocate a lot of PMD page tables.  Linux
kernel doesn't account PMD tables to the process, only PTE.

The use-cases below use few tricks to allocate a lot of PMD page tables
while keeping VmRSS and VmPTE low.  oom_score for the process will be 0.

	#include <errno.h>
	#include <stdio.h>
	#include <stdlib.h>
	#include <unistd.h>
	#include <sys/mman.h>
	#include <sys/prctl.h>

	#define PUD_SIZE (1UL << 30)
	#define PMD_SIZE (1UL << 21)

	#define NR_PUD 130000

	int main(void)
	{
		char *addr = NULL;
		unsigned long i;

		prctl(PR_SET_THP_DISABLE);
		for (i = 0; i < NR_PUD ; i++) {
			addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ,
					MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
			if (addr == MAP_FAILED) {
				perror("mmap");
				break;
			}
			*addr = 'x';
			munmap(addr, PMD_SIZE);
			mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ,
					MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0);
			if (addr == MAP_FAILED)
				perror("re-mmap"), exit(1);
		}
		printf("PID %d consumed %lu KiB in PMD page tables\n",
				getpid(), i * 4096 >> 10);
		return pause();
	}

The patch addresses the issue by account PMD tables to the process the
same way we account PTE.

The main place where PMD tables is accounted is __pmd_alloc() and
free_pmd_range(). But there're few corner cases:

 - HugeTLB can share PMD page tables. The patch handles by accounting
   the table to all processes who share it.

 - x86 PAE pre-allocates few PMD tables on fork.

 - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity
   check on exit(2).

Accounting only happens on configuration where PMD page table's level is
present (PMD is not folded).  As with nr_ptes we use per-mm counter.  The
counter value is used to calculate baseline for badness score by
oom-killer.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Reviewed-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: David Rientjes <rientjes@google.com>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/sysctl/vm.txt | 12 ++++++------
 arch/x86/mm/pgtable.c       | 14 +++++++++-----
 fs/proc/task_mmu.c          |  9 ++++++---
 include/linux/mm.h          | 24 ++++++++++++++++++++++++
 include/linux/mm_types.h    |  3 ++-
 kernel/fork.c               |  3 +++
 mm/debug.c                  |  3 ++-
 mm/hugetlb.c                |  8 ++++++--
 mm/memory.c                 | 15 +++++++++------
 mm/mmap.c                   |  4 +++-
 mm/oom_kill.c               |  9 +++++----
 11 files changed, 75 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 4415aa91568..e9c706e4627 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -555,12 +555,12 @@ this is causing problems for your system/application.
 
 oom_dump_tasks
 
-Enables a system-wide task dump (excluding kernel threads) to be
-produced when the kernel performs an OOM-killing and includes such
-information as pid, uid, tgid, vm size, rss, nr_ptes, swapents,
-oom_score_adj score, and name.  This is helpful to determine why the
-OOM killer was invoked, to identify the rogue task that caused it,
-and to determine why the OOM killer chose the task it did to kill.
+Enables a system-wide task dump (excluding kernel threads) to be produced
+when the kernel performs an OOM-killing and includes such information as
+pid, uid, tgid, vm size, rss, nr_ptes, nr_pmds, swapents, oom_score_adj
+score, and name.  This is helpful to determine why the OOM killer was
+invoked, to identify the rogue task that caused it, and to determine why
+the OOM killer chose the task it did to kill.
 
 If this is set to zero, this information is suppressed.  On very
 large systems with thousands of tasks it may not be feasible to dump
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 6fb6927f9e7..7b22adaad4f 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -190,7 +190,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 
 #endif	/* CONFIG_X86_PAE */
 
-static void free_pmds(pmd_t *pmds[])
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
 {
 	int i;
 
@@ -198,10 +198,11 @@ static void free_pmds(pmd_t *pmds[])
 		if (pmds[i]) {
 			pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
 			free_page((unsigned long)pmds[i]);
+			mm_dec_nr_pmds(mm);
 		}
 }
 
-static int preallocate_pmds(pmd_t *pmds[])
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 {
 	int i;
 	bool failed = false;
@@ -215,11 +216,13 @@ static int preallocate_pmds(pmd_t *pmds[])
 			pmd = NULL;
 			failed = true;
 		}
+		if (pmd)
+			mm_inc_nr_pmds(mm);
 		pmds[i] = pmd;
 	}
 
 	if (failed) {
-		free_pmds(pmds);
+		free_pmds(mm, pmds);
 		return -ENOMEM;
 	}
 
@@ -246,6 +249,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 
 			paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
 			pmd_free(mm, pmd);
+			mm_dec_nr_pmds(mm);
 		}
 	}
 }
@@ -283,7 +287,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	mm->pgd = pgd;
 
-	if (preallocate_pmds(pmds) != 0)
+	if (preallocate_pmds(mm, pmds) != 0)
 		goto out_free_pgd;
 
 	if (paravirt_pgd_alloc(mm) != 0)
@@ -304,7 +308,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	return pgd;
 
 out_free_pmds:
-	free_pmds(pmds);
+	free_pmds(mm, pmds);
 out_free_pgd:
 	free_page((unsigned long)pgd);
 out:
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6396f88c668..e6e0abeb5d1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -21,7 +21,7 @@
 
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
-	unsigned long data, text, lib, swap;
+	unsigned long data, text, lib, swap, ptes, pmds;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
 	/*
@@ -42,6 +42,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
 	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
 	swap = get_mm_counter(mm, MM_SWAPENTS);
+	ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes);
+	pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm);
 	seq_printf(m,
 		"VmPeak:\t%8lu kB\n"
 		"VmSize:\t%8lu kB\n"
@@ -54,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		"VmExe:\t%8lu kB\n"
 		"VmLib:\t%8lu kB\n"
 		"VmPTE:\t%8lu kB\n"
+		"VmPMD:\t%8lu kB\n"
 		"VmSwap:\t%8lu kB\n",
 		hiwater_vm << (PAGE_SHIFT-10),
 		total_vm << (PAGE_SHIFT-10),
@@ -63,8 +66,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		total_rss << (PAGE_SHIFT-10),
 		data << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
-		(PTRS_PER_PTE * sizeof(pte_t) *
-		 atomic_long_read(&mm->nr_ptes)) >> 10,
+		ptes >> 10,
+		pmds >> 10,
 		swap << (PAGE_SHIFT-10));
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c6bf813a6b3..644990b83cd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1438,8 +1438,32 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
 {
 	return 0;
 }
+
+static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void mm_inc_nr_pmds(struct mm_struct *mm) {}
+static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}
+
 #else
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
+
+static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
+{
+	return atomic_long_read(&mm->nr_pmds);
+}
+
+static inline void mm_inc_nr_pmds(struct mm_struct *mm)
+{
+	atomic_long_inc(&mm->nr_pmds);
+}
+
+static inline void mm_dec_nr_pmds(struct mm_struct *mm)
+{
+	atomic_long_dec(&mm->nr_pmds);
+}
 #endif
 
 int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 20ff2105b56..199a03aab8d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -363,7 +363,8 @@ struct mm_struct {
 	pgd_t * pgd;
 	atomic_t mm_users;			/* How many users with user space? */
 	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
-	atomic_long_t nr_ptes;			/* Page table pages */
+	atomic_long_t nr_ptes;			/* PTE page table pages */
+	atomic_long_t nr_pmds;			/* PMD page table pages */
 	int map_count;				/* number of VMAs */
 
 	spinlock_t page_table_lock;		/* Protects page tables and some counters */
diff --git a/kernel/fork.c b/kernel/fork.c
index b379d9abddc..c99098c5264 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -555,6 +555,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	INIT_LIST_HEAD(&mm->mmlist);
 	mm->core_state = NULL;
 	atomic_long_set(&mm->nr_ptes, 0);
+#ifndef __PAGETABLE_PMD_FOLDED
+	atomic_long_set(&mm->nr_pmds, 0);
+#endif
 	mm->map_count = 0;
 	mm->locked_vm = 0;
 	mm->pinned_vm = 0;
diff --git a/mm/debug.c b/mm/debug.c
index d69cb5a7ba9..3eb3ac2fcee 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -173,7 +173,7 @@ void dump_mm(const struct mm_struct *mm)
 		"get_unmapped_area %p\n"
 #endif
 		"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
-		"pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n"
+		"pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n"
 		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
 		"pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n"
 		"start_code %lx end_code %lx start_data %lx end_data %lx\n"
@@ -206,6 +206,7 @@ void dump_mm(const struct mm_struct *mm)
 		mm->pgd, atomic_read(&mm->mm_users),
 		atomic_read(&mm->mm_count),
 		atomic_long_read((atomic_long_t *)&mm->nr_ptes),
+		mm_nr_pmds((struct mm_struct *)mm),
 		mm->map_count,
 		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
 		mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index fd28d6ba5e5..0a9ac6c2683 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3598,6 +3598,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 		if (saddr) {
 			spte = huge_pte_offset(svma->vm_mm, saddr);
 			if (spte) {
+				mm_inc_nr_pmds(mm);
 				get_page(virt_to_page(spte));
 				break;
 			}
@@ -3609,11 +3610,13 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 
 	ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte);
 	spin_lock(ptl);
-	if (pud_none(*pud))
+	if (pud_none(*pud)) {
 		pud_populate(mm, pud,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
-	else
+	} else {
 		put_page(virt_to_page(spte));
+		mm_inc_nr_pmds(mm);
+	}
 	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
@@ -3644,6 +3647,7 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 
 	pud_clear(pud);
 	put_page(virt_to_page(ptep));
+	mm_dec_nr_pmds(mm);
 	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
 	return 1;
 }
diff --git a/mm/memory.c b/mm/memory.c
index d63849b5188..bbe6a73a899 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -428,6 +428,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	pmd = pmd_offset(pud, start);
 	pud_clear(pud);
 	pmd_free_tlb(tlb, pmd, start);
+	mm_dec_nr_pmds(tlb->mm);
 }
 
 static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
@@ -3322,15 +3323,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 
 	spin_lock(&mm->page_table_lock);
 #ifndef __ARCH_HAS_4LEVEL_HACK
-	if (pud_present(*pud))		/* Another has populated it */
-		pmd_free(mm, new);
-	else
+	if (!pud_present(*pud)) {
+		mm_inc_nr_pmds(mm);
 		pud_populate(mm, pud, new);
-#else
-	if (pgd_present(*pud))		/* Another has populated it */
+	} else	/* Another has populated it */
 		pmd_free(mm, new);
-	else
+#else
+	if (!pgd_present(*pud)) {
+		mm_inc_nr_pmds(mm);
 		pgd_populate(mm, pud, new);
+	} else /* Another has populated it */
+		pmd_free(mm, new);
 #endif /* __ARCH_HAS_4LEVEL_HACK */
 	spin_unlock(&mm->page_table_lock);
 	return 0;
diff --git a/mm/mmap.c b/mm/mmap.c
index 14d84666e8b..6a7d36d133f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2853,7 +2853,9 @@ void exit_mmap(struct mm_struct *mm)
 	vm_unacct_memory(nr_accounted);
 
 	WARN_ON(atomic_long_read(&mm->nr_ptes) >
-			(FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+			round_up(FIRST_USER_ADDRESS, PMD_SIZE) >> PMD_SHIFT);
+	WARN_ON(mm_nr_pmds(mm) >
+			round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT);
 }
 
 /* Insert vm structure into process list sorted by address
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index b8df76ee2be..642f38cb175 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -169,8 +169,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * The baseline for the badness score is the proportion of RAM that each
 	 * task's rss, pagetable and swap space use.
 	 */
-	points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) +
-		 get_mm_counter(p->mm, MM_SWAPENTS);
+	points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) +
+		atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm);
 	task_unlock(p);
 
 	/*
@@ -351,7 +351,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 	struct task_struct *p;
 	struct task_struct *task;
 
-	pr_info("[ pid ]   uid  tgid total_vm      rss nr_ptes swapents oom_score_adj name\n");
+	pr_info("[ pid ]   uid  tgid total_vm      rss nr_ptes nr_pmds swapents oom_score_adj name\n");
 	rcu_read_lock();
 	for_each_process(p) {
 		if (oom_unkillable_task(p, memcg, nodemask))
@@ -367,10 +367,11 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu         %5hd %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
 			atomic_long_read(&task->mm->nr_ptes),
+			mm_nr_pmds(task->mm),
 			get_mm_counter(task->mm, MM_SWAPENTS),
 			task->signal->oom_score_adj, task->comm);
 		task_unlock(task);
-- 
cgit v1.2.3-70-g09d2


From 4645f06334be1ad0eb61aa182c7999fe51bc1ba6 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Wed, 11 Feb 2015 15:26:58 -0800
Subject: mm/compaction: change tracepoint format from decimal to hexadecimal

To check the range that compaction is working, tracepoint print
start/end pfn of zone and start pfn of both scanner with decimal format.
Since we manage all pages in order of 2 and it is well represented by
hexadecimal, this patch change the tracepoint format from decimal to
hexadecimal.  This would improve readability.  For example, it makes us
easily notice whether current scanner try to compact previously
attempted pageblock or not.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/trace/events/compaction.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index c6814b917bd..1337d9e01e3 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -104,7 +104,7 @@ TRACE_EVENT(mm_compaction_begin,
 		__entry->zone_end = zone_end;
 	),
 
-	TP_printk("zone_start=%lu migrate_start=%lu free_start=%lu zone_end=%lu",
+	TP_printk("zone_start=0x%lx migrate_start=0x%lx free_start=0x%lx zone_end=0x%lx",
 		__entry->zone_start,
 		__entry->migrate_start,
 		__entry->free_start,
-- 
cgit v1.2.3-70-g09d2


From 16c4a097a035c01809aa0c0abd458ca1fe4ff3d0 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Wed, 11 Feb 2015 15:27:01 -0800
Subject: mm/compaction: enhance tracepoint output for compaction begin/end

We now have tracepoint for begin event of compaction and it prints start
position of both scanners, but, tracepoint for end event of compaction
doesn't print finish position of both scanners.  It'd be also useful to
know finish position of both scanners so this patch add it.  It will help
to find odd behavior or problem on compaction internal logic.

And mode is added to both begin/end tracepoint output, since according to
mode, compaction behavior is quite different.

And lastly, status format is changed to string rather than status number
for readability.

[akpm@linux-foundation.org: fix sparse warning]
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h        |  1 +
 include/trace/events/compaction.h | 49 ++++++++++++++++++++++++++++-----------
 mm/compaction.c                   | 15 ++++++++++--
 3 files changed, 49 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index f2efda2e6ac..db64cae0653 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -12,6 +12,7 @@
 #define COMPACT_PARTIAL		3
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	4
+/* When adding new state, please change compaction_status_string, too */
 
 /* Used to signal whether compaction detected need_sched() or lock contention */
 /* No contention detected */
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 1337d9e01e3..839f6fac921 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -85,46 +85,67 @@ TRACE_EVENT(mm_compaction_migratepages,
 );
 
 TRACE_EVENT(mm_compaction_begin,
-	TP_PROTO(unsigned long zone_start, unsigned long migrate_start,
-		unsigned long free_start, unsigned long zone_end),
+	TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn,
+		unsigned long free_pfn, unsigned long zone_end, bool sync),
 
-	TP_ARGS(zone_start, migrate_start, free_start, zone_end),
+	TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, zone_start)
-		__field(unsigned long, migrate_start)
-		__field(unsigned long, free_start)
+		__field(unsigned long, migrate_pfn)
+		__field(unsigned long, free_pfn)
 		__field(unsigned long, zone_end)
+		__field(bool, sync)
 	),
 
 	TP_fast_assign(
 		__entry->zone_start = zone_start;
-		__entry->migrate_start = migrate_start;
-		__entry->free_start = free_start;
+		__entry->migrate_pfn = migrate_pfn;
+		__entry->free_pfn = free_pfn;
 		__entry->zone_end = zone_end;
+		__entry->sync = sync;
 	),
 
-	TP_printk("zone_start=0x%lx migrate_start=0x%lx free_start=0x%lx zone_end=0x%lx",
+	TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s",
 		__entry->zone_start,
-		__entry->migrate_start,
-		__entry->free_start,
-		__entry->zone_end)
+		__entry->migrate_pfn,
+		__entry->free_pfn,
+		__entry->zone_end,
+		__entry->sync ? "sync" : "async")
 );
 
 TRACE_EVENT(mm_compaction_end,
-	TP_PROTO(int status),
+	TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn,
+		unsigned long free_pfn, unsigned long zone_end, bool sync,
+		int status),
 
-	TP_ARGS(status),
+	TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync, status),
 
 	TP_STRUCT__entry(
+		__field(unsigned long, zone_start)
+		__field(unsigned long, migrate_pfn)
+		__field(unsigned long, free_pfn)
+		__field(unsigned long, zone_end)
+		__field(bool, sync)
 		__field(int, status)
 	),
 
 	TP_fast_assign(
+		__entry->zone_start = zone_start;
+		__entry->migrate_pfn = migrate_pfn;
+		__entry->free_pfn = free_pfn;
+		__entry->zone_end = zone_end;
+		__entry->sync = sync;
 		__entry->status = status;
 	),
 
-	TP_printk("status=%d", __entry->status)
+	TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s status=%s",
+		__entry->zone_start,
+		__entry->migrate_pfn,
+		__entry->free_pfn,
+		__entry->zone_end,
+		__entry->sync ? "sync" : "async",
+		compaction_status_string[__entry->status])
 );
 
 #endif /* _TRACE_COMPACTION_H */
diff --git a/mm/compaction.c b/mm/compaction.c
index 9c7e6909dd2..66f7c365e88 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -34,6 +34,15 @@ static inline void count_compact_events(enum vm_event_item item, long delta)
 #endif
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
+#ifdef CONFIG_TRACEPOINTS
+static const char *const compaction_status_string[] = {
+	"deferred",
+	"skipped",
+	"continue",
+	"partial",
+	"complete",
+};
+#endif
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/compaction.h>
@@ -1197,7 +1206,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
 	}
 
-	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn);
+	trace_mm_compaction_begin(start_pfn, cc->migrate_pfn,
+				cc->free_pfn, end_pfn, sync);
 
 	migrate_prep_local();
 
@@ -1299,7 +1309,8 @@ out:
 			zone->compact_cached_free_pfn = free_pfn;
 	}
 
-	trace_mm_compaction_end(ret);
+	trace_mm_compaction_end(start_pfn, cc->migrate_pfn,
+				cc->free_pfn, end_pfn, sync, ret);
 
 	return ret;
 }
-- 
cgit v1.2.3-70-g09d2


From e34d85f0e3c60f7226e5589898b7c7c5cd2a4f02 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Wed, 11 Feb 2015 15:27:04 -0800
Subject: mm/compaction: print current range where compaction work

It'd be useful to know current range where compaction work for detailed
analysis.  With it, we can know pageblock where we actually scan and
isolate, and, how much pages we try in that pageblock and can guess why it
doesn't become freepage with pageblock order roughly.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/trace/events/compaction.h | 30 +++++++++++++++++++++++-------
 mm/compaction.c                   |  9 ++++++---
 2 files changed, 29 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 839f6fac921..139020b5561 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -11,39 +11,55 @@
 
 DECLARE_EVENT_CLASS(mm_compaction_isolate_template,
 
-	TP_PROTO(unsigned long nr_scanned,
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
 		unsigned long nr_taken),
 
-	TP_ARGS(nr_scanned, nr_taken),
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken),
 
 	TP_STRUCT__entry(
+		__field(unsigned long, start_pfn)
+		__field(unsigned long, end_pfn)
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_taken)
 	),
 
 	TP_fast_assign(
+		__entry->start_pfn = start_pfn;
+		__entry->end_pfn = end_pfn;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_taken = nr_taken;
 	),
 
-	TP_printk("nr_scanned=%lu nr_taken=%lu",
+	TP_printk("range=(0x%lx ~ 0x%lx) nr_scanned=%lu nr_taken=%lu",
+		__entry->start_pfn,
+		__entry->end_pfn,
 		__entry->nr_scanned,
 		__entry->nr_taken)
 );
 
 DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_migratepages,
 
-	TP_PROTO(unsigned long nr_scanned,
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
 		unsigned long nr_taken),
 
-	TP_ARGS(nr_scanned, nr_taken)
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
 );
 
 DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages,
-	TP_PROTO(unsigned long nr_scanned,
+
+	TP_PROTO(
+		unsigned long start_pfn,
+		unsigned long end_pfn,
+		unsigned long nr_scanned,
 		unsigned long nr_taken),
 
-	TP_ARGS(nr_scanned, nr_taken)
+	TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken)
 );
 
 TRACE_EVENT(mm_compaction_migratepages,
diff --git a/mm/compaction.c b/mm/compaction.c
index 66f7c365e88..b12df9fe10b 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -430,11 +430,12 @@ isolate_fail:
 
 	}
 
+	trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn,
+					nr_scanned, total_isolated);
+
 	/* Record how far we have got within the block */
 	*start_pfn = blockpfn;
 
-	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
-
 	/*
 	 * If strict isolation is requested by CMA then check that all the
 	 * pages requested were isolated. If there were any failures, 0 is
@@ -590,6 +591,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 	unsigned long flags = 0;
 	bool locked = false;
 	struct page *page = NULL, *valid_page = NULL;
+	unsigned long start_pfn = low_pfn;
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -750,7 +752,8 @@ isolate_success:
 	if (low_pfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, nr_isolated, true);
 
-	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
+	trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
+						nr_scanned, nr_isolated);
 
 	count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
 	if (nr_isolated)
-- 
cgit v1.2.3-70-g09d2


From 837d026d560c5ef26abeca0441713d82e4e82cad Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Wed, 11 Feb 2015 15:27:06 -0800
Subject: mm/compaction: more trace to understand when/why compaction
 start/finish

It is not well analyzed that when/why compaction start/finish or not.
With these new tracepoints, we can know much more about start/finish
reason of compaction.  I can find following bug with these tracepoint.

http://www.spinics.net/lists/linux-mm/msg81582.html

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h        |  3 ++
 include/trace/events/compaction.h | 74 +++++++++++++++++++++++++++++++++++++++
 mm/compaction.c                   | 38 +++++++++++++++++---
 3 files changed, 111 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index db64cae0653..501d7513aac 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -12,6 +12,9 @@
 #define COMPACT_PARTIAL		3
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	4
+/* For more detailed tracepoint output */
+#define COMPACT_NO_SUITABLE_PAGE	5
+#define COMPACT_NOT_SUITABLE_ZONE	6
 /* When adding new state, please change compaction_status_string, too */
 
 /* Used to signal whether compaction detected need_sched() or lock contention */
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 139020b5561..d46535801f6 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -164,6 +164,80 @@ TRACE_EVENT(mm_compaction_end,
 		compaction_status_string[__entry->status])
 );
 
+TRACE_EVENT(mm_compaction_try_to_compact_pages,
+
+	TP_PROTO(
+		int order,
+		gfp_t gfp_mask,
+		enum migrate_mode mode),
+
+	TP_ARGS(order, gfp_mask, mode),
+
+	TP_STRUCT__entry(
+		__field(int, order)
+		__field(gfp_t, gfp_mask)
+		__field(enum migrate_mode, mode)
+	),
+
+	TP_fast_assign(
+		__entry->order = order;
+		__entry->gfp_mask = gfp_mask;
+		__entry->mode = mode;
+	),
+
+	TP_printk("order=%d gfp_mask=0x%x mode=%d",
+		__entry->order,
+		__entry->gfp_mask,
+		(int)__entry->mode)
+);
+
+DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(char *, name)
+		__field(int, order)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->nid = zone_to_nid(zone);
+		__entry->name = (char *)zone->name;
+		__entry->order = order;
+		__entry->ret = ret;
+	),
+
+	TP_printk("node=%d zone=%-8s order=%d ret=%s",
+		__entry->nid,
+		__entry->name,
+		__entry->order,
+		compaction_status_string[__entry->ret])
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret)
+);
+
+DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
+
+	TP_PROTO(struct zone *zone,
+		int order,
+		int ret),
+
+	TP_ARGS(zone, order, ret)
+);
+
 #endif /* _TRACE_COMPACTION_H */
 
 /* This part must be outside protection */
diff --git a/mm/compaction.c b/mm/compaction.c
index b12df9fe10b..b6ede459c1b 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -41,6 +41,8 @@ static const char *const compaction_status_string[] = {
 	"continue",
 	"partial",
 	"complete",
+	"no_suitable_page",
+	"not_suitable_zone",
 };
 #endif
 
@@ -1049,7 +1051,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
 
-static int compact_finished(struct zone *zone, struct compact_control *cc,
+static int __compact_finished(struct zone *zone, struct compact_control *cc,
 			    const int migratetype)
 {
 	unsigned int order;
@@ -1104,7 +1106,20 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 			return COMPACT_PARTIAL;
 	}
 
-	return COMPACT_CONTINUE;
+	return COMPACT_NO_SUITABLE_PAGE;
+}
+
+static int compact_finished(struct zone *zone, struct compact_control *cc,
+			    const int migratetype)
+{
+	int ret;
+
+	ret = __compact_finished(zone, cc, migratetype);
+	trace_mm_compaction_finished(zone, cc->order, ret);
+	if (ret == COMPACT_NO_SUITABLE_PAGE)
+		ret = COMPACT_CONTINUE;
+
+	return ret;
 }
 
 /*
@@ -1114,7 +1129,7 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
-unsigned long compaction_suitable(struct zone *zone, int order,
+static unsigned long __compaction_suitable(struct zone *zone, int order,
 					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
@@ -1158,11 +1173,24 @@ unsigned long compaction_suitable(struct zone *zone, int order,
 	 */
 	fragindex = fragmentation_index(zone, order);
 	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
-		return COMPACT_SKIPPED;
+		return COMPACT_NOT_SUITABLE_ZONE;
 
 	return COMPACT_CONTINUE;
 }
 
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
+{
+	unsigned long ret;
+
+	ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx);
+	trace_mm_compaction_suitable(zone, order, ret);
+	if (ret == COMPACT_NOT_SUITABLE_ZONE)
+		ret = COMPACT_SKIPPED;
+
+	return ret;
+}
+
 static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
@@ -1376,6 +1404,8 @@ unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
+	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode);
+
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
 								ac->nodemask) {
-- 
cgit v1.2.3-70-g09d2


From 24e2716f63e613cf15d3beba3faa0711bcacc427 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Wed, 11 Feb 2015 15:27:09 -0800
Subject: mm/compaction: add tracepoint to observe behaviour of compaction
 defer

Compaction deferring logic is heavy hammer that block the way to the
compaction.  It doesn't consider overall system state, so it could prevent
user from doing compaction falsely.  In other words, even if system has
enough range of memory to compact, compaction would be skipped due to
compaction deferring logic.  This patch add new tracepoint to understand
work of deferring logic.  This will also help to check compaction success
and fail.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compaction.h        | 65 +++--------------------------------
 include/trace/events/compaction.h | 56 ++++++++++++++++++++++++++++++
 mm/compaction.c                   | 71 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 132 insertions(+), 60 deletions(-)

(limited to 'include')

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 501d7513aac..a014559e4a4 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -44,66 +44,11 @@ extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order,
 					int alloc_flags, int classzone_idx);
 
-/* Do not skip compaction more than 64 times */
-#define COMPACT_MAX_DEFER_SHIFT 6
-
-/*
- * Compaction is deferred when compaction fails to result in a page
- * allocation success. 1 << compact_defer_limit compactions are skipped up
- * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
- */
-static inline void defer_compaction(struct zone *zone, int order)
-{
-	zone->compact_considered = 0;
-	zone->compact_defer_shift++;
-
-	if (order < zone->compact_order_failed)
-		zone->compact_order_failed = order;
-
-	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
-		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
-}
-
-/* Returns true if compaction should be skipped this time */
-static inline bool compaction_deferred(struct zone *zone, int order)
-{
-	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
-
-	if (order < zone->compact_order_failed)
-		return false;
-
-	/* Avoid possible overflow */
-	if (++zone->compact_considered > defer_limit)
-		zone->compact_considered = defer_limit;
-
-	return zone->compact_considered < defer_limit;
-}
-
-/*
- * Update defer tracking counters after successful compaction of given order,
- * which means an allocation either succeeded (alloc_success == true) or is
- * expected to succeed.
- */
-static inline void compaction_defer_reset(struct zone *zone, int order,
-		bool alloc_success)
-{
-	if (alloc_success) {
-		zone->compact_considered = 0;
-		zone->compact_defer_shift = 0;
-	}
-	if (order >= zone->compact_order_failed)
-		zone->compact_order_failed = order + 1;
-}
-
-/* Returns true if restarting compaction after many failures */
-static inline bool compaction_restarting(struct zone *zone, int order)
-{
-	if (order < zone->compact_order_failed)
-		return false;
-
-	return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
-		zone->compact_considered >= 1UL << zone->compact_defer_shift;
-}
+extern void defer_compaction(struct zone *zone, int order);
+extern bool compaction_deferred(struct zone *zone, int order);
+extern void compaction_defer_reset(struct zone *zone, int order,
+				bool alloc_success);
+extern bool compaction_restarting(struct zone *zone, int order);
 
 #else
 static inline unsigned long try_to_compact_pages(gfp_t gfp_mask,
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index d46535801f6..9a6a3fe0fb5 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -238,6 +238,62 @@ DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable,
 	TP_ARGS(zone, order, ret)
 );
 
+#ifdef CONFIG_COMPACTION
+DECLARE_EVENT_CLASS(mm_compaction_defer_template,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(char *, name)
+		__field(int, order)
+		__field(unsigned int, considered)
+		__field(unsigned int, defer_shift)
+		__field(int, order_failed)
+	),
+
+	TP_fast_assign(
+		__entry->nid = zone_to_nid(zone);
+		__entry->name = (char *)zone->name;
+		__entry->order = order;
+		__entry->considered = zone->compact_considered;
+		__entry->defer_shift = zone->compact_defer_shift;
+		__entry->order_failed = zone->compact_order_failed;
+	),
+
+	TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu",
+		__entry->nid,
+		__entry->name,
+		__entry->order,
+		__entry->order_failed,
+		__entry->considered,
+		1UL << __entry->defer_shift)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_deferred,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_compaction,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+
+DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_reset,
+
+	TP_PROTO(struct zone *zone, int order),
+
+	TP_ARGS(zone, order)
+);
+#endif
+
 #endif /* _TRACE_COMPACTION_H */
 
 /* This part must be outside protection */
diff --git a/mm/compaction.c b/mm/compaction.c
index b6ede459c1b..b68736c8a1c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -124,6 +124,77 @@ static struct page *pageblock_pfn_to_page(unsigned long start_pfn,
 }
 
 #ifdef CONFIG_COMPACTION
+
+/* Do not skip compaction more than 64 times */
+#define COMPACT_MAX_DEFER_SHIFT 6
+
+/*
+ * Compaction is deferred when compaction fails to result in a page
+ * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
+ */
+void defer_compaction(struct zone *zone, int order)
+{
+	zone->compact_considered = 0;
+	zone->compact_defer_shift++;
+
+	if (order < zone->compact_order_failed)
+		zone->compact_order_failed = order;
+
+	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
+		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
+
+	trace_mm_compaction_defer_compaction(zone, order);
+}
+
+/* Returns true if compaction should be skipped this time */
+bool compaction_deferred(struct zone *zone, int order)
+{
+	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
+
+	if (order < zone->compact_order_failed)
+		return false;
+
+	/* Avoid possible overflow */
+	if (++zone->compact_considered > defer_limit)
+		zone->compact_considered = defer_limit;
+
+	if (zone->compact_considered >= defer_limit)
+		return false;
+
+	trace_mm_compaction_deferred(zone, order);
+
+	return true;
+}
+
+/*
+ * Update defer tracking counters after successful compaction of given order,
+ * which means an allocation either succeeded (alloc_success == true) or is
+ * expected to succeed.
+ */
+void compaction_defer_reset(struct zone *zone, int order,
+		bool alloc_success)
+{
+	if (alloc_success) {
+		zone->compact_considered = 0;
+		zone->compact_defer_shift = 0;
+	}
+	if (order >= zone->compact_order_failed)
+		zone->compact_order_failed = order + 1;
+
+	trace_mm_compaction_defer_reset(zone, order);
+}
+
+/* Returns true if restarting compaction after many failures */
+bool compaction_restarting(struct zone *zone, int order)
+{
+	if (order < zone->compact_order_failed)
+		return false;
+
+	return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
+		zone->compact_considered >= 1UL << zone->compact_defer_shift;
+}
+
 /* Returns true if the pageblock should be scanned for pages to isolate. */
 static inline bool isolation_suitable(struct compact_control *cc,
 					struct page *page)
-- 
cgit v1.2.3-70-g09d2


From 077fcf116c8c2bd7ee9487b645aa3b50368db7e1 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Wed, 11 Feb 2015 15:27:12 -0800
Subject: mm/thp: allocate transparent hugepages on local node

This make sure that we try to allocate hugepages from local node if
allowed by mempolicy.  If we can't, we fallback to small page allocation
based on mempolicy.  This is based on the observation that allocating
pages on local node is more beneficial than allocating hugepages on remote
node.

With this patch applied we may find transparent huge page allocation
failures if the current node doesn't have enough freee hugepages.  Before
this patch such failures result in us retrying the allocation on other
nodes in the numa node mask.

[akpm@linux-foundation.org: fix comment, add CONFIG_TRANSPARENT_HUGEPAGE dependency]
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h |  4 +++
 mm/huge_memory.c    | 24 +++++++-----------
 mm/mempolicy.c      | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 85 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index b840e3b2770..60110e06419 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -335,11 +335,15 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr,
 			int node);
+extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma,
+				       unsigned long addr, int order);
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
 #define alloc_pages_vma(gfp_mask, order, vma, addr, node)	\
 	alloc_pages(gfp_mask, order)
+#define alloc_hugepage_vma(gfp_mask, vma, addr, order)	\
+	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 88971318098..0531ea7dd7c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -761,15 +761,6 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
 	return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp;
 }
 
-static inline struct page *alloc_hugepage_vma(int defrag,
-					      struct vm_area_struct *vma,
-					      unsigned long haddr, int nd,
-					      gfp_t extra_gfp)
-{
-	return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp),
-			       HPAGE_PMD_ORDER, vma, haddr, nd);
-}
-
 /* Caller must hold page table lock. */
 static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd,
@@ -790,6 +781,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			       unsigned long address, pmd_t *pmd,
 			       unsigned int flags)
 {
+	gfp_t gfp;
 	struct page *page;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
 
@@ -824,8 +816,8 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 		return 0;
 	}
-	page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
-			vma, haddr, numa_node_id(), 0);
+	gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0);
+	page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
 	if (unlikely(!page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1113,10 +1105,12 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_unlock(ptl);
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
-	    !transparent_hugepage_debug_cow())
-		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
-					      vma, haddr, numa_node_id(), 0);
-	else
+	    !transparent_hugepage_debug_cow()) {
+		gfp_t gfp;
+
+		gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0);
+		new_page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+	} else
 		new_page = NULL;
 
 	if (unlikely(!new_page)) {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0e0961b8c39..8a32873fdbf 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2030,6 +2030,78 @@ retry_cpuset:
 	return page;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/**
+ * alloc_hugepage_vma: Allocate a hugepage for a VMA
+ * @gfp:
+ *   %GFP_USER	  user allocation.
+ *   %GFP_KERNEL  kernel allocations,
+ *   %GFP_HIGHMEM highmem/user allocations,
+ *   %GFP_FS	  allocation should not call back into a file system.
+ *   %GFP_ATOMIC  don't sleep.
+ *
+ * @vma:   Pointer to VMA or NULL if not available.
+ * @addr:  Virtual Address of the allocation. Must be inside the VMA.
+ * @order: Order of the hugepage for gfp allocation.
+ *
+ * This functions allocate a huge page from the kernel page pool and applies
+ * a NUMA policy associated with the VMA or the current process.
+ * For policy other than %MPOL_INTERLEAVE, we make sure we allocate hugepage
+ * only from the current node if the current node is part of the node mask.
+ * If we can't allocate a hugepage we fail the allocation and don' try to fallback
+ * to other nodes in the node mask. If the current node is not part of node mask
+ * or if the NUMA policy is MPOL_INTERLEAVE we use the allocator that can
+ * fallback to nodes in the policy node mask.
+ *
+ * When VMA is not NULL caller must hold down_read on the mmap_sem of the
+ * mm_struct of the VMA to prevent it from going away. Should be used for
+ * all allocations for pages that will be mapped into
+ * user space. Returns NULL when no page can be allocated.
+ *
+ * Should be called with vma->vm_mm->mmap_sem held.
+ *
+ */
+struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma,
+				unsigned long addr, int order)
+{
+	struct page *page;
+	nodemask_t *nmask;
+	struct mempolicy *pol;
+	int node = numa_node_id();
+	unsigned int cpuset_mems_cookie;
+
+retry_cpuset:
+	pol = get_vma_policy(vma, addr);
+	cpuset_mems_cookie = read_mems_allowed_begin();
+	/*
+	 * For interleave policy, we don't worry about
+	 * current node. Otherwise if current node is
+	 * in nodemask, try to allocate hugepage from
+	 * the current node. Don't fall back to other nodes
+	 * for THP.
+	 */
+	if (unlikely(pol->mode == MPOL_INTERLEAVE))
+		goto alloc_with_fallback;
+	nmask = policy_nodemask(gfp, pol);
+	if (!nmask || node_isset(node, *nmask)) {
+		mpol_cond_put(pol);
+		page = alloc_pages_exact_node(node, gfp, order);
+		if (unlikely(!page &&
+			     read_mems_allowed_retry(cpuset_mems_cookie)))
+			goto retry_cpuset;
+		return page;
+	}
+alloc_with_fallback:
+	mpol_cond_put(pol);
+	/*
+	 * if current node is not part of node mask, try
+	 * the allocation from any node, and we can do retry
+	 * in that case.
+	 */
+	return alloc_pages_vma(gfp, order, vma, addr, node);
+}
+#endif
+
 /**
  * 	alloc_pages_current - Allocate pages.
  *
-- 
cgit v1.2.3-70-g09d2


From be97a41b291e495d6cb767b3ee0f84ed05804892 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 11 Feb 2015 15:27:15 -0800
Subject: mm/mempolicy.c: merge alloc_hugepage_vma to alloc_pages_vma

The previous commit ("mm/thp: Allocate transparent hugepages on local
node") introduced alloc_hugepage_vma() to mm/mempolicy.c to perform a
special policy for THP allocations.  The function has the same interface
as alloc_pages_vma(), shares a lot of boilerplate code and a long
comment.

This patch merges the hugepage special case into alloc_pages_vma.  The
extra if condition should be cheap enough price to pay.  We also prevent
a (however unlikely) race with parallel mems_allowed update, which could
make hugepage allocation restart only within the fallback call to
alloc_hugepage_vma() and not reconsider the special rule in
alloc_hugepage_vma().

Also by making sure mpol_cond_put(pol) is always called before actual
allocation attempt, we can use a single exit path within the function.

Also update the comment for missing node parameter and obsolete reference
to mm_sem.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/gfp.h |  12 +++---
 mm/mempolicy.c      | 118 +++++++++++++++-------------------------------------
 2 files changed, 39 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 60110e06419..51bd1e72a91 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -334,22 +334,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 }
 extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr,
-			int node);
-extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma,
-				       unsigned long addr, int order);
+			int node, bool hugepage);
+#define alloc_hugepage_vma(gfp_mask, vma, addr, order)	\
+	alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr, node)	\
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
 	alloc_pages(gfp_mask, order)
 #define alloc_hugepage_vma(gfp_mask, vma, addr, order)	\
 	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
 #define alloc_page_vma(gfp_mask, vma, addr)			\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
+	alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
 #define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
-	alloc_pages_vma(gfp_mask, 0, vma, addr, node)
+	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
 
 extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order);
 extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask,
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 8a32873fdbf..acbbf4c821e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1988,120 +1988,68 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  *	@order:Order of the GFP allocation.
  * 	@vma:  Pointer to VMA or NULL if not available.
  *	@addr: Virtual Address of the allocation. Must be inside the VMA.
+ *	@node: Which node to prefer for allocation (modulo policy).
+ *	@hugepage: for hugepages try only the preferred node if possible
  *
  * 	This function allocates a page from the kernel page pool and applies
  *	a NUMA policy associated with the VMA or the current process.
  *	When VMA is not NULL caller must hold down_read on the mmap_sem of the
  *	mm_struct of the VMA to prevent it from going away. Should be used for
- *	all allocations for pages that will be mapped into
- * 	user space. Returns NULL when no page can be allocated.
- *
- *	Should be called with the mm_sem of the vma hold.
+ *	all allocations for pages that will be mapped into user space. Returns
+ *	NULL when no page can be allocated.
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, int node)
+		unsigned long addr, int node, bool hugepage)
 {
 	struct mempolicy *pol;
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
+	struct zonelist *zl;
+	nodemask_t *nmask;
 
 retry_cpuset:
 	pol = get_vma_policy(vma, addr);
 	cpuset_mems_cookie = read_mems_allowed_begin();
 
-	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
+	if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage &&
+					pol->mode != MPOL_INTERLEAVE)) {
+		/*
+		 * For hugepage allocation and non-interleave policy which
+		 * allows the current node, we only try to allocate from the
+		 * current node and don't fall back to other nodes, as the
+		 * cost of remote accesses would likely offset THP benefits.
+		 *
+		 * If the policy is interleave, or does not allow the current
+		 * node in its nodemask, we allocate the standard way.
+		 */
+		nmask = policy_nodemask(gfp, pol);
+		if (!nmask || node_isset(node, *nmask)) {
+			mpol_cond_put(pol);
+			page = alloc_pages_exact_node(node, gfp, order);
+			goto out;
+		}
+	}
+
+	if (pol->mode == MPOL_INTERLEAVE) {
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
-			goto retry_cpuset;
-
-		return page;
+		goto out;
 	}
-	page = __alloc_pages_nodemask(gfp, order,
-				      policy_zonelist(gfp, pol, node),
-				      policy_nodemask(gfp, pol));
+
+	nmask = policy_nodemask(gfp, pol);
+	zl = policy_zonelist(gfp, pol, node);
 	mpol_cond_put(pol);
+	page = __alloc_pages_nodemask(gfp, order, zl, nmask);
+out:
 	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/**
- * alloc_hugepage_vma: Allocate a hugepage for a VMA
- * @gfp:
- *   %GFP_USER	  user allocation.
- *   %GFP_KERNEL  kernel allocations,
- *   %GFP_HIGHMEM highmem/user allocations,
- *   %GFP_FS	  allocation should not call back into a file system.
- *   %GFP_ATOMIC  don't sleep.
- *
- * @vma:   Pointer to VMA or NULL if not available.
- * @addr:  Virtual Address of the allocation. Must be inside the VMA.
- * @order: Order of the hugepage for gfp allocation.
- *
- * This functions allocate a huge page from the kernel page pool and applies
- * a NUMA policy associated with the VMA or the current process.
- * For policy other than %MPOL_INTERLEAVE, we make sure we allocate hugepage
- * only from the current node if the current node is part of the node mask.
- * If we can't allocate a hugepage we fail the allocation and don' try to fallback
- * to other nodes in the node mask. If the current node is not part of node mask
- * or if the NUMA policy is MPOL_INTERLEAVE we use the allocator that can
- * fallback to nodes in the policy node mask.
- *
- * When VMA is not NULL caller must hold down_read on the mmap_sem of the
- * mm_struct of the VMA to prevent it from going away. Should be used for
- * all allocations for pages that will be mapped into
- * user space. Returns NULL when no page can be allocated.
- *
- * Should be called with vma->vm_mm->mmap_sem held.
- *
- */
-struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma,
-				unsigned long addr, int order)
-{
-	struct page *page;
-	nodemask_t *nmask;
-	struct mempolicy *pol;
-	int node = numa_node_id();
-	unsigned int cpuset_mems_cookie;
-
-retry_cpuset:
-	pol = get_vma_policy(vma, addr);
-	cpuset_mems_cookie = read_mems_allowed_begin();
-	/*
-	 * For interleave policy, we don't worry about
-	 * current node. Otherwise if current node is
-	 * in nodemask, try to allocate hugepage from
-	 * the current node. Don't fall back to other nodes
-	 * for THP.
-	 */
-	if (unlikely(pol->mode == MPOL_INTERLEAVE))
-		goto alloc_with_fallback;
-	nmask = policy_nodemask(gfp, pol);
-	if (!nmask || node_isset(node, *nmask)) {
-		mpol_cond_put(pol);
-		page = alloc_pages_exact_node(node, gfp, order);
-		if (unlikely(!page &&
-			     read_mems_allowed_retry(cpuset_mems_cookie)))
-			goto retry_cpuset;
-		return page;
-	}
-alloc_with_fallback:
-	mpol_cond_put(pol);
-	/*
-	 * if current node is not part of node mask, try
-	 * the allocation from any node, and we can do retry
-	 * in that case.
-	 */
-	return alloc_pages_vma(gfp, order, vma, addr, node);
-}
-#endif
-
 /**
  * 	alloc_pages_current - Allocate pages.
  *
-- 
cgit v1.2.3-70-g09d2


From f0818f472d8d527a96ec9cc2c3a56223497f9dd3 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Wed, 11 Feb 2015 15:27:17 -0800
Subject: mm: gup: add get_user_pages_locked and get_user_pages_unlocked

FAULT_FOLL_ALLOW_RETRY allows the page fault to drop the mmap_sem for
reading to reduce the mmap_sem contention (for writing), like while
waiting for I/O completion.  The problem is that right now practically no
get_user_pages call uses FAULT_FOLL_ALLOW_RETRY, so we're not leveraging
that nifty feature.

Andres fixed it for the KVM page fault.  However get_user_pages_fast
remains uncovered, and 99% of other get_user_pages aren't using it either
(the only exception being FOLL_NOWAIT in KVM which is really nonblocking
and in fact it doesn't even release the mmap_sem).

So this patchsets extends the optimization Andres did in the KVM page
fault to the whole kernel.  It makes most important places (including
gup_fast) to use FAULT_FOLL_ALLOW_RETRY to reduce the mmap_sem hold times
during I/O.

The only few places that remains uncovered are drivers like v4l and other
exceptions that tends to work on their own memory and they're not working
on random user memory (for example like O_DIRECT that uses gup_fast and is
fully covered by this patch).

A follow up patch should probably also add a printk_once warning to
get_user_pages that should go obsolete and be phased out eventually.  The
"vmas" parameter of get_user_pages makes it fundamentally incompatible
with FAULT_FOLL_ALLOW_RETRY (vmas array becomes meaningless the moment the
mmap_sem is released).

While this is just an optimization, this becomes an absolute requirement
for the userfaultfd feature http://lwn.net/Articles/615086/ .

The userfaultfd allows to block the page fault, and in order to do so I
need to drop the mmap_sem first.  So this patch also ensures that all
memory where userfaultfd could be registered by KVM, the very first fault
(no matter if it is a regular page fault, or a get_user_pages) always has
FAULT_FOLL_ALLOW_RETRY set.  Then the userfaultfd blocks and it is waken
only when the pagetable is already mapped.  The second fault attempt after
the wakeup doesn't need FAULT_FOLL_ALLOW_RETRY, so it's ok to retry
without it.

This patch (of 5):

We can leverage the VM_FAULT_RETRY functionality in the page fault paths
better by using either get_user_pages_locked or get_user_pages_unlocked.

The former allows conversion of get_user_pages invocations that will have
to pass a "&locked" parameter to know if the mmap_sem was dropped during
the call.  Example from:

    down_read(&mm->mmap_sem);
    do_something()
    get_user_pages(tsk, mm, ..., pages, NULL);
    up_read(&mm->mmap_sem);

to:

    int locked = 1;
    down_read(&mm->mmap_sem);
    do_something()
    get_user_pages_locked(tsk, mm, ..., pages, &locked);
    if (locked)
        up_read(&mm->mmap_sem);

The latter is suitable only as a drop in replacement of the form:

    down_read(&mm->mmap_sem);
    get_user_pages(tsk, mm, ..., pages, NULL);
    up_read(&mm->mmap_sem);

into:

    get_user_pages_unlocked(tsk, mm, ..., pages);

Where tsk, mm, the intermediate "..." paramters and "pages" can be any
value as before.  Just the last parameter of get_user_pages (vmas) must be
NULL for get_user_pages_locked|unlocked to be usable (the latter original
form wouldn't have been safe anyway if vmas wasn't null, for the former we
just make it explicit by dropping the parameter).

If vmas is not NULL these two methods cannot be used.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Reviewed-by: Peter Feiner <pfeiner@google.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |   7 +++
 mm/gup.c           | 177 +++++++++++++++++++++++++++++++++++++++++++++++++----
 mm/nommu.c         |  23 +++++++
 3 files changed, 196 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 644990b83cd..fc499e67547 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1261,6 +1261,13 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		    unsigned long start, unsigned long nr_pages,
 		    int write, int force, struct page **pages,
 		    struct vm_area_struct **vmas);
+long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
+		    unsigned long start, unsigned long nr_pages,
+		    int write, int force, struct page **pages,
+		    int *locked);
+long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+		    unsigned long start, unsigned long nr_pages,
+		    int write, int force, struct page **pages);
 int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 			struct page **pages);
 struct kvec;
diff --git a/mm/gup.c b/mm/gup.c
index 1a8ab05918e..71a37738a32 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -575,6 +575,165 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	return 0;
 }
 
+static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
+						struct mm_struct *mm,
+						unsigned long start,
+						unsigned long nr_pages,
+						int write, int force,
+						struct page **pages,
+						struct vm_area_struct **vmas,
+						int *locked, bool notify_drop)
+{
+	int flags = FOLL_TOUCH;
+	long ret, pages_done;
+	bool lock_dropped;
+
+	if (locked) {
+		/* if VM_FAULT_RETRY can be returned, vmas become invalid */
+		BUG_ON(vmas);
+		/* check caller initialized locked */
+		BUG_ON(*locked != 1);
+	}
+
+	if (pages)
+		flags |= FOLL_GET;
+	if (write)
+		flags |= FOLL_WRITE;
+	if (force)
+		flags |= FOLL_FORCE;
+
+	pages_done = 0;
+	lock_dropped = false;
+	for (;;) {
+		ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages,
+				       vmas, locked);
+		if (!locked)
+			/* VM_FAULT_RETRY couldn't trigger, bypass */
+			return ret;
+
+		/* VM_FAULT_RETRY cannot return errors */
+		if (!*locked) {
+			BUG_ON(ret < 0);
+			BUG_ON(ret >= nr_pages);
+		}
+
+		if (!pages)
+			/* If it's a prefault don't insist harder */
+			return ret;
+
+		if (ret > 0) {
+			nr_pages -= ret;
+			pages_done += ret;
+			if (!nr_pages)
+				break;
+		}
+		if (*locked) {
+			/* VM_FAULT_RETRY didn't trigger */
+			if (!pages_done)
+				pages_done = ret;
+			break;
+		}
+		/* VM_FAULT_RETRY triggered, so seek to the faulting offset */
+		pages += ret;
+		start += ret << PAGE_SHIFT;
+
+		/*
+		 * Repeat on the address that fired VM_FAULT_RETRY
+		 * without FAULT_FLAG_ALLOW_RETRY but with
+		 * FAULT_FLAG_TRIED.
+		 */
+		*locked = 1;
+		lock_dropped = true;
+		down_read(&mm->mmap_sem);
+		ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED,
+				       pages, NULL, NULL);
+		if (ret != 1) {
+			BUG_ON(ret > 1);
+			if (!pages_done)
+				pages_done = ret;
+			break;
+		}
+		nr_pages--;
+		pages_done++;
+		if (!nr_pages)
+			break;
+		pages++;
+		start += PAGE_SIZE;
+	}
+	if (notify_drop && lock_dropped && *locked) {
+		/*
+		 * We must let the caller know we temporarily dropped the lock
+		 * and so the critical section protected by it was lost.
+		 */
+		up_read(&mm->mmap_sem);
+		*locked = 0;
+	}
+	return pages_done;
+}
+
+/*
+ * We can leverage the VM_FAULT_RETRY functionality in the page fault
+ * paths better by using either get_user_pages_locked() or
+ * get_user_pages_unlocked().
+ *
+ * get_user_pages_locked() is suitable to replace the form:
+ *
+ *      down_read(&mm->mmap_sem);
+ *      do_something()
+ *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      up_read(&mm->mmap_sem);
+ *
+ *  to:
+ *
+ *      int locked = 1;
+ *      down_read(&mm->mmap_sem);
+ *      do_something()
+ *      get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ *      if (locked)
+ *          up_read(&mm->mmap_sem);
+ */
+long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   int write, int force, struct page **pages,
+			   int *locked)
+{
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+				       pages, NULL, locked, true);
+}
+EXPORT_SYMBOL(get_user_pages_locked);
+
+/*
+ * get_user_pages_unlocked() is suitable to replace the form:
+ *
+ *      down_read(&mm->mmap_sem);
+ *      get_user_pages(tsk, mm, ..., pages, NULL);
+ *      up_read(&mm->mmap_sem);
+ *
+ *  with:
+ *
+ *      get_user_pages_unlocked(tsk, mm, ..., pages);
+ *
+ * It is functionally equivalent to get_user_pages_fast so
+ * get_user_pages_fast should be used instead, if the two parameters
+ * "tsk" and "mm" are respectively equal to current and current->mm,
+ * or if "force" shall be set to 1 (get_user_pages_fast misses the
+ * "force" parameter).
+ */
+long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+			     unsigned long start, unsigned long nr_pages,
+			     int write, int force, struct page **pages)
+{
+	long ret;
+	int locked = 1;
+	down_read(&mm->mmap_sem);
+	ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+				      pages, NULL, &locked, false);
+	if (locked)
+		up_read(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(get_user_pages_unlocked);
+
 /*
  * get_user_pages() - pin user pages in memory
  * @tsk:	the task_struct to use for page fault accounting, or
@@ -624,22 +783,18 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
  * use the correct cache flushing APIs.
  *
  * See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
  */
 long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages, int write,
 		int force, struct page **pages, struct vm_area_struct **vmas)
 {
-	int flags = FOLL_TOUCH;
-
-	if (pages)
-		flags |= FOLL_GET;
-	if (write)
-		flags |= FOLL_WRITE;
-	if (force)
-		flags |= FOLL_FORCE;
-
-	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
-				NULL);
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+				       pages, vmas, NULL, false);
 }
 EXPORT_SYMBOL(get_user_pages);
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 541bed64e34..bfb690b0f98 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -214,6 +214,29 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 }
 EXPORT_SYMBOL(get_user_pages);
 
+long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   int write, int force, struct page **pages,
+			   int *locked)
+{
+	return get_user_pages(tsk, mm, start, nr_pages, write, force,
+			      pages, NULL);
+}
+EXPORT_SYMBOL(get_user_pages_locked);
+
+long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+			     unsigned long start, unsigned long nr_pages,
+			     int write, int force, struct page **pages)
+{
+	long ret;
+	down_read(&mm->mmap_sem);
+	ret = get_user_pages(tsk, mm, start, nr_pages, write, force,
+			     pages, NULL);
+	up_read(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(get_user_pages_unlocked);
+
 /**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
-- 
cgit v1.2.3-70-g09d2


From 0fd71a56f41d4ffabeda1dae9ff5ed4f34d4e935 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Wed, 11 Feb 2015 15:27:20 -0800
Subject: mm: gup: add __get_user_pages_unlocked to customize gup_flags

Some callers (like KVM) may want to set the gup_flags like FOLL_HWPOSION
to get a proper -EHWPOSION retval instead of -EFAULT to take a more
appropriate action if get_user_pages runs into a memory failure.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  4 ++++
 mm/gup.c           | 44 ++++++++++++++++++++++++++++++++------------
 mm/nommu.c         | 16 +++++++++++++---
 3 files changed, 49 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fc499e67547..3696b3bd1d7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1265,6 +1265,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 		    unsigned long start, unsigned long nr_pages,
 		    int write, int force, struct page **pages,
 		    int *locked);
+long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+			       unsigned long start, unsigned long nr_pages,
+			       int write, int force, struct page **pages,
+			       unsigned int gup_flags);
 long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 		    unsigned long start, unsigned long nr_pages,
 		    int write, int force, struct page **pages);
diff --git a/mm/gup.c b/mm/gup.c
index 71a37738a32..dad5875fb76 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -582,9 +582,9 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 						int write, int force,
 						struct page **pages,
 						struct vm_area_struct **vmas,
-						int *locked, bool notify_drop)
+						int *locked, bool notify_drop,
+						unsigned int flags)
 {
-	int flags = FOLL_TOUCH;
 	long ret, pages_done;
 	bool lock_dropped;
 
@@ -698,10 +698,36 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 			   int *locked)
 {
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				       pages, NULL, locked, true);
+				       pages, NULL, locked, true, FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages_locked);
 
+/*
+ * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows to
+ * pass additional gup_flags as last parameter (like FOLL_HWPOISON).
+ *
+ * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the
+ * caller if required (just like with __get_user_pages). "FOLL_GET",
+ * "FOLL_WRITE" and "FOLL_FORCE" are set implicitly as needed
+ * according to the parameters "pages", "write", "force"
+ * respectively.
+ */
+__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+					       unsigned long start, unsigned long nr_pages,
+					       int write, int force, struct page **pages,
+					       unsigned int gup_flags)
+{
+	long ret;
+	int locked = 1;
+	down_read(&mm->mmap_sem);
+	ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
+				      pages, NULL, &locked, false, gup_flags);
+	if (locked)
+		up_read(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(__get_user_pages_unlocked);
+
 /*
  * get_user_pages_unlocked() is suitable to replace the form:
  *
@@ -723,14 +749,8 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 			     unsigned long start, unsigned long nr_pages,
 			     int write, int force, struct page **pages)
 {
-	long ret;
-	int locked = 1;
-	down_read(&mm->mmap_sem);
-	ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				      pages, NULL, &locked, false);
-	if (locked)
-		up_read(&mm->mmap_sem);
-	return ret;
+	return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write,
+					 force, pages, FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
@@ -794,7 +814,7 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		int force, struct page **pages, struct vm_area_struct **vmas)
 {
 	return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force,
-				       pages, vmas, NULL, false);
+				       pages, vmas, NULL, false, FOLL_TOUCH);
 }
 EXPORT_SYMBOL(get_user_pages);
 
diff --git a/mm/nommu.c b/mm/nommu.c
index bfb690b0f98..4d1b8a19986 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -224,9 +224,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm,
 }
 EXPORT_SYMBOL(get_user_pages_locked);
 
-long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
-			     unsigned long start, unsigned long nr_pages,
-			     int write, int force, struct page **pages)
+long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+			       unsigned long start, unsigned long nr_pages,
+			       int write, int force, struct page **pages,
+			       unsigned int gup_flags)
 {
 	long ret;
 	down_read(&mm->mmap_sem);
@@ -235,6 +236,15 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
 	up_read(&mm->mmap_sem);
 	return ret;
 }
+EXPORT_SYMBOL(__get_user_pages_unlocked);
+
+long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm,
+			     unsigned long start, unsigned long nr_pages,
+			     int write, int force, struct page **pages)
+{
+	return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write,
+					 force, pages, 0);
+}
 EXPORT_SYMBOL(get_user_pages_unlocked);
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 0664e57ff0c68cbca012a45a38288fa277eb6795 Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Wed, 11 Feb 2015 15:27:28 -0800
Subject: mm: gup: kvm use get_user_pages_unlocked

Use the more generic get_user_pages_unlocked which has the additional
benefit of passing FAULT_FLAG_ALLOW_RETRY at the very first page fault
(which allows the first page fault in an unmapped area to be always able
to block indefinitely by being allowed to release the mmap_sem).

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Peter Feiner <pfeiner@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kvm_host.h | 11 -----------
 virt/kvm/async_pf.c      |  2 +-
 virt/kvm/kvm_main.c      | 50 ++++--------------------------------------------
 3 files changed, 5 insertions(+), 58 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 26f106022c8..d189ee098aa 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -200,17 +200,6 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-/*
- * Carry out a gup that requires IO. Allow the mm to relinquish the mmap
- * semaphore if the filemap/swap has to wait on a page lock. pagep == NULL
- * controls whether we retry the gup one more time to completion in that case.
- * Typically this is called after a FAULT_FLAG_RETRY_NOWAIT in the main tdp
- * handler.
- */
-int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm,
-			 unsigned long addr, bool write_fault,
-			 struct page **pagep);
-
 enum {
 	OUTSIDE_GUEST_MODE,
 	IN_GUEST_MODE,
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 5ff7f7f2689..44660aee335 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -80,7 +80,7 @@ static void async_pf_execute(struct work_struct *work)
 
 	might_sleep();
 
-	kvm_get_user_page_io(NULL, mm, addr, 1, NULL);
+	get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL);
 	kvm_async_page_present_sync(vcpu, apf);
 
 	spin_lock(&vcpu->async_pf.lock);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1cc6e2e1998..458b9b14b15 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1128,43 +1128,6 @@ static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
 	return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL);
 }
 
-int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm,
-			 unsigned long addr, bool write_fault,
-			 struct page **pagep)
-{
-	int npages;
-	int locked = 1;
-	int flags = FOLL_TOUCH | FOLL_HWPOISON |
-		    (pagep ? FOLL_GET : 0) |
-		    (write_fault ? FOLL_WRITE : 0);
-
-	/*
-	 * If retrying the fault, we get here *not* having allowed the filemap
-	 * to wait on the page lock. We should now allow waiting on the IO with
-	 * the mmap semaphore released.
-	 */
-	down_read(&mm->mmap_sem);
-	npages = __get_user_pages(tsk, mm, addr, 1, flags, pagep, NULL,
-				  &locked);
-	if (!locked) {
-		VM_BUG_ON(npages);
-
-		if (!pagep)
-			return 0;
-
-		/*
-		 * The previous call has now waited on the IO. Now we can
-		 * retry and complete. Pass TRIED to ensure we do not re
-		 * schedule async IO (see e.g. filemap_fault).
-		 */
-		down_read(&mm->mmap_sem);
-		npages = __get_user_pages(tsk, mm, addr, 1, flags | FOLL_TRIED,
-					  pagep, NULL, NULL);
-	}
-	up_read(&mm->mmap_sem);
-	return npages;
-}
-
 static inline int check_user_page_hwpoison(unsigned long addr)
 {
 	int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE;
@@ -1227,15 +1190,10 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 		npages = get_user_page_nowait(current, current->mm,
 					      addr, write_fault, page);
 		up_read(&current->mm->mmap_sem);
-	} else {
-		/*
-		 * By now we have tried gup_fast, and possibly async_pf, and we
-		 * are certainly not atomic. Time to retry the gup, allowing
-		 * mmap semaphore to be relinquished in the case of IO.
-		 */
-		npages = kvm_get_user_page_io(current, current->mm, addr,
-					      write_fault, page);
-	}
+	} else
+		npages = __get_user_pages_unlocked(current, current->mm, addr, 1,
+						   write_fault, 0, page,
+						   FOLL_TOUCH|FOLL_HWPOISON);
 	if (npages != 1)
 		return npages;
 
-- 
cgit v1.2.3-70-g09d2


From 0b1fbfe50006c41014cc25660c0e735d21c34939 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Wed, 11 Feb 2015 15:27:34 -0800
Subject: mm/pagewalk: remove pgd_entry() and pud_entry()

Currently no user of page table walker sets ->pgd_entry() or
->pud_entry(), so checking their existence in each loop is just wasting
CPU cycle.  So let's remove it to reduce overhead.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 6 ------
 mm/pagewalk.c      | 9 ++-------
 2 files changed, 2 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3696b3bd1d7..f6106d3f3da 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1164,8 +1164,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 
 /**
  * mm_walk - callbacks for walk_page_range
- * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
- * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
  * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
  *	       this handler is required to be able to handle
  *	       pmd_trans_huge() pmds.  They may simply choose to
@@ -1179,10 +1177,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
  * (see walk_page_range for more details)
  */
 struct mm_walk {
-	int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
-			 unsigned long next, struct mm_walk *walk);
-	int (*pud_entry)(pud_t *pud, unsigned long addr,
-	                 unsigned long next, struct mm_walk *walk);
 	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
 			 unsigned long next, struct mm_walk *walk);
 	int (*pte_entry)(pte_t *pte, unsigned long addr,
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index b264bda46e1..b793ef149da 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -86,9 +86,7 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 				break;
 			continue;
 		}
-		if (walk->pud_entry)
-			err = walk->pud_entry(pud, addr, next, walk);
-		if (!err && (walk->pmd_entry || walk->pte_entry))
+		if (walk->pmd_entry || walk->pte_entry)
 			err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
@@ -237,10 +235,7 @@ int walk_page_range(unsigned long addr, unsigned long end,
 			pgd++;
 			continue;
 		}
-		if (walk->pgd_entry)
-			err = walk->pgd_entry(pgd, addr, next, walk);
-		if (!err &&
-		    (walk->pud_entry || walk->pmd_entry || walk->pte_entry))
+		if (walk->pmd_entry || walk->pte_entry)
 			err = walk_pud_range(pgd, addr, next, walk);
 		if (err)
 			break;
-- 
cgit v1.2.3-70-g09d2


From fafaa4264eba49fd10695c193a82760558d093f4 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Wed, 11 Feb 2015 15:27:37 -0800
Subject: pagewalk: improve vma handling

Current implementation of page table walker has a fundamental problem in
vma handling, which started when we tried to handle vma(VM_HUGETLB).
Because it's done in pgd loop, considering vma boundary makes code
complicated and bug-prone.

From the users viewpoint, some user checks some vma-related condition to
determine whether the user really does page walk over the vma.

In order to solve these, this patch moves vma check outside pgd loop and
introduce a new callback ->test_walk().

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  15 +++-
 mm/pagewalk.c      | 206 ++++++++++++++++++++++++++++++-----------------------
 2 files changed, 129 insertions(+), 92 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f6106d3f3da..3891a368e5e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1171,10 +1171,16 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
  * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
  * @pte_hole: if set, called for each hole at all levels
  * @hugetlb_entry: if set, called for each hugetlb entry
- *		   *Caution*: The caller must hold mmap_sem() if @hugetlb_entry
- * 			      is used.
+ * @test_walk: caller specific callback function to determine whether
+ *             we walk over the current vma or not. A positive returned
+ *             value means "do page table walk over the current vma,"
+ *             and a negative one means "abort current page table walk
+ *             right now." 0 means "skip the current vma."
+ * @mm:        mm_struct representing the target process of page table walk
+ * @vma:       vma currently walked (NULL if walking outside vmas)
+ * @private:   private data for callbacks' usage
  *
- * (see walk_page_range for more details)
+ * (see the comment on walk_page_range() for more details)
  */
 struct mm_walk {
 	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
@@ -1186,7 +1192,10 @@ struct mm_walk {
 	int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
 			     unsigned long addr, unsigned long next,
 			     struct mm_walk *walk);
+	int (*test_walk)(unsigned long addr, unsigned long next,
+			struct mm_walk *walk);
 	struct mm_struct *mm;
+	struct vm_area_struct *vma;
 	void *private;
 };
 
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index b793ef149da..d9cc3caae80 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -59,7 +59,7 @@ again:
 			continue;
 
 		split_huge_page_pmd_mm(walk->mm, addr, pmd);
-		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
+		if (pmd_trans_unstable(pmd))
 			goto again;
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
@@ -95,6 +95,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	return err;
 }
 
+static int walk_pgd_range(unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	int err = 0;
+
+	pgd = pgd_offset(walk->mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none_or_clear_bad(pgd)) {
+			if (walk->pte_hole)
+				err = walk->pte_hole(addr, next, walk);
+			if (err)
+				break;
+			continue;
+		}
+		if (walk->pmd_entry || walk->pte_entry)
+			err = walk_pud_range(pgd, addr, next, walk);
+		if (err)
+			break;
+	} while (pgd++, addr = next, addr != end);
+
+	return err;
+}
+
 #ifdef CONFIG_HUGETLB_PAGE
 static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
 				       unsigned long end)
@@ -103,10 +129,10 @@ static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
 	return boundary < end ? boundary : end;
 }
 
-static int walk_hugetlb_range(struct vm_area_struct *vma,
-			      unsigned long addr, unsigned long end,
+static int walk_hugetlb_range(unsigned long addr, unsigned long end,
 			      struct mm_walk *walk)
 {
+	struct vm_area_struct *vma = walk->vma;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long next;
 	unsigned long hmask = huge_page_mask(h);
@@ -119,15 +145,14 @@ static int walk_hugetlb_range(struct vm_area_struct *vma,
 		if (pte && walk->hugetlb_entry)
 			err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
 		if (err)
-			return err;
+			break;
 	} while (addr = next, addr != end);
 
-	return 0;
+	return err;
 }
 
 #else /* CONFIG_HUGETLB_PAGE */
-static int walk_hugetlb_range(struct vm_area_struct *vma,
-			      unsigned long addr, unsigned long end,
+static int walk_hugetlb_range(unsigned long addr, unsigned long end,
 			      struct mm_walk *walk)
 {
 	return 0;
@@ -135,112 +160,115 @@ static int walk_hugetlb_range(struct vm_area_struct *vma,
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
+/*
+ * Decide whether we really walk over the current vma on [@start, @end)
+ * or skip it via the returned value. Return 0 if we do walk over the
+ * current vma, and return 1 if we skip the vma. Negative values means
+ * error, where we abort the current walk.
+ *
+ * Default check (only VM_PFNMAP check for now) is used when the caller
+ * doesn't define test_walk() callback.
+ */
+static int walk_page_test(unsigned long start, unsigned long end,
+			struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
 
+	if (walk->test_walk)
+		return walk->test_walk(start, end, walk);
+
+	/*
+	 * Do not walk over vma(VM_PFNMAP), because we have no valid struct
+	 * page backing a VM_PFNMAP range. See also commit a9ff785e4437.
+	 */
+	if (vma->vm_flags & VM_PFNMAP)
+		return 1;
+	return 0;
+}
+
+static int __walk_page_range(unsigned long start, unsigned long end,
+			struct mm_walk *walk)
+{
+	int err = 0;
+	struct vm_area_struct *vma = walk->vma;
+
+	if (vma && is_vm_hugetlb_page(vma)) {
+		if (walk->hugetlb_entry)
+			err = walk_hugetlb_range(start, end, walk);
+	} else
+		err = walk_pgd_range(start, end, walk);
+
+	return err;
+}
 
 /**
- * walk_page_range - walk a memory map's page tables with a callback
- * @addr: starting address
- * @end: ending address
- * @walk: set of callbacks to invoke for each level of the tree
- *
- * Recursively walk the page table for the memory area in a VMA,
- * calling supplied callbacks. Callbacks are called in-order (first
- * PGD, first PUD, first PMD, first PTE, second PTE... second PMD,
- * etc.). If lower-level callbacks are omitted, walking depth is reduced.
+ * walk_page_range - walk page table with caller specific callbacks
  *
- * Each callback receives an entry pointer and the start and end of the
- * associated range, and a copy of the original mm_walk for access to
- * the ->private or ->mm fields.
+ * Recursively walk the page table tree of the process represented by @walk->mm
+ * within the virtual address range [@start, @end). During walking, we can do
+ * some caller-specific works for each entry, by setting up pmd_entry(),
+ * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these
+ * callbacks, the associated entries/pages are just ignored.
+ * The return values of these callbacks are commonly defined like below:
+ *  - 0  : succeeded to handle the current entry, and if you don't reach the
+ *         end address yet, continue to walk.
+ *  - >0 : succeeded to handle the current entry, and return to the caller
+ *         with caller specific value.
+ *  - <0 : failed to handle the current entry, and return to the caller
+ *         with error code.
  *
- * Usually no locks are taken, but splitting transparent huge page may
- * take page table lock. And the bottom level iterator will map PTE
- * directories from highmem if necessary.
+ * Before starting to walk page table, some callers want to check whether
+ * they really want to walk over the current vma, typically by checking
+ * its vm_flags. walk_page_test() and @walk->test_walk() are used for this
+ * purpose.
  *
- * If any callback returns a non-zero value, the walk is aborted and
- * the return value is propagated back to the caller. Otherwise 0 is returned.
+ * struct mm_walk keeps current values of some common data like vma and pmd,
+ * which are useful for the access from callbacks. If you want to pass some
+ * caller-specific data to callbacks, @walk->private should be helpful.
  *
- * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry
- * is !NULL.
+ * Locking:
+ *   Callers of walk_page_range() and walk_page_vma() should hold
+ *   @walk->mm->mmap_sem, because these function traverse vma list and/or
+ *   access to vma's data.
  */
-int walk_page_range(unsigned long addr, unsigned long end,
+int walk_page_range(unsigned long start, unsigned long end,
 		    struct mm_walk *walk)
 {
-	pgd_t *pgd;
-	unsigned long next;
 	int err = 0;
+	unsigned long next;
+	struct vm_area_struct *vma;
 
-	if (addr >= end)
-		return err;
+	if (start >= end)
+		return -EINVAL;
 
 	if (!walk->mm)
 		return -EINVAL;
 
 	VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm);
 
-	pgd = pgd_offset(walk->mm, addr);
+	vma = find_vma(walk->mm, start);
 	do {
-		struct vm_area_struct *vma = NULL;
+		if (!vma) { /* after the last vma */
+			walk->vma = NULL;
+			next = end;
+		} else if (start < vma->vm_start) { /* outside vma */
+			walk->vma = NULL;
+			next = min(end, vma->vm_start);
+		} else { /* inside vma */
+			walk->vma = vma;
+			next = min(end, vma->vm_end);
+			vma = vma->vm_next;
 
-		next = pgd_addr_end(addr, end);
-
-		/*
-		 * This function was not intended to be vma based.
-		 * But there are vma special cases to be handled:
-		 * - hugetlb vma's
-		 * - VM_PFNMAP vma's
-		 */
-		vma = find_vma(walk->mm, addr);
-		if (vma) {
-			/*
-			 * There are no page structures backing a VM_PFNMAP
-			 * range, so do not allow split_huge_page_pmd().
-			 */
-			if ((vma->vm_start <= addr) &&
-			    (vma->vm_flags & VM_PFNMAP)) {
-				if (walk->pte_hole)
-					err = walk->pte_hole(addr, next, walk);
-				if (err)
-					break;
-				pgd = pgd_offset(walk->mm, next);
+			err = walk_page_test(start, next, walk);
+			if (err > 0)
 				continue;
-			}
-			/*
-			 * Handle hugetlb vma individually because pagetable
-			 * walk for the hugetlb page is dependent on the
-			 * architecture and we can't handled it in the same
-			 * manner as non-huge pages.
-			 */
-			if (walk->hugetlb_entry && (vma->vm_start <= addr) &&
-			    is_vm_hugetlb_page(vma)) {
-				if (vma->vm_end < next)
-					next = vma->vm_end;
-				/*
-				 * Hugepage is very tightly coupled with vma,
-				 * so walk through hugetlb entries within a
-				 * given vma.
-				 */
-				err = walk_hugetlb_range(vma, addr, next, walk);
-				if (err)
-					break;
-				pgd = pgd_offset(walk->mm, next);
-				continue;
-			}
-		}
-
-		if (pgd_none_or_clear_bad(pgd)) {
-			if (walk->pte_hole)
-				err = walk->pte_hole(addr, next, walk);
-			if (err)
+			if (err < 0)
 				break;
-			pgd++;
-			continue;
 		}
-		if (walk->pmd_entry || walk->pte_entry)
-			err = walk_pud_range(pgd, addr, next, walk);
+		if (walk->vma || walk->pte_hole)
+			err = __walk_page_range(start, next, walk);
 		if (err)
 			break;
-		pgd++;
-	} while (addr = next, addr < end);
-
+	} while (start = next, start < end);
 	return err;
 }
-- 
cgit v1.2.3-70-g09d2


From 900fc5f197b05253ae9433fb9a066c3f37d08f69 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Wed, 11 Feb 2015 15:27:40 -0800
Subject: pagewalk: add walk_page_vma()

Introduce walk_page_vma(), which is useful for the callers which want to
walk over a given vma.  It's used by later patches.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  1 +
 mm/pagewalk.c      | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3891a368e5e..a4d24f3c543 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1201,6 +1201,7 @@ struct mm_walk {
 
 int walk_page_range(unsigned long addr, unsigned long end,
 		struct mm_walk *walk);
+int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk);
 void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index d9cc3caae80..4c9a653ba56 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -272,3 +272,21 @@ int walk_page_range(unsigned long start, unsigned long end,
 	} while (start = next, start < end);
 	return err;
 }
+
+int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk)
+{
+	int err;
+
+	if (!walk->mm)
+		return -EINVAL;
+
+	VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
+	VM_BUG_ON(!vma);
+	walk->vma = vma;
+	err = walk_page_test(vma->vm_start, vma->vm_end, walk);
+	if (err > 0)
+		return 0;
+	if (err < 0)
+		return err;
+	return __walk_page_range(vma->vm_start, vma->vm_end, walk);
+}
-- 
cgit v1.2.3-70-g09d2


From 99592d598eca62bdbbf62b59941c189176dfc614 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 11 Feb 2015 15:28:15 -0800
Subject: mm: when stealing freepages, also take pages created by splitting
 buddy page

When studying page stealing, I noticed some weird looking decisions in
try_to_steal_freepages().  The first I assume is a bug (Patch 1), the
following two patches were driven by evaluation.

Testing was done with stress-highalloc of mmtests, using the
mm_page_alloc_extfrag tracepoint and postprocessing to get counts of how
often page stealing occurs for individual migratetypes, and what
migratetypes are used for fallbacks.  Arguably, the worst case of page
stealing is when UNMOVABLE allocation steals from MOVABLE pageblock.
RECLAIMABLE allocation stealing from MOVABLE allocation is also not ideal,
so the goal is to minimize these two cases.

The evaluation of v2 wasn't always clear win and Joonsoo questioned the
results.  Here I used different baseline which includes RFC compaction
improvements from [1].  I found that the compaction improvements reduce
variability of stress-highalloc, so there's less noise in the data.

First, let's look at stress-highalloc configured to do sync compaction,
and how these patches reduce page stealing events during the test.  First
column is after fresh reboot, other two are reiterations of test without
reboot.  That was all accumulater over 5 re-iterations (so the benchmark
was run 5x3 times with 5 fresh restarts).

Baseline:

                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                  5-nothp-1       5-nothp-2       5-nothp-3
Page alloc extfrag event                               10264225     8702233    10244125
Extfrag fragmenting                                    10263271     8701552    10243473
Extfrag fragmenting for unmovable                         13595       17616       15960
Extfrag fragmenting unmovable placed with movable          7989       12193        8447
Extfrag fragmenting for reclaimable                         658        1840        1817
Extfrag fragmenting reclaimable placed with movable         558        1677        1679
Extfrag fragmenting for movable                        10249018     8682096    10225696

With Patch 1:
                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                  6-nothp-1       6-nothp-2       6-nothp-3
Page alloc extfrag event                               11834954     9877523     9774860
Extfrag fragmenting                                    11833993     9876880     9774245
Extfrag fragmenting for unmovable                          7342       16129       11712
Extfrag fragmenting unmovable placed with movable          4191       10547        6270
Extfrag fragmenting for reclaimable                         373        1130         923
Extfrag fragmenting reclaimable placed with movable         302         906         738
Extfrag fragmenting for movable                        11826278     9859621     9761610

With Patch 2:
                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                  7-nothp-1       7-nothp-2       7-nothp-3
Page alloc extfrag event                                4725990     3668793     3807436
Extfrag fragmenting                                     4725104     3668252     3806898
Extfrag fragmenting for unmovable                          6678        7974        7281
Extfrag fragmenting unmovable placed with movable          2051        3829        4017
Extfrag fragmenting for reclaimable                         429        1208        1278
Extfrag fragmenting reclaimable placed with movable         369         976        1034
Extfrag fragmenting for movable                         4717997     3659070     3798339

With Patch 3:
                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                  8-nothp-1       8-nothp-2       8-nothp-3
Page alloc extfrag event                                5016183     4700142     3850633
Extfrag fragmenting                                     5015325     4699613     3850072
Extfrag fragmenting for unmovable                          1312        3154        3088
Extfrag fragmenting unmovable placed with movable          1115        2777        2714
Extfrag fragmenting for reclaimable                         437        1193        1097
Extfrag fragmenting reclaimable placed with movable         330         969         879
Extfrag fragmenting for movable                         5013576     4695266     3845887

In v2 we've seen apparent regression with Patch 1 for unmovable events,
this is now gone, suggesting it was indeed noise.  Here, each patch
improves the situation for unmovable events.  Reclaimable is improved by
patch 1 and then either the same modulo noise, or perhaps sligtly worse -
a small price for unmovable improvements, IMHO.  The number of movable
allocations falling back to other migratetypes is most noisy, but it's
reduced to half at Patch 2 nevertheless.  These are least critical as
compaction can move them around.

If we look at success rates, the patches don't affect them, that didn't change.

Baseline:
                             3.19-rc4              3.19-rc4              3.19-rc4
                            5-nothp-1             5-nothp-2             5-nothp-3
Success 1 Min         49.00 (  0.00%)       42.00 ( 14.29%)       41.00 ( 16.33%)
Success 1 Mean        51.00 (  0.00%)       45.00 ( 11.76%)       42.60 ( 16.47%)
Success 1 Max         55.00 (  0.00%)       51.00 (  7.27%)       46.00 ( 16.36%)
Success 2 Min         53.00 (  0.00%)       47.00 ( 11.32%)       44.00 ( 16.98%)
Success 2 Mean        59.60 (  0.00%)       50.80 ( 14.77%)       48.20 ( 19.13%)
Success 2 Max         64.00 (  0.00%)       56.00 ( 12.50%)       52.00 ( 18.75%)
Success 3 Min         84.00 (  0.00%)       82.00 (  2.38%)       78.00 (  7.14%)
Success 3 Mean        85.60 (  0.00%)       82.80 (  3.27%)       79.40 (  7.24%)
Success 3 Max         86.00 (  0.00%)       83.00 (  3.49%)       80.00 (  6.98%)

Patch 1:
                             3.19-rc4              3.19-rc4              3.19-rc4
                            6-nothp-1             6-nothp-2             6-nothp-3
Success 1 Min         49.00 (  0.00%)       44.00 ( 10.20%)       44.00 ( 10.20%)
Success 1 Mean        51.80 (  0.00%)       46.00 ( 11.20%)       45.80 ( 11.58%)
Success 1 Max         54.00 (  0.00%)       49.00 (  9.26%)       49.00 (  9.26%)
Success 2 Min         58.00 (  0.00%)       49.00 ( 15.52%)       48.00 ( 17.24%)
Success 2 Mean        60.40 (  0.00%)       51.80 ( 14.24%)       50.80 ( 15.89%)
Success 2 Max         63.00 (  0.00%)       54.00 ( 14.29%)       55.00 ( 12.70%)
Success 3 Min         84.00 (  0.00%)       81.00 (  3.57%)       79.00 (  5.95%)
Success 3 Mean        85.00 (  0.00%)       81.60 (  4.00%)       79.80 (  6.12%)
Success 3 Max         86.00 (  0.00%)       82.00 (  4.65%)       82.00 (  4.65%)

Patch 2:

                             3.19-rc4              3.19-rc4              3.19-rc4
                            7-nothp-1             7-nothp-2             7-nothp-3
Success 1 Min         50.00 (  0.00%)       44.00 ( 12.00%)       39.00 ( 22.00%)
Success 1 Mean        52.80 (  0.00%)       45.60 ( 13.64%)       42.40 ( 19.70%)
Success 1 Max         55.00 (  0.00%)       46.00 ( 16.36%)       47.00 ( 14.55%)
Success 2 Min         52.00 (  0.00%)       48.00 (  7.69%)       45.00 ( 13.46%)
Success 2 Mean        53.40 (  0.00%)       49.80 (  6.74%)       48.80 (  8.61%)
Success 2 Max         57.00 (  0.00%)       52.00 (  8.77%)       52.00 (  8.77%)
Success 3 Min         84.00 (  0.00%)       81.00 (  3.57%)       79.00 (  5.95%)
Success 3 Mean        85.00 (  0.00%)       82.40 (  3.06%)       79.60 (  6.35%)
Success 3 Max         86.00 (  0.00%)       83.00 (  3.49%)       80.00 (  6.98%)

Patch 3:
                             3.19-rc4              3.19-rc4              3.19-rc4
                            8-nothp-1             8-nothp-2             8-nothp-3
Success 1 Min         46.00 (  0.00%)       44.00 (  4.35%)       42.00 (  8.70%)
Success 1 Mean        50.20 (  0.00%)       45.60 (  9.16%)       44.00 ( 12.35%)
Success 1 Max         52.00 (  0.00%)       47.00 (  9.62%)       47.00 (  9.62%)
Success 2 Min         53.00 (  0.00%)       49.00 (  7.55%)       48.00 (  9.43%)
Success 2 Mean        55.80 (  0.00%)       50.60 (  9.32%)       49.00 ( 12.19%)
Success 2 Max         59.00 (  0.00%)       52.00 ( 11.86%)       51.00 ( 13.56%)
Success 3 Min         84.00 (  0.00%)       80.00 (  4.76%)       79.00 (  5.95%)
Success 3 Mean        85.40 (  0.00%)       81.60 (  4.45%)       80.40 (  5.85%)
Success 3 Max         87.00 (  0.00%)       83.00 (  4.60%)       82.00 (  5.75%)

While there's no improvement here, I consider reduced fragmentation events
to be worth on its own.  Patch 2 also seems to reduce scanning for free
pages, and migrations in compaction, suggesting it has somewhat less work
to do:

Patch 1:

Compaction stalls                 4153        3959        3978
Compaction success                1523        1441        1446
Compaction failures               2630        2517        2531
Page migrate success           4600827     4943120     5104348
Page migrate failure             19763       16656       17806
Compaction pages isolated      9597640    10305617    10653541
Compaction migrate scanned    77828948    86533283    87137064
Compaction free scanned      517758295   521312840   521462251
Compaction cost                   5503        5932        6110

Patch 2:

Compaction stalls                 3800        3450        3518
Compaction success                1421        1316        1317
Compaction failures               2379        2134        2201
Page migrate success           4160421     4502708     4752148
Page migrate failure             19705       14340       14911
Compaction pages isolated      8731983     9382374     9910043
Compaction migrate scanned    98362797    96349194    98609686
Compaction free scanned      496512560   469502017   480442545
Compaction cost                   5173        5526        5811

As with v2, /proc/pagetypeinfo appears unaffected with respect to numbers
of unmovable and reclaimable pageblocks.

Configuring the benchmark to allocate like THP page fault (i.e.  no sync
compaction) gives much noisier results for iterations 2 and 3 after
reboot.  This is not so surprising given how [1] offers lower improvements
in this scenario due to less restarts after deferred compaction which
would change compaction pivot.

Baseline:
                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                    5-thp-1         5-thp-2         5-thp-3
Page alloc extfrag event                                8148965     6227815     6646741
Extfrag fragmenting                                     8147872     6227130     6646117
Extfrag fragmenting for unmovable                         10324       12942       15975
Extfrag fragmenting unmovable placed with movable          5972        8495       10907
Extfrag fragmenting for reclaimable                         601        1707        2210
Extfrag fragmenting reclaimable placed with movable         520        1570        2000
Extfrag fragmenting for movable                         8136947     6212481     6627932

Patch 1:
                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                    6-thp-1         6-thp-2         6-thp-3
Page alloc extfrag event                                8345457     7574471     7020419
Extfrag fragmenting                                     8343546     7573777     7019718
Extfrag fragmenting for unmovable                         10256       18535       30716
Extfrag fragmenting unmovable placed with movable          6893       11726       22181
Extfrag fragmenting for reclaimable                         465        1208        1023
Extfrag fragmenting reclaimable placed with movable         353         996         843
Extfrag fragmenting for movable                         8332825     7554034     6987979

Patch 2:
                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                    7-thp-1         7-thp-2         7-thp-3
Page alloc extfrag event                                3512847     3020756     2891625
Extfrag fragmenting                                     3511940     3020185     2891059
Extfrag fragmenting for unmovable                          9017        6892        6191
Extfrag fragmenting unmovable placed with movable          1524        3053        2435
Extfrag fragmenting for reclaimable                         445        1081        1160
Extfrag fragmenting reclaimable placed with movable         375         918         986
Extfrag fragmenting for movable                         3502478     3012212     2883708

Patch 3:
                                                   3.19-rc4        3.19-rc4        3.19-rc4
                                                    8-thp-1         8-thp-2         8-thp-3
Page alloc extfrag event                                3181699     3082881     2674164
Extfrag fragmenting                                     3180812     3082303     2673611
Extfrag fragmenting for unmovable                          1201        4031        4040
Extfrag fragmenting unmovable placed with movable           974        3611        3645
Extfrag fragmenting for reclaimable                         478        1165        1294
Extfrag fragmenting reclaimable placed with movable         387         985        1030
Extfrag fragmenting for movable                         3179133     3077107     2668277

The improvements for first iteration are clear, the rest is much noisier
and can appear like regression for Patch 1.  Anyway, patch 2 rectifies it.

Allocation success rates are again unaffected so there's no point in
making this e-mail any longer.

[1] http://marc.info/?l=linux-mm&m=142166196321125&w=2

This patch (of 3):

When __rmqueue_fallback() is called to allocate a page of order X, it will
find a page of order Y >= X of a fallback migratetype, which is different
from the desired migratetype.  With the help of try_to_steal_freepages(),
it may change the migratetype (to the desired one) also of:

1) all currently free pages in the pageblock containing the fallback page
2) the fallback pageblock itself
3) buddy pages created by splitting the fallback page (when Y > X)

These decisions take the order Y into account, as well as the desired
migratetype, with the goal of preventing multiple fallback allocations
that could e.g.  distribute UNMOVABLE allocations among multiple
pageblocks.

Originally, decision for 1) has implied the decision for 3).  Commit
47118af076f6 ("mm: mmzone: MIGRATE_CMA migration type added") changed that
(probably unintentionally) so that the buddy pages in case 3) are always
changed to the desired migratetype, except for CMA pageblocks.

Commit fef903efcf0c ("mm/page_allo.c: restructure free-page stealing code
and fix a bug") did some refactoring and added a comment that the case of
3) is intended.  Commit 0cbef29a7821 ("mm: __rmqueue_fallback() should
respect pageblock type") removed the comment and tried to restore the
original behavior where 1) implies 3), but due to the previous
refactoring, the result is instead that only 2) implies 3) - and the
conditions for 2) are less frequently met than conditions for 1).  This
may increase fragmentation in situations where the code decides to steal
all free pages from the pageblock (case 1)), but then gives back the buddy
pages produced by splitting.

This patch restores the original intended logic where 1) implies 3).
During testing with stress-highalloc from mmtests, this has shown to
decrease the number of events where UNMOVABLE and RECLAIMABLE allocations
steal from MOVABLE pageblocks, which can lead to permanent fragmentation.
In some cases it has increased the number of events when MOVABLE
allocations steal from UNMOVABLE or RECLAIMABLE pageblocks, but these are
fixable by sync compaction and thus less harmful.

Note that evaluation has shown that the behavior introduced by
47118af076f6 for buddy pages in case 3) is actually even better than the
original logic, so the following patch will introduce it properly once
again.  For stable backports of this patch it makes thus sense to only fix
versions containing 0cbef29a7821.

[iamjoonsoo.kim@lge.com: tracepoint fix]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: <stable@vger.kernel.org>	[3.13+ containing 0cbef29a7821]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/trace/events/kmem.h |  7 ++++---
 mm/page_alloc.c             | 12 +++++-------
 2 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index aece1346ceb..4ad10baecd4 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -268,11 +268,11 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 
 	TP_PROTO(struct page *page,
 		int alloc_order, int fallback_order,
-		int alloc_migratetype, int fallback_migratetype, int new_migratetype),
+		int alloc_migratetype, int fallback_migratetype),
 
 	TP_ARGS(page,
 		alloc_order, fallback_order,
-		alloc_migratetype, fallback_migratetype, new_migratetype),
+		alloc_migratetype, fallback_migratetype),
 
 	TP_STRUCT__entry(
 		__field(	struct page *,	page			)
@@ -289,7 +289,8 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->fallback_order		= fallback_order;
 		__entry->alloc_migratetype	= alloc_migratetype;
 		__entry->fallback_migratetype	= fallback_migratetype;
-		__entry->change_ownership	= (new_migratetype == alloc_migratetype);
+		__entry->change_ownership	= (alloc_migratetype ==
+					get_pageblock_migratetype(page));
 	),
 
 	TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 134e2552504..b7a88101935 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1131,8 +1131,8 @@ static void change_pageblock_range(struct page *pageblock_page,
  * nor move CMA pages to different free lists. We don't want unmovable pages
  * to be allocated from MIGRATE_CMA areas.
  *
- * Returns the new migratetype of the pageblock (or the same old migratetype
- * if it was unchanged).
+ * Returns the allocation migratetype if free pages were stolen, or the
+ * fallback migratetype if it was decided not to steal.
  */
 static int try_to_steal_freepages(struct zone *zone, struct page *page,
 				  int start_type, int fallback_type)
@@ -1163,12 +1163,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
 
 		/* Claim the whole block if over half of it is free */
 		if (pages >= (1 << (pageblock_order-1)) ||
-				page_group_by_mobility_disabled) {
-
+				page_group_by_mobility_disabled)
 			set_pageblock_migratetype(page, start_type);
-			return start_type;
-		}
 
+		return start_type;
 	}
 
 	return fallback_type;
@@ -1220,7 +1218,7 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
 			set_freepage_migratetype(page, new_type);
 
 			trace_mm_page_alloc_extfrag(page, order, current_order,
-				start_migratetype, migratetype, new_type);
+				start_migratetype, migratetype);
 
 			return page;
 		}
-- 
cgit v1.2.3-70-g09d2


From 94f759d62b2c6a9d124b0622077b1ddcfac43fb5 Mon Sep 17 00:00:00 2001
From: Sergei Rogachev <rogachevsergei@gmail.com>
Date: Wed, 11 Feb 2015 15:28:34 -0800
Subject: mm/page_owner.c: remove unnecessary stack_trace field

Page owner uses the page_ext structure to keep meta-information for every
page in the system.  The structure also contains a field of type 'struct
stack_trace', page owner uses this field during invocation of the function
save_stack_trace.  It is easy to notice that keeping a copy of this
structure for every page in the system is very inefficiently in terms of
memory.

The patch removes this unnecessary field of page_ext and forces page owner
to use a stack_trace structure allocated on the stack.

[akpm@linux-foundation.org: use struct initializers]
Signed-off-by: Sergei Rogachev <rogachevsergei@gmail.com>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_ext.h |  2 +-
 mm/page_owner.c          | 26 ++++++++++++++------------
 2 files changed, 15 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index d2a2c84c72d..c42981cd99a 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -40,7 +40,7 @@ struct page_ext {
 #ifdef CONFIG_PAGE_OWNER
 	unsigned int order;
 	gfp_t gfp_mask;
-	struct stack_trace trace;
+	unsigned int nr_entries;
 	unsigned long trace_entries[8];
 #endif
 };
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 9ab4a9b5bc0..0993f5f36b0 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -59,20 +59,19 @@ void __reset_page_owner(struct page *page, unsigned int order)
 
 void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
 {
-	struct page_ext *page_ext;
-	struct stack_trace *trace;
-
-	page_ext = lookup_page_ext(page);
+	struct page_ext *page_ext = lookup_page_ext(page);
+	struct stack_trace trace = {
+		.nr_entries = 0,
+		.max_entries = ARRAY_SIZE(page_ext->trace_entries),
+		.entries = &page_ext->trace_entries[0],
+		.skip = 3,
+	};
 
-	trace = &page_ext->trace;
-	trace->nr_entries = 0;
-	trace->max_entries = ARRAY_SIZE(page_ext->trace_entries);
-	trace->entries = &page_ext->trace_entries[0];
-	trace->skip = 3;
-	save_stack_trace(&page_ext->trace);
+	save_stack_trace(&trace);
 
 	page_ext->order = order;
 	page_ext->gfp_mask = gfp_mask;
+	page_ext->nr_entries = trace.nr_entries;
 
 	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
 }
@@ -84,6 +83,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 	int ret;
 	int pageblock_mt, page_mt;
 	char *kbuf;
+	struct stack_trace trace = {
+		.nr_entries = page_ext->nr_entries,
+		.entries = &page_ext->trace_entries[0],
+	};
 
 	kbuf = kmalloc(count, GFP_KERNEL);
 	if (!kbuf)
@@ -121,8 +124,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 	if (ret >= count)
 		goto err;
 
-	ret += snprint_stack_trace(kbuf + ret, count - ret,
-					&page_ext->trace, 0);
+	ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
 	if (ret >= count)
 		goto err;
 
-- 
cgit v1.2.3-70-g09d2