Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Missing cancel of work items in mac80211 MLME, from Ben Greear.

 2) Fix DMA mapping handling in iwlwifi by using coherent DMA for
    command headers, from Johannes Berg.

 3) Decrease the amount of pressure on the page allocator by using order
    1 pages less in iwlwifi, from Emmanuel Grumbach.

 4) Fix mesh PS broadcast OOPS in mac80211, from Marco Porsch.

 5) Don't forget to recalculate idle state in mac80211 monitor
    interface, from Felix Fietkau.

 6) Fix varargs in netfilter conntrack handler, from Joe Perches.

 7) Need to reset entire chip when command queue fills up in iwlwifi,
    from Emmanuel Grumbach.

 8) The TX antenna value must be valid when calibrations are performed
    in iwlwifi, fix from Dor Shaish.

 9) Don't generate netfilter audit log entries when audit is disabled,
    from Gao Feng.

10) Deal with DMA unit hang on e1000e during power state transitions,
    from Bruce Allan.

11) Remove BUILD_BUG_ON check from igb driver, from Alexander Duyck.

12) Fix lockdep warning on i2c handling of igb driver, from Carolyn
    Wyborny.

13) Fix several TTY handling issues in IRDA ircomm tty driver, from
    Peter Hurley.

14) Several QFQ packet scheduler fixes from Paolo Valente.

15) When VXLAN encapsulates on transmit, we have to reset the netfilter
    state.  From Zang MingJie.

16) Fix jiffie check in net_rx_action() so that we really cap the
    processing at 2HZ.  From Eric Dumazet.

17) Fix erroneous trigger of IP option space exhaustion, when routers
    are pre-specified and we are looking to see if we can insert a
    timestamp, we will have the space.  From David Ward.

18) Fix various issues in benet driver wrt waiting for firmware to
    finish POST after resets or errors.  From Gavin Shan and Sathya
    Perla.

19) Fix TX locking in SFC driver, from Ben Hutchings.

20) Like the VXLAN fix above, when we encap in a TUN device we have to
    reset the netfilter state.  This should fix several strange crashes
    reported by Dave Jones and others.  From Eric Dumazet.

21) Don't forget to clean up MAC address resources when shutting down a
    port in mlx4 driver, from Yan Burman.

22) Fix divide by zero in vmxnet3 driver, from Bhavesh Davda.

23) Fix device statistic regression in tg3 when the driver is using
    phylib, from Nithin Sujir.

24) Fix info leak in several netlink handlers, from Mathias Krause.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
  6lowpan: Fix endianness issue in is_addr_link_local().
  rrunner.c: fix possible memory leak in rr_init_one()
  dcbnl: fix various netlink info leaks
  rtnl: fix info leak on RTM_GETLINK request for VF devices
  bridge: fix mdb info leaks
  tg3: Update link_up flag for phylib devices
  ipv6: stop multicast forwarding to process interface scoped addresses
  bridging: fix rx_handlers return code
  netlabel: fix build problems when CONFIG_IPV6=n
  drivers/isdn: checkng length to be sure not memory overflow
  net/rds: zero last byte for strncpy
  bnx2x: Fix SFP+ misconfiguration in iSCSI boot scenario
  bnx2x: Fix intermittent long KR2 link up time
  macvlan: Set IFF_UNICAST_FLT flag to prevent unnecessary promisc mode.
  team: unsyc the devices addresses when port is removed
  bridge: add missing vid to br_mdb_get()
  Fix: sparse warning in inet_csk_prepare_forced_close
  afkey: fix a typo
  MAINTAINERS: Update qlcnic maintainers list
  netlabel: correctly list all the static label mappings
  ...

15 files changed, 229 insertions, 339 deletions

diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c
index 94ef33838bc..b775769f832 100644
--- a/drivers/net/wireless/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/dvm/sta.c
@@ -151,7 +151,7 @@ int iwl_send_add_sta(struct iwl_priv *priv,
 		       sta_id, sta->sta.addr, flags & CMD_ASYNC ?  "a" : "");
 
 	if (!(flags & CMD_ASYNC)) {
-		cmd.flags |= CMD_WANT_SKB | CMD_WANT_HCMD;
+		cmd.flags |= CMD_WANT_SKB;
 		might_sleep();
 	}
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-devtrace.h b/drivers/net/wireless/iwlwifi/iwl-devtrace.h
index 10f01793d7a..81aa91fab5a 100644
--- a/drivers/net/wireless/iwlwifi/iwl-devtrace.h
+++ b/drivers/net/wireless/iwlwifi/iwl-devtrace.h
@@ -363,7 +363,7 @@ TRACE_EVENT(iwlwifi_dev_hcmd,
 		__entry->flags = cmd->flags;
 		memcpy(__get_dynamic_array(hcmd), hdr, sizeof(*hdr));
 
-		for (i = 0; i < IWL_MAX_CMD_TFDS; i++) {
+		for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
 			if (!cmd->len[i])
 				continue;
 			memcpy((u8 *)__get_dynamic_array(hcmd) + offset,
diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c
index 6f228bb2b84..fbfd2d13711 100644
--- a/drivers/net/wireless/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/iwlwifi/iwl-drv.c
@@ -1102,7 +1102,6 @@ void iwl_drv_stop(struct iwl_drv *drv)
 
 /* shared module parameters */
 struct iwl_mod_params iwlwifi_mod_params = {
-	.amsdu_size_8K = 1,
 	.restart_fw = 1,
 	.plcp_check = true,
 	.bt_coex_active = true,
@@ -1207,7 +1206,7 @@ MODULE_PARM_DESC(11n_disable,
 	"disable 11n functionality, bitmap: 1: full, 2: agg TX, 4: agg RX");
 module_param_named(amsdu_size_8K, iwlwifi_mod_params.amsdu_size_8K,
 		   int, S_IRUGO);
-MODULE_PARM_DESC(amsdu_size_8K, "enable 8K amsdu size");
+MODULE_PARM_DESC(amsdu_size_8K, "enable 8K amsdu size (default 0)");
 module_param_named(fw_restart, iwlwifi_mod_params.restart_fw, int, S_IRUGO);
 MODULE_PARM_DESC(fw_restart, "restart firmware in case of error");
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-modparams.h b/drivers/net/wireless/iwlwifi/iwl-modparams.h
index e5e3a79eae2..2c2a729092f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/iwlwifi/iwl-modparams.h
@@ -91,7 +91,7 @@ enum iwl_power_level {
  * @sw_crypto: using hardware encryption, default = 0
  * @disable_11n: disable 11n capabilities, default = 0,
  *	use IWL_DISABLE_HT_* constants
- * @amsdu_size_8K: enable 8K amsdu size, default = 1
+ * @amsdu_size_8K: enable 8K amsdu size, default = 0
  * @restart_fw: restart firmware, default = 1
  * @plcp_check: enable plcp health check, default = true
  * @wd_disable: enable stuck queue check, default = 0
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h
index 8c7bec6b9a0..0cac2b7af78 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/iwlwifi/iwl-trans.h
@@ -186,19 +186,13 @@ struct iwl_rx_packet {
  * @CMD_ASYNC: Return right away and don't want for the response
  * @CMD_WANT_SKB: valid only with CMD_SYNC. The caller needs the buffer of the
  *	response. The caller needs to call iwl_free_resp when done.
- * @CMD_WANT_HCMD: The caller needs to get the HCMD that was sent in the
- *	response handler. Chunks flagged by %IWL_HCMD_DFL_NOCOPY won't be
- *	copied. The pointer passed to the response handler is in the transport
- *	ownership and don't need to be freed by the op_mode. This also means
- *	that the pointer is invalidated after the op_mode's handler returns.
  * @CMD_ON_DEMAND: This command is sent by the test mode pipe.
  */
 enum CMD_MODE {
 	CMD_SYNC		= 0,
 	CMD_ASYNC		= BIT(0),
 	CMD_WANT_SKB		= BIT(1),
-	CMD_WANT_HCMD		= BIT(2),
-	CMD_ON_DEMAND		= BIT(3),
+	CMD_ON_DEMAND		= BIT(2),
 };
 
 #define DEF_CMD_PAYLOAD_SIZE 320
@@ -217,7 +211,11 @@ struct iwl_device_cmd {
 
 #define TFD_MAX_PAYLOAD_SIZE (sizeof(struct iwl_device_cmd))
 
-#define IWL_MAX_CMD_TFDS	2
+/*
+ * number of transfer buffers (fragments) per transmit frame descriptor;
+ * this is just the driver's idea, the hardware supports 20
+ */
+#define IWL_MAX_CMD_TBS_PER_TFD	2
 
 /**
  * struct iwl_hcmd_dataflag - flag for each one of the chunks of the command
@@ -254,15 +252,15 @@ enum iwl_hcmd_dataflag {
  * @id: id of the host command
  */
 struct iwl_host_cmd {
-	const void *data[IWL_MAX_CMD_TFDS];
+	const void *data[IWL_MAX_CMD_TBS_PER_TFD];
 	struct iwl_rx_packet *resp_pkt;
 	unsigned long _rx_page_addr;
 	u32 _rx_page_order;
 	int handler_status;
 
 	u32 flags;
-	u16 len[IWL_MAX_CMD_TFDS];
-	u8 dataflags[IWL_MAX_CMD_TFDS];
+	u16 len[IWL_MAX_CMD_TBS_PER_TFD];
+	u8 dataflags[IWL_MAX_CMD_TBS_PER_TFD];
 	u8 id;
 };
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
index 23eebda848b..2adb61f103f 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
@@ -762,18 +762,20 @@ struct iwl_phy_context_cmd {
 #define IWL_RX_INFO_PHY_CNT 8
 #define IWL_RX_INFO_AGC_IDX 1
 #define IWL_RX_INFO_RSSI_AB_IDX 2
-#define IWL_RX_INFO_RSSI_C_IDX 3
-#define IWL_OFDM_AGC_DB_MSK 0xfe00
-#define IWL_OFDM_AGC_DB_POS 9
+#define IWL_OFDM_AGC_A_MSK 0x0000007f
+#define IWL_OFDM_AGC_A_POS 0
+#define IWL_OFDM_AGC_B_MSK 0x00003f80
+#define IWL_OFDM_AGC_B_POS 7
+#define IWL_OFDM_AGC_CODE_MSK 0x3fe00000
+#define IWL_OFDM_AGC_CODE_POS 20
 #define IWL_OFDM_RSSI_INBAND_A_MSK 0x00ff
-#define IWL_OFDM_RSSI_ALLBAND_A_MSK 0xff00
 #define IWL_OFDM_RSSI_A_POS 0
+#define IWL_OFDM_RSSI_ALLBAND_A_MSK 0xff00
+#define IWL_OFDM_RSSI_ALLBAND_A_POS 8
 #define IWL_OFDM_RSSI_INBAND_B_MSK 0xff0000
-#define IWL_OFDM_RSSI_ALLBAND_B_MSK 0xff000000
 #define IWL_OFDM_RSSI_B_POS 16
-#define IWL_OFDM_RSSI_INBAND_C_MSK 0x00ff
-#define IWL_OFDM_RSSI_ALLBAND_C_MSK 0xff00
-#define IWL_OFDM_RSSI_C_POS 0
+#define IWL_OFDM_RSSI_ALLBAND_B_MSK 0xff000000
+#define IWL_OFDM_RSSI_ALLBAND_B_POS 24
 
 /**
  * struct iwl_rx_phy_info - phy info
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c
index d3d959db03a..500f818dba0 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/iwlwifi/mvm/fw.c
@@ -79,17 +79,8 @@
 #define UCODE_VALID_OK	cpu_to_le32(0x1)
 
 /* Default calibration values for WkP - set to INIT image w/o running */
-static const u8 wkp_calib_values_bb_filter[] = { 0xbf, 0x00, 0x5f, 0x00, 0x2f,
-						 0x00, 0x18, 0x00 };
-static const u8 wkp_calib_values_rx_dc[] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f,
-					     0x7f, 0x7f, 0x7f };
-static const u8 wkp_calib_values_tx_lo[] = { 0x00, 0x00, 0x00, 0x00 };
-static const u8 wkp_calib_values_tx_iq[] = { 0xff, 0x00, 0xff, 0x00, 0x00,
-					     0x00 };
-static const u8 wkp_calib_values_rx_iq[] = { 0xff, 0x00, 0x00, 0x00 };
 static const u8 wkp_calib_values_rx_iq_skew[] = { 0x00, 0x00, 0x01, 0x00 };
 static const u8 wkp_calib_values_tx_iq_skew[] = { 0x01, 0x00, 0x00, 0x00 };
-static const u8 wkp_calib_values_xtal[] = { 0xd2, 0xd2 };
 
 struct iwl_calib_default_data {
 	u16 size;
@@ -99,12 +90,7 @@ struct iwl_calib_default_data {
 #define CALIB_SIZE_N_DATA(_buf) {.size = sizeof(_buf), .data = &_buf}
 
 static const struct iwl_calib_default_data wkp_calib_default_data[12] = {
-	[5] = CALIB_SIZE_N_DATA(wkp_calib_values_rx_dc),
-	[6] = CALIB_SIZE_N_DATA(wkp_calib_values_bb_filter),
-	[7] = CALIB_SIZE_N_DATA(wkp_calib_values_tx_lo),
-	[8] = CALIB_SIZE_N_DATA(wkp_calib_values_tx_iq),
 	[9] = CALIB_SIZE_N_DATA(wkp_calib_values_tx_iq_skew),
-	[10] = CALIB_SIZE_N_DATA(wkp_calib_values_rx_iq),
 	[11] = CALIB_SIZE_N_DATA(wkp_calib_values_rx_iq_skew),
 };
 
@@ -241,20 +227,6 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 
 	return 0;
 }
-#define IWL_HW_REV_ID_RAINBOW	0x2
-#define IWL_PROJ_TYPE_LHP	0x5
-
-static u32 iwl_mvm_build_phy_cfg(struct iwl_mvm *mvm)
-{
-	struct iwl_nvm_data *data = mvm->nvm_data;
-	/* Temp calls to static definitions, will be changed to CSR calls */
-	u8 hw_rev_id = IWL_HW_REV_ID_RAINBOW;
-	u8 project_type = IWL_PROJ_TYPE_LHP;
-
-	return data->radio_cfg_dash | (data->radio_cfg_step << 2) |
-		(hw_rev_id << 4) | ((project_type & 0x7f) << 6) |
-		(data->valid_tx_ant << 16) | (data->valid_rx_ant << 20);
-}
 
 static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm)
 {
@@ -262,7 +234,7 @@ static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm)
 	enum iwl_ucode_type ucode_type = mvm->cur_ucode;
 
 	/* Set parameters */
-	phy_cfg_cmd.phy_cfg = cpu_to_le32(iwl_mvm_build_phy_cfg(mvm));
+	phy_cfg_cmd.phy_cfg = cpu_to_le32(mvm->fw->phy_config);
 	phy_cfg_cmd.calib_control.event_trigger =
 		mvm->fw->default_calib[ucode_type].event_trigger;
 	phy_cfg_cmd.calib_control.flow_trigger =
@@ -275,103 +247,6 @@ static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm)
 				    sizeof(phy_cfg_cmd), &phy_cfg_cmd);
 }
 
-/* Starting with the new PHY DB implementation - New calibs are enabled */
-/* Value - 0x405e7 */
-#define IWL_CALIB_DEFAULT_FLOW_INIT	(IWL_CALIB_CFG_XTAL_IDX		|\
-					 IWL_CALIB_CFG_TEMPERATURE_IDX	|\
-					 IWL_CALIB_CFG_VOLTAGE_READ_IDX	|\
-					 IWL_CALIB_CFG_DC_IDX		|\
-					 IWL_CALIB_CFG_BB_FILTER_IDX	|\
-					 IWL_CALIB_CFG_LO_LEAKAGE_IDX	|\
-					 IWL_CALIB_CFG_TX_IQ_IDX	|\
-					 IWL_CALIB_CFG_RX_IQ_IDX	|\
-					 IWL_CALIB_CFG_AGC_IDX)
-
-#define IWL_CALIB_DEFAULT_EVENT_INIT	0x0
-
-/* Value 0x41567 */
-#define IWL_CALIB_DEFAULT_FLOW_RUN	(IWL_CALIB_CFG_XTAL_IDX		|\
-					 IWL_CALIB_CFG_TEMPERATURE_IDX	|\
-					 IWL_CALIB_CFG_VOLTAGE_READ_IDX	|\
-					 IWL_CALIB_CFG_BB_FILTER_IDX	|\
-					 IWL_CALIB_CFG_DC_IDX		|\
-					 IWL_CALIB_CFG_TX_IQ_IDX	|\
-					 IWL_CALIB_CFG_RX_IQ_IDX	|\
-					 IWL_CALIB_CFG_SENSITIVITY_IDX	|\
-					 IWL_CALIB_CFG_AGC_IDX)
-
-#define IWL_CALIB_DEFAULT_EVENT_RUN	(IWL_CALIB_CFG_XTAL_IDX		|\
-					 IWL_CALIB_CFG_TEMPERATURE_IDX	|\
-					 IWL_CALIB_CFG_VOLTAGE_READ_IDX	|\
-					 IWL_CALIB_CFG_TX_PWR_IDX	|\
-					 IWL_CALIB_CFG_DC_IDX		|\
-					 IWL_CALIB_CFG_TX_IQ_IDX	|\
-					 IWL_CALIB_CFG_SENSITIVITY_IDX)
-
-/*
- * Sets the calibrations trigger values that will be sent to the FW for runtime
- * and init calibrations.
- * The ones given in the FW TLV are not correct.
- */
-static void iwl_set_default_calib_trigger(struct iwl_mvm *mvm)
-{
-	struct iwl_tlv_calib_ctrl default_calib;
-
-	/*
-	 * WkP FW TLV calib bits are wrong, overwrite them.
-	 * This defines the dynamic calibrations which are implemented in the
-	 * uCode both for init(flow) calculation and event driven calibs.
-	 */
-
-	/* Init Image */
-	default_calib.event_trigger = cpu_to_le32(IWL_CALIB_DEFAULT_EVENT_INIT);
-	default_calib.flow_trigger = cpu_to_le32(IWL_CALIB_DEFAULT_FLOW_INIT);
-
-	if (default_calib.event_trigger !=
-	    mvm->fw->default_calib[IWL_UCODE_INIT].event_trigger)
-		IWL_ERR(mvm,
-			"Updating the event calib for INIT image: 0x%x -> 0x%x\n",
-			mvm->fw->default_calib[IWL_UCODE_INIT].event_trigger,
-			default_calib.event_trigger);
-	if (default_calib.flow_trigger !=
-	    mvm->fw->default_calib[IWL_UCODE_INIT].flow_trigger)
-		IWL_ERR(mvm,
-			"Updating the flow calib for INIT image: 0x%x -> 0x%x\n",
-			mvm->fw->default_calib[IWL_UCODE_INIT].flow_trigger,
-			default_calib.flow_trigger);
-
-	memcpy((void *)&mvm->fw->default_calib[IWL_UCODE_INIT],
-	       &default_calib, sizeof(struct iwl_tlv_calib_ctrl));
-	IWL_ERR(mvm,
-		"Setting uCode init calibrations event 0x%x, trigger 0x%x\n",
-		default_calib.event_trigger,
-		default_calib.flow_trigger);
-
-	/* Run time image */
-	default_calib.event_trigger = cpu_to_le32(IWL_CALIB_DEFAULT_EVENT_RUN);
-	default_calib.flow_trigger = cpu_to_le32(IWL_CALIB_DEFAULT_FLOW_RUN);
-
-	if (default_calib.event_trigger !=
-	    mvm->fw->default_calib[IWL_UCODE_REGULAR].event_trigger)
-		IWL_ERR(mvm,
-			"Updating the event calib for RT image: 0x%x -> 0x%x\n",
-			mvm->fw->default_calib[IWL_UCODE_REGULAR].event_trigger,
-			default_calib.event_trigger);
-	if (default_calib.flow_trigger !=
-	    mvm->fw->default_calib[IWL_UCODE_REGULAR].flow_trigger)
-		IWL_ERR(mvm,
-			"Updating the flow calib for RT image: 0x%x -> 0x%x\n",
-			mvm->fw->default_calib[IWL_UCODE_REGULAR].flow_trigger,
-			default_calib.flow_trigger);
-
-	memcpy((void *)&mvm->fw->default_calib[IWL_UCODE_REGULAR],
-	       &default_calib, sizeof(struct iwl_tlv_calib_ctrl));
-	IWL_ERR(mvm,
-		"Setting uCode runtime calibs event 0x%x, trigger 0x%x\n",
-		default_calib.event_trigger,
-		default_calib.flow_trigger);
-}
-
 static int iwl_set_default_calibrations(struct iwl_mvm *mvm)
 {
 	u8 cmd_raw[16]; /* holds the variable size commands */
@@ -446,8 +321,10 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 	ret = iwl_nvm_check_version(mvm->nvm_data, mvm->trans);
 	WARN_ON(ret);
 
-	/* Override the calibrations from TLV and the const of fw */
-	iwl_set_default_calib_trigger(mvm);
+	/* Send TX valid antennas before triggering calibrations */
+	ret = iwl_send_tx_ant_cfg(mvm, mvm->nvm_data->valid_tx_ant);
+	if (ret)
+		goto error;
 
 	/* WkP doesn't have all calibrations, need to set default values */
 	if (mvm->cfg->device_family == IWL_DEVICE_FAMILY_7000) {
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index 537711b1047..bdae700c769 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -80,7 +80,8 @@
 
 #define IWL_INVALID_MAC80211_QUEUE	0xff
 #define IWL_MVM_MAX_ADDRESSES		2
-#define IWL_RSSI_OFFSET 44
+/* RSSI offset for WkP */
+#define IWL_RSSI_OFFSET 50
 
 enum iwl_mvm_tx_fifo {
 	IWL_MVM_TX_FIFO_BK = 0,
diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c
index aa59adf87db..d0f9c1e0475 100644
--- a/drivers/net/wireless/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/iwlwifi/mvm/ops.c
@@ -624,12 +624,8 @@ static void iwl_mvm_free_skb(struct iwl_op_mode *op_mode, struct sk_buff *skb)
 	ieee80211_free_txskb(mvm->hw, skb);
 }
 
-static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode)
+static void iwl_mvm_nic_restart(struct iwl_mvm *mvm)
 {
-	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
-
-	iwl_mvm_dump_nic_error_log(mvm);
-
 	iwl_abort_notification_waits(&mvm->notif_wait);
 
 	/*
@@ -663,9 +659,21 @@ static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode)
 	}
 }
 
+static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode)
+{
+	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
+	iwl_mvm_dump_nic_error_log(mvm);
+
+	iwl_mvm_nic_restart(mvm);
+}
+
 static void iwl_mvm_cmd_queue_full(struct iwl_op_mode *op_mode)
 {
+	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
 	WARN_ON(1);
+	iwl_mvm_nic_restart(mvm);
 }
 
 static const struct iwl_op_mode_ops iwl_mvm_ops = {
diff --git a/drivers/net/wireless/iwlwifi/mvm/rx.c b/drivers/net/wireless/iwlwifi/mvm/rx.c
index 3f40ab05bbd..b0b190d0ec2 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/rx.c
@@ -131,33 +131,42 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 static int iwl_mvm_calc_rssi(struct iwl_mvm *mvm,
 			     struct iwl_rx_phy_info *phy_info)
 {
-	u32 rssi_a, rssi_b, rssi_c, max_rssi, agc_db;
+	int rssi_a, rssi_b, rssi_a_dbm, rssi_b_dbm, max_rssi_dbm;
+	int rssi_all_band_a, rssi_all_band_b;
+	u32 agc_a, agc_b, max_agc;
 	u32 val;
 
-	/* Find max rssi among 3 possible receivers.
+	/* Find max rssi among 2 possible receivers.
 	 * These values are measured by the Digital Signal Processor (DSP).
 	 * They should stay fairly constant even as the signal strength varies,
 	 * if the radio's Automatic Gain Control (AGC) is working right.
 	 * AGC value (see below) will provide the "interesting" info.
 	 */
+	val = le32_to_cpu(phy_info->non_cfg_phy[IWL_RX_INFO_AGC_IDX]);
+	agc_a = (val & IWL_OFDM_AGC_A_MSK) >> IWL_OFDM_AGC_A_POS;
+	agc_b = (val & IWL_OFDM_AGC_B_MSK) >> IWL_OFDM_AGC_B_POS;
+	max_agc = max_t(u32, agc_a, agc_b);
+
 	val = le32_to_cpu(phy_info->non_cfg_phy[IWL_RX_INFO_RSSI_AB_IDX]);
 	rssi_a = (val & IWL_OFDM_RSSI_INBAND_A_MSK) >> IWL_OFDM_RSSI_A_POS;
 	rssi_b = (val & IWL_OFDM_RSSI_INBAND_B_MSK) >> IWL_OFDM_RSSI_B_POS;
-	val = le32_to_cpu(phy_info->non_cfg_phy[IWL_RX_INFO_RSSI_C_IDX]);
-	rssi_c = (val & IWL_OFDM_RSSI_INBAND_C_MSK) >> IWL_OFDM_RSSI_C_POS;
-
-	val = le32_to_cpu(phy_info->non_cfg_phy[IWL_RX_INFO_AGC_IDX]);
-	agc_db = (val & IWL_OFDM_AGC_DB_MSK) >> IWL_OFDM_AGC_DB_POS;
+	rssi_all_band_a = (val & IWL_OFDM_RSSI_ALLBAND_A_MSK) >>
+				IWL_OFDM_RSSI_ALLBAND_A_POS;
+	rssi_all_band_b = (val & IWL_OFDM_RSSI_ALLBAND_B_MSK) >>
+				IWL_OFDM_RSSI_ALLBAND_B_POS;
 
-	max_rssi = max_t(u32, rssi_a, rssi_b);
-	max_rssi = max_t(u32, max_rssi, rssi_c);
+	/*
+	 * dBm = rssi dB - agc dB - constant.
+	 * Higher AGC (higher radio gain) means lower signal.
+	 */
+	rssi_a_dbm = rssi_a - IWL_RSSI_OFFSET - agc_a;
+	rssi_b_dbm = rssi_b - IWL_RSSI_OFFSET - agc_b;
+	max_rssi_dbm = max_t(int, rssi_a_dbm, rssi_b_dbm);
 
-	IWL_DEBUG_STATS(mvm, "Rssi In A %d B %d C %d Max %d AGC dB %d\n",
-			rssi_a, rssi_b, rssi_c, max_rssi, agc_db);
+	IWL_DEBUG_STATS(mvm, "Rssi In A %d B %d Max %d AGCA %d AGCB %d\n",
+			rssi_a_dbm, rssi_b_dbm, max_rssi_dbm, agc_a, agc_b);
 
-	/* dBm = max_rssi dB - agc dB - constant.
-	 * Higher AGC (higher radio gain) means lower signal. */
-	return max_rssi - agc_db - IWL_RSSI_OFFSET;
+	return max_rssi_dbm;
 }
 
 /*
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index 861a7f9f8e7..274f44e2ef6 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -770,6 +770,16 @@ int iwl_mvm_sta_tx_agg_stop(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	u16 txq_id;
 	int err;
 
+
+	/*
+	 * If mac80211 is cleaning its state, then say that we finished since
+	 * our state has been cleared anyway.
+	 */
+	if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		return 0;
+	}
+
 	spin_lock_bh(&mvmsta->lock);
 
 	txq_id = tid_data->txq_id;
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 6b67ce3f679..6645efe5c03 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -607,12 +607,8 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 
 		/* Single frame failure in an AMPDU queue => send BAR */
 		if (txq_id >= IWL_FIRST_AMPDU_QUEUE &&
-		    !(info->flags & IEEE80211_TX_STAT_ACK)) {
-			/* there must be only one skb in the skb_list */
-			WARN_ON_ONCE(skb_freed > 1 ||
-				     !skb_queue_empty(&skbs));
+		    !(info->flags & IEEE80211_TX_STAT_ACK))
 			info->flags |= IEEE80211_TX_STAT_AMPDU_NO_BACK;
-		}
 
 		/* W/A FW bug: seq_ctl is wrong when the queue is flushed */
 		if (status == TX_STATUS_FAIL_FIFO_FLUSHED) {
diff --git a/drivers/net/wireless/iwlwifi/pcie/internal.h b/drivers/net/wireless/iwlwifi/pcie/internal.h
index 3d62e805535..148843e7f34 100644
--- a/drivers/net/wireless/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/iwlwifi/pcie/internal.h
@@ -137,10 +137,6 @@ static inline int iwl_queue_dec_wrap(int index, int n_bd)
 struct iwl_cmd_meta {
 	/* only for SYNC commands, iff the reply skb is wanted */
 	struct iwl_host_cmd *source;
-
-	DEFINE_DMA_UNMAP_ADDR(mapping);
-	DEFINE_DMA_UNMAP_LEN(len);
-
 	u32 flags;
 };
 
@@ -185,25 +181,36 @@ struct iwl_queue {
 /*
  * The FH will write back to the first TB only, so we need
  * to copy some data into the buffer regardless of whether
- * it should be mapped or not. This indicates how much to
- * copy, even for HCMDs it must be big enough to fit the
- * DRAM scratch from the TX cmd, at least 16 bytes.
+ * it should be mapped or not. This indicates how big the
+ * first TB must be to include the scratch buffer. Since
+ * the scratch is 4 bytes at offset 12, it's 16 now. If we
+ * make it bigger then allocations will be bigger and copy
+ * slower, so that's probably not useful.
  */
-#define IWL_HCMD_MIN_COPY_SIZE	16
+#define IWL_HCMD_SCRATCHBUF_SIZE	16
 
 struct iwl_pcie_txq_entry {
 	struct iwl_device_cmd *cmd;
-	struct iwl_device_cmd *copy_cmd;
 	struct sk_buff *skb;
 	/* buffer to free after command completes */
 	const void *free_buf;
 	struct iwl_cmd_meta meta;
 };
 
+struct iwl_pcie_txq_scratch_buf {
+	struct iwl_cmd_header hdr;
+	u8 buf[8];
+	__le32 scratch;
+};
+
 /**
  * struct iwl_txq - Tx Queue for DMA
  * @q: generic Rx/Tx queue descriptor
  * @tfds: transmit frame descriptors (DMA memory)
+ * @scratchbufs: start of command headers, including scratch buffers, for
+ *	the writeback -- this is DMA memory and an array holding one buffer
+ *	for each command on the queue
+ * @scratchbufs_dma: DMA address for the scratchbufs start
  * @entries: transmit entries (driver state)
  * @lock: queue lock
  * @stuck_timer: timer that fires if queue gets stuck
@@ -217,6 +224,8 @@ struct iwl_pcie_txq_entry {
 struct iwl_txq {
 	struct iwl_queue q;
 	struct iwl_tfd *tfds;
+	struct iwl_pcie_txq_scratch_buf *scratchbufs;
+	dma_addr_t scratchbufs_dma;
 	struct iwl_pcie_txq_entry *entries;
 	spinlock_t lock;
 	struct timer_list stuck_timer;
@@ -225,6 +234,13 @@ struct iwl_txq {
 	u8 active;
 };
 
+static inline dma_addr_t
+iwl_pcie_get_scratchbuf_dma(struct iwl_txq *txq, int idx)
+{
+	return txq->scratchbufs_dma +
+	       sizeof(struct iwl_pcie_txq_scratch_buf) * idx;
+}
+
 /**
  * struct iwl_trans_pcie - PCIe transport specific data
  * @rxq: all the RX queue data
diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c
index b0ae06d2456..567e67ad1f6 100644
--- a/drivers/net/wireless/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/rx.c
@@ -637,22 +637,14 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		index = SEQ_TO_INDEX(sequence);
 		cmd_index = get_cmd_index(&txq->q, index);
 
-		if (reclaim) {
-			struct iwl_pcie_txq_entry *ent;
-			ent = &txq->entries[cmd_index];
-			cmd = ent->copy_cmd;
-			WARN_ON_ONCE(!cmd && ent->meta.flags & CMD_WANT_HCMD);
-		} else {
+		if (reclaim)
+			cmd = txq->entries[cmd_index].cmd;
+		else
 			cmd = NULL;
-		}
 
 		err = iwl_op_mode_rx(trans->op_mode, &rxcb, cmd);
 
 		if (reclaim) {
-			/* The original command isn't needed any more */
-			kfree(txq->entries[cmd_index].copy_cmd);
-			txq->entries[cmd_index].copy_cmd = NULL;
-			/* nor is the duplicated part of the command */
 			kfree(txq->entries[cmd_index].free_buf);
 			txq->entries[cmd_index].free_buf = NULL;
 		}
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index 8b625a7f568..8595c16f74d 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -191,12 +191,9 @@ static void iwl_pcie_txq_stuck_timer(unsigned long data)
 	}
 
 	for (i = q->read_ptr; i != q->write_ptr;
-	     i = iwl_queue_inc_wrap(i, q->n_bd)) {
-		struct iwl_tx_cmd *tx_cmd =
-			(struct iwl_tx_cmd *)txq->entries[i].cmd->payload;
+	     i = iwl_queue_inc_wrap(i, q->n_bd))
 		IWL_ERR(trans, "scratch %d = 0x%08x\n", i,
-			get_unaligned_le32(&tx_cmd->scratch));
-	}
+			le32_to_cpu(txq->scratchbufs[i].scratch));
 
 	iwl_op_mode_nic_error(trans->op_mode);
 }
@@ -367,8 +364,8 @@ static inline u8 iwl_pcie_tfd_get_num_tbs(struct iwl_tfd *tfd)
 }
 
 static void iwl_pcie_tfd_unmap(struct iwl_trans *trans,
-			       struct iwl_cmd_meta *meta, struct iwl_tfd *tfd,
-			       enum dma_data_direction dma_dir)
+			       struct iwl_cmd_meta *meta,
+			       struct iwl_tfd *tfd)
 {
 	int i;
 	int num_tbs;
@@ -382,17 +379,12 @@ static void iwl_pcie_tfd_unmap(struct iwl_trans *trans,
 		return;
 	}
 
-	/* Unmap tx_cmd */
-	if (num_tbs)
-		dma_unmap_single(trans->dev,
-				dma_unmap_addr(meta, mapping),
-				dma_unmap_len(meta, len),
-				DMA_BIDIRECTIONAL);
+	/* first TB is never freed - it's the scratchbuf data */
 
-	/* Unmap chunks, if any. */
 	for (i = 1; i < num_tbs; i++)
 		dma_unmap_single(trans->dev, iwl_pcie_tfd_tb_get_addr(tfd, i),
-				 iwl_pcie_tfd_tb_get_len(tfd, i), dma_dir);
+				 iwl_pcie_tfd_tb_get_len(tfd, i),
+				 DMA_TO_DEVICE);
 
 	tfd->num_tbs = 0;
 }
@@ -406,8 +398,7 @@ static void iwl_pcie_tfd_unmap(struct iwl_trans *trans,
  * Does NOT advance any TFD circular buffer read/write indexes
  * Does NOT free the TFD itself (which is within circular buffer)
  */
-static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
-				  enum dma_data_direction dma_dir)
+static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 {
 	struct iwl_tfd *tfd_tmp = txq->tfds;
 
@@ -418,8 +409,7 @@ static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
 	lockdep_assert_held(&txq->lock);
 
 	/* We have only q->n_window txq->entries, but we use q->n_bd tfds */
-	iwl_pcie_tfd_unmap(trans, &txq->entries[idx].meta, &tfd_tmp[rd_ptr],
-			   dma_dir);
+	iwl_pcie_tfd_unmap(trans, &txq->entries[idx].meta, &tfd_tmp[rd_ptr]);
 
 	/* free SKB */
 	if (txq->entries) {
@@ -479,6 +469,7 @@ static int iwl_pcie_txq_alloc(struct iwl_trans *trans,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	size_t tfd_sz = sizeof(struct iwl_tfd) * TFD_QUEUE_SIZE_MAX;
+	size_t scratchbuf_sz;
 	int i;
 
 	if (WARN_ON(txq->entries || txq->tfds))
@@ -514,9 +505,25 @@ static int iwl_pcie_txq_alloc(struct iwl_trans *trans,
 		IWL_ERR(trans, "dma_alloc_coherent(%zd) failed\n", tfd_sz);
 		goto error;
 	}
+
+	BUILD_BUG_ON(IWL_HCMD_SCRATCHBUF_SIZE != sizeof(*txq->scratchbufs));
+	BUILD_BUG_ON(offsetof(struct iwl_pcie_txq_scratch_buf, scratch) !=
+			sizeof(struct iwl_cmd_header) +
+			offsetof(struct iwl_tx_cmd, scratch));
+
+	scratchbuf_sz = sizeof(*txq->scratchbufs) * slots_num;
+
+	txq->scratchbufs = dma_alloc_coherent(trans->dev, scratchbuf_sz,
+					      &txq->scratchbufs_dma,
+					      GFP_KERNEL);
+	if (!txq->scratchbufs)
+		goto err_free_tfds;
+
 	txq->q.id = txq_id;
 
 	return 0;
+err_free_tfds:
+	dma_free_coherent(trans->dev, tfd_sz, txq->tfds, txq->q.dma_addr);
 error:
 	if (txq->entries && txq_id == trans_pcie->cmd_queue)
 		for (i = 0; i < slots_num; i++)
@@ -565,22 +572,13 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
 	struct iwl_queue *q = &txq->q;
-	enum dma_data_direction dma_dir;
 
 	if (!q->n_bd)
 		return;
 
-	/* In the command queue, all the TBs are mapped as BIDI
-	 * so unmap them as such.
-	 */
-	if (txq_id == trans_pcie->cmd_queue)
-		dma_dir = DMA_BIDIRECTIONAL;
-	else
-		dma_dir = DMA_TO_DEVICE;
-
 	spin_lock_bh(&txq->lock);
 	while (q->write_ptr != q->read_ptr) {
-		iwl_pcie_txq_free_tfd(trans, txq, dma_dir);
+		iwl_pcie_txq_free_tfd(trans, txq);
 		q->read_ptr = iwl_queue_inc_wrap(q->read_ptr, q->n_bd);
 	}
 	spin_unlock_bh(&txq->lock);
@@ -610,7 +608,6 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	if (txq_id == trans_pcie->cmd_queue)
 		for (i = 0; i < txq->q.n_window; i++) {
 			kfree(txq->entries[i].cmd);
-			kfree(txq->entries[i].copy_cmd);
 			kfree(txq->entries[i].free_buf);
 		}
 
@@ -619,6 +616,10 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 		dma_free_coherent(dev, sizeof(struct iwl_tfd) *
 				  txq->q.n_bd, txq->tfds, txq->q.dma_addr);
 		txq->q.dma_addr = 0;
+
+		dma_free_coherent(dev,
+				  sizeof(*txq->scratchbufs) * txq->q.n_window,
+				  txq->scratchbufs, txq->scratchbufs_dma);
 	}
 
 	kfree(txq->entries);
@@ -962,7 +963,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 		iwl_pcie_txq_inval_byte_cnt_tbl(trans, txq);
 
-		iwl_pcie_txq_free_tfd(trans, txq, DMA_TO_DEVICE);
+		iwl_pcie_txq_free_tfd(trans, txq);
 	}
 
 	iwl_pcie_txq_progress(trans_pcie, txq);
@@ -1152,29 +1153,29 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	void *dup_buf = NULL;
 	dma_addr_t phys_addr;
 	int idx;
-	u16 copy_size, cmd_size, dma_size;
+	u16 copy_size, cmd_size, scratch_size;
 	bool had_nocopy = false;
 	int i;
 	u32 cmd_pos;
-	const u8 *cmddata[IWL_MAX_CMD_TFDS];
-	u16 cmdlen[IWL_MAX_CMD_TFDS];
+	const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD];
+	u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD];
 
 	copy_size = sizeof(out_cmd->hdr);
 	cmd_size = sizeof(out_cmd->hdr);
 
 	/* need one for the header if the first is NOCOPY */
-	BUILD_BUG_ON(IWL_MAX_CMD_TFDS > IWL_NUM_OF_TBS - 1);
+	BUILD_BUG_ON(IWL_MAX_CMD_TBS_PER_TFD > IWL_NUM_OF_TBS - 1);
 
-	for (i = 0; i < IWL_MAX_CMD_TFDS; i++) {
+	for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
 		cmddata[i] = cmd->data[i];
 		cmdlen[i] = cmd->len[i];
 
 		if (!cmd->len[i])
 			continue;
 
-		/* need at least IWL_HCMD_MIN_COPY_SIZE copied */
-		if (copy_size < IWL_HCMD_MIN_COPY_SIZE) {
-			int copy = IWL_HCMD_MIN_COPY_SIZE - copy_size;
+		/* need at least IWL_HCMD_SCRATCHBUF_SIZE copied */
+		if (copy_size < IWL_HCMD_SCRATCHBUF_SIZE) {
+			int copy = IWL_HCMD_SCRATCHBUF_SIZE - copy_size;
 
 			if (copy > cmdlen[i])
 				copy = cmdlen[i];
@@ -1260,15 +1261,15 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	/* and copy the data that needs to be copied */
 	cmd_pos = offsetof(struct iwl_device_cmd, payload);
 	copy_size = sizeof(out_cmd->hdr);
-	for (i = 0; i < IWL_MAX_CMD_TFDS; i++) {
+	for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
 		int copy = 0;
 
 		if (!cmd->len)
 			continue;
 
-		/* need at least IWL_HCMD_MIN_COPY_SIZE copied */
-		if (copy_size < IWL_HCMD_MIN_COPY_SIZE) {
-			copy = IWL_HCMD_MIN_COPY_SIZE - copy_size;
+		/* need at least IWL_HCMD_SCRATCHBUF_SIZE copied */
+		if (copy_size < IWL_HCMD_SCRATCHBUF_SIZE) {
+			copy = IWL_HCMD_SCRATCHBUF_SIZE - copy_size;
 
 			if (copy > cmd->len[i])
 				copy = cmd->len[i];
@@ -1286,50 +1287,38 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		}
 	}
 
-	WARN_ON_ONCE(txq->entries[idx].copy_cmd);
-
-	/*
-	 * since out_cmd will be the source address of the FH, it will write
-	 * the retry count there. So when the user needs to receivce the HCMD
-	 * that corresponds to the response in the response handler, it needs
-	 * to set CMD_WANT_HCMD.
-	 */
-	if (cmd->flags & CMD_WANT_HCMD) {
-		txq->entries[idx].copy_cmd =
-			kmemdup(out_cmd, cmd_pos, GFP_ATOMIC);
-		if (unlikely(!txq->entries[idx].copy_cmd)) {
-			idx = -ENOMEM;
-			goto out;
-		}
-	}
-
 	IWL_DEBUG_HC(trans,
 		     "Sending command %s (#%x), seq: 0x%04X, %d bytes at %d[%d]:%d\n",
 		     get_cmd_string(trans_pcie, out_cmd->hdr.cmd),
 		     out_cmd->hdr.cmd, le16_to_cpu(out_cmd->hdr.sequence),
 		     cmd_size, q->write_ptr, idx, trans_pcie->cmd_queue);
 
-	/*
-	 * If the entire command is smaller than IWL_HCMD_MIN_COPY_SIZE, we must
-	 * still map at least that many bytes for the hardware to write back to.
-	 * We have enough space, so that's not a problem.
-	 */
-	dma_size = max_t(u16, copy_size, IWL_HCMD_MIN_COPY_SIZE);
+	/* start the TFD with the scratchbuf */
+	scratch_size = min_t(int, copy_size, IWL_HCMD_SCRATCHBUF_SIZE);
+	memcpy(&txq->scratchbufs[q->write_ptr], &out_cmd->hdr, scratch_size);
+	iwl_pcie_txq_build_tfd(trans, txq,
+			       iwl_pcie_get_scratchbuf_dma(txq, q->write_ptr),
+			       scratch_size, 1);
+
+	/* map first command fragment, if any remains */
+	if (copy_size > scratch_size) {
+		phys_addr = dma_map_single(trans->dev,
+					   ((u8 *)&out_cmd->hdr) + scratch_size,
+					   copy_size - scratch_size,
+					   DMA_TO_DEVICE);
+		if (dma_mapping_error(trans->dev, phys_addr)) {
+			iwl_pcie_tfd_unmap(trans, out_meta,
+					   &txq->tfds[q->write_ptr]);
+			idx = -ENOMEM;
+			goto out;
+		}
 
-	phys_addr = dma_map_single(trans->dev, &out_cmd->hdr, dma_size,
-				   DMA_BIDIRECTIONAL);
-	if (unlikely(dma_mapping_error(trans->dev, phys_addr))) {
-		idx = -ENOMEM;
-		goto out;
+		iwl_pcie_txq_build_tfd(trans, txq, phys_addr,
+				       copy_size - scratch_size, 0);
 	}
 
-	dma_unmap_addr_set(out_meta, mapping, phys_addr);
-	dma_unmap_len_set(out_meta, len, dma_size);
-
-	iwl_pcie_txq_build_tfd(trans, txq, phys_addr, copy_size, 1);
-
 	/* map the remaining (adjusted) nocopy/dup fragments */
-	for (i = 0; i < IWL_MAX_CMD_TFDS; i++) {
+	for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
 		const void *data = cmddata[i];
 
 		if (!cmdlen[i])
@@ -1340,11 +1329,10 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		if (cmd->dataflags[i] & IWL_HCMD_DFL_DUP)
 			data = dup_buf;
 		phys_addr = dma_map_single(trans->dev, (void *)data,
-					   cmdlen[i], DMA_BIDIRECTIONAL);
+					   cmdlen[i], DMA_TO_DEVICE);
 		if (dma_mapping_error(trans->dev, phys_addr)) {
 			iwl_pcie_tfd_unmap(trans, out_meta,
-					   &txq->tfds[q->write_ptr],
-					   DMA_BIDIRECTIONAL);
+					   &txq->tfds[q->write_ptr]);
 			idx = -ENOMEM;
 			goto out;
 		}
@@ -1418,7 +1406,7 @@ void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 	cmd = txq->entries[cmd_index].cmd;
 	meta = &txq->entries[cmd_index].meta;
 
-	iwl_pcie_tfd_unmap(trans, meta, &txq->tfds[index], DMA_BIDIRECTIONAL);
+	iwl_pcie_tfd_unmap(trans, meta, &txq->tfds[index]);
 
 	/* Input error checking is done when commands are added to queue. */
 	if (meta->flags & CMD_WANT_SKB) {
@@ -1597,10 +1585,9 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	struct iwl_cmd_meta *out_meta;
 	struct iwl_txq *txq;
 	struct iwl_queue *q;
-	dma_addr_t phys_addr = 0;
-	dma_addr_t txcmd_phys;
-	dma_addr_t scratch_phys;
-	u16 len, firstlen, secondlen;
+	dma_addr_t tb0_phys, tb1_phys, scratch_phys;
+	void *tb1_addr;
+	u16 len, tb1_len, tb2_len;
 	u8 wait_write_ptr = 0;
 	__le16 fc = hdr->frame_control;
 	u8 hdr_len = ieee80211_hdrlen(fc);
@@ -1638,85 +1625,80 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
 			    INDEX_TO_SEQ(q->write_ptr)));
 
+	tb0_phys = iwl_pcie_get_scratchbuf_dma(txq, q->write_ptr);
+	scratch_phys = tb0_phys + sizeof(struct iwl_cmd_header) +
+		       offsetof(struct iwl_tx_cmd, scratch);
+
+	tx_cmd->dram_lsb_ptr = cpu_to_le32(scratch_phys);
+	tx_cmd->dram_msb_ptr = iwl_get_dma_hi_addr(scratch_phys);
+
 	/* Set up first empty entry in queue's array of Tx/cmd buffers */
 	out_meta = &txq->entries[q->write_ptr].meta;
 
 	/*
-	 * Use the first empty entry in this queue's command buffer array
-	 * to contain the Tx command and MAC header concatenated together
-	 * (payload data will be in another buffer).
-	 * Size of this varies, due to varying MAC header length.
-	 * If end is not dword aligned, we'll have 2 extra bytes at the end
-	 * of the MAC header (device reads on dword boundaries).
-	 * We'll tell device about this padding later.
+	 * The second TB (tb1) points to the remainder of the TX command
+	 * and the 802.11 header - dword aligned size
+	 * (This calculation modifies the TX command, so do it before the
+	 * setup of the first TB)
 	 */
-	len = sizeof(struct iwl_tx_cmd) +
-		sizeof(struct iwl_cmd_header) + hdr_len;
-	firstlen = (len + 3) & ~3;
+	len = sizeof(struct iwl_tx_cmd) + sizeof(struct iwl_cmd_header) +
+	      hdr_len - IWL_HCMD_SCRATCHBUF_SIZE;
+	tb1_len = (len + 3) & ~3;
 
 	/* Tell NIC about any 2-byte padding after MAC header */
-	if (firstlen != len)
+	if (tb1_len != len)
 		tx_cmd->tx_flags |= TX_CMD_FLG_MH_PAD_MSK;
 
-	/* Physical address of this Tx command's header (not MAC header!),
-	 * within command buffer array. */
-	txcmd_phys = dma_map_single(trans->dev,
-				    &dev_cmd->hdr, firstlen,
-				    DMA_BIDIRECTIONAL);
-	if (unlikely(dma_mapping_error(trans->dev, txcmd_phys)))
-		goto out_err;
-	dma_unmap_addr_set(out_meta, mapping, txcmd_phys);
-	dma_unmap_len_set(out_meta, len, firstlen);
+	/* The first TB points to the scratchbuf data - min_copy bytes */
+	memcpy(&txq->scratchbufs[q->write_ptr], &dev_cmd->hdr,
+	       IWL_HCMD_SCRATCHBUF_SIZE);
+	iwl_pcie_txq_build_tfd(trans, txq, tb0_phys,
+			       IWL_HCMD_SCRATCHBUF_SIZE, 1);
 
-	if (!ieee80211_has_morefrags(fc)) {
-		txq->need_update = 1;
-	} else {
-		wait_write_ptr = 1;
-		txq->need_update = 0;
-	}
+	/* there must be data left over for TB1 or this code must be changed */
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd) < IWL_HCMD_SCRATCHBUF_SIZE);
 
-	/* Set up TFD's 2nd entry to point directly to remainder of skb,
-	 * if any (802.11 null frames have no payload). */
-	secondlen = skb->len - hdr_len;
-	if (secondlen > 0) {
-		phys_addr = dma_map_single(trans->dev, skb->data + hdr_len,
-					   secondlen, DMA_TO_DEVICE);
-		if (unlikely(dma_mapping_error(trans->dev, phys_addr))) {
-			dma_unmap_single(trans->dev,
-					 dma_unmap_addr(out_meta, mapping),
-					 dma_unmap_len(out_meta, len),
-					 DMA_BIDIRECTIONAL);
+	/* map the data for TB1 */
+	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_HCMD_SCRATCHBUF_SIZE;
+	tb1_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, tb1_phys)))
+		goto out_err;
+	iwl_pcie_txq_build_tfd(trans, txq, tb1_phys, tb1_len, 0);
+
+	/*
+	 * Set up TFD's third entry to point directly to remainder
+	 * of skb, if any (802.11 null frames have no payload).
+	 */
+	tb2_len = skb->len - hdr_len;
+	if (tb2_len > 0) {
+		dma_addr_t tb2_phys = dma_map_single(trans->dev,
+						     skb->data + hdr_len,
+						     tb2_len, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(trans->dev, tb2_phys))) {
+			iwl_pcie_tfd_unmap(trans, out_meta,
+					   &txq->tfds[q->write_ptr]);
 			goto out_err;
 		}
+		iwl_pcie_txq_build_tfd(trans, txq, tb2_phys, tb2_len, 0);
 	}
 
-	/* Attach buffers to TFD */
-	iwl_pcie_txq_build_tfd(trans, txq, txcmd_phys, firstlen, 1);
-	if (secondlen > 0)
-		iwl_pcie_txq_build_tfd(trans, txq, phys_addr, secondlen, 0);
-
-	scratch_phys = txcmd_phys + sizeof(struct iwl_cmd_header) +
-				offsetof(struct iwl_tx_cmd, scratch);
-
-	/* take back ownership of DMA buffer to enable update */
-	dma_sync_single_for_cpu(trans->dev, txcmd_phys, firstlen,
-				DMA_BIDIRECTIONAL);
-	tx_cmd->dram_lsb_ptr = cpu_to_le32(scratch_phys);
-	tx_cmd->dram_msb_ptr = iwl_get_dma_hi_addr(scratch_phys);
-
 	/* Set up entry for this TFD in Tx byte-count array */
 	iwl_pcie_txq_update_byte_cnt_tbl(trans, txq, le16_to_cpu(tx_cmd->len));
 
-	dma_sync_single_for_device(trans->dev, txcmd_phys, firstlen,
-				   DMA_BIDIRECTIONAL);
-
 	trace_iwlwifi_dev_tx(trans->dev, skb,
 			     &txq->tfds[txq->q.write_ptr],
 			     sizeof(struct iwl_tfd),
-			     &dev_cmd->hdr, firstlen,
-			     skb->data + hdr_len, secondlen);
+			     &dev_cmd->hdr, IWL_HCMD_SCRATCHBUF_SIZE + tb1_len,
+			     skb->data + hdr_len, tb2_len);
 	trace_iwlwifi_dev_tx_data(trans->dev, skb,
-				  skb->data + hdr_len, secondlen);
+				  skb->data + hdr_len, tb2_len);
+
+	if (!ieee80211_has_morefrags(fc)) {
+		txq->need_update = 1;
+	} else {
+		wait_write_ptr = 1;
+		txq->need_update = 0;
+	}
 
 	/* start timer if queue currently empty */
 	if (txq->need_update && q->read_ptr == q->write_ptr &&