Merge remote-tracking branch 'airlied/drm-core-next' into drm-nouveau-next

4 files changed, 167 insertions, 91 deletions

diff --git a/drivers/net/cxgb4vf/adapter.h b/drivers/net/cxgb4vf/adapter.h
index 8ea01962e04..4766b4116b4 100644
--- a/drivers/net/cxgb4vf/adapter.h
+++ b/drivers/net/cxgb4vf/adapter.h
@@ -60,7 +60,7 @@ enum {
 	 * MSI-X interrupt index usage.
 	 */
 	MSIX_FW		= 0,		/* MSI-X index for firmware Q */
-	MSIX_NIQFLINT	= 1,		/* MSI-X index base for Ingress Qs */
+	MSIX_IQFLINT	= 1,		/* MSI-X index base for Ingress Qs */
 	MSIX_EXTRAS	= 1,
 	MSIX_ENTRIES	= MAX_ETH_QSETS + MSIX_EXTRAS,
 
diff --git a/drivers/net/cxgb4vf/cxgb4vf_main.c b/drivers/net/cxgb4vf/cxgb4vf_main.c
index c3449bbc585..56166ae2059 100644
--- a/drivers/net/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/cxgb4vf/cxgb4vf_main.c
@@ -280,9 +280,7 @@ static void name_msix_vecs(struct adapter *adapter)
 		const struct port_info *pi = netdev_priv(dev);
 		int qs, msi;
 
-		for (qs = 0, msi = MSIX_NIQFLINT;
-		     qs < pi->nqsets;
-		     qs++, msi++) {
+		for (qs = 0, msi = MSIX_IQFLINT; qs < pi->nqsets; qs++, msi++) {
 			snprintf(adapter->msix_info[msi].desc, namelen,
 				 "%s-%d", dev->name, qs);
 			adapter->msix_info[msi].desc[namelen] = 0;
@@ -309,7 +307,7 @@ static int request_msix_queue_irqs(struct adapter *adapter)
 	/*
 	 * Ethernet queues.
 	 */
-	msi = MSIX_NIQFLINT;
+	msi = MSIX_IQFLINT;
 	for_each_ethrxq(s, rxq) {
 		err = request_irq(adapter->msix_info[msi].vec,
 				  t4vf_sge_intr_msix, 0,
@@ -337,7 +335,7 @@ static void free_msix_queue_irqs(struct adapter *adapter)
 	int rxq, msi;
 
 	free_irq(adapter->msix_info[MSIX_FW].vec, &s->fw_evtq);
-	msi = MSIX_NIQFLINT;
+	msi = MSIX_IQFLINT;
 	for_each_ethrxq(s, rxq)
 		free_irq(adapter->msix_info[msi++].vec,
 			 &s->ethrxq[rxq].rspq);
@@ -527,7 +525,7 @@ static int setup_sge_queues(struct adapter *adapter)
 	 * brought up at which point lots of things get nailed down
 	 * permanently ...
 	 */
-	msix = MSIX_NIQFLINT;
+	msix = MSIX_IQFLINT;
 	for_each_port(adapter, pidx) {
 		struct net_device *dev = adapter->port[pidx];
 		struct port_info *pi = netdev_priv(dev);
@@ -751,13 +749,19 @@ static int cxgb4vf_open(struct net_device *dev)
 	netif_set_real_num_tx_queues(dev, pi->nqsets);
 	err = netif_set_real_num_rx_queues(dev, pi->nqsets);
 	if (err)
-		return err;
-	set_bit(pi->port_id, &adapter->open_device_map);
+		goto err_unwind;
 	err = link_start(dev);
 	if (err)
-		return err;
+		goto err_unwind;
+
 	netif_tx_start_all_queues(dev);
+	set_bit(pi->port_id, &adapter->open_device_map);
 	return 0;
+
+err_unwind:
+	if (adapter->open_device_map == 0)
+		adapter_down(adapter);
+	return err;
 }
 
 /*
@@ -766,13 +770,12 @@ static int cxgb4vf_open(struct net_device *dev)
  */
 static int cxgb4vf_stop(struct net_device *dev)
 {
-	int ret;
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
 
 	netif_tx_stop_all_queues(dev);
 	netif_carrier_off(dev);
-	ret = t4vf_enable_vi(adapter, pi->viid, false, false);
+	t4vf_enable_vi(adapter, pi->viid, false, false);
 	pi->link_cfg.link_ok = 0;
 
 	clear_bit(pi->port_id, &adapter->open_device_map);
@@ -816,40 +819,48 @@ static struct net_device_stats *cxgb4vf_get_stats(struct net_device *dev)
 }
 
 /*
- * Collect up to maxaddrs worth of a netdevice's unicast addresses into an
- * array of addrss pointers and return the number collected.
+ * Collect up to maxaddrs worth of a netdevice's unicast addresses, starting
+ * at a specified offset within the list, into an array of addrss pointers and
+ * return the number collected.
  */
-static inline int collect_netdev_uc_list_addrs(const struct net_device *dev,
-					       const u8 **addr,
-					       unsigned int maxaddrs)
+static inline unsigned int collect_netdev_uc_list_addrs(const struct net_device *dev,
+							const u8 **addr,
+							unsigned int offset,
+							unsigned int maxaddrs)
 {
+	unsigned int index = 0;
 	unsigned int naddr = 0;
 	const struct netdev_hw_addr *ha;
 
-	for_each_dev_addr(dev, ha) {
-		addr[naddr++] = ha->addr;
-		if (naddr >= maxaddrs)
-			break;
-	}
+	for_each_dev_addr(dev, ha)
+		if (index++ >= offset) {
+			addr[naddr++] = ha->addr;
+			if (naddr >= maxaddrs)
+				break;
+		}
 	return naddr;
 }
 
 /*
- * Collect up to maxaddrs worth of a netdevice's multicast addresses into an
- * array of addrss pointers and return the number collected.
+ * Collect up to maxaddrs worth of a netdevice's multicast addresses, starting
+ * at a specified offset within the list, into an array of addrss pointers and
+ * return the number collected.
  */
-static inline int collect_netdev_mc_list_addrs(const struct net_device *dev,
-					       const u8 **addr,
-					       unsigned int maxaddrs)
+static inline unsigned int collect_netdev_mc_list_addrs(const struct net_device *dev,
+							const u8 **addr,
+							unsigned int offset,
+							unsigned int maxaddrs)
 {
+	unsigned int index = 0;
 	unsigned int naddr = 0;
 	const struct netdev_hw_addr *ha;
 
-	netdev_for_each_mc_addr(ha, dev) {
-		addr[naddr++] = ha->addr;
-		if (naddr >= maxaddrs)
-			break;
-	}
+	netdev_for_each_mc_addr(ha, dev)
+		if (index++ >= offset) {
+			addr[naddr++] = ha->addr;
+			if (naddr >= maxaddrs)
+				break;
+		}
 	return naddr;
 }
 
@@ -862,16 +873,20 @@ static int set_addr_filters(const struct net_device *dev, bool sleep)
 	u64 mhash = 0;
 	u64 uhash = 0;
 	bool free = true;
-	u16 filt_idx[7];
+	unsigned int offset, naddr;
 	const u8 *addr[7];
-	int ret, naddr = 0;
+	int ret;
 	const struct port_info *pi = netdev_priv(dev);
 
 	/* first do the secondary unicast addresses */
-	naddr = collect_netdev_uc_list_addrs(dev, addr, ARRAY_SIZE(addr));
-	if (naddr > 0) {
+	for (offset = 0; ; offset += naddr) {
+		naddr = collect_netdev_uc_list_addrs(dev, addr, offset,
+						     ARRAY_SIZE(addr));
+		if (naddr == 0)
+			break;
+
 		ret = t4vf_alloc_mac_filt(pi->adapter, pi->viid, free,
-					  naddr, addr, filt_idx, &uhash, sleep);
+					  naddr, addr, NULL, &uhash, sleep);
 		if (ret < 0)
 			return ret;
 
@@ -879,12 +894,17 @@ static int set_addr_filters(const struct net_device *dev, bool sleep)
 	}
 
 	/* next set up the multicast addresses */
-	naddr = collect_netdev_mc_list_addrs(dev, addr, ARRAY_SIZE(addr));
-	if (naddr > 0) {
+	for (offset = 0; ; offset += naddr) {
+		naddr = collect_netdev_mc_list_addrs(dev, addr, offset,
+						     ARRAY_SIZE(addr));
+		if (naddr == 0)
+			break;
+
 		ret = t4vf_alloc_mac_filt(pi->adapter, pi->viid, free,
-					  naddr, addr, filt_idx, &mhash, sleep);
+					  naddr, addr, NULL, &mhash, sleep);
 		if (ret < 0)
 			return ret;
+		free = false;
 	}
 
 	return t4vf_set_addr_hash(pi->adapter, pi->viid, uhash != 0,
@@ -1348,6 +1368,8 @@ struct queue_port_stats {
 	u64 rx_csum;
 	u64 vlan_ex;
 	u64 vlan_ins;
+	u64 lro_pkts;
+	u64 lro_merged;
 };
 
 /*
@@ -1385,6 +1407,8 @@ static const char stats_strings[][ETH_GSTRING_LEN] = {
 	"RxCsumGood        ",
 	"VLANextractions   ",
 	"VLANinsertions    ",
+	"GROPackets        ",
+	"GROMerged         ",
 };
 
 /*
@@ -1434,6 +1458,8 @@ static void collect_sge_port_stats(const struct adapter *adapter,
 		stats->rx_csum += rxq->stats.rx_cso;
 		stats->vlan_ex += rxq->stats.vlan_ex;
 		stats->vlan_ins += txq->vlan_ins;
+		stats->lro_pkts += rxq->stats.lro_pkts;
+		stats->lro_merged += rxq->stats.lro_merged;
 	}
 }
 
@@ -1530,14 +1556,19 @@ static void cxgb4vf_get_wol(struct net_device *dev,
 }
 
 /*
+ * TCP Segmentation Offload flags which we support.
+ */
+#define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+
+/*
  * Set TCP Segmentation Offloading feature capabilities.
  */
 static int cxgb4vf_set_tso(struct net_device *dev, u32 tso)
 {
 	if (tso)
-		dev->features |= NETIF_F_TSO | NETIF_F_TSO6;
+		dev->features |= TSO_FLAGS;
 	else
-		dev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+		dev->features &= ~TSO_FLAGS;
 	return 0;
 }
 
@@ -2028,7 +2059,7 @@ static int __devinit setup_debugfs(struct adapter *adapter)
  * Tear down the /sys/kernel/debug/cxgb4vf sub-nodes created above.  We leave
  * it to our caller to tear down the directory (debugfs_root).
  */
-static void __devexit cleanup_debugfs(struct adapter *adapter)
+static void cleanup_debugfs(struct adapter *adapter)
 {
 	BUG_ON(adapter->debugfs_root == NULL);
 
@@ -2046,7 +2077,7 @@ static void __devexit cleanup_debugfs(struct adapter *adapter)
  * adapter parameters we're going to be using and initialize basic adapter
  * hardware support.
  */
-static int adap_init0(struct adapter *adapter)
+static int __devinit adap_init0(struct adapter *adapter)
 {
 	struct vf_resources *vfres = &adapter->params.vfres;
 	struct sge_params *sge_params = &adapter->params.sge;
@@ -2252,6 +2283,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
 {
 	struct sge *s = &adapter->sge;
 	int q10g, n10g, qidx, pidx, qs;
+	size_t iqe_size;
 
 	/*
 	 * We should not be called till we know how many Queue Sets we can
@@ -2296,6 +2328,13 @@ static void __devinit cfg_queues(struct adapter *adapter)
 	s->ethqsets = qidx;
 
 	/*
+	 * The Ingress Queue Entry Size for our various Response Queues needs
+	 * to be big enough to accommodate the largest message we can receive
+	 * from the chip/firmware; which is 64 bytes ...
+	 */
+	iqe_size = 64;
+
+	/*
 	 * Set up default Queue Set parameters ...  Start off with the
 	 * shortest interrupt holdoff timer.
 	 */
@@ -2303,7 +2342,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
 		struct sge_eth_rxq *rxq = &s->ethrxq[qs];
 		struct sge_eth_txq *txq = &s->ethtxq[qs];
 
-		init_rspq(&rxq->rspq, 0, 0, 1024, L1_CACHE_BYTES);
+		init_rspq(&rxq->rspq, 0, 0, 1024, iqe_size);
 		rxq->fl.size = 72;
 		txq->q.size = 1024;
 	}
@@ -2312,8 +2351,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
 	 * The firmware event queue is used for link state changes and
 	 * notifications of TX DMA completions.
 	 */
-	init_rspq(&s->fw_evtq, SGE_TIMER_RSTRT_CNTR, 0, 512,
-		  L1_CACHE_BYTES);
+	init_rspq(&s->fw_evtq, SGE_TIMER_RSTRT_CNTR, 0, 512, iqe_size);
 
 	/*
 	 * The forwarded interrupt queue is used when we're in MSI interrupt
@@ -2329,7 +2367,7 @@ static void __devinit cfg_queues(struct adapter *adapter)
 	 * any time ...
 	 */
 	init_rspq(&s->intrq, SGE_TIMER_RSTRT_CNTR, 0, MSIX_ENTRIES + 1,
-		  L1_CACHE_BYTES);
+		  iqe_size);
 }
 
 /*
@@ -2470,7 +2508,6 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
 		version_printed = 1;
 	}
 
-
 	/*
 	 * Initialize generic PCI device state.
 	 */
@@ -2607,7 +2644,7 @@ static int __devinit cxgb4vf_pci_probe(struct pci_dev *pdev,
 		netif_carrier_off(netdev);
 		netdev->irq = pdev->irq;
 
-		netdev->features = (NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
+		netdev->features = (NETIF_F_SG | TSO_FLAGS |
 				    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 				    NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX |
 				    NETIF_F_GRO);
diff --git a/drivers/net/cxgb4vf/sge.c b/drivers/net/cxgb4vf/sge.c
index ecf0770bf0f..e0b3d1bc2fd 100644
--- a/drivers/net/cxgb4vf/sge.c
+++ b/drivers/net/cxgb4vf/sge.c
@@ -1568,6 +1568,9 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 	} else
 		skb_checksum_none_assert(skb);
 
+	/*
+	 * Deliver the packet to the stack.
+	 */
 	if (unlikely(pkt->vlan_ex)) {
 		struct vlan_group *grp = pi->vlan_grp;
 
@@ -2143,7 +2146,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 
 		/*
 		 * Calculate the size of the hardware free list ring plus
-		 * status page (which the SGE will place at the end of the
+		 * Status Page (which the SGE will place after the end of the
 		 * free list ring) in Egress Queue Units.
 		 */
 		flsz = (fl->size / FL_PER_EQ_UNIT +
@@ -2240,8 +2243,8 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq,
 	struct port_info *pi = netdev_priv(dev);
 
 	/*
-	 * Calculate the size of the hardware TX Queue (including the
-	 * status age on the end) in units of TX Descriptors.
+	 * Calculate the size of the hardware TX Queue (including the Status
+	 * Page on the end of the TX Queue) in units of TX Descriptors.
 	 */
 	nentries = txq->q.size + STAT_LEN / sizeof(struct tx_desc);
 
diff --git a/drivers/net/cxgb4vf/t4vf_hw.c b/drivers/net/cxgb4vf/t4vf_hw.c
index e306c20dfae..0f51c80475c 100644
--- a/drivers/net/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/cxgb4vf/t4vf_hw.c
@@ -116,7 +116,7 @@ static void dump_mbox(struct adapter *adapter, const char *tag, u32 mbox_data)
 int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 		      void *rpl, bool sleep_ok)
 {
-	static int delay[] = {
+	static const int delay[] = {
 		1, 1, 3, 5, 10, 10, 20, 50, 100
 	};
 
@@ -147,9 +147,20 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 	/*
 	 * Write the command array into the Mailbox Data register array and
 	 * transfer ownership of the mailbox to the firmware.
+	 *
+	 * For the VFs, the Mailbox Data "registers" are actually backed by
+	 * T4's "MA" interface rather than PL Registers (as is the case for
+	 * the PFs).  Because these are in different coherency domains, the
+	 * write to the VF's PL-register-backed Mailbox Control can race in
+	 * front of the writes to the MA-backed VF Mailbox Data "registers".
+	 * So we need to do a read-back on at least one byte of the VF Mailbox
+	 * Data registers before doing the write to the VF Mailbox Control
+	 * register.
 	 */
 	for (i = 0, p = cmd; i < size; i += 8)
 		t4_write_reg64(adapter, mbox_data + i, be64_to_cpu(*p++));
+	t4_read_reg(adapter, mbox_data);         /* flush write */
+
 	t4_write_reg(adapter, mbox_ctl,
 		     MBMSGVALID | MBOWNER(MBOX_OWNER_FW));
 	t4_read_reg(adapter, mbox_ctl);          /* flush write */
@@ -1014,48 +1025,72 @@ int t4vf_alloc_mac_filt(struct adapter *adapter, unsigned int viid, bool free,
 			unsigned int naddr, const u8 **addr, u16 *idx,
 			u64 *hash, bool sleep_ok)
 {
-	int i, ret;
+	int offset, ret = 0;
+	unsigned nfilters = 0;
+	unsigned int rem = naddr;
 	struct fw_vi_mac_cmd cmd, rpl;
-	struct fw_vi_mac_exact *p;
-	size_t len16;
 
-	if (naddr > ARRAY_SIZE(cmd.u.exact))
+	if (naddr > FW_CLS_TCAM_NUM_ENTRIES)
 		return -EINVAL;
-	len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
-				      u.exact[naddr]), 16);
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) |
-				     FW_CMD_REQUEST |
-				     FW_CMD_WRITE |
-				     (free ? FW_CMD_EXEC : 0) |
-				     FW_VI_MAC_CMD_VIID(viid));
-	cmd.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) |
-					    FW_CMD_LEN16(len16));
+	for (offset = 0; offset < naddr; /**/) {
+		unsigned int fw_naddr = (rem < ARRAY_SIZE(cmd.u.exact)
+					 ? rem
+					 : ARRAY_SIZE(cmd.u.exact));
+		size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
+						     u.exact[fw_naddr]), 16);
+		struct fw_vi_mac_exact *p;
+		int i;
 
-	for (i = 0, p = cmd.u.exact; i < naddr; i++, p++) {
-		p->valid_to_idx =
-			cpu_to_be16(FW_VI_MAC_CMD_VALID |
-				    FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC));
-		memcpy(p->macaddr, addr[i], sizeof(p->macaddr));
-	}
+		memset(&cmd, 0, sizeof(cmd));
+		cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) |
+					     FW_CMD_REQUEST |
+					     FW_CMD_WRITE |
+					     (free ? FW_CMD_EXEC : 0) |
+					     FW_VI_MAC_CMD_VIID(viid));
+		cmd.freemacs_to_len16 =
+			cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) |
+				    FW_CMD_LEN16(len16));
+
+		for (i = 0, p = cmd.u.exact; i < fw_naddr; i++, p++) {
+			p->valid_to_idx = cpu_to_be16(
+				FW_VI_MAC_CMD_VALID |
+				FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC));
+			memcpy(p->macaddr, addr[offset+i], sizeof(p->macaddr));
+		}
+
+
+		ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl,
+					sleep_ok);
+		if (ret && ret != -ENOMEM)
+			break;
 
-	ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl, sleep_ok);
-	if (ret)
-		return ret;
-
-	for (i = 0, p = rpl.u.exact; i < naddr; i++, p++) {
-		u16 index = FW_VI_MAC_CMD_IDX_GET(be16_to_cpu(p->valid_to_idx));
-
-		if (idx)
-			idx[i] = (index >= FW_CLS_TCAM_NUM_ENTRIES
-				  ? 0xffff
-				  : index);
-		if (index < FW_CLS_TCAM_NUM_ENTRIES)
-			ret++;
-		else if (hash)
-			*hash |= (1 << hash_mac_addr(addr[i]));
+		for (i = 0, p = rpl.u.exact; i < fw_naddr; i++, p++) {
+			u16 index = FW_VI_MAC_CMD_IDX_GET(
+				be16_to_cpu(p->valid_to_idx));
+
+			if (idx)
+				idx[offset+i] =
+					(index >= FW_CLS_TCAM_NUM_ENTRIES
+					 ? 0xffff
+					 : index);
+			if (index < FW_CLS_TCAM_NUM_ENTRIES)
+				nfilters++;
+			else if (hash)
+				*hash |= (1ULL << hash_mac_addr(addr[offset+i]));
+		}
+
+		free = false;
+		offset += fw_naddr;
+		rem -= fw_naddr;
 	}
+
+	/*
+	 * If there were no errors or we merely ran out of room in our MAC
+	 * address arena, return the number of filters actually written.
+	 */
+	if (ret == 0 || ret == -ENOMEM)
+		ret = nfilters;
 	return ret;
 }
 
@@ -1276,7 +1311,7 @@ int t4vf_eth_eq_free(struct adapter *adapter, unsigned int eqid)
  */
 int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
 {
-	struct fw_cmd_hdr *cmd_hdr = (struct fw_cmd_hdr *)rpl;
+	const struct fw_cmd_hdr *cmd_hdr = (const struct fw_cmd_hdr *)rpl;
 	u8 opcode = FW_CMD_OP_GET(be32_to_cpu(cmd_hdr->hi));
 
 	switch (opcode) {
@@ -1284,7 +1319,8 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
 		/*
 		 * Link/module state change message.
 		 */
-		const struct fw_port_cmd *port_cmd = (void *)rpl;
+		const struct fw_port_cmd *port_cmd =
+			(const struct fw_port_cmd *)rpl;
 		u32 word;
 		int action, port_id, link_ok, speed, fc, pidx;