Linux-libre 4.3.2-gnu

15 files changed, 272 insertions, 67 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 0a3202047..2177e56ed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2398,7 +2398,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 			}
 		}
 
-		memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size);
+		memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
 		priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
 		INIT_WORK(&priv->mfunc.master.comm_work,
 			  mlx4_master_comm_channel);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 63769df87..eb8a4988d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -100,7 +100,6 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int err = 0;
-	char name[25];
 	int timestamp_en = 0;
 	bool assigned_eq = false;
 
@@ -119,8 +118,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 			err = mlx4_assign_eq(mdev->dev, priv->port,
 					     &cq->vector);
 			if (err) {
-				mlx4_err(mdev, "Failed assigning an EQ to %s\n",
-					 name);
+				mlx4_err(mdev, "Failed assigning an EQ to CQ vector %d\n",
+					 cq->vector);
 				goto free_eq;
 			}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 99ba1c50e..f79d81243 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -102,6 +102,7 @@ mlx4_en_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 
 static const char mlx4_en_priv_flags[][ETH_GSTRING_LEN] = {
 	"blueflame",
+	"phv-bit"
 };
 
 static const char main_strings[][ETH_GSTRING_LEN] = {
@@ -1797,35 +1798,49 @@ static int mlx4_en_get_ts_info(struct net_device *dev,
 static int mlx4_en_set_priv_flags(struct net_device *dev, u32 flags)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
 	bool bf_enabled_new = !!(flags & MLX4_EN_PRIV_FLAGS_BLUEFLAME);
 	bool bf_enabled_old = !!(priv->pflags & MLX4_EN_PRIV_FLAGS_BLUEFLAME);
+	bool phv_enabled_new = !!(flags & MLX4_EN_PRIV_FLAGS_PHV);
+	bool phv_enabled_old = !!(priv->pflags & MLX4_EN_PRIV_FLAGS_PHV);
 	int i;
+	int ret = 0;
 
-	if (bf_enabled_new == bf_enabled_old)
-		return 0; /* Nothing to do */
+	if (bf_enabled_new != bf_enabled_old) {
+		if (bf_enabled_new) {
+			bool bf_supported = true;
 
-	if (bf_enabled_new) {
-		bool bf_supported = true;
+			for (i = 0; i < priv->tx_ring_num; i++)
+				bf_supported &= priv->tx_ring[i]->bf_alloced;
 
-		for (i = 0; i < priv->tx_ring_num; i++)
-			bf_supported &= priv->tx_ring[i]->bf_alloced;
+			if (!bf_supported) {
+				en_err(priv, "BlueFlame is not supported\n");
+				return -EINVAL;
+			}
 
-		if (!bf_supported) {
-			en_err(priv, "BlueFlame is not supported\n");
-			return -EINVAL;
+			priv->pflags |= MLX4_EN_PRIV_FLAGS_BLUEFLAME;
+		} else {
+			priv->pflags &= ~MLX4_EN_PRIV_FLAGS_BLUEFLAME;
 		}
 
-		priv->pflags |= MLX4_EN_PRIV_FLAGS_BLUEFLAME;
-	} else {
-		priv->pflags &= ~MLX4_EN_PRIV_FLAGS_BLUEFLAME;
-	}
-
-	for (i = 0; i < priv->tx_ring_num; i++)
-		priv->tx_ring[i]->bf_enabled = bf_enabled_new;
+		for (i = 0; i < priv->tx_ring_num; i++)
+			priv->tx_ring[i]->bf_enabled = bf_enabled_new;
 
-	en_info(priv, "BlueFlame %s\n",
-		bf_enabled_new ?  "Enabled" : "Disabled");
+		en_info(priv, "BlueFlame %s\n",
+			bf_enabled_new ?  "Enabled" : "Disabled");
+	}
 
+	if (phv_enabled_new != phv_enabled_old) {
+		ret = set_phv_bit(mdev->dev, priv->port, (int)phv_enabled_new);
+		if (ret)
+			return ret;
+		else if (phv_enabled_new)
+			priv->pflags |= MLX4_EN_PRIV_FLAGS_PHV;
+		else
+			priv->pflags &= ~MLX4_EN_PRIV_FLAGS_PHV;
+		en_info(priv, "PHV bit %s\n",
+			phv_enabled_new ?  "Enabled" : "Disabled");
+	}
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 913b716ed..a946e4bf7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -224,6 +224,26 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
 	kfree(mdev);
 }
 
+static void mlx4_en_activate(struct mlx4_dev *dev, void *ctx)
+{
+	int i;
+	struct mlx4_en_dev *mdev = ctx;
+
+	/* Create a netdev for each port */
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+		mlx4_info(mdev, "Activating port:%d\n", i);
+		if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i]))
+			mdev->pndev[i] = NULL;
+	}
+
+	/* register notifier */
+	mdev->nb.notifier_call = mlx4_en_netdev_event;
+	if (register_netdevice_notifier(&mdev->nb)) {
+		mdev->nb.notifier_call = NULL;
+		mlx4_err(mdev, "Failed to create notifier\n");
+	}
+}
+
 static void *mlx4_en_add(struct mlx4_dev *dev)
 {
 	struct mlx4_en_dev *mdev;
@@ -297,21 +317,6 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	mutex_init(&mdev->state_lock);
 	mdev->device_up = true;
 
-	/* Setup ports */
-
-	/* Create a netdev for each port */
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
-		mlx4_info(mdev, "Activating port:%d\n", i);
-		if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i]))
-			mdev->pndev[i] = NULL;
-	}
-	/* register notifier */
-	mdev->nb.notifier_call = mlx4_en_netdev_event;
-	if (register_netdevice_notifier(&mdev->nb)) {
-		mdev->nb.notifier_call = NULL;
-		mlx4_err(mdev, "Failed to create notifier\n");
-	}
-
 	return mdev;
 
 err_mr:
@@ -335,6 +340,7 @@ static struct mlx4_interface mlx4_en_interface = {
 	.event		= mlx4_en_event,
 	.get_dev	= mlx4_en_get_netdev,
 	.protocol	= MLX4_PROT_ETH,
+	.activate	= mlx4_en_activate,
 };
 
 static void mlx4_en_verify_params(void)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index e0de2fd1c..4726122ea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2184,6 +2184,25 @@ static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	}
 }
 
+static netdev_features_t mlx4_en_fix_features(struct net_device *netdev,
+					      netdev_features_t features)
+{
+	struct mlx4_en_priv *en_priv = netdev_priv(netdev);
+	struct mlx4_en_dev *mdev = en_priv->mdev;
+
+	/* Since there is no support for separate RX C-TAG/S-TAG vlan accel
+	 * enable/disable make sure S-TAG flag is always in same state as
+	 * C-TAG.
+	 */
+	if (features & NETIF_F_HW_VLAN_CTAG_RX &&
+	    !(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN))
+		features |= NETIF_F_HW_VLAN_STAG_RX;
+	else
+		features &= ~NETIF_F_HW_VLAN_STAG_RX;
+
+	return features;
+}
+
 static int mlx4_en_set_features(struct net_device *netdev,
 		netdev_features_t features)
 {
@@ -2218,6 +2237,10 @@ static int mlx4_en_set_features(struct net_device *netdev,
 		en_info(priv, "Turn %s TX vlan strip offload\n",
 			(features & NETIF_F_HW_VLAN_CTAG_TX) ? "ON" : "OFF");
 
+	if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_HW_VLAN_STAG_TX))
+		en_info(priv, "Turn %s TX S-VLAN strip offload\n",
+			(features & NETIF_F_HW_VLAN_STAG_TX) ? "ON" : "OFF");
+
 	if (DEV_FEATURE_CHANGED(netdev, features, NETIF_F_LOOPBACK)) {
 		en_info(priv, "Turn %s loopback\n",
 			(features & NETIF_F_LOOPBACK) ? "ON" : "OFF");
@@ -2460,6 +2483,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_poll_controller	= mlx4_en_netpoll,
 #endif
 	.ndo_set_features	= mlx4_en_set_features,
+	.ndo_fix_features	= mlx4_en_fix_features,
 	.ndo_setup_tc		= mlx4_en_setup_tc,
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
@@ -2500,6 +2524,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = {
 	.ndo_poll_controller	= mlx4_en_netpoll,
 #endif
 	.ndo_set_features	= mlx4_en_set_features,
+	.ndo_fix_features	= mlx4_en_fix_features,
 	.ndo_setup_tc		= mlx4_en_setup_tc,
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer	= mlx4_en_filter_rfs,
@@ -2931,6 +2956,27 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	dev->hw_features |= NETIF_F_LOOPBACK |
 			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 
+	if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN)) {
+		dev->features |= NETIF_F_HW_VLAN_STAG_RX |
+			NETIF_F_HW_VLAN_STAG_FILTER;
+		dev->hw_features |= NETIF_F_HW_VLAN_STAG_RX;
+	}
+
+	if (mlx4_is_slave(mdev->dev)) {
+		int phv;
+
+		err = get_phv_bit(mdev->dev, port, &phv);
+		if (!err && phv) {
+			dev->hw_features |= NETIF_F_HW_VLAN_STAG_TX;
+			priv->pflags |= MLX4_EN_PRIV_FLAGS_PHV;
+		}
+	} else {
+		if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN &&
+		    !(mdev->dev->caps.flags2 &
+		      MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN))
+			dev->hw_features |= NETIF_F_HW_VLAN_STAG_TX;
+	}
+
 	if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP)
 		dev->hw_features |= NETIF_F_RXFCS;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 4f95fa7b5..e7a5000aa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -725,7 +725,7 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
-	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK) &&
+	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) &&
 	    !(dev_features & NETIF_F_HW_VLAN_CTAG_RX)) {
 		hw_checksum = get_fixed_vlan_csum(hw_checksum, hdr);
 		hdr += sizeof(struct vlan_hdr);
@@ -906,17 +906,25 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				gro_skb->csum_level = 1;
 
 			if ((cqe->vlan_my_qpn &
-			    cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK)) &&
+			    cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK)) &&
 			    (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
 				u16 vid = be16_to_cpu(cqe->sl_vid);
 
 				__vlan_hwaccel_put_tag(gro_skb, htons(ETH_P_8021Q), vid);
+			} else if ((be32_to_cpu(cqe->vlan_my_qpn) &
+				  MLX4_CQE_SVLAN_PRESENT_MASK) &&
+				 (dev->features & NETIF_F_HW_VLAN_STAG_RX)) {
+				__vlan_hwaccel_put_tag(gro_skb,
+						       htons(ETH_P_8021AD),
+						       be16_to_cpu(cqe->sl_vid));
 			}
 
 			if (dev->features & NETIF_F_RXHASH)
 				skb_set_hash(gro_skb,
 					     be32_to_cpu(cqe->immed_rss_invalid),
-					     PKT_HASH_TYPE_L3);
+					     (ip_summed == CHECKSUM_UNNECESSARY) ?
+						PKT_HASH_TYPE_L4 :
+						PKT_HASH_TYPE_L3);
 
 			skb_record_rx_queue(gro_skb, cq->ring);
 			skb_mark_napi_id(gro_skb, &cq->napi);
@@ -962,12 +970,19 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		if (dev->features & NETIF_F_RXHASH)
 			skb_set_hash(skb,
 				     be32_to_cpu(cqe->immed_rss_invalid),
-				     PKT_HASH_TYPE_L3);
+				     (ip_summed == CHECKSUM_UNNECESSARY) ?
+					PKT_HASH_TYPE_L4 :
+					PKT_HASH_TYPE_L3);
 
 		if ((be32_to_cpu(cqe->vlan_my_qpn) &
-		    MLX4_CQE_VLAN_PRESENT_MASK) &&
+		    MLX4_CQE_CVLAN_PRESENT_MASK) &&
 		    (dev->features & NETIF_F_HW_VLAN_CTAG_RX))
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->sl_vid));
+		else if ((be32_to_cpu(cqe->vlan_my_qpn) &
+			  MLX4_CQE_SVLAN_PRESENT_MASK) &&
+			 (dev->features & NETIF_F_HW_VLAN_STAG_RX))
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD),
+					       be16_to_cpu(cqe->sl_vid));
 
 		if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
 			timestamp = mlx4_en_get_cqe_ts(cqe);
@@ -1032,13 +1047,15 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 
 	/* If we used up all the quota - we're probably not done yet... */
 	if (done == budget) {
-		int cpu_curr;
 		const struct cpumask *aff;
+		struct irq_data *idata;
+		int cpu_curr;
 
 		INC_PERF_COUNTER(priv->pstats.napi_quota);
 
 		cpu_curr = smp_processor_id();
-		aff = irq_desc_get_irq_data(cq->irq_desc)->affinity;
+		idata = irq_desc_get_irq_data(cq->irq_desc);
+		aff = irq_data_get_affinity_mask(idata);
 
 		if (likely(cpumask_test_cpu(cpu_curr, aff)))
 			return budget;
@@ -1065,7 +1082,10 @@ static const int frag_sizes[] = {
 void mlx4_en_calc_rx_buf(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	int eff_mtu = dev->mtu + ETH_HLEN + VLAN_HLEN;
+	/* VLAN_HLEN is added twice,to support skb vlan tagged with multiple
+	 * headers. (For example: ETH_P_8021Q and ETH_P_8021AD).
+	 */
+	int eff_mtu = dev->mtu + ETH_HLEN + (2 * VLAN_HLEN);
 	int buf_size = 0;
 	int i = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index c10d98f6a..4421bf546 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -718,6 +718,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	u32 index, bf_index;
 	__be32 op_own;
 	u16 vlan_tag = 0;
+	u16 vlan_proto = 0;
 	int i_frag;
 	int lso_header_size;
 	void *fragptr = NULL;
@@ -750,9 +751,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_drop;
 	}
 
-	if (skb_vlan_tag_present(skb))
+	if (skb_vlan_tag_present(skb)) {
 		vlan_tag = skb_vlan_tag_get(skb);
-
+		vlan_proto = be16_to_cpu(skb->vlan_proto);
+	}
 
 	netdev_txq_bql_enqueue_prefetchw(ring->tx_queue);
 
@@ -958,8 +960,13 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		ring->bf.offset ^= ring->bf.buf_size;
 	} else {
 		tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
-		tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
-			!!skb_vlan_tag_present(skb);
+		if (vlan_proto == ETH_P_8021AD)
+			tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN;
+		else if (vlan_proto == ETH_P_8021Q)
+			tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN;
+		else
+			tx_desc->ctrl.ins_vlan = 0;
+
 		tx_desc->ctrl.fence_size = real_size;
 
 		/* Ensure new descriptor hits memory
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 8e81e53c3..603d1c3d3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -196,7 +196,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 		return;
 	}
 
-	memcpy(s_eqe, eqe, dev->caps.eqe_size - 1);
+	memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
 	s_eqe->slave_id = slave;
 	/* ensure all information is written before setting the ownersip bit */
 	dma_wmb();
@@ -1364,6 +1364,10 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 	 * and performing a NOP command
 	 */
 	for(i = 0; !err && (i < dev->caps.num_comp_vectors); ++i) {
+		/* Make sure request_irq was called */
+		if (!priv->eq_table.eq[i].have_irq)
+			continue;
+
 		/* Temporary use polling for command completions */
 		mlx4_cmd_use_polling(dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index e30bf57ad..e8ec1dec5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -154,6 +154,7 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[26] = "Port ETS Scheduler support",
 		[27] = "Port beacon support",
 		[28] = "RX-ALL support",
+		[29] = "802.1ad offload support",
 	};
 	int i;
 
@@ -307,6 +308,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 
 #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
 #define QUERY_FUNC_CAP_SUPPORTS_NON_POWER_OF_2_NUM_EQS (1 << 31)
+#define QUERY_FUNC_CAP_PHV_BIT			0x40
 
 	if (vhcr->op_modifier == 1) {
 		struct mlx4_active_ports actv_ports =
@@ -351,6 +353,12 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier],
 			 QUERY_FUNC_CAP_PHYS_PORT_ID);
 
+		if (dev->caps.phv_bit[port]) {
+			field = QUERY_FUNC_CAP_PHV_BIT;
+			MLX4_PUT(outbox->buf, field,
+				 QUERY_FUNC_CAP_FLAGS0_OFFSET);
+		}
+
 	} else if (vhcr->op_modifier == 0) {
 		struct mlx4_active_ports actv_ports =
 			mlx4_get_active_ports(dev, slave);
@@ -600,6 +608,9 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 		MLX4_GET(func_cap->phys_port_id, outbox,
 			 QUERY_FUNC_CAP_PHYS_PORT_ID);
 
+	MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS0_OFFSET);
+	func_cap->flags |= (field & QUERY_FUNC_CAP_PHV_BIT);
+
 	/* All other resources are allocated by the master, but we still report
 	 * 'num' and 'reserved' capabilities as follows:
 	 * - num remains the maximum resource index
@@ -700,6 +711,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_D_MPT_ENTRY_SZ_OFFSET	0x92
 #define QUERY_DEV_CAP_BMME_FLAGS_OFFSET		0x94
 #define QUERY_DEV_CAP_CONFIG_DEV_OFFSET		0x94
+#define QUERY_DEV_CAP_PHV_EN_OFFSET		0x96
 #define QUERY_DEV_CAP_RSVD_LKEY_OFFSET		0x98
 #define QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET		0xa0
 #define QUERY_DEV_CAP_ETH_BACKPL_OFFSET		0x9c
@@ -898,6 +910,12 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_CONFIG_DEV;
 	if (field & (1 << 2))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_IGNORE_FCS;
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_PHV_EN_OFFSET);
+	if (field & 0x80)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_PHV_EN;
+	if (field & 0x40)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN;
+
 	MLX4_GET(dev_cap->reserved_lkey, outbox,
 		 QUERY_DEV_CAP_RSVD_LKEY_OFFSET);
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_ETH_BACKPL_OFFSET);
@@ -1992,6 +2010,10 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	MLX4_GET(param->uar_page_sz, outbox, INIT_HCA_UAR_PAGE_SZ_OFFSET);
 	MLX4_GET(param->log_uar_sz, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
 
+	/* phv_check enable */
+	MLX4_GET(byte_field, outbox, INIT_HCA_CACHELINE_SZ_OFFSET);
+	if (byte_field & 0x2)
+		param->phv_check_en = 1;
 out:
 	mlx4_free_cmd_mailbox(dev, mailbox);
 
@@ -2758,3 +2780,63 @@ int mlx4_ACCESS_REG_wrapper(struct mlx4_dev *dev, int slave,
 			    0, MLX4_CMD_ACCESS_REG, MLX4_CMD_TIME_CLASS_C,
 			    MLX4_CMD_NATIVE);
 }
+
+static int mlx4_SET_PORT_phv_bit(struct mlx4_dev *dev, u8 port, u8 phv_bit)
+{
+#define SET_PORT_GEN_PHV_VALID	0x10
+#define SET_PORT_GEN_PHV_EN	0x80
+
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_set_port_general_context *context;
+	u32 in_mod;
+	int err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+	context = mailbox->buf;
+
+	context->v_ignore_fcs |=  SET_PORT_GEN_PHV_VALID;
+	if (phv_bit)
+		context->phv_en |=  SET_PORT_GEN_PHV_EN;
+
+	in_mod = MLX4_SET_PORT_GENERAL << 8 | port;
+	err = mlx4_cmd(dev, mailbox->dma, in_mod, MLX4_SET_PORT_ETH_OPCODE,
+		       MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+		       MLX4_CMD_NATIVE);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+int get_phv_bit(struct mlx4_dev *dev, u8 port, int *phv)
+{
+	int err;
+	struct mlx4_func_cap func_cap;
+
+	memset(&func_cap, 0, sizeof(func_cap));
+	err = mlx4_QUERY_FUNC_CAP(dev, port, &func_cap);
+	if (!err)
+		*phv = func_cap.flags & QUERY_FUNC_CAP_PHV_BIT;
+	return err;
+}
+EXPORT_SYMBOL(get_phv_bit);
+
+int set_phv_bit(struct mlx4_dev *dev, u8 port, int new_val)
+{
+	int ret;
+
+	if (mlx4_is_slave(dev))
+		return -EPERM;
+
+	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN &&
+	    !(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SKIP_OUTER_VLAN)) {
+		ret = mlx4_SET_PORT_phv_bit(dev, port, new_val);
+		if (!ret)
+			dev->caps.phv_bit[port] = new_val;
+		return ret;
+	}
+
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(set_phv_bit);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 07cb7c246..08de5555c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -204,6 +204,7 @@ struct mlx4_init_hca_param {
 	u16 cqe_size; /* For use only when CQE stride feature enabled */
 	u16 eqe_size; /* For use only when EQE stride feature enabled */
 	u8 rss_ip_frags;
+	u8 phv_check_en; /* for QUERY_HCA */
 };
 
 struct mlx4_init_ib_param {
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 0d80aed59..0472941af 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -63,8 +63,11 @@ static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv)
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
 		spin_unlock_irq(&priv->ctx_lock);
+		if (intf->activate)
+			intf->activate(&priv->dev, dev_ctx->context);
 	} else
 		kfree(dev_ctx);
+
 }
 
 static void mlx4_remove_device(struct mlx4_interface *intf, struct mlx4_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index a408977a5..cc3a98975 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -405,6 +405,21 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 
+	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) {
+		struct mlx4_init_hca_param hca_param;
+
+		memset(&hca_param, 0, sizeof(hca_param));
+		err = mlx4_QUERY_HCA(dev, &hca_param);
+		/* Turn off PHV_EN flag in case phv_check_en is set.
+		 * phv_check_en is a HW check that parse the packet and verify
+		 * phv bit was reported correctly in the wqe. To allow QinQ
+		 * PHV_EN flag should be set and phv_check_en must be cleared
+		 * otherwise QinQ packets will be drop by the HW.
+		 */
+		if (err || hca_param.phv_check_en)
+			dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_PHV_EN;
+	}
+
 	/* Sense port always allowed on supported devices for ConnectX-1 and -2 */
 	if (mlx4_priv(dev)->pci_dev_data & MLX4_PCI_DEV_FORCE_SENSE_PORT)
 		dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;
@@ -2654,14 +2669,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 
 	if (msi_x) {
 		int nreq = dev->caps.num_ports * num_online_cpus() + 1;
-		bool shared_ports = false;
 
 		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
 			     nreq);
-		if (nreq > MAX_MSIX) {
+		if (nreq > MAX_MSIX)
 			nreq = MAX_MSIX;
-			shared_ports = true;
-		}
 
 		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
 		if (!entries)
@@ -2684,9 +2696,6 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 		bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports,
 			    dev->caps.num_ports);
 
-		if (MLX4_IS_LEGACY_EQ_MODE(dev->caps))
-			shared_ports = true;
-
 		for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) {
 			if (i == MLX4_EQ_ASYNC)
 				continue;
@@ -2694,7 +2703,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 			priv->eq_table.eq[i].irq =
 				entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector;
 
-			if (shared_ports) {
+			if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) {
 				bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
 					    dev->caps.num_ports);
 				/* We don't set affinity hint when there
@@ -2920,6 +2929,8 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
 {
 	u64 dev_flags = dev->flags;
 	int err = 0;
+	int fw_enabled_sriov_vfs = min(pci_sriov_get_totalvfs(pdev),
+					MLX4_MAX_NUM_VF);
 
 	if (reset_flow) {
 		dev->dev_vfs = kcalloc(total_vfs, sizeof(*dev->dev_vfs),
@@ -2945,6 +2956,12 @@ static u64 mlx4_enable_sriov(struct mlx4_dev *dev, struct pci_dev *pdev,
 	}
 
 	if (!(dev->flags &  MLX4_FLAG_SRIOV)) {
+		if (total_vfs > fw_enabled_sriov_vfs) {
+			mlx4_err(dev, "requested vfs (%d) > available vfs (%d). Continuing without SR_IOV\n",
+				 total_vfs, fw_enabled_sriov_vfs);
+			err = -ENOMEM;
+			goto disable_sriov;
+		}
 		mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", total_vfs);
 		err = pci_enable_sriov(pdev, total_vfs);
 	}
@@ -3426,20 +3443,20 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 			goto err_disable_pdev;
 		}
 	}
-	if (total_vfs >= MLX4_MAX_NUM_VF) {
+	if (total_vfs > MLX4_MAX_NUM_VF) {
 		dev_err(&pdev->dev,
-			"Requested more VF's (%d) than allowed (%d)\n",
-			total_vfs, MLX4_MAX_NUM_VF - 1);
+			"Requested more VF's (%d) than allowed by hw (%d)\n",
+			total_vfs, MLX4_MAX_NUM_VF);
 		err = -EINVAL;
 		goto err_disable_pdev;
 	}
 
 	for (i = 0; i < MLX4_MAX_PORTS; i++) {
-		if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) {
+		if (nvfs[i] + nvfs[2] > MLX4_MAX_NUM_VF_P_PORT) {
 			dev_err(&pdev->dev,
-				"Requested more VF's (%d) for port (%d) than allowed (%d)\n",
+				"Requested more VF's (%d) for port (%d) than allowed by driver (%d)\n",
 				nvfs[i] + nvfs[2], i + 1,
-				MLX4_MAX_NUM_VF_P_PORT - 1);
+				MLX4_MAX_NUM_VF_P_PORT);
 			err = -EINVAL;
 			goto err_disable_pdev;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index bd9ea0d01..1d4e2e054 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1184,10 +1184,11 @@ out:
 	if (prot == MLX4_PROT_ETH) {
 		/* manage the steering entry for promisc mode */
 		if (new_entry)
-			new_steering_entry(dev, port, steer, index, qp->qpn);
+			err = new_steering_entry(dev, port, steer,
+						 index, qp->qpn);
 		else
-			existing_steering_entry(dev, port, steer,
-						index, qp->qpn);
+			err = existing_steering_entry(dev, port, steer,
+						      index, qp->qpn);
 	}
 	if (err && link && index != -1) {
 		if (index < dev->caps.num_mgms)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index a092c5c34..232b2b55f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -787,6 +787,9 @@ struct mlx4_set_port_general_context {
 	u8 pprx;
 	u8 pfcrx;
 	u16 reserved4;
+	u32 reserved5;
+	u8 phv_en;
+	u8 reserved6[3];
 };
 
 struct mlx4_set_port_rqp_calc_context {
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 666d1669e..defcf8c39 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -95,6 +95,7 @@
  */
 
 #define MLX4_EN_PRIV_FLAGS_BLUEFLAME 1
+#define MLX4_EN_PRIV_FLAGS_PHV	     2
 
 #define MLX4_EN_WATCHDOG_TIMEOUT	(15 * HZ)