Merge branch 'mlx4-802.1ad-accel'

Amir Vadai says:

====================
net/mlx4_en: Hardware accelerated 802.1ad

This patchset by Hadar introduces support in Hardware accelerated 802.1ad, for
ConnectX-3pro NIC's.  In order to support existing deployment, and due to some
hardware limitations, the feature is disabled by default, and needed to be
enabled using a private flag in ethtool. Ofcourse user can enable the private
flag only if hardware has support.
After being enabled, the standard ethtool -k/-K can be used.

Patchset was applied and tested over commit 71790a2 ("hv_netvsc: Add structs
and handlers for VF messages")
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

Author: davem330

drivers/infiniband/hw/mlx4/cq.c

@@ -871,7 +871,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
 		if (is_eth) {
 			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 13;
 			if (be32_to_cpu(cqe->vlan_my_qpn) &
-					MLX4_CQE_VLAN_PRESENT_MASK) {
+					MLX4_CQE_CVLAN_PRESENT_MASK) {
 				wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
 					MLX4_CQE_VID_MASK;
 			} else {

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;
 }
 

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;
 

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -726,7 +726,7 @@ 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);
@@ -907,11 +907,17 @@ 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)
@@ -970,9 +976,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 					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);
@@ -1070,7 +1081,10 @@ 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;
 

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 +960,11 @@ 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;
+
 		tx_desc->ctrl.fence_size = real_size;
 
 		/* Ensure new descriptor hits memory

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, 1, &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);

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 {