IB/mlx4: Handle Ethernet L2 parameters for IP based GID addressing

IP based RoCE gids don't store Ethernet L2 parameters, MAC and VLAN.

Therefore, we need to extract them from the CQE and place them in
struct ib_wc (to be used for cases were they were taken from the gid).

Also, when modifying a QP or building address handle, instead of
parsing the dgid to get the MAC and VLAN, take them from the address
handle attributes.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

6 files changed, 130 insertions, 62 deletions

diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index a251becdaa98..170dca608042 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -39,25 +39,6 @@
 
 #include "mlx4_ib.h"
 
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
-			u8 *mac, int *is_mcast, u8 port)
-{
-	struct in6_addr in6;
-
-	*is_mcast = 0;
-
-	memcpy(&in6, ah_attr->grh.dgid.raw, sizeof in6);
-	if (rdma_link_local_addr(&in6))
-		rdma_get_ll_mac(&in6, mac);
-	else if (rdma_is_multicast_addr(&in6)) {
-		rdma_get_mcast_mac(&in6, mac);
-		*is_mcast = 1;
-	} else
-		return -EINVAL;
-
-	return 0;
-}
-
 static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 				  struct mlx4_ib_ah *ah)
 {
@@ -92,21 +73,18 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 {
 	struct mlx4_ib_dev *ibdev = to_mdev(pd->device);
 	struct mlx4_dev *dev = ibdev->dev;
-	union ib_gid sgid;
-	u8 mac[6];
-	int err;
 	int is_mcast;
+	struct in6_addr in6;
 	u16 vlan_tag;
 
-	err = mlx4_ib_resolve_grh(ibdev, ah_attr, mac, &is_mcast, ah_attr->port_num);
-	if (err)
-		return ERR_PTR(err);
-
-	memcpy(ah->av.eth.mac, mac, 6);
-	err = ib_get_cached_gid(pd->device, ah_attr->port_num, ah_attr->grh.sgid_index, &sgid);
-	if (err)
-		return ERR_PTR(err);
-	vlan_tag = rdma_get_vlan_id(&sgid);
+	memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
+	if (rdma_is_multicast_addr(&in6)) {
+		is_mcast = 1;
+		rdma_get_mcast_mac(&in6, ah->av.eth.mac);
+	} else {
+		memcpy(ah->av.eth.mac, ah_attr->dmac, ETH_ALEN);
+	}
+	vlan_tag = ah_attr->vlan_id;
 	if (vlan_tag < 0x1000)
 		vlan_tag |= (ah_attr->sl & 7) << 13;
 	ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 66dbf8062374..cc40f08ca8f1 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -798,6 +798,15 @@ repoll:
 			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 13;
 		else
 			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 12;
+		if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK) {
+			wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
+				MLX4_CQE_VID_MASK;
+		} else {
+			wc->vlan_id = 0xffff;
+		}
+		wc->wc_flags |= IB_WC_WITH_VLAN;
+		memcpy(wc->smac, cqe->smac, ETH_ALEN);
+		wc->wc_flags |= IB_WC_WITH_SMAC;
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 133f41f42194..c06f571619df 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -678,9 +678,6 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
 int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
 			union ib_gid *gid, int netw_view);
 
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
-			u8 *mac, int *is_mcast, u8 port);
-
 static inline bool mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
 {
 	u8 port = be32_to_cpu(ah->av.ib.port_pd) >> 24 & 3;
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index da6f5fa0c328..e0c2186529ff 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -90,6 +90,21 @@ enum {
 	MLX4_RAW_QP_MSGMAX	= 31,
 };
 
+#ifndef ETH_ALEN
+#define ETH_ALEN        6
+#endif
+static inline u64 mlx4_mac_to_u64(u8 *addr)
+{
+	u64 mac = 0;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		mac <<= 8;
+		mac |= addr[i];
+	}
+	return mac;
+}
+
 static const __be32 mlx4_ib_opcode[] = {
 	[IB_WR_SEND]				= cpu_to_be32(MLX4_OPCODE_SEND),
 	[IB_WR_LSO]				= cpu_to_be32(MLX4_OPCODE_LSO),
@@ -1144,16 +1159,15 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port)
 	path->sched_queue = (path->sched_queue & 0xbf) | ((port - 1) << 6);
 }
 
-static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
-			 struct mlx4_qp_path *path, u8 port)
+static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
+			  u64 smac, u16 vlan_tag, struct mlx4_qp_path *path,
+			  u8 port)
 {
-	int err;
 	int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) ==
 		IB_LINK_LAYER_ETHERNET;
-	u8 mac[6];
-	int is_mcast;
-	u16 vlan_tag;
 	int vidx;
+	int smac_index;
+
 
 	path->grh_mylmc     = ah->src_path_bits & 0x7f;
 	path->rlid	    = cpu_to_be16(ah->dlid);
@@ -1188,22 +1202,27 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 		if (!(ah->ah_flags & IB_AH_GRH))
 			return -1;
 
-		err = mlx4_ib_resolve_grh(dev, ah, mac, &is_mcast, port);
-		if (err)
-			return err;
-
-		memcpy(path->dmac, mac, 6);
+		memcpy(path->dmac, ah->dmac, ETH_ALEN);
 		path->ackto = MLX4_IB_LINK_TYPE_ETH;
-		/* use index 0 into MAC table for IBoE */
-		path->grh_mylmc &= 0x80;
+		/* find the index  into MAC table for IBoE */
+		if (!is_zero_ether_addr((const u8 *)&smac)) {
+			if (mlx4_find_cached_mac(dev->dev, port, smac,
+						 &smac_index))
+				return -ENOENT;
+		} else {
+			smac_index = 0;
+		}
+
+		path->grh_mylmc &= 0x80 | smac_index;
 
-		vlan_tag = rdma_get_vlan_id(&dev->iboe.gid_table[port - 1][ah->grh.sgid_index]);
+		path->feup |= MLX4_FEUP_FORCE_ETH_UP;
 		if (vlan_tag < 0x1000) {
 			if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx))
 				return -ENOENT;
 
 			path->vlan_index = vidx;
 			path->fl = 1 << 6;
+			path->feup |= MLX4_FVL_FORCE_ETH_VLAN;
 		}
 	} else
 		path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
@@ -1212,6 +1231,28 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 	return 0;
 }
 
+static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp,
+			 enum ib_qp_attr_mask qp_attr_mask,
+			 struct mlx4_qp_path *path, u8 port)
+{
+	return _mlx4_set_path(dev, &qp->ah_attr,
+			      mlx4_mac_to_u64((u8 *)qp->smac),
+			      (qp_attr_mask & IB_QP_VID) ? qp->vlan_id : 0xffff,
+			      path, port);
+}
+
+static int mlx4_set_alt_path(struct mlx4_ib_dev *dev,
+			     const struct ib_qp_attr *qp,
+			     enum ib_qp_attr_mask qp_attr_mask,
+			     struct mlx4_qp_path *path, u8 port)
+{
+	return _mlx4_set_path(dev, &qp->alt_ah_attr,
+			      mlx4_mac_to_u64((u8 *)qp->alt_smac),
+			      (qp_attr_mask & IB_QP_ALT_VID) ?
+			      qp->alt_vlan_id : 0xffff,
+			      path, port);
+}
+
 static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
 {
 	struct mlx4_ib_gid_entry *ge, *tmp;
@@ -1329,7 +1370,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (attr_mask & IB_QP_AV) {
-		if (mlx4_set_path(dev, &attr->ah_attr, &context->pri_path,
+		if (mlx4_set_path(dev, attr, attr_mask, &context->pri_path,
 				  attr_mask & IB_QP_PORT ?
 				  attr->port_num : qp->port))
 			goto out;
@@ -1352,8 +1393,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		    dev->dev->caps.pkey_table_len[attr->alt_port_num])
 			goto out;
 
-		if (mlx4_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
-				  attr->alt_port_num))
+		if (mlx4_set_alt_path(dev, attr, attr_mask, &context->alt_path,
+				      attr->alt_port_num))
 			goto out;
 
 		context->alt_path.pkey_index = attr->alt_pkey_index;
@@ -1464,6 +1505,17 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		context->pri_path.ackto = (context->pri_path.ackto & 0xf8) |
 					MLX4_IB_LINK_TYPE_ETH;
 
+	if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
+		int is_eth = rdma_port_get_link_layer(
+				&dev->ib_dev, qp->port) ==
+				IB_LINK_LAYER_ETHERNET;
+		if (is_eth) {
+			context->pri_path.ackto = MLX4_IB_LINK_TYPE_ETH;
+			optpar |= MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH;
+		}
+	}
+
+
 	if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD	&&
 	    attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify)
 		sqd_event = 1;
@@ -1561,18 +1613,21 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	struct mlx4_ib_qp *qp = to_mqp(ibqp);
 	enum ib_qp_state cur_state, new_state;
 	int err = -EINVAL;
-	int p = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+	int ll;
 	mutex_lock(&qp->mutex);
 
 	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
-	if (cur_state == new_state && cur_state == IB_QPS_RESET)
-		p = IB_LINK_LAYER_UNSPECIFIED;
+	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
+		ll = IB_LINK_LAYER_UNSPECIFIED;
+	} else {
+		int port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+		ll = rdma_port_get_link_layer(&dev->ib_dev, port);
+	}
 
 	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
-				attr_mask,
-				rdma_port_get_link_layer(&dev->ib_dev, p))) {
+				attr_mask, ll)) {
 		pr_debug("qpn 0x%x: invalid attribute mask specified "
 			 "for transition %d to %d. qp_type %d,"
 			 " attr_mask 0x%x\n",
@@ -1789,8 +1844,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 				return err;
 		}
 
-		vlan = rdma_get_vlan_id(&sgid);
-		is_vlan = vlan < 0x1000;
+		if (ah->av.eth.vlan != 0xffff) {
+			vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
+			is_vlan = 1;
+		}
 	}
 	ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 97d342fa5032..f50ef6a5ee5e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -123,6 +123,26 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	struct mlx4_mac_table *table = &info->mac_table;
+	int i;
+
+	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+		if (!table->refs[i])
+			continue;
+
+		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
+			*idx = i;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
+
 int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h
index 98fa492cf406..e1862997f933 100644
--- a/include/linux/mlx4/cq.h
+++ b/include/linux/mlx4/cq.h
@@ -34,6 +34,7 @@
 #define MLX4_CQ_H
 
 #include <linux/types.h>
+#include <uapi/linux/if_ether.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -43,10 +44,15 @@ struct mlx4_cqe {
 	__be32			immed_rss_invalid;
 	__be32			g_mlpath_rqpn;
 	__be16			sl_vid;
-	__be16			rlid;
-	__be16			status;
-	u8			ipv6_ext_mask;
-	u8			badfcs_enc;
+	union {
+		struct {
+			__be16	rlid;
+			__be16  status;
+			u8      ipv6_ext_mask;
+			u8      badfcs_enc;
+		};
+		u8  smac[ETH_ALEN];
+	};
 	__be32			byte_cnt;
 	__be16			wqe_index;
 	__be16			checksum;
@@ -83,6 +89,7 @@ struct mlx4_ts_cqe {
 enum {
 	MLX4_CQE_VLAN_PRESENT_MASK	= 1 << 29,
 	MLX4_CQE_QPN_MASK		= 0xffffff,
+	MLX4_CQE_VID_MASK		= 0xfff,
 };
 
 enum {