IB/core: Use GID table in AH creation and dmac resolution

Previously, vlan id and source MAC were used from QP attributes. Since
the net device is now stored in the GID attributes, they could be used
instead of getting this information from the QP attributes.

IB_QP_SMAC, IB_QP_ALT_SMAC, IB_QP_VID and IB_QP_ALT_VID were removed
because there is no known libibverbs that uses them.

This commit also modifies the vendors (mlx4, ocrdma) drivers in order
to use the new approach.

ocrdma driver changes were done by Somnath Kotur <Somnath.Kotur@Avagotech.Com>

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

4 files changed, 98 insertions, 71 deletions

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 746cdf5..d3c42b3 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -458,7 +458,7 @@ static void resolve_cb(int status, struct sockaddr *src_addr,
 }
 
 int rdma_addr_find_dmac_by_grh(const union ib_gid *sgid, const union ib_gid *dgid,
-			       u8 *dmac, u16 *vlan_id)
+			       u8 *dmac, u16 *vlan_id, int if_index)
 {
 	int ret = 0;
 	struct rdma_dev_addr dev_addr;
@@ -476,6 +476,7 @@ int rdma_addr_find_dmac_by_grh(const union ib_gid *sgid, const union ib_gid *dgi
 	rdma_gid2ip(&dgid_addr._sockaddr, dgid);
 
 	memset(&dev_addr, 0, sizeof(dev_addr));
+	dev_addr.bound_dev_if = if_index;
 
 	ctx.addr = &dev_addr;
 	init_completion(&ctx.comp);
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 0df82b1..5cf6eb7 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -46,8 +46,8 @@ void ib_device_unregister_sysfs(struct ib_device *device);
 void ib_cache_setup(void);
 void ib_cache_cleanup(void);
 
-int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
-			    struct ib_qp_attr *qp_attr, int *qp_attr_mask);
+int ib_resolve_eth_dmac(struct ib_qp *qp,
+			struct ib_qp_attr *qp_attr, int *qp_attr_mask);
 
 typedef void (*roce_netdev_callback)(struct ib_device *device, u8 port,
 	      struct net_device *idev, void *cookie);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index ece9f4c..74dbfd7 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2345,7 +2345,7 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 	attr->alt_ah_attr.port_num 	    = cmd.alt_dest.port_num;
 
 	if (qp->real_qp == qp) {
-		ret = ib_resolve_eth_l2_attrs(qp, attr, &cmd.attr_mask);
+		ret = ib_resolve_eth_dmac(qp, attr, &cmd.attr_mask);
 		if (ret)
 			goto release_qp;
 		ret = qp->device->modify_qp(qp, attr,
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 6012f5e..46d97f0 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -41,6 +41,9 @@
 #include <linux/export.h>
 #include <linux/string.h>
 #include <linux/slab.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <net/addrconf.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
@@ -308,6 +311,35 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
 }
 EXPORT_SYMBOL(ib_create_ah);
 
+struct find_gid_index_context {
+	u16 vlan_id;
+};
+
+static bool find_gid_index(const union ib_gid *gid,
+			   const struct ib_gid_attr *gid_attr,
+			   void *context)
+{
+	struct find_gid_index_context *ctx =
+		(struct find_gid_index_context *)context;
+
+	if ((!!(ctx->vlan_id != 0xffff) == !is_vlan_dev(gid_attr->ndev)) ||
+	    (is_vlan_dev(gid_attr->ndev) &&
+	     vlan_dev_vlan_id(gid_attr->ndev) != ctx->vlan_id))
+		return false;
+
+	return true;
+}
+
+static int get_sgid_index_from_eth(struct ib_device *device, u8 port_num,
+				   u16 vlan_id, const union ib_gid *sgid,
+				   u16 *gid_index)
+{
+	struct find_gid_index_context context = {.vlan_id = vlan_id};
+
+	return ib_find_gid_by_filter(device, sgid, port_num, find_gid_index,
+				     &context, gid_index);
+}
+
 int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 		       const struct ib_wc *wc, const struct ib_grh *grh,
 		       struct ib_ah_attr *ah_attr)
@@ -318,21 +350,30 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 
 	memset(ah_attr, 0, sizeof *ah_attr);
 	if (rdma_cap_eth_ah(device, port_num)) {
+		u16 vlan_id = wc->wc_flags & IB_WC_WITH_VLAN ?
+				wc->vlan_id : 0xffff;
+
 		if (!(wc->wc_flags & IB_WC_GRH))
 			return -EPROTOTYPE;
 
-		if (wc->wc_flags & IB_WC_WITH_SMAC &&
-		    wc->wc_flags & IB_WC_WITH_VLAN) {
-			memcpy(ah_attr->dmac, wc->smac, ETH_ALEN);
-			ah_attr->vlan_id = wc->vlan_id;
-		} else {
+		if (!(wc->wc_flags & IB_WC_WITH_SMAC) ||
+		    !(wc->wc_flags & IB_WC_WITH_VLAN)) {
 			ret = rdma_addr_find_dmac_by_grh(&grh->dgid, &grh->sgid,
-					ah_attr->dmac, &ah_attr->vlan_id);
+							 ah_attr->dmac,
+							 wc->wc_flags & IB_WC_WITH_VLAN ?
+							 NULL : &vlan_id,
+							 0);
 			if (ret)
 				return ret;
 		}
-	} else {
-		ah_attr->vlan_id = 0xffff;
+
+		ret = get_sgid_index_from_eth(device, port_num, vlan_id,
+					      &grh->dgid, &gid_index);
+		if (ret)
+			return ret;
+
+		if (wc->wc_flags & IB_WC_WITH_SMAC)
+			memcpy(ah_attr->dmac, wc->smac, ETH_ALEN);
 	}
 
 	ah_attr->dlid = wc->slid;
@@ -344,10 +385,13 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 		ah_attr->ah_flags = IB_AH_GRH;
 		ah_attr->grh.dgid = grh->sgid;
 
-		ret = ib_find_cached_gid(device, &grh->dgid,
-					 NULL, &port_num, &gid_index);
-		if (ret)
-			return ret;
+		if (!rdma_cap_eth_ah(device, port_num)) {
+			ret = ib_find_cached_gid_by_port(device, &grh->dgid,
+							 port_num, NULL,
+							 &gid_index);
+			if (ret)
+				return ret;
+		}
 
 		ah_attr->grh.sgid_index = (u8) gid_index;
 		flow_class = be32_to_cpu(grh->version_tclass_flow);
@@ -617,9 +661,7 @@ EXPORT_SYMBOL(ib_create_qp);
 static const struct {
 	int			valid;
 	enum ib_qp_attr_mask	req_param[IB_QPT_MAX];
-	enum ib_qp_attr_mask	req_param_add_eth[IB_QPT_MAX];
 	enum ib_qp_attr_mask	opt_param[IB_QPT_MAX];
-	enum ib_qp_attr_mask	opt_param_add_eth[IB_QPT_MAX];
 } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = {
 	[IB_QPS_RESET] = {
 		[IB_QPS_RESET] = { .valid = 1 },
@@ -700,12 +742,6 @@ static const struct {
 						IB_QP_MAX_DEST_RD_ATOMIC	|
 						IB_QP_MIN_RNR_TIMER),
 			},
-			.req_param_add_eth = {
-				[IB_QPT_RC]  = (IB_QP_SMAC),
-				[IB_QPT_UC]  = (IB_QP_SMAC),
-				[IB_QPT_XRC_INI]  = (IB_QP_SMAC),
-				[IB_QPT_XRC_TGT]  = (IB_QP_SMAC)
-			},
 			.opt_param = {
 				 [IB_QPT_UD]  = (IB_QP_PKEY_INDEX		|
 						 IB_QP_QKEY),
@@ -726,21 +762,7 @@ static const struct {
 				 [IB_QPT_GSI] = (IB_QP_PKEY_INDEX		|
 						 IB_QP_QKEY),
 			 },
-			.opt_param_add_eth = {
-				[IB_QPT_RC]  = (IB_QP_ALT_SMAC			|
-						IB_QP_VID			|
-						IB_QP_ALT_VID),
-				[IB_QPT_UC]  = (IB_QP_ALT_SMAC			|
-						IB_QP_VID			|
-						IB_QP_ALT_VID),
-				[IB_QPT_XRC_INI]  = (IB_QP_ALT_SMAC			|
-						IB_QP_VID			|
-						IB_QP_ALT_VID),
-				[IB_QPT_XRC_TGT]  = (IB_QP_ALT_SMAC			|
-						IB_QP_VID			|
-						IB_QP_ALT_VID)
-			}
-		}
+		},
 	},
 	[IB_QPS_RTR]   = {
 		[IB_QPS_RESET] = { .valid = 1 },
@@ -962,13 +984,6 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 	req_param = qp_state_table[cur_state][next_state].req_param[type];
 	opt_param = qp_state_table[cur_state][next_state].opt_param[type];
 
-	if (ll == IB_LINK_LAYER_ETHERNET) {
-		req_param |= qp_state_table[cur_state][next_state].
-			req_param_add_eth[type];
-		opt_param |= qp_state_table[cur_state][next_state].
-			opt_param_add_eth[type];
-	}
-
 	if ((mask & req_param) != req_param)
 		return 0;
 
@@ -979,41 +994,52 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 }
 EXPORT_SYMBOL(ib_modify_qp_is_ok);
 
-int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
-			    struct ib_qp_attr *qp_attr, int *qp_attr_mask)
+int ib_resolve_eth_dmac(struct ib_qp *qp,
+			struct ib_qp_attr *qp_attr, int *qp_attr_mask)
 {
 	int           ret = 0;
-	union ib_gid  sgid;
 
-	if ((*qp_attr_mask & IB_QP_AV)  &&
-	    (rdma_cap_eth_ah(qp->device, qp_attr->ah_attr.port_num))) {
-		ret = ib_query_gid(qp->device, qp_attr->ah_attr.port_num,
-				   qp_attr->ah_attr.grh.sgid_index, &sgid,
-				   NULL);
-		if (ret)
-			goto out;
+	if (*qp_attr_mask & IB_QP_AV) {
+		if (qp_attr->ah_attr.port_num < rdma_start_port(qp->device) ||
+		    qp_attr->ah_attr.port_num > rdma_end_port(qp->device))
+			return -EINVAL;
+
+		if (!rdma_cap_eth_ah(qp->device, qp_attr->ah_attr.port_num))
+			return 0;
+
 		if (rdma_link_local_addr((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw)) {
-			rdma_get_ll_mac((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw, qp_attr->ah_attr.dmac);
-			rdma_get_ll_mac((struct in6_addr *)sgid.raw, qp_attr->smac);
-			if (!(*qp_attr_mask & IB_QP_VID))
-				qp_attr->vlan_id = rdma_get_vlan_id(&sgid);
+			rdma_get_ll_mac((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw,
+					qp_attr->ah_attr.dmac);
 		} else {
-			ret = rdma_addr_find_dmac_by_grh(&sgid, &qp_attr->ah_attr.grh.dgid,
-					qp_attr->ah_attr.dmac, &qp_attr->vlan_id);
-			if (ret)
-				goto out;
-			ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr->smac, NULL);
-			if (ret)
+			union ib_gid		sgid;
+			struct ib_gid_attr	sgid_attr;
+			int			ifindex;
+
+			ret = ib_query_gid(qp->device,
+					   qp_attr->ah_attr.port_num,
+					   qp_attr->ah_attr.grh.sgid_index,
+					   &sgid, &sgid_attr);
+
+			if (ret || !sgid_attr.ndev) {
+				if (!ret)
+					ret = -ENXIO;
 				goto out;
+			}
+
+			ifindex = sgid_attr.ndev->ifindex;
+
+			ret = rdma_addr_find_dmac_by_grh(&sgid,
+							 &qp_attr->ah_attr.grh.dgid,
+							 qp_attr->ah_attr.dmac,
+							 NULL, ifindex);
+
+			dev_put(sgid_attr.ndev);
 		}
-		*qp_attr_mask |= IB_QP_SMAC;
-		if (qp_attr->vlan_id < 0xFFFF)
-			*qp_attr_mask |= IB_QP_VID;
 	}
 out:
 	return ret;
 }
-EXPORT_SYMBOL(ib_resolve_eth_l2_attrs);
+EXPORT_SYMBOL(ib_resolve_eth_dmac);
 
 
 int ib_modify_qp(struct ib_qp *qp,
@@ -1022,7 +1048,7 @@ int ib_modify_qp(struct ib_qp *qp,
 {
 	int ret;
 
-	ret = ib_resolve_eth_l2_attrs(qp, qp_attr, &qp_attr_mask);
+	ret = ib_resolve_eth_dmac(qp, qp_attr, &qp_attr_mask);
 	if (ret)
 		return ret;