IB/core: Add VLAN support for IBoE

Add 802.1q VLAN support to IBoE. The VLAN tag is encoded within the
GID derived from a link local address in the following way:

    GID[11] GID[12] contain the VLAN ID when the GID contains a VLAN.

The 3 bits user priority field of the packets are identical to the 3
bits of the SL.

In case of rdma_cm apps, the TOS field is used to generate the SL
field by doing a shift right of 5 bits effectively taking to 3 MS bits
of the TOS field.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

7 files changed, 95 insertions, 16 deletions

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index f61bc0738488..6884da24fde1 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1791,6 +1791,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	struct sockaddr_in *src_addr = (struct sockaddr_in *)&route->addr.src_addr;
 	struct sockaddr_in *dst_addr = (struct sockaddr_in *)&route->addr.dst_addr;
 	struct net_device *ndev = NULL;
+	u16 vid;
 
 	if (src_addr->sin_family != dst_addr->sin_family)
 		return -EINVAL;
@@ -1810,14 +1811,6 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 
 	route->num_paths = 1;
 
-	iboe_mac_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr);
-	iboe_mac_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr);
-
-	route->path_rec->hop_limit = 1;
-	route->path_rec->reversible = 1;
-	route->path_rec->pkey = cpu_to_be16(0xffff);
-	route->path_rec->mtu_selector = IB_SA_EQ;
-
 	if (addr->dev_addr.bound_dev_if)
 		ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if);
 	if (!ndev) {
@@ -1825,6 +1818,17 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 		goto err2;
 	}
 
+	vid = rdma_vlan_dev_vlan_id(ndev);
+
+	iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr, vid);
+	iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, vid);
+
+	route->path_rec->hop_limit = 1;
+	route->path_rec->reversible = 1;
+	route->path_rec->pkey = cpu_to_be16(0xffff);
+	route->path_rec->mtu_selector = IB_SA_EQ;
+	route->path_rec->sl = id_priv->tos >> 5;
+
 	route->path_rec->mtu = iboe_get_mtu(ndev->mtu);
 	route->path_rec->rate_selector = IB_SA_EQ;
 	route->path_rec->rate = iboe_get_rate(ndev);
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 3d3c9264c450..357a766bd220 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -587,13 +587,21 @@ static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
 				 struct rdma_route *route)
 {
 	struct rdma_dev_addr *dev_addr;
+	struct net_device *dev;
+	u16 vid = 0;
 
 	resp->num_paths = route->num_paths;
 	switch (route->num_paths) {
 	case 0:
 		dev_addr = &route->addr.dev_addr;
-		iboe_mac_to_ll((union ib_gid *) &resp->ib_route[0].dgid,
-			       dev_addr->dst_dev_addr);
+		dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+			if (dev) {
+				vid = rdma_vlan_dev_vlan_id(dev);
+				dev_put(dev);
+			}
+
+		iboe_mac_vlan_to_ll((union ib_gid *) &resp->ib_route[0].dgid,
+				    dev_addr->dst_dev_addr, vid);
 		iboe_addr_get_sgid(dev_addr,
 				   (union ib_gid *) &resp->ib_route[0].sgid);
 		resp->ib_route[0].pkey = cpu_to_be16(0xffff);
diff --git a/drivers/infiniband/core/ud_header.c b/drivers/infiniband/core/ud_header.c
index cb0dd5ae2777..bb7e19280821 100644
--- a/drivers/infiniband/core/ud_header.c
+++ b/drivers/infiniband/core/ud_header.c
@@ -33,6 +33,7 @@
 
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/if_ether.h>
 
 #include <rdma/ib_pack.h>
 
@@ -103,6 +104,17 @@ static const struct ib_field eth_table[]  = {
 	  .size_bits    = 16 }
 };
 
+static const struct ib_field vlan_table[]  = {
+	{ STRUCT_FIELD(vlan, tag),
+	  .offset_words = 0,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ STRUCT_FIELD(vlan, type),
+	  .offset_words = 0,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 }
+};
+
 static const struct ib_field grh_table[]  = {
 	{ STRUCT_FIELD(grh, ip_version),
 	  .offset_words = 0,
@@ -205,6 +217,7 @@ static const struct ib_field deth_table[] = {
  * @payload_bytes:Length of packet payload
  * @lrh_present: specify if LRH is present
  * @eth_present: specify if Eth header is present
+ * @vlan_present: packet is tagged vlan
  * @grh_present:GRH flag (if non-zero, GRH will be included)
  * @immediate_present: specify if immediate data is present
  * @header:Structure to initialize
@@ -212,6 +225,7 @@ static const struct ib_field deth_table[] = {
 void ib_ud_header_init(int     		    payload_bytes,
 		       int		    lrh_present,
 		       int		    eth_present,
+		       int		    vlan_present,
 		       int    		    grh_present,
 		       int		    immediate_present,
 		       struct ib_ud_header *header)
@@ -234,6 +248,9 @@ void ib_ud_header_init(int     		    payload_bytes,
 		header->lrh.packet_length = cpu_to_be16(packet_length);
 	}
 
+	if (vlan_present)
+		header->eth.type = cpu_to_be16(ETH_P_8021Q);
+
 	if (grh_present) {
 		header->grh.ip_version      = 6;
 		header->grh.payload_length  =
@@ -254,6 +271,7 @@ void ib_ud_header_init(int     		    payload_bytes,
 
 	header->lrh_present = lrh_present;
 	header->eth_present = eth_present;
+	header->vlan_present = vlan_present;
 	header->grh_present = grh_present;
 	header->immediate_present = immediate_present;
 }
@@ -312,6 +330,11 @@ int ib_ud_header_pack(struct ib_ud_header *header,
 			&header->eth, buf + len);
 		len += IB_ETH_BYTES;
 	}
+	if (header->vlan_present) {
+		ib_pack(vlan_table, ARRAY_SIZE(vlan_table),
+			&header->vlan, buf + len);
+		len += IB_VLAN_BYTES;
+	}
 	if (header->grh_present) {
 		ib_pack(grh_table, ARRAY_SIZE(grh_table),
 			&header->grh, buf + len);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 17f60fe6e5b6..269648445113 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1291,7 +1291,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 
 	is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET;
 	is_grh = mlx4_ib_ah_grh_present(ah);
-	ib_ud_header_init(send_size, !is_eth, is_eth, is_grh, 0, &sqp->ud_header);
+	ib_ud_header_init(send_size, !is_eth, is_eth, 0, is_grh, 0, &sqp->ud_header);
 
 	if (!is_eth) {
 		sqp->ud_header.lrh.service_level =
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 1a1c55fb13f3..a34c9d38e822 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -1493,7 +1493,7 @@ static int build_mlx_header(struct mthca_dev *dev, struct mthca_sqp *sqp,
 	int err;
 	u16 pkey;
 
-	ib_ud_header_init(256, /* assume a MAD */ 1, 0,
+	ib_ud_header_init(256, /* assume a MAD */ 1, 0, 0,
 			  mthca_ah_grh_present(to_mah(wr->wr.ud.ah)), 0,
 			  &sqp->ud_header);
 
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index 904ffa92fc93..b5fc9f39122b 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -39,6 +39,7 @@
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
 #include <linux/socket.h>
+#include <linux/if_vlan.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
 
@@ -129,21 +130,41 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr)
 	return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0;
 }
 
-static inline void iboe_mac_to_ll(union ib_gid *gid, u8 *mac)
+static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid)
 {
 	memset(gid->raw, 0, 16);
 	*((__be32 *) gid->raw) = cpu_to_be32(0xfe800000);
-	gid->raw[12] = 0xfe;
-	gid->raw[11] = 0xff;
+	if (vid < 0x1000) {
+		gid->raw[12] = vid & 0xff;
+		gid->raw[11] = vid >> 8;
+	} else {
+		gid->raw[12] = 0xfe;
+		gid->raw[11] = 0xff;
+	}
 	memcpy(gid->raw + 13, mac + 3, 3);
 	memcpy(gid->raw + 8, mac, 3);
 	gid->raw[8] ^= 2;
 }
 
+static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_802_1Q_VLAN ?
+		vlan_dev_vlan_id(dev) : 0xffff;
+}
+
 static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 				      union ib_gid *gid)
 {
-	iboe_mac_to_ll(gid, dev_addr->src_dev_addr);
+	struct net_device *dev;
+	u16 vid = 0xffff;
+
+	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+	if (dev) {
+		vid = rdma_vlan_dev_vlan_id(dev);
+		dev_put(dev);
+	}
+
+	iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid);
 }
 
 static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
@@ -244,4 +265,18 @@ static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
 		mac[i] = addr->s6_addr[i + 10];
 }
 
+static inline u16 rdma_get_vlan_id(union ib_gid *dgid)
+{
+	u16 vid;
+
+	vid = dgid->raw[11] << 8 | dgid->raw[12];
+	return vid < 0x1000 ? vid : 0xffff;
+}
+
+static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_802_1Q_VLAN ?
+		vlan_dev_real_dev(dev) : 0;
+}
+
 #endif /* IB_ADDR_H */
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index 6b91d8e7a1fa..b37fe3b10a9d 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -38,6 +38,7 @@
 enum {
 	IB_LRH_BYTES  = 8,
 	IB_ETH_BYTES  = 14,
+	IB_VLAN_BYTES = 4,
 	IB_GRH_BYTES  = 40,
 	IB_BTH_BYTES  = 12,
 	IB_DETH_BYTES = 8
@@ -219,11 +220,18 @@ struct ib_unpacked_eth {
 	__be16	type;
 };
 
+struct ib_unpacked_vlan {
+	__be16  tag;
+	__be16  type;
+};
+
 struct ib_ud_header {
 	int                     lrh_present;
 	struct ib_unpacked_lrh  lrh;
 	int			eth_present;
 	struct ib_unpacked_eth	eth;
+	int                     vlan_present;
+	struct ib_unpacked_vlan vlan;
 	int			grh_present;
 	struct ib_unpacked_grh	grh;
 	struct ib_unpacked_bth	bth;
@@ -245,6 +253,7 @@ void ib_unpack(const struct ib_field        *desc,
 void ib_ud_header_init(int		    payload_bytes,
 		       int		    lrh_present,
 		       int		    eth_present,
+		       int		    vlan_present,
 		       int		    grh_present,
 		       int		    immediate_present,
 		       struct ib_ud_header *header);