IB/core: Ethernet L2 attributes in verbs/cm structures

This patch add the support for Ethernet L2 attributes in the
verbs/cm/cma structures.

When dealing with L2 Ethernet, we should use smac, dmac, vlan ID and priority
in a similar manner that the IB L2 (and the L4 PKEY) attributes are used.

Thus, those attributes were added to the following structures:

* ib_ah_attr - added dmac
* ib_qp_attr - added smac and vlan_id, (sl remains vlan priority)
* ib_wc - added smac, vlan_id
* ib_sa_path_rec - added smac, dmac, vlan_id
* cm_av - added smac and vlan_id

For the path record structure, extra care was taken to avoid the new
fields when packing it into wire format, so we don't break the IB CM
and SA wire protocol.

On the active side, the CM fills. its internal structures from the
path provided by the ULP.  We add there taking the ETH L2 attributes
and placing them into the CM Address Handle (struct cm_av).

On the passive side, the CM fills its internal structures from the WC
associated with the REQ message.  We add there taking the ETH L2
attributes from the WC.

When the HW driver provides the required ETH L2 attributes in the WC,
they set the IB_WC_WITH_SMAC and IB_WC_WITH_VLAN flags. The IB core
code checks for the presence of these flags, and in their absence does
address resolution from the ib_init_ah_from_wc() helper function.

ib_modify_qp_is_ok is also updated to consider the link layer. Some
parameters are mandatory for Ethernet link layer, while they are
irrelevant for IB.  Vendor drivers are modified to support the new
function signature.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

5 files changed, 65 insertions, 3 deletions

diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index f3ac0f2..a071560 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -42,6 +42,7 @@
 #include <linux/if_vlan.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
+#include <net/ipv6.h>
 
 struct rdma_addr_client {
 	atomic_t refcount;
@@ -72,7 +73,8 @@ struct rdma_dev_addr {
  * rdma_translate_ip - Translate a local IP address to an RDMA hardware
  *   address.
  */
-int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr);
+int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
+		      u16 *vlan_id);
 
 /**
  * rdma_resolve_ip - Resolve source and destination IP addresses to
@@ -104,6 +106,10 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
 
 int rdma_addr_size(struct sockaddr *addr);
 
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id);
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac,
+			       u16 *vlan_id);
+
 static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
 {
 	return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9];
@@ -142,6 +148,40 @@ static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid)
 	gid->raw[8] ^= 2;
 }
 
+static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
+{
+	switch (addr->sa_family) {
+	case AF_INET:
+		ipv6_addr_set_v4mapped(((struct sockaddr_in *)
+					addr)->sin_addr.s_addr,
+				       (struct in6_addr *)gid);
+		break;
+	case AF_INET6:
+		memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */
+static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
+{
+	if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
+		struct sockaddr_in *out_in = (struct sockaddr_in *)out;
+		memset(out_in, 0, sizeof(*out_in));
+		out_in->sin_family = AF_INET;
+		memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4);
+	} else {
+		struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out;
+		memset(out_in, 0, sizeof(*out_in));
+		out_in->sin6_family = AF_INET6;
+		memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16);
+	}
+	return 0;
+}
+
 static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_802_1Q_VLAN ?
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index 0e3ff30..f29e3a2 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -601,4 +601,5 @@ struct ib_cm_sidr_rep_param {
 int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
 			struct ib_cm_sidr_rep_param *param);
 
+int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac);
 #endif /* IB_CM_H */
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index b37fe3b..b1f7592 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -34,6 +34,7 @@
 #define IB_PACK_H
 
 #include <rdma/ib_verbs.h>
+#include <uapi/linux/if_ether.h>
 
 enum {
 	IB_LRH_BYTES  = 8,
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index 125f871..7e071a6 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -154,6 +154,9 @@ struct ib_sa_path_rec {
 	u8           packet_life_time_selector;
 	u8           packet_life_time;
 	u8           preference;
+	u8           smac[ETH_ALEN];
+	u8           dmac[ETH_ALEN];
+	u16	     vlan_id;
 };
 
 #define IB_SA_MCMEMBER_REC_MGID				IB_SA_COMP_MASK( 0)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 61e1935..ea0f6ee 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -48,6 +48,7 @@
 #include <linux/rwsem.h>
 #include <linux/scatterlist.h>
 #include <linux/workqueue.h>
+#include <uapi/linux/if_ether.h>
 
 #include <linux/atomic.h>
 #include <asm/uaccess.h>
@@ -472,6 +473,8 @@ struct ib_ah_attr {
 	u8			static_rate;
 	u8			ah_flags;
 	u8			port_num;
+	u8			dmac[ETH_ALEN];
+	u16			vlan_id;
 };
 
 enum ib_wc_status {
@@ -524,6 +527,8 @@ enum ib_wc_flags {
 	IB_WC_WITH_IMM		= (1<<1),
 	IB_WC_WITH_INVALIDATE	= (1<<2),
 	IB_WC_IP_CSUM_OK	= (1<<3),
+	IB_WC_WITH_SMAC		= (1<<4),
+	IB_WC_WITH_VLAN		= (1<<5),
 };
 
 struct ib_wc {
@@ -544,6 +549,8 @@ struct ib_wc {
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */
+	u8			smac[ETH_ALEN];
+	u16			vlan_id;
 };
 
 enum ib_cq_notify_flags {
@@ -721,7 +728,11 @@ enum ib_qp_attr_mask {
 	IB_QP_MAX_DEST_RD_ATOMIC	= (1<<17),
 	IB_QP_PATH_MIG_STATE		= (1<<18),
 	IB_QP_CAP			= (1<<19),
-	IB_QP_DEST_QPN			= (1<<20)
+	IB_QP_DEST_QPN			= (1<<20),
+	IB_QP_SMAC			= (1<<21),
+	IB_QP_ALT_SMAC			= (1<<22),
+	IB_QP_VID			= (1<<23),
+	IB_QP_ALT_VID			= (1<<24),
 };
 
 enum ib_qp_state {
@@ -771,6 +782,10 @@ struct ib_qp_attr {
 	u8			rnr_retry;
 	u8			alt_port_num;
 	u8			alt_timeout;
+	u8			smac[ETH_ALEN];
+	u8			alt_smac[ETH_ALEN];
+	u16			vlan_id;
+	u16			alt_vlan_id;
 };
 
 enum ib_wr_opcode {
@@ -1488,6 +1503,7 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
  * @next_state: Next QP state
  * @type: QP type
  * @mask: Mask of supplied QP attributes
+ * @ll : link layer of port
  *
  * This function is a helper function that a low-level driver's
  * modify_qp method can use to validate the consumer's input.  It
@@ -1496,7 +1512,8 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
  * and that the attribute mask supplied is allowed for the transition.
  */
 int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
-		       enum ib_qp_type type, enum ib_qp_attr_mask mask);
+		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
+		       enum rdma_link_layer ll);
 
 int ib_register_event_handler  (struct ib_event_handler *event_handler);
 int ib_unregister_event_handler(struct ib_event_handler *event_handler);