IB/core: Add rdma_network_type to wc

Providers should tell IB core the wc's network type.
This is used in order to search for the proper GID in the
GID table. When using HCAs that can't provide this info,
IB core tries to deep examine the packet and extract
the GID type by itself.

We choose sgid_index and type from all the matching entries in
RDMA-CM based on hint from the IP stack and we set hop_limit for
the IP packet based on above hint from IP stack.

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

2 files changed, 45 insertions, 0 deletions

diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index 11528591d0d7..c799caacf353 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -83,6 +83,7 @@ struct rdma_dev_addr {
 	int bound_dev_if;
 	enum rdma_transport_type transport;
 	struct net *net;
+	enum rdma_network_type network;
 };
 
 /**
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index ab05ef695d63..368fc22f30f1 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -51,6 +51,8 @@
 #include <linux/socket.h>
 #include <linux/irq_poll.h>
 #include <uapi/linux/if_ether.h>
+#include <net/ipv6.h>
+#include <net/ip.h>
 
 #include <linux/atomic.h>
 #include <linux/mmu_notifier.h>
@@ -109,6 +111,35 @@ enum rdma_protocol_type {
 __attribute_const__ enum rdma_transport_type
 rdma_node_get_transport(enum rdma_node_type node_type);
 
+enum rdma_network_type {
+	RDMA_NETWORK_IB,
+	RDMA_NETWORK_ROCE_V1 = RDMA_NETWORK_IB,
+	RDMA_NETWORK_IPV4,
+	RDMA_NETWORK_IPV6
+};
+
+static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type)
+{
+	if (network_type == RDMA_NETWORK_IPV4 ||
+	    network_type == RDMA_NETWORK_IPV6)
+		return IB_GID_TYPE_ROCE_UDP_ENCAP;
+
+	/* IB_GID_TYPE_IB same as RDMA_NETWORK_ROCE_V1 */
+	return IB_GID_TYPE_IB;
+}
+
+static inline enum rdma_network_type ib_gid_to_network_type(enum ib_gid_type gid_type,
+							    union ib_gid *gid)
+{
+	if (gid_type == IB_GID_TYPE_IB)
+		return RDMA_NETWORK_IB;
+
+	if (ipv6_addr_v4mapped((struct in6_addr *)gid))
+		return RDMA_NETWORK_IPV4;
+	else
+		return RDMA_NETWORK_IPV6;
+}
+
 enum rdma_link_layer {
 	IB_LINK_LAYER_UNSPECIFIED,
 	IB_LINK_LAYER_INFINIBAND,
@@ -537,6 +568,17 @@ struct ib_grh {
 	union ib_gid	dgid;
 };
 
+union rdma_network_hdr {
+	struct ib_grh ibgrh;
+	struct {
+		/* The IB spec states that if it's IPv4, the header
+		 * is located in the last 20 bytes of the header.
+		 */
+		u8		reserved[20];
+		struct iphdr	roce4grh;
+	};
+};
+
 enum {
 	IB_MULTICAST_QPN = 0xffffff
 };
@@ -773,6 +815,7 @@ enum ib_wc_flags {
 	IB_WC_IP_CSUM_OK	= (1<<3),
 	IB_WC_WITH_SMAC		= (1<<4),
 	IB_WC_WITH_VLAN		= (1<<5),
+	IB_WC_WITH_NETWORK_HDR_TYPE	= (1<<6),
 };
 
 struct ib_wc {
@@ -798,6 +841,7 @@ struct ib_wc {
 	u8			port_num;	/* valid only for DR SMPs on switches */
 	u8			smac[ETH_ALEN];
 	u16			vlan_id;
+	u8			network_hdr_type;
 };
 
 enum ib_cq_notify_flags {