RDMA/cm: Add RDMA CM support for IBoE devices
Add support for IBoE device binding and IP --> GID resolution. Path
resolving and multicast joining are implemented within cma.c by
filling in the responses and running callbacks in the CMA work queue.
IP --> GID resolution always yields IPv6 link local addresses; remote
GIDs are derived from the destination MAC address of the remote port.
Multicast GIDs are always mapped to multicast MACs as is done in IPv6.
(IPv4 multicast is enabled by translating IPv4 multicast addresses to
IPv6 multicast as described in
<http://www.mail-archive.com/ipng@sunroof.eng.sun.com/msg02134.html>.)
Some helper functions are added to ib_addr.h.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index fa0d52b..904ffa9 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -40,6 +40,7 @@
#include <linux/netdevice.h>
#include <linux/socket.h>
#include <rdma/ib_verbs.h>
+#include <rdma/ib_pack.h>
struct rdma_addr_client {
atomic_t refcount;
@@ -63,6 +64,7 @@
unsigned char broadcast[MAX_ADDR_LEN];
unsigned short dev_type;
int bound_dev_if;
+ enum rdma_transport_type transport;
};
/**
@@ -127,9 +129,31 @@
return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0;
}
+static inline void iboe_mac_to_ll(union ib_gid *gid, u8 *mac)
+{
+ memset(gid->raw, 0, 16);
+ *((__be32 *) gid->raw) = cpu_to_be32(0xfe800000);
+ 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 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);
+}
+
static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
{
- memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid);
+ if (dev_addr->transport == RDMA_TRANSPORT_IB &&
+ dev_addr->dev_type != ARPHRD_INFINIBAND)
+ iboe_addr_get_sgid(dev_addr, gid);
+ else
+ memcpy(gid, dev_addr->src_dev_addr +
+ rdma_addr_gid_offset(dev_addr), sizeof *gid);
}
static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
@@ -147,4 +171,77 @@
memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid);
}
+static inline enum ib_mtu iboe_get_mtu(int mtu)
+{
+ /*
+ * reduce IB headers from effective IBoE MTU. 28 stands for
+ * atomic header which is the biggest possible header after BTH
+ */
+ mtu = mtu - IB_GRH_BYTES - IB_BTH_BYTES - 28;
+
+ if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096))
+ return IB_MTU_4096;
+ else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048))
+ return IB_MTU_2048;
+ else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024))
+ return IB_MTU_1024;
+ else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512))
+ return IB_MTU_512;
+ else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256))
+ return IB_MTU_256;
+ else
+ return 0;
+}
+
+static inline int iboe_get_rate(struct net_device *dev)
+{
+ struct ethtool_cmd cmd;
+
+ if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings ||
+ dev->ethtool_ops->get_settings(dev, &cmd))
+ return IB_RATE_PORT_CURRENT;
+
+ if (cmd.speed >= 40000)
+ return IB_RATE_40_GBPS;
+ else if (cmd.speed >= 30000)
+ return IB_RATE_30_GBPS;
+ else if (cmd.speed >= 20000)
+ return IB_RATE_20_GBPS;
+ else if (cmd.speed >= 10000)
+ return IB_RATE_10_GBPS;
+ else
+ return IB_RATE_PORT_CURRENT;
+}
+
+static inline int rdma_link_local_addr(struct in6_addr *addr)
+{
+ if (addr->s6_addr32[0] == htonl(0xfe800000) &&
+ addr->s6_addr32[1] == 0)
+ return 1;
+
+ return 0;
+}
+
+static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
+{
+ memcpy(mac, &addr->s6_addr[8], 3);
+ memcpy(mac + 3, &addr->s6_addr[13], 3);
+ mac[0] ^= 2;
+}
+
+static inline int rdma_is_multicast_addr(struct in6_addr *addr)
+{
+ return addr->s6_addr[0] == 0xff;
+}
+
+static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
+{
+ int i;
+
+ mac[0] = 0x33;
+ mac[1] = 0x33;
+ for (i = 2; i < 6; ++i)
+ mac[i] = addr->s6_addr[i + 10];
+}
+
#endif /* IB_ADDR_H */