summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorUrsula Braun <ubraun@linux.vnet.ibm.com>2017-01-09 16:55:14 +0100
committerDavid S. Miller <davem@davemloft.net>2017-01-09 16:07:38 -0500
commita4cf0443c4143b19e42389a1674b5b65224544ce (patch)
treeddb307b528feb0c8bc38e64a7caa9ee51f9d8da5
parentac7138746e14137a451f8539614cdd349153e0c0 (diff)
smc: introduce SMC as an IB-client
* create a list of SMC IB-devices Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/smc/Makefile2
-rw-r--r--net/smc/af_smc.c10
-rw-r--r--net/smc/smc.h6
-rw-r--r--net/smc/smc_ib.c143
-rw-r--r--net/smc/smc_ib.h40
5 files changed, 200 insertions, 1 deletions
diff --git a/net/smc/Makefile b/net/smc/Makefile
index c285c868dd82..56f2170e6f64 100644
--- a/net/smc/Makefile
+++ b/net/smc/Makefile
@@ -1,2 +1,2 @@
obj-$(CONFIG_SMC) += smc.o
-smc-y := af_smc.o
+smc-y := af_smc.o smc_ib.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 7fd773fc6238..50492ee495ce 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -20,6 +20,7 @@
#include <net/sock.h>
#include "smc.h"
+#include "smc_ib.h"
static void smc_set_keepalive(struct sock *sk, int val)
{
@@ -597,8 +598,16 @@ static int __init smc_init(void)
goto out_proto;
}
+ rc = smc_ib_register_client();
+ if (rc) {
+ pr_err("%s: ib_register fails with %d\n", __func__, rc);
+ goto out_sock;
+ }
+
return 0;
+out_sock:
+ sock_unregister(PF_SMC);
out_proto:
proto_unregister(&smc_proto);
out:
@@ -607,6 +616,7 @@ out:
static void __exit smc_exit(void)
{
+ smc_ib_unregister_client();
sock_unregister(PF_SMC);
proto_unregister(&smc_proto);
}
diff --git a/net/smc/smc.h b/net/smc/smc.h
index fcea7399e2eb..e87d79867099 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -16,6 +16,8 @@
#define SMCPROTO_SMC 0 /* SMC protocol */
+#define SMC_MAX_PORTS 2 /* Max # of ports */
+
enum smc_state { /* possible states of an SMC socket */
SMC_ACTIVE = 1,
SMC_INIT = 2,
@@ -34,4 +36,8 @@ static inline struct smc_sock *smc_sk(const struct sock *sk)
return (struct smc_sock *)sk;
}
+#define SMC_SYSTEMID_LEN 8
+
+extern u8 local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */
+
#endif /* __SMC_H */
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
new file mode 100644
index 000000000000..7222b7ede900
--- /dev/null
+++ b/net/smc/smc_ib.c
@@ -0,0 +1,143 @@
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * IB infrastructure:
+ * Establish SMC-R as an Infiniband Client to be notified about added and
+ * removed IB devices of type RDMA.
+ * Determine device and port characteristics for these IB devices.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com>
+ */
+
+#include <linux/random.h>
+#include <rdma/ib_verbs.h>
+
+#include "smc_ib.h"
+#include "smc.h"
+
+struct smc_ib_devices smc_ib_devices = { /* smc-registered ib devices */
+ .lock = __SPIN_LOCK_UNLOCKED(smc_ib_devices.lock),
+ .list = LIST_HEAD_INIT(smc_ib_devices.list),
+};
+
+#define SMC_LOCAL_SYSTEMID_RESET "%%%%%%%"
+
+u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET; /* unique system
+ * identifier
+ */
+
+static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
+{
+ struct net_device *ndev;
+ int rc;
+
+ rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
+ &smcibdev->gid[ibport - 1], NULL);
+ /* the SMC protocol requires specification of the roce MAC address;
+ * if net_device cannot be determined, it can be derived from gid 0
+ */
+ ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
+ if (ndev) {
+ memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
+ } else if (!rc) {
+ memcpy(&smcibdev->mac[ibport - 1][0],
+ &smcibdev->gid[ibport - 1].raw[8], 3);
+ memcpy(&smcibdev->mac[ibport - 1][3],
+ &smcibdev->gid[ibport - 1].raw[13], 3);
+ smcibdev->mac[ibport - 1][0] &= ~0x02;
+ }
+ return rc;
+}
+
+/* Create an identifier unique for this instance of SMC-R.
+ * The MAC-address of the first active registered IB device
+ * plus a random 2-byte number is used to create this identifier.
+ * This name is delivered to the peer during connection initialization.
+ */
+static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
+ u8 ibport)
+{
+ memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
+ sizeof(smcibdev->mac[ibport - 1]));
+ get_random_bytes(&local_systemid[0], 2);
+}
+
+bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
+{
+ return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
+}
+
+int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
+{
+ int rc;
+
+ memset(&smcibdev->pattr[ibport - 1], 0,
+ sizeof(smcibdev->pattr[ibport - 1]));
+ rc = ib_query_port(smcibdev->ibdev, ibport,
+ &smcibdev->pattr[ibport - 1]);
+ if (rc)
+ goto out;
+ rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
+ if (rc)
+ goto out;
+ if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
+ sizeof(local_systemid)) &&
+ smc_ib_port_active(smcibdev, ibport))
+ /* create unique system identifier */
+ smc_ib_define_local_systemid(smcibdev, ibport);
+out:
+ return rc;
+}
+
+static struct ib_client smc_ib_client;
+
+/* callback function for ib_register_client() */
+static void smc_ib_add_dev(struct ib_device *ibdev)
+{
+ struct smc_ib_device *smcibdev;
+
+ if (ibdev->node_type != RDMA_NODE_IB_CA)
+ return;
+
+ smcibdev = kzalloc(sizeof(*smcibdev), GFP_KERNEL);
+ if (!smcibdev)
+ return;
+
+ smcibdev->ibdev = ibdev;
+
+ spin_lock(&smc_ib_devices.lock);
+ list_add_tail(&smcibdev->list, &smc_ib_devices.list);
+ spin_unlock(&smc_ib_devices.lock);
+ ib_set_client_data(ibdev, &smc_ib_client, smcibdev);
+}
+
+/* callback function for ib_register_client() */
+static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
+{
+ struct smc_ib_device *smcibdev;
+
+ smcibdev = ib_get_client_data(ibdev, &smc_ib_client);
+ ib_set_client_data(ibdev, &smc_ib_client, NULL);
+ spin_lock(&smc_ib_devices.lock);
+ list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
+ spin_unlock(&smc_ib_devices.lock);
+ kfree(smcibdev);
+}
+
+static struct ib_client smc_ib_client = {
+ .name = "smc_ib",
+ .add = smc_ib_add_dev,
+ .remove = smc_ib_remove_dev,
+};
+
+int __init smc_ib_register_client(void)
+{
+ return ib_register_client(&smc_ib_client);
+}
+
+void smc_ib_unregister_client(void)
+{
+ ib_unregister_client(&smc_ib_client);
+}
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
new file mode 100644
index 000000000000..63613e715f4f
--- /dev/null
+++ b/net/smc/smc_ib.h
@@ -0,0 +1,40 @@
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ * Definitions for IB environment
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * Author(s): Ursula Braun <Ursula Braun@linux.vnet.ibm.com>
+ */
+
+#ifndef _SMC_IB_H
+#define _SMC_IB_H
+
+#include <rdma/ib_verbs.h>
+
+#define SMC_MAX_PORTS 2 /* Max # of ports */
+#define SMC_GID_SIZE sizeof(union ib_gid)
+
+struct smc_ib_devices { /* list of smc ib devices definition */
+ struct list_head list;
+ spinlock_t lock; /* protects list of smc ib devices */
+};
+
+extern struct smc_ib_devices smc_ib_devices; /* list of smc ib devices */
+
+struct smc_ib_device { /* ib-device infos for smc */
+ struct list_head list;
+ struct ib_device *ibdev;
+ struct ib_port_attr pattr[SMC_MAX_PORTS]; /* ib dev. port attrs */
+ char mac[SMC_MAX_PORTS][6]; /* mac address per port*/
+ union ib_gid gid[SMC_MAX_PORTS]; /* gid per port */
+ u8 initialized : 1; /* ib dev CQ, evthdl done */
+};
+
+int smc_ib_register_client(void) __init;
+void smc_ib_unregister_client(void);
+bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport);
+int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport);
+
+#endif