diff options
author | Or Gerlitz <ogerlitz@voltaire.com> | 2008-07-22 14:14:22 -0700 |
---|---|---|
committer | Roland Dreier <rolandd@cisco.com> | 2008-07-22 14:14:22 -0700 |
commit | dd5bdff83b19d9174126e0398b47117c3a80e22d (patch) | |
tree | 2bdbc102afcc851d1cd0bef07e3a47d4e9ec1ae9 /drivers/infiniband | |
parent | d35cb360c29956510b2fe1a953bd4968536f7216 (diff) | |
download | talos-op-linux-dd5bdff83b19d9174126e0398b47117c3a80e22d.tar.gz talos-op-linux-dd5bdff83b19d9174126e0398b47117c3a80e22d.zip |
RDMA/cma: Add RDMA_CM_EVENT_ADDR_CHANGE event
Add an RDMA_CM_EVENT_ADDR_CHANGE event can be used by rdma-cm
consumers that wish to have their RDMA sessions always use the same
links (eg <hca/port>) as the IP stack does. In the current code, this
does not happen when bonding is used and fail-over happened but the IB
link used by an already existing session is operating fine.
Use the netevent notification for sensing that a change has happened
in the IP stack, then scan the rdma-cm ID list to see if there is an
ID that is "misaligned" with respect to the IP stack, and deliver
RDMA_CM_EVENT_ADDR_CHANGE for this ID. The consumer can act on the
event or just ignore it.
Signed-off-by: Or Gerlitz <ogerlitz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r-- | drivers/infiniband/core/cma.c | 92 |
1 files changed, 92 insertions, 0 deletions
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index ae11d5cc74d0..79792c92e6fb 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -168,6 +168,12 @@ struct cma_work { struct rdma_cm_event event; }; +struct cma_ndev_work { + struct work_struct work; + struct rdma_id_private *id; + struct rdma_cm_event event; +}; + union cma_ip_addr { struct in6_addr ip6; struct { @@ -1598,6 +1604,30 @@ out: kfree(work); } +static void cma_ndev_work_handler(struct work_struct *_work) +{ + struct cma_ndev_work *work = container_of(_work, struct cma_ndev_work, work); + struct rdma_id_private *id_priv = work->id; + int destroy = 0; + + mutex_lock(&id_priv->handler_mutex); + if (id_priv->state == CMA_DESTROYING || + id_priv->state == CMA_DEVICE_REMOVAL) + goto out; + + if (id_priv->id.event_handler(&id_priv->id, &work->event)) { + cma_exch(id_priv, CMA_DESTROYING); + destroy = 1; + } + +out: + mutex_unlock(&id_priv->handler_mutex); + cma_deref_id(id_priv); + if (destroy) + rdma_destroy_id(&id_priv->id); + kfree(work); +} + static int cma_resolve_ib_route(struct rdma_id_private *id_priv, int timeout_ms) { struct rdma_route *route = &id_priv->id.route; @@ -2723,6 +2753,65 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) } EXPORT_SYMBOL(rdma_leave_multicast); +static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv) +{ + struct rdma_dev_addr *dev_addr; + struct cma_ndev_work *work; + + dev_addr = &id_priv->id.route.addr.dev_addr; + + if ((dev_addr->src_dev == ndev) && + memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) { + printk(KERN_INFO "RDMA CM addr change for ndev %s used by id %p\n", + ndev->name, &id_priv->id); + work = kzalloc(sizeof *work, GFP_KERNEL); + if (!work) + return -ENOMEM; + + INIT_WORK(&work->work, cma_ndev_work_handler); + work->id = id_priv; + work->event.event = RDMA_CM_EVENT_ADDR_CHANGE; + atomic_inc(&id_priv->refcount); + queue_work(cma_wq, &work->work); + } + + return 0; +} + +static int cma_netdev_callback(struct notifier_block *self, unsigned long event, + void *ctx) +{ + struct net_device *ndev = (struct net_device *)ctx; + struct cma_device *cma_dev; + struct rdma_id_private *id_priv; + int ret = NOTIFY_DONE; + + if (dev_net(ndev) != &init_net) + return NOTIFY_DONE; + + if (event != NETDEV_BONDING_FAILOVER) + return NOTIFY_DONE; + + if (!(ndev->flags & IFF_MASTER) || !(ndev->priv_flags & IFF_BONDING)) + return NOTIFY_DONE; + + mutex_lock(&lock); + list_for_each_entry(cma_dev, &dev_list, list) + list_for_each_entry(id_priv, &cma_dev->id_list, list) { + ret = cma_netdev_change(ndev, id_priv); + if (ret) + goto out; + } + +out: + mutex_unlock(&lock); + return ret; +} + +static struct notifier_block cma_nb = { + .notifier_call = cma_netdev_callback +}; + static void cma_add_one(struct ib_device *device) { struct cma_device *cma_dev; @@ -2831,6 +2920,7 @@ static int cma_init(void) ib_sa_register_client(&sa_client); rdma_addr_register_client(&addr_client); + register_netdevice_notifier(&cma_nb); ret = ib_register_client(&cma_client); if (ret) @@ -2838,6 +2928,7 @@ static int cma_init(void) return 0; err: + unregister_netdevice_notifier(&cma_nb); rdma_addr_unregister_client(&addr_client); ib_sa_unregister_client(&sa_client); destroy_workqueue(cma_wq); @@ -2847,6 +2938,7 @@ err: static void cma_cleanup(void) { ib_unregister_client(&cma_client); + unregister_netdevice_notifier(&cma_nb); rdma_addr_unregister_client(&addr_client); ib_sa_unregister_client(&sa_client); destroy_workqueue(cma_wq); |