kernel/linux.git/drivers/infiniband/ulp, branch linux-2.6.16.y

IPoIB: Rejoin all multicast groups after a port event

2007-03-11T06:36:27+00:00

When ipoib_ib_dev_flush() is called because of a port event, the driver needs to rejoin all multicast groups, since the flush will call ipoib_mcast_dev_flush() (via ipoib_ib_dev_down()). Otherwise no (non-broadcast) multicast groups will be rejoined until the networking core calls ->set_multicast_list again, and so multicast reception will be broken for potentially a long time. Signed-off-by: Eli Cohen Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier Signed-off-by: Adrian Bunk

IB/srp: Don't send task management commands after target removal

2006-03-04T01:50:16+00:00

Just fail abort and reset requests that come in after we've already decided to remove a target. Signed-off-by: Roland Dreier

IPoIB: Yet another fix for send-only joins

2006-02-11T20:22:12+00:00

Even after the last fix, it's still possible for a send-only join to start before the join for the broadcast group has finished. This could cause us to create a multicast group using attributes from the broadcast group that haven't been initialized yet, so we would use garbage for the Q_Key, etc. Fix this by waiting until the broadcast group's attached flag is set before starting send-only joins. Signed-off-by: Roland Dreier

IPoIB: Fix another send-only join race

2006-02-08T00:39:26+00:00

Further, there's an additional issue that I saw in testing: ipoib_mcast_send may get called when priv->broadcast is NULL (e.g. if the device was downed and then upped internally because of a port event). If this happends and the send-only join request gets completed before priv->broadcast is set, we get an oops. Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier

IPoIB: Don't start send-only joins while multicast thread is stopped

2006-02-08T00:37:08+00:00

Fix the following race scenario: - Device is up. - Port event or set mcast list triggers ipoib_mcast_stop_thread, this cancels the query and waits on mcast "done" completion. - Completion is called and "done" is set. - Meanwhile, ipoib_mcast_send arrives and starts a new query, re-initializing "done". Fix this by adding a "multicast started" bit and checking it before starting a send-only join. Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier

IB/srp: Semaphore to mutex conversion

2006-01-30T23:21:21+00:00

Convert srp_host->target_mutex from a semaphore to a mutex. Signed-off-by: Ingo Molnar Signed-off-by: Roland Dreier

IPoIB: Lock accesses to multicast packet queues

2006-01-17T20:19:40+00:00

Avoid corrupting mcast->pkt_queue by serializing access with priv->tx_lock. Also, update dropped packet statistics to count multicast packets removed from pkt_queue as dropped. Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier

IPoIB: Make sure path is fully initialized before using it

2006-01-17T17:22:05+00:00

The SA path record query completion can initialize path->pathrec.dlid before IPoIB's callback runs and initializes path->ah, so we must test ah rather than dlid. Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier

IB: convert from semaphores to mutexes

2006-01-13T22:51:39+00:00

semaphore to mutex conversion by Ingo and Arjan's script. Signed-off-by: Ingo Molnar [ Sanity-checked on real IB hardware ] Signed-off-by: Roland Dreier

IPoIB: Fix memory leak of multicast group structures

2006-01-12T22:32:20+00:00

The current handling of multicast groups in IPoIB ends up never freeing send-only multicast groups. It turns out the logic was much more complicated than it needed to be; we can fix this bug and completely kill ipoib_mcast_dev_down() at the same time. Signed-off-by: Eli Cohen Signed-off-by: Michael S. Tsirkin Signed-off-by: Roland Dreier