linux/drivers/infiniband
Ralph Campbell 4780c1953f IB/mad: Fix ib_post_send_mad() returning 0 with no generate send comp
If ib_post_send_mad() returns 0, the API guarantees that there will be
a callback to send_buf->mad_agent->send_handler() so that the sender
can call ib_free_send_mad().  Otherwise, the ib_mad_send_buf will be
leaked and the mad_agent reference count will never go to zero and the
IB device module cannot be unloaded.  The above can happen without
this patch if process_mad() returns (IB_MAD_RESULT_SUCCESS |
IB_MAD_RESULT_CONSUMED).

If process_mad() returns IB_MAD_RESULT_SUCCESS and there is no agent
registered to receive the mad being sent, handle_outgoing_dr_smp()
returns zero which causes a MAD packet which is at the end of the
directed route to be incorrectly sent on the wire but doesn't cause a
hang since the HCA generates a send completion.

Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
2009-03-03 14:22:17 -08:00
..
core IB/mad: Fix ib_post_send_mad() returning 0 with no generate send comp 2009-03-03 14:22:17 -08:00
hw Merge branches 'ehca', 'ipoib' and 'mlx4' into for-linus 2009-01-16 15:05:54 -08:00
ulp IPoIB: Do not print error messages for multicast join retries 2009-01-16 13:42:59 -08:00
Kconfig RDMA/addr: Fix build breakage when IPv6 is disabled 2008-12-29 23:37:14 -08:00
Makefile RDMA/nes: Add a driver for NetEffect RNICs 2008-02-04 20:20:45 -08:00