diff options
author | Eli Cohen <eli@mellanox.com> | 2012-03-06 08:50:51 -0500 |
---|---|---|
committer | Roland Dreier <roland@purestorage.com> | 2012-03-12 19:24:59 -0400 |
commit | 3616f9cead935d4e4c35915600d5e4d1384219cd (patch) | |
tree | b82899b32ce3c64195195351358267764e535c04 /drivers/infiniband/hw/mlx4/cq.c | |
parent | 5984be90046fa978d94a5ec08bbf8f760cff2b30 (diff) |
IB/mlx4: Fix possible missed completion event
If an erroneous CQE is polled in the first iteration (i.e. npolled ==
0), we don't update the consumer index and hence the hardware could
get a wrong notion of how many CQEs software polled. Fix this by
unconditionally updating the doorbell record. We could change the
check to be something like
if (npolled || err != -EAGAIN)
...
but it does not seem worth the effort since a posted write to memory
should not cost too much.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Diffstat (limited to 'drivers/infiniband/hw/mlx4/cq.c')
-rw-r--r-- | drivers/infiniband/hw/mlx4/cq.c | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index 5ecf38d97269..275861bddf1c 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c | |||
@@ -747,8 +747,7 @@ int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc) | |||
747 | break; | 747 | break; |
748 | } | 748 | } |
749 | 749 | ||
750 | if (npolled) | 750 | mlx4_cq_set_ci(&cq->mcq); |
751 | mlx4_cq_set_ci(&cq->mcq); | ||
752 | 751 | ||
753 | spin_unlock_irqrestore(&cq->lock, flags); | 752 | spin_unlock_irqrestore(&cq->lock, flags); |
754 | 753 | ||