linux_dsm_epyc7002/drivers/infiniband/hw
Roland Dreier 0c87b67209 IB/mlx4: Don't use GFP_ATOMIC for CQ resize struct
We allocate a small tracking structure as part of mlx4_ib_resize_cq().
However, we don't need to use GFP_ATOMIC -- immediately after the
allocation, we call mlx4_cq_resize(), which allocates a command
mailbox with GFP_KERNEL and then sleeps on a firmware command, so we
better not be in an atomic context.

This actually has a real impact, because when this GFP_ATOMIC
allocation fails (and GFP_ATOMIC does fail in practice) then a
userspace consumer resizing a CQ will get a spurious failure that we
can easily avoid.

Signed-off-by: Roland Dreier <roland@purestorage.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-08-03 21:03:32 -04:00
..
cxgb3 Round two of 4.7 merge window patches 2016-05-28 11:04:16 -07:00
cxgb4 IB/core: Make device counter infrastructure dynamic 2016-05-26 12:52:51 -04:00
hfi1 IB/hfi1: Disable by default 2016-08-03 21:03:32 -04:00
i40iw IB/core: Make device counter infrastructure dynamic 2016-05-26 12:52:51 -04:00
mlx4 IB/mlx4: Don't use GFP_ATOMIC for CQ resize struct 2016-08-03 21:03:32 -04:00
mlx5 IB/mlx5: Fix alternate path code 2016-06-07 10:03:50 -04:00
mthca mm/gup: Switch all callers of get_user_pages() to not pass tsk/mm 2016-02-16 10:11:12 +01:00
nes Primary 4.7 merge window changes 2016-05-20 14:35:07 -07:00
ocrdma IB/core: Enhance ib_map_mr_sg() 2016-05-13 13:37:57 -04:00
qib Round two of 4.7 merge window patches 2016-05-28 11:04:16 -07:00
usnic IB/usnic: Remove unused DMA attributes 2016-06-06 19:28:06 -04:00
Makefile IB/hfi1: Move driver out of staging 2016-05-26 11:35:14 -04:00