diff options
| author | Alexander Duyck <alexander.h.duyck@redhat.com> | 2015-04-09 04:49:36 +0300 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-04-09 21:25:25 +0300 |
| commit | 12b3375f3963536ba3ad47d2db49f72067b4905e (patch) | |
| tree | 1aa5051a9936718911a87d8cc4eed864d703132b /drivers/net/ethernet/mellanox/mlx4/eq.c | |
| parent | 019be1cff44bdfed23163be7469419be4f38589b (diff) | |
| download | linux-12b3375f3963536ba3ad47d2db49f72067b4905e.tar.xz | |
mlx4/mlx5: Use dma_wmb/rmb where appropriate
This patch should help to improve the performance of the mlx4 and mlx5 on a
number of architectures. For example, on x86 the dma_wmb/rmb equates out
to a barrer() call as the architecture is already strong ordered, and on
PowerPC the call works out to a lwsync which is significantly less expensive
than the sync call that was being used for wmb.
I placed the new barriers between any spots that seemed to be trying to
order memory/memory reads or writes, if there are any spots that involved
MMIO I left the existing wmb in place as the new barriers cannot order
transactions between coherent and non-coherent memories.
v2: Reduced the replacments to just the spots where I could clearly
identify the usage pattern.
Cc: Amir Vadai <amirv@mellanox.com>
Cc: Ido Shamay <idos@mellanox.com>
Cc: Eli Cohen <eli@mellanox.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4/eq.c')
| -rw-r--r-- | drivers/net/ethernet/mellanox/mlx4/eq.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 6e70ffee8e87..190fd624bdfe 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -188,7 +188,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe) memcpy(s_eqe, eqe, dev->caps.eqe_size - 1); s_eqe->slave_id = slave; /* ensure all information is written before setting the ownersip bit */ - wmb(); + dma_wmb(); s_eqe->owner = !!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE) ? 0x0 : 0x80; ++slave_eq->prod; @@ -473,7 +473,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) * Make sure we read EQ entry contents after we've * checked the ownership bit. */ - rmb(); + dma_rmb(); switch (eqe->type) { case MLX4_EVENT_TYPE_COMP: |