On Thu, Apr 4, 2019 at 4:46 AM Gal Pressman <galpr...@amazon.com> wrote: > > On 03-Apr-19 02:03, Saeed Mahameed wrote: > > From: Tariq Toukan <tar...@mellanox.com> > > > > Soften the memory barrier call of mb() by a sufficient wmb() in the > > consumer index update of the event queues. > > > > Signed-off-by: Tariq Toukan <tar...@mellanox.com> > > Signed-off-by: Saeed Mahameed <sae...@mellanox.com> > > --- > > drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c > > b/drivers/net/ethernet/mellanox/mlx5/core/eq.c > > index 46a747f7c162..e9837aeb7088 100644 > > --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c > > +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c > > @@ -707,7 +707,7 @@ void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool > > arm) > > > > __raw_writel((__force u32)cpu_to_be32(val), addr); > > /* We still want ordering, just not swabbing, so add a barrier */ > > - mb(); > > + wmb(); > > Shouldn't this barrier be placed prior to __raw_writel()?
same effect in both cases, we just want a fence between every two consecutive writes.
