[ofa-general] [PATCH] IB/mlx4 mlx4_ib: eq interrupts

[Roland Dreier]

Thanks... should we optimize out the

	if (eqes_found)
		eq_set_ci(eq, 1);

at the end of mlx4_eq_int() now?  Actually the best fix is probably:

diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c
index 8d641b8..acf1c80 100644
--- a/drivers/net/mlx4/eq.c
+++ b/drivers/net/mlx4/eq.c
@@ -249,8 +249,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 		}
 	}
 
-	if (eqes_found)
-		eq_set_ci(eq, 1);
+	eq_set_ci(eq, 1);
 
 	return eqes_found;
 }

because it seems sort of strange if we ever don't rearm the EQ on an
MSI-X interrupt.

What do you think?

On the other hand, this patch (and your patch) rearms the EQ on shared
interrupts for other devices too.  Can't be helped I guess.

 - R.