Commit 0b394982 authored by Shenming Lu's avatar Shenming Lu Committed by Marc Zyngier

irqchip/gic-v4.1: Reduce the delay when polling GICR_VPENDBASER.Dirty

The 10us delay of the poll on the GICR_VPENDBASER.Dirty bit is too
high, which might greatly affect the total scheduling latency of a
vCPU in our measurement. So we reduce it to 1 to lessen the impact.
Signed-off-by: default avatarShenming Lu <lushenming@huawei.com>
Signed-off-by: default avatarMarc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20201128141857.983-2-lushenming@huawei.com
parent 3841245e
...@@ -3808,7 +3808,7 @@ static void its_wait_vpt_parse_complete(void) ...@@ -3808,7 +3808,7 @@ static void its_wait_vpt_parse_complete(void)
WARN_ON_ONCE(readq_relaxed_poll_timeout_atomic(vlpi_base + GICR_VPENDBASER, WARN_ON_ONCE(readq_relaxed_poll_timeout_atomic(vlpi_base + GICR_VPENDBASER,
val, val,
!(val & GICR_VPENDBASER_Dirty), !(val & GICR_VPENDBASER_Dirty),
10, 500)); 1, 500));
} }
static void its_vpe_schedule(struct its_vpe *vpe) static void its_vpe_schedule(struct its_vpe *vpe)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment