[PATCH AUTOSEL 5.2 138/185] iommu/iova: Avoid false sharing on fq_timer_on

From: Sasha Levin
Date: Sun Sep 22 2019 - 15:22:53 EST


From: Eric Dumazet <edumazet@xxxxxxxxxx>

[ Upstream commit 0d87308cca2c124f9bce02383f1d9632c9be89c4 ]

In commit 14bd9a607f90 ("iommu/iova: Separate atomic variables
to improve performance") Jinyu Qi identified that the atomic_cmpxchg()
in queue_iova() was causing a performance loss and moved critical fields
so that the false sharing would not impact them.

However, avoiding the false sharing in the first place seems easy.
We should attempt the atomic_cmpxchg() no more than 100 times
per second. Adding an atomic_read() will keep the cache
line mostly shared.

This false sharing came with commit 9a005a800ae8
("iommu/iova: Add flush timer").

Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Fixes: 9a005a800ae8 ('iommu/iova: Add flush timer')
Cc: Jinyu Qi <jinyuqi@xxxxxxxxxx>
Cc: Joerg Roedel <jroedel@xxxxxxx>
Acked-by: Robin Murphy <robin.murphy@xxxxxxx>
Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/iommu/iova.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 3e1a8a6755723..41c605b0058f9 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -577,7 +577,9 @@ void queue_iova(struct iova_domain *iovad,

spin_unlock_irqrestore(&fq->lock, flags);

- if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0)
+ /* Avoid false sharing as much as possible. */
+ if (!atomic_read(&iovad->fq_timer_on) &&
+ !atomic_cmpxchg(&iovad->fq_timer_on, 0, 1))
mod_timer(&iovad->fq_timer,
jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
}
--
2.20.1