Switch back to using a spinlock again by moving the IOMMU unmap outside
of the locked region.
This avoids contention especially while freeing pages.
v2: Add a comment explaining why we need sync_shrinkers().
Signed-off-by: Christian König
Acked-by: Huang Rui
Reviewed-by: Daniel Vetter
---
dr
Just a gentle ping?
Are you ok with this explanation Andrew or should I look for a different
approach?
Thanks,
Christian.
Am 16.04.21 um 09:08 schrieb Christian König:
Am 15.04.21 um 22:33 schrieb Andrew Morton:
On Thu, 15 Apr 2021 13:56:24 +0200 "Christian König"
wrote:
@@ -530,6 +525,
Am 15.04.21 um 22:33 schrieb Andrew Morton:
On Thu, 15 Apr 2021 13:56:24 +0200 "Christian König"
wrote:
@@ -530,6 +525,11 @@ void ttm_pool_fini(struct ttm_pool *pool)
for (j = 0; j < MAX_ORDER; ++j)
ttm_pool_type_fini(&pool->caching[i].o
On Thu, 15 Apr 2021 13:56:24 +0200 "Christian König"
wrote:
> @@ -530,6 +525,11 @@ void ttm_pool_fini(struct ttm_pool *pool)
> for (j = 0; j < MAX_ORDER; ++j)
> ttm_pool_type_fini(&pool->caching[i].orders[j]);
> }
> +
> + /* We remove
On Thu, Apr 15, 2021 at 07:56:24PM +0800, Christian König wrote:
> Switch back to using a spinlock again by moving the IOMMU unmap outside
> of the locked region.
>
> v2: Add a comment explaining why we need sync_shrinkers().
>
> Signed-off-by: Christian König
Series look good for me as well.
Switch back to using a spinlock again by moving the IOMMU unmap outside
of the locked region.
v2: Add a comment explaining why we need sync_shrinkers().
Signed-off-by: Christian König
---
drivers/gpu/drm/ttm/ttm_pool.c | 44 +-
1 file changed, 22 insertions(+), 2
