drm/msm: Remove exclusive-fence hack
Subsystems (4)
PATCH 1/1 drm/msm: Remove exclusive-fence hack
From: Rob Clark <[email protected]>
The workaround was initially necessary due to dma_resv having only a single exclusive fence slot, yet whe don't necessarily know what order the gpu scheduler will schedule jobs. Unfortunately this workaround also has the result of forcing implicit sync, even when userspace does not want it.
However, since commit 047a1b877ed4 ("dma-buf & drm/amdgpu: remove dma_resv workaround") the workaround is no longer needed. So remove it. This effectively reverts commit f1b3f696a084 ("drm/msm: Don't break exclusive fence ordering")
--- drivers/gpu/drm/msm/msm_gem_submit.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/gpu/drm/msm/msm_gem_submit.c +1 -2
@@ -334,8 +334,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)if (ret)return ret; -/* exclusive fences must be ordered */ -if (no_implicit && !write) +if (no_implicit)continue ; ret = drm_sched_job_add_implicit_dependencies(&submit->base,
Signature · 1 line
2.38.1
Am 01.11.22 um 22:40 schrieb Rob Clark:
Quoted 8 lines
From: Rob Clark <[email protected]>
The workaround was initially necessary due to
dma_resvhaving only a single exclusive fence slot, yet whe don't necessarily know what order the gpu scheduler will schedule jobs. Unfortunately this workaround also has the result of forcing implicit sync, even when userspace does not want it.
Quoted 6 lines
However, since commit
047a1b877ed4("dma-buf & drm/amdgpu: removedma_resvworkaround") the workaround is no longer needed. So remove it. This effectively reverts commitf1b3f696a084("drm/msm: Don't break exclusive fence ordering")Signed-off-by Rob Clark <[email protected]>
Oh, yes please. I had that on my todo list for after the initial patch had landed, but couldn't find the time to look into it once more.
There was another case with one of the other ARM drivers which could be cleaned up now, but I can't find it any more of hand.
Anyway this patch here is Acked-by: Christian König <[email protected]>.
Regards,
Christian.
Quoted 18 lines
--- drivers/gpu/drm/msm/msm_gem_submit.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)drivers/gpu/drm/msm/msm_gem_submit.c +1
-2@@ -334,8 +334,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)if (ret)return ret; -/* exclusive fences must be ordered */ -if (no_implicit && !write) +if (no_implicit)continue ; ret = drm_sched_job_add_implicit_dependencies(&submit->base,
Quoted 17 lines · Christian König
Am 01.11.22 um 22:40 schrieb Rob Clark:
Quoted 8 lines
From: Rob Clark <[email protected]>
The workaround was initially necessary due to
dma_resvhaving only a single exclusive fence slot, yet whe don't necessarily know what order the gpu scheduler will schedule jobs. Unfortunately this workaround also has the result of forcing implicit sync, even when userspace does not want it.Quoted 6 lines
However, since commit
047a1b877ed4("dma-buf & drm/amdgpu: removedma_resvworkaround") the workaround is no longer needed. So remove it. This effectively reverts commitf1b3f696a084("drm/msm: Don't break exclusive fence ordering")Signed-off-by Rob Clark <[email protected]>
Quoted 8 lines
Oh, yes please. I had that on my todo list for after the initial patch had landed, but couldn't find the time to look into it once more.
There was another case with one of the other ARM drivers which could be cleaned up now, but I can't find it any more of hand.
Anyway this patch here is Acked-by: Christian König <[email protected]>.
Thanks.. I had a quick look for the other driver but couldn't spot anything, so perhaps it has already been fixed?
BR,
-R
Quoted 23 lines
Regards,
Christian.Quoted 18 lines
--- drivers/gpu/drm/msm/msm_gem_submit.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)drivers/gpu/drm/msm/msm_gem_submit.c +1
-2@@ -334,8 +334,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)if (ret)return ret; -/* exclusive fences must be ordered */ -if (no_implicit && !write) +if (no_implicit)continue ; ret = drm_sched_job_add_implicit_dependencies(&submit->base,