drm/amdkfd: start_cpsch don't map queues
Subsystems (3)
PATCH 1/1 drm/amdkfd: start_cpsch don't map queues
start_cpsch map queues when kfd_init_node have race condition with IOMMUv2 init, and cause the gfx ring test failed later. Remove it from start_cpsch because map queues will be done when creating queues and resume queues.
--- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 3 --- 1 file changed, 3 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +0 -3
@@ -1658,9 +1658,6 @@ static int start_cpsch(struct device_queue_manager *dqm) dqm->is_resetting = false; dqm->sched_running = true; -if (!dqm->dev->kfd->shared_resources.enable_mes) -execute_queues_cpsch (dqm,KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES ,0 ,USE_DEFAULT_GRACE_PERIOD ); -/* Set CWSR grace period to 1x1000 cycle for GFX9.4.3 APU */ if (amdgpu_emu_mode ==0 && dqm->dev->adev->gmc.is_app_apu && (KFD_GC_VERSION (dqm->dev) ==IP_VERSION (9 ,4 ,3 ))) {
Signature · 1 line
2.35.1
Quoted 7 lines · Philip Yang
start_cpschmap queues whenkfd_init_nodehave race condition with IOMMUv2 init, and cause the gfx ring test failed later. Remove it fromstart_cpschbecause map queues will be done when creating queues and resume queues.Reported-by Michel Dänzer <[email protected]>Signed-off-by Philip Yang <[email protected]>
Michel, can you test whether this fixes your regression on Raven? Would be good to get a Tested-by for this patch, since we haven't been able to reproduce the problem yet.
Thanks,
Felix
Quoted 18 lines
--- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 3 --- 1 file changed, 3 deletions(-)drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +0
-3@@ -1658,9 +1658,6 @@ static int start_cpsch(struct device_queue_manager *dqm) dqm->is_resetting = false; dqm->sched_running = true; -if (!dqm->dev->kfd->shared_resources.enable_mes) -execute_queues_cpsch (dqm,KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES ,0 ,USE_DEFAULT_GRACE_PERIOD ); -/* Set CWSR grace period to 1x1000 cycle for GFX9.4.3 APU */ if (amdgpu_emu_mode ==0 && dqm->dev->adev->gmc.is_app_apu && (KFD_GC_VERSION (dqm->dev) ==IP_VERSION (9 ,4 ,3 ))) {
Quoted 7 lines · Philip Yang
start_cpschmap queues whenkfd_init_nodehave race condition with IOMMUv2 init, and cause the gfx ring test failed later. Remove it fromstart_cpschbecause map queues will be done when creating queues and resume queues.Reported-by Michel Dänzer <[email protected]>Signed-off-by Philip Yang <[email protected]>
This patch doesn't help for any of the symptoms I've described I'm afraid.
iommu=pt on the kernel command line avoids the IB test failures for the compute rings, but doesn't help for any of the other symptoms either, which still leaves the system unusable overall.
Sorry I don't have better news,
Signature · 2 lines
Earthling Michel Dänzer | https://redhat.com Libre software enthusiast | Mesa and Xwayland developer
Quoted 10 lines · Michel Dänzer
Quoted 7 lines · Philip Yang
start_cpschmap queues whenkfd_init_nodehave race condition with IOMMUv2 init, and cause the gfx ring test failed later. Remove it fromstart_cpschbecause map queues will be done when creating queues and resume queues.Reported-by Michel Dänzer <[email protected]>Signed-off-by Philip Yang <[email protected]>This patch doesn't help for any of the symptoms I've described I'm afraid.
Actually, I failed to check one thing before:
The patch fixed both IOMMU page faults. The IB tests on the compute rings still failed though.
Interestingly, with iommu=pt there was still one IOMMU page fault, even with this patch:
amdgpu 0000:05:00.0: AMD-Vi: Event logged [IO_PAGE_FAULT domain=0x0000 address=0x14105a380 flags=0x0070]
Signature · 2 lines
Earthling Michel Dänzer | https://redhat.com Libre software enthusiast | Mesa and Xwayland developer