drm/amdgpu: Fix SDMA TO after GPU reset v3

[ Upstream commit d8de8260a45aae8f74af77eae9a162bdc0ed48d2 ]

After GPU reset amdgpu_vm_clear_bo triggers VM flush
but job->vm_pd_addr is not set causing SDMA TO.

v2:
Per advise by Christian König avoid flushing VM for jobs where
job->vm_pd_addr wasn't explicitly set.

v3:
Shortcut vm_flush_needed early.

Fixes cbd5285 drm/amdgpu: move setting the GART addr into TTM.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 391e2f7..f823d4b 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -66,6 +66,7 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
        amdgpu_sync_create(&(*job)->sync);
        amdgpu_sync_create(&(*job)->sched_sync);
        (*job)->vram_lost_counter = atomic_read(&adev->vram_lost_counter);
+       (*job)->vm_pd_addr = AMDGPU_BO_INVALID_OFFSET;
 
        return 0;
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index b17771d..6a84526 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -714,7 +714,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
        }
 
        gds_switch_needed &= !!ring->funcs->emit_gds_switch;
-       vm_flush_needed &= !!ring->funcs->emit_vm_flush;
+       vm_flush_needed &= !!ring->funcs->emit_vm_flush  &&
+                       job->vm_pd_addr != AMDGPU_BO_INVALID_OFFSET;
        pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping &&
                ring->funcs->emit_wreg;