Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
drm/amdgpu: Avoid kcq disable during reset
Reset sequence indicates that hardware already ran into a bad state.
Avoid sending unmap queue request to reset KCQ. This will also cover RAS
error scenarios which need a reset to recover, hence remove the check.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
authored by
Lijo Lazar
and committed by
Alex Deucher
7b1ebbe8
fa317985
+1
-9
+1
-9
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+1
-9
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
···
515
515
if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
516
516
return -EINVAL;
517
517
518
-
if (!kiq_ring->sched.ready || adev->job_hang)
519
-
return 0;
520
-
/**
521
-
* This is workaround: only skip kiq_ring test
522
-
* during ras recovery in suspend stage for gfx9.4.3
523
-
*/
524
-
if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
525
-
amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) &&
526
-
amdgpu_ras_in_recovery(adev))
518
+
if (!kiq_ring->sched.ready || adev->job_hang || amdgpu_in_reset(adev))
527
519
return 0;
528
520
529
521
spin_lock(&kiq->ring_lock);