Am 29.07.21 um 12:49 schrieb Guchun Chen:
In amdgpu_fence_driver_hw_fini, no need to call drm_sched_fini to stop
scheduler in s3 test, otherwise, fence errors will occur after resume.
So introduce a new parameter to distingiush the case in this API.
NAK, the problem is rather that drm_sched_fini() is part of the sw
shutdown and should never be called during hw_fini.
Christian.
Fixes: cd87a6dcf6af drm/amdgpu: adjust fence driver enable sequence
Signed-off-by: Guchun Chen <guchun.chen@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++--
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 8 +++++---
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 2 +-
3 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b1d2dc39e8be..aaff8ebbb7dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3844,7 +3844,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
else
drm_atomic_helper_shutdown(adev_to_drm(adev));
}
- amdgpu_fence_driver_hw_fini(adev);
+ amdgpu_fence_driver_hw_fini(adev, false);
if (adev->pm_sysfs_en)
amdgpu_pm_sysfs_fini(adev);
@@ -3941,7 +3941,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
/* evict vram memory */
amdgpu_bo_evict_vram(adev);
- amdgpu_fence_driver_hw_fini(adev);
+ amdgpu_fence_driver_hw_fini(adev, adev->in_suspend);
amdgpu_device_ip_suspend_phase2(adev);
/* evict remaining vram memory
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 49c5c7331c53..7e6a73c2919d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -515,14 +515,15 @@ int amdgpu_fence_driver_init(struct amdgpu_device *adev)
}
/**
- * amdgpu_fence_driver_fini - tear down the fence driver
+ * amdgpu_fence_driver_hw_fini - tear down the fence driver
* for all possible rings.
*
* @adev: amdgpu device pointer
+ * @in_reset: indicator to distingiush device removal case or s3 case
*
* Tear down the fence driver for all possible rings (all asics).
*/
-void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
+void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev, bool in_reset)
{
int i, r;
@@ -531,8 +532,9 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
if (!ring || !ring->fence_drv.initialized)
continue;
- if (!ring->no_scheduler)
+ if (!ring->no_scheduler && !in_reset)
drm_sched_fini(&ring->sched);
+
/* You can't wait for HW to signal if it's gone */
if (!drm_dev_is_unplugged(&adev->ddev))
r = amdgpu_fence_wait_empty(ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 27adffa7658d..42cbecfc26a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -115,7 +115,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
struct amdgpu_irq_src *irq_src,
unsigned irq_type);
-void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev);
+void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev, bool in_reset);
void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev);
void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev);
int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence,
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
