Please go ahead. Thanks!
Alex
On Thu, Aug 19, 2021 at 8:05 AM Mike Lothian <mike@xxxxxxxxxxxxxx> wrote:
>
> Hi
>
> Do I need to open a new bug report for this?
>
> Cheers
>
> Mike
>
> On Wed, 18 Aug 2021 at 06:26, Andrey Grodzovsky <andrey.grodzovsky@xxxxxxx> wrote:
>>
>>
>> On 2021-08-02 1:16 a.m., Guchun Chen wrote:
>> > In amdgpu_fence_driver_hw_fini, no need to call drm_sched_fini to stop
>> > scheduler in s3 test, otherwise, fence related failure will arrive
>> > after resume. To fix this and for a better clean up, move drm_sched_fini
>> > from fence_hw_fini to fence_sw_fini, as it's part of driver shutdown, and
>> > should never be called in hw_fini.
>> >
>> > v2: rename amdgpu_fence_driver_init to amdgpu_fence_driver_sw_init,
>> > to keep sw_init and sw_fini paired.
>> >
>> > Fixes: cd87a6dcf6af drm/amdgpu: adjust fence driver enable sequence
>> > Suggested-by: Christian König <christian.koenig@xxxxxxx>
>> > Signed-off-by: Guchun Chen <guchun.chen@xxxxxxx>
>> > ---
>> > drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 ++---
>> > drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 12 +++++++-----
>> > drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 4 ++--
>> > 3 files changed, 11 insertions(+), 10 deletions(-)
>> >
>> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> > index b1d2dc39e8be..9e53ff851496 100644
>> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
>> > @@ -3646,9 +3646,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
>> >
>> > fence_driver_init:
>> > /* Fence driver */
>> > - r = amdgpu_fence_driver_init(adev);
>> > + r = amdgpu_fence_driver_sw_init(adev);
>> > if (r) {
>> > - dev_err(adev->dev, "amdgpu_fence_driver_init failed\n");
>> > + dev_err(adev->dev, "amdgpu_fence_driver_sw_init failed\n");
>> > amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_FENCE_INIT_FAIL, 0, 0);
>> > goto failed;
>> > }
>> > @@ -3988,7 +3988,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
>> > }
>> > amdgpu_fence_driver_hw_init(adev);
>> >
>> > -
>> > r = amdgpu_device_ip_late_init(adev);
>> > if (r)
>> > return r;
>> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> > index 49c5c7331c53..7495911516c2 100644
>> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> > @@ -498,7 +498,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
>> > }
>> >
>> > /**
>> > - * amdgpu_fence_driver_init - init the fence driver
>> > + * amdgpu_fence_driver_sw_init - init the fence driver
>> > * for all possible rings.
>> > *
>> > * @adev: amdgpu device pointer
>> > @@ -509,13 +509,13 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
>> > * amdgpu_fence_driver_start_ring().
>> > * Returns 0 for success.
>> > */
>> > -int amdgpu_fence_driver_init(struct amdgpu_device *adev)
>> > +int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev)
>> > {
>> > return 0;
>> > }
>> >
>> > /**
>> > - * 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
>> > @@ -531,8 +531,7 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
>> >
>> > if (!ring || !ring->fence_drv.initialized)
>> > continue;
>> > - if (!ring->no_scheduler)
>> > - 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);
>>
>>
>> Sorry for late notice, missed this patch. By moving drm_sched_fini
>> past amdgpu_fence_wait_empty a race is created as even after you waited
>> for all fences on the ring to signal the sw scheduler will keep submitting
>> new jobs on the ring and so the ring won't stay empty.
>>
>> For hot device removal also we want to prevent any access to HW past PCI
>> removal
>> in order to not do any MMIO accesses inside the physical MMIO range that
>> no longer
>> belongs to this device after it's removal by the PCI core. Stopping all
>> the schedulers prevents any MMIO
>> accesses done during job submissions and that why drm_sched_fini was
>> done as part of amdgpu_fence_driver_hw_fini
>> and not amdgpu_fence_driver_sw_fini
>>
>> Andrey
>>
>> > @@ -560,6 +559,9 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
>> > if (!ring || !ring->fence_drv.initialized)
>> > continue;
>> >
>> > + if (!ring->no_scheduler)
>> > + drm_sched_fini(&ring->sched);
>> > +
>> > for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
>> > dma_fence_put(ring->fence_drv.fences[j]);
>> > kfree(ring->fence_drv.fences);
>> > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
>> > index 27adffa7658d..9c11ced4312c 100644
>> > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
>> > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
>> > @@ -106,7 +106,6 @@ struct amdgpu_fence_driver {
>> > struct dma_fence **fences;
>> > };
>> >
>> > -int amdgpu_fence_driver_init(struct amdgpu_device *adev);
>> > void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
>> >
>> > int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
>> > @@ -115,9 +114,10 @@ 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_init(struct amdgpu_device *adev);
>> > void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev);
>> > +int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev);
>> > 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,
>> > unsigned flags);
>> > int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,
