On Thu, Jan 4, 2024 at 12:55 AM Ma Jun <Jun.Ma2@xxxxxxx> wrote:
>
> Fix the warning info below during mode1 reset.
> [ +0.000004] Call Trace:
> [ +0.000004] <TASK>
> [ +0.000006] ? show_regs+0x6e/0x80
> [ +0.000011] ? __flush_work.isra.0+0x2e8/0x390
> [ +0.000005] ? __warn+0x91/0x150
> [ +0.000009] ? __flush_work.isra.0+0x2e8/0x390
> [ +0.000006] ? report_bug+0x19d/0x1b0
> [ +0.000013] ? handle_bug+0x46/0x80
> [ +0.000012] ? exc_invalid_op+0x1d/0x80
> [ +0.000011] ? asm_exc_invalid_op+0x1f/0x30
> [ +0.000014] ? __flush_work.isra.0+0x2e8/0x390
> [ +0.000007] ? __flush_work.isra.0+0x208/0x390
> [ +0.000007] ? _prb_read_valid+0x216/0x290
> [ +0.000008] __cancel_work_timer+0x11d/0x1a0
> [ +0.000007] ? try_to_grab_pending+0xe8/0x190
> [ +0.000012] cancel_work_sync+0x14/0x20
> [ +0.000008] amddrm_sched_stop+0x3c/0x1d0 [amd_sched]
> [ +0.000032] amdgpu_device_gpu_recover+0x29a/0xe90 [amdgpu]
>
> This warning info was printed after applying the patch
> "drm/sched: Convert drm scheduler to use a work queue rather than kthread".
> The root cause is that amdgpu driver tries to use the uninitialized
> work_struct in the struct drm_gpu_scheduler
>
> Signed-off-by: Ma Jun <Jun.Ma2@xxxxxxx>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 16 +++++++++++++---
> drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 3 ++-
> 2 files changed, 15 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 4b1d5f42249f..7bac3019aa0a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -5575,6 +5575,16 @@ static inline void amdgpu_device_stop_pending_resets(struct amdgpu_device *adev)
>
> }
>
> +static bool amdgpu_is_ring_sched_ready(struct amdgpu_ring *ring)
I would either rename this amdgpu_device_is_ring_sched_ready() for
consistency, or move it to amdgpu_ring.c and rename it to
amdgpu_ring_sched_ready().
Alex
> +{
> + if (!ring)
> + return false;
> +
> + if (ring->no_scheduler || !drm_sched_wqueue_ready(&ring->sched))
> + return false;
> +
> + return true;
> +}
> /**
> * amdgpu_device_gpu_recover - reset the asic and recover scheduler
> *
> @@ -5700,7 +5710,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = tmp_adev->rings[i];
>
> - if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> + if (!amdgpu_is_ring_sched_ready(ring))
> continue;
>
> drm_sched_stop(&ring->sched, job ? &job->base : NULL);
> @@ -5776,7 +5786,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = tmp_adev->rings[i];
>
> - if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> + if (!amdgpu_is_ring_sched_ready(ring))
> continue;
>
> drm_sched_start(&ring->sched, true);
> @@ -6265,7 +6275,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
> for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> struct amdgpu_ring *ring = adev->rings[i];
>
> - if (!ring || !drm_sched_wqueue_ready(&ring->sched))
> + if (!amdgpu_is_ring_sched_ready(ring))
> continue;
>
> drm_sched_start(&ring->sched, true);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> index 41266bc99345..3650e4d06e53 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> @@ -636,7 +636,8 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
> DRM_DEV_DEBUG(adev->dev, "ring test on %s succeeded\n",
> ring->name);
>
> - ring->sched.ready = !r;
> + if (!ring->no_scheduler)
> + ring->sched.ready = !r;
> return r;
> }
>
> --
> 2.34.1
>
