[PATCH 6.6.y 2/3] drm/amdgpu: plumb timedout fence through to force completion

[Sasha Levin <sashal@kernel.org>]

From: Alex Deucher <alexander.deucher@amd.com>

[ Upstream commit c184df870db1e328691ea0fbb7d0e59efd9d3f9f ]

When we do a full adapter reset, if we know the timedout fence
mark the fence with -ETIME rather than -ECANCELED so it
gets properly handled by userspace.

v2: rebase

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Stable backport notes:
- Keep the two-argument force-completion API and its existing callers so
  6760f5cb12d2 can add the UVD fence-driver initialization check unchanged.
- Use &job->hw_fence.base for 6.6's embedded hardware fence. Preserve the
  existing scheduler reset and job-fence clearing flow used for resubmission.
- Drop SDMA, VCN and JPEG reset hunks whose functions do not exist here;
  vcn_v5_0_1.c is also absent. Do not import newer queue-reset helpers or
  their declarations. No functions are added by this backport.
- Restore the direct return after amdgpu_ring_undo() on VM-flush failure.
  The earlier ccea36c819df backport introduced a goto free_fence without
  the label or the newer fence-allocation model it depends on. In 6.6,
  amdgpu_ib_schedule() has no locally allocated fence to free on this
  path. This restores the original 6.6 error handling and fixes the
  build without importing the unrelated fence-lifetime conversion.

[ sashal: Reduced backport -- upstream c184df870db1e touches 9 file(s), this
  backport carries 6. Not backported here:
  drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
  drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
  drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
  drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
  This note is generated from the file lists only; see the resolution record
  for the reasoning. ]

Stable-dep-of: 6760f5cb12d2 ("drm/amdgpu: avoid force-completing uninitialized UVD rings")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |  6 ++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c   | 25 ++++++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c      |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h    |  3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c     |  2 +-
 6 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 256cc15fc9b5a..2044f5cca3514 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1947,7 +1947,7 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
 		/* swap out the old fences */
 		amdgpu_ib_preempt_fences_swap(ring, fences);
 
-		amdgpu_fence_driver_force_completion(ring);
+		amdgpu_fence_driver_force_completion(ring, NULL);
 
 		/* resubmit unfinished jobs */
 		amdgpu_ib_preempt_job_recovery(&ring->sched);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 892a40c439637..60e1d9cda3a8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4894,6 +4894,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 {
 	int i, r = 0;
 	struct amdgpu_job *job = NULL;
+	struct dma_fence *fence = NULL;
 	bool need_full_reset =
 		test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
 
@@ -4907,6 +4908,9 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 
 	amdgpu_fence_driver_isr_toggle(adev, true);
 
+	if (job)
+		fence = &job->hw_fence.base;
+
 	/* block all schedulers and reset given job's ring */
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -4920,7 +4924,7 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 		amdgpu_fence_driver_clear_job_fences(ring);
 
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
-		amdgpu_fence_driver_force_completion(ring);
+		amdgpu_fence_driver_force_completion(ring, fence);
 	}
 
 	amdgpu_fence_driver_isr_toggle(adev, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 017dd494d0a2f..93208bd5631af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -595,7 +595,7 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 			r = -ENODEV;
 		/* no need to trigger GPU reset as we are unloading */
 		if (r)
-			amdgpu_fence_driver_force_completion(ring);
+			amdgpu_fence_driver_force_completion(ring, NULL);
 
 		if (!drm_dev_is_unplugged(adev_to_drm(adev)) &&
 		    ring->fence_drv.irq_src &&
@@ -740,11 +740,30 @@ void amdgpu_fence_driver_set_error(struct amdgpu_ring *ring, int error)
  * amdgpu_fence_driver_force_completion - force signal latest fence of ring
  *
  * @ring: fence of the ring to signal
+ * @timedout_fence: fence of the timedout job
  *
  */
-void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring)
+void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring,
+					  struct dma_fence *timedout_fence)
 {
-	amdgpu_fence_driver_set_error(ring, -ECANCELED);
+	struct amdgpu_fence_driver *drv = &ring->fence_drv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&drv->lock, flags);
+	for (unsigned int i = 0; i <= drv->num_fences_mask; ++i) {
+		struct dma_fence *fence;
+
+		fence = rcu_dereference_protected(drv->fences[i],
+						  lockdep_is_held(&drv->lock));
+		if (fence && !dma_fence_is_signaled_locked(fence)) {
+			if (fence == timedout_fence)
+				dma_fence_set_error(fence, -ETIME);
+			else
+				dma_fence_set_error(fence, -ECANCELED);
+		}
+	}
+	spin_unlock_irqrestore(&drv->lock, flags);
+
 	amdgpu_fence_write(ring, ring->fence_drv.sync_seq);
 	amdgpu_fence_process(ring);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 2cce0a378ecb3..806ec5d021995 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -217,7 +217,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
 		r = amdgpu_vm_flush(ring, job, need_pipe_sync);
 		if (r) {
 			amdgpu_ring_undo(ring);
-			goto free_fence;
+			return r;
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index dc17e2ce84d07..b40dbe2f4fc25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -143,7 +143,8 @@ extern const struct drm_sched_backend_ops amdgpu_sched_ops;
 
 void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
 void amdgpu_fence_driver_set_error(struct amdgpu_ring *ring, int error);
-void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
+void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring,
+					  struct dma_fence *timedout_fence);
 
 int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring);
 int amdgpu_fence_driver_start_ring(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index aab293ec3417e..b6047dea0a1c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -511,7 +511,7 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 			}
 			memset_io(ptr, 0, size);
 			/* to restore uvd fence seq */
-			amdgpu_fence_driver_force_completion(&adev->uvd.inst[i].ring);
+			amdgpu_fence_driver_force_completion(&adev->uvd.inst[i].ring, NULL);
 		}
 	}
 	return 0;
-- 
2.53.0