From: Lijo Lazar <lijo.la...@amd.com> Add a fallback mechanism to attempt pipe reset when KCQ reset fails to recover the ring. After performing the KCQ reset and queue remapping, test the ring functionality. If the ring test fails, initiate a pipe reset as an additional recovery step.
v2: fix the typo (Lijo) v3: try pipeline reset when kiq mapping fails (Lijo) Signed-off-by: Lijo Lazar <lijo.la...@amd.com> Signed-off-by: Jesse Zhang <jesse.zh...@amd.com> --- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 8ba66d4dfe86..77f9d5b9a556 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -3560,6 +3560,7 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring, struct amdgpu_device *adev = ring->adev; struct amdgpu_kiq *kiq = &adev->gfx.kiq[ring->xcc_id]; struct amdgpu_ring *kiq_ring = &kiq->ring; + int reset_mode = AMDGPU_RESET_TYPE_PER_QUEUE; unsigned long flags; int r; @@ -3597,6 +3598,7 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring, if (!(adev->gfx.compute_supported_reset & AMDGPU_RESET_TYPE_PER_PIPE)) return -EOPNOTSUPP; r = gfx_v9_4_3_reset_hw_pipe(ring); + reset_mode = AMDGPU_RESET_TYPE_PER_PIPE; dev_info(adev->dev, "ring: %s pipe reset :%s\n", ring->name, r ? "failed" : "successfully"); if (r) @@ -3619,10 +3621,20 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring, r = amdgpu_ring_test_ring(kiq_ring); spin_unlock_irqrestore(&kiq->ring_lock, flags); if (r) { + if (reset_mode == AMDGPU_RESET_TYPE_PER_QUEUE) + goto pipe_reset; + dev_err(adev->dev, "fail to remap queue\n"); return r; } + if (reset_mode == AMDGPU_RESET_TYPE_PER_QUEUE) { + r = amdgpu_ring_test_ring(ring); + if (r) + goto pipe_reset; + } + + return amdgpu_ring_reset_helper_end(ring, timedout_fence); } -- 2.49.0