[PATCH 5.10.y] drm/amdgpu: finish GPU recovery callbacks before restarting schedulers

[Sasha Levin <sashal@kernel.org>]

From: Prike Liang <Prike.Liang@amd.com>

[ Upstream commit 733389cb31e2c55e355410759fdc68afe74a4582 ]

Run GPU post-reset callbacks, including KFD and display-audio resume,
before restarting DRM scheduler workqueues. IP hardware initialization
already happens inside ASIC recovery; this change orders the remaining
callbacks before new scheduler submissions. Preserve the emergency-stop
and guity job completition path's callbacks without starting schedulers,

Signed-off-by: Prike Liang <Prike.Liang@amd.com>
Acked-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1f6433e2b264e75c56ae95f187788806201bdbc3)
Cc: stable@vger.kernel.org
[ sashal: adapted recovery helper reordering to inline callback code in amdgpu_device_gpu_recover() ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 873346c377787..ea0fd088c97f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4646,7 +4646,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	}
 
 	if (need_emergency_restart)
-		goto skip_sched_resume;
+		goto post_resume;
 
 	/*
 	 * Must check guilty signal here since after this point all old
@@ -4658,7 +4658,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	    dma_fence_is_signaled(job->base.s_fence->parent)) {
 		job_signaled = true;
 		dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
-		goto skip_hw_reset;
+		goto post_resume;
 	}
 
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
@@ -4686,7 +4686,17 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			goto retry;
 	}
 
-skip_hw_reset:
+post_resume:
+	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
+		/* unlock kfd: SRIOV would do it separately */
+		if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
+			amdgpu_amdkfd_post_reset(tmp_adev);
+		if (audio_suspended)
+			amdgpu_device_resume_display_audio(tmp_adev);
+	}
+
+	if (need_emergency_restart)
+		goto skip_sched_resume;
 
 	/* Post ASIC reset for all devs .*/
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
@@ -4721,11 +4731,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 skip_sched_resume:
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
-		/*unlock kfd: SRIOV would do it separately */
-		if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
-	                amdgpu_amdkfd_post_reset(tmp_adev);
-		if (audio_suspended)
-			amdgpu_device_resume_display_audio(tmp_adev);
 		amdgpu_device_unlock_adev(tmp_adev);
 	}
 
-- 
2.53.0