FAILED: patch "[PATCH] drm/amdgpu: finish GPU recovery callbacks before restarting schedulers" failed to apply to 6.6-stable tree

FAILED: patch "[PATCH] drm/amdgpu: finish GPU recovery callbacks before restarting schedulers" failed to apply to 6.6-stable tree

[Sasha Levin]

The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 733389cb31e2c55e355410759fdc68afe74a4582
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '20261109201417-failed-6.6-733389cb31e2@kernel.org' --subject-prefix 'PATCH 6.6.y' 'HEAD^..'

Thanks,
Sasha

------------------ original commit in Linus's tree ------------------

From 733389cb31e2c55e355410759fdc68afe74a4582 Mon Sep 17 00:00:00 2001
From: Prike Liang <Prike.Liang@amd.com>
Date: Thu, 20 Aug 2026 15:27:56 +0800
Subject: [PATCH] drm/amdgpu: finish GPU recovery callbacks before restarting
 schedulers

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
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 53f05ee7193f2..5bec9cd3f7d39 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5859,8 +5859,10 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 	amdgpu_device_halt_activities(adev, job, reset_context, &device_list,
 				      hive, need_emergency_restart);
-	if (need_emergency_restart)
-		goto skip_sched_resume;
+	if (need_emergency_restart) {
+		amdgpu_device_gpu_resume(adev, &device_list, need_emergency_restart);
+		goto reset_unlock;
+	}
 	/*
 	 * Must check guilty signal here since after this point all old
 	 * HW fences are force signaled.
@@ -5870,18 +5872,17 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	if (job && (dma_fence_get_status(&job->hw_fence->base) > 0)) {
 		job_signaled = true;
 		dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
-		goto skip_hw_reset;
+		goto post_resume;
 	}
 
 	r = amdgpu_device_asic_reset(adev, &device_list, reset_context);
 	if (r)
 		goto reset_unlock;
-skip_hw_reset:
+post_resume:
+	amdgpu_device_gpu_resume(adev, &device_list, need_emergency_restart);
 	r = amdgpu_device_sched_resume(&device_list, reset_context, job_signaled);
 	if (r)
 		goto reset_unlock;
-skip_sched_resume:
-	amdgpu_device_gpu_resume(adev, &device_list, need_emergency_restart);
 reset_unlock:
 	amdgpu_device_recovery_put_reset_lock(adev, &device_list);
 	amdgpu_ras_post_reset(adev, &device_list);
-- 
2.53.0

[PATCH 6.6.y] drm/amdgpu: finish GPU recovery callbacks before restarting schedulers

[Sasha Levin]

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 helper reordering to inline code in amdgpu_device_gpu_recover() because the upstream recovery helpers are absent. ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 47 +++++++++++-----------
 1 file changed, 24 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2cdbee6700ecd..41fac9d273622 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5511,7 +5511,7 @@ 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
@@ -5522,7 +5522,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	if (job && dma_fence_is_signaled(&job->hw_fence.base)) {
 		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. */
@@ -5567,7 +5567,28 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 			goto recover_end;
 	}
 
-skip_hw_reset:
+post_resume:
+	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
+		/* unlock kfd: SRIOV would do it separately */
+		if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
+			amdgpu_amdkfd_post_reset(tmp_adev);
+
+		/* kfd_post_reset will do nothing if kfd device is not initialized,
+		 * need to bring up kfd here if it's not be initialized before
+		 */
+		if (!adev->kfd.init_complete)
+			amdgpu_amdkfd_device_init(adev);
+
+		if (audio_suspended)
+			amdgpu_device_resume_display_audio(tmp_adev);
+
+		amdgpu_device_unset_mp1_state(tmp_adev);
+
+		amdgpu_ras_set_error_query_ready(tmp_adev, true);
+	}
+
+	if (need_emergency_restart)
+		goto recover_end;
 
 	/* Post ASIC reset for all devs .*/
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
@@ -5603,26 +5624,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		}
 	}
 
-skip_sched_resume:
-	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-		/* unlock kfd: SRIOV would do it separately */
-		if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev))
-			amdgpu_amdkfd_post_reset(tmp_adev);
-
-		/* kfd_post_reset will do nothing if kfd device is not initialized,
-		 * need to bring up kfd here if it's not be initialized before
-		 */
-		if (!adev->kfd.init_complete)
-			amdgpu_amdkfd_device_init(adev);
-
-		if (audio_suspended)
-			amdgpu_device_resume_display_audio(tmp_adev);
-
-		amdgpu_device_unset_mp1_state(tmp_adev);
-
-		amdgpu_ras_set_error_query_ready(tmp_adev, true);
-	}
-
 recover_end:
 	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
 					    reset_list);
-- 
2.53.0