Merge tag 'amd-drm-next-6.19-2025-10-24' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.19-2025-10-24:

amdgpu:
- HMM cleanup
- Add new RAS framework
- DML2.1 updates
- YCbCr420 fixes
- DC FP fixes
- DMUB fixes
- LTTPR fixes
- DTBCLK fixes
- DMU cursor offload handling
- Userq validation improvements
- Misc code cleanups
- Unify shutdown callback handling
- Suspend improvements
- Power limit code cleanup
- Fence cleanup
- IP Discovery cleanup
- SR-IOV fixes
- AUX backlight fixes
- DCN 3.5 fixes
- HDMI compliance fixes
- DCN 4.0.1 cursor updates
- DCN interrupt fix
- DC KMS full update improvements
- Add additional HDCP traces
- DCN 3.2 fixes
- DP MST fixes
- Add support for new SR-IOV mailbox interface

Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20251024175249.58099-1-alexander.deucher@amd.com

1 files changed, 30 insertions, 13 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index d020a890a0ea..e08d837668f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -137,7 +137,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 		   ring->funcs->reset) {
 		dev_err(adev->dev, "Starting %s ring reset\n",
 			s_job->sched->name);
-		r = amdgpu_ring_reset(ring, job->vmid, &job->hw_fence);
+		r = amdgpu_ring_reset(ring, job->vmid, job->hw_fence);
 		if (!r) {
 			atomic_inc(&ring->adev->gpu_reset_counter);
 			dev_err(adev->dev, "Ring %s reset succeeded\n",
@@ -186,6 +186,9 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		     unsigned int num_ibs, struct amdgpu_job **job,
 		     u64 drm_client_id)
 {
+	struct amdgpu_fence *af;
+	int r;
+
 	if (num_ibs == 0)
 		return -EINVAL;
 
@@ -193,6 +196,20 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (!*job)
 		return -ENOMEM;
 
+	af = kzalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	if (!af) {
+		r = -ENOMEM;
+		goto err_job;
+	}
+	(*job)->hw_fence = af;
+
+	af = kzalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	if (!af) {
+		r = -ENOMEM;
+		goto err_fence;
+	}
+	(*job)->hw_vm_fence = af;
+
 	(*job)->vm = vm;
 
 	amdgpu_sync_create(&(*job)->explicit_sync);
@@ -204,6 +221,13 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 	return drm_sched_job_init(&(*job)->base, entity, 1, owner,
 				  drm_client_id);
+
+err_fence:
+	kfree((*job)->hw_fence);
+err_job:
+	kfree(*job);
+
+	return r;
 }
 
 int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev,
@@ -251,11 +275,11 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	struct dma_fence *f;
 	unsigned i;
 
-	/* Check if any fences where initialized */
+	/* Check if any fences were initialized */
 	if (job->base.s_fence && job->base.s_fence->finished.ops)
 		f = &job->base.s_fence->finished;
-	else if (job->hw_fence.base.ops)
-		f = &job->hw_fence.base;
+	else if (job->hw_fence && job->hw_fence->base.ops)
+		f = &job->hw_fence->base;
 	else
 		f = NULL;
 
@@ -271,11 +295,7 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 
 	amdgpu_sync_free(&job->explicit_sync);
 
-	/* only put the hw fence if has embedded fence */
-	if (!job->hw_fence.base.ops)
-		kfree(job);
-	else
-		dma_fence_put(&job->hw_fence.base);
+	kfree(job);
 }
 
 void amdgpu_job_set_gang_leader(struct amdgpu_job *job,
@@ -304,10 +324,7 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	if (job->gang_submit != &job->base.s_fence->scheduled)
 		dma_fence_put(job->gang_submit);
 
-	if (!job->hw_fence.base.ops)
-		kfree(job);
-	else
-		dma_fence_put(&job->hw_fence.base);
+	kfree(job);
 }
 
 struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job)