drm/amdgpu: move force completion into ring resets

alexdeucher · alexdeucher · commit 2dee58ca471d · 2025-06-30T11:57:29.000-04:00
Move the force completion handling into each ring
reset function so that each engine can determine
whether or not it needs to force completion on the
jobs in the ring.

Reviewed-by: Christian König &lt;christian.koenig@amd.com&gt;
Signed-off-by: Alex Deucher &lt;alexander.deucher@amd.com&gt;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -161,10 +161,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 
 		r = amdgpu_ring_reset(ring, job->vmid, NULL);
 		if (!r) {
-			if (is_guilty) {
+			if (is_guilty)
 				atomic_inc(&ring->adev->gpu_reset_counter);
-				amdgpu_fence_driver_force_completion(ring);
-			}
 			drm_sched_wqueue_start(&ring->sched);
 			dev_err(adev->dev, "Ring %s reset succeeded\n",
 				ring->sched.name);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -9577,7 +9577,11 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring,
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
@@ -9650,7 +9654,11 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v10_ip_print(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -6842,7 +6842,11 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int gfx_v11_0_reset_compute_pipe(struct amdgpu_ring *ring)
@@ -7004,7 +7008,11 @@ static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring,
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v11_ip_print(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -5337,7 +5337,11 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int gfx_v12_0_reset_compute_pipe(struct amdgpu_ring *ring)
@@ -5452,7 +5456,11 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring,
 		return r;
 	}
 
-	return amdgpu_ring_test_ring(ring);
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v12_0_ring_begin_use(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -7242,7 +7242,12 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
 		DRM_ERROR("fail to remap queue\n");
 		return r;
 	}
-	return amdgpu_ring_test_ring(ring);
+
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static void gfx_v9_ip_print(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -3620,7 +3620,12 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 		dev_err(adev->dev, "fail to remap queue\n");
 		return r;
 	}
-	return amdgpu_ring_test_ring(ring);
+
+	r = amdgpu_ring_test_ring(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 enum amdgpu_gfx_cp_ras_mem_id {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -768,9 +768,15 @@ static int jpeg_v2_0_ring_reset(struct amdgpu_ring *ring,
 				unsigned int vmid,
 				struct amdgpu_fence *timedout_fence)
 {
+	int r;
+
 	jpeg_v2_0_stop(ring->adev);
 	jpeg_v2_0_start(ring->adev);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -647,9 +647,15 @@ static int jpeg_v2_5_ring_reset(struct amdgpu_ring *ring,
 				unsigned int vmid,
 				struct amdgpu_fence *timedout_fence)
 {
+	int r;
+
 	jpeg_v2_5_stop_inst(ring->adev, ring->me);
 	jpeg_v2_5_start_inst(ring->adev, ring->me);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v2_5_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -559,9 +559,15 @@ static int jpeg_v3_0_ring_reset(struct amdgpu_ring *ring,
 				unsigned int vmid,
 				struct amdgpu_fence *timedout_fence)
 {
+	int r;
+
 	jpeg_v3_0_stop(ring->adev);
 	jpeg_v3_0_start(ring->adev);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v3_0_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -724,12 +724,18 @@ static int jpeg_v4_0_ring_reset(struct amdgpu_ring *ring,
 				unsigned int vmid,
 				struct amdgpu_fence *timedout_fence)
 {
+	int r;
+
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EINVAL;
 
 	jpeg_v4_0_stop(ring->adev);
 	jpeg_v4_0_start(ring->adev);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v4_0_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -1147,12 +1147,18 @@ static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring,
 				  unsigned int vmid,
 				  struct amdgpu_fence *timedout_fence)
 {
+	int r;
+
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EOPNOTSUPP;
 
 	jpeg_v4_0_3_core_stall_reset(ring);
 	jpeg_v4_0_3_start_jrbc(ring);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v4_0_3_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -838,12 +838,18 @@ static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring,
 				  unsigned int vmid,
 				  struct amdgpu_fence *timedout_fence)
 {
+	int r;
+
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EOPNOTSUPP;
 
 	jpeg_v5_0_1_core_stall_reset(ring);
 	jpeg_v5_0_1_init_jrbc(ring);
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amd_ip_funcs jpeg_v5_0_1_ip_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -1679,6 +1679,7 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring,
 				   unsigned int vmid,
 				   struct amdgpu_fence *timedout_fence)
 {
+	bool is_guilty = ring->funcs->is_guilty(ring);
 	struct amdgpu_device *adev = ring->adev;
 	u32 id = ring->me;
 	int r;
@@ -1689,8 +1690,13 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring,
 	amdgpu_amdkfd_suspend(adev, true);
 	r = amdgpu_sdma_reset_engine(adev, id);
 	amdgpu_amdkfd_resume(adev, true);
+	if (r)
+		return r;
 
-	return r;
+	if (is_guilty)
+		amdgpu_fence_driver_force_completion(ring);
+
+	return 0;
 }
 
 static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring)
@@ -1734,8 +1740,8 @@ static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring)
 static int sdma_v4_4_2_restore_queue(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 inst_mask;
-	int i;
+	u32 inst_mask, tmp_mask;
+	int i, r;
 
 	inst_mask = 1 << ring->me;
 	udelay(50);
@@ -1752,7 +1758,24 @@ static int sdma_v4_4_2_restore_queue(struct amdgpu_ring *ring)
 		return -ETIMEDOUT;
 	}
 
-	return sdma_v4_4_2_inst_start(adev, inst_mask, true);
+	r = sdma_v4_4_2_inst_start(adev, inst_mask, true);
+	if (r)
+		return r;
+
+	tmp_mask = inst_mask;
+	for_each_inst(i, tmp_mask) {
+		ring = &adev->sdma.instance[i].ring;
+
+		amdgpu_fence_driver_force_completion(ring);
+
+		if (adev->sdma.has_page_queue) {
+			struct amdgpu_ring *page = &adev->sdma.instance[i].page;
+
+			amdgpu_fence_driver_force_completion(page);
+		}
+	}
+
+	return r;
 }
 
 static int sdma_v4_4_2_soft_reset_engine(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1618,7 +1618,10 @@ static int sdma_v5_0_restore_queue(struct amdgpu_ring *ring)
 
 	r = sdma_v5_0_gfx_resume_instance(adev, inst_id, true);
 	amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
-	return r;
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int sdma_v5_0_ring_preempt_ib(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1534,7 +1534,10 @@ static int sdma_v5_2_restore_queue(struct amdgpu_ring *ring)
 	r = sdma_v5_2_gfx_resume_instance(adev, inst_id, true);
 
 	amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
-	return r;
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int sdma_v5_2_ring_preempt_ib(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1574,7 +1574,11 @@ static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 
-	return sdma_v6_0_gfx_resume_instance(adev, i, true);
+	r = sdma_v6_0_gfx_resume_instance(adev, i, true);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static int sdma_v6_0_set_trap_irq_state(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -826,7 +826,11 @@ static int sdma_v7_0_reset_queue(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 
-	return sdma_v7_0_gfx_resume_instance(adev, i, true);
+	r = sdma_v7_0_gfx_resume_instance(adev, i, true);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1973,14 +1973,19 @@ static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring,
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];
+	int r;
 
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
 
 	vcn_v4_0_stop(vinst);
 	vcn_v4_0_start(vinst);
 
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static struct amdgpu_ring_funcs vcn_v4_0_unified_ring_vm_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -1623,8 +1623,10 @@ static int vcn_v4_0_3_ring_reset(struct amdgpu_ring *ring,
 	vcn_v4_0_3_hw_init_inst(vinst);
 	vcn_v4_0_3_start_dpg_mode(vinst, adev->vcn.inst[ring->me].indirect_sram);
 	r = amdgpu_ring_test_helper(ring);
-
-	return r;
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -1471,14 +1471,19 @@ static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring,
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];
+	int r;
 
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
 
 	vcn_v4_0_5_stop(vinst);
 	vcn_v4_0_5_start(vinst);
 
-	return amdgpu_ring_test_helper(ring);
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
+		return r;
+	amdgpu_fence_driver_force_completion(ring);
+	return 0;
 }
 
 static struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c

Original file line number	Diff line number	Diff line change
`@@ -6842,7 +6842,11 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,`
`6842`	`6842`	`return r;`
`6843`	`6843`	`}`
`6844`	`6844`
`6845`		`- return amdgpu_ring_test_ring(ring);`
	`6845`	`+ r = amdgpu_ring_test_ring(ring);`
	`6846`	`+ if (r)`
	`6847`	`+ return r;`
	`6848`	`+ amdgpu_fence_driver_force_completion(ring);`
	`6849`	`+ return 0;`
`6846`	`6850`	`}`
`6847`	`6851`
`6848`	`6852`	`static int gfx_v11_0_reset_compute_pipe(struct amdgpu_ring *ring)`
`@@ -7004,7 +7008,11 @@ static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring,`
`7004`	`7008`	`return r;`
`7005`	`7009`	`}`
`7006`	`7010`
`7007`		`- return amdgpu_ring_test_ring(ring);`
	`7011`	`+ r = amdgpu_ring_test_ring(ring);`
	`7012`	`+ if (r)`
	`7013`	`+ return r;`
	`7014`	`+ amdgpu_fence_driver_force_completion(ring);`
	`7015`	`+ return 0;`
`7008`	`7016`	`}`
`7009`	`7017`
`7010`	`7018`	`static void gfx_v11_ip_print(struct amdgpu_ip_block ip_block, struct drm_printer p)`
Original file line number	Diff line number	Diff line change
`@@ -5337,7 +5337,11 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,`
`5337`	`5337`	`return r;`
`5338`	`5338`	`}`
`5339`	`5339`
`5340`		`- return amdgpu_ring_test_ring(ring);`
	`5340`	`+ r = amdgpu_ring_test_ring(ring);`
	`5341`	`+ if (r)`
	`5342`	`+ return r;`
	`5343`	`+ amdgpu_fence_driver_force_completion(ring);`
	`5344`	`+ return 0;`
`5341`	`5345`	`}`
`5342`	`5346`
`5343`	`5347`	`static int gfx_v12_0_reset_compute_pipe(struct amdgpu_ring *ring)`
`@@ -5452,7 +5456,11 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring,`
`5452`	`5456`	`return r;`
`5453`	`5457`	`}`
`5454`	`5458`
`5455`		`- return amdgpu_ring_test_ring(ring);`
	`5459`	`+ r = amdgpu_ring_test_ring(ring);`
	`5460`	`+ if (r)`
	`5461`	`+ return r;`
	`5462`	`+ amdgpu_fence_driver_force_completion(ring);`
	`5463`	`+ return 0;`
`5456`	`5464`	`}`
`5457`	`5465`
`5458`	`5466`	`static void gfx_v12_0_ring_begin_use(struct amdgpu_ring *ring)`
Original file line number	Diff line number	Diff line change
`@@ -7242,7 +7242,12 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,`
`7242`	`7242`	`DRM_ERROR("fail to remap queue\n");`
`7243`	`7243`	`return r;`
`7244`	`7244`	`}`
`7245`		`- return amdgpu_ring_test_ring(ring);`
	`7245`	`+`
	`7246`	`+ r = amdgpu_ring_test_ring(ring);`
	`7247`	`+ if (r)`
	`7248`	`+ return r;`
	`7249`	`+ amdgpu_fence_driver_force_completion(ring);`
	`7250`	`+ return 0;`
`7246`	`7251`	`}`
`7247`	`7252`
`7248`	`7253`	`static void gfx_v9_ip_print(struct amdgpu_ip_block ip_block, struct drm_printer p)`
Original file line number	Diff line number	Diff line change
`@@ -3620,7 +3620,12 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,`
`3620`	`3620`	`dev_err(adev->dev, "fail to remap queue\n");`
`3621`	`3621`	`return r;`
`3622`	`3622`	`}`
`3623`		`- return amdgpu_ring_test_ring(ring);`
	`3623`	`+`
	`3624`	`+ r = amdgpu_ring_test_ring(ring);`
	`3625`	`+ if (r)`
	`3626`	`+ return r;`
	`3627`	`+ amdgpu_fence_driver_force_completion(ring);`
	`3628`	`+ return 0;`
`3624`	`3629`	`}`
`3625`	`3630`
`3626`	`3631`	`enum amdgpu_gfx_cp_ras_mem_id {`