19 files changed, 55 insertions, 21 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 3b7d3844a74b..f0b7080dccb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -135,17 +135,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	} else if (amdgpu_gpu_recovery && ring->funcs->reset) {
 		dev_err(adev->dev, "Starting %s ring reset\n",
 			s_job->sched->name);
-
-		/*
-		 * Stop the scheduler to prevent anybody else from touching the
-		 * ring buffer.
-		 */
-		drm_sched_wqueue_stop(&ring->sched);
-
 		r = amdgpu_ring_reset(ring, job->vmid, NULL);
 		if (!r) {
 			atomic_inc(&ring->adev->gpu_reset_counter);
-			drm_sched_wqueue_start(&ring->sched);
 			dev_err(adev->dev, "Ring %s reset succeeded\n",
 				ring->sched.name);
 			drm_dev_wedged_event(adev_to_drm(adev),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index cf5733d5d26d..7e26a44dcc1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -554,22 +554,16 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
 	struct amdgpu_ring *gfx_ring = &sdma_instance->ring;
 	struct amdgpu_ring *page_ring = &sdma_instance->page;
-	bool gfx_sched_stopped = false, page_sched_stopped = false;
 
 	mutex_lock(&sdma_instance->engine_reset_mutex);
 	/* Stop the scheduler's work queue for the GFX and page rings if they are running.
 	* This ensures that no new tasks are submitted to the queues while
 	* the reset is in progress.
 	*/
-	if (!amdgpu_ring_sched_ready(gfx_ring)) {
-		drm_sched_wqueue_stop(&gfx_ring->sched);
-		gfx_sched_stopped = true;
-	}
+	drm_sched_wqueue_stop(&gfx_ring->sched);
 
-	if (adev->sdma.has_page_queue && !amdgpu_ring_sched_ready(page_ring)) {
+	if (adev->sdma.has_page_queue)
 		drm_sched_wqueue_stop(&page_ring->sched);
-		page_sched_stopped = true;
-	}
 
 	if (sdma_instance->funcs->stop_kernel_queue) {
 		sdma_instance->funcs->stop_kernel_queue(gfx_ring);
@@ -596,12 +590,9 @@ exit:
 	 * to be submitted to the queues after the reset is complete.
 	 */
 	if (!ret) {
-		if (gfx_sched_stopped && amdgpu_ring_sched_ready(gfx_ring)) {
-			drm_sched_wqueue_start(&gfx_ring->sched);
-		}
-		if (page_sched_stopped && amdgpu_ring_sched_ready(page_ring)) {
+		drm_sched_wqueue_start(&gfx_ring->sched);
+		if (adev->sdma.has_page_queue)
 			drm_sched_wqueue_start(&page_ring->sched);
-		}
 	}
 	mutex_unlock(&sdma_instance->engine_reset_mutex);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 4d0ee3ffe985..8c377ecbb8a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -9540,6 +9540,8 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring,
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 
 	if (amdgpu_ring_alloc(kiq_ring, 5 + 7 + 7 + kiq->pmf->map_queues_size)) {
@@ -9581,6 +9583,7 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
@@ -9600,6 +9603,8 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 
 	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
@@ -9658,6 +9663,7 @@ static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 39f4dd18c277..37dcec2d0784 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -6821,6 +6821,8 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false);
 	if (r) {
 
@@ -6846,6 +6848,7 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
@@ -6989,6 +6992,8 @@ static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, true);
 	if (r) {
 		dev_warn(adev->dev, "fail(%d) to reset kcq and try pipe reset\n", r);
@@ -7012,6 +7017,7 @@ static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 964fa3f2e271..e4fc42470cf3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -5317,6 +5317,8 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false);
 	if (r) {
 		dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r);
@@ -5341,6 +5343,7 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
@@ -5437,6 +5440,8 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, true);
 	if (r) {
 		dev_warn(adev->dev, "fail(%d) to reset kcq  and try pipe reset\n", r);
@@ -5460,6 +5465,7 @@ static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 95e319974f22..76ba664efecb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -7187,6 +7187,8 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 
 	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
@@ -7247,6 +7249,7 @@ static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
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 8bfee17a826e..daed0f187bda 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -3567,6 +3567,8 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	spin_lock_irqsave(&kiq->ring_lock, flags);
 
 	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
@@ -3625,6 +3627,7 @@ pipe_reset:
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
index 6621a7b1f29f..781a5a8a8361 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -770,12 +770,14 @@ static int jpeg_v2_0_ring_reset(struct amdgpu_ring *ring,
 {
 	int r;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	jpeg_v2_0_stop(ring->adev);
 	jpeg_v2_0_start(ring->adev);
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
index 44a5c0e82ca4..5be9cdcae32c 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -649,12 +649,14 @@ static int jpeg_v2_5_ring_reset(struct amdgpu_ring *ring,
 {
 	int r;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	jpeg_v2_5_stop_inst(ring->adev, ring->me);
 	jpeg_v2_5_start_inst(ring->adev, ring->me);
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
index e813af4eedd2..a24bd833d644 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -561,12 +561,14 @@ static int jpeg_v3_0_ring_reset(struct amdgpu_ring *ring,
 {
 	int r;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	jpeg_v3_0_stop(ring->adev);
 	jpeg_v3_0_start(ring->adev);
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index 190f0742d701..1d4edd77837d 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -729,12 +729,14 @@ static int jpeg_v4_0_ring_reset(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EINVAL;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	jpeg_v4_0_stop(ring->adev);
 	jpeg_v4_0_start(ring->adev);
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 04755b7a62d9..78441f8fce97 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -1152,12 +1152,14 @@ static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EOPNOTSUPP;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	jpeg_v4_0_3_core_stall_reset(ring);
 	jpeg_v4_0_3_start_jrbc(ring);
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index e7f942dc714a..6f8a16da9d60 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -843,12 +843,14 @@ static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring,
 	if (amdgpu_sriov_vf(ring->adev))
 		return -EOPNOTSUPP;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	jpeg_v5_0_1_core_stall_reset(ring);
 	jpeg_v5_0_1_init_jrbc(ring);
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index c6cb7ff15caa..cac0882770fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1570,6 +1570,8 @@ static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring,
 		return -EINVAL;
 	}
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	r = amdgpu_mes_reset_legacy_queue(adev, ring, vmid, true);
 	if (r)
 		return r;
@@ -1578,6 +1580,7 @@ static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index b00c63812899..99a080bad2a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -822,6 +822,8 @@ static int sdma_v7_0_reset_queue(struct amdgpu_ring *ring,
 		return -EINVAL;
 	}
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	r = amdgpu_mes_reset_legacy_queue(adev, ring, vmid, true);
 	if (r)
 		return r;
@@ -830,6 +832,7 @@ static int sdma_v7_0_reset_queue(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 6c25e9fc4f0f..eec9133e1b2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1978,6 +1978,7 @@ static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring,
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	vcn_v4_0_stop(vinst);
 	vcn_v4_0_start(vinst);
 
@@ -1985,6 +1986,7 @@ static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 1e1dd61b774e..d8fd32c1e38e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -1609,6 +1609,8 @@ static int vcn_v4_0_3_ring_reset(struct amdgpu_ring *ring,
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
 
+	drm_sched_wqueue_stop(&ring->sched);
+
 	vcn_inst = GET_INST(VCN, ring->me);
 	r = amdgpu_dpm_reset_vcn(adev, 1 << vcn_inst);
 
@@ -1626,6 +1628,7 @@ static int vcn_v4_0_3_ring_reset(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 9c02446bb1a5..7e37ddea6355 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -1476,6 +1476,7 @@ static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring,
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	vcn_v4_0_5_stop(vinst);
 	vcn_v4_0_5_start(vinst);
 
@@ -1483,6 +1484,7 @@ static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index c8924f97cf58..47c0bcc9e7d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -1203,6 +1203,7 @@ static int vcn_v5_0_0_ring_reset(struct amdgpu_ring *ring,
 	if (!(adev->vcn.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
 		return -EOPNOTSUPP;
 
+	drm_sched_wqueue_stop(&ring->sched);
 	vcn_v5_0_0_stop(vinst);
 	vcn_v5_0_0_start(vinst);
 
@@ -1210,6 +1211,7 @@ static int vcn_v5_0_0_ring_reset(struct amdgpu_ring *ring,
 	if (r)
 		return r;
 	amdgpu_fence_driver_force_completion(ring);
+	drm_sched_wqueue_start(&ring->sched);
 	return 0;
 }