[PATCH 25/28] drm/amdgpu/vcn: add a helper framework for engine resets

[Alex Deucher]

With engine resets we reset all queues on the engine rather
than just a single queue.  Add a framework to handle this
similar to SDMA.

Reviewed-by: Sathishkumar S <sathishkumar.sundararaju at amd.com>
Tested-by: Sathishkumar S <sathishkumar.sundararaju at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 76 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h |  6 +-
 2 files changed, 81 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index c8885c3d54b33..f1f67521c29ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -134,6 +134,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i)
 
 	mutex_init(&adev->vcn.inst[i].vcn1_jpeg1_workaround);
 	mutex_init(&adev->vcn.inst[i].vcn_pg_lock);
+	mutex_init(&adev->vcn.inst[i].engine_reset_mutex);
 	atomic_set(&adev->vcn.inst[i].total_submission_cnt, 0);
 	INIT_DELAYED_WORK(&adev->vcn.inst[i].idle_work, amdgpu_vcn_idle_work_handler);
 	atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
@@ -1451,3 +1452,78 @@ int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block,
 
 	return ret;
 }
+
+/**
+ * amdgpu_vcn_reset_engine - Reset a specific VCN engine
+ * @adev: Pointer to the AMDGPU device
+ * @instance_id: VCN engine instance to reset
+ *
+ * Returns: 0 on success, or a negative error code on failure.
+ */
+static int amdgpu_vcn_reset_engine(struct amdgpu_device *adev,
+				   uint32_t instance_id)
+{
+	struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[instance_id];
+	int r, i;
+
+	mutex_lock(&vinst->engine_reset_mutex);
+	/* Stop the scheduler's work queue for the dec and enc rings if they are running.
+	 * This ensures that no new tasks are submitted to the queues while
+	 * the reset is in progress.
+	 */
+	drm_sched_wqueue_stop(&vinst->ring_dec.sched);
+	for (i = 0; i < vinst->num_enc_rings; i++)
+		drm_sched_wqueue_stop(&vinst->ring_enc[i].sched);
+
+	/* Perform the VCN reset for the specified instance */
+	r = vinst->reset(vinst);
+	if (r)
+		goto unlock;
+	r = amdgpu_ring_test_ring(&vinst->ring_dec);
+	if (r)
+		goto unlock;
+	for (i = 0; i < vinst->num_enc_rings; i++) {
+		r = amdgpu_ring_test_ring(&vinst->ring_enc[i]);
+		if (r)
+			goto unlock;
+	}
+	amdgpu_fence_driver_force_completion(&vinst->ring_dec);
+	for (i = 0; i < vinst->num_enc_rings; i++)
+		amdgpu_fence_driver_force_completion(&vinst->ring_enc[i]);
+
+	/* Restart the scheduler's work queue for the dec and enc rings
+	 * if they were stopped by this function. This allows new tasks
+	 * to be submitted to the queues after the reset is complete.
+	 */
+	drm_sched_wqueue_start(&vinst->ring_dec.sched);
+	for (i = 0; i < vinst->num_enc_rings; i++)
+		drm_sched_wqueue_start(&vinst->ring_enc[i].sched);
+
+unlock:
+	mutex_unlock(&vinst->engine_reset_mutex);
+
+	return r;
+}
+
+/**
+ * amdgpu_vcn_ring_reset - Reset a VCN ring
+ * @ring: ring to reset
+ * @vmid: vmid of guilty job
+ * @timedout_fence: fence of timed out job
+ *
+ * This helper is for VCN blocks without unified queues because
+ * resetting the engine resets all queues in that case.  With
+ * unified queues we have one queue per engine.
+ * Returns: 0 on success, or a negative error code on failure.
+ */
+int amdgpu_vcn_ring_reset(struct amdgpu_ring *ring,
+			  unsigned int vmid,
+			  struct amdgpu_fence *timedout_fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (adev->vcn.inst[ring->me].using_unified_queue)
+		return -EINVAL;
+
+	return amdgpu_vcn_reset_engine(adev, ring->me);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 83adf81defc71..0bc0a94d7cf0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -330,7 +330,9 @@ struct amdgpu_vcn_inst {
 			      struct dpg_pause_state *new_state);
 	int (*set_pg_state)(struct amdgpu_vcn_inst *vinst,
 			    enum amd_powergating_state state);
+	int (*reset)(struct amdgpu_vcn_inst *vinst);
 	bool using_unified_queue;
+	struct mutex		engine_reset_mutex;
 };
 
 struct amdgpu_vcn_ras {
@@ -552,5 +554,7 @@ void amdgpu_debugfs_vcn_sched_mask_init(struct amdgpu_device *adev);
 
 int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block,
 			      enum amd_powergating_state state);
-
+int amdgpu_vcn_ring_reset(struct amdgpu_ring *ring,
+			  unsigned int vmid,
+			  struct amdgpu_fence *guilty_fence);
 #endif
-- 
2.50.0