[PATCH 03/21] drm/amdgpu: detect timeout error when deactivating hqd

[andresx7@xxxxxxxxx (Andres Rodriguez)]

Handle HQD deactivation timeouts instead of ignoring them.

Signed-off-by: Andres Rodriguez <andresx7 at gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 044449a..af4b505 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -4884,20 +4884,21 @@ static int gfx_v8_0_mqd_commit(struct amdgpu_device *adev, struct vi_mqd *mqd)
 	/* activate the queue */
 	WREG32(mmCP_HQD_ACTIVE, mqd->cp_hqd_active);
 
 	return 0;
 }
 
 static int gfx_v8_0_kiq_queue_init(struct amdgpu_ring *ring,
 				   struct vi_mqd *mqd,
 				   u64 mqd_gpu_addr)
 {
+	int r = 0;
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	uint64_t eop_gpu_addr;
 	bool is_kiq = false;
 
 	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
 		is_kiq = true;
 
 	if (is_kiq) {
 		eop_gpu_addr = kiq->eop_gpu_addr;
@@ -4905,34 +4906,45 @@ static int gfx_v8_0_kiq_queue_init(struct amdgpu_ring *ring,
 	} else
 		eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr +
 					ring->queue * GFX8_MEC_HPD_SIZE;
 
 	mutex_lock(&adev->srbm_mutex);
 	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
 	gfx_v8_0_mqd_init(adev, mqd, mqd_gpu_addr, eop_gpu_addr, ring);
 
 	if (is_kiq) {
-		gfx_v8_0_mqd_deactivate(adev);
+		r = gfx_v8_0_mqd_deactivate(adev);
+		if (r) {
+			dev_err(adev->dev, "failed to deactivate ring %s\n", ring->name);
+			goto out_unlock;
+		}
+
 		gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
 		gfx_v8_0_mqd_commit(adev, mqd);
 	}
 
 	vi_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
 
 	if (is_kiq)
 		gfx_v8_0_kiq_enable(ring);
 	else
 		gfx_v8_0_map_queue_enable(&kiq->ring, ring);
 
 	return 0;
+
+out_unlock:
+	vi_srbm_select(adev, 0, 0, 0, 0);
+	mutex_unlock(&adev->srbm_mutex);
+
+	return r;
 }
 
 static void gfx_v8_0_kiq_free_queue(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring = NULL;
 	int i;
 
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
 		amdgpu_bo_free_kernel(&ring->mqd_obj, NULL, NULL);
@@ -5052,24 +5064,30 @@ static int gfx_v8_0_compute_queue_init(struct amdgpu_device *adev,
 	eop_gpu_addr >>= 8;
 
 	/* init the mqd struct */
 	memset(mqd, 0, sizeof(struct vi_mqd));
 
 	mutex_lock(&adev->srbm_mutex);
 	vi_srbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
 
 	gfx_v8_0_mqd_init(adev, mqd, mqd_gpu_addr, eop_gpu_addr, ring);
 
-	gfx_v8_0_mqd_deactivate(adev);
+	r = gfx_v8_0_mqd_deactivate(adev);
+	if (r) {
+		dev_err(adev->dev, "failed to deactivate ring %s\n", ring->name);
+		goto out_unlock;
+	}
+
 	gfx_v8_0_enable_doorbell(adev, ring->use_doorbell);
 	gfx_v8_0_mqd_commit(adev, mqd);
 
+out_unlock:
 	vi_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
 
 	amdgpu_bo_kunmap(ring->mqd_obj);
 out_unreserve:
 	amdgpu_bo_unreserve(ring->mqd_obj);
 out:
 	return r;
 }
 
-- 
2.9.3