1 files changed, 38 insertions, 22 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 4303b447efe8..0b109aebfec6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -55,8 +55,21 @@ struct amdgpu_fence {
 };
 
 static struct kmem_cache *amdgpu_fence_slab;
-static atomic_t amdgpu_fence_slab_ref = ATOMIC_INIT(0);
 
+int amdgpu_fence_slab_init(void)
+{
+	amdgpu_fence_slab = kmem_cache_create(
+		"amdgpu_fence", sizeof(struct amdgpu_fence), 0,
+		SLAB_HWCACHE_ALIGN, NULL);
+	if (!amdgpu_fence_slab)
+		return -ENOMEM;
+	return 0;
+}
+
+void amdgpu_fence_slab_fini(void)
+{
+	kmem_cache_destroy(amdgpu_fence_slab);
+}
 /*
  * Cast helper
  */
@@ -121,7 +134,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct fence **f)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_fence *fence;
-	struct fence **ptr;
+	struct fence *old, **ptr;
 	uint32_t seq;
 
 	fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL);
@@ -141,7 +154,11 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct fence **f)
 	/* This function can't be called concurrently anyway, otherwise
 	 * emitting the fence would mess up the hardware ring buffer.
 	 */
-	BUG_ON(rcu_dereference_protected(*ptr, 1));
+	old = rcu_dereference_protected(*ptr, 1);
+	if (old && !fence_is_signaled(old)) {
+		DRM_INFO("rcu slot is busy\n");
+		fence_wait(old, false);
+	}
 
 	rcu_assign_pointer(*ptr, fence_get(&fence->base));
 
@@ -187,16 +204,25 @@ void amdgpu_fence_process(struct amdgpu_ring *ring)
 	if (seq != ring->fence_drv.sync_seq)
 		amdgpu_fence_schedule_fallback(ring);
 
-	while (last_seq != seq) {
+	if (unlikely(seq == last_seq))
+		return;
+
+	last_seq &= drv->num_fences_mask;
+	seq &= drv->num_fences_mask;
+
+	do {
 		struct fence *fence, **ptr;
 
-		ptr = &drv->fences[++last_seq & drv->num_fences_mask];
+		++last_seq;
+		last_seq &= drv->num_fences_mask;
+		ptr = &drv->fences[last_seq];
 
 		/* There is always exactly one thread signaling this fence slot */
 		fence = rcu_dereference_protected(*ptr, 1);
-		rcu_assign_pointer(*ptr, NULL);
+		RCU_INIT_POINTER(*ptr, NULL);
 
-		BUG_ON(!fence);
+		if (!fence)
+			continue;
 
 		r = fence_signal(fence);
 		if (!r)
@@ -205,7 +231,7 @@ void amdgpu_fence_process(struct amdgpu_ring *ring)
 			BUG();
 
 		fence_put(fence);
-	}
+	} while (last_seq != seq);
 }
 
 /**
@@ -348,9 +374,9 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 	setup_timer(&ring->fence_drv.fallback_timer, amdgpu_fence_fallback,
 		    (unsigned long)ring);
 
-	ring->fence_drv.num_fences_mask = num_hw_submission - 1;
+	ring->fence_drv.num_fences_mask = num_hw_submission * 2 - 1;
 	spin_lock_init(&ring->fence_drv.lock);
-	ring->fence_drv.fences = kcalloc(num_hw_submission, sizeof(void *),
+	ring->fence_drv.fences = kcalloc(num_hw_submission * 2, sizeof(void *),
 					 GFP_KERNEL);
 	if (!ring->fence_drv.fences)
 		return -ENOMEM;
@@ -392,13 +418,6 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
  */
 int amdgpu_fence_driver_init(struct amdgpu_device *adev)
 {
-	if (atomic_inc_return(&amdgpu_fence_slab_ref) == 1) {
-		amdgpu_fence_slab = kmem_cache_create(
-			"amdgpu_fence", sizeof(struct amdgpu_fence), 0,
-			SLAB_HWCACHE_ALIGN, NULL);
-		if (!amdgpu_fence_slab)
-			return -ENOMEM;
-	}
 	if (amdgpu_debugfs_fence_init(adev))
 		dev_err(adev->dev, "fence debugfs file creation failed\n");
 
@@ -433,13 +452,10 @@ void amdgpu_fence_driver_fini(struct amdgpu_device *adev)
 		amd_sched_fini(&ring->sched);
 		del_timer_sync(&ring->fence_drv.fallback_timer);
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)
-			fence_put(ring->fence_drv.fences[i]);
+			fence_put(ring->fence_drv.fences[j]);
 		kfree(ring->fence_drv.fences);
 		ring->fence_drv.initialized = false;
 	}
-
-	if (atomic_dec_and_test(&amdgpu_fence_slab_ref))
-		kmem_cache_destroy(amdgpu_fence_slab);
 }
 
 /**
@@ -635,7 +651,7 @@ static int amdgpu_debugfs_gpu_reset(struct seq_file *m, void *data)
 	return 0;
 }
 
-static struct drm_info_list amdgpu_debugfs_fence_list[] = {
+static const struct drm_info_list amdgpu_debugfs_fence_list[] = {
 	{"amdgpu_fence_info", &amdgpu_debugfs_fence_info, 0, NULL},
 	{"amdgpu_gpu_reset", &amdgpu_debugfs_gpu_reset, 0, NULL}
 };