drm/radeon: replace the per ring mutex with a global one

A single global mutex for ring submissions seems sufficient.
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/radeon.h

@@ -676,7 +676,6 @@ struct radeon_ring {
 	uint64_t		gpu_addr;
 	uint32_t		align_mask;
 	uint32_t		ptr_mask;
-	struct mutex		mutex;
 	bool			ready;
 	u32			ptr_reg_shift;
 	u32			ptr_reg_mask;
@@ -815,6 +814,7 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *cp, unsign
 int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ndw);
 void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *cp);
+void radeon_ring_undo(struct radeon_ring *ring);
 void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *cp);
 int radeon_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring);
@@ -1534,6 +1534,7 @@ struct radeon_device {
 	rwlock_t			fence_lock;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
 	struct radeon_semaphore_driver	semaphore_drv;
+	struct mutex			ring_lock;
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
 	struct radeon_ib_pool		ib_pool;
 	struct radeon_irq		irq;

drivers/gpu/drm/radeon/radeon_device.c

@@ -724,8 +724,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	 * can recall function without having locking issues */
 	radeon_mutex_init(&rdev->cs_mutex);
 	radeon_mutex_init(&rdev->ib_pool.mutex);
-	for (i = 0; i < RADEON_NUM_RINGS; ++i)
-		mutex_init(&rdev->ring[i].mutex);
+	mutex_init(&rdev->ring_lock);
 	mutex_init(&rdev->dc_hw_i2c_mutex);
 	if (rdev->family >= CHIP_R600)
 		spin_lock_init(&rdev->ih.lock);

drivers/gpu/drm/radeon/radeon_pm.c

@@ -252,10 +252,7 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev)
 
 	mutex_lock(&rdev->ddev->struct_mutex);
 	mutex_lock(&rdev->vram_mutex);
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (rdev->ring[i].ring_obj)
-			mutex_lock(&rdev->ring[i].mutex);
-	}
+	mutex_lock(&rdev->ring_lock);
 
 	/* gui idle int has issues on older chips it seems */
 	if (rdev->family >= CHIP_R600) {
@@ -311,10 +308,7 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev)
 
 	rdev->pm.dynpm_planned_action = DYNPM_ACTION_NONE;
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (rdev->ring[i].ring_obj)
-			mutex_unlock(&rdev->ring[i].mutex);
-	}
+	mutex_unlock(&rdev->ring_lock);
 	mutex_unlock(&rdev->vram_mutex);
 	mutex_unlock(&rdev->ddev->struct_mutex);
 }

drivers/gpu/drm/radeon/radeon_ring.c

@@ -346,9 +346,9 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsi
 		if (ndw < ring->ring_free_dw) {
 			break;
 		}
-		mutex_unlock(&ring->mutex);
+		mutex_unlock(&rdev->ring_lock);
 		r = radeon_fence_wait_next(rdev, radeon_ring_index(rdev, ring));
-		mutex_lock(&ring->mutex);
+		mutex_lock(&rdev->ring_lock);
 		if (r)
 			return r;
 	}
@@ -361,10 +361,10 @@ int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 {
 	int r;
 
-	mutex_lock(&ring->mutex);
+	mutex_lock(&rdev->ring_lock);
 	r = radeon_ring_alloc(rdev, ring, ndw);
 	if (r) {
-		mutex_unlock(&ring->mutex);
+		mutex_unlock(&rdev->ring_lock);
 		return r;
 	}
 	return 0;
@@ -389,20 +389,25 @@ void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring)
 void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	radeon_ring_commit(rdev, ring);
-	mutex_unlock(&ring->mutex);
+	mutex_unlock(&rdev->ring_lock);
 }
 
-void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *ring)
+void radeon_ring_undo(struct radeon_ring *ring)
 {
 	ring->wptr = ring->wptr_old;
-	mutex_unlock(&ring->mutex);
+}
+
+void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	radeon_ring_undo(ring);
+	mutex_unlock(&rdev->ring_lock);
 }
 
 void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	int r;
 
-	mutex_lock(&ring->mutex);
+	mutex_lock(&rdev->ring_lock);
 	radeon_ring_free_size(rdev, ring);
 	if (ring->rptr == ring->wptr) {
 		r = radeon_ring_alloc(rdev, ring, 1);
@@ -411,7 +416,7 @@ void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *
 			radeon_ring_commit(rdev, ring);
 		}
 	}
-	mutex_unlock(&ring->mutex);
+	mutex_unlock(&rdev->ring_lock);
 }
 
 void radeon_ring_lockup_update(struct radeon_ring *ring)
@@ -520,11 +525,12 @@ void radeon_ring_fini(struct radeon_device *rdev, struct radeon_ring *ring)
 	int r;
 	struct radeon_bo *ring_obj;
 
-	mutex_lock(&ring->mutex);
+	mutex_lock(&rdev->ring_lock);
 	ring_obj = ring->ring_obj;
+	ring->ready = false;
 	ring->ring = NULL;
 	ring->ring_obj = NULL;
-	mutex_unlock(&ring->mutex);
+	mutex_unlock(&rdev->ring_lock);
 
 	if (ring_obj) {
 		r = radeon_bo_reserve(ring_obj, false);

drivers/gpu/drm/radeon/radeon_semaphore.c

@@ -39,7 +39,6 @@ static int radeon_semaphore_add_bo(struct radeon_device *rdev)
 	uint32_t *cpu_ptr;
 	int r, i;
 
-
 	bo = kmalloc(sizeof(struct radeon_semaphore_bo), GFP_KERNEL);
 	if (bo == NULL) {
 		return -ENOMEM;
@@ -154,13 +153,17 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 				bool sync_to[RADEON_NUM_RINGS],
 				int dst_ring)
 {
-	int i, r;
+	int i = 0, r;
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		unsigned num_ops = i == dst_ring ? RADEON_NUM_RINGS : 1;
+	mutex_lock(&rdev->ring_lock);
+	r = radeon_ring_alloc(rdev, &rdev->ring[dst_ring], RADEON_NUM_RINGS * 8);
+	if (r) {
+		goto error;
+	}
 
-		/* don't lock unused rings */
-		if (!sync_to[i] && i != dst_ring)
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		/* no need to sync to our own or unused rings */
+		if (!sync_to[i] || i == dst_ring)
 			continue;
 
 		/* prevent GPU deadlocks */
@@ -170,38 +173,31 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 			goto error;
 		}
 
-                r = radeon_ring_lock(rdev, &rdev->ring[i], num_ops * 8);
-                if (r)
+		r = radeon_ring_alloc(rdev, &rdev->ring[i], 8);
+		if (r) {
 			goto error;
 		}
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		/* no need to sync to our own or unused rings */
-		if (!sync_to[i] || i == dst_ring)
-                        continue;
-
 		radeon_semaphore_emit_signal(rdev, i, semaphore);
 		radeon_semaphore_emit_wait(rdev, dst_ring, semaphore);
-	}
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-
-		/* don't unlock unused rings */
-		if (!sync_to[i] && i != dst_ring)
-			continue;
-
-		radeon_ring_unlock_commit(rdev, &rdev->ring[i]);
+		radeon_ring_commit(rdev, &rdev->ring[i]);
 	}
 
+	radeon_ring_commit(rdev, &rdev->ring[dst_ring]);
+	mutex_unlock(&rdev->ring_lock);
+
 	return 0;
 
 error:
 	/* unlock all locks taken so far */
 	for (--i; i >= 0; --i) {
 		if (sync_to[i] || i == dst_ring) {
-			radeon_ring_unlock_undo(rdev, &rdev->ring[i]);
+			radeon_ring_undo(&rdev->ring[i]);
 		}
 	}
+	radeon_ring_undo(&rdev->ring[dst_ring]);
+	mutex_unlock(&rdev->ring_lock);
 	return r;
 }