1 files changed, 197 insertions, 199 deletions

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index cc33b3d7c33..493a7be7530 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -24,6 +24,7 @@
  * Authors: Dave Airlie
  *          Alex Deucher
  *          Jerome Glisse
+ *          Christian König
  */
 #include <linux/seq_file.h>
 #include <linux/slab.h>
@@ -33,8 +34,10 @@
 #include "radeon.h"
 #include "atom.h"
 
-int radeon_debugfs_ib_init(struct radeon_device *rdev);
-int radeon_debugfs_ring_init(struct radeon_device *rdev);
+/*
+ * IB.
+ */
+int radeon_debugfs_sa_init(struct radeon_device *rdev);
 
 u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
 {
@@ -61,123 +64,37 @@ u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
 	return idx_value;
 }
 
-void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
-{
-#if DRM_DEBUG_CODE
-	if (ring->count_dw <= 0) {
-		DRM_ERROR("radeon: writting more dword to ring than expected !\n");
-	}
-#endif
-	ring->ring[ring->wptr++] = v;
-	ring->wptr &= ring->ptr_mask;
-	ring->count_dw--;
-	ring->ring_free_dw--;
-}
-
-/*
- * IB.
- */
-bool radeon_ib_try_free(struct radeon_device *rdev, struct radeon_ib *ib)
-{
-	bool done = false;
-
-	/* only free ib which have been emited */
-	if (ib->fence && ib->fence->emitted) {
-		if (radeon_fence_signaled(ib->fence)) {
-			radeon_fence_unref(&ib->fence);
-			radeon_sa_bo_free(rdev, &ib->sa_bo);
-			done = true;
-		}
-	}
-	return done;
-}
-
 int radeon_ib_get(struct radeon_device *rdev, int ring,
-		  struct radeon_ib **ib, unsigned size)
+		  struct radeon_ib *ib, unsigned size)
 {
-	struct radeon_fence *fence;
-	unsigned cretry = 0;
-	int r = 0, i, idx;
-
-	*ib = NULL;
-	/* align size on 256 bytes */
-	size = ALIGN(size, 256);
+	int r;
 
-	r = radeon_fence_create(rdev, &fence, ring);
+	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256, true);
 	if (r) {
-		dev_err(rdev->dev, "failed to create fence for new IB\n");
+		dev_err(rdev->dev, "failed to get a new IB (%d)\n", r);
 		return r;
 	}
-
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	idx = rdev->ib_pool.head_id;
-retry:
-	if (cretry > 5) {
-		dev_err(rdev->dev, "failed to get an ib after 5 retry\n");
-		radeon_mutex_unlock(&rdev->ib_pool.mutex);
-		radeon_fence_unref(&fence);
-		return -ENOMEM;
-	}
-	cretry++;
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		radeon_ib_try_free(rdev, &rdev->ib_pool.ibs[idx]);
-		if (rdev->ib_pool.ibs[idx].fence == NULL) {
-			r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
-					     &rdev->ib_pool.ibs[idx].sa_bo,
-					     size, 256);
-			if (!r) {
-				*ib = &rdev->ib_pool.ibs[idx];
-				(*ib)->ptr = rdev->ib_pool.sa_manager.cpu_ptr;
-				(*ib)->ptr += ((*ib)->sa_bo.offset >> 2);
-				(*ib)->gpu_addr = rdev->ib_pool.sa_manager.gpu_addr;
-				(*ib)->gpu_addr += (*ib)->sa_bo.offset;
-				(*ib)->fence = fence;
-				(*ib)->vm_id = 0;
-				(*ib)->is_const_ib = false;
-				/* ib are most likely to be allocated in a ring fashion
-				 * thus rdev->ib_pool.head_id should be the id of the
-				 * oldest ib
-				 */
-				rdev->ib_pool.head_id = (1 + idx);
-				rdev->ib_pool.head_id &= (RADEON_IB_POOL_SIZE - 1);
-				radeon_mutex_unlock(&rdev->ib_pool.mutex);
-				return 0;
-			}
-		}
-		idx = (idx + 1) & (RADEON_IB_POOL_SIZE - 1);
-	}
-	/* this should be rare event, ie all ib scheduled none signaled yet.
-	 */
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		if (rdev->ib_pool.ibs[idx].fence && rdev->ib_pool.ibs[idx].fence->emitted) {
-			r = radeon_fence_wait(rdev->ib_pool.ibs[idx].fence, false);
-			if (!r) {
-				goto retry;
-			}
-			/* an error happened */
-			break;
-		}
-		idx = (idx + 1) & (RADEON_IB_POOL_SIZE - 1);
+	r = radeon_fence_create(rdev, &ib->fence, ring);
+	if (r) {
+		dev_err(rdev->dev, "failed to create fence for new IB (%d)\n", r);
+		radeon_sa_bo_free(rdev, &ib->sa_bo, NULL);
+		return r;
 	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
-	radeon_fence_unref(&fence);
-	return r;
+
+	ib->ptr = radeon_sa_bo_cpu_addr(ib->sa_bo);
+	ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
+	ib->vm_id = 0;
+	ib->is_const_ib = false;
+	ib->semaphore = NULL;
+
+	return 0;
 }
 
-void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
+void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 {
-	struct radeon_ib *tmp = *ib;
-
-	*ib = NULL;
-	if (tmp == NULL) {
-		return;
-	}
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (tmp->fence && !tmp->fence->emitted) {
-		radeon_sa_bo_free(rdev, &tmp->sa_bo);
-		radeon_fence_unref(&tmp->fence);
-	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
+	radeon_semaphore_free(rdev, ib->semaphore, ib->fence);
+	radeon_sa_bo_free(rdev, &ib->sa_bo, ib->fence);
+	radeon_fence_unref(&ib->fence);
 }
 
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
@@ -187,14 +104,14 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 
 	if (!ib->length_dw || !ring->ready) {
 		/* TODO: Nothings in the ib we should report. */
-		DRM_ERROR("radeon: couldn't schedule IB(%u).\n", ib->idx);
+		dev_err(rdev->dev, "couldn't schedule ib\n");
 		return -EINVAL;
 	}
 
 	/* 64 dwords should be enough for fence too */
 	r = radeon_ring_lock(rdev, ring, 64);
 	if (r) {
-		DRM_ERROR("radeon: scheduling IB failed (%d).\n", r);
+		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
 		return r;
 	}
 	radeon_ring_ib_execute(rdev, ib->fence->ring, ib);
@@ -205,74 +122,90 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 
 int radeon_ib_pool_init(struct radeon_device *rdev)
 {
-	struct radeon_sa_manager tmp;
-	int i, r;
+	int r;
 
-	r = radeon_sa_bo_manager_init(rdev, &tmp,
+	if (rdev->ib_pool_ready) {
+		return 0;
+	}
+	r = radeon_sa_bo_manager_init(rdev, &rdev->ring_tmp_bo,
 				      RADEON_IB_POOL_SIZE*64*1024,
 				      RADEON_GEM_DOMAIN_GTT);
 	if (r) {
 		return r;
 	}
-
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (rdev->ib_pool.ready) {
-		radeon_mutex_unlock(&rdev->ib_pool.mutex);
-		radeon_sa_bo_manager_fini(rdev, &tmp);
-		return 0;
-	}
-
-	rdev->ib_pool.sa_manager = tmp;
-	INIT_LIST_HEAD(&rdev->ib_pool.sa_manager.sa_bo);
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		rdev->ib_pool.ibs[i].fence = NULL;
-		rdev->ib_pool.ibs[i].idx = i;
-		rdev->ib_pool.ibs[i].length_dw = 0;
-		INIT_LIST_HEAD(&rdev->ib_pool.ibs[i].sa_bo.list);
-	}
-	rdev->ib_pool.head_id = 0;
-	rdev->ib_pool.ready = true;
-	DRM_INFO("radeon: ib pool ready.\n");
-
-	if (radeon_debugfs_ib_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for IB !\n");
-	}
-	if (radeon_debugfs_ring_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for rings !\n");
+	rdev->ib_pool_ready = true;
+	if (radeon_debugfs_sa_init(rdev)) {
+		dev_err(rdev->dev, "failed to register debugfs file for SA\n");
 	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 	return 0;
 }
 
 void radeon_ib_pool_fini(struct radeon_device *rdev)
 {
-	unsigned i;
-
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (rdev->ib_pool.ready) {
-		for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-			radeon_sa_bo_free(rdev, &rdev->ib_pool.ibs[i].sa_bo);
-			radeon_fence_unref(&rdev->ib_pool.ibs[i].fence);
-		}
-		radeon_sa_bo_manager_fini(rdev, &rdev->ib_pool.sa_manager);
-		rdev->ib_pool.ready = false;
+	if (rdev->ib_pool_ready) {
+		radeon_sa_bo_manager_fini(rdev, &rdev->ring_tmp_bo);
+		rdev->ib_pool_ready = false;
 	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 }
 
 int radeon_ib_pool_start(struct radeon_device *rdev)
 {
-	return radeon_sa_bo_manager_start(rdev, &rdev->ib_pool.sa_manager);
+	return radeon_sa_bo_manager_start(rdev, &rdev->ring_tmp_bo);
 }
 
 int radeon_ib_pool_suspend(struct radeon_device *rdev)
 {
-	return radeon_sa_bo_manager_suspend(rdev, &rdev->ib_pool.sa_manager);
+	return radeon_sa_bo_manager_suspend(rdev, &rdev->ring_tmp_bo);
+}
+
+int radeon_ib_ring_tests(struct radeon_device *rdev)
+{
+	unsigned i;
+	int r;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		struct radeon_ring *ring = &rdev->ring[i];
+
+		if (!ring->ready)
+			continue;
+
+		r = radeon_ib_test(rdev, i, ring);
+		if (r) {
+			ring->ready = false;
+
+			if (i == RADEON_RING_TYPE_GFX_INDEX) {
+				/* oh, oh, that's really bad */
+				DRM_ERROR("radeon: failed testing IB on GFX ring (%d).\n", r);
+		                rdev->accel_working = false;
+				return r;
+
+			} else {
+				/* still not good, but we can live with it */
+				DRM_ERROR("radeon: failed testing IB on ring %d (%d).\n", i, r);
+			}
+		}
+	}
+	return 0;
 }
 
 /*
  * Ring.
  */
+int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
+
+void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
+{
+#if DRM_DEBUG_CODE
+	if (ring->count_dw <= 0) {
+		DRM_ERROR("radeon: writting more dword to ring than expected !\n");
+	}
+#endif
+	ring->ring[ring->wptr++] = v;
+	ring->wptr &= ring->ptr_mask;
+	ring->count_dw--;
+	ring->ring_free_dw--;
+}
+
 int radeon_ring_index(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	/* r1xx-r5xx only has CP ring */
@@ -319,7 +252,7 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsi
 		if (ndw < ring->ring_free_dw) {
 			break;
 		}
-		r = radeon_fence_wait_next(rdev, radeon_ring_index(rdev, ring));
+		r = radeon_fence_wait_next_locked(rdev, radeon_ring_index(rdev, ring));
 		if (r)
 			return r;
 	}
@@ -332,10 +265,10 @@ 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;
@@ -360,13 +293,85 @@ 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;
+
+	radeon_ring_free_size(rdev, ring);
+	if (ring->rptr == ring->wptr) {
+		r = radeon_ring_alloc(rdev, ring, 1);
+		if (!r) {
+			radeon_ring_write(ring, ring->nop);
+			radeon_ring_commit(rdev, ring);
+		}
+	}
+}
+
+void radeon_ring_lockup_update(struct radeon_ring *ring)
+{
+	ring->last_rptr = ring->rptr;
+	ring->last_activity = jiffies;
+}
+
+/**
+ * radeon_ring_test_lockup() - check if ring is lockedup by recording information
+ * @rdev:       radeon device structure
+ * @ring:       radeon_ring structure holding ring information
+ *
+ * We don't need to initialize the lockup tracking information as we will either
+ * have CP rptr to a different value of jiffies wrap around which will force
+ * initialization of the lockup tracking informations.
+ *
+ * A possible false positivie is if we get call after while and last_cp_rptr ==
+ * the current CP rptr, even if it's unlikely it might happen. To avoid this
+ * if the elapsed time since last call is bigger than 2 second than we return
+ * false and update the tracking information. Due to this the caller must call
+ * radeon_ring_test_lockup several time in less than 2sec for lockup to be reported
+ * the fencing code should be cautious about that.
+ *
+ * Caller should write to the ring to force CP to do something so we don't get
+ * false positive when CP is just gived nothing to do.
+ *
+ **/
+bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
+{
+	unsigned long cjiffies, elapsed;
+	uint32_t rptr;
+
+	cjiffies = jiffies;
+	if (!time_after(cjiffies, ring->last_activity)) {
+		/* likely a wrap around */
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	rptr = RREG32(ring->rptr_reg);
+	ring->rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
+	if (ring->rptr != ring->last_rptr) {
+		/* CP is still working no lockup */
+		radeon_ring_lockup_update(ring);
+		return false;
+	}
+	elapsed = jiffies_to_msecs(cjiffies - ring->last_activity);
+	if (radeon_lockup_timeout && elapsed >= radeon_lockup_timeout) {
+		dev_err(rdev->dev, "GPU lockup CP stall for more than %lumsec\n", elapsed);
+		return true;
+	}
+	/* give a chance to the GPU ... */
+	return false;
 }
 
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size,
@@ -385,8 +390,8 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	/* Allocate ring buffer */
 	if (ring->ring_obj == NULL) {
 		r = radeon_bo_create(rdev, ring->ring_size, PAGE_SIZE, true,
-					RADEON_GEM_DOMAIN_GTT,
-					&ring->ring_obj);
+				     RADEON_GEM_DOMAIN_GTT,
+				     NULL, &ring->ring_obj);
 		if (r) {
 			dev_err(rdev->dev, "(%d) ring create failed\n", r);
 			return r;
@@ -411,6 +416,9 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	}
 	ring->ptr_mask = (ring->ring_size / 4) - 1;
 	ring->ring_free_dw = ring->ring_size / 4;
+	if (radeon_debugfs_ring_init(rdev, ring)) {
+		DRM_ERROR("Failed to register debugfs file for rings !\n");
+	}
 	return 0;
 }
 
@@ -419,11 +427,12 @@ 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);
@@ -476,59 +485,48 @@ static struct drm_info_list radeon_debugfs_ring_info_list[] = {
 	{"radeon_ring_cp2", radeon_debugfs_ring_info, 0, &cayman_ring_type_cp2_index},
 };
 
-static int radeon_debugfs_ib_info(struct seq_file *m, void *data)
+static int radeon_debugfs_sa_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_ib *ib = &rdev->ib_pool.ibs[*((unsigned*)node->info_ent->data)];
-	unsigned i;
 
-	if (ib == NULL) {
-		return 0;
-	}
-	seq_printf(m, "IB %04u\n", ib->idx);
-	seq_printf(m, "IB fence %p\n", ib->fence);
-	seq_printf(m, "IB size %05u dwords\n", ib->length_dw);
-	for (i = 0; i < ib->length_dw; i++) {
-		seq_printf(m, "[%05u]=0x%08X\n", i, ib->ptr[i]);
-	}
+	radeon_sa_bo_dump_debug_info(&rdev->ring_tmp_bo, m);
+
 	return 0;
+
 }
 
-static struct drm_info_list radeon_debugfs_ib_list[RADEON_IB_POOL_SIZE];
-static char radeon_debugfs_ib_names[RADEON_IB_POOL_SIZE][32];
-static unsigned radeon_debugfs_ib_idx[RADEON_IB_POOL_SIZE];
+static struct drm_info_list radeon_debugfs_sa_list[] = {
+        {"radeon_sa_info", &radeon_debugfs_sa_info, 0, NULL},
+};
+
 #endif
 
-int radeon_debugfs_ring_init(struct radeon_device *rdev)
+int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 #if defined(CONFIG_DEBUG_FS)
-	if (rdev->family >= CHIP_CAYMAN)
-		return radeon_debugfs_add_files(rdev, radeon_debugfs_ring_info_list,
-						ARRAY_SIZE(radeon_debugfs_ring_info_list));
-	else
-		return radeon_debugfs_add_files(rdev, radeon_debugfs_ring_info_list, 1);
-#else
-	return 0;
+	unsigned i;
+	for (i = 0; i < ARRAY_SIZE(radeon_debugfs_ring_info_list); ++i) {
+		struct drm_info_list *info = &radeon_debugfs_ring_info_list[i];
+		int ridx = *(int*)radeon_debugfs_ring_info_list[i].data;
+		unsigned r;
+
+		if (&rdev->ring[ridx] != ring)
+			continue;
+
+		r = radeon_debugfs_add_files(rdev, info, 1);
+		if (r)
+			return r;
+	}
 #endif
+	return 0;
 }
 
-int radeon_debugfs_ib_init(struct radeon_device *rdev)
+int radeon_debugfs_sa_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
-	unsigned i;
-
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		sprintf(radeon_debugfs_ib_names[i], "radeon_ib_%04u", i);
-		radeon_debugfs_ib_idx[i] = i;
-		radeon_debugfs_ib_list[i].name = radeon_debugfs_ib_names[i];
-		radeon_debugfs_ib_list[i].show = &radeon_debugfs_ib_info;
-		radeon_debugfs_ib_list[i].driver_features = 0;
-		radeon_debugfs_ib_list[i].data = &radeon_debugfs_ib_idx[i];
-	}
-	return radeon_debugfs_add_files(rdev, radeon_debugfs_ib_list,
-					RADEON_IB_POOL_SIZE);
+	return radeon_debugfs_add_files(rdev, radeon_debugfs_sa_list, 1);
 #else
 	return 0;
 #endif