1 files changed, 19 insertions, 280 deletions

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index f8050f5429e2..d65607902537 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -26,258 +26,8 @@
  *          Jerome Glisse
  *          Christian König
  */
-#include <linux/seq_file.h>
-#include <linux/slab.h>
 #include <drm/drmP.h>
-#include <drm/radeon_drm.h>
-#include "radeon_reg.h"
 #include "radeon.h"
-#include "atom.h"
-
-/*
- * IB
- * IBs (Indirect Buffers) and areas of GPU accessible memory where
- * commands are stored.  You can put a pointer to the IB in the
- * command ring and the hw will fetch the commands from the IB
- * and execute them.  Generally userspace acceleration drivers
- * produce command buffers which are send to the kernel and
- * put in IBs for execution by the requested ring.
- */
-static int radeon_debugfs_sa_init(struct radeon_device *rdev);
-
-/**
- * radeon_ib_get - request an IB (Indirect Buffer)
- *
- * @rdev: radeon_device pointer
- * @ring: ring index the IB is associated with
- * @ib: IB object returned
- * @size: requested IB size
- *
- * Request an IB (all asics).  IBs are allocated using the
- * suballocator.
- * Returns 0 on success, error on failure.
- */
-int radeon_ib_get(struct radeon_device *rdev, int ring,
-		  struct radeon_ib *ib, struct radeon_vm *vm,
-		  unsigned size)
-{
-	int r;
-
-	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256);
-	if (r) {
-		dev_err(rdev->dev, "failed to get a new IB (%d)\n", r);
-		return r;
-	}
-
-	r = radeon_semaphore_create(rdev, &ib->semaphore);
-	if (r) {
-		return r;
-	}
-
-	ib->ring = ring;
-	ib->fence = NULL;
-	ib->ptr = radeon_sa_bo_cpu_addr(ib->sa_bo);
-	ib->vm = vm;
-	if (vm) {
-		/* ib pool is bound at RADEON_VA_IB_OFFSET in virtual address
-		 * space and soffset is the offset inside the pool bo
-		 */
-		ib->gpu_addr = ib->sa_bo->soffset + RADEON_VA_IB_OFFSET;
-	} else {
-		ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
-	}
-	ib->is_const_ib = false;
-
-	return 0;
-}
-
-/**
- * radeon_ib_free - free an IB (Indirect Buffer)
- *
- * @rdev: radeon_device pointer
- * @ib: IB object to free
- *
- * Free an IB (all asics).
- */
-void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
-{
-	radeon_semaphore_free(rdev, &ib->semaphore, ib->fence);
-	radeon_sa_bo_free(rdev, &ib->sa_bo, ib->fence);
-	radeon_fence_unref(&ib->fence);
-}
-
-/**
- * radeon_ib_schedule - schedule an IB (Indirect Buffer) on the ring
- *
- * @rdev: radeon_device pointer
- * @ib: IB object to schedule
- * @const_ib: Const IB to schedule (SI only)
- *
- * Schedule an IB on the associated ring (all asics).
- * Returns 0 on success, error on failure.
- *
- * On SI, there are two parallel engines fed from the primary ring,
- * the CE (Constant Engine) and the DE (Drawing Engine).  Since
- * resource descriptors have moved to memory, the CE allows you to
- * prime the caches while the DE is updating register state so that
- * the resource descriptors will be already in cache when the draw is
- * processed.  To accomplish this, the userspace driver submits two
- * IBs, one for the CE and one for the DE.  If there is a CE IB (called
- * a CONST_IB), it will be put on the ring prior to the DE IB.  Prior
- * to SI there was just a DE IB.
- */
-int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
-		       struct radeon_ib *const_ib)
-{
-	struct radeon_ring *ring = &rdev->ring[ib->ring];
-	int r = 0;
-
-	if (!ib->length_dw || !ring->ready) {
-		/* TODO: Nothings in the ib we should report. */
-		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 + RADEON_NUM_SYNCS * 8);
-	if (r) {
-		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
-		return r;
-	}
-
-	/* grab a vm id if necessary */
-	if (ib->vm) {
-		struct radeon_fence *vm_id_fence;
-		vm_id_fence = radeon_vm_grab_id(rdev, ib->vm, ib->ring);
-        	radeon_semaphore_sync_to(ib->semaphore, vm_id_fence);
-	}
-
-	/* sync with other rings */
-	r = radeon_semaphore_sync_rings(rdev, ib->semaphore, ib->ring);
-	if (r) {
-		dev_err(rdev->dev, "failed to sync rings (%d)\n", r);
-		radeon_ring_unlock_undo(rdev, ring);
-		return r;
-	}
-
-	if (ib->vm)
-		radeon_vm_flush(rdev, ib->vm, ib->ring);
-
-	if (const_ib) {
-		radeon_ring_ib_execute(rdev, const_ib->ring, const_ib);
-		radeon_semaphore_free(rdev, &const_ib->semaphore, NULL);
-	}
-	radeon_ring_ib_execute(rdev, ib->ring, ib);
-	r = radeon_fence_emit(rdev, &ib->fence, ib->ring);
-	if (r) {
-		dev_err(rdev->dev, "failed to emit fence for new IB (%d)\n", r);
-		radeon_ring_unlock_undo(rdev, ring);
-		return r;
-	}
-	if (const_ib) {
-		const_ib->fence = radeon_fence_ref(ib->fence);
-	}
-
-	if (ib->vm)
-		radeon_vm_fence(rdev, ib->vm, ib->fence);
-
-	radeon_ring_unlock_commit(rdev, ring);
-	return 0;
-}
-
-/**
- * radeon_ib_pool_init - Init the IB (Indirect Buffer) pool
- *
- * @rdev: radeon_device pointer
- *
- * Initialize the suballocator to manage a pool of memory
- * for use as IBs (all asics).
- * Returns 0 on success, error on failure.
- */
-int radeon_ib_pool_init(struct radeon_device *rdev)
-{
-	int r;
-
-	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_GPU_PAGE_SIZE,
-				      RADEON_GEM_DOMAIN_GTT);
-	if (r) {
-		return r;
-	}
-
-	r = radeon_sa_bo_manager_start(rdev, &rdev->ring_tmp_bo);
-	if (r) {
-		return r;
-	}
-
-	rdev->ib_pool_ready = true;
-	if (radeon_debugfs_sa_init(rdev)) {
-		dev_err(rdev->dev, "failed to register debugfs file for SA\n");
-	}
-	return 0;
-}
-
-/**
- * radeon_ib_pool_fini - Free the IB (Indirect Buffer) pool
- *
- * @rdev: radeon_device pointer
- *
- * Tear down the suballocator managing the pool of memory
- * for use as IBs (all asics).
- */
-void radeon_ib_pool_fini(struct radeon_device *rdev)
-{
-	if (rdev->ib_pool_ready) {
-		radeon_sa_bo_manager_suspend(rdev, &rdev->ring_tmp_bo);
-		radeon_sa_bo_manager_fini(rdev, &rdev->ring_tmp_bo);
-		rdev->ib_pool_ready = false;
-	}
-}
-
-/**
- * radeon_ib_ring_tests - test IBs on the rings
- *
- * @rdev: radeon_device pointer
- *
- * Test an IB (Indirect Buffer) on each ring.
- * If the test fails, disable the ring.
- * Returns 0 on success, error if the primary GFX ring
- * IB test fails.
- */
-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;
-			rdev->needs_reset = 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;
-}
 
 /*
  * Rings
@@ -427,17 +177,29 @@ int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *ring, unsig
  *
  * @rdev: radeon_device pointer
  * @ring: radeon_ring structure holding ring information
+ * @hdp_flush: Whether or not to perform an HDP cache flush
  *
  * Update the wptr (write pointer) to tell the GPU to
  * execute new commands on the ring buffer (all asics).
  */
-void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring)
+void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring,
+			bool hdp_flush)
 {
+	/* If we are emitting the HDP flush via the ring buffer, we need to
+	 * do it before padding.
+	 */
+	if (hdp_flush && rdev->asic->ring[ring->idx]->hdp_flush)
+		rdev->asic->ring[ring->idx]->hdp_flush(rdev, ring);
 	/* We pad to match fetch size */
 	while (ring->wptr & ring->align_mask) {
 		radeon_ring_write(ring, ring->nop);
 	}
 	mb();
+	/* If we are emitting the HDP flush via MMIO, we need to do it after
+	 * all CPU writes to VRAM finished.
+	 */
+	if (hdp_flush && rdev->asic->mmio_hdp_flush)
+		rdev->asic->mmio_hdp_flush(rdev);
 	radeon_ring_set_wptr(rdev, ring);
 }
 
@@ -447,12 +209,14 @@ void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring)
  *
  * @rdev: radeon_device pointer
  * @ring: radeon_ring structure holding ring information
+ * @hdp_flush: Whether or not to perform an HDP cache flush
  *
  * Call radeon_ring_commit() then unlock the ring (all asics).
  */
-void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *ring)
+void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *ring,
+			       bool hdp_flush)
 {
-	radeon_ring_commit(rdev, ring);
+	radeon_ring_commit(rdev, ring, hdp_flush);
 	mutex_unlock(&rdev->ring_lock);
 }
 
@@ -612,7 +376,7 @@ int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring,
 		radeon_ring_write(ring, data[i]);
 	}
 
-	radeon_ring_unlock_commit(rdev, ring);
+	radeon_ring_unlock_commit(rdev, ring, false);
 	kfree(data);
 	return 0;
 }
@@ -640,7 +404,7 @@ 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,
+				     RADEON_GEM_DOMAIN_GTT, 0,
 				     NULL, &ring->ring_obj);
 		if (r) {
 			dev_err(rdev->dev, "(%d) ring create failed\n", r);
@@ -791,22 +555,6 @@ static struct drm_info_list radeon_debugfs_ring_info_list[] = {
 	{"radeon_ring_vce2", radeon_debugfs_ring_info, 0, &si_vce2_index},
 };
 
-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;
-
-	radeon_sa_bo_dump_debug_info(&rdev->ring_tmp_bo, m);
-
-	return 0;
-
-}
-
-static struct drm_info_list radeon_debugfs_sa_list[] = {
-        {"radeon_sa_info", &radeon_debugfs_sa_info, 0, NULL},
-};
-
 #endif
 
 static int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring)
@@ -828,12 +576,3 @@ static int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ri
 #endif
 	return 0;
 }
-
-static int radeon_debugfs_sa_init(struct radeon_device *rdev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, radeon_debugfs_sa_list, 1);
-#else
-	return 0;
-#endif
-}