From 876dc9f32907e57e0298bcd0f1607cb7a2582f63 Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Tue, 8 May 2012 14:24:01 +0200
Subject: drm/radeon: remove radeon_fence_create
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is completely unnecessary to create fences
before they are emitted, so remove it and a bunch
of checks if fences are emitted or not.

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
---
 drivers/gpu/drm/radeon/radeon_ring.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 983658c91358..dd506c216d8f 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -49,13 +49,9 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 		dev_err(rdev->dev, "failed to get a new IB (%d)\n", r);
 		return r;
 	}
-	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;
-	}
 
+	ib->ring = ring;
+	ib->fence = NULL;
 	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;
@@ -74,7 +70,7 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 {
-	struct radeon_ring *ring = &rdev->ring[ib->fence->ring];
+	struct radeon_ring *ring = &rdev->ring[ib->ring];
 	int r = 0;
 
 	if (!ib->length_dw || !ring->ready) {
@@ -89,8 +85,13 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
 		return r;
 	}
-	radeon_ring_ib_execute(rdev, ib->fence->ring, ib);
-	radeon_fence_emit(rdev, ib->fence);
+	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;
+	}
 	radeon_ring_unlock_commit(rdev, ring);
 	return 0;
 }
-- 
cgit v1.2.3


From 220907d9835ce5181b9f782c862b1ee7a4d24c23 Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Thu, 10 May 2012 16:46:43 +0200
Subject: drm/radeon: rework ring syncing code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move inter ring syncing with semaphores into the
existing ring allocations, with that we need to
lock the ring mutex only once.

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
---
 drivers/gpu/drm/radeon/evergreen_blit_kms.c |  3 +-
 drivers/gpu/drm/radeon/r600.c               |  5 +-
 drivers/gpu/drm/radeon/r600_blit_kms.c      | 24 ++++++++--
 drivers/gpu/drm/radeon/radeon.h             |  6 +--
 drivers/gpu/drm/radeon/radeon_asic.h        |  5 +-
 drivers/gpu/drm/radeon/radeon_cs.c          | 38 ++++-----------
 drivers/gpu/drm/radeon/radeon_ring.c        | 30 ++++++++++--
 drivers/gpu/drm/radeon/radeon_semaphore.c   | 71 ++++++++++-------------------
 drivers/gpu/drm/radeon/radeon_test.c        |  6 +--
 drivers/gpu/drm/radeon/radeon_ttm.c         | 20 --------
 10 files changed, 92 insertions(+), 116 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index 1e96bd458cfd..e512560ffc6f 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -622,7 +622,8 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	rdev->r600_blit.primitives.draw_auto = draw_auto;
 	rdev->r600_blit.primitives.set_default_state = set_default_state;
 
-	rdev->r600_blit.ring_size_common = 55; /* shaders + def state */
+	rdev->r600_blit.ring_size_common = 8; /* sync semaphore */
+	rdev->r600_blit.ring_size_common += 55; /* shaders + def state */
 	rdev->r600_blit.ring_size_common += 16; /* fence emit for VB IB */
 	rdev->r600_blit.ring_size_common += 5; /* done copy */
 	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index a80e61e138db..aced97bb79e0 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2311,15 +2311,16 @@ int r600_copy_blit(struct radeon_device *rdev,
 		   unsigned num_gpu_pages,
 		   struct radeon_fence **fence)
 {
+	struct radeon_semaphore *sem = NULL;
 	struct radeon_sa_bo *vb = NULL;
 	int r;
 
-	r = r600_blit_prepare_copy(rdev, num_gpu_pages, &vb);
+	r = r600_blit_prepare_copy(rdev, num_gpu_pages, fence, &vb, &sem);
 	if (r) {
 		return r;
 	}
 	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages, vb);
-	r600_blit_done_copy(rdev, fence, vb);
+	r600_blit_done_copy(rdev, fence, vb, sem);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index 02f4eebf805f..2b8d6418a30c 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -512,7 +512,8 @@ int r600_blit_init(struct radeon_device *rdev)
 	rdev->r600_blit.primitives.draw_auto = draw_auto;
 	rdev->r600_blit.primitives.set_default_state = set_default_state;
 
-	rdev->r600_blit.ring_size_common = 40; /* shaders + def state */
+	rdev->r600_blit.ring_size_common = 8; /* sync semaphore */
+	rdev->r600_blit.ring_size_common += 40; /* shaders + def state */
 	rdev->r600_blit.ring_size_common += 5; /* done copy */
 	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
 
@@ -666,7 +667,8 @@ static unsigned r600_blit_create_rect(unsigned num_gpu_pages,
 
 
 int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
-			   struct radeon_sa_bo **vb)
+			   struct radeon_fence **fence, struct radeon_sa_bo **vb,
+			   struct radeon_semaphore **sem)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
@@ -689,22 +691,37 @@ int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
 		return r;
 	}
 
+	r = radeon_semaphore_create(rdev, sem);
+	if (r) {
+		radeon_sa_bo_free(rdev, vb, NULL);
+		return r;
+	}
+
 	/* calculate number of loops correctly */
 	ring_size = num_loops * dwords_per_loop;
 	ring_size += rdev->r600_blit.ring_size_common;
 	r = radeon_ring_lock(rdev, ring, ring_size);
 	if (r) {
 		radeon_sa_bo_free(rdev, vb, NULL);
+		radeon_semaphore_free(rdev, sem, NULL);
 		return r;
 	}
 
+	if (radeon_fence_need_sync(*fence, RADEON_RING_TYPE_GFX_INDEX)) {
+		radeon_semaphore_sync_rings(rdev, *sem, (*fence)->ring,
+					    RADEON_RING_TYPE_GFX_INDEX);
+		radeon_fence_note_sync(*fence, RADEON_RING_TYPE_GFX_INDEX);
+	} else {
+		radeon_semaphore_free(rdev, sem, NULL);
+	}
+
 	rdev->r600_blit.primitives.set_default_state(rdev);
 	rdev->r600_blit.primitives.set_shaders(rdev);
 	return 0;
 }
 
 void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence **fence,
-			 struct radeon_sa_bo *vb)
+			 struct radeon_sa_bo *vb, struct radeon_semaphore *sem)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
@@ -717,6 +734,7 @@ void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence **fence
 
 	radeon_ring_unlock_commit(rdev, ring);
 	radeon_sa_bo_free(rdev, &vb, *fence);
+	radeon_semaphore_free(rdev, &sem, *fence);
 }
 
 void r600_kms_blit_copy(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 33a72dc9af85..4563e50cbdde 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -470,10 +470,9 @@ void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 				struct radeon_semaphore *semaphore);
 int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 				struct radeon_semaphore *semaphore,
-				bool sync_to[RADEON_NUM_RINGS],
-				int dst_ring);
+				int signaler, int waiter);
 void radeon_semaphore_free(struct radeon_device *rdev,
-			   struct radeon_semaphore *semaphore,
+			   struct radeon_semaphore **semaphore,
 			   struct radeon_fence *fence);
 
 /*
@@ -653,6 +652,7 @@ struct radeon_ib {
 	struct radeon_fence		*fence;
 	unsigned			vm_id;
 	bool				is_const_ib;
+	struct radeon_fence		*sync_to[RADEON_NUM_RINGS];
 	struct radeon_semaphore		*semaphore;
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 8cdf075aacfd..94c427ab0f5c 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -363,9 +363,10 @@ int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder);
 void r600_hdmi_update_audio_settings(struct drm_encoder *encoder);
 /* r600 blit */
 int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
-			   struct radeon_sa_bo **vb);
+			   struct radeon_fence **fence, struct radeon_sa_bo **vb,
+			   struct radeon_semaphore **sem);
 void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence **fence,
-			 struct radeon_sa_bo *vb);
+			 struct radeon_sa_bo *vb, struct radeon_semaphore *sem);
 void r600_kms_blit_copy(struct radeon_device *rdev,
 			u64 src_gpu_addr, u64 dst_gpu_addr,
 			unsigned num_gpu_pages,
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 142f89462aa4..dd3e234294e4 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -115,36 +115,20 @@ static int radeon_cs_get_ring(struct radeon_cs_parser *p, u32 ring, s32 priority
 	return 0;
 }
 
-static int radeon_cs_sync_rings(struct radeon_cs_parser *p)
+static void radeon_cs_sync_rings(struct radeon_cs_parser *p)
 {
-	bool sync_to_ring[RADEON_NUM_RINGS] = { };
-	bool need_sync = false;
-	int i, r;
+	int i;
 
 	for (i = 0; i < p->nrelocs; i++) {
-		struct radeon_fence *fence;
+		struct radeon_fence *a, *b;
 
 		if (!p->relocs[i].robj || !p->relocs[i].robj->tbo.sync_obj)
 			continue;
 
-		fence = p->relocs[i].robj->tbo.sync_obj;
-		if (fence->ring != p->ring && !radeon_fence_signaled(fence)) {
-			sync_to_ring[fence->ring] = true;
-			need_sync = true;
-		}
-	}
-
-	if (!need_sync) {
-		return 0;
-	}
-
-	r = radeon_semaphore_create(p->rdev, &p->ib.semaphore);
-	if (r) {
-		return r;
+		a = p->relocs[i].robj->tbo.sync_obj;
+		b = p->ib.sync_to[a->ring];
+		p->ib.sync_to[a->ring] = radeon_fence_later(a, b);
 	}
-
-	return radeon_semaphore_sync_rings(p->rdev, p->ib.semaphore,
-					   sync_to_ring, p->ring);
 }
 
 /* XXX: note that this is called from the legacy UMS CS ioctl as well */
@@ -368,10 +352,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 		DRM_ERROR("Invalid command stream !\n");
 		return r;
 	}
-	r = radeon_cs_sync_rings(parser);
-	if (r) {
-		DRM_ERROR("Failed to synchronize rings !\n");
-	}
+	radeon_cs_sync_rings(parser);
 	parser->ib.vm_id = 0;
 	r = radeon_ib_schedule(rdev, &parser->ib);
 	if (r) {
@@ -468,10 +449,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 	if (r) {
 		goto out;
 	}
-	r = radeon_cs_sync_rings(parser);
-	if (r) {
-		DRM_ERROR("Failed to synchronize rings !\n");
-	}
+	radeon_cs_sync_rings(parser);
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index dd506c216d8f..0826e77f99ae 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -42,7 +42,7 @@ int radeon_debugfs_sa_init(struct radeon_device *rdev);
 int radeon_ib_get(struct radeon_device *rdev, int ring,
 		  struct radeon_ib *ib, unsigned size)
 {
-	int r;
+	int i, r;
 
 	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256, true);
 	if (r) {
@@ -50,20 +50,26 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 		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->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
 	ib->vm_id = 0;
 	ib->is_const_ib = false;
-	ib->semaphore = NULL;
+	for (i = 0; i < RADEON_NUM_RINGS; ++i)
+		ib->sync_to[i] = NULL;
 
 	return 0;
 }
 
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 {
-	radeon_semaphore_free(rdev, ib->semaphore, ib->fence);
+	radeon_semaphore_free(rdev, &ib->semaphore, ib->fence);
 	radeon_sa_bo_free(rdev, &ib->sa_bo, ib->fence);
 	radeon_fence_unref(&ib->fence);
 }
@@ -71,7 +77,8 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
-	int r = 0;
+	bool need_sync = false;
+	int i, r = 0;
 
 	if (!ib->length_dw || !ring->ready) {
 		/* TODO: Nothings in the ib we should report. */
@@ -80,11 +87,24 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 	}
 
 	/* 64 dwords should be enough for fence too */
-	r = radeon_ring_lock(rdev, ring, 64);
+	r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_RINGS * 8);
 	if (r) {
 		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
 		return r;
 	}
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		struct radeon_fence *fence = ib->sync_to[i];
+		if (radeon_fence_need_sync(fence, ib->ring)) {
+			need_sync = true;
+			radeon_semaphore_sync_rings(rdev, ib->semaphore,
+						    fence->ring, ib->ring);
+			radeon_fence_note_sync(fence, ib->ring);
+		}
+	}
+	/* immediately free semaphore when we don't need to sync */
+	if (!need_sync) {
+		radeon_semaphore_free(rdev, &ib->semaphore, NULL);
+	}
 	radeon_ring_ib_execute(rdev, ib->ring, ib);
 	r = radeon_fence_emit(rdev, &ib->fence, ib->ring);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index e2ace5dce117..7cc78de6ddc3 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -68,70 +68,49 @@ void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, true);
 }
 
+/* caller must hold ring lock */
 int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 				struct radeon_semaphore *semaphore,
-				bool sync_to[RADEON_NUM_RINGS],
-				int dst_ring)
+				int signaler, int waiter)
 {
-	int i = 0, r;
+	int r;
 
-	mutex_lock(&rdev->ring_lock);
-	r = radeon_ring_alloc(rdev, &rdev->ring[dst_ring], RADEON_NUM_RINGS * 8);
-	if (r) {
-		goto error;
+	/* no need to signal and wait on the same ring */
+	if (signaler == waiter) {
+		return 0;
 	}
 
-	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 */
-		if (!rdev->ring[i].ready) {
-			dev_err(rdev->dev, "Trying to sync to a disabled ring!");
-			r = -EINVAL;
-			goto error;
-		}
-
-		r = radeon_ring_alloc(rdev, &rdev->ring[i], 8);
-		if (r) {
-			goto error;
-		}
-
-		radeon_semaphore_emit_signal(rdev, i, semaphore);
-		radeon_semaphore_emit_wait(rdev, dst_ring, semaphore);
+	/* prevent GPU deadlocks */
+	if (!rdev->ring[signaler].ready) {
+		dev_err(rdev->dev, "Trying to sync to a disabled ring!");
+		return -EINVAL;
+	}
 
-		radeon_ring_commit(rdev, &rdev->ring[i]);
+	r = radeon_ring_alloc(rdev, &rdev->ring[signaler], 8);
+	if (r) {
+		return r;
 	}
+	radeon_semaphore_emit_signal(rdev, signaler, semaphore);
+	radeon_ring_commit(rdev, &rdev->ring[signaler]);
 
-	radeon_ring_commit(rdev, &rdev->ring[dst_ring]);
-	mutex_unlock(&rdev->ring_lock);
+	/* we assume caller has already allocated space on waiters ring */
+	radeon_semaphore_emit_wait(rdev, waiter, semaphore);
 
 	return 0;
-
-error:
-	/* unlock all locks taken so far */
-	for (--i; i >= 0; --i) {
-		if (sync_to[i] || i == dst_ring) {
-			radeon_ring_undo(&rdev->ring[i]);
-		}
-	}
-	radeon_ring_undo(&rdev->ring[dst_ring]);
-	mutex_unlock(&rdev->ring_lock);
-	return r;
 }
 
 void radeon_semaphore_free(struct radeon_device *rdev,
-			   struct radeon_semaphore *semaphore,
+			   struct radeon_semaphore **semaphore,
 			   struct radeon_fence *fence)
 {
-	if (semaphore == NULL) {
+	if (semaphore == NULL || *semaphore == NULL) {
 		return;
 	}
-	if (semaphore->waiters > 0) {
+	if ((*semaphore)->waiters > 0) {
 		dev_err(rdev->dev, "semaphore %p has more waiters than signalers,"
-			" hardware lockup imminent!\n", semaphore);
+			" hardware lockup imminent!\n", *semaphore);
 	}
-	radeon_sa_bo_free(rdev, &semaphore->sa_bo, fence);
-	kfree(semaphore);
+	radeon_sa_bo_free(rdev, &(*semaphore)->sa_bo, fence);
+	kfree(*semaphore);
+	*semaphore = NULL;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 47e1535f2706..a94f66fb3b13 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -303,8 +303,7 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 	}
 
 out_cleanup:
-	if (semaphore)
-		radeon_semaphore_free(rdev, semaphore, NULL);
+	radeon_semaphore_free(rdev, &semaphore, NULL);
 
 	if (fence1)
 		radeon_fence_unref(&fence1);
@@ -422,8 +421,7 @@ void radeon_test_ring_sync2(struct radeon_device *rdev,
 	}
 
 out_cleanup:
-	if (semaphore)
-		radeon_semaphore_free(rdev, semaphore, NULL);
+	radeon_semaphore_free(rdev, &semaphore, NULL);
 
 	if (fenceA)
 		radeon_fence_unref(&fenceA);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 2d36bdda9327..c43035c5cc3e 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -223,7 +223,6 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 	struct radeon_device *rdev;
 	uint64_t old_start, new_start;
 	struct radeon_fence *fence;
-	struct radeon_semaphore *sem = NULL;
 	int r, ridx;
 
 	rdev = radeon_get_rdev(bo->bdev);
@@ -262,31 +261,12 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
 
 	/* sync other rings */
 	fence = bo->sync_obj;
-	if (fence && fence->ring != ridx
-	    && !radeon_fence_signaled(fence)) {
-		bool sync_to_ring[RADEON_NUM_RINGS] = { };
-		sync_to_ring[fence->ring] = true;
-
-		r = radeon_semaphore_create(rdev, &sem);
-		if (r) {
-			return r;
-		}
-
-		r = radeon_semaphore_sync_rings(rdev, sem, sync_to_ring, ridx);
-		if (r) {
-			radeon_semaphore_free(rdev, sem, NULL);
-			return r;
-		}
-	}
-
-	fence = NULL;
 	r = radeon_copy(rdev, old_start, new_start,
 			new_mem->num_pages * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE), /* GPU pages */
 			&fence);
 	/* FIXME: handle copy error */
 	r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL,
 				      evict, no_wait_reserve, no_wait_gpu, new_mem);
-	radeon_semaphore_free(rdev, sem, fence);
 	radeon_fence_unref(&fence);
 	return r;
 }
-- 
cgit v1.2.3


From 07a713305a2b55d6ec424000f2c5bed1268ac56b Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Sat, 7 Jul 2012 12:11:32 +0200
Subject: drm/radeon: fix ring commit padding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We don't need to pad anything if the number of dwords
written to the ring already matches the requirements.

Fixes some "writting more dword to ring than expected"
warnings.

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_ring.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 0826e77f99ae..674aabac2212 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -272,13 +272,8 @@ int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 
 void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	unsigned count_dw_pad;
-	unsigned i;
-
 	/* We pad to match fetch size */
-	count_dw_pad = (ring->align_mask + 1) -
-		       (ring->wptr & ring->align_mask);
-	for (i = 0; i < count_dw_pad; i++) {
+	while (ring->wptr & ring->align_mask) {
 		radeon_ring_write(ring, ring->nop);
 	}
 	DRM_MEMORYBARRIER();
-- 
cgit v1.2.3


From 2898c348e5caa50b31b9113726dfa45b2dfc3124 Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Thu, 5 Jul 2012 11:55:34 +0200
Subject: drm/radeon: remove ip_pool start/suspend
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The IB pool is in gart memory, so it is completely
superfluous to unpin / repin it on suspend / resume.

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c   | 17 ++++++-----------
 drivers/gpu/drm/radeon/ni.c          | 16 ++++++----------
 drivers/gpu/drm/radeon/r100.c        | 23 ++++++-----------------
 drivers/gpu/drm/radeon/r300.c        | 17 ++++++-----------
 drivers/gpu/drm/radeon/r420.c        | 17 ++++++-----------
 drivers/gpu/drm/radeon/r520.c        | 14 +++++---------
 drivers/gpu/drm/radeon/r600.c        | 17 ++++++-----------
 drivers/gpu/drm/radeon/radeon.h      |  2 --
 drivers/gpu/drm/radeon/radeon_asic.h |  1 -
 drivers/gpu/drm/radeon/radeon_ring.c | 17 +++++++----------
 drivers/gpu/drm/radeon/rs400.c       | 17 ++++++-----------
 drivers/gpu/drm/radeon/rs600.c       | 17 ++++++-----------
 drivers/gpu/drm/radeon/rs690.c       | 17 ++++++-----------
 drivers/gpu/drm/radeon/rv515.c       | 16 ++++++----------
 drivers/gpu/drm/radeon/rv770.c       | 17 ++++++-----------
 drivers/gpu/drm/radeon/si.c          | 16 ++++++----------
 16 files changed, 84 insertions(+), 157 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index eb9a71a7a646..64e06e67facd 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3087,9 +3087,11 @@ static int evergreen_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -3137,7 +3139,6 @@ int evergreen_suspend(struct radeon_device *rdev)
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 
 	r600_audio_fini(rdev);
-	radeon_ib_pool_suspend(rdev);
 	r600_blit_suspend(rdev);
 	r700_cp_stop(rdev);
 	ring->ready = false;
@@ -3224,20 +3225,14 @@ int evergreen_init(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = evergreen_startup(rdev);
 	if (r) {
 		dev_err(rdev->dev, "disabling GPU acceleration\n");
 		r700_cp_fini(rdev);
 		r600_irq_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		evergreen_pcie_gart_fini(rdev);
 		rdev->accel_working = false;
@@ -3264,7 +3259,7 @@ void evergreen_fini(struct radeon_device *rdev)
 	r700_cp_fini(rdev);
 	r600_irq_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	evergreen_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8b1df33c7be9..fe553102df82 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1270,9 +1270,11 @@ static int cayman_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -1313,7 +1315,6 @@ int cayman_resume(struct radeon_device *rdev)
 int cayman_suspend(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
-	radeon_ib_pool_suspend(rdev);
 	radeon_vm_manager_suspend(rdev);
 	r600_blit_suspend(rdev);
 	cayman_cp_enable(rdev, false);
@@ -1391,12 +1392,7 @@ int cayman_init(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
 	r = radeon_vm_manager_init(rdev);
 	if (r) {
 		dev_err(rdev->dev, "vm manager initialization failed (%d).\n", r);
@@ -1410,7 +1406,7 @@ int cayman_init(struct radeon_device *rdev)
 		if (rdev->flags & RADEON_IS_IGP)
 			si_rlc_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_vm_manager_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		cayman_pcie_gart_fini(rdev);
@@ -1441,7 +1437,7 @@ void cayman_fini(struct radeon_device *rdev)
 		si_rlc_fini(rdev);
 	radeon_wb_fini(rdev);
 	radeon_vm_manager_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index d06c8dd8ddfa..9524bd4aca75 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3722,12 +3722,6 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	return r;
 }
 
-void r100_ib_fini(struct radeon_device *rdev)
-{
-	radeon_ib_pool_suspend(rdev);
-	radeon_ib_pool_fini(rdev);
-}
-
 void r100_mc_stop(struct radeon_device *rdev, struct r100_mc_save *save)
 {
 	/* Shutdown CP we shouldn't need to do that but better be safe than
@@ -3887,9 +3881,11 @@ static int r100_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -3930,7 +3926,6 @@ int r100_resume(struct radeon_device *rdev)
 
 int r100_suspend(struct radeon_device *rdev)
 {
-	radeon_ib_pool_suspend(rdev);
 	r100_cp_disable(rdev);
 	radeon_wb_disable(rdev);
 	r100_irq_disable(rdev);
@@ -3943,7 +3938,7 @@ void r100_fini(struct radeon_device *rdev)
 {
 	r100_cp_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_gem_fini(rdev);
 	if (rdev->flags & RADEON_IS_PCI)
 		r100_pci_gart_fini(rdev);
@@ -4050,20 +4045,14 @@ int r100_init(struct radeon_device *rdev)
 	}
 	r100_set_safe_registers(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = r100_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		if (rdev->flags & RADEON_IS_PCI)
 			r100_pci_gart_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 97722a33e513..b396e341a7b8 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -1391,9 +1391,11 @@ static int r300_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -1436,7 +1438,6 @@ int r300_resume(struct radeon_device *rdev)
 
 int r300_suspend(struct radeon_device *rdev)
 {
-	radeon_ib_pool_suspend(rdev);
 	r100_cp_disable(rdev);
 	radeon_wb_disable(rdev);
 	r100_irq_disable(rdev);
@@ -1451,7 +1452,7 @@ void r300_fini(struct radeon_device *rdev)
 {
 	r100_cp_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_gem_fini(rdev);
 	if (rdev->flags & RADEON_IS_PCIE)
 		rv370_pcie_gart_fini(rdev);
@@ -1538,20 +1539,14 @@ int r300_init(struct radeon_device *rdev)
 	}
 	r300_set_reg_safe(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = r300_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		if (rdev->flags & RADEON_IS_PCIE)
 			rv370_pcie_gart_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 99137be7a300..0062938a589c 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -275,9 +275,11 @@ static int r420_startup(struct radeon_device *rdev)
 	}
 	r420_cp_errata_init(rdev);
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -324,7 +326,6 @@ int r420_resume(struct radeon_device *rdev)
 
 int r420_suspend(struct radeon_device *rdev)
 {
-	radeon_ib_pool_suspend(rdev);
 	r420_cp_errata_fini(rdev);
 	r100_cp_disable(rdev);
 	radeon_wb_disable(rdev);
@@ -340,7 +341,7 @@ void r420_fini(struct radeon_device *rdev)
 {
 	r100_cp_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_gem_fini(rdev);
 	if (rdev->flags & RADEON_IS_PCIE)
 		rv370_pcie_gart_fini(rdev);
@@ -438,20 +439,14 @@ int r420_init(struct radeon_device *rdev)
 	}
 	r420_set_reg_safe(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = r420_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		if (rdev->flags & RADEON_IS_PCIE)
 			rv370_pcie_gart_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r520.c b/drivers/gpu/drm/radeon/r520.c
index b5cf8375cd25..6df3e51acb9f 100644
--- a/drivers/gpu/drm/radeon/r520.c
+++ b/drivers/gpu/drm/radeon/r520.c
@@ -203,9 +203,11 @@ static int r520_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -311,20 +313,14 @@ int r520_init(struct radeon_device *rdev)
 		return r;
 	rv515_set_safe_registers(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = r520_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		rv370_pcie_gart_fini(rdev);
 		radeon_agp_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index de4de2dac160..9750f538cc86 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2403,9 +2403,11 @@ int r600_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -2459,7 +2461,6 @@ int r600_resume(struct radeon_device *rdev)
 int r600_suspend(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
-	radeon_ib_pool_suspend(rdev);
 	r600_blit_suspend(rdev);
 	r600_cp_stop(rdev);
 	rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready = false;
@@ -2542,20 +2543,14 @@ int r600_init(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = r600_startup(rdev);
 	if (r) {
 		dev_err(rdev->dev, "disabling GPU acceleration\n");
 		r600_cp_fini(rdev);
 		r600_irq_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		r600_pcie_gart_fini(rdev);
 		rdev->accel_working = false;
@@ -2571,7 +2566,7 @@ void r600_fini(struct radeon_device *rdev)
 	r600_cp_fini(rdev);
 	r600_irq_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	r600_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 44878738bcde..7df76b9cc3af 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -755,8 +755,6 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_pool_init(struct radeon_device *rdev);
 void radeon_ib_pool_fini(struct radeon_device *rdev);
-int radeon_ib_pool_start(struct radeon_device *rdev);
-int radeon_ib_pool_suspend(struct radeon_device *rdev);
 int radeon_ib_ring_tests(struct radeon_device *rdev);
 /* Ring access between begin & end cannot sleep */
 int radeon_ring_index(struct radeon_device *rdev, struct radeon_ring *cp);
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 94c427ab0f5c..f4af24310438 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -103,7 +103,6 @@ int r100_pci_gart_enable(struct radeon_device *rdev);
 void r100_pci_gart_disable(struct radeon_device *rdev);
 int r100_debugfs_mc_info_init(struct radeon_device *rdev);
 int r100_gui_wait_for_idle(struct radeon_device *rdev);
-void r100_ib_fini(struct radeon_device *rdev);
 int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring);
 void r100_irq_disable(struct radeon_device *rdev);
 void r100_mc_stop(struct radeon_device *rdev, struct r100_mc_save *save);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 674aabac2212..087383408a8f 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -129,6 +129,12 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 	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");
@@ -139,21 +145,12 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 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;
 	}
 }
 
-int radeon_ib_pool_start(struct radeon_device *rdev)
-{
-	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->ring_tmp_bo);
-}
-
 int radeon_ib_ring_tests(struct radeon_device *rdev)
 {
 	unsigned i;
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index a464eb5e2df2..aa26076ff468 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -426,9 +426,11 @@ static int rs400_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -470,7 +472,6 @@ int rs400_resume(struct radeon_device *rdev)
 
 int rs400_suspend(struct radeon_device *rdev)
 {
-	radeon_ib_pool_suspend(rdev);
 	r100_cp_disable(rdev);
 	radeon_wb_disable(rdev);
 	r100_irq_disable(rdev);
@@ -482,7 +483,7 @@ void rs400_fini(struct radeon_device *rdev)
 {
 	r100_cp_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_gem_fini(rdev);
 	rs400_gart_fini(rdev);
 	radeon_irq_kms_fini(rdev);
@@ -550,20 +551,14 @@ int rs400_init(struct radeon_device *rdev)
 		return r;
 	r300_set_reg_safe(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = rs400_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		rs400_gart_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		rdev->accel_working = false;
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index e11bc4651784..6dad4e617727 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -907,9 +907,11 @@ static int rs600_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -955,7 +957,6 @@ int rs600_resume(struct radeon_device *rdev)
 
 int rs600_suspend(struct radeon_device *rdev)
 {
-	radeon_ib_pool_suspend(rdev);
 	r600_audio_fini(rdev);
 	r100_cp_disable(rdev);
 	radeon_wb_disable(rdev);
@@ -969,7 +970,7 @@ void rs600_fini(struct radeon_device *rdev)
 	r600_audio_fini(rdev);
 	r100_cp_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_gem_fini(rdev);
 	rs600_gart_fini(rdev);
 	radeon_irq_kms_fini(rdev);
@@ -1037,20 +1038,14 @@ int rs600_init(struct radeon_device *rdev)
 		return r;
 	rs600_set_safe_registers(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = rs600_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		rs600_gart_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		rdev->accel_working = false;
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 159b6a43fda0..0c026b0210d4 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -637,9 +637,11 @@ static int rs690_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -685,7 +687,6 @@ int rs690_resume(struct radeon_device *rdev)
 
 int rs690_suspend(struct radeon_device *rdev)
 {
-	radeon_ib_pool_suspend(rdev);
 	r600_audio_fini(rdev);
 	r100_cp_disable(rdev);
 	radeon_wb_disable(rdev);
@@ -699,7 +700,7 @@ void rs690_fini(struct radeon_device *rdev)
 	r600_audio_fini(rdev);
 	r100_cp_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_gem_fini(rdev);
 	rs400_gart_fini(rdev);
 	radeon_irq_kms_fini(rdev);
@@ -768,20 +769,14 @@ int rs690_init(struct radeon_device *rdev)
 		return r;
 	rs600_set_safe_registers(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = rs690_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		rs400_gart_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		rdev->accel_working = false;
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 7f08cedb5333..01e9155541ea 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -408,9 +408,11 @@ static int rv515_startup(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -469,7 +471,7 @@ void rv515_fini(struct radeon_device *rdev)
 {
 	r100_cp_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_gem_fini(rdev);
 	rv370_pcie_gart_fini(rdev);
 	radeon_agp_fini(rdev);
@@ -543,20 +545,14 @@ int rv515_init(struct radeon_device *rdev)
 		return r;
 	rv515_set_safe_registers(rdev);
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = rv515_startup(rdev);
 	if (r) {
 		/* Somethings want wront with the accel init stop accel */
 		dev_err(rdev->dev, "Disabling GPU acceleration\n");
 		r100_cp_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		rv370_pcie_gart_fini(rdev);
 		radeon_agp_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 7e230f62f0fa..cc0ffb9be2bd 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -951,9 +951,11 @@ static int rv770_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_ring_tests(rdev);
 	if (r)
@@ -994,7 +996,6 @@ int rv770_resume(struct radeon_device *rdev)
 int rv770_suspend(struct radeon_device *rdev)
 {
 	r600_audio_fini(rdev);
-	radeon_ib_pool_suspend(rdev);
 	r600_blit_suspend(rdev);
 	r700_cp_stop(rdev);
 	rdev->ring[RADEON_RING_TYPE_GFX_INDEX].ready = false;
@@ -1075,20 +1076,14 @@ int rv770_init(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
-
 	r = rv770_startup(rdev);
 	if (r) {
 		dev_err(rdev->dev, "disabling GPU acceleration\n");
 		r700_cp_fini(rdev);
 		r600_irq_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		rv770_pcie_gart_fini(rdev);
 		rdev->accel_working = false;
@@ -1103,7 +1098,7 @@ void rv770_fini(struct radeon_device *rdev)
 	r700_cp_fini(rdev);
 	r600_irq_fini(rdev);
 	radeon_wb_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	rv770_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 78c790fec63f..40405d302723 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -3750,9 +3750,11 @@ static int si_startup(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_start(rdev);
-	if (r)
+	r = radeon_ib_pool_init(rdev);
+	if (r) {
+		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
 		return r;
+	}
 
 	r = radeon_ib_test(rdev, RADEON_RING_TYPE_GFX_INDEX, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
 	if (r) {
@@ -3807,7 +3809,6 @@ int si_resume(struct radeon_device *rdev)
 
 int si_suspend(struct radeon_device *rdev)
 {
-	radeon_ib_pool_suspend(rdev);
 	radeon_vm_manager_suspend(rdev);
 #if 0
 	r600_blit_suspend(rdev);
@@ -3900,12 +3901,7 @@ int si_init(struct radeon_device *rdev)
 	if (r)
 		return r;
 
-	r = radeon_ib_pool_init(rdev);
 	rdev->accel_working = true;
-	if (r) {
-		dev_err(rdev->dev, "IB initialization failed (%d).\n", r);
-		rdev->accel_working = false;
-	}
 	r = radeon_vm_manager_init(rdev);
 	if (r) {
 		dev_err(rdev->dev, "vm manager initialization failed (%d).\n", r);
@@ -3918,7 +3914,7 @@ int si_init(struct radeon_device *rdev)
 		si_irq_fini(rdev);
 		si_rlc_fini(rdev);
 		radeon_wb_fini(rdev);
-		r100_ib_fini(rdev);
+		radeon_ib_pool_fini(rdev);
 		radeon_vm_manager_fini(rdev);
 		radeon_irq_kms_fini(rdev);
 		si_pcie_gart_fini(rdev);
@@ -3947,7 +3943,7 @@ void si_fini(struct radeon_device *rdev)
 	si_rlc_fini(rdev);
 	radeon_wb_fini(rdev);
 	radeon_vm_manager_fini(rdev);
-	r100_ib_fini(rdev);
+	radeon_ib_pool_fini(rdev);
 	radeon_irq_kms_fini(rdev);
 	si_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
-- 
cgit v1.2.3


From 45df68035c4964d42ea3850980708ce8674f75b3 Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Fri, 6 Jul 2012 16:22:55 +0200
Subject: drm/radeon: record what is next valid wptr for each ring v4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before emitting any indirect buffer, emit the offset of the next
valid ring content if any. This allow code that want to resume
ring to resume ring right after ib that caused GPU lockup.

v2: use scratch registers instead of storing it into memory
v3: skip over the surface sync for ni and si as well
v4: use SET_CONFIG_REG instead of PACKET0

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c   | 10 +++++++++-
 drivers/gpu/drm/radeon/ni.c          | 13 ++++++++++++-
 drivers/gpu/drm/radeon/r600.c        | 20 ++++++++++++++++++--
 drivers/gpu/drm/radeon/radeon.h      |  1 +
 drivers/gpu/drm/radeon/radeon_ring.c |  4 ++++
 drivers/gpu/drm/radeon/rv770.c       |  4 +++-
 drivers/gpu/drm/radeon/si.c          | 24 +++++++++++++++++++++---
 7 files changed, 68 insertions(+), 8 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index f39b900d46f9..4b8e5c5fcf84 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1368,7 +1368,15 @@ void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
 	radeon_ring_write(ring, 1);
-	/* FIXME: implement */
+
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg - 
+					  PACKET3_SET_CONFIG_REG_START) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	radeon_ring_write(ring,
 #ifdef __BIG_ENDIAN
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index f2afefb44b7c..ddfef8cdd838 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -855,6 +855,15 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
 	radeon_ring_write(ring, 1);
+
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4 + 8;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg - 
+					  PACKET3_SET_CONFIG_REG_START) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	radeon_ring_write(ring,
 #ifdef __BIG_ENDIAN
@@ -981,8 +990,10 @@ static int cayman_cp_start(struct radeon_device *rdev)
 
 static void cayman_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	cayman_cp_enable(rdev, false);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 int cayman_cp_resume(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index c808fa976d2d..3156d251b3c2 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2155,18 +2155,27 @@ int r600_cp_resume(struct radeon_device *rdev)
 void r600_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size)
 {
 	u32 rb_bufsz;
+	int r;
 
 	/* Align ring size */
 	rb_bufsz = drm_order(ring_size / 8);
 	ring_size = (1 << (rb_bufsz + 1)) * 4;
 	ring->ring_size = ring_size;
 	ring->align_mask = 16 - 1;
+
+	r = radeon_scratch_get(rdev, &ring->rptr_save_reg);
+	if (r) {
+		DRM_ERROR("failed to get scratch reg for rptr save (%d).\n", r);
+		ring->rptr_save_reg = 0;
+	}
 }
 
 void r600_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r600_cp_stop(rdev);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 
@@ -2568,7 +2577,14 @@ void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
 
-	/* FIXME: implement */
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg -
+					 PACKET3_SET_CONFIG_REG_OFFSET) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
 	radeon_ring_write(ring,
 #ifdef __BIG_ENDIAN
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 872270c9a0d0..64d39adaad91 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -622,6 +622,7 @@ struct radeon_ring {
 	unsigned		rptr;
 	unsigned		rptr_offs;
 	unsigned		rptr_reg;
+	unsigned		rptr_save_reg;
 	unsigned		wptr;
 	unsigned		wptr_old;
 	unsigned		wptr_reg;
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 087383408a8f..ce8eb9d5af5d 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -451,6 +451,10 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 	count = (ring->ring_size / 4) - ring->ring_free_dw;
 	seq_printf(m, "wptr(0x%04x): 0x%08x\n", ring->wptr_reg, RREG32(ring->wptr_reg));
 	seq_printf(m, "rptr(0x%04x): 0x%08x\n", ring->rptr_reg, RREG32(ring->rptr_reg));
+	if (ring->rptr_save_reg) {
+		seq_printf(m, "rptr next(0x%04x): 0x%08x\n", ring->rptr_save_reg,
+			   RREG32(ring->rptr_save_reg));
+	}
 	seq_printf(m, "driver's copy of the wptr: 0x%08x\n", ring->wptr);
 	seq_printf(m, "driver's copy of the rptr: 0x%08x\n", ring->rptr);
 	seq_printf(m, "%u free dwords in ring\n", ring->ring_free_dw);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index b4b1256fb15b..eb4704e72bdb 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -358,8 +358,10 @@ static int rv770_cp_load_microcode(struct radeon_device *rdev)
 
 void r700_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	r700_cp_stop(rdev);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 /*
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index f61b550f9efd..53e313b05751 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1765,6 +1765,14 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
 	u32 header;
 
+	if (ring->rptr_save_reg) {
+		uint32_t next_rptr = ring->wptr + 3 + 4 + 8;
+		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(ring, ((ring->rptr_save_reg - 
+					  PACKET3_SET_CONFIG_REG_START) >> 2));
+		radeon_ring_write(ring, next_rptr);
+	}
+
 	if (ib->is_const_ib)
 		header = PACKET3(PACKET3_INDIRECT_BUFFER_CONST, 2);
 	else
@@ -1917,10 +1925,20 @@ static int si_cp_start(struct radeon_device *rdev)
 
 static void si_cp_fini(struct radeon_device *rdev)
 {
+	struct radeon_ring *ring;
 	si_cp_enable(rdev, false);
-	radeon_ring_fini(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
-	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX]);
-	radeon_ring_fini(rdev, &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX]);
+
+	ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
+
+	ring = &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX];
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
+
+	ring = &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX];
+	radeon_ring_fini(rdev, ring);
+	radeon_scratch_free(rdev, ring->rptr_save_reg);
 }
 
 static int si_cp_resume(struct radeon_device *rdev)
-- 
cgit v1.2.3


From 55d7c22192becd0ec827a6901899ff56fa985658 Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Mon, 9 Jul 2012 11:52:44 +0200
Subject: drm/radeon: implement ring saving on reset v4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Try to save whatever is on the rings when
we encounter an lockup.

v2: Fix spelling error. Free saved ring data if reset fails.
    Add documentation for the new functions.
v3: Some more spelling fixes
v4: It doesn't make sense to save anything if all fences
    are signaled

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon.h        |  4 ++
 drivers/gpu/drm/radeon/radeon_device.c | 48 ++++++++++++++++----
 drivers/gpu/drm/radeon/radeon_ring.c   | 82 ++++++++++++++++++++++++++++++++++
 3 files changed, 126 insertions(+), 8 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 64d39adaad91..6715e4c695fa 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -768,6 +768,10 @@ 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);
 void radeon_ring_lockup_update(struct radeon_ring *ring);
 bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring);
+unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring,
+			    uint32_t **data);
+int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring,
+			unsigned size, uint32_t *data);
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ring_size,
 		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
 		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index bbd09718e956..0302a9f3e674 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -996,7 +996,12 @@ int radeon_resume_kms(struct drm_device *dev)
 
 int radeon_gpu_reset(struct radeon_device *rdev)
 {
-	int r;
+	unsigned ring_sizes[RADEON_NUM_RINGS];
+	uint32_t *ring_data[RADEON_NUM_RINGS];
+
+	bool saved = false;
+
+	int i, r;
 	int resched;
 
 	down_write(&rdev->exclusive_lock);
@@ -1005,20 +1010,47 @@ int radeon_gpu_reset(struct radeon_device *rdev)
 	resched = ttm_bo_lock_delayed_workqueue(&rdev->mman.bdev);
 	radeon_suspend(rdev);
 
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		ring_sizes[i] = radeon_ring_backup(rdev, &rdev->ring[i],
+						   &ring_data[i]);
+		if (ring_sizes[i]) {
+			saved = true;
+			dev_info(rdev->dev, "Saved %d dwords of commands "
+				 "on ring %d.\n", ring_sizes[i], i);
+		}
+	}
+
+retry:
 	r = radeon_asic_reset(rdev);
 	if (!r) {
-		dev_info(rdev->dev, "GPU reset succeed\n");
+		dev_info(rdev->dev, "GPU reset succeeded, trying to resume\n");
 		radeon_resume(rdev);
+	}
 
-		r = radeon_ib_ring_tests(rdev);
-		if (r)
-			DRM_ERROR("ib ring test failed (%d).\n", r);
+	radeon_restore_bios_scratch_regs(rdev);
+	drm_helper_resume_force_mode(rdev->ddev);
 
-		radeon_restore_bios_scratch_regs(rdev);
-		drm_helper_resume_force_mode(rdev->ddev);
-		ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
+	if (!r) {
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			radeon_ring_restore(rdev, &rdev->ring[i],
+					    ring_sizes[i], ring_data[i]);
+		}
+
+		r = radeon_ib_ring_tests(rdev);
+		if (r) {
+			dev_err(rdev->dev, "ib ring test failed (%d).\n", r);
+			if (saved) {
+				radeon_suspend(rdev);
+				goto retry;
+			}
+		}
+	} else {
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			kfree(ring_data[i]);
+		}
 	}
 
+	ttm_bo_unlock_delayed_workqueue(&rdev->mman.bdev, resched);
 	if (r) {
 		/* bad news, how to tell it to userspace ? */
 		dev_info(rdev->dev, "GPU reset failed\n");
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index ce8eb9d5af5d..75cbe4641138 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -362,6 +362,88 @@ bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 	return false;
 }
 
+/**
+ * radeon_ring_backup - Back up the content of a ring
+ *
+ * @rdev: radeon_device pointer
+ * @ring: the ring we want to back up
+ *
+ * Saves all unprocessed commits from a ring, returns the number of dwords saved.
+ */
+unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring,
+			    uint32_t **data)
+{
+	unsigned size, ptr, i;
+	int ridx = radeon_ring_index(rdev, ring);
+
+	/* just in case lock the ring */
+	mutex_lock(&rdev->ring_lock);
+	*data = NULL;
+
+	if (ring->ring_obj == NULL || !ring->rptr_save_reg) {
+		mutex_unlock(&rdev->ring_lock);
+		return 0;
+	}
+
+	/* it doesn't make sense to save anything if all fences are signaled */
+	if (!radeon_fence_count_emitted(rdev, ridx)) {
+		mutex_unlock(&rdev->ring_lock);
+		return 0;
+	}
+
+	/* calculate the number of dw on the ring */
+	ptr = RREG32(ring->rptr_save_reg);
+	size = ring->wptr + (ring->ring_size / 4);
+	size -= ptr;
+	size &= ring->ptr_mask;
+	if (size == 0) {
+		mutex_unlock(&rdev->ring_lock);
+		return 0;
+	}
+
+	/* and then save the content of the ring */
+	*data = kmalloc(size * 4, GFP_KERNEL);
+	for (i = 0; i < size; ++i) {
+		(*data)[i] = ring->ring[ptr++];
+		ptr &= ring->ptr_mask;
+	}
+
+	mutex_unlock(&rdev->ring_lock);
+	return size;
+}
+
+/**
+ * radeon_ring_restore - append saved commands to the ring again
+ *
+ * @rdev: radeon_device pointer
+ * @ring: ring to append commands to
+ * @size: number of dwords we want to write
+ * @data: saved commands
+ *
+ * Allocates space on the ring and restore the previously saved commands.
+ */
+int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring,
+			unsigned size, uint32_t *data)
+{
+	int i, r;
+
+	if (!size || !data)
+		return 0;
+
+	/* restore the saved ring content */
+	r = radeon_ring_lock(rdev, ring, size);
+	if (r)
+		return r;
+
+	for (i = 0; i < size; ++i) {
+		radeon_ring_write(ring, data[i]);
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	kfree(data);
+	return 0;
+}
+
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size,
 		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
 		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop)
-- 
cgit v1.2.3


From 4ef72566f1035fef5abd0913100d13746e066ee3 Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Fri, 13 Jul 2012 13:06:00 +0200
Subject: drm/radeon: fix const IB handling v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Const IBs are executed on the CE not the CP, so we can't
fence them in the normal way.

So submit them directly before the IB instead, just as
the documentation says.

v2: keep the extra documentation

Signed-off-by: Christian König <deathsimple@vodafone.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r100.c        |  2 +-
 drivers/gpu/drm/radeon/r600.c        |  2 +-
 drivers/gpu/drm/radeon/radeon.h      |  3 ++-
 drivers/gpu/drm/radeon/radeon_cs.c   | 25 ++++++++++++-------------
 drivers/gpu/drm/radeon/radeon_ring.c | 10 +++++++++-
 5 files changed, 25 insertions(+), 17 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index e0f5ae895f07..4ee5a74dac22 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -3693,7 +3693,7 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	ib.ptr[6] = PACKET2(0);
 	ib.ptr[7] = PACKET2(0);
 	ib.length_dw = 8;
-	r = radeon_ib_schedule(rdev, &ib);
+	r = radeon_ib_schedule(rdev, &ib, NULL);
 	if (r) {
 		radeon_scratch_free(rdev, scratch);
 		radeon_ib_free(rdev, &ib);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 3156d251b3c2..c2e506919995 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2619,7 +2619,7 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	ib.ptr[1] = ((scratch - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
 	ib.ptr[2] = 0xDEADBEEF;
 	ib.length_dw = 3;
-	r = radeon_ib_schedule(rdev, &ib);
+	r = radeon_ib_schedule(rdev, &ib, NULL);
 	if (r) {
 		radeon_scratch_free(rdev, scratch);
 		radeon_ib_free(rdev, &ib);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 2cb355bf2725..2d7f06c85336 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -751,7 +751,8 @@ struct si_rlc {
 int radeon_ib_get(struct radeon_device *rdev, int ring,
 		  struct radeon_ib *ib, unsigned size);
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib);
-int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib);
+int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
+		       struct radeon_ib *const_ib);
 int radeon_ib_pool_init(struct radeon_device *rdev);
 void radeon_ib_pool_fini(struct radeon_device *rdev);
 int radeon_ib_ring_tests(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 553da67a4cdd..8a4c49ef0cc4 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -354,7 +354,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
 	}
 	radeon_cs_sync_rings(parser);
 	parser->ib.vm_id = 0;
-	r = radeon_ib_schedule(rdev, &parser->ib);
+	r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	if (r) {
 		DRM_ERROR("Failed to schedule IB !\n");
 	}
@@ -452,25 +452,24 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
 	}
 	radeon_cs_sync_rings(parser);
 
+	parser->ib.vm_id = vm->id;
+	/* ib pool is bind at 0 in virtual address space,
+	 * so gpu_addr is the offset inside the pool bo
+	 */
+	parser->ib.gpu_addr = parser->ib.sa_bo->soffset;
+
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
 		parser->const_ib.vm_id = vm->id;
-		/* ib pool is bind at 0 in virtual address space to gpu_addr is the
-		 * offset inside the pool bo
+		/* ib pool is bind at 0 in virtual address space,
+		 * so gpu_addr is the offset inside the pool bo
 		 */
 		parser->const_ib.gpu_addr = parser->const_ib.sa_bo->soffset;
-		r = radeon_ib_schedule(rdev, &parser->const_ib);
-		if (r)
-			goto out;
+		r = radeon_ib_schedule(rdev, &parser->ib, &parser->const_ib);
+	} else {
+		r = radeon_ib_schedule(rdev, &parser->ib, NULL);
 	}
 
-	parser->ib.vm_id = vm->id;
-	/* ib pool is bind at 0 in virtual address space to gpu_addr is the
-	 * offset inside the pool bo
-	 */
-	parser->ib.gpu_addr = parser->ib.sa_bo->soffset;
-	parser->ib.is_const_ib = false;
-	r = radeon_ib_schedule(rdev, &parser->ib);
 out:
 	if (!r) {
 		if (vm->fence) {
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 75cbe4641138..c48c35403774 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -74,7 +74,8 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 	radeon_fence_unref(&ib->fence);
 }
 
-int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *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];
 	bool need_sync = false;
@@ -105,6 +106,10 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 	if (!need_sync) {
 		radeon_semaphore_free(rdev, &ib->semaphore, NULL);
 	}
+	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) {
@@ -112,6 +117,9 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 		radeon_ring_unlock_undo(rdev, ring);
 		return r;
 	}
+	if (const_ib) {
+		const_ib->fence = radeon_fence_ref(ib->fence);
+	}
 	radeon_ring_unlock_commit(rdev, ring);
 	return 0;
 }
-- 
cgit v1.2.3


From 8b25ed3482885e5f1dc65ace796e90f879d76c52 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 17 Jul 2012 14:02:30 -0400
Subject: drm/radeon: remove radeon_ring_index()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just store the index in the ring structure.
Idea taken from one of Jerome's wip rptr patches.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/radeon/r600.c          | 11 +++++------
 drivers/gpu/drm/radeon/radeon.h        |  2 +-
 drivers/gpu/drm/radeon/radeon_device.c |  4 ++++
 drivers/gpu/drm/radeon/radeon_ring.c   | 20 ++-----------------
 drivers/gpu/drm/radeon/radeon_test.c   | 35 +++++++++++++++-------------------
 5 files changed, 27 insertions(+), 45 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index c2e506919995..9f24a804f6ea 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2198,7 +2198,7 @@ int r600_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	uint32_t scratch;
 	uint32_t tmp = 0;
-	unsigned i, ridx = radeon_ring_index(rdev, ring);
+	unsigned i;
 	int r;
 
 	r = radeon_scratch_get(rdev, &scratch);
@@ -2209,7 +2209,7 @@ int r600_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	WREG32(scratch, 0xCAFEDEAD);
 	r = radeon_ring_lock(rdev, ring, 3);
 	if (r) {
-		DRM_ERROR("radeon: cp failed to lock ring %d (%d).\n", ridx, r);
+		DRM_ERROR("radeon: cp failed to lock ring %d (%d).\n", ring->idx, r);
 		radeon_scratch_free(rdev, scratch);
 		return r;
 	}
@@ -2224,10 +2224,10 @@ int r600_ring_test(struct radeon_device *rdev, struct radeon_ring *ring)
 		DRM_UDELAY(1);
 	}
 	if (i < rdev->usec_timeout) {
-		DRM_INFO("ring test on %d succeeded in %d usecs\n", ridx, i);
+		DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
 	} else {
 		DRM_ERROR("radeon: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
-			  ridx, scratch, tmp);
+			  ring->idx, scratch, tmp);
 		r = -EINVAL;
 	}
 	radeon_scratch_free(rdev, scratch);
@@ -2602,7 +2602,6 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	uint32_t tmp = 0;
 	unsigned i;
 	int r;
-	int ring_index = radeon_ring_index(rdev, ring);
 
 	r = radeon_scratch_get(rdev, &scratch);
 	if (r) {
@@ -2610,7 +2609,7 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 		return r;
 	}
 	WREG32(scratch, 0xCAFEDEAD);
-	r = radeon_ib_get(rdev, ring_index, &ib, 256);
+	r = radeon_ib_get(rdev, ring->idx, &ib, 256);
 	if (r) {
 		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
 		return r;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 2d7f06c85336..be454725c377 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -638,6 +638,7 @@ struct radeon_ring {
 	u32			ptr_reg_shift;
 	u32			ptr_reg_mask;
 	u32			nop;
+	u32			idx;
 };
 
 /*
@@ -757,7 +758,6 @@ int radeon_ib_pool_init(struct radeon_device *rdev);
 void radeon_ib_pool_fini(struct radeon_device *rdev);
 int radeon_ib_ring_tests(struct radeon_device *rdev);
 /* Ring access between begin & end cannot sleep */
-int radeon_ring_index(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *cp);
 int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ndw);
 int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ndw);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 0302a9f3e674..6c534f42ef7b 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -721,6 +721,10 @@ int radeon_device_init(struct radeon_device *rdev,
 	rdev->usec_timeout = RADEON_MAX_USEC_TIMEOUT;
 	rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
 	rdev->accel_working = false;
+	/* set up ring ids */
+	for (i = 0; i < RADEON_NUM_RINGS; i++) {
+		rdev->ring[i].idx = i;
+	}
 
 	DRM_INFO("initializing kernel modesetting (%s 0x%04X:0x%04X 0x%04X:0x%04X).\n",
 		radeon_family_name[rdev->family], pdev->vendor, pdev->device,
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index c48c35403774..c5828b909024 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -207,21 +207,6 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
 	ring->ring_free_dw--;
 }
 
-int radeon_ring_index(struct radeon_device *rdev, struct radeon_ring *ring)
-{
-	/* r1xx-r5xx only has CP ring */
-	if (rdev->family < CHIP_R600)
-		return RADEON_RING_TYPE_GFX_INDEX;
-
-	if (rdev->family >= CHIP_CAYMAN) {
-		if (ring == &rdev->ring[CAYMAN_RING_TYPE_CP1_INDEX])
-			return CAYMAN_RING_TYPE_CP1_INDEX;
-		else if (ring == &rdev->ring[CAYMAN_RING_TYPE_CP2_INDEX])
-			return CAYMAN_RING_TYPE_CP2_INDEX;
-	}
-	return RADEON_RING_TYPE_GFX_INDEX;
-}
-
 void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	u32 rptr;
@@ -253,7 +238,7 @@ 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_locked(rdev, radeon_ring_index(rdev, ring));
+		r = radeon_fence_wait_next_locked(rdev, ring->idx);
 		if (r)
 			return r;
 	}
@@ -382,7 +367,6 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring
 			    uint32_t **data)
 {
 	unsigned size, ptr, i;
-	int ridx = radeon_ring_index(rdev, ring);
 
 	/* just in case lock the ring */
 	mutex_lock(&rdev->ring_lock);
@@ -394,7 +378,7 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring
 	}
 
 	/* it doesn't make sense to save anything if all fences are signaled */
-	if (!radeon_fence_count_emitted(rdev, ridx)) {
+	if (!radeon_fence_count_emitted(rdev, ring->idx)) {
 		mutex_unlock(&rdev->ring_lock);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index a94f66fb3b13..7c16540c10ff 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -229,8 +229,6 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 {
 	struct radeon_fence *fence1 = NULL, *fence2 = NULL;
 	struct radeon_semaphore *semaphore = NULL;
-	int ridxA = radeon_ring_index(rdev, ringA);
-	int ridxB = radeon_ring_index(rdev, ringB);
 	int r;
 
 	r = radeon_semaphore_create(rdev, &semaphore);
@@ -241,18 +239,18 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 
 	r = radeon_ring_lock(rdev, ringA, 64);
 	if (r) {
-		DRM_ERROR("Failed to lock ring A %d\n", ridxA);
+		DRM_ERROR("Failed to lock ring A %d\n", ringA->idx);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_wait(rdev, ridxA, semaphore);
-	r = radeon_fence_emit(rdev, &fence1, ridxA);
+	radeon_semaphore_emit_wait(rdev, ringA->idx, semaphore);
+	r = radeon_fence_emit(rdev, &fence1, ringA->idx);
 	if (r) {
 		DRM_ERROR("Failed to emit fence 1\n");
 		radeon_ring_unlock_undo(rdev, ringA);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_wait(rdev, ridxA, semaphore);
-	r = radeon_fence_emit(rdev, &fence2, ridxA);
+	radeon_semaphore_emit_wait(rdev, ringA->idx, semaphore);
+	r = radeon_fence_emit(rdev, &fence2, ringA->idx);
 	if (r) {
 		DRM_ERROR("Failed to emit fence 2\n");
 		radeon_ring_unlock_undo(rdev, ringA);
@@ -272,7 +270,7 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 		DRM_ERROR("Failed to lock ring B %p\n", ringB);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_signal(rdev, ridxB, semaphore);
+	radeon_semaphore_emit_signal(rdev, ringB->idx, semaphore);
 	radeon_ring_unlock_commit(rdev, ringB);
 
 	r = radeon_fence_wait(fence1, false);
@@ -293,7 +291,7 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 		DRM_ERROR("Failed to lock ring B %p\n", ringB);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_signal(rdev, ridxB, semaphore);
+	radeon_semaphore_emit_signal(rdev, ringB->idx, semaphore);
 	radeon_ring_unlock_commit(rdev, ringB);
 
 	r = radeon_fence_wait(fence2, false);
@@ -322,9 +320,6 @@ void radeon_test_ring_sync2(struct radeon_device *rdev,
 {
 	struct radeon_fence *fenceA = NULL, *fenceB = NULL;
 	struct radeon_semaphore *semaphore = NULL;
-	int ridxA = radeon_ring_index(rdev, ringA);
-	int ridxB = radeon_ring_index(rdev, ringB);
-	int ridxC = radeon_ring_index(rdev, ringC);
 	bool sigA, sigB;
 	int i, r;
 
@@ -336,11 +331,11 @@ void radeon_test_ring_sync2(struct radeon_device *rdev,
 
 	r = radeon_ring_lock(rdev, ringA, 64);
 	if (r) {
-		DRM_ERROR("Failed to lock ring A %d\n", ridxA);
+		DRM_ERROR("Failed to lock ring A %d\n", ringA->idx);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_wait(rdev, ridxA, semaphore);
-	r = radeon_fence_emit(rdev, &fenceA, ridxA);
+	radeon_semaphore_emit_wait(rdev, ringA->idx, semaphore);
+	r = radeon_fence_emit(rdev, &fenceA, ringA->idx);
 	if (r) {
 		DRM_ERROR("Failed to emit sync fence 1\n");
 		radeon_ring_unlock_undo(rdev, ringA);
@@ -350,11 +345,11 @@ void radeon_test_ring_sync2(struct radeon_device *rdev,
 
 	r = radeon_ring_lock(rdev, ringB, 64);
 	if (r) {
-		DRM_ERROR("Failed to lock ring B %d\n", ridxB);
+		DRM_ERROR("Failed to lock ring B %d\n", ringB->idx);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_wait(rdev, ridxB, semaphore);
-	r = radeon_fence_emit(rdev, &fenceB, ridxB);
+	radeon_semaphore_emit_wait(rdev, ringB->idx, semaphore);
+	r = radeon_fence_emit(rdev, &fenceB, ringB->idx);
 	if (r) {
 		DRM_ERROR("Failed to create sync fence 2\n");
 		radeon_ring_unlock_undo(rdev, ringB);
@@ -378,7 +373,7 @@ void radeon_test_ring_sync2(struct radeon_device *rdev,
 		DRM_ERROR("Failed to lock ring B %p\n", ringC);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_signal(rdev, ridxC, semaphore);
+	radeon_semaphore_emit_signal(rdev, ringC->idx, semaphore);
 	radeon_ring_unlock_commit(rdev, ringC);
 
 	for (i = 0; i < 30; ++i) {
@@ -404,7 +399,7 @@ void radeon_test_ring_sync2(struct radeon_device *rdev,
 		DRM_ERROR("Failed to lock ring B %p\n", ringC);
 		goto out_cleanup;
 	}
-	radeon_semaphore_emit_signal(rdev, ridxC, semaphore);
+	radeon_semaphore_emit_signal(rdev, ringC->idx, semaphore);
 	radeon_ring_unlock_commit(rdev, ringC);
 
 	mdelay(1000);
-- 
cgit v1.2.3


From 89d35807fb0fe53b84e88e759cc39107a6195e5f Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 17 Jul 2012 14:02:31 -0400
Subject: drm/radeon: update rptr saving logic for memory buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for using memory buffers rather than
scratch registers.  Some rings may not be able to
write to scratch registers.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/radeon/evergreen.c   | 10 +++++++++-
 drivers/gpu/drm/radeon/r600.c        | 20 +++++++++++++++-----
 drivers/gpu/drm/radeon/radeon.h      |  5 +++++
 drivers/gpu/drm/radeon/radeon_ring.c | 31 +++++++++++++++++++++++++++++--
 drivers/gpu/drm/radeon/si.c          | 10 +++++++++-
 5 files changed, 67 insertions(+), 9 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 4b8e5c5fcf84..870009ad5f56 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1364,17 +1364,25 @@ void evergreen_mc_program(struct radeon_device *rdev)
 void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
+	u32 next_rptr;
 
 	/* set to DX10/11 mode */
 	radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));
 	radeon_ring_write(ring, 1);
 
 	if (ring->rptr_save_reg) {
-		uint32_t next_rptr = ring->wptr + 3 + 4;
+		next_rptr = ring->wptr + 3 + 4;
 		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
 		radeon_ring_write(ring, ((ring->rptr_save_reg - 
 					  PACKET3_SET_CONFIG_REG_START) >> 2));
 		radeon_ring_write(ring, next_rptr);
+	} else if (rdev->wb.enabled) {
+		next_rptr = ring->wptr + 5 + 4;
+		radeon_ring_write(ring, PACKET3(PACKET3_MEM_WRITE, 3));
+		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+		radeon_ring_write(ring, (upper_32_bits(ring->next_rptr_gpu_addr) & 0xff) | (1 << 18));
+		radeon_ring_write(ring, next_rptr);
+		radeon_ring_write(ring, 0);
 	}
 
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 9f24a804f6ea..c5b2e9069362 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2163,10 +2163,12 @@ void r600_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsign
 	ring->ring_size = ring_size;
 	ring->align_mask = 16 - 1;
 
-	r = radeon_scratch_get(rdev, &ring->rptr_save_reg);
-	if (r) {
-		DRM_ERROR("failed to get scratch reg for rptr save (%d).\n", r);
-		ring->rptr_save_reg = 0;
+	if (radeon_ring_supports_scratch_reg(rdev, ring)) {
+		r = radeon_scratch_get(rdev, &ring->rptr_save_reg);
+		if (r) {
+			DRM_ERROR("failed to get scratch reg for rptr save (%d).\n", r);
+			ring->rptr_save_reg = 0;
+		}
 	}
 }
 
@@ -2576,13 +2578,21 @@ void r600_fini(struct radeon_device *rdev)
 void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 {
 	struct radeon_ring *ring = &rdev->ring[ib->ring];
+	u32 next_rptr;
 
 	if (ring->rptr_save_reg) {
-		uint32_t next_rptr = ring->wptr + 3 + 4;
+		next_rptr = ring->wptr + 3 + 4;
 		radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
 		radeon_ring_write(ring, ((ring->rptr_save_reg -
 					 PACKET3_SET_CONFIG_REG_OFFSET) >> 2));
 		radeon_ring_write(ring, next_rptr);
+	} else if (rdev->wb.enabled) {
+		next_rptr = ring->wptr + 5 + 4;
+		radeon_ring_write(ring, PACKET3(PACKET3_MEM_WRITE, 3));
+		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+		radeon_ring_write(ring, (upper_32_bits(ring->next_rptr_gpu_addr) & 0xff) | (1 << 18));
+		radeon_ring_write(ring, next_rptr);
+		radeon_ring_write(ring, 0);
 	}
 
 	radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index be454725c377..5431af292408 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -623,6 +623,8 @@ struct radeon_ring {
 	unsigned		rptr_offs;
 	unsigned		rptr_reg;
 	unsigned		rptr_save_reg;
+	u64			next_rptr_gpu_addr;
+	volatile u32		*next_rptr_cpu_addr;
 	unsigned		wptr;
 	unsigned		wptr_old;
 	unsigned		wptr_reg;
@@ -758,6 +760,8 @@ int radeon_ib_pool_init(struct radeon_device *rdev);
 void radeon_ib_pool_fini(struct radeon_device *rdev);
 int radeon_ib_ring_tests(struct radeon_device *rdev);
 /* Ring access between begin & end cannot sleep */
+bool radeon_ring_supports_scratch_reg(struct radeon_device *rdev,
+				      struct radeon_ring *ring);
 void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *cp);
 int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ndw);
 int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ndw);
@@ -871,6 +875,7 @@ struct radeon_wb {
 };
 
 #define RADEON_WB_SCRATCH_OFFSET 0
+#define RADEON_WB_RING0_NEXT_RPTR 256
 #define RADEON_WB_CP_RPTR_OFFSET 1024
 #define RADEON_WB_CP1_RPTR_OFFSET 1280
 #define RADEON_WB_CP2_RPTR_OFFSET 1536
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index c5828b909024..c1efde6d53d3 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -207,6 +207,19 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
 	ring->ring_free_dw--;
 }
 
+bool radeon_ring_supports_scratch_reg(struct radeon_device *rdev,
+				      struct radeon_ring *ring)
+{
+	switch (ring->idx) {
+	case RADEON_RING_TYPE_GFX_INDEX:
+	case CAYMAN_RING_TYPE_CP1_INDEX:
+	case CAYMAN_RING_TYPE_CP2_INDEX:
+		return true;
+	default:
+		return false;
+	}
+}
+
 void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	u32 rptr;
@@ -372,7 +385,7 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring
 	mutex_lock(&rdev->ring_lock);
 	*data = NULL;
 
-	if (ring->ring_obj == NULL || !ring->rptr_save_reg) {
+	if (ring->ring_obj == NULL) {
 		mutex_unlock(&rdev->ring_lock);
 		return 0;
 	}
@@ -384,7 +397,16 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring
 	}
 
 	/* calculate the number of dw on the ring */
-	ptr = RREG32(ring->rptr_save_reg);
+	if (ring->rptr_save_reg)
+		ptr = RREG32(ring->rptr_save_reg);
+	else if (rdev->wb.enabled)
+		ptr = le32_to_cpu(*ring->next_rptr_cpu_addr);
+	else {
+		/* no way to read back the next rptr */
+		mutex_unlock(&rdev->ring_lock);
+		return 0;
+	}
+
 	size = ring->wptr + (ring->ring_size / 4);
 	size -= ptr;
 	size &= ring->ptr_mask;
@@ -478,6 +500,11 @@ 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 (rdev->wb.enabled) {
+		u32 index = RADEON_WB_RING0_NEXT_RPTR + (ring->idx * 4);
+		ring->next_rptr_gpu_addr = rdev->wb.gpu_addr + index;
+		ring->next_rptr_cpu_addr = &rdev->wb.wb[index/4];
+	}
 	if (radeon_debugfs_ring_init(rdev, ring)) {
 		DRM_ERROR("Failed to register debugfs file for rings !\n");
 	}
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 2b12cae52b29..7c3e330c7b59 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -1772,12 +1772,20 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 
 		header = PACKET3(PACKET3_INDIRECT_BUFFER_CONST, 2);
 	} else {
+		u32 next_rptr;
 		if (ring->rptr_save_reg) {
-			uint32_t next_rptr = ring->wptr + 3 + 4 + 8;
+			next_rptr = ring->wptr + 3 + 4 + 8;
 			radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
 			radeon_ring_write(ring, ((ring->rptr_save_reg -
 						  PACKET3_SET_CONFIG_REG_START) >> 2));
 			radeon_ring_write(ring, next_rptr);
+		} else if (rdev->wb.enabled) {
+			next_rptr = ring->wptr + 5 + 4 + 8;
+			radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+			radeon_ring_write(ring, (1 << 8));
+			radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+			radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+			radeon_ring_write(ring, next_rptr);
 		}
 
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
-- 
cgit v1.2.3


From 75923280e580b76463a5572da457faa994a8b31d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 17 Jul 2012 14:02:38 -0400
Subject: drm/radeon: document radeon_ring.c (v4)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adds documentation to most of the functions in
radeon_ring.c

v2: adjust per Christian's suggestions
v3: adjust per Christian's latest patches
v4: adjust per my latest changes

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/radeon/radeon_ring.c | 208 ++++++++++++++++++++++++++++++++++-
 1 file changed, 205 insertions(+), 3 deletions(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index c1efde6d53d3..f2fc25de0b2f 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -35,10 +35,28 @@
 #include "atom.h"
 
 /*
- * IB.
+ * 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.
  */
 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, unsigned size)
 {
@@ -67,6 +85,14 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
 	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);
@@ -74,6 +100,26 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 	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)
 {
@@ -124,6 +170,15 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib,
 	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;
@@ -150,6 +205,14 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 	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) {
@@ -159,6 +222,16 @@ void radeon_ib_pool_fini(struct radeon_device *rdev)
 	}
 }
 
+/**
+ * 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;
@@ -190,10 +263,28 @@ int radeon_ib_ring_tests(struct radeon_device *rdev)
 }
 
 /*
- * Ring.
+ * Rings
+ * Most engines on the GPU are fed via ring buffers.  Ring
+ * buffers are areas of GPU accessible memory that the host
+ * writes commands into and the GPU reads commands out of.
+ * There is a rptr (read pointer) that determines where the
+ * GPU is currently reading, and a wptr (write pointer)
+ * which determines where the host has written.  When the
+ * pointers are equal, the ring is idle.  When the host
+ * writes commands to the ring buffer, it increments the
+ * wptr.  The GPU then starts fetching commands and executes
+ * them until the pointers are equal again.
  */
 int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
 
+/**
+ * radeon_ring_write - write a value to the ring
+ *
+ * @ring: radeon_ring structure holding ring information
+ * @v: dword (dw) value to write
+ *
+ * Write a value to the requested ring buffer (all asics).
+ */
 void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
 {
 #if DRM_DEBUG_CODE
@@ -207,6 +298,16 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
 	ring->ring_free_dw--;
 }
 
+/**
+ * radeon_ring_supports_scratch_reg - check if the ring supports
+ * writing to scratch registers
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Check if a specific ring supports writing to scratch registers (all asics).
+ * Returns true if the ring supports writing to scratch regs, false if not.
+ */
 bool radeon_ring_supports_scratch_reg(struct radeon_device *rdev,
 				      struct radeon_ring *ring)
 {
@@ -220,6 +321,14 @@ bool radeon_ring_supports_scratch_reg(struct radeon_device *rdev,
 	}
 }
 
+/**
+ * radeon_ring_free_size - update the free size
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Update the free dw slots in the ring buffer (all asics).
+ */
 void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	u32 rptr;
@@ -238,7 +347,16 @@ void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *ring)
 	}
 }
 
-
+/**
+ * radeon_ring_alloc - allocate space on the ring buffer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ * @ndw: number of dwords to allocate in the ring buffer
+ *
+ * Allocate @ndw dwords in the ring buffer (all asics).
+ * Returns 0 on success, error on failure.
+ */
 int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ndw)
 {
 	int r;
@@ -260,6 +378,17 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsi
 	return 0;
 }
 
+/**
+ * radeon_ring_lock - lock the ring and allocate space on it
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ * @ndw: number of dwords to allocate in the ring buffer
+ *
+ * Lock the ring and allocate @ndw dwords in the ring buffer
+ * (all asics).
+ * Returns 0 on success, error on failure.
+ */
 int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ndw)
 {
 	int r;
@@ -273,6 +402,16 @@ int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	return 0;
 }
 
+/**
+ * radeon_ring_commit - tell the GPU to execute the new
+ * commands on the ring buffer
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * 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)
 {
 	/* We pad to match fetch size */
@@ -284,23 +423,55 @@ void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring)
 	(void)RREG32(ring->wptr_reg);
 }
 
+/**
+ * radeon_ring_unlock_commit - tell the GPU to execute the new
+ * commands on the ring buffer and unlock it
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Call radeon_ring_commit() then unlock the ring (all asics).
+ */
 void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	radeon_ring_commit(rdev, ring);
 	mutex_unlock(&rdev->ring_lock);
 }
 
+/**
+ * radeon_ring_undo - reset the wptr
+ *
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Reset the driver's copy of the wtpr (all asics).
+ */
 void radeon_ring_undo(struct radeon_ring *ring)
 {
 	ring->wptr = ring->wptr_old;
 }
 
+/**
+ * radeon_ring_unlock_undo - reset the wptr and unlock the ring
+ *
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Call radeon_ring_undo() then unlock the ring (all asics).
+ */
 void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	radeon_ring_undo(ring);
 	mutex_unlock(&rdev->ring_lock);
 }
 
+/**
+ * radeon_ring_force_activity - add some nop packets to the ring
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Add some nop packets to the ring to force activity (all asics).
+ * Used for lockup detection to see if the rptr is advancing.
+ */
 void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	int r;
@@ -315,6 +486,13 @@ void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *
 	}
 }
 
+/**
+ * radeon_ring_force_activity - update lockup variables
+ *
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Update the last rptr value and timestamp (all asics).
+ */
 void radeon_ring_lockup_update(struct radeon_ring *ring)
 {
 	ring->last_rptr = ring->rptr;
@@ -458,6 +636,22 @@ int radeon_ring_restore(struct radeon_device *rdev, struct radeon_ring *ring,
 	return 0;
 }
 
+/**
+ * radeon_ring_init - init driver ring struct.
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ * @ring_size: size of the ring
+ * @rptr_offs: offset of the rptr writeback location in the WB buffer
+ * @rptr_reg: MMIO offset of the rptr register
+ * @wptr_reg: MMIO offset of the wptr register
+ * @ptr_reg_shift: bit offset of the rptr/wptr values
+ * @ptr_reg_mask: bit mask of the rptr/wptr values
+ * @nop: nop packet for this ring
+ *
+ * Initialize the driver information for the selected ring (all asics).
+ * Returns 0 on success, error on failure.
+ */
 int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsigned ring_size,
 		     unsigned rptr_offs, unsigned rptr_reg, unsigned wptr_reg,
 		     u32 ptr_reg_shift, u32 ptr_reg_mask, u32 nop)
@@ -511,6 +705,14 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	return 0;
 }
 
+/**
+ * radeon_ring_fini - tear down the driver ring struct.
+ *
+ * @rdev: radeon_device pointer
+ * @ring: radeon_ring structure holding ring information
+ *
+ * Tear down the driver information for the selected ring (all asics).
+ */
 void radeon_ring_fini(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	int r;
-- 
cgit v1.2.3


From 1e179d4e283bd197035960ef751b5ccac06cbf91 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 20 Jul 2012 14:17:00 +0300
Subject: drm/radeon: check for allocation failure in radeon_ring_backup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Static checkers complain if this we don't check for allocation failure.
Also we can use the new kmalloc_array() function here as a cleanup.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/radeon/radeon_ring.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index f2fc25de0b2f..ec79b3750430 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -594,7 +594,11 @@ unsigned radeon_ring_backup(struct radeon_device *rdev, struct radeon_ring *ring
 	}
 
 	/* and then save the content of the ring */
-	*data = kmalloc(size * 4, GFP_KERNEL);
+	*data = kmalloc_array(size, sizeof(uint32_t), GFP_KERNEL);
+	if (!*data) {
+		mutex_unlock(&rdev->ring_lock);
+		return 0;
+	}
 	for (i = 0; i < size; ++i) {
 		(*data)[i] = ring->ring[ptr++];
 		ptr &= ring->ptr_mask;
-- 
cgit v1.2.3


From 48c0ac9911839daf188e4a0b6b132ac31050a241 Mon Sep 17 00:00:00 2001
From: Christian König <deathsimple@vodafone.de>
Date: Mon, 20 Aug 2012 15:38:47 +0200
Subject: drm/radeon: init lockup timeout on ring init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reset the lockup timeout on ring (re-)initialisation.

Otherwise we get error messages like this on gpu resets:
[ 1559.949177] radeon 0000:01:00.0: GPU lockup CP stall for more than 1482270msec

Signed-off-by: Christian König <deathsimple@vodafone.de>
cc: stable@vger.kernel.org
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
---
 drivers/gpu/drm/radeon/radeon_ring.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/gpu/drm/radeon/radeon_ring.c')

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index ec79b3750430..43c431a2686d 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -706,6 +706,7 @@ int radeon_ring_init(struct radeon_device *rdev, struct radeon_ring *ring, unsig
 	if (radeon_debugfs_ring_init(rdev, ring)) {
 		DRM_ERROR("Failed to register debugfs file for rings !\n");
 	}
+	radeon_ring_lockup_update(ring);
 	return 0;
 }
 
-- 
cgit v1.2.3