Re: [PATCH 01/10] drm/radeon: remove radeon_fence_create

On Thu, May 24, 2012 at 09:49:05AM +0200, Christian König wrote:

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/evergreen.c | 2 +- drivers/gpu/drm/radeon/ni.c | 2 +- drivers/gpu/drm/radeon/r100.c | 4 +- drivers/gpu/drm/radeon/r200.c | 4 +- drivers/gpu/drm/radeon/r600.c | 4 +- drivers/gpu/drm/radeon/r600_blit_kms.c | 6 +-- drivers/gpu/drm/radeon/radeon.h | 11 +++-- drivers/gpu/drm/radeon/radeon_asic.h | 8 ++-- drivers/gpu/drm/radeon/radeon_benchmark.c | 10 +---- drivers/gpu/drm/radeon/radeon_fence.c | 42 ++++++------------ drivers/gpu/drm/radeon/radeon_ring.c | 19 +++++---- drivers/gpu/drm/radeon/radeon_sa.c | 2 +- drivers/gpu/drm/radeon/radeon_test.c | 66 ++++++++++++----------------- drivers/gpu/drm/radeon/radeon_ttm.c | 30 +++++-------- drivers/gpu/drm/radeon/si.c | 6 +-- 15 files changed, 86 insertions(+), 130 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 58991af..dd3cea4 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -1366,7 +1366,7 @@ 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->fence->ring];

• struct radeon_ring *ring = &rdev->ring[ib->ring];

  /* set to DX10/11 mode */ radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));

diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index b01c2dd..9d9f5ac 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1127,7 +1127,7 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,

void cayman_ring_ib_execute(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];

  /* set to DX10/11 mode */ radeon_ring_write(ring, PACKET3(PACKET3_MODE_CONTROL, 0));

diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index fb44e7e..415b7d8 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -883,7 +883,7 @@ int r100_copy_blit(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

•    struct radeon_fence *fence)
  

•    struct radeon_fence **fence)
  

{ struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]; uint32_t cur_pages; @@ -947,7 +947,7 @@ int r100_copy_blit(struct radeon_device *rdev, RADEON_WAIT_HOST_IDLECLEAN | RADEON_WAIT_DMA_GUI_IDLE); if (fence) {

• r = radeon_fence_emit(rdev, fence);
  

• r = radeon_fence_emit(rdev, fence, RADEON_RING_TYPE_GFX_INDEX);
  

  } radeon_ring_unlock_commit(rdev, ring); return r;

diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c index a26144d..f088925 100644 --- a/drivers/gpu/drm/radeon/r200.c +++ b/drivers/gpu/drm/radeon/r200.c @@ -85,7 +85,7 @@ int r200_copy_dma(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

•   struct radeon_fence *fence)
  

•   struct radeon_fence **fence)
  

{ struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]; uint32_t size; @@ -120,7 +120,7 @@ int r200_copy_dma(struct radeon_device *rdev, radeon_ring_write(ring, PACKET0(RADEON_WAIT_UNTIL, 0)); radeon_ring_write(ring, RADEON_WAIT_DMA_GUI_IDLE); if (fence) {

• r = radeon_fence_emit(rdev, fence);
  

• r = radeon_fence_emit(rdev, fence, RADEON_RING_TYPE_GFX_INDEX);
  

  } radeon_ring_unlock_commit(rdev, ring); return r;

diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index f388a1d..e5279f9 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -2369,7 +2369,7 @@ int r600_copy_blit(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

•    struct radeon_fence *fence)
  

•    struct radeon_fence **fence)
  

{ struct radeon_sa_bo *vb = NULL; int r; @@ -2670,7 +2670,7 @@ 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->fence->ring];

• struct radeon_ring *ring = &rdev->ring[ib->ring];

  /* FIXME: implement */ radeon_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2));

diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c index 03b6e0d..02f4eeb 100644 --- a/drivers/gpu/drm/radeon/r600_blit_kms.c +++ b/drivers/gpu/drm/radeon/r600_blit_kms.c @@ -703,20 +703,20 @@ int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages, return 0; }

-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence, +void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence **fence, struct radeon_sa_bo *vb) { struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]; int r;

• r = radeon_fence_emit(rdev, fence);

• r = radeon_fence_emit(rdev, fence, RADEON_RING_TYPE_GFX_INDEX); if (r) { radeon_ring_unlock_undo(rdev, ring); return; }

  radeon_ring_unlock_commit(rdev, ring);

• radeon_sa_bo_free(rdev, &vb, fence);

• radeon_sa_bo_free(rdev, &vb, *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 1dc3a4a..5e259b4 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -113,7 +113,6 @@ extern int radeon_lockup_timeout;

/* fence seq are set to this number when signaled */ #define RADEON_FENCE_SIGNALED_SEQ 0LL -#define RADEON_FENCE_NOTEMITED_SEQ (~0LL)

/* internal ring indices */ /* r1xx+ has gfx CP ring */ @@ -277,8 +276,7 @@ struct radeon_fence { int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring); int radeon_fence_driver_init(struct radeon_device *rdev); void radeon_fence_driver_fini(struct radeon_device *rdev); -int radeon_fence_create(struct radeon_device *rdev, struct radeon_fence **fence, int ring); -int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence); +int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence **fence, int ring); void radeon_fence_process(struct radeon_device *rdev, int ring); bool radeon_fence_signaled(struct radeon_fence *fence); int radeon_fence_wait(struct radeon_fence *fence, bool interruptible); @@ -627,6 +625,7 @@ struct radeon_ib { uint32_t length_dw; uint64_t gpu_addr; uint32_t *ptr;

• int ring; struct radeon_fence *fence; unsigned vm_id; bool is_const_ib;

@@ -1190,20 +1189,20 @@ struct radeon_asic { uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

• 	    struct radeon_fence *fence);
  

• 	    struct radeon_fence **fence);
  

  u32 blit_ring_index; int (*dma)(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

• 	   struct radeon_fence *fence);
  

• 	   struct radeon_fence **fence);
  

  u32 dma_ring_index; /* method used for bo copy */ int (*copy)(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

• 	    struct radeon_fence *fence);
  

• 	    struct radeon_fence **fence);
  

  /* ring used for bo copies */ u32 copy_ring_index; } copy;

diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index e76a941..8cdf075 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -79,7 +79,7 @@ int r100_copy_blit(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

•    struct radeon_fence *fence);
  

•    struct radeon_fence **fence);
  

int r100_set_surface_reg(struct radeon_device *rdev, int reg, uint32_t tiling_flags, uint32_t pitch, uint32_t offset, uint32_t obj_size); @@ -144,7 +144,7 @@ extern int r200_copy_dma(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset, unsigned num_gpu_pages,

• 	 struct radeon_fence *fence);
  

• 	 struct radeon_fence **fence);
  

void r200_set_safe_registers(struct radeon_device *rdev);

/* @@ -318,7 +318,7 @@ void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib); int r600_ring_test(struct radeon_device *rdev, struct radeon_ring *cp); int r600_copy_blit(struct radeon_device *rdev, uint64_t src_offset, uint64_t dst_offset,

•    unsigned num_gpu_pages, struct radeon_fence *fence);
  

•    unsigned num_gpu_pages, struct radeon_fence **fence);
  

void r600_hpd_init(struct radeon_device *rdev); void r600_hpd_fini(struct radeon_device *rdev); bool r600_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd); @@ -364,7 +364,7 @@ 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); -void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence, +void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence **fence, struct radeon_sa_bo *vb); void r600_kms_blit_copy(struct radeon_device *rdev, u64 src_gpu_addr, u64 dst_gpu_addr, diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c index 364f5b1..bedda9c 100644 --- a/drivers/gpu/drm/radeon/radeon_benchmark.c +++ b/drivers/gpu/drm/radeon/radeon_benchmark.c @@ -45,20 +45,14 @@ static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size, for (i = 0; i < n; i++) { switch (flag) { case RADEON_BENCHMARK_COPY_DMA:

• 	r = radeon_fence_create(rdev, &fence, radeon_copy_dma_ring_index(rdev));
  

• 	if (r)
  

• 		return r;
  r = radeon_copy_dma(rdev, saddr, daddr,
  		    size / RADEON_GPU_PAGE_SIZE,
  

• 			    fence);
  

• 			    &fence);
  break;
  

  case RADEON_BENCHMARK_COPY_BLIT:

• 	r = radeon_fence_create(rdev, &fence, radeon_copy_blit_ring_index(rdev));
  

• 	if (r)
  

• 		return r;
  r = radeon_copy_blit(rdev, saddr, daddr,
  		     size / RADEON_GPU_PAGE_SIZE,
  

• 			     fence);
  

• 			     &fence);
  break;
  

  default: DRM_ERROR("Unknown copy method\n");

diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 11f5f40..401d346 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -61,15 +61,21 @@ static u32 radeon_fence_read(struct radeon_device *rdev, int ring) return seq; }

-int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence) +int radeon_fence_emit(struct radeon_device *rdev,

•       struct radeon_fence **fence,
  

•       int ring)
  

{ /* we are protected by the ring emission mutex */

• if (fence->seq && fence->seq < RADEON_FENCE_NOTEMITED_SEQ) {

• return 0;
  

• *fence = kmalloc(sizeof(struct radeon_fence), GFP_KERNEL);
• if ((*fence) == NULL) {

• return -ENOMEM;
  

  }

• fence->seq = ++rdev->fence_drv[fence->ring].seq;
• radeon_fence_ring_emit(rdev, fence->ring, fence);
• trace_radeon_fence_emit(rdev->ddev, fence->seq);

• kref_init(&((*fence)->kref));
• (*fence)->rdev = rdev;
• (*fence)->seq = ++rdev->fence_drv[ring].seq;
• (*fence)->ring = ring;
• radeon_fence_ring_emit(rdev, ring, *fence);
• trace_radeon_fence_emit(rdev->ddev, (*fence)->seq); return 0;

}

@@ -138,25 +144,9 @@ static void radeon_fence_destroy(struct kref *kref) struct radeon_fence *fence;

fence = container_of(kref, struct radeon_fence, kref);

• fence->seq = RADEON_FENCE_NOTEMITED_SEQ; kfree(fence);

}

-int radeon_fence_create(struct radeon_device *rdev,

• 	struct radeon_fence **fence,
  

• 	int ring)
  

-{

• *fence = kmalloc(sizeof(struct radeon_fence), GFP_KERNEL);
• if ((*fence) == NULL) {

• return -ENOMEM;
  

• }
• kref_init(&((*fence)->kref));
• (*fence)->rdev = rdev;
• (*fence)->seq = RADEON_FENCE_NOTEMITED_SEQ;
• (*fence)->ring = ring;
• return 0;

-}

static bool radeon_fence_seq_signaled(struct radeon_device *rdev, u64 seq, unsigned ring) { @@ -176,10 +166,6 @@ bool radeon_fence_signaled(struct radeon_fence *fence) if (!fence) { return true; }

• if (fence->seq == RADEON_FENCE_NOTEMITED_SEQ) {

• WARN(1, "Querying an unemitted fence : %p !\n", fence);
  

• return true;
  

• } if (fence->seq == RADEON_FENCE_SIGNALED_SEQ) { return true; }

@@ -444,9 +430,7 @@ int radeon_fence_wait_any(struct radeon_device *rdev, return 0; }

• if (fences[i]->seq < RADEON_FENCE_NOTEMITED_SEQ) {
  

• 	seq[i] = fences[i]->seq;
  

• }
  

• seq[i] = fences[i]->seq;
  

  }

  r = radeon_fence_wait_any_seq(rdev, seq, intr);

diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 493a7be..a0b9970 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -74,13 +74,9 @@ 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;

@@ -99,7 +95,7 @@ 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) {

@@ -114,8 +110,13 @@ 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;

} diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c index 32059b7..81dbb5b 100644 --- a/drivers/gpu/drm/radeon/radeon_sa.c +++ b/drivers/gpu/drm/radeon/radeon_sa.c @@ -349,7 +349,7 @@ void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo **sa_bo,

sa_manager = (*sa_bo)->manager; spin_lock(&sa_manager->lock);

• if (fence && fence->seq && fence->seq < RADEON_FENCE_NOTEMITED_SEQ) {

• if (fence && !radeon_fence_signaled(fence)) { (*sa_bo)->fence = radeon_fence_ref(fence); list_add_tail(&(*sa_bo)->flist, &sa_manager->flist[fence->ring]);

diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c index efff929..47e1535 100644 --- a/drivers/gpu/drm/radeon/radeon_test.c +++ b/drivers/gpu/drm/radeon/radeon_test.c @@ -106,13 +106,7 @@ void radeon_test_moves(struct radeon_device *rdev)

radeon_bo_kunmap(gtt_obj[i]);

• r = radeon_fence_create(rdev, &fence, RADEON_RING_TYPE_GFX_INDEX);
  

• if (r) {
  

• 	DRM_ERROR("Failed to create GTT->VRAM fence %d\n", i);
  

• 	goto out_cleanup;
  

• }
  

• r = radeon_copy(rdev, gtt_addr, vram_addr, size / RADEON_GPU_PAGE_SIZE, fence);
  

• r = radeon_copy(rdev, gtt_addr, vram_addr, size / RADEON_GPU_PAGE_SIZE, &fence);
  

  if (r) { DRM_ERROR("Failed GTT->VRAM copy %d\n", i); goto out_cleanup;

@@ -155,13 +149,7 @@ void radeon_test_moves(struct radeon_device *rdev)

radeon_bo_kunmap(vram_obj);

• r = radeon_fence_create(rdev, &fence, RADEON_RING_TYPE_GFX_INDEX);
  

• if (r) {
  

• 	DRM_ERROR("Failed to create VRAM->GTT fence %d\n", i);
  

• 	goto out_cleanup;
  

• }
  

• r = radeon_copy(rdev, vram_addr, gtt_addr, size / RADEON_GPU_PAGE_SIZE, fence);
  

• r = radeon_copy(rdev, vram_addr, gtt_addr, size / RADEON_GPU_PAGE_SIZE, &fence);
  

  if (r) { DRM_ERROR("Failed VRAM->GTT copy %d\n", i); goto out_cleanup;

@@ -245,17 +233,6 @@ void radeon_test_ring_sync(struct radeon_device *rdev, int ridxB = radeon_ring_index(rdev, ringB); int r;

• r = radeon_fence_create(rdev, &fence1, ridxA);
• if (r) {

• DRM_ERROR("Failed to create sync fence 1\n");
  

• goto out_cleanup;
  

• }
• r = radeon_fence_create(rdev, &fence2, ridxA);
• if (r) {

• DRM_ERROR("Failed to create sync fence 2\n");
  

• goto out_cleanup;
  

• }
• r = radeon_semaphore_create(rdev, &semaphore); if (r) { DRM_ERROR("Failed to create semaphore\n");

@@ -268,9 +245,19 @@ void radeon_test_ring_sync(struct radeon_device *rdev, goto out_cleanup; } radeon_semaphore_emit_wait(rdev, ridxA, semaphore);

• radeon_fence_emit(rdev, fence1);

• r = radeon_fence_emit(rdev, &fence1, ridxA);
• 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);

• radeon_fence_emit(rdev, fence2);

• r = radeon_fence_emit(rdev, &fence2, ridxA);

• if (r) {

• DRM_ERROR("Failed to emit fence 2\n");
  

• radeon_ring_unlock_undo(rdev, ringA);
  

• goto out_cleanup;
  

• } radeon_ring_unlock_commit(rdev, ringA);

  mdelay(1000);

@@ -342,17 +329,6 @@ void radeon_test_ring_sync2(struct radeon_device *rdev, bool sigA, sigB; int i, r;

• r = radeon_fence_create(rdev, &fenceA, ridxA);
• if (r) {

• DRM_ERROR("Failed to create sync fence 1\n");
  

• goto out_cleanup;
  

• }
• r = radeon_fence_create(rdev, &fenceB, ridxB);
• if (r) {

• DRM_ERROR("Failed to create sync fence 2\n");
  

• goto out_cleanup;
  

• }
• r = radeon_semaphore_create(rdev, &semaphore); if (r) { DRM_ERROR("Failed to create semaphore\n");

@@ -365,7 +341,12 @@ void radeon_test_ring_sync2(struct radeon_device *rdev, goto out_cleanup; } radeon_semaphore_emit_wait(rdev, ridxA, semaphore);

• radeon_fence_emit(rdev, fenceA);

• r = radeon_fence_emit(rdev, &fenceA, ridxA);

• if (r) {

• DRM_ERROR("Failed to emit sync fence 1\n");
  

• radeon_ring_unlock_undo(rdev, ringA);
  

• goto out_cleanup;
  

• } radeon_ring_unlock_commit(rdev, ringA);

  r = radeon_ring_lock(rdev, ringB, 64);

@@ -374,7 +355,12 @@ void radeon_test_ring_sync2(struct radeon_device *rdev, goto out_cleanup; } radeon_semaphore_emit_wait(rdev, ridxB, semaphore);

• radeon_fence_emit(rdev, fenceB);

• r = radeon_fence_emit(rdev, &fenceB, ridxB);

• if (r) {

• DRM_ERROR("Failed to create sync fence 2\n");
  

• radeon_ring_unlock_undo(rdev, ringB);
  

• goto out_cleanup;
  

• } radeon_ring_unlock_commit(rdev, ringB);

  mdelay(1000);

diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index c94a225..2d36bdd 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -222,15 +222,12 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, { struct radeon_device *rdev; uint64_t old_start, new_start;

• struct radeon_fence *fence, *old_fence;

• struct radeon_fence *fence; struct radeon_semaphore *sem = NULL;

• int r;

• int r, ridx;

  rdev = radeon_get_rdev(bo->bdev);

• r = radeon_fence_create(rdev, &fence, radeon_copy_ring_index(rdev));
• if (unlikely(r)) {

• return r;
  

• }

• ridx = radeon_copy_ring_index(rdev); old_start = old_mem->start << PAGE_SHIFT; new_start = new_mem->start << PAGE_SHIFT;

@@ -243,7 +240,6 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, break; default: DRM_ERROR("Unknown placement %d\n", old_mem->mem_type);

• radeon_fence_unref(&fence);
  

  return -EINVAL; } switch (new_mem->mem_type) {

@@ -255,42 +251,38 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, break; default: DRM_ERROR("Unknown placement %d\n", old_mem->mem_type);

• radeon_fence_unref(&fence);
  

  return -EINVAL; }
• if (!rdev->ring[radeon_copy_ring_index(rdev)].ready) {

• if (!rdev->ring[ridx].ready) { DRM_ERROR("Trying to move memory with ring turned off.\n");

• radeon_fence_unref(&fence);
  

  return -EINVAL; }

  BUILD_BUG_ON((PAGE_SIZE % RADEON_GPU_PAGE_SIZE) != 0);

  /* sync other rings */

• old_fence = bo->sync_obj;

• if (old_fence && old_fence->ring != fence->ring

•    && !radeon_fence_signaled(old_fence)) {
  

• fence = bo->sync_obj;
• if (fence && fence->ring != ridx

•    && !radeon_fence_signaled(fence)) {
  

  bool sync_to_ring[RADEON_NUM_RINGS] = { };

• sync_to_ring[old_fence->ring] = true;
  

• sync_to_ring[fence->ring] = true;
  
  

  r = radeon_semaphore_create(rdev, &sem); if (r) {

• 	radeon_fence_unref(&fence);
  return r;
  

  }

• r = radeon_semaphore_sync_rings(rdev, sem,
  

• 				sync_to_ring, fence->ring);
  

• r = radeon_semaphore_sync_rings(rdev, sem, sync_to_ring, ridx);
  

  if (r) { radeon_semaphore_free(rdev, sem, NULL);

• 	radeon_fence_unref(&fence);
  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);
  

• 	&fence);
  

  /* FIXME: handle copy error */ r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL, evict, no_wait_reserve, no_wait_gpu, new_mem);

diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 549732e..5ca8ef5 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -1915,7 +1915,7 @@ void si_fence_ring_emit(struct radeon_device *rdev, */ void si_ring_ib_execute(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]; u32 header;

  if (ib->is_const_ib)

@@ -2855,7 +2855,7 @@ int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib) if (ib->is_const_ib) ret = si_vm_packet3_ce_check(rdev, ib->ptr, &pkt); else {

• 		switch (ib->fence->ring) {
  

• 		switch (ib->ring) {
  	case RADEON_RING_TYPE_GFX_INDEX:
  		ret = si_vm_packet3_gfx_check(rdev, ib->ptr, &pkt);
  		break;
  

@@ -2864,7 +2864,7 @@ int si_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib) ret = si_vm_packet3_compute_check(rdev, ib->ptr, &pkt); break; default:

• 			dev_err(rdev->dev, "Non-PM4 ring %d !\n", ib->fence->ring);
  

• 			dev_err(rdev->dev, "Non-PM4 ring %d !\n", ib->ring);
  		ret = -EINVAL;
  		break;
  	}
  

-- 1.7.9.5