Commit 975700d2 authored by Christian König's avatar Christian König Committed by Alex Deucher
Browse files

drm/radeon: split semaphore and sync object handling v2 



Previously we just allocated space for four hardware semaphores
in each software semaphore object. Make software semaphore objects
represent only one hardware semaphore address again by splitting
the sync code into it's own object.

v2: fix typo in comment

Signed-off-by: default avatarChristian König <christian.koenig@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent e0602c35

drivers/gpu/drm/radeon/Makefile

+2 −1
Original line number Diff line number Diff line
@@ -80,7 +80,8 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \ 
	r600_dpm.o rs780_dpm.o rv6xx_dpm.o rv770_dpm.o rv730_dpm.o rv740_dpm.o \

	rv770_smc.o cypress_dpm.o btc_dpm.o sumo_dpm.o sumo_smc.o trinity_dpm.o \

	trinity_smc.o ni_dpm.o si_smc.o si_dpm.o kv_smc.o kv_dpm.o ci_smc.o \

	ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o

	ci_dpm.o dce6_afmt.o radeon_vm.o radeon_ucode.o radeon_ib.o radeon_mn.o \

	radeon_sync.o



# add async DMA block

radeon-y += \

drivers/gpu/drm/radeon/cik.c

+7 −11
Original line number Diff line number Diff line
@@ -3994,31 +3994,27 @@ struct radeon_fence *cik_copy_cpdma(struct radeon_device *rdev, 
				    unsigned num_gpu_pages,

				    struct reservation_object *resv)

{

	struct radeon_semaphore *sem = NULL;

	struct radeon_fence *fence;

	struct radeon_sync sync;

	int ring_index = rdev->asic->copy.blit_ring_index;

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

	u32 size_in_bytes, cur_size_in_bytes, control;

	int i, num_loops;

	int r = 0;



	r = radeon_semaphore_create(rdev, &sem);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		return ERR_PTR(r);

	}

	radeon_sync_create(&sync);



	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);

	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);

	r = radeon_ring_lock(rdev, ring, num_loops * 7 + 18);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_semaphore_sync_resv(rdev, sem, resv, false);

	radeon_semaphore_sync_rings(rdev, sem, ring->idx);

	radeon_sync_resv(rdev, &sync, resv, false);

	radeon_sync_rings(rdev, &sync, ring->idx);



	for (i = 0; i < num_loops; i++) {

		cur_size_in_bytes = size_in_bytes;
@@ -4042,12 +4038,12 @@ struct radeon_fence *cik_copy_cpdma(struct radeon_device *rdev, 
	r = radeon_fence_emit(rdev, &fence, ring->idx);

	if (r) {

		radeon_ring_unlock_undo(rdev, ring);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_ring_unlock_commit(rdev, ring, false);

	radeon_semaphore_free(rdev, &sem, fence);

	radeon_sync_free(rdev, &sync, fence);



	return fence;

}

drivers/gpu/drm/radeon/cik_sdma.c

+7 −11
Original line number Diff line number Diff line
@@ -541,31 +541,27 @@ struct radeon_fence *cik_copy_dma(struct radeon_device *rdev, 
				  unsigned num_gpu_pages,

				  struct reservation_object *resv)

{

	struct radeon_semaphore *sem = NULL;

	struct radeon_fence *fence;

	struct radeon_sync sync;

	int ring_index = rdev->asic->copy.dma_ring_index;

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

	u32 size_in_bytes, cur_size_in_bytes;

	int i, num_loops;

	int r = 0;



	r = radeon_semaphore_create(rdev, &sem);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		return ERR_PTR(r);

	}

	radeon_sync_create(&sync);



	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);

	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);

	r = radeon_ring_lock(rdev, ring, num_loops * 7 + 14);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_semaphore_sync_resv(rdev, sem, resv, false);

	radeon_semaphore_sync_rings(rdev, sem, ring->idx);

	radeon_sync_resv(rdev, &sync, resv, false);

	radeon_sync_rings(rdev, &sync, ring->idx);



	for (i = 0; i < num_loops; i++) {

		cur_size_in_bytes = size_in_bytes;
@@ -586,12 +582,12 @@ struct radeon_fence *cik_copy_dma(struct radeon_device *rdev, 
	r = radeon_fence_emit(rdev, &fence, ring->idx);

	if (r) {

		radeon_ring_unlock_undo(rdev, ring);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_ring_unlock_commit(rdev, ring, false);

	radeon_semaphore_free(rdev, &sem, fence);

	radeon_sync_free(rdev, &sync, fence);



	return fence;

}

drivers/gpu/drm/radeon/evergreen_dma.c

+7 −11
Original line number Diff line number Diff line
@@ -110,31 +110,27 @@ struct radeon_fence *evergreen_copy_dma(struct radeon_device *rdev, 
					unsigned num_gpu_pages,

					struct reservation_object *resv)

{

	struct radeon_semaphore *sem = NULL;

	struct radeon_fence *fence;

	struct radeon_sync sync;

	int ring_index = rdev->asic->copy.dma_ring_index;

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

	u32 size_in_dw, cur_size_in_dw;

	int i, num_loops;

	int r = 0;



	r = radeon_semaphore_create(rdev, &sem);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		return ERR_PTR(r);

	}

	radeon_sync_create(&sync);



	size_in_dw = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT) / 4;

	num_loops = DIV_ROUND_UP(size_in_dw, 0xfffff);

	r = radeon_ring_lock(rdev, ring, num_loops * 5 + 11);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_semaphore_sync_resv(rdev, sem, resv, false);

	radeon_semaphore_sync_rings(rdev, sem, ring->idx);

	radeon_sync_resv(rdev, &sync, resv, false);

	radeon_sync_rings(rdev, &sync, ring->idx);



	for (i = 0; i < num_loops; i++) {

		cur_size_in_dw = size_in_dw;
@@ -153,12 +149,12 @@ struct radeon_fence *evergreen_copy_dma(struct radeon_device *rdev, 
	r = radeon_fence_emit(rdev, &fence, ring->idx);

	if (r) {

		radeon_ring_unlock_undo(rdev, ring);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_ring_unlock_commit(rdev, ring, false);

	radeon_semaphore_free(rdev, &sem, fence);

	radeon_sync_free(rdev, &sync, fence);



	return fence;

}

drivers/gpu/drm/radeon/r600.c

+7 −11
Original line number Diff line number Diff line
@@ -2889,31 +2889,27 @@ struct radeon_fence *r600_copy_cpdma(struct radeon_device *rdev, 
				     unsigned num_gpu_pages,

				     struct reservation_object *resv)

{

	struct radeon_semaphore *sem = NULL;

	struct radeon_fence *fence;

	struct radeon_sync sync;

	int ring_index = rdev->asic->copy.blit_ring_index;

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

	u32 size_in_bytes, cur_size_in_bytes, tmp;

	int i, num_loops;

	int r = 0;



	r = radeon_semaphore_create(rdev, &sem);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		return ERR_PTR(r);

	}

	radeon_sync_create(&sync);



	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);

	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);

	r = radeon_ring_lock(rdev, ring, num_loops * 6 + 24);

	if (r) {

		DRM_ERROR("radeon: moving bo (%d).\n", r);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_semaphore_sync_resv(rdev, sem, resv, false);

	radeon_semaphore_sync_rings(rdev, sem, ring->idx);

	radeon_sync_resv(rdev, &sync, resv, false);

	radeon_sync_rings(rdev, &sync, ring->idx);



	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));

	radeon_ring_write(ring, (WAIT_UNTIL - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
@@ -2942,12 +2938,12 @@ struct radeon_fence *r600_copy_cpdma(struct radeon_device *rdev, 
	r = radeon_fence_emit(rdev, &fence, ring->idx);

	if (r) {

		radeon_ring_unlock_undo(rdev, ring);

		radeon_semaphore_free(rdev, &sem, NULL);

		radeon_sync_free(rdev, &sync, NULL);

		return ERR_PTR(r);

	}



	radeon_ring_unlock_commit(rdev, ring, false);

	radeon_semaphore_free(rdev, &sem, fence);

	radeon_sync_free(rdev, &sync, fence);



	return fence;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE