Store a reference to the VM into the IB structure, that makes calculating the IBs address a bit less complicated.
Signed-off-by: Christian König deathsimple@vodafone.de --- drivers/gpu/drm/radeon/ni.c | 5 +++-- drivers/gpu/drm/radeon/r100.c | 2 +- drivers/gpu/drm/radeon/r600.c | 2 +- drivers/gpu/drm/radeon/radeon.h | 5 +++-- drivers/gpu/drm/radeon/radeon_cs.c | 18 +++--------------- drivers/gpu/drm/radeon/radeon_ring.c | 14 +++++++++++--- drivers/gpu/drm/radeon/si.c | 5 +++-- 7 files changed, 25 insertions(+), 26 deletions(-)
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 9945d86..efa3ab9 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -871,12 +871,13 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) #endif (ib->gpu_addr & 0xFFFFFFFC)); radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFF); - radeon_ring_write(ring, ib->length_dw | (ib->vm_id << 24)); + radeon_ring_write(ring, ib->length_dw | + (ib->vm ? (ib->vm->id << 24) : 0));
/* flush read cache over gart for this vmid */ radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1)); radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2); - radeon_ring_write(ring, ib->vm_id); + radeon_ring_write(ring, ib->vm ? ib->vm->id : 0); radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3)); radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA); radeon_ring_write(ring, 0xFFFFFFFF); diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 8acb34f..5f5f524 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -3816,7 +3816,7 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring) return r; } WREG32(scratch, 0xCAFEDEAD); - r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib, 256); + r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX, &ib, NULL, 256); if (r) { return r; } diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 637280f..75d448d 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -2635,7 +2635,7 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring) return r; } WREG32(scratch, 0xCAFEDEAD); - r = radeon_ib_get(rdev, ring->idx, &ib, 256); + r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 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 8d75c65..ef1fdf2 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -611,7 +611,7 @@ struct radeon_ib { uint32_t *ptr; int ring; struct radeon_fence *fence; - unsigned vm_id; + struct radeon_vm *vm; bool is_const_ib; struct radeon_fence *sync_to[RADEON_NUM_RINGS]; struct radeon_semaphore *semaphore; @@ -753,7 +753,8 @@ struct si_rlc { };
int radeon_ib_get(struct radeon_device *rdev, int ring, - struct radeon_ib *ib, unsigned size); + struct radeon_ib *ib, struct radeon_vm *vm, + 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, struct radeon_ib *const_ib); diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index b4a0db24..0a9d1eb 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -363,7 +363,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev, * uncached). */ r = radeon_ib_get(rdev, parser->ring, &parser->ib, - ib_chunk->length_dw * 4); + NULL, ib_chunk->length_dw * 4); if (r) { DRM_ERROR("Failed to get ib !\n"); return r; @@ -380,7 +380,6 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev, return r; } radeon_cs_sync_rings(parser); - parser->ib.vm_id = 0; r = radeon_ib_schedule(rdev, &parser->ib, NULL); if (r) { DRM_ERROR("Failed to schedule IB !\n"); @@ -426,7 +425,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, return -EINVAL; } r = radeon_ib_get(rdev, parser->ring, &parser->const_ib, - ib_chunk->length_dw * 4); + vm, ib_chunk->length_dw * 4); if (r) { DRM_ERROR("Failed to get const ib !\n"); return r; @@ -450,7 +449,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, return -EINVAL; } r = radeon_ib_get(rdev, parser->ring, &parser->ib, - ib_chunk->length_dw * 4); + vm, ib_chunk->length_dw * 4); if (r) { DRM_ERROR("Failed to get ib !\n"); return r; @@ -478,19 +477,8 @@ 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, - * 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->ib, &parser->const_ib); } else { r = radeon_ib_schedule(rdev, &parser->ib, NULL); diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index ec79b37..9ab3a3c 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -58,7 +58,8 @@ int radeon_debugfs_sa_init(struct radeon_device *rdev); * Returns 0 on success, error on failure. */ int radeon_ib_get(struct radeon_device *rdev, int ring, - struct radeon_ib *ib, unsigned size) + struct radeon_ib *ib, struct radeon_vm *vm, + unsigned size) { int i, r;
@@ -76,8 +77,15 @@ int radeon_ib_get(struct radeon_device *rdev, int ring, 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->vm = vm; + if (vm) { + /* ib pool is bind at 0 in virtual address space, + * so gpu_addr is the offset inside the pool bo + */ + ib->gpu_addr = ib->sa_bo->soffset; + } else { + ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo); + } ib->is_const_ib = false; for (i = 0; i < RADEON_NUM_RINGS; ++i) ib->sync_to[i] = NULL; diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index c053f81..4ebcb33 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -1798,13 +1798,14 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) #endif (ib->gpu_addr & 0xFFFFFFFC)); radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF); - radeon_ring_write(ring, ib->length_dw | (ib->vm_id << 24)); + radeon_ring_write(ring, ib->length_dw | + (ib->vm ? (ib->vm->id << 24) : 0));
if (!ib->is_const_ib) { /* flush read cache over gart for this vmid */ radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1)); radeon_ring_write(ring, (CP_COHER_CNTL2 - PACKET3_SET_CONFIG_REG_START) >> 2); - radeon_ring_write(ring, ib->vm_id); + radeon_ring_write(ring, ib->vm ? ib->vm->id : 0); radeon_ring_write(ring, PACKET3(PACKET3_SURFACE_SYNC, 3)); radeon_ring_write(ring, PACKET3_TCL1_ACTION_ENA | PACKET3_TC_ACTION_ENA |