提交 4bf3dd92 编写于 作者: C Christian König 提交者: Alex Deucher

drm/radeon: cleanup VM id handling a bit

Store a reference to the VM into the IB structure, that
makes calculating the IBs address a bit less complicated.
Signed-off-by: NChristian König <deathsimple@vodafone.de>
Reviewed-by: NJerome Glisse <jglisse@redhat.com>
上级 1f0e2943
...@@ -879,12 +879,13 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) ...@@ -879,12 +879,13 @@ void cayman_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
#endif #endif
(ib->gpu_addr & 0xFFFFFFFC)); (ib->gpu_addr & 0xFFFFFFFC));
radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFF); 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 */ /* flush read cache over gart for this vmid */
radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1)); 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, (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(PACKET3_SURFACE_SYNC, 3));
radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA); radeon_ring_write(ring, PACKET3_TC_ACTION_ENA | PACKET3_SH_ACTION_ENA);
radeon_ring_write(ring, 0xFFFFFFFF); radeon_ring_write(ring, 0xFFFFFFFF);
......
...@@ -3800,7 +3800,7 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring) ...@@ -3800,7 +3800,7 @@ int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
return r; return r;
} }
WREG32(scratch, 0xCAFEDEAD); 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) { if (r) {
return r; return r;
} }
......
...@@ -2635,7 +2635,7 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring) ...@@ -2635,7 +2635,7 @@ int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
return r; return r;
} }
WREG32(scratch, 0xCAFEDEAD); WREG32(scratch, 0xCAFEDEAD);
r = radeon_ib_get(rdev, ring->idx, &ib, 256); r = radeon_ib_get(rdev, ring->idx, &ib, NULL, 256);
if (r) { if (r) {
DRM_ERROR("radeon: failed to get ib (%d).\n", r); DRM_ERROR("radeon: failed to get ib (%d).\n", r);
return r; return r;
......
...@@ -592,7 +592,7 @@ struct radeon_ib { ...@@ -592,7 +592,7 @@ struct radeon_ib {
uint32_t *ptr; uint32_t *ptr;
int ring; int ring;
struct radeon_fence *fence; struct radeon_fence *fence;
unsigned vm_id; struct radeon_vm *vm;
bool is_const_ib; bool is_const_ib;
struct radeon_fence *sync_to[RADEON_NUM_RINGS]; struct radeon_fence *sync_to[RADEON_NUM_RINGS];
struct radeon_semaphore *semaphore; struct radeon_semaphore *semaphore;
...@@ -734,7 +734,8 @@ struct si_rlc { ...@@ -734,7 +734,8 @@ struct si_rlc {
}; };
int radeon_ib_get(struct radeon_device *rdev, int ring, 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); 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); struct radeon_ib *const_ib);
......
...@@ -363,7 +363,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev, ...@@ -363,7 +363,7 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
* uncached). * uncached).
*/ */
r = radeon_ib_get(rdev, parser->ring, &parser->ib, r = radeon_ib_get(rdev, parser->ring, &parser->ib,
ib_chunk->length_dw * 4); NULL, ib_chunk->length_dw * 4);
if (r) { if (r) {
DRM_ERROR("Failed to get ib !\n"); DRM_ERROR("Failed to get ib !\n");
return r; return r;
...@@ -380,7 +380,6 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev, ...@@ -380,7 +380,6 @@ static int radeon_cs_ib_chunk(struct radeon_device *rdev,
return r; return r;
} }
radeon_cs_sync_rings(parser); radeon_cs_sync_rings(parser);
parser->ib.vm_id = 0;
r = radeon_ib_schedule(rdev, &parser->ib, NULL); r = radeon_ib_schedule(rdev, &parser->ib, NULL);
if (r) { if (r) {
DRM_ERROR("Failed to schedule IB !\n"); DRM_ERROR("Failed to schedule IB !\n");
...@@ -426,7 +425,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, ...@@ -426,7 +425,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
return -EINVAL; return -EINVAL;
} }
r = radeon_ib_get(rdev, parser->ring, &parser->const_ib, r = radeon_ib_get(rdev, parser->ring, &parser->const_ib,
ib_chunk->length_dw * 4); vm, ib_chunk->length_dw * 4);
if (r) { if (r) {
DRM_ERROR("Failed to get const ib !\n"); DRM_ERROR("Failed to get const ib !\n");
return r; return r;
...@@ -450,7 +449,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, ...@@ -450,7 +449,7 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
return -EINVAL; return -EINVAL;
} }
r = radeon_ib_get(rdev, parser->ring, &parser->ib, r = radeon_ib_get(rdev, parser->ring, &parser->ib,
ib_chunk->length_dw * 4); vm, ib_chunk->length_dw * 4);
if (r) { if (r) {
DRM_ERROR("Failed to get ib !\n"); DRM_ERROR("Failed to get ib !\n");
return r; return r;
...@@ -478,19 +477,8 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev, ...@@ -478,19 +477,8 @@ static int radeon_cs_ib_vm_chunk(struct radeon_device *rdev,
} }
radeon_cs_sync_rings(parser); 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) && if ((rdev->family >= CHIP_TAHITI) &&
(parser->chunk_const_ib_idx != -1)) { (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); r = radeon_ib_schedule(rdev, &parser->ib, &parser->const_ib);
} else { } else {
r = radeon_ib_schedule(rdev, &parser->ib, NULL); r = radeon_ib_schedule(rdev, &parser->ib, NULL);
......
...@@ -58,7 +58,8 @@ int radeon_debugfs_sa_init(struct radeon_device *rdev); ...@@ -58,7 +58,8 @@ int radeon_debugfs_sa_init(struct radeon_device *rdev);
* Returns 0 on success, error on failure. * Returns 0 on success, error on failure.
*/ */
int radeon_ib_get(struct radeon_device *rdev, int ring, 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; int i, r;
...@@ -76,8 +77,15 @@ int radeon_ib_get(struct radeon_device *rdev, int ring, ...@@ -76,8 +77,15 @@ int radeon_ib_get(struct radeon_device *rdev, int ring,
ib->ring = ring; ib->ring = ring;
ib->fence = NULL; ib->fence = NULL;
ib->ptr = radeon_sa_bo_cpu_addr(ib->sa_bo); ib->ptr = radeon_sa_bo_cpu_addr(ib->sa_bo);
ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo); ib->vm = vm;
ib->vm_id = 0; 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; ib->is_const_ib = false;
for (i = 0; i < RADEON_NUM_RINGS; ++i) for (i = 0; i < RADEON_NUM_RINGS; ++i)
ib->sync_to[i] = NULL; ib->sync_to[i] = NULL;
......
...@@ -1806,13 +1806,14 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib) ...@@ -1806,13 +1806,14 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
#endif #endif
(ib->gpu_addr & 0xFFFFFFFC)); (ib->gpu_addr & 0xFFFFFFFC));
radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF); 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) { if (!ib->is_const_ib) {
/* flush read cache over gart for this vmid */ /* flush read cache over gart for this vmid */
radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1)); 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, (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(PACKET3_SURFACE_SYNC, 3));
radeon_ring_write(ring, PACKET3_TCL1_ACTION_ENA | radeon_ring_write(ring, PACKET3_TCL1_ACTION_ENA |
PACKET3_TC_ACTION_ENA | PACKET3_TC_ACTION_ENA |
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册