[Intel-gfx] [PATCH 07/10] drm/amdgpu: add timeline support in amdgpu CS v2
syncobj wait/signal operation is appending in command submission.
v2: separate to two kinds in/out_deps functions
Signed-off-by: Chunming Zhou
Cc: Daniel Rakos
Cc: Jason Ekstrand
Cc: Bas Nieuwenhuizen
Cc: Dave Airlie
Cc: Christian König
Cc: Chris Wilson
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 10 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 147 +
include/uapi/drm/amdgpu_drm.h | 8 ++
3 files changed, 140 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 42f882c633ee..f9160ea1396a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -545,6 +545,12 @@ struct amdgpu_cs_chunk {
void*kdata;
};
+struct amdgpu_cs_post_dep {
+ struct drm_syncobj *syncobj;
+ struct dma_fence_chain *chain;
+ u64 point;
+};
+
struct amdgpu_cs_parser {
struct amdgpu_device*adev;
struct drm_file *filp;
@@ -574,8 +580,8 @@ struct amdgpu_cs_parser {
/* user fence */
struct amdgpu_bo_list_entry uf_entry;
- unsigned num_post_dep_syncobjs;
- struct drm_syncobj **post_dep_syncobjs;
+ unsignednum_post_deps;
+ struct amdgpu_cs_post_dep *post_deps;
};
static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index dc54e9efd910..580f1ea27157 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -213,6 +213,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser
*p, union drm_amdgpu_cs
case AMDGPU_CHUNK_ID_DEPENDENCIES:
case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
+ case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
+ case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
break;
default:
@@ -792,9 +794,11 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser
*parser, int error,
ttm_eu_backoff_reservation(>ticket,
>validated);
- for (i = 0; i < parser->num_post_dep_syncobjs; i++)
- drm_syncobj_put(parser->post_dep_syncobjs[i]);
- kfree(parser->post_dep_syncobjs);
+ for (i = 0; i < parser->num_post_deps; i++) {
+ drm_syncobj_put(parser->post_deps[i].syncobj);
+ kfree(parser->post_deps[i].chain);
+ }
+ kfree(parser->post_deps);
dma_fence_put(parser->fence);
@@ -1100,13 +1104,18 @@ static int amdgpu_cs_process_fence_dep(struct
amdgpu_cs_parser *p,
}
static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
-uint32_t handle)
+uint32_t handle, u64 point,
+u64 flags)
{
- int r;
struct dma_fence *fence;
- r = drm_syncobj_find_fence(p->filp, handle, 0, 0, );
- if (r)
+ int r;
+
+ r = drm_syncobj_find_fence(p->filp, handle, point, flags, );
+ if (r) {
+ DRM_ERROR("syncobj %u failed to find fence @ %llu (%d)!\n",
+ handle, point, r);
return r;
+ }
r = amdgpu_sync_fence(p->adev, >job->sync, fence, true);
dma_fence_put(fence);
@@ -1117,46 +1126,115 @@ static int
amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
static int amdgpu_cs_process_syncobj_in_dep(struct amdgpu_cs_parser *p,
struct amdgpu_cs_chunk *chunk)
{
+ struct drm_amdgpu_cs_chunk_sem *deps;
unsigned num_deps;
int i, r;
- struct drm_amdgpu_cs_chunk_sem *deps;
deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
num_deps = chunk->length_dw * 4 /
sizeof(struct drm_amdgpu_cs_chunk_sem);
+ for (i = 0; i < num_deps; ++i) {
+ r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle,
+ 0, 0);
+ if (r)
+ return r;
+ }
+
+ return 0;
+}
+
+static int amdgpu_cs_process_syncobj_timeline_in_dep(struct amdgpu_cs_parser
*p,
+struct amdgpu_cs_chunk
*chunk)
+{
+ struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;
+ unsigned num_deps;
+ int i, r;
+
+ syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata;
+ num_deps = chunk->length_dw * 4 /
+ sizeof(struct drm_amdgpu_cs_chunk_syncobj);
for (i = 0; i < num_deps; ++i) {
- r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle);
+ r =
[Intel-gfx] [PATCH 07/10] drm/amdgpu: add timeline support in amdgpu CS v2
syncobj wait/signal operation is appending in command submission.
v2: separate to two kinds in/out_deps functions
Signed-off-by: Chunming Zhou
Cc: Daniel Rakos
Cc: Jason Ekstrand
Cc: Bas Nieuwenhuizen
Cc: Dave Airlie
Cc: Christian König
Cc: Chris Wilson
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 10 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 147 +
include/uapi/drm/amdgpu_drm.h | 8 ++
3 files changed, 140 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 42f882c633ee..f9160ea1396a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -545,6 +545,12 @@ struct amdgpu_cs_chunk {
void*kdata;
};
+struct amdgpu_cs_post_dep {
+ struct drm_syncobj *syncobj;
+ struct dma_fence_chain *chain;
+ u64 point;
+};
+
struct amdgpu_cs_parser {
struct amdgpu_device*adev;
struct drm_file *filp;
@@ -574,8 +580,8 @@ struct amdgpu_cs_parser {
/* user fence */
struct amdgpu_bo_list_entry uf_entry;
- unsigned num_post_dep_syncobjs;
- struct drm_syncobj **post_dep_syncobjs;
+ unsignednum_post_deps;
+ struct amdgpu_cs_post_dep *post_deps;
};
static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index dc54e9efd910..580f1ea27157 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -213,6 +213,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser
*p, union drm_amdgpu_cs
case AMDGPU_CHUNK_ID_DEPENDENCIES:
case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
+ case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
+ case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
break;
default:
@@ -792,9 +794,11 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser
*parser, int error,
ttm_eu_backoff_reservation(>ticket,
>validated);
- for (i = 0; i < parser->num_post_dep_syncobjs; i++)
- drm_syncobj_put(parser->post_dep_syncobjs[i]);
- kfree(parser->post_dep_syncobjs);
+ for (i = 0; i < parser->num_post_deps; i++) {
+ drm_syncobj_put(parser->post_deps[i].syncobj);
+ kfree(parser->post_deps[i].chain);
+ }
+ kfree(parser->post_deps);
dma_fence_put(parser->fence);
@@ -1100,13 +1104,18 @@ static int amdgpu_cs_process_fence_dep(struct
amdgpu_cs_parser *p,
}
static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
-uint32_t handle)
+uint32_t handle, u64 point,
+u64 flags)
{
- int r;
struct dma_fence *fence;
- r = drm_syncobj_find_fence(p->filp, handle, 0, 0, );
- if (r)
+ int r;
+
+ r = drm_syncobj_find_fence(p->filp, handle, point, flags, );
+ if (r) {
+ DRM_ERROR("syncobj %u failed to find fence @ %llu (%d)!\n",
+ handle, point, r);
return r;
+ }
r = amdgpu_sync_fence(p->adev, >job->sync, fence, true);
dma_fence_put(fence);
@@ -1117,46 +1126,115 @@ static int
amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
static int amdgpu_cs_process_syncobj_in_dep(struct amdgpu_cs_parser *p,
struct amdgpu_cs_chunk *chunk)
{
+ struct drm_amdgpu_cs_chunk_sem *deps;
unsigned num_deps;
int i, r;
- struct drm_amdgpu_cs_chunk_sem *deps;
deps = (struct drm_amdgpu_cs_chunk_sem *)chunk->kdata;
num_deps = chunk->length_dw * 4 /
sizeof(struct drm_amdgpu_cs_chunk_sem);
+ for (i = 0; i < num_deps; ++i) {
+ r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle,
+ 0, 0);
+ if (r)
+ return r;
+ }
+
+ return 0;
+}
+
+static int amdgpu_cs_process_syncobj_timeline_in_dep(struct amdgpu_cs_parser
*p,
+struct amdgpu_cs_chunk
*chunk)
+{
+ struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;
+ unsigned num_deps;
+ int i, r;
+
+ syncobj_deps = (struct drm_amdgpu_cs_chunk_syncobj *)chunk->kdata;
+ num_deps = chunk->length_dw * 4 /
+ sizeof(struct drm_amdgpu_cs_chunk_syncobj);
for (i = 0; i < num_deps; ++i) {
- r = amdgpu_syncobj_lookup_and_add_to_sync(p, deps[i].handle);
+ r =
