[8/8] amdgpu: use sync file for shared semaphores (v2.1)

Commit Message

Mao, David April 12, 2017, 2:36 a.m. UTC

Does it means we have to submit command to trigger the semaphore wait/signal?

Best Regards,
David

-----Original Message-----
From: amd-gfx [mailto:[e-mail]] On Behalf Of Dave Airlie
Sent: Tuesday, April 11, 2017 11:22 AM
To: [e-mail]; [e-mail]
Subject: [PATCH 8/8] amdgpu: use sync file for shared semaphores (v2.1)

From: Dave Airlie <[e-mail]>

This creates a new command submission chunk for amdgpu to add wait and signal sync objects around the submission.

Sync objects are managed via the drm syncobj ioctls.

The command submission interface is enhanced with two new chunks, one for semaphore waiting, one for semaphore signalling and just takes a list of handles for each.

This is based on work originally done by David Zhou at AMD, with input from Christian Konig on what things should look like.

NOTE: this interface addition needs a version bump to expose it to userspace.

v1.1: keep file reference on import.
v2: move to using syncobjs
v2.1: change some APIs to just use p pointer.

Signed-off-by: Dave Airlie <[e-mail]>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  | 82 ++++++++++++++++++++++++++++++++-  drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c |  2 +-
 include/uapi/drm/amdgpu_drm.h           |  6 +++
 3 files changed, 88 insertions(+), 2 deletions(-)

--
2.9.3

_______________________________________________
amd-gfx mailing list
[e-mail]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index df25b32..77bfe80 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -27,6 +27,7 @@ 
 #include <linux/pagemap.h>
 #include <drm/drmP.h>
 #include <drm/amdgpu_drm.h>
+#include <drm/drm_syncobj.h>
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 
@@ -217,6 +218,8 @@  int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 			break;
 
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
+		case AMDGPU_CHUNK_ID_SEM_WAIT:
+		case AMDGPU_CHUNK_ID_SEM_SIGNAL:
 			break;
 
 		default:
@@ -1008,6 +1011,41 @@  static int amdgpu_process_fence_dep(struct amdgpu_cs_parser *p,
 	return 0;
 }
 
+static int amdgpu_sem_lookup_and_sync(struct amdgpu_cs_parser *p,
+				      uint32_t handle)
+{
+	int r;
+	struct dma_fence *old_fence;
+
+	r = drm_syncobj_swap_fences(p->filp, handle, NULL, &old_fence);
+	if (r)
+		return r;
+
+	r = amdgpu_sync_fence(p->adev, &p->job->sync, old_fence);
+	dma_fence_put(old_fence);
+
+	return r;
+}
+
+static int amdgpu_process_sem_wait_dep(struct amdgpu_cs_parser *p,
+				       struct amdgpu_cs_chunk *chunk) {
+	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_sem_lookup_and_sync(p, deps[i].handle);
+		if (r)
+			return r;
+	}
+	return 0;
+}
+
 static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 				  struct amdgpu_cs_parser *p)
 {
@@ -1022,12 +1060,54 @@  static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 			r = amdgpu_process_fence_dep(p, chunk);
 			if (r)
 				return r;
+		} else if (chunk->chunk_id == AMDGPU_CHUNK_ID_SEM_WAIT) {
+			r = amdgpu_process_sem_wait_dep(p, chunk);
+			if (r)
+				return r;
 		}
 	}
 
 	return 0;
 }
 
+static int amdgpu_process_sem_signal_dep(struct amdgpu_cs_parser *p,
+					 struct amdgpu_cs_chunk *chunk)
+{
+	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 = drm_syncobj_replace_fence(p->filp, deps[i].handle,
+					      p->fence);
+		if (r)
+			return r;
+	}
+	return 0;
+}
+
+static int amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p) {
+	int i, r;
+
+	for (i = 0; i < p->nchunks; ++i) {
+		struct amdgpu_cs_chunk *chunk;
+
+		chunk = &p->chunks[i];
+
+		if (chunk->chunk_id == AMDGPU_CHUNK_ID_SEM_SIGNAL) {
+			r = amdgpu_process_sem_signal_dep(p, chunk);
+			if (r)
+				return r;
+		}
+	}
+	return 0;
+}
+
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
@@ -1055,7 +1135,7 @@  static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	trace_amdgpu_cs_ioctl(job);
 	amd_sched_entity_push_job(&job->base);
 
-	return 0;
+	return amdgpu_cs_post_dependencies(p);
 }
 
 int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b76cd69..e95951e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -683,7 +683,7 @@  static struct drm_driver kms_driver = {
 	.driver_features =
 	    DRIVER_USE_AGP |
 	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM |
-	    DRIVER_PRIME | DRIVER_RENDER | DRIVER_MODESET,
+	    DRIVER_PRIME | DRIVER_RENDER | DRIVER_MODESET | DRIVER_SYNCOBJ,
 	.load = amdgpu_driver_load_kms,
 	.open = amdgpu_driver_open_kms,
 	.preclose = amdgpu_driver_preclose_kms, diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 5797283..647c520 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -390,6 +390,8 @@  struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_IB		0x01
 #define AMDGPU_CHUNK_ID_FENCE		0x02
 #define AMDGPU_CHUNK_ID_DEPENDENCIES	0x03
+#define AMDGPU_CHUNK_ID_SEM_WAIT        0x04
+#define AMDGPU_CHUNK_ID_SEM_SIGNAL      0x05
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
@@ -454,6 +456,10 @@  struct drm_amdgpu_cs_chunk_fence {
 	__u32 offset;
 };
 
+struct drm_amdgpu_cs_chunk_sem {
+	__u32 handle;
+};
+
 struct drm_amdgpu_cs_chunk_data {
 	union {
 		struct drm_amdgpu_cs_chunk_ib		ib_data;