[PATCH 02/10] amdgpu: add the interface of waiting multiple fences

[Marek Olšák]

From: Junwei Zhang <Jerry.Zhang at amd.com>

Signed-off-by: Junwei Zhang <Jerry.Zhang at amd.com>
Reviewed-by: Christian König <christian.koenig at amd.com>
Reviewed-by: Jammy Zhou <Jammy.Zhou at amd.com>
---
 amdgpu/amdgpu.h          | 22 +++++++++++++++
 amdgpu/amdgpu_cs.c       | 71 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/drm/amdgpu_drm.h | 27 ++++++++++++++++++
 3 files changed, 120 insertions(+)

diff --git a/amdgpu/amdgpu.h b/amdgpu/amdgpu.h
index e44d802..9ae6ca3 100644
--- a/amdgpu/amdgpu.h
+++ b/amdgpu/amdgpu.h
@@ -902,6 +902,28 @@ int amdgpu_cs_query_fence_status(struct amdgpu_cs_fence *fence,
 				 uint64_t flags,
 				 uint32_t *expired);
 
+/**
+ *  Wait for multiple fences
+ *
+ * \param   fences      - \c [in] The fence array to wait
+ * \param   fence_count - \c [in] The fence count
+ * \param   wait_all    - \c [in] If true, wait all fences to be signaled,
+ *                                otherwise, wait at least one fence
+ * \param   timeout_ns  - \c [in] The timeout to wait, in nanoseconds
+ * \param   status      - \c [out] '1' for signaled, '0' for timeout
+ *
+ * \return  0 on success
+ *          <0 - Negative POSIX Error code
+ *
+ * \note    Currently it supports only one amdgpu_device. All fences come from
+ *          the same amdgpu_device with the same fd.
+*/
+int amdgpu_cs_wait_fences(struct amdgpu_cs_fence *fences,
+			  uint32_t fence_count,
+			  bool wait_all,
+			  uint64_t timeout_ns,
+			  uint32_t *status);
+
 /*
  * Query / Info API
  *
diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
index 511d53f..d5e4ea0 100644
--- a/amdgpu/amdgpu_cs.c
+++ b/amdgpu/amdgpu_cs.c
@@ -379,3 +379,74 @@ int amdgpu_cs_query_fence_status(struct amdgpu_cs_fence *fence,
 	return r;
 }
 
+static int amdgpu_ioctl_wait_fences(struct amdgpu_cs_fence *fences,
+				    uint32_t fence_count,
+				    bool wait_all,
+				    uint64_t timeout_ns,
+				    uint32_t *status)
+{
+	struct drm_amdgpu_fence *drm_fences;
+	amdgpu_device_handle dev = fences[0].context->dev;
+	union drm_amdgpu_wait_fences args;
+	int r;
+	uint32_t i;
+
+	drm_fences = alloca(sizeof(struct drm_amdgpu_fence) * fence_count);
+	for (i = 0; i < fence_count; i++) {
+		drm_fences[i].ctx_id = fences[i].context->id;
+		drm_fences[i].ip_type = fences[i].ip_type;
+		drm_fences[i].ip_instance = fences[i].ip_instance;
+		drm_fences[i].ring = fences[i].ring;
+		drm_fences[i].seq_no = fences[i].fence;
+	}
+
+	memset(&args, 0, sizeof(args));
+	args.in.fences = (uint64_t)(uintptr_t)drm_fences;
+	args.in.fence_count = fence_count;
+	args.in.wait_all = wait_all;
+	args.in.timeout_ns = amdgpu_cs_calculate_timeout(timeout_ns);
+
+	r = drmIoctl(dev->fd, DRM_IOCTL_AMDGPU_WAIT_FENCES, &args);
+	if (r)
+		return -errno;
+
+	*status = args.out.status;
+	return 0;
+}
+
+int amdgpu_cs_wait_fences(struct amdgpu_cs_fence *fences,
+			  uint32_t fence_count,
+			  bool wait_all,
+			  uint64_t timeout_ns,
+			  uint32_t *status)
+{
+	uint32_t ioctl_status = 0;
+	uint32_t i;
+	int r;
+
+	/* Sanity check */
+	if (NULL == fences)
+		return -EINVAL;
+	if (NULL == status)
+		return -EINVAL;
+	if (fence_count <= 0)
+		return -EINVAL;
+	for (i = 0; i < fence_count; i++) {
+		if (NULL == fences[i].context)
+			return -EINVAL;
+		if (fences[i].ip_type >= AMDGPU_HW_IP_NUM)
+			return -EINVAL;
+		if (fences[i].ring >= AMDGPU_CS_MAX_RINGS)
+			return -EINVAL;
+	}
+
+	*status = 0;
+
+	r = amdgpu_ioctl_wait_fences(fences, fence_count, wait_all, timeout_ns,
+					&ioctl_status);
+
+	if (!r)
+		*status = ioctl_status;
+
+	return r;
+}
diff --git a/include/drm/amdgpu_drm.h b/include/drm/amdgpu_drm.h
index fbdd118..2cbea72 100644
--- a/include/drm/amdgpu_drm.h
+++ b/include/drm/amdgpu_drm.h
@@ -46,6 +46,7 @@
 #define DRM_AMDGPU_WAIT_CS		0x09
 #define DRM_AMDGPU_GEM_OP		0x10
 #define DRM_AMDGPU_GEM_USERPTR		0x11
+#define DRM_AMDGPU_WAIT_FENCES		0x12
 
 #define DRM_IOCTL_AMDGPU_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
 #define DRM_IOCTL_AMDGPU_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
@@ -59,6 +60,7 @@
 #define DRM_IOCTL_AMDGPU_WAIT_CS	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_CS, union drm_amdgpu_wait_cs)
 #define DRM_IOCTL_AMDGPU_GEM_OP		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_OP, struct drm_amdgpu_gem_op)
 #define DRM_IOCTL_AMDGPU_GEM_USERPTR	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_USERPTR, struct drm_amdgpu_gem_userptr)
+#define DRM_IOCTL_AMDGPU_WAIT_FENCES	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_FENCES, union drm_amdgpu_wait_fences)
 
 #define AMDGPU_GEM_DOMAIN_CPU		0x1
 #define AMDGPU_GEM_DOMAIN_GTT		0x2
@@ -297,6 +299,31 @@ union drm_amdgpu_wait_cs {
 	struct drm_amdgpu_wait_cs_out out;
 };
 
+struct drm_amdgpu_fence {
+	uint32_t ctx_id;
+	uint32_t ip_type;
+	uint32_t ip_instance;
+	uint32_t ring;
+	uint64_t seq_no;
+};
+
+struct drm_amdgpu_wait_fences_in {
+	/** This points to uint64_t * which points to fences */
+	uint64_t fences;
+	uint32_t fence_count;
+	uint32_t wait_all;
+	uint64_t timeout_ns;
+};
+
+struct drm_amdgpu_wait_fences_out {
+	uint64_t status;
+};
+
+union drm_amdgpu_wait_fences {
+	struct drm_amdgpu_wait_fences_in in;
+	struct drm_amdgpu_wait_fences_out out;
+};
+
 #define AMDGPU_GEM_OP_GET_GEM_CREATE_INFO	0
 #define AMDGPU_GEM_OP_SET_PLACEMENT		1
 
-- 
2.1.4