drm/amdgpu: add the interface of waiting multiple fences (v4)

v2: agd: rebase and squash in all the previous optimizations and
changes so everything compiles.
v3: squash in Slava's 32bit build fix
v4: rebase on drm-next (fence -> dma_fence),
    squash in Monk's ioctl update patch
Signed-off-by: NJunwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: NMonk Liu <monk.liu@amd.com>
Reviewed-by: NJammy Zhou <Jammy.Zhou@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Signed-off-by: NSumit Semwal <sumit.semwal@linaro.org>
 [sumits: fix checkpatch warnings]
Link: http://patchwork.freedesktop.org/patch/msgid/1478290570-30982-2-git-send-email-alexander.deucher@amd.com

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -1212,6 +1212,8 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *filp);
 int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
 int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
+int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *filp);
 
 int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp);

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

@@ -1139,6 +1139,180 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+/**
+ * amdgpu_cs_get_fence - helper to get fence from drm_amdgpu_fence
+ *
+ * @adev: amdgpu device
+ * @filp: file private
+ * @user: drm_amdgpu_fence copied from user space
+ */
+static struct dma_fence *amdgpu_cs_get_fence(struct amdgpu_device *adev,
+					     struct drm_file *filp,
+					     struct drm_amdgpu_fence *user)
+{
+	struct amdgpu_ring *ring;
+	struct amdgpu_ctx *ctx;
+	struct dma_fence *fence;
+	int r;
+
+	r = amdgpu_cs_get_ring(adev, user->ip_type, user->ip_instance,
+			       user->ring, &ring);
+	if (r)
+		return ERR_PTR(r);
+
+	ctx = amdgpu_ctx_get(filp->driver_priv, user->ctx_id);
+	if (ctx == NULL)
+		return ERR_PTR(-EINVAL);
+
+	fence = amdgpu_ctx_get_fence(ctx, ring, user->seq_no);
+	amdgpu_ctx_put(ctx);
+
+	return fence;
+}
+
+/**
+ * amdgpu_cs_wait_all_fence - wait on all fences to signal
+ *
+ * @adev: amdgpu device
+ * @filp: file private
+ * @wait: wait parameters
+ * @fences: array of drm_amdgpu_fence
+ */
+static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev,
+				     struct drm_file *filp,
+				     union drm_amdgpu_wait_fences *wait,
+				     struct drm_amdgpu_fence *fences)
+{
+	uint32_t fence_count = wait->in.fence_count;
+	unsigned int i;
+	long r = 1;
+
+	for (i = 0; i < fence_count; i++) {
+		struct dma_fence *fence;
+		unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout_ns);
+
+		fence = amdgpu_cs_get_fence(adev, filp, &fences[i]);
+		if (IS_ERR(fence))
+			return PTR_ERR(fence);
+		else if (!fence)
+			continue;
+
+		r = dma_fence_wait_timeout(fence, true, timeout);
+		if (r < 0)
+			return r;
+
+		if (r == 0)
+			break;
+	}
+
+	memset(wait, 0, sizeof(*wait));
+	wait->out.status = (r > 0);
+
+	return 0;
+}
+
+/**
+ * amdgpu_cs_wait_any_fence - wait on any fence to signal
+ *
+ * @adev: amdgpu device
+ * @filp: file private
+ * @wait: wait parameters
+ * @fences: array of drm_amdgpu_fence
+ */
+static int amdgpu_cs_wait_any_fence(struct amdgpu_device *adev,
+				    struct drm_file *filp,
+				    union drm_amdgpu_wait_fences *wait,
+				    struct drm_amdgpu_fence *fences)
+{
+	unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout_ns);
+	uint32_t fence_count = wait->in.fence_count;
+	uint32_t first = ~0;
+	struct dma_fence **array;
+	unsigned int i;
+	long r;
+
+	/* Prepare the fence array */
+	array = kcalloc(fence_count, sizeof(struct dma_fence *), GFP_KERNEL);
+
+	if (array == NULL)
+		return -ENOMEM;
+
+	for (i = 0; i < fence_count; i++) {
+		struct dma_fence *fence;
+
+		fence = amdgpu_cs_get_fence(adev, filp, &fences[i]);
+		if (IS_ERR(fence)) {
+			r = PTR_ERR(fence);
+			goto err_free_fence_array;
+		} else if (fence) {
+			array[i] = fence;
+		} else { /* NULL, the fence has been already signaled */
+			r = 1;
+			goto out;
+		}
+	}
+
+	r = dma_fence_wait_any_timeout(array, fence_count, true, timeout,
+				       &first);
+	if (r < 0)
+		goto err_free_fence_array;
+
+out:
+	memset(wait, 0, sizeof(*wait));
+	wait->out.status = (r > 0);
+	wait->out.first_signaled = first;
+	/* set return value 0 to indicate success */
+	r = 0;
+
+err_free_fence_array:
+	for (i = 0; i < fence_count; i++)
+		dma_fence_put(array[i]);
+	kfree(array);
+
+	return r;
+}
+
+/**
+ * amdgpu_cs_wait_fences_ioctl - wait for multiple command submissions to finish
+ *
+ * @dev: drm device
+ * @data: data from userspace
+ * @filp: file private
+ */
+int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *filp)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	union drm_amdgpu_wait_fences *wait = data;
+	uint32_t fence_count = wait->in.fence_count;
+	struct drm_amdgpu_fence *fences_user;
+	struct drm_amdgpu_fence *fences;
+	int r;
+
+	/* Get the fences from userspace */
+	fences = kmalloc_array(fence_count, sizeof(struct drm_amdgpu_fence),
+			GFP_KERNEL);
+	if (fences == NULL)
+		return -ENOMEM;
+
+	fences_user = (void __user *)(unsigned long)(wait->in.fences);
+	if (copy_from_user(fences, fences_user,
+		sizeof(struct drm_amdgpu_fence) * fence_count)) {
+		r = -EFAULT;
+		goto err_free_fences;
+	}
+
+	if (wait->in.wait_all)
+		r = amdgpu_cs_wait_all_fences(adev, filp, wait, fences);
+	else
+		r = amdgpu_cs_wait_any_fence(adev, filp, wait, fences);
+
+err_free_fences:
+	kfree(fences);
+
+	return r;
+}
+
 /**
  * amdgpu_cs_find_bo_va - find bo_va for VM address
  *

drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

@@ -825,6 +825,7 @@ const struct drm_ioctl_desc amdgpu_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(AMDGPU_CS, amdgpu_cs_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_INFO, amdgpu_info_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_WAIT_CS, amdgpu_cs_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(AMDGPU_WAIT_FENCES, amdgpu_cs_wait_fences_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_GEM_METADATA, amdgpu_gem_metadata_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_GEM_VA, amdgpu_gem_va_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_GEM_OP, amdgpu_gem_op_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),

drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c

@@ -361,7 +361,8 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 		if (count) {
 			spin_unlock(&sa_manager->wq.lock);
 			t = dma_fence_wait_any_timeout(fences, count, false,
-						       MAX_SCHEDULE_TIMEOUT);
+						       MAX_SCHEDULE_TIMEOUT,
+						       NULL);
 			for (i = 0; i < count; ++i)
 				dma_fence_put(fences[i]);
 

include/uapi/drm/amdgpu_drm.h

@@ -50,6 +50,7 @@ extern "C" {
 #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)
@@ -63,6 +64,7 @@ extern "C" {
 #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
@@ -307,6 +309,32 @@ union drm_amdgpu_wait_cs {
 	struct drm_amdgpu_wait_cs_out out;
 };
 
+struct drm_amdgpu_fence {
+	__u32 ctx_id;
+	__u32 ip_type;
+	__u32 ip_instance;
+	__u32 ring;
+	__u64 seq_no;
+};
+
+struct drm_amdgpu_wait_fences_in {
+	/** This points to uint64_t * which points to fences */
+	__u64 fences;
+	__u32 fence_count;
+	__u32 wait_all;
+	__u64 timeout_ns;
+};
+
+struct drm_amdgpu_wait_fences_out {
+	__u32 status;
+	__u32 first_signaled;
+};
+
+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