drm/v3d: add multiple syncobjs support

Using the generic extension from the previous patch, a specific multisync
extension enables more than one in/out binary syncobj per job submission.
Arrays of syncobjs are set in struct drm_v3d_multisync, that also cares
of determining the stage for sync (wait deps) according to the job
queue.

v2:
- subclass the generic extension struct (Daniel)
- simplify adding dependency conditions to make understandable (Iago)

v3:
- fix conditions to consider single or multiples in/out_syncs (Iago)
- remove irrelevant comment (Iago)
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ffd8b2e3dd2e0c686db441a0c0a4a0181ff85328.1633016479.git.mwen@igalia.com

drivers/gpu/drm/v3d/v3d_drv.c

@@ -96,6 +96,9 @@ static int v3d_get_param_ioctl(struct drm_device *dev, void *data,
 	case DRM_V3D_PARAM_SUPPORTS_PERFMON:
 		args->value = (v3d->ver >= 40);
 		return 0;
+	case DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT:
+		args->value = 1;
+		return 0;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", args->param);
 		return -EINVAL;
@@ -135,9 +138,8 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file)
 	struct v3d_file_priv *v3d_priv = file->driver_priv;
 	enum v3d_queue q;
 
-	for (q = 0; q < V3D_MAX_QUEUES; q++) {
+	for (q = 0; q < V3D_MAX_QUEUES; q++)
 		drm_sched_entity_destroy(&v3d_priv->sched_entity[q]);
-	}
 
 	v3d_perfmon_close_file(v3d_priv);
 	kfree(v3d_priv);

drivers/gpu/drm/v3d/v3d_drv.h

@@ -19,15 +19,6 @@ struct reset_control;
 
 #define GMP_GRANULARITY (128 * 1024)
 
-/* Enum for each of the V3D queues. */
-enum v3d_queue {
-	V3D_BIN,
-	V3D_RENDER,
-	V3D_TFU,
-	V3D_CSD,
-	V3D_CACHE_CLEAN,
-};
-
 #define V3D_MAX_QUEUES (V3D_CACHE_CLEAN + 1)
 
 struct v3d_queue_state {
@@ -294,6 +285,21 @@ struct v3d_csd_job {
 	struct drm_v3d_submit_csd args;
 };
 
+struct v3d_submit_outsync {
+	struct drm_syncobj *syncobj;
+};
+
+struct v3d_submit_ext {
+	u32 flags;
+	u32 wait_stage;
+
+	u32 in_sync_count;
+	u64 in_syncs;
+
+	u32 out_sync_count;
+	struct v3d_submit_outsync *out_syncs;
+};
+
 /**
  * __wait_for - magic wait macro
  *

include/uapi/drm/v3d_drm.h

@@ -73,6 +73,53 @@ struct drm_v3d_extension {
 	__u32 flags; /* mbz */
 };
 
+/* struct drm_v3d_sem - wait/signal semaphore
+ *
+ * If binary semaphore, it only takes syncobj handle and ignores flags and
+ * point fields. Point is defined for timeline syncobj feature.
+ */
+struct drm_v3d_sem {
+	__u32 handle; /* syncobj */
+	/* rsv below, for future uses */
+	__u32 flags;
+	__u64 point;  /* for timeline sem support */
+	__u64 mbz[2]; /* must be zero, rsv */
+};
+
+/* Enum for each of the V3D queues. */
+enum v3d_queue {
+	V3D_BIN,
+	V3D_RENDER,
+	V3D_TFU,
+	V3D_CSD,
+	V3D_CACHE_CLEAN,
+};
+
+/**
+ * struct drm_v3d_multi_sync - ioctl extension to add support multiples
+ * syncobjs for commands submission.
+ *
+ * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to
+ * this extension to define wait and signal dependencies, instead of single
+ * in/out sync entries on submitting commands. The field flags is used to
+ * determine the stage to set wait dependencies.
+ */
+struct drm_v3d_multi_sync {
+	struct drm_v3d_extension base;
+	/* Array of wait and signal semaphores */
+	__u64 in_syncs;
+	__u64 out_syncs;
+
+	/* Number of entries */
+	__u32 in_sync_count;
+	__u32 out_sync_count;
+
+	/* set the stage (v3d_queue) to sync */
+	__u32 wait_stage;
+
+	__u32 pad; /* mbz */
+};
+
 /**
  * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D
  * engine.
@@ -228,6 +275,7 @@ enum drm_v3d_param {
 	DRM_V3D_PARAM_SUPPORTS_CSD,
 	DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH,
 	DRM_V3D_PARAM_SUPPORTS_PERFMON,
+	DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT,
 };
 
 struct drm_v3d_get_param {
@@ -271,7 +319,6 @@ struct drm_v3d_submit_tfu {
 
 	/* Pointer to an array of ioctl extensions*/
 	__u64 extensions;
-
 };
 
 /* Submits a compute shader for dispatch.  This job will block on any