drm/v3d: Create a CPU job extension for the timestamp query job

A CPU job is a type of job that performs operations that requires CPU
intervention. A timestamp query job is a job that calculates the
query timestamp and updates the query availability by signaling a
syncobj. As V3D doesn't provide any mechanism to obtain a timestamp
from the GPU, it is a job that needs CPU intervention.

So, create a user extension for the CPU job that enables the creation
of a timestamp query job. This user extension will allow the creation of
a CPU job that performs the timestamp query calculation and updates the
timestamp BO with the proper value.

Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231130164420.932823-15-mcanal@igalia.com

drivers/gpu/drm/v3d/v3d_drv.h

@@ -318,6 +318,15 @@ struct v3d_csd_job {
 
 enum v3d_cpu_job_type {
 	V3D_CPU_JOB_TYPE_INDIRECT_CSD = 1,
+	V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY,
+};
+
+struct v3d_timestamp_query {
+	/* Offset of this query in the timestamp BO for its value. */
+	u32 offset;
+
+	/* Syncobj that indicates the timestamp availability */
+	struct drm_syncobj *syncobj;
 };
 
 struct v3d_indirect_csd_info {
@@ -345,12 +354,20 @@ struct v3d_indirect_csd_info {
 	struct ww_acquire_ctx acquire_ctx;
 };
 
+struct v3d_timestamp_query_info {
+	struct v3d_timestamp_query *queries;
+
+	u32 count;
+};
+
 struct v3d_cpu_job {
 	struct v3d_job base;
 
 	enum v3d_cpu_job_type job_type;
 
 	struct v3d_indirect_csd_info indirect_csd;
+
+	struct v3d_timestamp_query_info timestamp_query;
 };
 
 typedef void (*v3d_cpu_job_fn)(struct v3d_cpu_job *);

drivers/gpu/drm/v3d/v3d_sched.c

@@ -21,6 +21,8 @@
 #include <linux/sched/clock.h>
 #include <linux/kthread.h>
 
+#include <drm/drm_syncobj.h>
+
 #include "v3d_drv.h"
 #include "v3d_regs.h"
 #include "v3d_trace.h"
@@ -71,6 +73,21 @@ v3d_sched_job_free(struct drm_sched_job *sched_job)
 	v3d_job_cleanup(job);
 }
 
+static void
+v3d_cpu_job_free(struct drm_sched_job *sched_job)
+{
+	struct v3d_cpu_job *job = to_cpu_job(sched_job);
+	struct v3d_timestamp_query_info *timestamp_query = &job->timestamp_query;
+
+	if (timestamp_query->queries) {
+		for (int i = 0; i < timestamp_query->count; i++)
+			drm_syncobj_put(timestamp_query->queries[i].syncobj);
+		kvfree(timestamp_query->queries);
+	}
+
+	v3d_job_cleanup(&job->base);
+}
+
 static void
 v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job)
 {
@@ -305,8 +322,29 @@ v3d_rewrite_csd_job_wg_counts_from_indirect(struct v3d_cpu_job *job)
 	v3d_put_bo_vaddr(bo);
 }
 
+static void
+v3d_timestamp_query(struct v3d_cpu_job *job)
+{
+	struct v3d_timestamp_query_info *timestamp_query = &job->timestamp_query;
+	struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]);
+	u8 *value_addr;
+
+	v3d_get_bo_vaddr(bo);
+
+	for (int i = 0; i < timestamp_query->count; i++) {
+		value_addr = ((u8 *)bo->vaddr) + timestamp_query->queries[i].offset;
+		*((u64 *)value_addr) = i == 0 ? ktime_get_ns() : 0ull;
+
+		drm_syncobj_replace_fence(timestamp_query->queries[i].syncobj,
+					  job->base.done_fence);
+	}
+
+	v3d_put_bo_vaddr(bo);
+}
+
 static const v3d_cpu_job_fn cpu_job_function[] = {
 	[V3D_CPU_JOB_TYPE_INDIRECT_CSD] = v3d_rewrite_csd_job_wg_counts_from_indirect,
+	[V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY] = v3d_timestamp_query,
 };
 
 static struct dma_fence *
@@ -504,7 +542,7 @@ static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = {
 static const struct drm_sched_backend_ops v3d_cpu_sched_ops = {
 	.run_job = v3d_cpu_job_run,
 	.timedout_job = v3d_generic_job_timedout,
-	.free_job = v3d_sched_job_free
+	.free_job = v3d_cpu_job_free
 };
 
 int

drivers/gpu/drm/v3d/v3d_submit.c

@@ -433,6 +433,64 @@ v3d_get_cpu_indirect_csd_params(struct drm_file *file_priv,
 					  NULL, &info->acquire_ctx);
 }
 
+/* Get data for the query timestamp job submission. */
+static int
+v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv,
+				   struct drm_v3d_extension __user *ext,
+				   struct v3d_cpu_job *job)
+{
+	u32 __user *offsets, *syncs;
+	struct drm_v3d_timestamp_query timestamp;
+
+	if (!job) {
+		DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
+		return -EINVAL;
+	}
+
+	if (job->job_type) {
+		DRM_DEBUG("Two CPU job extensions were added to the same CPU job.\n");
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&timestamp, ext, sizeof(timestamp)))
+		return -EFAULT;
+
+	if (timestamp.pad)
+		return -EINVAL;
+
+	job->job_type = V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY;
+
+	job->timestamp_query.queries = kvmalloc_array(timestamp.count,
+						      sizeof(struct v3d_timestamp_query),
+						      GFP_KERNEL);
+	if (!job->timestamp_query.queries)
+		return -ENOMEM;
+
+	offsets = u64_to_user_ptr(timestamp.offsets);
+	syncs = u64_to_user_ptr(timestamp.syncs);
+
+	for (int i = 0; i < timestamp.count; i++) {
+		u32 offset, sync;
+
+		if (copy_from_user(&offset, offsets++, sizeof(offset))) {
+			kvfree(job->timestamp_query.queries);
+			return -EFAULT;
+		}
+
+		job->timestamp_query.queries[i].offset = offset;
+
+		if (copy_from_user(&sync, syncs++, sizeof(sync))) {
+			kvfree(job->timestamp_query.queries);
+			return -EFAULT;
+		}
+
+		job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+	}
+	job->timestamp_query.count = timestamp.count;
+
+	return 0;
+}
+
 /* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data
  * according to the extension id (name).
  */
@@ -461,6 +519,9 @@ v3d_get_extensions(struct drm_file *file_priv,
 		case DRM_V3D_EXT_ID_CPU_INDIRECT_CSD:
 			ret = v3d_get_cpu_indirect_csd_params(file_priv, user_ext, job);
 			break;
+		case DRM_V3D_EXT_ID_CPU_TIMESTAMP_QUERY:
+			ret = v3d_get_cpu_timestamp_query_params(file_priv, user_ext, job);
+			break;
 		default:
 			DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id);
 			return -EINVAL;
@@ -837,6 +898,7 @@ fail:
 
 static const unsigned int cpu_job_bo_handle_count[] = {
 	[V3D_CPU_JOB_TYPE_INDIRECT_CSD] = 1,
+	[V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY] = 1,
 };
 
 /**
@@ -974,6 +1036,7 @@ fail:
 	v3d_job_cleanup((void *)csd_job);
 	v3d_job_cleanup(clean_job);
 	v3d_put_multisync_post_deps(&se);
+	kvfree(cpu_job->timestamp_query.queries);
 
 	return ret;
 }

include/uapi/drm/v3d_drm.h

@@ -73,6 +73,7 @@ struct drm_v3d_extension {
 	__u32 id;
 #define DRM_V3D_EXT_ID_MULTI_SYNC			0x01
 #define DRM_V3D_EXT_ID_CPU_INDIRECT_CSD		0x02
+#define DRM_V3D_EXT_ID_CPU_TIMESTAMP_QUERY		0x03
 	__u32 flags; /* mbz */
 };
 
@@ -400,11 +401,40 @@ struct drm_v3d_indirect_csd {
 	__u32 wg_uniform_offsets[3];
 };
 
+/**
+ * struct drm_v3d_timestamp_query - ioctl extension for the CPU job to calculate
+ * a timestamp query
+ *
+ * When an extension DRM_V3D_EXT_ID_TIMESTAMP_QUERY is defined, it points to
+ * this extension to define a timestamp query submission. This CPU job will
+ * calculate the timestamp query and update the query value within the
+ * timestamp BO. Moreover, it will signal the timestamp syncobj to indicate
+ * query availability.
+ */
+struct drm_v3d_timestamp_query {
+	struct drm_v3d_extension base;
+
+	/* Array of queries' offsets within the timestamp BO for their value */
+	__u64 offsets;
+
+	/* Array of timestamp's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* mbz */
+	__u32 pad;
+};
+
 struct drm_v3d_submit_cpu {
 	/* Pointer to a u32 array of the BOs that are referenced by the job.
 	 *
 	 * For DRM_V3D_EXT_ID_CPU_INDIRECT_CSD, it must contain only one BO,
 	 * that contains the workgroup counts.
+	 *
+	 * For DRM_V3D_EXT_ID_TIMESTAMP_QUERY, it must contain only one BO,
+	 * that will contain the timestamp.
 	 */
 	__u64 bo_handles;