drm/v3d: Create a CPU job extension to copy timestamp query to a buffer

A CPU job is a type of job that performs operations that requires CPU
intervention. A copy timestamp query job is a job that copy the complete
or partial result of a query to a buffer. 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 copy timestamp query job. This user extension will allow the creation
of a CPU job that copy the results of a timestamp query to a BO with the
possibility to indicate the timestamp availability with a availability bit.

Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231130164420.932823-17-mcanal@igalia.com

3 files changed, 145 insertions, 0 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 3988407635ed..5058a354fffd 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -320,6 +320,7 @@ enum v3d_cpu_job_type {
 	V3D_CPU_JOB_TYPE_INDIRECT_CSD = 1,
 	V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY,
 	V3D_CPU_JOB_TYPE_RESET_TIMESTAMP_QUERY,
+	V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY,
 };
 
 struct v3d_timestamp_query {
@@ -361,6 +362,23 @@ struct v3d_timestamp_query_info {
 	u32 count;
 };
 
+struct v3d_copy_query_results_info {
+	/* Define if should write to buffer using 64 or 32 bits */
+	bool do_64bit;
+
+	/* Define if it can write to buffer even if the query is not available */
+	bool do_partial;
+
+	/* Define if it should write availability bit to buffer */
+	bool availability_bit;
+
+	/* Offset of the copy buffer in the BO */
+	u32 offset;
+
+	/* Stride of the copy buffer in the BO */
+	u32 stride;
+};
+
 struct v3d_cpu_job {
 	struct v3d_job base;
 
@@ -369,6 +387,8 @@ struct v3d_cpu_job {
 	struct v3d_indirect_csd_info indirect_csd;
 
 	struct v3d_timestamp_query_info timestamp_query;
+
+	struct v3d_copy_query_results_info copy;
 };
 
 typedef void (*v3d_cpu_job_fn)(struct v3d_cpu_job *);
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index e287f42d3621..b1662d32a929 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -362,10 +362,66 @@ v3d_reset_timestamp_queries(struct v3d_cpu_job *job)
 	v3d_put_bo_vaddr(bo);
 }
 
+static void
+write_to_buffer(void *dst, u32 idx, bool do_64bit, u64 value)
+{
+	if (do_64bit) {
+		u64 *dst64 = (u64 *)dst;
+
+		dst64[idx] = value;
+	} else {
+		u32 *dst32 = (u32 *)dst;
+
+		dst32[idx] = (u32)value;
+	}
+}
+
+static void
+v3d_copy_query_results(struct v3d_cpu_job *job)
+{
+	struct v3d_timestamp_query_info *timestamp_query = &job->timestamp_query;
+	struct v3d_timestamp_query *queries = timestamp_query->queries;
+	struct v3d_bo *bo = to_v3d_bo(job->base.bo[0]);
+	struct v3d_bo *timestamp = to_v3d_bo(job->base.bo[1]);
+	struct v3d_copy_query_results_info *copy = &job->copy;
+	struct dma_fence *fence;
+	u8 *query_addr;
+	bool available, write_result;
+	u8 *data;
+	int i;
+
+	v3d_get_bo_vaddr(bo);
+	v3d_get_bo_vaddr(timestamp);
+
+	data = ((u8 *)bo->vaddr) + copy->offset;
+
+	for (i = 0; i < timestamp_query->count; i++) {
+		fence = drm_syncobj_fence_get(queries[i].syncobj);
+		available = fence ? dma_fence_is_signaled(fence) : false;
+
+		write_result = available || copy->do_partial;
+		if (write_result) {
+			query_addr = ((u8 *)timestamp->vaddr) + queries[i].offset;
+			write_to_buffer(data, 0, copy->do_64bit, *((u64 *)query_addr));
+		}
+
+		if (copy->availability_bit)
+			write_to_buffer(data, 1, copy->do_64bit, available ? 1u : 0u);
+
+		data += copy->stride;
+
+		dma_fence_put(fence);
+	}
+
+	v3d_put_bo_vaddr(timestamp);
+	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,
 	[V3D_CPU_JOB_TYPE_RESET_TIMESTAMP_QUERY] = v3d_reset_timestamp_queries,
+	[V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY] = v3d_copy_query_results,
 };
 
 static struct dma_fence *
diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index 1c719416e26a..bafd49c6440c 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -539,6 +539,71 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv,
 	return 0;
 }
 
+/* Get data for the copy timestamp query results job submission. */
+static int
+v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv,
+				      struct drm_v3d_extension __user *ext,
+				      struct v3d_cpu_job *job)
+{
+	u32 __user *offsets, *syncs;
+	struct drm_v3d_copy_timestamp_query copy;
+	int i;
+
+	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(&copy, ext, sizeof(copy)))
+		return -EFAULT;
+
+	if (copy.pad)
+		return -EINVAL;
+
+	job->job_type = V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY;
+
+	job->timestamp_query.queries = kvmalloc_array(copy.count,
+						      sizeof(struct v3d_timestamp_query),
+						      GFP_KERNEL);
+	if (!job->timestamp_query.queries)
+		return -ENOMEM;
+
+	offsets = u64_to_user_ptr(copy.offsets);
+	syncs = u64_to_user_ptr(copy.syncs);
+
+	for (i = 0; i < copy.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 = copy.count;
+
+	job->copy.do_64bit = copy.do_64bit;
+	job->copy.do_partial = copy.do_partial;
+	job->copy.availability_bit = copy.availability_bit;
+	job->copy.offset = copy.offset;
+	job->copy.stride = copy.stride;
+
+	return 0;
+}
+
 /* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data
  * according to the extension id (name).
  */
@@ -573,6 +638,9 @@ v3d_get_extensions(struct drm_file *file_priv,
 		case DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY:
 			ret = v3d_get_cpu_reset_timestamp_params(file_priv, user_ext, job);
 			break;
+		case DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY:
+			ret = v3d_get_cpu_copy_query_results_params(file_priv, user_ext, job);
+			break;
 		default:
 			DRM_DEBUG_DRIVER("Unknown extension id: %d\n", ext.id);
 			return -EINVAL;
@@ -951,6 +1019,7 @@ static const unsigned int cpu_job_bo_handle_count[] = {
 	[V3D_CPU_JOB_TYPE_INDIRECT_CSD] = 1,
 	[V3D_CPU_JOB_TYPE_TIMESTAMP_QUERY] = 1,
 	[V3D_CPU_JOB_TYPE_RESET_TIMESTAMP_QUERY] = 1,
+	[V3D_CPU_JOB_TYPE_COPY_TIMESTAMP_QUERY] = 2,
 };
 
 /**