[v2] drm/v3d: Add DRM_IOCTL_V3D_PERFMON_SET_GLOBAL

Commit Message

Christian Gmeiner Oct. 31, 2024, 8:51 p.m. UTC

From: Christian Gmeiner <[e-mail]>

Add a new ioctl, DRM_IOCTL_V3D_PERFMON_SET_GLOBAL, to allow
configuration of a global performance monitor (perfmon).
Use the global perfmon for all jobs to ensure consistent
performance tracking across submissions.

Signed-off-by: Christian Gmeiner <[e-mail]>

---
Changes in v2:
- Reworked commit message.
- Removed num_perfmon counter for tracking perfmon allocations.
- Allowing allocation of perfmons when the global perfmon is active.
- Return -EAGAIN for submissions with a per job perfmon if the global perfmon is active.
---
 drivers/gpu/drm/v3d/v3d_drv.c     |  1 +
 drivers/gpu/drm/v3d/v3d_drv.h     |  8 ++++++++
 drivers/gpu/drm/v3d/v3d_perfmon.c | 34 +++++++++++++++++++++++++++++++
 drivers/gpu/drm/v3d/v3d_sched.c   | 14 ++++++++++---
 drivers/gpu/drm/v3d/v3d_submit.c  | 10 +++++++++
 include/uapi/drm/v3d_drm.h        | 15 ++++++++++++++
 6 files changed, 79 insertions(+), 3 deletions(-)

Patch

diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index d7ff1f5fa481..3c89f0daa5b8 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -214,6 +214,7 @@  static const struct drm_ioctl_desc v3d_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_VALUES, v3d_perfmon_get_values_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(V3D_SUBMIT_CPU, v3d_submit_cpu_ioctl, DRM_RENDER_ALLOW | DRM_AUTH),
 	DRM_IOCTL_DEF_DRV(V3D_PERFMON_GET_COUNTER, v3d_perfmon_get_counter_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(V3D_PERFMON_SET_GLOBAL, v3d_perfmon_set_global_ioctl, DRM_RENDER_ALLOW),
 };
 
 static const struct drm_driver v3d_drm_driver = {
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index cf4b23369dc4..a0d920ec2b1d 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -179,6 +179,12 @@  struct v3d_dev {
 		u32 num_allocated;
 		u32 pages_allocated;
 	} bo_stats;
+
+	/* To support a performance analysis tool in user space, we require
+	 * a single, globally configured performance monitor (perfmon) for
+	 * all jobs.
+	 */
+	struct v3d_perfmon *global_perfmon;
 };
 
 static inline struct v3d_dev *
@@ -584,6 +590,8 @@  int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
 int v3d_perfmon_get_counter_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
+int v3d_perfmon_set_global_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
 
 /* v3d_sysfs.c */
 int v3d_sysfs_init(struct device *dev);
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
index 156be13ab2ef..bf42303c292b 100644
--- a/drivers/gpu/drm/v3d/v3d_perfmon.c
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -312,6 +312,9 @@  static int v3d_perfmon_idr_del(int id, void *elem, void *data)
 	if (perfmon == v3d->active_perfmon)
 		v3d_perfmon_stop(v3d, perfmon, false);
 
+	/* If the global perfmon is being destroyed, set it to NULL */
+	cmpxchg(&v3d->global_perfmon, perfmon, NULL);
+
 	v3d_perfmon_put(perfmon);
 
 	return 0;
@@ -451,3 +454,34 @@  int v3d_perfmon_get_counter_ioctl(struct drm_device *dev, void *data,
 
 	return 0;
 }
+
+int v3d_perfmon_set_global_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+	struct drm_v3d_perfmon_set_global *req = data;
+	struct v3d_dev *v3d = to_v3d_dev(dev);
+	struct v3d_perfmon *perfmon;
+
+	if (req->flags & ~DRM_V3D_PERFMON_CLEAR_GLOBAL)
+		return -EINVAL;
+
+	perfmon = v3d_perfmon_find(v3d_priv, req->id);
+	if (!perfmon)
+		return -EINVAL;
+
+	/* If the request is to clear the global performance monitor */
+	if (req->flags & DRM_V3D_PERFMON_CLEAR_GLOBAL) {
+		if (!v3d->global_perfmon)
+			return -EINVAL;
+
+		xchg(&v3d->global_perfmon, NULL);
+
+		return 0;
+	}
+
+	if (cmpxchg(&v3d->global_perfmon, NULL, perfmon))
+		return -EBUSY;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 08d2a2739582..38690740f593 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -120,11 +120,19 @@  v3d_cpu_job_free(struct drm_sched_job *sched_job)
 static void
 v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job)
 {
-	if (job->perfmon != v3d->active_perfmon)
+	struct v3d_perfmon *perfmon = v3d->global_perfmon;
+
+	if (!perfmon)
+		perfmon = job->perfmon;
+
+	if (perfmon == v3d->active_perfmon)
+		return;
+
+	if (perfmon != v3d->active_perfmon)
 		v3d_perfmon_stop(v3d, v3d->active_perfmon, true);
 
-	if (job->perfmon && v3d->active_perfmon != job->perfmon)
-		v3d_perfmon_start(v3d, job->perfmon);
+	if (perfmon && v3d->active_perfmon != perfmon)
+		v3d_perfmon_start(v3d, perfmon);
 }
 
 static void
diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index d607aa9c4ec2..9e439c9f0a93 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -981,6 +981,11 @@  v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 		goto fail;
 
 	if (args->perfmon_id) {
+		if (v3d->global_perfmon) {
+			ret = -EAGAIN;
+			goto fail_perfmon;
+		}
+
 		render->base.perfmon = v3d_perfmon_find(v3d_priv,
 							args->perfmon_id);
 
@@ -1196,6 +1201,11 @@  v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
 		goto fail;
 
 	if (args->perfmon_id) {
+		if (v3d->global_perfmon) {
+			ret = -EAGAIN;
+			goto fail_perfmon;
+		}
+
 		job->base.perfmon = v3d_perfmon_find(v3d_priv,
 						     args->perfmon_id);
 		if (!job->base.perfmon) {
diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
index 87fc5bb0a61e..709724fe28e6 100644
--- a/include/uapi/drm/v3d_drm.h
+++ b/include/uapi/drm/v3d_drm.h
@@ -43,6 +43,7 @@  extern "C" {
 #define DRM_V3D_PERFMON_GET_VALUES                0x0a
 #define DRM_V3D_SUBMIT_CPU                        0x0b
 #define DRM_V3D_PERFMON_GET_COUNTER               0x0c
+#define DRM_V3D_PERFMON_SET_GLOBAL                0x0d
 
 #define DRM_IOCTL_V3D_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl)
 #define DRM_IOCTL_V3D_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo)
@@ -61,6 +62,8 @@  extern "C" {
 #define DRM_IOCTL_V3D_SUBMIT_CPU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CPU, struct drm_v3d_submit_cpu)
 #define DRM_IOCTL_V3D_PERFMON_GET_COUNTER DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_COUNTER, \
 						   struct drm_v3d_perfmon_get_counter)
+#define DRM_IOCTL_V3D_PERFMON_SET_GLOBAL  DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_PERFMON_SET_GLOBAL, \
+						   struct drm_v3d_perfmon_set_global)
 
 #define DRM_V3D_SUBMIT_CL_FLUSH_CACHE             0x01
 #define DRM_V3D_SUBMIT_EXTENSION		  0x02
@@ -765,6 +768,18 @@  struct drm_v3d_perfmon_get_counter {
 	__u8 reserved[7];
 };
 
+#define DRM_V3D_PERFMON_CLEAR_GLOBAL    0x0001
+
+/*
+ * struct drm_v3d_perfmon_set_global - ioctl to define a
+ * global performance counter that is used if a job has
+ * not assigned one on its own.
+ */
+struct drm_v3d_perfmon_set_global {
+	__u32 flags;
+	__u32 id;
+};
+
 #if defined(__cplusplus)
 }
 #endif