drm/v3d: Expose the total GPU usage stats on sysfs

The previous patch exposed the accumulated amount of active time per
client for each V3D queue. But this doesn't provide a global notion of
the GPU usage.

Therefore, provide the accumulated amount of active time for each V3D
queue (BIN, RENDER, CSD, TFU and CACHE_CLEAN), considering all the jobs
submitted to the queue, independent of the client.

This data is exposed through the sysfs interface, so that if the
interface is queried at two different points of time the usage percentage
of each of the queues can be calculated.

Co-developed-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
Signed-off-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Acked-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
Reviewed-by: Melissa Wen <mwen@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230905213416.1290219-3-mcanal@igalia.com

7 files changed, 135 insertions, 3 deletions

diff --git a/drivers/gpu/drm/v3d/Makefile b/drivers/gpu/drm/v3d/Makefile
index e8b314137020..4b21b20e4998 100644
--- a/drivers/gpu/drm/v3d/Makefile
+++ b/drivers/gpu/drm/v3d/Makefile
@@ -11,7 +11,8 @@ v3d-y := \
 	v3d_mmu.o \
 	v3d_perfmon.o \
 	v3d_trace_points.o \
-	v3d_sched.o
+	v3d_sched.o \
+	v3d_sysfs.o
 
 v3d-$(CONFIG_DEBUG_FS) += v3d_debugfs.o
 
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index 82984b4df2a2..44a1ca57d6a4 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -316,8 +316,14 @@ static int v3d_platform_drm_probe(struct platform_device *pdev)
 	if (ret)
 		goto irq_disable;
 
+	ret = v3d_sysfs_init(dev);
+	if (ret)
+		goto drm_unregister;
+
 	return 0;
 
+drm_unregister:
+	drm_dev_unregister(drm);
 irq_disable:
 	v3d_irq_disable(v3d);
 gem_destroy:
@@ -331,6 +337,9 @@ static void v3d_platform_drm_remove(struct platform_device *pdev)
 {
 	struct drm_device *drm = platform_get_drvdata(pdev);
 	struct v3d_dev *v3d = to_v3d_dev(drm);
+	struct device *dev = &pdev->dev;
+
+	v3d_sysfs_destroy(dev);
 
 	drm_dev_unregister(drm);
 
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 8f9d93239a17..4c59fefaa0b4 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -38,6 +38,10 @@ struct v3d_queue_state {
 
 	u64 fence_context;
 	u64 emit_seqno;
+
+	u64 start_ns;
+	u64 enabled_ns;
+	u64 jobs_sent;
 };
 
 /* Performance monitor object. The perform lifetime is controlled by userspace
@@ -441,3 +445,7 @@ int v3d_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *file_priv);
 int v3d_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
+
+/* v3d_sysfs.c */
+int v3d_sysfs_init(struct device *dev);
+void v3d_sysfs_destroy(struct device *dev);
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index a33e90f29bd5..712675134c04 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -1014,8 +1014,12 @@ v3d_gem_init(struct drm_device *dev)
 	u32 pt_size = 4096 * 1024;
 	int ret, i;
 
-	for (i = 0; i < V3D_MAX_QUEUES; i++)
+	for (i = 0; i < V3D_MAX_QUEUES; i++) {
 		v3d->queue[i].fence_context = dma_fence_context_alloc(1);
+		v3d->queue[i].start_ns = 0;
+		v3d->queue[i].enabled_ns = 0;
+		v3d->queue[i].jobs_sent = 0;
+	}
 
 	spin_lock_init(&v3d->mm_lock);
 	spin_lock_init(&v3d->job_lock);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index ba390b782103..afc76390a197 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -103,10 +103,17 @@ v3d_irq(int irq, void *arg)
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->bin_job->base.irq_fence);
 		struct v3d_file_priv *file = v3d->bin_job->base.file->driver_priv;
+		u64 runtime = local_clock() - file->start_ns[V3D_BIN];
 
 		file->enabled_ns[V3D_BIN] += local_clock() - file->start_ns[V3D_BIN];
 		file->jobs_sent[V3D_BIN]++;
+		v3d->queue[V3D_BIN].jobs_sent++;
+
 		file->start_ns[V3D_BIN] = 0;
+		v3d->queue[V3D_BIN].start_ns = 0;
+
+		file->enabled_ns[V3D_BIN] += runtime;
+		v3d->queue[V3D_BIN].enabled_ns += runtime;
 
 		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -117,10 +124,17 @@ v3d_irq(int irq, void *arg)
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->render_job->base.irq_fence);
 		struct v3d_file_priv *file = v3d->render_job->base.file->driver_priv;
+		u64 runtime = local_clock() - file->start_ns[V3D_RENDER];
 
 		file->enabled_ns[V3D_RENDER] += local_clock() - file->start_ns[V3D_RENDER];
 		file->jobs_sent[V3D_RENDER]++;
+		v3d->queue[V3D_RENDER].jobs_sent++;
+
 		file->start_ns[V3D_RENDER] = 0;
+		v3d->queue[V3D_RENDER].start_ns = 0;
+
+		file->enabled_ns[V3D_RENDER] += runtime;
+		v3d->queue[V3D_RENDER].enabled_ns += runtime;
 
 		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -131,10 +145,17 @@ v3d_irq(int irq, void *arg)
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->csd_job->base.irq_fence);
 		struct v3d_file_priv *file = v3d->csd_job->base.file->driver_priv;
+		u64 runtime = local_clock() - file->start_ns[V3D_CSD];
 
 		file->enabled_ns[V3D_CSD] += local_clock() - file->start_ns[V3D_CSD];
 		file->jobs_sent[V3D_CSD]++;
+		v3d->queue[V3D_CSD].jobs_sent++;
+
 		file->start_ns[V3D_CSD] = 0;
+		v3d->queue[V3D_CSD].start_ns = 0;
+
+		file->enabled_ns[V3D_CSD] += runtime;
+		v3d->queue[V3D_CSD].enabled_ns += runtime;
 
 		trace_v3d_csd_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
@@ -172,10 +193,17 @@ v3d_hub_irq(int irq, void *arg)
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->tfu_job->base.irq_fence);
 		struct v3d_file_priv *file = v3d->tfu_job->base.file->driver_priv;
+		u64 runtime = local_clock() - file->start_ns[V3D_TFU];
 
 		file->enabled_ns[V3D_TFU] += local_clock() - file->start_ns[V3D_TFU];
 		file->jobs_sent[V3D_TFU]++;
+		v3d->queue[V3D_TFU].jobs_sent++;
+
 		file->start_ns[V3D_TFU] = 0;
+		v3d->queue[V3D_TFU].start_ns = 0;
+
+		file->enabled_ns[V3D_TFU] += runtime;
+		v3d->queue[V3D_TFU].enabled_ns += runtime;
 
 		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 19afceacda83..fccbea2a5f2e 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -110,6 +110,7 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 			    job->start, job->end);
 
 	file->start_ns[V3D_BIN] = local_clock();
+	v3d->queue[V3D_BIN].start_ns = file->start_ns[V3D_BIN];
 
 	v3d_switch_perfmon(v3d, &job->base);
 
@@ -164,6 +165,7 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
 			    job->start, job->end);
 
 	file->start_ns[V3D_RENDER] = local_clock();
+	v3d->queue[V3D_RENDER].start_ns = file->start_ns[V3D_RENDER];
 
 	v3d_switch_perfmon(v3d, &job->base);
 
@@ -199,6 +201,7 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 	trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno);
 
 	file->start_ns[V3D_TFU] = local_clock();
+	v3d->queue[V3D_TFU].start_ns = file->start_ns[V3D_TFU];
 
 	V3D_WRITE(V3D_TFU_IIA(v3d->ver), job->args.iia);
 	V3D_WRITE(V3D_TFU_IIS(v3d->ver), job->args.iis);
@@ -245,6 +248,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 	trace_v3d_submit_csd(dev, to_v3d_fence(fence)->seqno);
 
 	file->start_ns[V3D_CSD] = local_clock();
+	v3d->queue[V3D_CSD].start_ns = file->start_ns[V3D_CSD];
 
 	v3d_switch_perfmon(v3d, &job->base);
 
@@ -264,14 +268,23 @@ v3d_cache_clean_job_run(struct drm_sched_job *sched_job)
 	struct v3d_job *job = to_v3d_job(sched_job);
 	struct v3d_dev *v3d = job->v3d;
 	struct v3d_file_priv *file = job->file->driver_priv;
+	u64 runtime;
 
 	file->start_ns[V3D_CACHE_CLEAN] = local_clock();
+	v3d->queue[V3D_CACHE_CLEAN].start_ns = file->start_ns[V3D_CACHE_CLEAN];
 
 	v3d_clean_caches(v3d);
 
-	file->enabled_ns[V3D_CACHE_CLEAN] += local_clock() - file->start_ns[V3D_CACHE_CLEAN];
+	runtime = local_clock() - file->start_ns[V3D_CACHE_CLEAN];
+
+	file->enabled_ns[V3D_CACHE_CLEAN] += runtime;
+	v3d->queue[V3D_CACHE_CLEAN].enabled_ns += runtime;
+
 	file->jobs_sent[V3D_CACHE_CLEAN]++;
+	v3d->queue[V3D_CACHE_CLEAN].jobs_sent++;
+
 	file->start_ns[V3D_CACHE_CLEAN] = 0;
+	v3d->queue[V3D_CACHE_CLEAN].start_ns = 0;
 
 	return NULL;
 }
diff --git a/drivers/gpu/drm/v3d/v3d_sysfs.c b/drivers/gpu/drm/v3d/v3d_sysfs.c
new file mode 100644
index 000000000000..d106845ba890
--- /dev/null
+++ b/drivers/gpu/drm/v3d/v3d_sysfs.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2023 Igalia S.L.
+ */
+
+#include <linux/sched/clock.h>
+#include <linux/sysfs.h>
+
+#include "v3d_drv.h"
+
+static ssize_t
+gpu_stats_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+	struct v3d_dev *v3d = to_v3d_dev(drm);
+	enum v3d_queue queue;
+	u64 timestamp = local_clock();
+	u64 active_runtime;
+	ssize_t len = 0;
+
+	len += sysfs_emit(buf, "queue\ttimestamp\tjobs\truntime\n");
+
+	for (queue = 0; queue < V3D_MAX_QUEUES; queue++) {
+		if (v3d->queue[queue].start_ns)
+			active_runtime = timestamp - v3d->queue[queue].start_ns;
+		else
+			active_runtime = 0;
+
+		/* Each line will display the queue name, timestamp, the number
+		 * of jobs sent to that queue and the runtime, as can be seem here:
+		 *
+		 * queue	timestamp	jobs	runtime
+		 * bin		239043069420	22620	17438164056
+		 * render	239043069420	22619	27284814161
+		 * tfu		239043069420	8763	394592566
+		 * csd		239043069420	3168	10787905530
+		 * cache_clean	239043069420	6127	237375940
+		 */
+		len += sysfs_emit_at(buf, len, "%s\t%llu\t%llu\t%llu\n",
+				     v3d_queue_to_string(queue),
+				     timestamp,
+				     v3d->queue[queue].jobs_sent,
+				     v3d->queue[queue].enabled_ns + active_runtime);
+	}
+
+	return len;
+}
+static DEVICE_ATTR_RO(gpu_stats);
+
+static struct attribute *v3d_sysfs_entries[] = {
+	&dev_attr_gpu_stats.attr,
+	NULL,
+};
+
+static struct attribute_group v3d_sysfs_attr_group = {
+	.attrs = v3d_sysfs_entries,
+};
+
+int
+v3d_sysfs_init(struct device *dev)
+{
+	return sysfs_create_group(&dev->kobj, &v3d_sysfs_attr_group);
+}
+
+void
+v3d_sysfs_destroy(struct device *dev)
+{
+	return sysfs_remove_group(&dev->kobj, &v3d_sysfs_attr_group);
+}