summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/v3d/v3d_sched.c
diff options
context:
space:
mode:
authorMaíra Canal <mcanal@igalia.com>2023-09-05 18:06:34 -0300
committerMaíra Canal <mcanal@igalia.com>2023-11-06 10:09:23 -0300
commit09a93cc4f7d1893777f6b788bffe60d64e4d5df7 (patch)
treeda3b555b3007c5c2d05b87a161c502b6729c3ed9 /drivers/gpu/drm/v3d/v3d_sched.c
parent5faf6e1853d30d113ebc9977e015d0152e5e1970 (diff)
drm/v3d: Implement show_fdinfo() callback for GPU usage stats
This patch exposes the accumulated amount of active time per client through the fdinfo infrastructure. The amount of active time is exposed for each V3D queue: BIN, RENDER, CSD, TFU and CACHE_CLEAN. In order to calculate the amount of active time per client, a CPU clock is used through the function local_clock(). The point where the jobs has started is marked and is finally compared with the time that the job had finished. Moreover, the number of jobs submitted to each queue is also exposed on fdinfo through the identifier "v3d-jobs-<queue>". 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
Diffstat (limited to 'drivers/gpu/drm/v3d/v3d_sched.c')
-rw-r--r--drivers/gpu/drm/v3d/v3d_sched.c20
1 files changed, 20 insertions, 0 deletions
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index f59b63e51b14..19afceacda83 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -18,6 +18,7 @@
* semaphores to interlock between them.
*/
+#include <linux/sched/clock.h>
#include <linux/kthread.h>
#include "v3d_drv.h"
@@ -76,6 +77,7 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
{
struct v3d_bin_job *job = to_bin_job(sched_job);
struct v3d_dev *v3d = job->base.v3d;
+ struct v3d_file_priv *file = job->base.file->driver_priv;
struct drm_device *dev = &v3d->drm;
struct dma_fence *fence;
unsigned long irqflags;
@@ -107,6 +109,8 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
trace_v3d_submit_cl(dev, false, to_v3d_fence(fence)->seqno,
job->start, job->end);
+ file->start_ns[V3D_BIN] = local_clock();
+
v3d_switch_perfmon(v3d, &job->base);
/* Set the current and end address of the control list.
@@ -131,6 +135,7 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
{
struct v3d_render_job *job = to_render_job(sched_job);
struct v3d_dev *v3d = job->base.v3d;
+ struct v3d_file_priv *file = job->base.file->driver_priv;
struct drm_device *dev = &v3d->drm;
struct dma_fence *fence;
@@ -158,6 +163,8 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
trace_v3d_submit_cl(dev, true, to_v3d_fence(fence)->seqno,
job->start, job->end);
+ file->start_ns[V3D_RENDER] = local_clock();
+
v3d_switch_perfmon(v3d, &job->base);
/* XXX: Set the QCFG */
@@ -176,6 +183,7 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
{
struct v3d_tfu_job *job = to_tfu_job(sched_job);
struct v3d_dev *v3d = job->base.v3d;
+ struct v3d_file_priv *file = job->base.file->driver_priv;
struct drm_device *dev = &v3d->drm;
struct dma_fence *fence;
@@ -190,6 +198,8 @@ 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_WRITE(V3D_TFU_IIA(v3d->ver), job->args.iia);
V3D_WRITE(V3D_TFU_IIS(v3d->ver), job->args.iis);
V3D_WRITE(V3D_TFU_ICA(v3d->ver), job->args.ica);
@@ -215,6 +225,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
{
struct v3d_csd_job *job = to_csd_job(sched_job);
struct v3d_dev *v3d = job->base.v3d;
+ struct v3d_file_priv *file = job->base.file->driver_priv;
struct drm_device *dev = &v3d->drm;
struct dma_fence *fence;
int i, csd_cfg0_reg, csd_cfg_reg_count;
@@ -233,6 +244,8 @@ 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_switch_perfmon(v3d, &job->base);
csd_cfg0_reg = V3D_CSD_QUEUED_CFG0(v3d->ver);
@@ -250,9 +263,16 @@ 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;
+
+ file->start_ns[V3D_CACHE_CLEAN] = local_clock();
v3d_clean_caches(v3d);
+ file->enabled_ns[V3D_CACHE_CLEAN] += local_clock() - file->start_ns[V3D_CACHE_CLEAN];
+ file->jobs_sent[V3D_CACHE_CLEAN]++;
+ file->start_ns[V3D_CACHE_CLEAN] = 0;
+
return NULL;
}