Re: [PATCH 3/5] drm/v3d: Create a struct to store the GPU stats
El 3/4/24 a las 22:24, Maíra Canal escribió: This will make it easier to instantiate the GPU stats variables and it will create a structure where we can store all the variables that refer to GPU stats. Signed-off-by: Maíra Canal --- drivers/gpu/drm/v3d/v3d_drv.c | 14 ++ drivers/gpu/drm/v3d/v3d_drv.h | 18 ++ drivers/gpu/drm/v3d/v3d_gem.c | 4 +--- drivers/gpu/drm/v3d/v3d_sched.c | 20 drivers/gpu/drm/v3d/v3d_sysfs.c | 10 ++ 5 files changed, 35 insertions(+), 31 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 3debf37e7d9b..cbb62be18aa5 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -115,14 +115,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file) v3d_priv->v3d = v3d; for (i = 0; i < V3D_MAX_QUEUES; i++) { - v3d_priv->enabled_ns[i] = 0; - v3d_priv->start_ns[i] = 0; - v3d_priv->jobs_sent[i] = 0; - sched = &v3d->queue[i].sched; drm_sched_entity_init(&v3d_priv->sched_entity[i], DRM_SCHED_PRIORITY_NORMAL, &sched, 1, NULL); + memset(&v3d_priv->stats[i], 0, sizeof(v3d_priv->stats[i])); } v3d_perfmon_open_file(v3d_priv); @@ -151,20 +148,21 @@ static void v3d_show_fdinfo(struct drm_printer *p, struct drm_file *file) enum v3d_queue queue; for (queue = 0; queue < V3D_MAX_QUEUES; queue++) { + struct v3d_stats *stats = &file_priv->stats[queue]; + /* Note that, in case of a GPU reset, the time spent during an * attempt of executing the job is not computed in the runtime. */ drm_printf(p, "drm-engine-%s: \t%llu ns\n", v3d_queue_to_string(queue), - file_priv->start_ns[queue] ? file_priv->enabled_ns[queue] - + timestamp - file_priv->start_ns[queue] - : file_priv->enabled_ns[queue]); + stats->start_ns ? stats->enabled_ns + timestamp - stats->start_ns + : stats->enabled_ns); /* Note that we only count jobs that completed. Therefore, jobs * that were resubmitted due to a GPU reset are not computed. */ drm_printf(p, "v3d-jobs-%s: \t%llu jobs\n", - v3d_queue_to_string(queue), file_priv->jobs_sent[queue]); + v3d_queue_to_string(queue), stats->jobs_sent); } } diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index ee3545226d7f..0117593976ed 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -36,15 +36,20 @@ static inline char *v3d_queue_to_string(enum v3d_queue queue) return "UNKNOWN"; } +struct v3d_stats { + u64 start_ns; + u64 enabled_ns; + u64 jobs_sent; As currently, we are only accounting jobs that have been completed. What do you think of renaming jobs_sent to jobs_completed? +}; + struct v3d_queue_state { struct drm_gpu_scheduler sched; u64 fence_context; u64 emit_seqno; - u64 start_ns; - u64 enabled_ns; - u64 jobs_sent; + /* Stores the GPU stats for this queue in the global context. */ + struct v3d_stats stats; }; /* Performance monitor object. The perform lifetime is controlled by userspace @@ -188,11 +193,8 @@ struct v3d_file_priv { struct drm_sched_entity sched_entity[V3D_MAX_QUEUES]; - u64 start_ns[V3D_MAX_QUEUES]; - - u64 enabled_ns[V3D_MAX_QUEUES]; - - u64 jobs_sent[V3D_MAX_QUEUES]; + /* Stores the GPU stats for a specific queue for this fd. */ + struct v3d_stats stats[V3D_MAX_QUEUES]; }; struct v3d_bo { diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index afc565078c78..d14589d3ae6c 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -248,9 +248,7 @@ v3d_gem_init(struct drm_device *dev) 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; + memset(&v3d->queue[i].stats, 0, sizeof(v3d->queue[i].stats)); } spin_lock_init(&v3d->mm_lock); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 8ca61bcd4b1c..ea5f5a84b55b 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -110,10 +110,12 @@ v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue) { struct v3d_dev *v3d = job->v3
Re: [PATCH 3/5] drm/v3d: Create a struct to store the GPU stats
On 03/04/2024 21:24, Maíra Canal wrote: This will make it easier to instantiate the GPU stats variables and it will create a structure where we can store all the variables that refer to GPU stats. Signed-off-by: Maíra Canal --- drivers/gpu/drm/v3d/v3d_drv.c | 14 ++ drivers/gpu/drm/v3d/v3d_drv.h | 18 ++ drivers/gpu/drm/v3d/v3d_gem.c | 4 +--- drivers/gpu/drm/v3d/v3d_sched.c | 20 drivers/gpu/drm/v3d/v3d_sysfs.c | 10 ++ 5 files changed, 35 insertions(+), 31 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 3debf37e7d9b..cbb62be18aa5 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -115,14 +115,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file) v3d_priv->v3d = v3d; for (i = 0; i < V3D_MAX_QUEUES; i++) { - v3d_priv->enabled_ns[i] = 0; - v3d_priv->start_ns[i] = 0; - v3d_priv->jobs_sent[i] = 0; - sched = &v3d->queue[i].sched; drm_sched_entity_init(&v3d_priv->sched_entity[i], DRM_SCHED_PRIORITY_NORMAL, &sched, 1, NULL); + memset(&v3d_priv->stats[i], 0, sizeof(v3d_priv->stats[i])); } v3d_perfmon_open_file(v3d_priv); @@ -151,20 +148,21 @@ static void v3d_show_fdinfo(struct drm_printer *p, struct drm_file *file) enum v3d_queue queue; for (queue = 0; queue < V3D_MAX_QUEUES; queue++) { + struct v3d_stats *stats = &file_priv->stats[queue]; + /* Note that, in case of a GPU reset, the time spent during an * attempt of executing the job is not computed in the runtime. */ drm_printf(p, "drm-engine-%s: \t%llu ns\n", v3d_queue_to_string(queue), - file_priv->start_ns[queue] ? file_priv->enabled_ns[queue] - + timestamp - file_priv->start_ns[queue] - : file_priv->enabled_ns[queue]); + stats->start_ns ? stats->enabled_ns + timestamp - stats->start_ns + : stats->enabled_ns); /* Note that we only count jobs that completed. Therefore, jobs * that were resubmitted due to a GPU reset are not computed. */ drm_printf(p, "v3d-jobs-%s: \t%llu jobs\n", - v3d_queue_to_string(queue), file_priv->jobs_sent[queue]); + v3d_queue_to_string(queue), stats->jobs_sent); } } diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index ee3545226d7f..0117593976ed 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -36,15 +36,20 @@ static inline char *v3d_queue_to_string(enum v3d_queue queue) return "UNKNOWN"; } +struct v3d_stats { + u64 start_ns; + u64 enabled_ns; + u64 jobs_sent; +}; + struct v3d_queue_state { struct drm_gpu_scheduler sched; u64 fence_context; u64 emit_seqno; - u64 start_ns; - u64 enabled_ns; - u64 jobs_sent; + /* Stores the GPU stats for this queue in the global context. */ + struct v3d_stats stats; }; /* Performance monitor object. The perform lifetime is controlled by userspace @@ -188,11 +193,8 @@ struct v3d_file_priv { struct drm_sched_entity sched_entity[V3D_MAX_QUEUES]; - u64 start_ns[V3D_MAX_QUEUES]; - - u64 enabled_ns[V3D_MAX_QUEUES]; - - u64 jobs_sent[V3D_MAX_QUEUES]; + /* Stores the GPU stats for a specific queue for this fd. */ + struct v3d_stats stats[V3D_MAX_QUEUES]; }; struct v3d_bo { diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index afc565078c78..d14589d3ae6c 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -248,9 +248,7 @@ v3d_gem_init(struct drm_device *dev) 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; + memset(&v3d->queue[i].stats, 0, sizeof(v3d->queue[i].stats)); } spin_lock_init(&v3d->mm_lock); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 8ca61bcd4b1c..ea5f5a84b55b 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -110,10 +110,12 @@ v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue) { struct v3d_dev *v3d = job->v3d; struct v3d_file_priv *file = job->file->driver_priv; + struct v3d_stats *global_stats = &v3d->queue[queue].stats; +
[PATCH 3/5] drm/v3d: Create a struct to store the GPU stats
This will make it easier to instantiate the GPU stats variables and it will create a structure where we can store all the variables that refer to GPU stats. Signed-off-by: Maíra Canal --- drivers/gpu/drm/v3d/v3d_drv.c | 14 ++ drivers/gpu/drm/v3d/v3d_drv.h | 18 ++ drivers/gpu/drm/v3d/v3d_gem.c | 4 +--- drivers/gpu/drm/v3d/v3d_sched.c | 20 drivers/gpu/drm/v3d/v3d_sysfs.c | 10 ++ 5 files changed, 35 insertions(+), 31 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c index 3debf37e7d9b..cbb62be18aa5 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.c +++ b/drivers/gpu/drm/v3d/v3d_drv.c @@ -115,14 +115,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file) v3d_priv->v3d = v3d; for (i = 0; i < V3D_MAX_QUEUES; i++) { - v3d_priv->enabled_ns[i] = 0; - v3d_priv->start_ns[i] = 0; - v3d_priv->jobs_sent[i] = 0; - sched = &v3d->queue[i].sched; drm_sched_entity_init(&v3d_priv->sched_entity[i], DRM_SCHED_PRIORITY_NORMAL, &sched, 1, NULL); + memset(&v3d_priv->stats[i], 0, sizeof(v3d_priv->stats[i])); } v3d_perfmon_open_file(v3d_priv); @@ -151,20 +148,21 @@ static void v3d_show_fdinfo(struct drm_printer *p, struct drm_file *file) enum v3d_queue queue; for (queue = 0; queue < V3D_MAX_QUEUES; queue++) { + struct v3d_stats *stats = &file_priv->stats[queue]; + /* Note that, in case of a GPU reset, the time spent during an * attempt of executing the job is not computed in the runtime. */ drm_printf(p, "drm-engine-%s: \t%llu ns\n", v3d_queue_to_string(queue), - file_priv->start_ns[queue] ? file_priv->enabled_ns[queue] - + timestamp - file_priv->start_ns[queue] - : file_priv->enabled_ns[queue]); + stats->start_ns ? stats->enabled_ns + timestamp - stats->start_ns + : stats->enabled_ns); /* Note that we only count jobs that completed. Therefore, jobs * that were resubmitted due to a GPU reset are not computed. */ drm_printf(p, "v3d-jobs-%s: \t%llu jobs\n", - v3d_queue_to_string(queue), file_priv->jobs_sent[queue]); + v3d_queue_to_string(queue), stats->jobs_sent); } } diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index ee3545226d7f..0117593976ed 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -36,15 +36,20 @@ static inline char *v3d_queue_to_string(enum v3d_queue queue) return "UNKNOWN"; } +struct v3d_stats { + u64 start_ns; + u64 enabled_ns; + u64 jobs_sent; +}; + struct v3d_queue_state { struct drm_gpu_scheduler sched; u64 fence_context; u64 emit_seqno; - u64 start_ns; - u64 enabled_ns; - u64 jobs_sent; + /* Stores the GPU stats for this queue in the global context. */ + struct v3d_stats stats; }; /* Performance monitor object. The perform lifetime is controlled by userspace @@ -188,11 +193,8 @@ struct v3d_file_priv { struct drm_sched_entity sched_entity[V3D_MAX_QUEUES]; - u64 start_ns[V3D_MAX_QUEUES]; - - u64 enabled_ns[V3D_MAX_QUEUES]; - - u64 jobs_sent[V3D_MAX_QUEUES]; + /* Stores the GPU stats for a specific queue for this fd. */ + struct v3d_stats stats[V3D_MAX_QUEUES]; }; struct v3d_bo { diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index afc565078c78..d14589d3ae6c 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -248,9 +248,7 @@ v3d_gem_init(struct drm_device *dev) 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; + memset(&v3d->queue[i].stats, 0, sizeof(v3d->queue[i].stats)); } spin_lock_init(&v3d->mm_lock); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 8ca61bcd4b1c..ea5f5a84b55b 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -110,10 +110,12 @@ v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue) { struct v3d_dev *v3d = job->v3d; struct v3d_file_priv *file = job->file->driver_priv; + struct v3d_stats *global_stats = &v3d->queue[queue].stats; + struct v3d_stats *loc