On Tue, 3 Sep 2024 21:25:36 +0100
Adrián Larumbe <adrian.larumbe@xxxxxxxxxxxxx> wrote:
> Drawing from the FW-calculated values in the previous commit, we can
> increase the numbers for an open file by collecting them from finished jobs
> when updating their group synchronisation objects.
>
> Display of fdinfo key-value pairs is governed by a flag that is by default
> disabled in the present commit, and supporting manual toggle of it will be
> the matter of a later commit.
>
> Signed-off-by: Adrián Larumbe <adrian.larumbe@xxxxxxxxxxxxx>
> ---
> drivers/gpu/drm/panthor/panthor_devfreq.c | 18 ++++++++-
> drivers/gpu/drm/panthor/panthor_device.h | 14 +++++++
> drivers/gpu/drm/panthor/panthor_drv.c | 35 ++++++++++++++++++
> drivers/gpu/drm/panthor/panthor_sched.c | 45 +++++++++++++++++++++++
> 4 files changed, 111 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/panthor/panthor_devfreq.c b/drivers/gpu/drm/panthor/panthor_devfreq.c
> index c6d3c327cc24..9d0f891b9b53 100644
> --- a/drivers/gpu/drm/panthor/panthor_devfreq.c
> +++ b/drivers/gpu/drm/panthor/panthor_devfreq.c
> @@ -62,14 +62,20 @@ static void panthor_devfreq_update_utilization(struct panthor_devfreq *pdevfreq)
> static int panthor_devfreq_target(struct device *dev, unsigned long *freq,
> u32 flags)
> {
> + struct panthor_device *ptdev = dev_get_drvdata(dev);
> struct dev_pm_opp *opp;
> + int err;
>
> opp = devfreq_recommended_opp(dev, freq, flags);
> if (IS_ERR(opp))
> return PTR_ERR(opp);
> dev_pm_opp_put(opp);
>
> - return dev_pm_opp_set_rate(dev, *freq);
> + err = dev_pm_opp_set_rate(dev, *freq);
> + if (!err)
> + ptdev->current_frequency = *freq;
> +
> + return err;
> }
>
> static void panthor_devfreq_reset(struct panthor_devfreq *pdevfreq)
> @@ -130,6 +136,7 @@ int panthor_devfreq_init(struct panthor_device *ptdev)
> struct panthor_devfreq *pdevfreq;
> struct dev_pm_opp *opp;
> unsigned long cur_freq;
> + unsigned long freq = ULONG_MAX;
> int ret;
>
> pdevfreq = drmm_kzalloc(&ptdev->base, sizeof(*ptdev->devfreq), GFP_KERNEL);
> @@ -161,6 +168,7 @@ int panthor_devfreq_init(struct panthor_device *ptdev)
> return PTR_ERR(opp);
>
> panthor_devfreq_profile.initial_freq = cur_freq;
> + ptdev->current_frequency = cur_freq;
>
> /* Regulator coupling only takes care of synchronizing/balancing voltage
> * updates, but the coupled regulator needs to be enabled manually.
> @@ -204,6 +212,14 @@ int panthor_devfreq_init(struct panthor_device *ptdev)
>
> dev_pm_opp_put(opp);
>
> + /* Find the fastest defined rate */
> + opp = dev_pm_opp_find_freq_floor(dev, &freq);
> + if (IS_ERR(opp))
> + return PTR_ERR(opp);
> + ptdev->fast_rate = freq;
> +
> + dev_pm_opp_put(opp);
> +
> /*
> * Setup default thresholds for the simple_ondemand governor.
> * The values are chosen based on experiments.
> diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h
> index a48e30d0af30..0e68f5a70d20 100644
> --- a/drivers/gpu/drm/panthor/panthor_device.h
> +++ b/drivers/gpu/drm/panthor/panthor_device.h
> @@ -184,6 +184,17 @@ struct panthor_device {
>
> /** @profile_mask: User-set profiling flags for job accounting. */
> u32 profile_mask;
> +
> + /** @current_frequency: Device clock frequency at present. Set by DVFS*/
> + unsigned long current_frequency;
> +
> + /** @fast_rate: Maximum device clock frequency. Set by DVFS */
> + unsigned long fast_rate;
> +};
Can we move the current_frequency/fast_rate retrieval in a separate
patch?
> +
> +struct panthor_gpu_usage {
> + u64 time;
> + u64 cycles;
> };
>
> /**
> @@ -198,6 +209,9 @@ struct panthor_file {
>
> /** @groups: Scheduling group pool attached to this file. */
> struct panthor_group_pool *groups;
> +
> + /** @stats: cycle and timestamp measures for job execution. */
> + struct panthor_gpu_usage stats;
> };
>
> int panthor_device_init(struct panthor_device *ptdev);
> diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
> index b5e7b919f241..e18838754963 100644
> --- a/drivers/gpu/drm/panthor/panthor_drv.c
> +++ b/drivers/gpu/drm/panthor/panthor_drv.c
> @@ -3,12 +3,17 @@
> /* Copyright 2019 Linaro, Ltd., Rob Herring <robh@xxxxxxxxxx> */
> /* Copyright 2019 Collabora ltd. */
>
> +#ifdef CONFIG_ARM_ARCH_TIMER
> +#include <asm/arch_timer.h>
> +#endif
> +
> #include <linux/list.h>
> #include <linux/module.h>
> #include <linux/of_platform.h>
> #include <linux/pagemap.h>
> #include <linux/platform_device.h>
> #include <linux/pm_runtime.h>
> +#include <linux/time64.h>
>
> #include <drm/drm_debugfs.h>
> #include <drm/drm_drv.h>
> @@ -1351,6 +1356,34 @@ static int panthor_mmap(struct file *filp, struct vm_area_struct *vma)
> return ret;
> }
>
> +static void panthor_gpu_show_fdinfo(struct panthor_device *ptdev,
> + struct panthor_file *pfile,
> + struct drm_printer *p)
> +{
> + if (ptdev->profile_mask & PANTHOR_DEVICE_PROFILING_TIMESTAMP) {
> +#ifdef CONFIG_ARM_ARCH_TIMER
> + drm_printf(p, "drm-engine-panthor:\t%llu ns\n",
> + DIV_ROUND_UP_ULL((pfile->stats.time * NSEC_PER_SEC),
> + arch_timer_get_cntfrq()));
> +#endif
> + }
> + if (ptdev->profile_mask & PANTHOR_DEVICE_PROFILING_CYCLES)
> + drm_printf(p, "drm-cycles-panthor:\t%llu\n", pfile->stats.cycles);
Don't know if that's an issue, but another thread might be updating the
stats while show_fdinfo() is run, which means the data you return might
be coming from two different sampling points.
> +
> + drm_printf(p, "drm-maxfreq-panthor:\t%lu Hz\n", ptdev->fast_rate);
> + drm_printf(p, "drm-curfreq-panthor:\t%lu Hz\n", ptdev->current_frequency);
> +}
> +
> +static void panthor_show_fdinfo(struct drm_printer *p, struct drm_file *file)
> +{
> + struct drm_device *dev = file->minor->dev;
> + struct panthor_device *ptdev = container_of(dev, struct panthor_device, base);
> +
> + panthor_gpu_show_fdinfo(ptdev, file->driver_priv, p);
> +
> + drm_show_memory_stats(p, file);
> +}
> +
> static const struct file_operations panthor_drm_driver_fops = {
> .open = drm_open,
> .release = drm_release,
> @@ -1360,6 +1393,7 @@ static const struct file_operations panthor_drm_driver_fops = {
> .read = drm_read,
> .llseek = noop_llseek,
> .mmap = panthor_mmap,
> + .show_fdinfo = drm_show_fdinfo,
> };
>
> #ifdef CONFIG_DEBUG_FS
> @@ -1378,6 +1412,7 @@ static const struct drm_driver panthor_drm_driver = {
> DRIVER_SYNCOBJ_TIMELINE | DRIVER_GEM_GPUVA,
> .open = panthor_open,
> .postclose = panthor_postclose,
> + .show_fdinfo = panthor_show_fdinfo,
> .ioctls = panthor_drm_driver_ioctls,
> .num_ioctls = ARRAY_SIZE(panthor_drm_driver_ioctls),
> .fops = &panthor_drm_driver_fops,
> diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
> index b087648bf59a..e69ab5175ae8 100644
> --- a/drivers/gpu/drm/panthor/panthor_sched.c
> +++ b/drivers/gpu/drm/panthor/panthor_sched.c
> @@ -619,6 +619,18 @@ struct panthor_group {
> */
> struct panthor_kernel_bo *syncobjs;
>
> + /** @fdinfo: Per-file total cycle and timestamp values reference. */
> + struct {
> + /** @data: Pointer to actual per-file sample data. */
> + struct panthor_gpu_usage *data;
> +
> + /**
> + * @lock: Mutex to govern concurrent access from drm file's fdinfo callback
> + * and job post-completion processing function
> + */
> + struct mutex lock;
> + } fdinfo;
> +
> /** @state: Group state. */
> enum panthor_group_state state;
>
> @@ -886,6 +898,8 @@ static void group_release_work(struct work_struct *work)
> release_work);
> u32 i;
>
> + mutex_destroy(&group->fdinfo.lock);
> +
> for (i = 0; i < group->queue_count; i++)
> group_free_queue(group, group->queues[i]);
>
> @@ -2808,6 +2822,28 @@ void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed)
> }
> }
>
> +static void update_fdinfo_stats(struct panthor_job *job)
> +{
> + struct panthor_group *group = job->group;
> + struct panthor_queue *queue = group->queues[job->queue_idx];
> + struct panthor_gpu_usage *fdinfo;
> + struct panthor_job_profiling_data *times;
> +
> + times = (struct panthor_job_profiling_data *)
> + ((unsigned long) queue->profiling_info.slots->kmap +
> + (job->profiling_slot * sizeof(struct panthor_job_profiling_data)));
> +
> + mutex_lock(&group->fdinfo.lock);
> + if ((group->fdinfo.data)) {
> + fdinfo = group->fdinfo.data;
> + if (job->profile_mask & PANTHOR_DEVICE_PROFILING_CYCLES)
> + fdinfo->cycles += times->cycles.after - times->cycles.before;
> + if (job->profile_mask & PANTHOR_DEVICE_PROFILING_TIMESTAMP)
> + fdinfo->time += times->time.after - times->time.before;
> + }
> + mutex_unlock(&group->fdinfo.lock);
> +}
> +
> static void group_sync_upd_work(struct work_struct *work)
> {
> struct panthor_group *group =
> @@ -2840,6 +2876,8 @@ static void group_sync_upd_work(struct work_struct *work)
> dma_fence_end_signalling(cookie);
>
> list_for_each_entry_safe(job, job_tmp, &done_jobs, node) {
> + if (job->profile_mask)
> + update_fdinfo_stats(job);
> list_del_init(&job->node);
> panthor_job_put(&job->base);
> }
> @@ -3430,6 +3468,9 @@ int panthor_group_create(struct panthor_file *pfile,
> }
> mutex_unlock(&sched->reset.lock);
>
> + group->fdinfo.data = &pfile->stats;
> + mutex_init(&group->fdinfo.lock);
> +
> return gid;
>
> err_put_group:
> @@ -3469,6 +3510,10 @@ int panthor_group_destroy(struct panthor_file *pfile, u32 group_handle)
> mutex_unlock(&sched->lock);
> mutex_unlock(&sched->reset.lock);
>
> + mutex_lock(&group->fdinfo.lock);
> + group->fdinfo.data = NULL;
> + mutex_unlock(&group->fdinfo.lock);
> +
> group_put(group);
> return 0;
> }
