The drm-stats fdinfo tags made available to user space are drm-engine,
drm-cycles, drm-max-freq and drm-curfreq, one per job slot.
This deviates from standard practice in other DRM drivers, where a single
set of key:value pairs is provided for the whole render engine. However,
Panfrost has separate queues for fragment and vertex/tiler jobs, so a
decision was made to calculate bus cycles and workload times separately.
Maximum operating frequency is calculated at devfreq initialisation time.
Current frequency is made available to user space because nvtop uses it
when performing engine usage calculations.
It is important to bear in mind that both GPU cycle and kernel time numbers
provided are at best rough estimations, and always reported in excess from
the actual figure because of two reasons:
- Excess time because of the delay between the end of a job processing,
the subsequent job IRQ and the actual time of the sample.
- Time spent in the engine queue waiting for the GPU to pick up the next
job.
To avoid race conditions during enablement/disabling, a reference counting
mechanism was introduced, and a job flag that tells us whether a given job
increased the refcount. This is necessary, because user space can toggle
cycle counting through a debugfs file, and a given job might have been in
flight by the time cycle counting was disabled.
The main goal of the debugfs cycle counter knob is letting tools like nvtop
or IGT's gputop switch it at any time, to avoid power waste in case no
engine usage measuring is necessary.
Also add a documentation file explaining the possible values for fdinfo's
engine keystrings and Panfrost-specific drm-curfreq-<keystr> pairs.
Signed-off-by: Adrián Larumbe <adrian.larumbe@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230929181616.2769345-3-adrian.larumbe@collabora.com
-------------------------------
:ref:`i915-usage-stats`
+:ref:`panfrost-usage-stats`
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0+
+
+=========================
+ drm/Panfrost Mali Driver
+=========================
+
+.. _panfrost-usage-stats:
+
+Panfrost DRM client usage stats implementation
+==============================================
+
+The drm/Panfrost driver implements the DRM client usage stats specification as
+documented in :ref:`drm-client-usage-stats`.
+
+Example of the output showing the implemented key value pairs and entirety of
+the currently possible format options:
+
+::
+ pos: 0
+ flags: 02400002
+ mnt_id: 27
+ ino: 531
+ drm-driver: panfrost
+ drm-client-id: 14
+ drm-engine-fragment: 1846584880 ns
+ drm-cycles-fragment: 1424359409
+ drm-maxfreq-fragment: 799999987 Hz
+ drm-curfreq-fragment: 799999987 Hz
+ drm-engine-vertex-tiler: 71932239 ns
+ drm-cycles-vertex-tiler: 52617357
+ drm-maxfreq-vertex-tiler: 799999987 Hz
+ drm-curfreq-vertex-tiler: 799999987 Hz
+ drm-total-memory: 290 MiB
+ drm-shared-memory: 0 MiB
+ drm-active-memory: 226 MiB
+ drm-resident-memory: 36496 KiB
+ drm-purgeable-memory: 128 KiB
+
+Possible `drm-engine-` key names are: `fragment`, and `vertex-tiler`.
+`drm-curfreq-` values convey the current operating frequency for that engine.
L: dri-devel@lists.freedesktop.org
S: Supported
T: git git://anongit.freedesktop.org/drm/drm-misc
+F: Documentation/gpu/panfrost.rst
F: drivers/gpu/drm/panfrost/
F: include/uapi/drm/panfrost_drm.h
panfrost_perfcnt.o \
panfrost_dump.o
+panfrost-$(CONFIG_DEBUG_FS) += panfrost_debugfs.o
+
obj-$(CONFIG_DRM_PANFROST) += panfrost.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2023 Collabora ltd. */
+/* Copyright 2023 Amazon.com, Inc. or its affiliates. */
+
+#include <linux/debugfs.h>
+#include <linux/platform_device.h>
+#include <drm/drm_debugfs.h>
+#include <drm/drm_file.h>
+#include <drm/panfrost_drm.h>
+
+#include "panfrost_device.h"
+#include "panfrost_gpu.h"
+#include "panfrost_debugfs.h"
+
+void panfrost_debugfs_init(struct drm_minor *minor)
+{
+ struct drm_device *dev = minor->dev;
+ struct panfrost_device *pfdev = platform_get_drvdata(to_platform_device(dev->dev));
+
+ debugfs_create_atomic_t("profile", 0600, minor->debugfs_root, &pfdev->profile_mode);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2023 Collabora ltd.
+ * Copyright 2023 Amazon.com, Inc. or its affiliates.
+ */
+
+#ifndef PANFROST_DEBUGFS_H
+#define PANFROST_DEBUGFS_H
+
+#ifdef CONFIG_DEBUG_FS
+void panfrost_debugfs_init(struct drm_minor *minor);
+#endif
+
+#endif /* PANFROST_DEBUGFS_H */
spin_lock_irqsave(&pfdevfreq->lock, irqflags);
panfrost_devfreq_update_utilization(pfdevfreq);
+ pfdevfreq->current_frequency = status->current_frequency;
status->total_time = ktime_to_ns(ktime_add(pfdevfreq->busy_time,
pfdevfreq->idle_time));
struct devfreq *devfreq;
struct thermal_cooling_device *cooling;
struct panfrost_devfreq *pfdevfreq = &pfdev->pfdevfreq;
+ unsigned long freq = ULONG_MAX;
if (pfdev->comp->num_supplies > 1) {
/*
return ret;
}
+ /* Find the fastest defined rate */
+ opp = dev_pm_opp_find_freq_floor(dev, &freq);
+ if (IS_ERR(opp))
+ return PTR_ERR(opp);
+ pfdevfreq->fast_rate = freq;
+
dev_pm_opp_put(opp);
/*
struct devfreq_simple_ondemand_data gov_data;
bool opp_of_table_added;
+ unsigned long current_frequency;
+ unsigned long fast_rate;
+
ktime_t busy_time;
ktime_t idle_time;
ktime_t time_last_update;
spin_lock_init(&pfdev->as_lock);
+ spin_lock_init(&pfdev->cycle_counter.lock);
+
err = panfrost_clk_init(pfdev);
if (err) {
dev_err(pfdev->dev, "clk init failed %d\n", err);
struct list_head scheduled_jobs;
struct panfrost_perfcnt *perfcnt;
+ atomic_t profile_mode;
struct mutex sched_lock;
struct shrinker shrinker;
struct panfrost_devfreq pfdevfreq;
+
+ struct {
+ atomic_t use_count;
+ spinlock_t lock;
+ } cycle_counter;
};
struct panfrost_mmu {
struct list_head list;
};
+struct panfrost_engine_usage {
+ unsigned long long elapsed_ns[NUM_JOB_SLOTS];
+ unsigned long long cycles[NUM_JOB_SLOTS];
+};
+
struct panfrost_file_priv {
struct panfrost_device *pfdev;
struct drm_sched_entity sched_entity[NUM_JOB_SLOTS];
struct panfrost_mmu *mmu;
+
+ struct panfrost_engine_usage engine_usage;
};
static inline struct panfrost_device *to_panfrost_device(struct drm_device *ddev)
#include "panfrost_job.h"
#include "panfrost_gpu.h"
#include "panfrost_perfcnt.h"
+#include "panfrost_debugfs.h"
static bool unstable_ioctls;
module_param_unsafe(unstable_ioctls, bool, 0600);
job->requirements = args->requirements;
job->flush_id = panfrost_gpu_get_latest_flush_id(pfdev);
job->mmu = file_priv->mmu;
+ job->engine_usage = &file_priv->engine_usage;
slot = panfrost_job_get_slot(job);
PANFROST_IOCTL(MADVISE, madvise, DRM_RENDER_ALLOW),
};
-DEFINE_DRM_GEM_FOPS(panfrost_drm_driver_fops);
+static void panfrost_gpu_show_fdinfo(struct panfrost_device *pfdev,
+ struct panfrost_file_priv *panfrost_priv,
+ struct drm_printer *p)
+{
+ int i;
+
+ /*
+ * IMPORTANT NOTE: drm-cycles and drm-engine measurements are not
+ * accurate, as they only provide a rough estimation of the number of
+ * GPU cycles and CPU time spent in a given context. This is due to two
+ * different factors:
+ * - Firstly, we must consider the time the CPU and then the kernel
+ * takes to process the GPU interrupt, which means additional time and
+ * GPU cycles will be added in excess to the real figure.
+ * - Secondly, the pipelining done by the Job Manager (2 job slots per
+ * engine) implies there is no way to know exactly how much time each
+ * job spent on the GPU.
+ */
+
+ static const char * const engine_names[] = {
+ "fragment", "vertex-tiler", "compute-only"
+ };
+
+ BUILD_BUG_ON(ARRAY_SIZE(engine_names) != NUM_JOB_SLOTS);
+
+ for (i = 0; i < NUM_JOB_SLOTS - 1; i++) {
+ drm_printf(p, "drm-engine-%s:\t%llu ns\n",
+ engine_names[i], panfrost_priv->engine_usage.elapsed_ns[i]);
+ drm_printf(p, "drm-cycles-%s:\t%llu\n",
+ engine_names[i], panfrost_priv->engine_usage.cycles[i]);
+ drm_printf(p, "drm-maxfreq-%s:\t%lu Hz\n",
+ engine_names[i], pfdev->pfdevfreq.fast_rate);
+ drm_printf(p, "drm-curfreq-%s:\t%lu Hz\n",
+ engine_names[i], pfdev->pfdevfreq.current_frequency);
+ }
+}
+
+static void panfrost_show_fdinfo(struct drm_printer *p, struct drm_file *file)
+{
+ struct drm_device *dev = file->minor->dev;
+ struct panfrost_device *pfdev = dev->dev_private;
+
+ panfrost_gpu_show_fdinfo(pfdev, file->driver_priv, p);
+}
+
+static const struct file_operations panfrost_drm_driver_fops = {
+ .owner = THIS_MODULE,
+ DRM_GEM_FOPS,
+ .show_fdinfo = drm_show_fdinfo,
+};
/*
* Panfrost driver version:
.driver_features = DRIVER_RENDER | DRIVER_GEM | DRIVER_SYNCOBJ,
.open = panfrost_open,
.postclose = panfrost_postclose,
+ .show_fdinfo = panfrost_show_fdinfo,
.ioctls = panfrost_drm_driver_ioctls,
.num_ioctls = ARRAY_SIZE(panfrost_drm_driver_ioctls),
.fops = &panfrost_drm_driver_fops,
.gem_create_object = panfrost_gem_create_object,
.gem_prime_import_sg_table = panfrost_gem_prime_import_sg_table,
+
+#ifdef CONFIG_DEBUG_FS
+ .debugfs_init = panfrost_debugfs_init,
+#endif
};
static int panfrost_probe(struct platform_device *pdev)
gpu_write(pfdev, GPU_INT_CLEAR, GPU_IRQ_MASK_ALL);
gpu_write(pfdev, GPU_INT_MASK, GPU_IRQ_MASK_ALL);
+ /*
+ * All in-flight jobs should have released their cycle
+ * counter references upon reset, but let us make sure
+ */
+ if (drm_WARN_ON(pfdev->ddev, atomic_read(&pfdev->cycle_counter.use_count) != 0))
+ atomic_set(&pfdev->cycle_counter.use_count, 0);
+
return 0;
}
pfdev->features.shader_present, pfdev->features.l2_present);
}
+void panfrost_cycle_counter_get(struct panfrost_device *pfdev)
+{
+ if (atomic_inc_not_zero(&pfdev->cycle_counter.use_count))
+ return;
+
+ spin_lock(&pfdev->cycle_counter.lock);
+ if (atomic_inc_return(&pfdev->cycle_counter.use_count) == 1)
+ gpu_write(pfdev, GPU_CMD, GPU_CMD_CYCLE_COUNT_START);
+ spin_unlock(&pfdev->cycle_counter.lock);
+}
+
+void panfrost_cycle_counter_put(struct panfrost_device *pfdev)
+{
+ if (atomic_add_unless(&pfdev->cycle_counter.use_count, -1, 1))
+ return;
+
+ spin_lock(&pfdev->cycle_counter.lock);
+ if (atomic_dec_return(&pfdev->cycle_counter.use_count) == 0)
+ gpu_write(pfdev, GPU_CMD, GPU_CMD_CYCLE_COUNT_STOP);
+ spin_unlock(&pfdev->cycle_counter.lock);
+}
+
+unsigned long long panfrost_cycle_counter_read(struct panfrost_device *pfdev)
+{
+ u32 hi, lo;
+
+ do {
+ hi = gpu_read(pfdev, GPU_CYCLE_COUNT_HI);
+ lo = gpu_read(pfdev, GPU_CYCLE_COUNT_LO);
+ } while (hi != gpu_read(pfdev, GPU_CYCLE_COUNT_HI));
+
+ return ((u64)hi << 32) | lo;
+}
+
void panfrost_gpu_power_on(struct panfrost_device *pfdev)
{
int ret;
void panfrost_gpu_power_on(struct panfrost_device *pfdev);
void panfrost_gpu_power_off(struct panfrost_device *pfdev);
+void panfrost_cycle_counter_get(struct panfrost_device *pfdev);
+void panfrost_cycle_counter_put(struct panfrost_device *pfdev);
+unsigned long long panfrost_cycle_counter_read(struct panfrost_device *pfdev);
+
void panfrost_gpu_amlogic_quirk(struct panfrost_device *pfdev);
#endif
struct panfrost_job *job = pfdev->jobs[slot][0];
WARN_ON(!job);
+ if (job->is_profiled) {
+ if (job->engine_usage) {
+ job->engine_usage->elapsed_ns[slot] +=
+ ktime_to_ns(ktime_sub(ktime_get(), job->start_time));
+ job->engine_usage->cycles[slot] +=
+ panfrost_cycle_counter_read(pfdev) - job->start_cycles;
+ }
+ panfrost_cycle_counter_put(job->pfdev);
+ }
+
pfdev->jobs[slot][0] = pfdev->jobs[slot][1];
pfdev->jobs[slot][1] = NULL;
subslot = panfrost_enqueue_job(pfdev, js, job);
/* Don't queue the job if a reset is in progress */
if (!atomic_read(&pfdev->reset.pending)) {
+ if (atomic_read(&pfdev->profile_mode)) {
+ panfrost_cycle_counter_get(pfdev);
+ job->is_profiled = true;
+ job->start_time = ktime_get();
+ job->start_cycles = panfrost_cycle_counter_read(pfdev);
+ }
+
job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START);
dev_dbg(pfdev->dev,
"JS: Submitting atom %p to js[%d][%d] with head=0x%llx AS %d",
* stuck jobs. Let's make sure the PM counters stay balanced by
* manually calling pm_runtime_put_noidle() and
* panfrost_devfreq_record_idle() for each stuck job.
+ * Let's also make sure the cycle counting register's refcnt is
+ * kept balanced to prevent it from running forever
*/
spin_lock(&pfdev->js->job_lock);
for (i = 0; i < NUM_JOB_SLOTS; i++) {
for (j = 0; j < ARRAY_SIZE(pfdev->jobs[0]) && pfdev->jobs[i][j]; j++) {
+ if (pfdev->jobs[i][j]->is_profiled)
+ panfrost_cycle_counter_put(pfdev->jobs[i][j]->pfdev);
pm_runtime_put_noidle(pfdev->dev);
panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
}
}
job_write(pfdev, JS_COMMAND(i), cmd);
+
+ /* Jobs can outlive their file context */
+ job->engine_usage = NULL;
}
}
spin_unlock(&pfdev->js->job_lock);
/* Fence to be signaled by drm-sched once its done with the job */
struct dma_fence *render_done_fence;
+
+ struct panfrost_engine_usage *engine_usage;
+ bool is_profiled;
+ ktime_t start_time;
+ u64 start_cycles;
};
int panfrost_job_init(struct panfrost_device *pfdev);
projects / linux.git / commitdiff