drm/msm: Expose client engine utilization via fdinfo

Similar to AMD commit
87444254 ("drm/amdgpu: Add show_fdinfo() interface"), using the
infrastructure added in previous patches, we add basic client info
and GPU engine utilisation for msm.

Example output:

	# cat /proc/`pgrep glmark2`/fdinfo/6
	pos:	0
	flags:	02400002
	mnt_id:	21
	ino:	162
	drm-driver:	msm
	drm-client-id:	7
	drm-engine-gpu:	1734371319 ns
	drm-cycles-gpu:	1153645024
	drm-maxfreq-gpu:	800000000 Hz

See also: https://patchwork.freedesktop.org/patch/468505/

v2: Add dev-maxfreq-$engine and update drm-usage-stats.rst
v3: spelling and compiler warning
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Patchwork: https://patchwork.freedesktop.org/patch/488906/
Link: https://lore.kernel.org/r/20220609174213.2265938-2-robdclark@gmail.comSigned-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>

Documentation/gpu/drm-usage-stats.rst

@@ -105,6 +105,27 @@ object belong to this client, in the respective memory region.
 Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
 indicating kibi- or mebi-bytes.
 
+- drm-cycles-<str> <uint>
+
+Engine identifier string must be the same as the one specified in the
+drm-engine-<str> tag and shall contain the number of busy cycles for the given
+engine.
+
+Values are not required to be constantly monotonic if it makes the driver
+implementation easier, but are required to catch up with the previously reported
+larger value within a reasonable period. Upon observing a value lower than what
+was previously read, userspace is expected to stay with that larger previous
+value until a monotonic update is seen.
+
+- drm-maxfreq-<str> <uint> [Hz|MHz|KHz]
+
+Engine identifier string must be the same as the one specified in the
+drm-engine-<str> tag and shall contain the maximum frequency for the given
+engine.  Taken together with drm-cycles-<str>, this can be used to calculate
+percentage utilization of the engine, whereas drm-engine-<str> only reflects
+time active without considering what frequency the engine is operating as a
+percentage of it's maximum frequency.
+
 ===============================
 Driver specific implementations
 ===============================

drivers/gpu/drm/msm/msm_drv.c

@@ -948,7 +948,24 @@ static const struct drm_ioctl_desc msm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MSM_SUBMITQUEUE_QUERY, msm_ioctl_submitqueue_query, DRM_RENDER_ALLOW),
 };
 
-DEFINE_DRM_GEM_FOPS(fops);
+static void msm_fop_show_fdinfo(struct seq_file *m, struct file *f)
+{
+	struct drm_file *file = f->private_data;
+	struct drm_device *dev = file->minor->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_printer p = drm_seq_file_printer(m);
+
+	if (!priv->gpu)
+		return;
+
+	msm_gpu_show_fdinfo(priv->gpu, file->driver_priv, &p);
+}
+
+static const struct file_operations fops = {
+	.owner = THIS_MODULE,
+	DRM_GEM_FOPS,
+	.show_fdinfo = msm_fop_show_fdinfo,
+};
 
 static const struct drm_driver msm_driver = {
 	.driver_features    = DRIVER_GEM |

drivers/gpu/drm/msm/msm_gpu.c

@@ -4,6 +4,8 @@
  * Author: Rob Clark <robdclark@gmail.com>
  */
 
+#include "drm/drm_drv.h"
+
 #include "msm_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
@@ -146,6 +148,16 @@ int msm_gpu_pm_suspend(struct msm_gpu *gpu)
 	return 0;
 }
 
+void msm_gpu_show_fdinfo(struct msm_gpu *gpu, struct msm_file_private *ctx,
+			 struct drm_printer *p)
+{
+	drm_printf(p, "drm-driver:\t%s\n", gpu->dev->driver->name);
+	drm_printf(p, "drm-client-id:\t%u\n", ctx->seqno);
+	drm_printf(p, "drm-engine-gpu:\t%llu ns\n", ctx->elapsed_ns);
+	drm_printf(p, "drm-cycles-gpu:\t%llu\n", ctx->cycles);
+	drm_printf(p, "drm-maxfreq-gpu:\t%u Hz\n", gpu->fast_rate);
+}
+
 int msm_gpu_hw_init(struct msm_gpu *gpu)
 {
 	int ret;
@@ -634,7 +646,7 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 {
 	int index = submit->seqno % MSM_GPU_SUBMIT_STATS_COUNT;
 	volatile struct msm_gpu_submit_stats *stats;
-	u64 elapsed, clock = 0;
+	u64 elapsed, clock = 0, cycles;
 	unsigned long flags;
 
 	stats = &ring->memptrs->stats[index];
@@ -642,12 +654,17 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	elapsed = (stats->alwayson_end - stats->alwayson_start) * 10000;
 	do_div(elapsed, 192);
 
+	cycles = stats->cpcycles_end - stats->cpcycles_start;
+
 	/* Calculate the clock frequency from the number of CP cycles */
 	if (elapsed) {
-		clock = (stats->cpcycles_end - stats->cpcycles_start) * 1000;
+		clock = cycles * 1000;
 		do_div(clock, elapsed);
 	}
 
+	submit->queue->ctx->elapsed_ns += elapsed;
+	submit->queue->ctx->cycles     += cycles;
+
 	trace_msm_gpu_submit_retired(submit, elapsed, clock,
 		stats->alwayson_start, stats->alwayson_end);
 

drivers/gpu/drm/msm/msm_gpu.h

@@ -361,6 +361,22 @@ struct msm_file_private {
 	/** cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE */
 	char *cmdline;
 
+	/**
+	 * elapsed:
+	 *
+	 * The total (cumulative) elapsed time GPU was busy with rendering
+	 * from this context in ns.
+	 */
+	uint64_t elapsed_ns;
+
+	/**
+	 * cycles:
+	 *
+	 * The total (cumulative) GPU cycles elapsed attributed to this
+	 * context.
+	 */
+	uint64_t cycles;
+
 	/**
 	 * entities:
 	 *
@@ -544,6 +560,9 @@ static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val)
 int msm_gpu_pm_suspend(struct msm_gpu *gpu);
 int msm_gpu_pm_resume(struct msm_gpu *gpu);
 
+void msm_gpu_show_fdinfo(struct msm_gpu *gpu, struct msm_file_private *ctx,
+			 struct drm_printer *p);
+
 int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx);
 struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx,
 		u32 id);