| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <f460b115-6ff6-7f69-8b0d-174c4defc771@linux.intel.com>
Date: Mon, 28 Feb 2022 14:33:41 +0000
From: Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>
To: Rob Clark <robdclark@...il.com>,
dri-devel <dri-devel@...ts.freedesktop.org>
Cc: freedreno <freedreno@...ts.freedesktop.org>,
linux-arm-msm <linux-arm-msm@...r.kernel.org>,
Rob Clark <robdclark@...omium.org>,
Sean Paul <sean@...rly.run>,
Abhinav Kumar <quic_abhinavk@...cinc.com>,
David Airlie <airlied@...ux.ie>,
Daniel Vetter <daniel@...ll.ch>,
open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 3/3] drm/msm: Expose client engine utilization via fdinfo
On 25/02/2022 22:14, Rob Clark wrote:
> On Fri, Feb 25, 2022 at 12:25 PM Rob Clark <robdclark@...il.com> wrote:
>>
>> From: Rob Clark <robdclark@...omium.org>
>>
>> Similar to AMD commit
>> 874442541133 ("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
Nice, so my vendor agnostic actually worked (with that single fixup of
accounting for the fact pdev tag is optional)?
> Note that it might be useful to have a standardized way to report # of
> cycles and max freq, so userspace tool can derive %utilization in
> addition to just %busy
How do you define %utilisation vs %busy - I don't exactly follow since I
see the two as same?
Looking at your patch I guess I don't understand the difference between
'elapsed' and 'cycles' inside your retire_submit(). Both are scoped to a
single context and are not global? If 'elapsed' is time context has
spent on the GPU, cycles isn't the same just in a different unit?
Regards,
Tvrtko
> BR,
> -R
>
>>
>> See also: https://patchwork.freedesktop.org/patch/468505/
>>
>> Signed-off-by: Rob Clark <robdclark@...omium.org>
>> ---
>> drivers/gpu/drm/msm/msm_drv.c | 17 ++++++++++++++++-
>> drivers/gpu/drm/msm/msm_gpu.c | 20 ++++++++++++++++++--
>> drivers/gpu/drm/msm/msm_gpu.h | 19 +++++++++++++++++++
>> 3 files changed, 53 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
>> index 16f37f3d9061..fdf401e6f09e 100644
>> --- a/drivers/gpu/drm/msm/msm_drv.c
>> +++ b/drivers/gpu/drm/msm/msm_drv.c
>> @@ -911,7 +911,22 @@ 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);
>> +}
>> +
>> +DEFINE_DRM_GEM_FOPS(fops,
>> + .show_fdinfo = msm_fop_show_fdinfo,
>> +);
>>
>> static const struct drm_driver msm_driver = {
>> .driver_features = DRIVER_GEM |
>> diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
>> index 173ebd449f2f..6302f3fe564b 100644
>> --- a/drivers/gpu/drm/msm/msm_gpu.c
>> +++ b/drivers/gpu/drm/msm/msm_gpu.c
>> @@ -4,6 +4,8 @@
>> * Author: Rob Clark <robdclark@...il.com>
>> */
>>
>> +#include "drm/drm_drv.h"
>> +
>> #include "msm_gpu.h"
>> #include "msm_gem.h"
>> #include "msm_mmu.h"
>> @@ -146,6 +148,15 @@ 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);
>> +}
>> +
>> int msm_gpu_hw_init(struct msm_gpu *gpu)
>> {
>> int ret;
>> @@ -643,7 +654,7 @@ 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];
>> @@ -651,12 +662,17 @@ 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);
>>
>> diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
>> index 696e2ed8a236..ad4fe05dee03 100644
>> --- a/drivers/gpu/drm/msm/msm_gpu.h
>> +++ b/drivers/gpu/drm/msm/msm_gpu.h
>> @@ -328,6 +328,22 @@ struct msm_file_private {
>> struct kref ref;
>> int seqno;
>>
>> + /**
>> + * 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:
>> *
>> @@ -511,6 +527,9 @@ 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);
>> --
>> 2.35.1
>>
Powered by blists - more mailing lists