Re: [RFC 4/5] drm/i915: Expose per-engine client busyness

[Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>]

On 14/02/2018 19:17, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2018-02-14 18:50:34)
>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>>
>> Expose per-client and per-engine busyness under the previously added sysfs
>> client root.
>>
>> The new files are one per-engine instance and located under the 'busy'
>> directory.
>>
>> Each contains a monotonically increasing nano-second resolution times each
>> client's jobs were executing on the GPU.
>>
>> $ cat /sys/class/drm/card0/clients/5/busy/rcs0
>> 32516602
>>
>> This data can serve as an interface to implement a top like utility for
>> GPU jobs. For instance I have prototyped a tool in IGT which produces
>> periodic output like:
>>
>> neverball[  6011]:  rcs0:  41.01%  bcs0:   0.00%  vcs0:   0.00%  vecs0:   0.00%
>>       Xorg[  5664]:  rcs0:  31.16%  bcs0:   0.00%  vcs0:   0.00%  vecs0:   0.00%
>>      xfwm4[  5727]:  rcs0:   0.00%  bcs0:   0.00%  vcs0:   0.00%  vecs0:   0.00%
>>
>> This tools can also be extended to use the i915 PMU and show overall engine
>> busyness, and engine loads using the queue depth metric.
>>
>> v2: Use intel_context_engine_get_busy_time.
>> v3: New directory structure.
>>
>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
>> ---
>>   drivers/gpu/drm/i915/i915_drv.h |  8 ++++
>>   drivers/gpu/drm/i915/i915_gem.c | 86 +++++++++++++++++++++++++++++++++++++++--
>>   2 files changed, 91 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
>> index 372d13cb2472..d6b2883b42fe 100644
>> --- a/drivers/gpu/drm/i915/i915_drv.h
>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>> @@ -315,6 +315,12 @@ struct drm_i915_private;
>>   struct i915_mm_struct;
>>   struct i915_mmu_object;
>>   
>> +struct i915_engine_busy_attribute {
>> +       struct device_attribute attr;
>> +       struct drm_i915_file_private *file_priv;
>> +       struct intel_engine_cs *engine;
>> +};
>> +
>>   struct drm_i915_file_private {
>>          struct drm_i915_private *dev_priv;
>>          struct drm_file *file;
>> @@ -350,10 +356,12 @@ struct drm_i915_file_private {
>>          unsigned int client_pid;
>>          char *client_name;
>>          struct kobject *client_root;
>> +       struct kobject *busy_root;
>>   
>>          struct {
>>                  struct device_attribute pid;
>>                  struct device_attribute name;
>> +               struct i915_engine_busy_attribute busy[I915_NUM_ENGINES];
>>          } attr;
>>   };
>>   
>> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
>> index 46ac7b3ca348..01298d924524 100644
>> --- a/drivers/gpu/drm/i915/i915_gem.c
>> +++ b/drivers/gpu/drm/i915/i915_gem.c
>> @@ -5631,6 +5631,45 @@ show_client_pid(struct device *kdev, struct device_attribute *attr, char *buf)
>>          return snprintf(buf, PAGE_SIZE, "%u", file_priv->client_pid);
>>   }
>>   
>> +struct busy_ctx {
>> +       struct intel_engine_cs *engine;
>> +       u64 total;
>> +};
>> +
>> +static int busy_add(int _id, void *p, void *data)
>> +{
>> +       struct i915_gem_context *ctx = p;
>> +       struct busy_ctx *bc = data;
>> +
>> +       bc->total +=
>> +               ktime_to_ns(intel_context_engine_get_busy_time(ctx,
>> +                                                              bc->engine));
>> +
>> +       return 0;
>> +}
>> +
>> +static ssize_t
>> +show_client_busy(struct device *kdev, struct device_attribute *attr, char *buf)
>> +{
>> +       struct i915_engine_busy_attribute *i915_attr =
>> +               container_of(attr, typeof(*i915_attr), attr);
>> +       struct drm_i915_file_private *file_priv = i915_attr->file_priv;
>> +       struct intel_engine_cs *engine = i915_attr->engine;
>> +       struct drm_i915_private *i915 = engine->i915;
>> +       struct busy_ctx bc = { .engine = engine };
>> +       int ret;
>> +
>> +       ret = i915_mutex_lock_interruptible(&i915->drm);
>> +       if (ret)
>> +               return ret;
>> +
> 
> Doesn't need struct_mutex, just rcu_read_lock() will suffice.
> 
> Neither the context nor idr will be freed too soon, and the data is
> involatile when the context is unreffed (and contexts don't have the
> nasty zombie/undead status of requests). So the busy-time will be
> stable.

Are you sure? What holds a reference to contexts while userspace might 
by in sysfs reading the stat? It would be super nice if we could avoid 
struct mutex here.. I just don't understand at the moment why it would 
be safe.

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx