Re: [PATCH 7/7] drm/i915: add i915_get_reset_stats_ioctl

[Ian Romanick <idr@freedesktop.org>]

On 10/27/2013 05:30 AM, Daniel Vetter wrote:
> On Fri, Oct 25, 2013 at 06:42:35PM -0700, Ian Romanick wrote:
>> Since the Mesa merge window is closing soon, I'm finally getting back on
>> this.  I've pushed a rebase of my old Mesa branch to my fd.o repo
>>
>> http://cgit.freedesktop.org/~idr/mesa/log/?h=robustness3
>>
>> I have a couple questions...
>>
>> 1. Has any of this landed an a kernel tree anywhere?
> 
> Afaik everything but the actual ioctl and i-g-t testcase has landed.

And that stuff will land once my patches hit the Mesa list or ... ?

>> 2. Has any support code landed in a libdrm tree anywhere?
> 
> Dunno whether Mika has libdrm patches. Since mesa is the only expected
> user I'd just go with putting the ioctl wrapper (using the drmIoctl
> helper) into mesa itself, that get rids of a dep for merging this support.

What's the right way to get the ctx_id out of the drm_intel_context?
That struct is private to libdrm, but the ioctl needs it.

>> 3. What method should I use to detect that the kernel has support?  In
>> early discussions, reset notification was only going to be available on
>> some GPUs, so there was a getparam to detect actual availability.  I
>> guess now it's just based on kernel version?
> 
> Usually we add a new feature flag to get get_param ioctl if there's no
> natural way otherwise for userspace to figure this out (usually by calling
> the new ioctl and disabling the feature if that doesn't work).
> -Daniel
> 
>>
>> It looks like I should just need to update df87cdd and 61dad8e in my
>> Mesa tree.
>>
>> On 07/03/2013 07:22 AM, Mika Kuoppala wrote:
>>> This ioctl returns reset stats for specified context.
>>>
>>> The struct returned contains context loss counters.
>>>
>>> reset_count:    all resets across all contexts
>>> batch_active:   active batches lost on resets
>>> batch_pending:  pending batches lost on resets
>>>
>>> v2: get rid of state tracking completely and deliver only counts. Idea
>>>     from Chris Wilson.
>>>
>>> v3: fix commit message
>>>
>>> v4: default context handled inside i915_gem_contest_get_hang_stats
>>>
>>> v5: reset_count only for priviledged process
>>>
>>> v6: ctx=0 needs CAP_SYS_ADMIN for batch_* counters (Chris Wilson)
>>>
>>> v7: context hang stats never returns NULL
>>>
>>> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
>>> Cc: Ian Romanick <idr@freedesktop.org>
>>> Cc: Chris Wilson <chris@chris-wilson.co.uk>
>>> Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
>>> ---
>>>  drivers/gpu/drm/i915/i915_dma.c |    1 +
>>>  drivers/gpu/drm/i915/i915_drv.c |   34 ++++++++++++++++++++++++++++++++++
>>>  drivers/gpu/drm/i915/i915_drv.h |    2 ++
>>>  include/uapi/drm/i915_drm.h     |   17 +++++++++++++++++
>>>  4 files changed, 54 insertions(+)
>>>
>>> diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
>>> index 0e22142..d1a006f 100644
>>> --- a/drivers/gpu/drm/i915/i915_dma.c
>>> +++ b/drivers/gpu/drm/i915/i915_dma.c
>>> @@ -1889,6 +1889,7 @@ struct drm_ioctl_desc i915_ioctls[] = {
>>>  	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_CREATE, i915_gem_context_create_ioctl, DRM_UNLOCKED),
>>>  	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED),
>>>  	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED),
>>> +	DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_get_reset_stats_ioctl, DRM_UNLOCKED),
>>>  };
>>>  
>>>  int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);
>>> diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
>>> index 33cb973..0d4e3a8 100644
>>> --- a/drivers/gpu/drm/i915/i915_drv.c
>>> +++ b/drivers/gpu/drm/i915/i915_drv.c
>>> @@ -1350,3 +1350,37 @@ int i915_reg_read_ioctl(struct drm_device *dev,
>>>  
>>>  	return 0;
>>>  }
>>> +
>>> +int i915_get_reset_stats_ioctl(struct drm_device *dev,
>>> +			       void *data, struct drm_file *file)
>>> +{
>>> +	struct drm_i915_private *dev_priv = dev->dev_private;
>>> +	struct drm_i915_reset_stats *args = data;
>>> +	struct i915_ctx_hang_stats *hs;
>>> +	int ret;
>>> +
>>> +	if (args->ctx_id == 0 && !capable(CAP_SYS_ADMIN))
>>> +		return -EPERM;
>>> +
>>> +	ret = mutex_lock_interruptible(&dev->struct_mutex);
>>> +	if (ret)
>>> +		return ret;
>>> +
>>> +	hs = i915_gem_context_get_hang_stats(dev, file, args->ctx_id);
>>> +	if (IS_ERR(hs)) {
>>> +		mutex_unlock(&dev->struct_mutex);
>>> +		return PTR_ERR(hs);
>>> +	}
>>> +
>>> +	if (capable(CAP_SYS_ADMIN))
>>> +		args->reset_count = i915_reset_count(&dev_priv->gpu_error);
>>> +	else
>>> +		args->reset_count = 0;
>>> +
>>> +	args->batch_active = hs->batch_active;
>>> +	args->batch_pending = hs->batch_pending;
>>> +
>>> +	mutex_unlock(&dev->struct_mutex);
>>> +
>>> +	return 0;
>>> +}
>>> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
>>> index 1def049..0ca98fa 100644
>>> --- a/drivers/gpu/drm/i915/i915_drv.h
>>> +++ b/drivers/gpu/drm/i915/i915_drv.h
>>> @@ -2021,6 +2021,8 @@ extern int intel_enable_rc6(const struct drm_device *dev);
>>>  extern bool i915_semaphore_is_enabled(struct drm_device *dev);
>>>  int i915_reg_read_ioctl(struct drm_device *dev, void *data,
>>>  			struct drm_file *file);
>>> +int i915_get_reset_stats_ioctl(struct drm_device *dev, void *data,
>>> +			       struct drm_file *file);
>>>  
>>>  /* overlay */
>>>  #ifdef CONFIG_DEBUG_FS
>>> diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
>>> index 923ed7f..29b07fd 100644
>>> --- a/include/uapi/drm/i915_drm.h
>>> +++ b/include/uapi/drm/i915_drm.h
>>> @@ -198,6 +198,7 @@ typedef struct _drm_i915_sarea {
>>>  #define DRM_I915_GEM_SET_CACHING	0x2f
>>>  #define DRM_I915_GEM_GET_CACHING	0x30
>>>  #define DRM_I915_REG_READ		0x31
>>> +#define DRM_I915_GET_RESET_STATS	0x32
>>>  
>>>  #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
>>>  #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
>>> @@ -247,6 +248,7 @@ typedef struct _drm_i915_sarea {
>>>  #define DRM_IOCTL_I915_GEM_CONTEXT_CREATE	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
>>>  #define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
>>>  #define DRM_IOCTL_I915_REG_READ			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
>>> +#define DRM_IOCTL_I915_GET_RESET_STATS		DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
>>>  
>>>  /* Allow drivers to submit batchbuffers directly to hardware, relying
>>>   * on the security mechanisms provided by hardware.
>>> @@ -981,4 +983,19 @@ struct drm_i915_reg_read {
>>>  	__u64 offset;
>>>  	__u64 val; /* Return value */
>>>  };
>>> +
>>> +struct drm_i915_reset_stats {
>>> +	__u32 ctx_id;
>>> +	__u32 flags;
>>> +
>>> +	/* For all contexts */
>>> +	__u32 reset_count;
>>> +
>>> +	/* For this context */
>>> +	__u32 batch_active;
>>> +	__u32 batch_pending;
>>> +
>>> +	__u32 pad;
>>> +};
>>> +
>>>  #endif /* _UAPI_I915_DRM_H_ */
>>>