[Intel-gfx] [PATCH] drm/i915: Debugfs to disable context banning

[Jeff McGee]

On Tue, Oct 17, 2017 at 05:36:54PM +0200, Daniel Vetter wrote:
> On Tue, Oct 17, 2017 at 08:25:33AM -0700, jeff.mcgee at intel.com wrote:
> > From: Jeff McGee <jeff.mcgee at intel.com>
> > 
> > Useful for stress testing various reset scenarios. The ioctl that we
> > have for specific client/context banning disable is difficult to utilize
> > outside of unit testing.
> 
> Do we have these stress tests available somewhere?
> -Daniel
> 
Potentially any test scenario that relies upon app/umd instead of IGT to
inject batches that need to be reset would benefit from the ability to
disable context banning. We are using such scenarios to validate for the
Yocto APL project, specifically for a feature where preemption of non-
preemptible batches is forced using reset. It it not needed for IGT-based
reset stress tests.
-Jeff

> > 
> > Signed-off-by: Jeff McGee <jeff.mcgee at intel.com>
> > ---
> >  drivers/gpu/drm/i915/i915_debugfs.c | 25 +++++++++++++++++++++++++
> >  drivers/gpu/drm/i915/i915_drv.h     |  2 ++
> >  drivers/gpu/drm/i915/i915_gem.c     |  3 ++-
> >  3 files changed, 29 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> > index 0bb6e01121fc..17e6b388b80c 100644
> > --- a/drivers/gpu/drm/i915/i915_debugfs.c
> > +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> > @@ -4408,6 +4408,30 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_min_freq_fops,
> >  			i915_min_freq_get, i915_min_freq_set,
> >  			"%llu\n");
> >  
> > +static int i915_banning_disable_get(void *data, u64 *val)
> > +{
> > +	struct drm_device *dev = data;
> > +	struct drm_i915_private *dev_priv = dev->dev_private;
> > +
> > +	*val = dev_priv->gpu_error.banning_disabled;
> > +
> > +	return 0;
> > +}
> > +
> > +static int i915_banning_disable_set(void *data, u64 val)
> > +{
> > +	struct drm_device *dev = data;
> > +	struct drm_i915_private *dev_priv = dev->dev_private;
> > +
> > +	dev_priv->gpu_error.banning_disabled = (bool)val;
> > +
> > +	return 0;
> > +}
> > +
> > +DEFINE_SIMPLE_ATTRIBUTE(i915_banning_disable_fops,
> > +			i915_banning_disable_get, i915_banning_disable_set,
> > +			"%llu\n");
> > +
> >  static int
> >  i915_cache_sharing_get(void *data, u64 *val)
> >  {
> > @@ -4829,6 +4853,7 @@ static const struct i915_debugfs_files {
> >  	{"i915_guc_log_control", &i915_guc_log_control_fops},
> >  	{"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops},
> >  	{"i915_ipc_status", &i915_ipc_status_fops}
> > +	{"i915_banning_disable", &i915_banning_disable_fops},
> >  };
> >  
> >  int i915_debugfs_register(struct drm_i915_private *dev_priv)
> > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> > index c7b2ca6aff05..da65b6f8cc6f 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -1667,6 +1667,8 @@ struct i915_gpu_error {
> >  
> >  	/* For missed irq/seqno simulation. */
> >  	unsigned long test_irq_rings;
> > +
> > +	bool banning_disabled;
> >  };
> >  
> >  enum modeset_restore {
> > diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> > index 20fcac37c85a..e0cb53cafc66 100644
> > --- a/drivers/gpu/drm/i915/i915_gem.c
> > +++ b/drivers/gpu/drm/i915/i915_gem.c
> > @@ -2770,7 +2770,8 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
> >  static bool ban_context(const struct i915_gem_context *ctx,
> >  			unsigned int score)
> >  {
> > -	return (i915_gem_context_is_bannable(ctx) &&
> > +	return (!ctx->i915->gpu_error.banning_disabled &&
> > +		i915_gem_context_is_bannable(ctx) &&
> >  		score >= CONTEXT_SCORE_BAN_THRESHOLD);
> >  }
> >  
> > -- 
> > 2.14.2
> > 
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx at lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/intel-gfx
> 
> -- 
> Daniel Vetter
> Software Engineer, Intel Corporation
> http://blog.ffwll.ch