Re: [PATCH v3 1/6] drm/i915/skl: Add support for the SAGV, fix underrun hangs

["Ville Syrjälä" <ville.syrjala@linux.intel.com>]

On Tue, Jul 26, 2016 at 04:58:58PM +0200, Maarten Lankhorst wrote:
> Op 26-07-16 om 16:50 schreef Lyude:
> > Since the watermark calculations for Skylake are still broken, we're apt
> > to hitting underruns very easily under multi-monitor configurations.
> > While it would be lovely if this was fixed, it's not. Another problem
> > that's been coming from this however, is the mysterious issue of
> > underruns causing full system hangs. An easy way to reproduce this with
> > a skylake system:
> >
> > - Get a laptop with a skylake GPU, and hook up two external monitors to
> >   it
> > - Move the cursor from the built-in LCD to one of the external displays
> >   as quickly as you can
> > - You'll get a few pipe underruns, and eventually the entire system will
> >   just freeze.
> >
> > After doing a lot of investigation and reading through the bspec, I
> > found the existence of the SAGV, which is responsible for adjusting the
> > system agent voltage and clock frequencies depending on how much power
> > we need. According to the bspec:
> >
> > "The display engine access to system memory is blocked during the
> >  adjustment time. SAGV defaults to enabled. Software must use the
> >  GT-driver pcode mailbox to disable SAGV when the display engine is not
> >  able to tolerate the blocking time."
> >
> > The rest of the bspec goes on to explain that software can simply leave
> > the SAGV enabled, and disable it when we use interlaced pipes/have more
> > then one pipe active.
> >
> > Sure enough, with this patchset the system hangs resulting from pipe
> > underruns on Skylake have completely vanished on my T460s. Additionally,
> > the bspec mentions turning off the SAGV	with more then one pipe enabled
> > as a workaround for display underruns. While this patch doesn't entirely
> > fix that, it looks like it does improve the situation a little bit so
> > it's likely this is going to be required to make watermarks on Skylake
> > fully functional.
> >
> > Changes since v3:
> >  - Use time_before() to compare timeout to jiffies
> > Changes since v2:
> >  - Really apply minor style nitpicks to patch this time
> > Changes since v1:
> >  - Added comments about this probably being one of the requirements to
> >    fixing Skylake's watermark issues
> >  - Minor style nitpicks from Matt Roper
> >  - Disable these functions on Broxton, since it doesn't have an SAGV
> >
> > Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
> > Signed-off-by: Lyude <cpaul@redhat.com>
> > Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
> > Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > Cc: stable@vger.kernel.org
> > ---
> >  drivers/gpu/drm/i915/i915_drv.h |   2 +
> >  drivers/gpu/drm/i915/i915_reg.h |   5 ++
> >  drivers/gpu/drm/i915/intel_pm.c | 110 ++++++++++++++++++++++++++++++++++++++++
> >  3 files changed, 117 insertions(+)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> > index 9f655e2..1f6fe8c 100644
> > --- a/drivers/gpu/drm/i915/i915_drv.h
> > +++ b/drivers/gpu/drm/i915/i915_drv.h
> > @@ -1962,6 +1962,8 @@ struct drm_i915_private {
> >  	struct i915_suspend_saved_registers regfile;
> >  	struct vlv_s0ix_state vlv_s0ix_state;
> >  
> > +	bool skl_sagv_enabled;
> > +
> >  	struct {
> >  		/*
> >  		 * Raw watermark latency values:
> > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> > index 9397dde..89d146f 100644
> > --- a/drivers/gpu/drm/i915/i915_reg.h
> > +++ b/drivers/gpu/drm/i915/i915_reg.h
> > @@ -7166,6 +7166,11 @@ enum {
> >  #define   HSW_PCODE_DE_WRITE_FREQ_REQ		0x17
> >  #define   DISPLAY_IPS_CONTROL			0x19
> >  #define	  HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL	0x1A
> > +#define   GEN9_PCODE_SAGV_CONTROL		0x21
> > +#define     GEN9_SAGV_DISABLE			0x0
> > +#define     GEN9_SAGV_LOW_FREQ			0x1
> > +#define     GEN9_SAGV_HIGH_FREQ			0x2
> > +#define     GEN9_SAGV_DYNAMIC_FREQ              0x3
> >  #define GEN6_PCODE_DATA				_MMIO(0x138128)
> >  #define   GEN6_PCODE_FREQ_IA_RATIO_SHIFT	8
> >  #define   GEN6_PCODE_FREQ_RING_RATIO_SHIFT	16
> > diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> > index 64d628c..066fe6b 100644
> > --- a/drivers/gpu/drm/i915/intel_pm.c
> > +++ b/drivers/gpu/drm/i915/intel_pm.c
> > @@ -2876,6 +2876,109 @@ skl_wm_plane_id(const struct intel_plane *plane)
> >  }
> >  
> >  static void
> > +skl_sagv_get_hw_state(struct drm_i915_private *dev_priv)
> > +{
> > +	u32 temp;
> > +	int ret;
> > +
> > +	if (IS_BROXTON(dev_priv))
> > +		return;
> > +
> > +	mutex_lock(&dev_priv->rps.hw_lock);
> > +	ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL, &temp);
> > +	mutex_unlock(&dev_priv->rps.hw_lock);
> > +
> > +	if (!ret) {
> > +		dev_priv->skl_sagv_enabled = !!(temp & GEN9_SAGV_DYNAMIC_FREQ);
> > +	} else {
> > +		/*
> > +		 * If for some reason we can't access the SAGV state, follow
> > +		 * the bspec and assume it's enabled
> > +		 */
> > +		DRM_ERROR("Failed to get SAGV state, assuming enabled\n");
> > +		dev_priv->skl_sagv_enabled = true;
> > +	}
> > +}
> > +
> > +/*
> > + * SAGV dynamically adjusts the system agent voltage and clock frequencies
> > + * depending on power and performance requirements. The display engine access
> > + * to system memory is blocked during the adjustment time. Having this enabled
> > + * in multi-pipe configurations can cause issues (such as underruns causing
> > + * full system hangs), and the bspec also suggests that software disable it
> > + * when more then one pipe is enabled.
> > + */
> > +static int
> > +skl_enable_sagv(struct drm_i915_private *dev_priv)
> > +{
> > +	int ret;
> > +
> > +	if (IS_BROXTON(dev_priv))
> > +		return 0;
> > +	if (dev_priv->skl_sagv_enabled)
> > +		return 0;
> > +
> > +	mutex_lock(&dev_priv->rps.hw_lock);
> > +	DRM_DEBUG_KMS("Enabling the SAGV\n");
> > +
> > +	ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
> > +				      GEN9_SAGV_DYNAMIC_FREQ);
> > +	if (!ret)
> > +		dev_priv->skl_sagv_enabled = true;
> > +	else
> > +		DRM_ERROR("Failed to enable the SAGV\n");
> > +
> > +	/* We don't need to wait for SAGV when enabling */
> > +	mutex_unlock(&dev_priv->rps.hw_lock);
> > +	return ret;
> > +}
> > +
> > +static int
> > +skl_disable_sagv(struct drm_i915_private *dev_priv)
> > +{
> > +	int ret = 0;
> > +	unsigned long timeout;
> > +	u32 temp;
> > +
> > +	if (IS_BROXTON(dev_priv))
> > +		return 0;
> > +	if (!dev_priv->skl_sagv_enabled)
> > +		return 0;
> > +
> > +	mutex_lock(&dev_priv->rps.hw_lock);
> > +	DRM_DEBUG_KMS("Disabling the SAGV\n");
> > +
> > +	/* bspec says to keep retrying for at least 1 ms */
> > +	timeout = jiffies + msecs_to_jiffies(1);
> > +	do {
> > +		ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
> > +					      GEN9_SAGV_DISABLE);
> > +		if (ret) {
> > +			DRM_ERROR("Failed to disable the SAGV\n");
> > +			goto out;
> > +		}
> > +
> > +		ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL,
> > +					     &temp);
> > +		if (ret) {
> > +			DRM_ERROR("Failed to check the status of the SAGV\n");
> > +			goto out;
> > +		}
> > +	} while (!(temp & 0x1) && time_before(jiffies, timeout));
> > +
> > +	if (temp & 0x1) {
> > +		dev_priv->skl_sagv_enabled = false;
> > +	} else {
> > +		ret = -1;
> > +		DRM_ERROR("Request to disable SAGV timed out\n");
> > +	}
> > +
> > +out:
> > +	mutex_unlock(&dev_priv->rps.hw_lock);
> > +	return ret;
> > +}
> > +
> > +static void
> >  skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
> >  				   const struct intel_crtc_state *cstate,
> >  				   struct skl_ddb_entry *alloc, /* out */
> > @@ -3686,6 +3789,11 @@ static void skl_write_wm_values(struct drm_i915_private *dev_priv,
> >  	struct drm_device *dev = &dev_priv->drm;
> >  	struct intel_crtc *crtc;
> >  
> > +	if (dev_priv->active_crtcs == 1)
> > +		skl_enable_sagv(dev_priv);
> > +	else
> > +		skl_disable_sagv(dev_priv);
> active_crtcs is a bitmask, so unless you only want to enable it for PIPE_A,
> you should use: if (intel_state->modeset && hweight32(intel_state->active_crtcs) == 1)

is_power_of_2() is a bit cheaper. Oh and we want this this thing enabled
w/ 0 active pipes too.

-- 
Ville Syrjälä
Intel OTC