Message ID | 1390223426-27627-3-git-send-email-deepak.s@intel.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On Mon, Jan 20, 2014 at 06:40:25PM +0530, deepak.s@intel.com wrote: > From: Deepak S <deepak.s@intel.com> > > When we enter RC6 and GFX Clocks are off, the voltage remains higher > than Vmin. When we try to set the freq to RPe, it might fail since the > Gfx clocks are down. So to fix this in Gfx idle, Bring the GFX clock up > and set the freq to RPe then move GFx down. > > v2: remove vlv_update_rps_cur_delay function. Update commit message (Daniel) > > v3: Fix the timeout during wait for gfx clock (Jesse) > > Signed-off-by: Deepak S <deepak.s@intel.com> > --- > drivers/gpu/drm/i915/i915_reg.h | 4 ++++ > drivers/gpu/drm/i915/intel_pm.c | 48 ++++++++++++++++++++++++++++++++++++++++- > 2 files changed, 51 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h > index cc2f3de..e1d5f31 100644 > --- a/drivers/gpu/drm/i915/i915_reg.h > +++ b/drivers/gpu/drm/i915/i915_reg.h > @@ -4944,6 +4944,10 @@ > GEN6_PM_RP_DOWN_THRESHOLD | \ > GEN6_PM_RP_DOWN_TIMEOUT) > > +#define VLV_GTLC_SURVIVABILITY_REG 0x130098 > +#define VLV_GFX_CLK_STATUS_BIT (1<<3) > +#define VLV_GFX_CLK_FORCE_ON_BIT (1<<2) > + > #define GEN6_GT_GFX_RC6_LOCKED 0x138104 > #define VLV_COUNTER_CONTROL 0x138104 > #define VLV_COUNT_RANGE_HIGH (1<<15) > diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c > index d00a2cf..86d87e5 100644 > --- a/drivers/gpu/drm/i915/intel_pm.c > +++ b/drivers/gpu/drm/i915/intel_pm.c > @@ -3035,6 +3035,51 @@ void gen6_set_rps(struct drm_device *dev, u8 val) > trace_intel_gpu_freq_change(val * 50); > } > > +/* vlv_set_rps_idle: Set the frequency to Rpe if Gfx clocks are down > + * > + * * If Gfx is Idle, then > + * 1. Mask Turbo interrupts > + * 2. Bring up Gfx clock > + * 3. Change the freq to Rpe and wait till P-Unit updates freq > + * 4. Clear the Force GFX CLK ON bit so that Gfx can down > + * 5. Unmask Turbo interrupts > +*/ > +static void vlv_set_rps_idle(struct drm_i915_private *dev_priv) > +{ > + /* > + * When we are idle. Drop to min voltage state. > + */ > + > + if (dev_priv->rps.cur_delay == dev_priv->rps.rpe_delay) > + return; > + > + /* Mask turbo interrupt so that they will not come in between */ > + I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); > + > + /* Bring up the Gfx clock */ > + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, > + I915_READ(VLV_GTLC_SURVIVABILITY_REG) | > + VLV_GFX_CLK_FORCE_ON_BIT); > + > + if (wait_for_atomic_us(((VLV_GFX_CLK_STATUS_BIT & > + I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 500)) { > + DRM_ERROR("GFX_CLK_ON request timed out\n"); > + return; > + } > + > + valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay); We're not actually waiting for Punit here. Should we? Also valleyview_set_rps() won't actually do anything if cur_delay == rpe_delay. Are we required to actually poke the Punit here, or is it enough that we had already previously requested <=rpe_delay? In that case I think it might make sense to skip this if cur_delay <= rpe_delay. But if we really need to poke Punit to make sure it changes the frequency/voltage, then I guess we should force the issue by eg. setting cur_delay=0 just before calling valleyview_set_rps(). > + > + /* Release the Gfx clock */ > + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, > + I915_READ(VLV_GTLC_SURVIVABILITY_REG) & > + ~VLV_GFX_CLK_FORCE_ON_BIT); > + > + /* Unmask Turbo interrupts */ > + I915_WRITE(GEN6_PMINTRMSK, ~GEN6_PM_RPS_EVENTS); > +} > + > + > + > void gen6_rps_idle(struct drm_i915_private *dev_priv) > { > struct drm_device *dev = dev_priv->dev; > @@ -3042,7 +3087,7 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv) > mutex_lock(&dev_priv->rps.hw_lock); > if (dev_priv->rps.enabled) { > if (IS_VALLEYVIEW(dev)) > - valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_delay); > + vlv_set_rps_idle(dev_priv); > else > gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay); > dev_priv->rps.last_adj = 0; > @@ -4273,6 +4318,7 @@ void intel_gpu_ips_teardown(void) > i915_mch_dev = NULL; > spin_unlock_irq(&mchdev_lock); > } > + > static void intel_init_emon(struct drm_device *dev) > { > struct drm_i915_private *dev_priv = dev->dev_private; > -- > 1.8.4.2 > > _______________________________________________ > Intel-gfx mailing list > Intel-gfx@lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/intel-gfx
>We're not actually waiting for Punit here. Should we? Ideally yes, we need to wait for the Punit to grant the freq. Based on your suggestion on " vlv_update_rps_cur_delay" that the punit will recheck the situation periodically, and it will try to use PUNIT_REG_GPU_FREQ_REQ. I removed the wait form this patch. I do believe we need to wait here. To make sure the requested freq is set before bring down the Gfx clk. >Also valleyview_set_rps() won't actually do anything if cur_delay == rpe_delay. Are we required to actually poke the Punit here, or is it enough that we had already previously requested <=rpe_delay? In that case I think it might make sense to skip this if cur_delay <= rpe_delay. >But if we really need to poke Punit to make sure it changes the frequency/voltage, then I guess we should force the issue by eg. setting >cur_delay=0 just before calling valleyview_set_rps(). I agree, I think instead of valleyview_set_rps we can use " vlv_punit_write" and request the freq and wait for punit to grant the freq if required. Btw, still using outlook, I will send the next replay from new email client :) -----Original Message----- From: Ville Syrjälä [mailto:ville.syrjala@linux.intel.com] Sent: Tuesday, January 21, 2014 8:13 PM To: S, Deepak Cc: intel-gfx@lists.freedesktop.org Subject: Re: [Intel-gfx] [PATCH v3 2/3] drm/i915/vlv: WA to fix Voltage not getting dropped to Vmin when Gfx is power gated. On Mon, Jan 20, 2014 at 06:40:25PM +0530, deepak.s@intel.com wrote: > From: Deepak S <deepak.s@intel.com> > > When we enter RC6 and GFX Clocks are off, the voltage remains higher > than Vmin. When we try to set the freq to RPe, it might fail since the > Gfx clocks are down. So to fix this in Gfx idle, Bring the GFX clock > up and set the freq to RPe then move GFx down. > > v2: remove vlv_update_rps_cur_delay function. Update commit message > (Daniel) > > v3: Fix the timeout during wait for gfx clock (Jesse) > > Signed-off-by: Deepak S <deepak.s@intel.com> > --- > drivers/gpu/drm/i915/i915_reg.h | 4 ++++ > drivers/gpu/drm/i915/intel_pm.c | 48 > ++++++++++++++++++++++++++++++++++++++++- > 2 files changed, 51 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/i915/i915_reg.h > b/drivers/gpu/drm/i915/i915_reg.h index cc2f3de..e1d5f31 100644 > --- a/drivers/gpu/drm/i915/i915_reg.h > +++ b/drivers/gpu/drm/i915/i915_reg.h > @@ -4944,6 +4944,10 @@ > GEN6_PM_RP_DOWN_THRESHOLD | \ > GEN6_PM_RP_DOWN_TIMEOUT) > > +#define VLV_GTLC_SURVIVABILITY_REG 0x130098 > +#define VLV_GFX_CLK_STATUS_BIT (1<<3) > +#define VLV_GFX_CLK_FORCE_ON_BIT (1<<2) > + > #define GEN6_GT_GFX_RC6_LOCKED 0x138104 > #define VLV_COUNTER_CONTROL 0x138104 > #define VLV_COUNT_RANGE_HIGH (1<<15) > diff --git a/drivers/gpu/drm/i915/intel_pm.c > b/drivers/gpu/drm/i915/intel_pm.c index d00a2cf..86d87e5 100644 > --- a/drivers/gpu/drm/i915/intel_pm.c > +++ b/drivers/gpu/drm/i915/intel_pm.c > @@ -3035,6 +3035,51 @@ void gen6_set_rps(struct drm_device *dev, u8 val) > trace_intel_gpu_freq_change(val * 50); } > > +/* vlv_set_rps_idle: Set the frequency to Rpe if Gfx clocks are down > + * > + * * If Gfx is Idle, then > + * 1. Mask Turbo interrupts > + * 2. Bring up Gfx clock > + * 3. Change the freq to Rpe and wait till P-Unit updates freq > + * 4. Clear the Force GFX CLK ON bit so that Gfx can down > + * 5. Unmask Turbo interrupts > +*/ > +static void vlv_set_rps_idle(struct drm_i915_private *dev_priv) { > + /* > + * When we are idle. Drop to min voltage state. > + */ > + > + if (dev_priv->rps.cur_delay == dev_priv->rps.rpe_delay) > + return; > + > + /* Mask turbo interrupt so that they will not come in between */ > + I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); > + > + /* Bring up the Gfx clock */ > + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, > + I915_READ(VLV_GTLC_SURVIVABILITY_REG) | > + VLV_GFX_CLK_FORCE_ON_BIT); > + > + if (wait_for_atomic_us(((VLV_GFX_CLK_STATUS_BIT & > + I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 500)) { > + DRM_ERROR("GFX_CLK_ON request timed out\n"); > + return; > + } > + > + valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay); We're not actually waiting for Punit here. Should we? Also valleyview_set_rps() won't actually do anything if cur_delay == rpe_delay. Are we required to actually poke the Punit here, or is it enough that we had already previously requested <=rpe_delay? In that case I think it might make sense to skip this if cur_delay <= rpe_delay. But if we really need to poke Punit to make sure it changes the frequency/voltage, then I guess we should force the issue by eg. setting cur_delay=0 just before calling valleyview_set_rps(). > + > + /* Release the Gfx clock */ > + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, > + I915_READ(VLV_GTLC_SURVIVABILITY_REG) & > + ~VLV_GFX_CLK_FORCE_ON_BIT); > + > + /* Unmask Turbo interrupts */ > + I915_WRITE(GEN6_PMINTRMSK, ~GEN6_PM_RPS_EVENTS); } > + > + > + > void gen6_rps_idle(struct drm_i915_private *dev_priv) { > struct drm_device *dev = dev_priv->dev; @@ -3042,7 +3087,7 @@ void > gen6_rps_idle(struct drm_i915_private *dev_priv) > mutex_lock(&dev_priv->rps.hw_lock); > if (dev_priv->rps.enabled) { > if (IS_VALLEYVIEW(dev)) > - valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_delay); > + vlv_set_rps_idle(dev_priv); > else > gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay); > dev_priv->rps.last_adj = 0; > @@ -4273,6 +4318,7 @@ void intel_gpu_ips_teardown(void) > i915_mch_dev = NULL; > spin_unlock_irq(&mchdev_lock); > } > + > static void intel_init_emon(struct drm_device *dev) { > struct drm_i915_private *dev_priv = dev->dev_private; > -- > 1.8.4.2 > > _______________________________________________ > Intel-gfx mailing list > Intel-gfx@lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/intel-gfx -- Ville Syrjälä Intel OTC
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index cc2f3de..e1d5f31 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4944,6 +4944,10 @@ GEN6_PM_RP_DOWN_THRESHOLD | \ GEN6_PM_RP_DOWN_TIMEOUT) +#define VLV_GTLC_SURVIVABILITY_REG 0x130098 +#define VLV_GFX_CLK_STATUS_BIT (1<<3) +#define VLV_GFX_CLK_FORCE_ON_BIT (1<<2) + #define GEN6_GT_GFX_RC6_LOCKED 0x138104 #define VLV_COUNTER_CONTROL 0x138104 #define VLV_COUNT_RANGE_HIGH (1<<15) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index d00a2cf..86d87e5 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3035,6 +3035,51 @@ void gen6_set_rps(struct drm_device *dev, u8 val) trace_intel_gpu_freq_change(val * 50); } +/* vlv_set_rps_idle: Set the frequency to Rpe if Gfx clocks are down + * + * * If Gfx is Idle, then + * 1. Mask Turbo interrupts + * 2. Bring up Gfx clock + * 3. Change the freq to Rpe and wait till P-Unit updates freq + * 4. Clear the Force GFX CLK ON bit so that Gfx can down + * 5. Unmask Turbo interrupts +*/ +static void vlv_set_rps_idle(struct drm_i915_private *dev_priv) +{ + /* + * When we are idle. Drop to min voltage state. + */ + + if (dev_priv->rps.cur_delay == dev_priv->rps.rpe_delay) + return; + + /* Mask turbo interrupt so that they will not come in between */ + I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); + + /* Bring up the Gfx clock */ + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, + I915_READ(VLV_GTLC_SURVIVABILITY_REG) | + VLV_GFX_CLK_FORCE_ON_BIT); + + if (wait_for_atomic_us(((VLV_GFX_CLK_STATUS_BIT & + I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 500)) { + DRM_ERROR("GFX_CLK_ON request timed out\n"); + return; + } + + valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay); + + /* Release the Gfx clock */ + I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, + I915_READ(VLV_GTLC_SURVIVABILITY_REG) & + ~VLV_GFX_CLK_FORCE_ON_BIT); + + /* Unmask Turbo interrupts */ + I915_WRITE(GEN6_PMINTRMSK, ~GEN6_PM_RPS_EVENTS); +} + + + void gen6_rps_idle(struct drm_i915_private *dev_priv) { struct drm_device *dev = dev_priv->dev; @@ -3042,7 +3087,7 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv) mutex_lock(&dev_priv->rps.hw_lock); if (dev_priv->rps.enabled) { if (IS_VALLEYVIEW(dev)) - valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_delay); + vlv_set_rps_idle(dev_priv); else gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay); dev_priv->rps.last_adj = 0; @@ -4273,6 +4318,7 @@ void intel_gpu_ips_teardown(void) i915_mch_dev = NULL; spin_unlock_irq(&mchdev_lock); } + static void intel_init_emon(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private;