* [PATCH 01/10] drm/i915/bdw: Implement a basic PM interrupt handler
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-07 13:58 ` Ville Syrjälä
2014-05-05 12:47 ` [PATCH 02/10] drm/i915: Enable PM Interrupts target via Display Interface deepak.s
` (9 subsequent siblings)
10 siblings, 1 reply; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: Ben Widawsky, fafael.barbalho, Ben Widawsky
From: Ben Widawsky <benjamin.widawsky@intel.com>
Almost all of it is reusable from the existing code. The primary
difference is we need to do even less in the interrupt handler, since
interrupts are not shared in the same way.
The patch is mostly a copy-paste of the existing snb+ code, with updates
to the relevant parts requiring changes to the interrupt handling. As
such it /should/ be relatively trivial. It's highly likely that I missed
some places where I need a gen8 version of the PM interrupts, but it has
become invisible to me by now.
This patch could probably be split into adding the new functions,
followed by actually handling the interrupts. Since the code is
currently disabled (and broken) I think the patch stands better by
itself.
v2: Move the commit about not touching the ringbuffer interrupt to the
snb_* function where it belongs (Rodrigo)
v3: Rebased on Paulo's runtime PM changes
v4: Not well validated, but rebase on
commit 730488b2eddded4497f63f70867b1256cd9e117c
Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri Mar 7 20:12:32 2014 -0300
drm/i915: kill dev_priv->pm.regsave
v5: Rebased on latest code base. (Deepak)
v6: Remove conflict markers, Unnecessary empty line and use right
IIR interrupt (Ville)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
---
drivers/gpu/drm/i915/i915_irq.c | 75 ++++++++++++++++++++++++++++++++++++++--
drivers/gpu/drm/i915/i915_reg.h | 1 +
drivers/gpu/drm/i915/intel_drv.h | 2 ++
drivers/gpu/drm/i915/intel_pm.c | 38 ++++++++++++++++++--
4 files changed, 112 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 2d76183..6af51ad 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -248,6 +248,49 @@ static bool ivb_can_enable_err_int(struct drm_device *dev)
return true;
}
+/**
+ * bdw_update_pm_irq - update GT interrupt 2
+ * @dev_priv: driver private
+ * @interrupt_mask: mask of interrupt bits to update
+ * @enabled_irq_mask: mask of interrupt bits to enable
+ *
+ * Copied from the snb function, updated with relevant register offsets
+ */
+static void bdw_update_pm_irq(struct drm_i915_private *dev_priv,
+ uint32_t interrupt_mask,
+ uint32_t enabled_irq_mask)
+{
+ uint32_t new_val;
+
+ assert_spin_locked(&dev_priv->irq_lock);
+
+ if (dev_priv->pm.irqs_disabled) {
+ WARN(1, "IRQs disabled\n");
+ return;
+ }
+
+ new_val = dev_priv->pm_irq_mask;
+ new_val &= ~interrupt_mask;
+ new_val |= (~enabled_irq_mask & interrupt_mask);
+
+ if (new_val != dev_priv->pm_irq_mask) {
+ dev_priv->pm_irq_mask = new_val;
+ I915_WRITE(GEN8_GT_IMR(2), I915_READ(GEN8_GT_IMR(2)) |
+ dev_priv->pm_irq_mask);
+ POSTING_READ(GEN8_GT_IMR(2));
+ }
+}
+
+void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+ bdw_update_pm_irq(dev_priv, mask, mask);
+}
+
+void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+ bdw_update_pm_irq(dev_priv, mask, 0);
+}
+
static bool cpt_can_enable_serr_int(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1098,8 +1141,12 @@ static void gen6_pm_rps_work(struct work_struct *work)
spin_lock_irq(&dev_priv->irq_lock);
pm_iir = dev_priv->rps.pm_iir;
dev_priv->rps.pm_iir = 0;
- /* Make sure not to corrupt PMIMR state used by ringbuffer code */
- snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+ if (IS_BROADWELL(dev_priv->dev))
+ bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+ else {
+ /* Make sure not to corrupt PMIMR state used by ringbuffer */
+ snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+ }
spin_unlock_irq(&dev_priv->irq_lock);
/* Make sure we didn't queue anything we're not going to process. */
@@ -1296,6 +1343,19 @@ static void snb_gt_irq_handler(struct drm_device *dev,
ivybridge_parity_error_irq_handler(dev, gt_iir);
}
+static void gen8_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
+{
+ if ((pm_iir & dev_priv->pm_rps_events) == 0)
+ return;
+
+ spin_lock(&dev_priv->irq_lock);
+ dev_priv->rps.pm_iir |= pm_iir & dev_priv->pm_rps_events;
+ bdw_disable_pm_irq(dev_priv, pm_iir & dev_priv->pm_rps_events);
+ spin_unlock(&dev_priv->irq_lock);
+
+ queue_work(dev_priv->wq, &dev_priv->rps.work);
+}
+
static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
struct drm_i915_private *dev_priv,
u32 master_ctl)
@@ -1334,6 +1394,17 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
DRM_ERROR("The master control interrupt lied (GT1)!\n");
}
+ if (master_ctl & GEN8_GT_PM_IRQ) {
+ tmp = I915_READ(GEN8_GT_IIR(2));
+ if (tmp & dev_priv->pm_rps_events) {
+ ret = IRQ_HANDLED;
+ gen8_rps_irq_handler(dev_priv, tmp);
+ I915_WRITE(GEN8_GT_IIR(2),
+ tmp & dev_priv->pm_rps_events);
+ } else
+ DRM_ERROR("The master control interrupt lied (PM)!\n");
+ }
+
if (master_ctl & GEN8_GT_VECS_IRQ) {
tmp = I915_READ(GEN8_GT_IIR(3));
if (tmp) {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0eff337..ca4f8b9 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4194,6 +4194,7 @@ enum punit_power_well {
#define GEN8_DE_PIPE_A_IRQ (1<<16)
#define GEN8_DE_PIPE_IRQ(pipe) (1<<(16+pipe))
#define GEN8_GT_VECS_IRQ (1<<6)
+#define GEN8_GT_PM_IRQ (1<<4)
#define GEN8_GT_VCS2_IRQ (1<<3)
#define GEN8_GT_VCS1_IRQ (1<<2)
#define GEN8_GT_BCS_IRQ (1<<1)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index d8b540b..d560a9b 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -653,6 +653,8 @@ void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
void intel_runtime_pm_disable_interrupts(struct drm_device *dev);
void intel_runtime_pm_restore_interrupts(struct drm_device *dev);
int intel_get_crtc_scanline(struct intel_crtc *crtc);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 834c49c..0e69c97 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3246,6 +3246,26 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val));
}
+static void gen8_disable_rps_interrupts(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
+ I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
+ ~dev_priv->pm_rps_events);
+ /* Complete PM interrupt masking here doesn't race with the rps work
+ * item again unmasking PM interrupts because that is using a different
+ * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
+ * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
+ * gen8_enable_rps will clean up. */
+
+ spin_lock_irq(&dev_priv->irq_lock);
+ dev_priv->rps.pm_iir = 0;
+ spin_unlock_irq(&dev_priv->irq_lock);
+
+ I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
+}
+
static void gen6_disable_rps_interrupts(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3272,7 +3292,10 @@ static void gen6_disable_rps(struct drm_device *dev)
I915_WRITE(GEN6_RC_CONTROL, 0);
I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
- gen6_disable_rps_interrupts(dev);
+ if (IS_BROADWELL(dev))
+ gen8_disable_rps_interrupts(dev);
+ else
+ gen6_disable_rps_interrupts(dev);
}
static void valleyview_disable_rps(struct drm_device *dev)
@@ -3344,6 +3367,17 @@ int intel_enable_rc6(const struct drm_device *dev)
return i915.enable_rc6;
}
+static void gen8_enable_rps_interrupts(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ spin_lock_irq(&dev_priv->irq_lock);
+ WARN_ON(dev_priv->rps.pm_iir);
+ bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+ I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
+ spin_unlock_irq(&dev_priv->irq_lock);
+}
+
static void gen6_enable_rps_interrupts(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3446,7 +3480,7 @@ static void gen8_enable_rps(struct drm_device *dev)
gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8);
- gen6_enable_rps_interrupts(dev);
+ gen8_enable_rps_interrupts(dev);
gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
}
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH 01/10] drm/i915/bdw: Implement a basic PM interrupt handler
2014-05-05 12:47 ` [PATCH 01/10] drm/i915/bdw: Implement a basic PM interrupt handler deepak.s
@ 2014-05-07 13:58 ` Ville Syrjälä
0 siblings, 0 replies; 26+ messages in thread
From: Ville Syrjälä @ 2014-05-07 13:58 UTC (permalink / raw)
To: deepak.s; +Cc: intel-gfx, fafael.barbalho, Ben Widawsky, Ben Widawsky
On Mon, May 05, 2014 at 06:17:30PM +0530, deepak.s@linux.intel.com wrote:
> From: Ben Widawsky <benjamin.widawsky@intel.com>
>
> Almost all of it is reusable from the existing code. The primary
> difference is we need to do even less in the interrupt handler, since
> interrupts are not shared in the same way.
>
> The patch is mostly a copy-paste of the existing snb+ code, with updates
> to the relevant parts requiring changes to the interrupt handling. As
> such it /should/ be relatively trivial. It's highly likely that I missed
> some places where I need a gen8 version of the PM interrupts, but it has
> become invisible to me by now.
>
> This patch could probably be split into adding the new functions,
> followed by actually handling the interrupts. Since the code is
> currently disabled (and broken) I think the patch stands better by
> itself.
>
> v2: Move the commit about not touching the ringbuffer interrupt to the
> snb_* function where it belongs (Rodrigo)
>
> v3: Rebased on Paulo's runtime PM changes
>
> v4: Not well validated, but rebase on
> commit 730488b2eddded4497f63f70867b1256cd9e117c
> Author: Paulo Zanoni <paulo.r.zanoni@intel.com>
> Date: Fri Mar 7 20:12:32 2014 -0300
>
> drm/i915: kill dev_priv->pm.regsave
>
> v5: Rebased on latest code base. (Deepak)
>
> v6: Remove conflict markers, Unnecessary empty line and use right
> IIR interrupt (Ville)
>
> Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_irq.c | 75 ++++++++++++++++++++++++++++++++++++++--
> drivers/gpu/drm/i915/i915_reg.h | 1 +
> drivers/gpu/drm/i915/intel_drv.h | 2 ++
> drivers/gpu/drm/i915/intel_pm.c | 38 ++++++++++++++++++--
> 4 files changed, 112 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
> index 2d76183..6af51ad 100644
> --- a/drivers/gpu/drm/i915/i915_irq.c
> +++ b/drivers/gpu/drm/i915/i915_irq.c
> @@ -248,6 +248,49 @@ static bool ivb_can_enable_err_int(struct drm_device *dev)
> return true;
> }
>
> +/**
> + * bdw_update_pm_irq - update GT interrupt 2
> + * @dev_priv: driver private
> + * @interrupt_mask: mask of interrupt bits to update
> + * @enabled_irq_mask: mask of interrupt bits to enable
> + *
> + * Copied from the snb function, updated with relevant register offsets
> + */
> +static void bdw_update_pm_irq(struct drm_i915_private *dev_priv,
> + uint32_t interrupt_mask,
> + uint32_t enabled_irq_mask)
> +{
> + uint32_t new_val;
> +
> + assert_spin_locked(&dev_priv->irq_lock);
> +
> + if (dev_priv->pm.irqs_disabled) {
> + WARN(1, "IRQs disabled\n");
> + return;
> + }
Could be just 'if (WARN...' just like in the snb function.
> +
> + new_val = dev_priv->pm_irq_mask;
> + new_val &= ~interrupt_mask;
> + new_val |= (~enabled_irq_mask & interrupt_mask);
> +
> + if (new_val != dev_priv->pm_irq_mask) {
> + dev_priv->pm_irq_mask = new_val;
> + I915_WRITE(GEN8_GT_IMR(2), I915_READ(GEN8_GT_IMR(2)) |
> + dev_priv->pm_irq_mask);
I just realized that this doesn't actually clear the old bits. I think
we should just kill the RMW here and mandate that all users of GT_IMR(2)
need to use this function.
Also you're forgetting to initialize pm_irq_mask. I guess it should be
initialized in gen8_gt_irq_postinstall() to match the gen6 code.
> + POSTING_READ(GEN8_GT_IMR(2));
> + }
> +}
> +
> +void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
> +{
> + bdw_update_pm_irq(dev_priv, mask, mask);
> +}
> +
> +void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
> +{
> + bdw_update_pm_irq(dev_priv, mask, 0);
> +}
> +
> static bool cpt_can_enable_serr_int(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -1098,8 +1141,12 @@ static void gen6_pm_rps_work(struct work_struct *work)
> spin_lock_irq(&dev_priv->irq_lock);
> pm_iir = dev_priv->rps.pm_iir;
> dev_priv->rps.pm_iir = 0;
> - /* Make sure not to corrupt PMIMR state used by ringbuffer code */
> - snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
> + if (IS_BROADWELL(dev_priv->dev))
> + bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
> + else {
> + /* Make sure not to corrupt PMIMR state used by ringbuffer */
> + snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
> + }
> spin_unlock_irq(&dev_priv->irq_lock);
>
> /* Make sure we didn't queue anything we're not going to process. */
> @@ -1296,6 +1343,19 @@ static void snb_gt_irq_handler(struct drm_device *dev,
> ivybridge_parity_error_irq_handler(dev, gt_iir);
> }
>
> +static void gen8_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
> +{
> + if ((pm_iir & dev_priv->pm_rps_events) == 0)
> + return;
> +
> + spin_lock(&dev_priv->irq_lock);
> + dev_priv->rps.pm_iir |= pm_iir & dev_priv->pm_rps_events;
> + bdw_disable_pm_irq(dev_priv, pm_iir & dev_priv->pm_rps_events);
> + spin_unlock(&dev_priv->irq_lock);
> +
> + queue_work(dev_priv->wq, &dev_priv->rps.work);
> +}
> +
> static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
> struct drm_i915_private *dev_priv,
> u32 master_ctl)
> @@ -1334,6 +1394,17 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
> DRM_ERROR("The master control interrupt lied (GT1)!\n");
> }
>
> + if (master_ctl & GEN8_GT_PM_IRQ) {
> + tmp = I915_READ(GEN8_GT_IIR(2));
> + if (tmp & dev_priv->pm_rps_events) {
> + ret = IRQ_HANDLED;
> + gen8_rps_irq_handler(dev_priv, tmp);
> + I915_WRITE(GEN8_GT_IIR(2),
> + tmp & dev_priv->pm_rps_events);
> + } else
> + DRM_ERROR("The master control interrupt lied (PM)!\n");
> + }
> +
> if (master_ctl & GEN8_GT_VECS_IRQ) {
> tmp = I915_READ(GEN8_GT_IIR(3));
> if (tmp) {
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index 0eff337..ca4f8b9 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -4194,6 +4194,7 @@ enum punit_power_well {
> #define GEN8_DE_PIPE_A_IRQ (1<<16)
> #define GEN8_DE_PIPE_IRQ(pipe) (1<<(16+pipe))
> #define GEN8_GT_VECS_IRQ (1<<6)
> +#define GEN8_GT_PM_IRQ (1<<4)
> #define GEN8_GT_VCS2_IRQ (1<<3)
> #define GEN8_GT_VCS1_IRQ (1<<2)
> #define GEN8_GT_BCS_IRQ (1<<1)
> diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
> index d8b540b..d560a9b 100644
> --- a/drivers/gpu/drm/i915/intel_drv.h
> +++ b/drivers/gpu/drm/i915/intel_drv.h
> @@ -653,6 +653,8 @@ void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
> void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
> void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
> void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
> +void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
> +void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
> void intel_runtime_pm_disable_interrupts(struct drm_device *dev);
> void intel_runtime_pm_restore_interrupts(struct drm_device *dev);
> int intel_get_crtc_scanline(struct intel_crtc *crtc);
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 834c49c..0e69c97 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3246,6 +3246,26 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
> trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val));
> }
>
> +static void gen8_disable_rps_interrupts(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> +
> + I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
> + I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
> + ~dev_priv->pm_rps_events);
> + /* Complete PM interrupt masking here doesn't race with the rps work
> + * item again unmasking PM interrupts because that is using a different
> + * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
> + * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
> + * gen8_enable_rps will clean up. */
> +
> + spin_lock_irq(&dev_priv->irq_lock);
> + dev_priv->rps.pm_iir = 0;
> + spin_unlock_irq(&dev_priv->irq_lock);
> +
> + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
> +}
> +
> static void gen6_disable_rps_interrupts(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3272,7 +3292,10 @@ static void gen6_disable_rps(struct drm_device *dev)
> I915_WRITE(GEN6_RC_CONTROL, 0);
> I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
>
> - gen6_disable_rps_interrupts(dev);
> + if (IS_BROADWELL(dev))
> + gen8_disable_rps_interrupts(dev);
> + else
> + gen6_disable_rps_interrupts(dev);
> }
>
> static void valleyview_disable_rps(struct drm_device *dev)
> @@ -3344,6 +3367,17 @@ int intel_enable_rc6(const struct drm_device *dev)
> return i915.enable_rc6;
> }
>
> +static void gen8_enable_rps_interrupts(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> +
> + spin_lock_irq(&dev_priv->irq_lock);
> + WARN_ON(dev_priv->rps.pm_iir);
> + bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
> + I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
> + spin_unlock_irq(&dev_priv->irq_lock);
> +}
> +
> static void gen6_enable_rps_interrupts(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3446,7 +3480,7 @@ static void gen8_enable_rps(struct drm_device *dev)
>
> gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8);
>
> - gen6_enable_rps_interrupts(dev);
> + gen8_enable_rps_interrupts(dev);
>
> gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
> }
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Ville Syrjälä
Intel OTC
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH 02/10] drm/i915: Enable PM Interrupts target via Display Interface.
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
2014-05-05 12:47 ` [PATCH 01/10] drm/i915/bdw: Implement a basic PM interrupt handler deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-07 14:08 ` Ville Syrjälä
2014-05-14 15:37 ` [PATCH v3] " deepak.s
2014-05-05 12:47 ` [PATCH 03/10] drm/i915/chv: Enable Render Standby (RC6) for Cherryview deepak.s
` (8 subsequent siblings)
10 siblings, 2 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Deepak S <deepak.s@linux.intel.com>
In BDW, Apart from unmasking up/down threshold interrupts. we need
to umask bit 32 of PM_INTRMASK to route interrupts to target via Display
Interface.
v2: Add (1<<31) mask (Ville)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
---
drivers/gpu/drm/i915/i915_reg.h | 1 +
drivers/gpu/drm/i915/intel_pm.c | 2 ++
2 files changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ca4f8b9..c850254 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5112,6 +5112,7 @@ enum punit_power_well {
#define GEN6_RC6p_THRESHOLD 0xA0BC
#define GEN6_RC6pp_THRESHOLD 0xA0C0
#define GEN6_PMINTRMSK 0xA168
+#define GEN8_PMINTR_REDIRECT_TO_NON_DISP (1<<31)
#define GEN6_PMISR 0x44020
#define GEN6_PMIMR 0x44024 /* rps_lock */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0e69c97..ebb5c88 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3114,6 +3114,8 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev))
mask |= GEN6_PM_RP_UP_EI_EXPIRED;
+ mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP;
+
return ~mask;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH 02/10] drm/i915: Enable PM Interrupts target via Display Interface.
2014-05-05 12:47 ` [PATCH 02/10] drm/i915: Enable PM Interrupts target via Display Interface deepak.s
@ 2014-05-07 14:08 ` Ville Syrjälä
2014-05-14 15:37 ` [PATCH v3] " deepak.s
1 sibling, 0 replies; 26+ messages in thread
From: Ville Syrjälä @ 2014-05-07 14:08 UTC (permalink / raw)
To: deepak.s; +Cc: intel-gfx, fafael.barbalho
On Mon, May 05, 2014 at 06:17:31PM +0530, deepak.s@linux.intel.com wrote:
> From: Deepak S <deepak.s@linux.intel.com>
>
> In BDW, Apart from unmasking up/down threshold interrupts. we need
> to umask bit 32 of PM_INTRMASK to route interrupts to target via Display
> Interface.
>
> v2: Add (1<<31) mask (Ville)
>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_reg.h | 1 +
> drivers/gpu/drm/i915/intel_pm.c | 2 ++
> 2 files changed, 3 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index ca4f8b9..c850254 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -5112,6 +5112,7 @@ enum punit_power_well {
> #define GEN6_RC6p_THRESHOLD 0xA0BC
> #define GEN6_RC6pp_THRESHOLD 0xA0C0
> #define GEN6_PMINTRMSK 0xA168
> +#define GEN8_PMINTR_REDIRECT_TO_NON_DISP (1<<31)
>
> #define GEN6_PMISR 0x44020
> #define GEN6_PMIMR 0x44024 /* rps_lock */
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 0e69c97..ebb5c88 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3114,6 +3114,8 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
> if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev))
> mask |= GEN6_PM_RP_UP_EI_EXPIRED;
>
> + mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP;
> +
Didn't Ben want a gen check here?
> return ~mask;
> }
>
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Ville Syrjälä
Intel OTC
^ permalink raw reply [flat|nested] 26+ messages in thread* [PATCH v3] drm/i915: Enable PM Interrupts target via Display Interface.
2014-05-05 12:47 ` [PATCH 02/10] drm/i915: Enable PM Interrupts target via Display Interface deepak.s
2014-05-07 14:08 ` Ville Syrjälä
@ 2014-05-14 15:37 ` deepak.s
2014-05-14 15:47 ` Ville Syrjälä
1 sibling, 1 reply; 26+ messages in thread
From: deepak.s @ 2014-05-14 15:37 UTC (permalink / raw)
To: intel-gfx
From: Deepak S <deepak.s@linux.intel.com>
In BDW, Apart from unmasking up/down threshold interrupts. we need
to umask bit 32 of PM_INTRMASK to route interrupts to target via Display
Interface.
v2: Add (1<<31) mask (Ville)
v3: Add Gen check for the mask (ville)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
---
drivers/gpu/drm/i915/i915_reg.h | 1 +
drivers/gpu/drm/i915/intel_pm.c | 3 +++
2 files changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ca4f8b9..c850254 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5112,6 +5112,7 @@ enum punit_power_well {
#define GEN6_RC6p_THRESHOLD 0xA0BC
#define GEN6_RC6pp_THRESHOLD 0xA0C0
#define GEN6_PMINTRMSK 0xA168
+#define GEN8_PMINTR_REDIRECT_TO_NON_DISP (1<<31)
#define GEN6_PMISR 0x44020
#define GEN6_PMIMR 0x44024 /* rps_lock */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 0e69c97..270b659 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3114,6 +3114,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev))
mask |= GEN6_PM_RP_UP_EI_EXPIRED;
+ if (IS_GEN8(dev_priv->dev))
+ mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP;
+
return ~mask;
}
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v3] drm/i915: Enable PM Interrupts target via Display Interface.
2014-05-14 15:37 ` [PATCH v3] " deepak.s
@ 2014-05-14 15:47 ` Ville Syrjälä
0 siblings, 0 replies; 26+ messages in thread
From: Ville Syrjälä @ 2014-05-14 15:47 UTC (permalink / raw)
To: deepak.s; +Cc: intel-gfx
On Wed, May 14, 2014 at 09:07:53PM +0530, deepak.s@linux.intel.com wrote:
> From: Deepak S <deepak.s@linux.intel.com>
>
> In BDW, Apart from unmasking up/down threshold interrupts. we need
> to umask bit 32 of PM_INTRMASK to route interrupts to target via Display
> Interface.
>
> v2: Add (1<<31) mask (Ville)
>
> v3: Add Gen check for the mask (ville)
>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_reg.h | 1 +
> drivers/gpu/drm/i915/intel_pm.c | 3 +++
> 2 files changed, 4 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index ca4f8b9..c850254 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -5112,6 +5112,7 @@ enum punit_power_well {
> #define GEN6_RC6p_THRESHOLD 0xA0BC
> #define GEN6_RC6pp_THRESHOLD 0xA0C0
> #define GEN6_PMINTRMSK 0xA168
> +#define GEN8_PMINTR_REDIRECT_TO_NON_DISP (1<<31)
>
> #define GEN6_PMISR 0x44020
> #define GEN6_PMIMR 0x44024 /* rps_lock */
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 0e69c97..270b659 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3114,6 +3114,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
> if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev))
> mask |= GEN6_PM_RP_UP_EI_EXPIRED;
>
> + if (IS_GEN8(dev_priv->dev))
> + mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP;
> +
> return ~mask;
> }
>
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Ville Syrjälä
Intel OTC
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH 03/10] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
2014-05-05 12:47 ` [PATCH 01/10] drm/i915/bdw: Implement a basic PM interrupt handler deepak.s
2014-05-05 12:47 ` [PATCH 02/10] drm/i915: Enable PM Interrupts target via Display Interface deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-09 13:19 ` Mika Kuoppala
2014-05-15 9:57 ` [PATCH v5] " deepak.s
2014-05-05 12:47 ` [PATCH 04/10] drm/i915/chv: Added CHV specific register read and write deepak.s
` (7 subsequent siblings)
10 siblings, 2 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Deepak S <deepak.s@linux.intel.com>
v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
v3: Fix PCBR condition check during CHV RC6 Enable flag set
v4: Fixup PCBR comment msg. (Chris)
Rebase against latest code (Deak)
Fixup Spurious hunk (Ben)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
---
drivers/gpu/drm/i915/i915_reg.h | 2 +
drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
2 files changed, 111 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c850254..b4074fd 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -962,6 +962,8 @@ enum punit_power_well {
#define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
#define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
#define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
+#define VLV_PCBR_ADDR_SHIFT 12
+
#define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
#define EIR 0x020b0
#define EMR 0x020b4
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ebb5c88..f0359b6 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3300,6 +3300,13 @@ static void gen6_disable_rps(struct drm_device *dev)
gen6_disable_rps_interrupts(dev);
}
+static void cherryview_disable_rps(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(GEN6_RC_CONTROL, 0);
+}
+
static void valleyview_disable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3722,6 +3729,33 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
dev_priv->vlv_pctx->stolen->start);
}
+
+/* Check that the pcbr address is not empty. */
+static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
+{
+ unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
+
+ WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
+}
+
+static void cherryview_setup_pctx(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned long pctx_paddr;
+ struct i915_gtt *gtt = &dev_priv->gtt;
+ u32 pcbr;
+ int pctx_size = 32*1024;
+
+ WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+ pcbr = I915_READ(VLV_PCBR);
+ if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
+ pctx_paddr = (dev_priv->mm.stolen_base +
+ (gtt->stolen_size - pctx_size));
+ I915_WRITE(VLV_PCBR, pctx_paddr);
+ }
+}
+
static void valleyview_setup_pctx(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3811,11 +3845,72 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
mutex_unlock(&dev_priv->rps.hw_lock);
}
+static void cherryview_init_gt_powersave(struct drm_device *dev)
+{
+ cherryview_setup_pctx(dev);
+}
+
static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
{
valleyview_cleanup_pctx(dev);
}
+static void cherryview_enable_rps(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_ring_buffer *ring;
+ u32 gtfifodbg, rc6_mode = 0, pcbr;
+ int i;
+
+ WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+ gtfifodbg = I915_READ(GTFIFODBG);
+ if (gtfifodbg) {
+ DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
+ gtfifodbg);
+ I915_WRITE(GTFIFODBG, gtfifodbg);
+ }
+
+ cherryview_check_pctx(dev_priv);
+
+ /* 1a & 1b: Get forcewake during program sequence. Although the driver
+ * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
+ gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+
+ /* 2a: Program RC6 thresholds.*/
+ I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+ I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+ I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+
+ for_each_ring(ring, dev_priv, i)
+ I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+
+ I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+
+ /* allows RC6 residency counter to work */
+ I915_WRITE(VLV_COUNTER_CONTROL,
+ _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+ VLV_MEDIA_RC6_COUNT_EN |
+ VLV_RENDER_RC6_COUNT_EN));
+
+ /* Todo: If BIOS has not configured PCBR
+ * then allocate in BIOS Reserved */
+
+ /* For now we assume BIOS is allocating and populating the PCBR */
+ pcbr = I915_READ(VLV_PCBR);
+
+ DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
+
+ /* 3: Enable RC6 */
+ if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
+ (pcbr >> VLV_PCBR_ADDR_SHIFT))
+ rc6_mode = GEN6_RC_CTL_EI_MODE(1) | VLV_RC_CTL_CTX_RST_PARALLEL;
+
+ I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
+
+ gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+}
+
static void valleyview_enable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4624,13 +4719,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
{
i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ cherryview_init_gt_powersave(dev);
+ else if (IS_VALLEYVIEW(dev))
valleyview_init_gt_powersave(dev);
}
void intel_cleanup_gt_powersave(struct drm_device *dev)
{
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ return;
+ else if (IS_VALLEYVIEW(dev))
valleyview_cleanup_gt_powersave(dev);
}
@@ -4644,11 +4743,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
if (IS_IRONLAKE_M(dev)) {
ironlake_disable_drps(dev);
ironlake_disable_rc6(dev);
- } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+ } else if (INTEL_INFO(dev)->gen >= 6) {
cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
cancel_work_sync(&dev_priv->rps.work);
mutex_lock(&dev_priv->rps.hw_lock);
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ cherryview_disable_rps(dev);
+ else if (IS_VALLEYVIEW(dev))
valleyview_disable_rps(dev);
else
gen6_disable_rps(dev);
@@ -4666,7 +4767,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
mutex_lock(&dev_priv->rps.hw_lock);
- if (IS_VALLEYVIEW(dev)) {
+ if (IS_CHERRYVIEW(dev)) {
+ cherryview_enable_rps(dev);
+ } else if (IS_VALLEYVIEW(dev)) {
valleyview_enable_rps(dev);
} else if (IS_BROADWELL(dev)) {
gen8_enable_rps(dev);
@@ -4691,7 +4794,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
ironlake_enable_rc6(dev);
intel_init_emon(dev);
mutex_unlock(&dev->struct_mutex);
- } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+ } else if (INTEL_INFO(dev)->gen >= 6) {
/*
* PCU communication is slow and this doesn't need to be
* done at any specific time, so do this out of our fast path
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH 03/10] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-05 12:47 ` [PATCH 03/10] drm/i915/chv: Enable Render Standby (RC6) for Cherryview deepak.s
@ 2014-05-09 13:19 ` Mika Kuoppala
2014-05-14 15:47 ` Deepak S
2014-05-15 9:57 ` [PATCH v5] " deepak.s
1 sibling, 1 reply; 26+ messages in thread
From: Mika Kuoppala @ 2014-05-09 13:19 UTC (permalink / raw)
To: deepak.s, intel-gfx; +Cc: fafael.barbalho
Hi Deepak,
deepak.s@linux.intel.com writes:
> From: Deepak S <deepak.s@linux.intel.com>
>
> v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
>
> v3: Fix PCBR condition check during CHV RC6 Enable flag set
>
> v4: Fixup PCBR comment msg. (Chris)
> Rebase against latest code (Deak)
> Fixup Spurious hunk (Ben)
>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
> Acked-by: Ben Widawsky <ben@bwidawsk.net>
> ---
> drivers/gpu/drm/i915/i915_reg.h | 2 +
> drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
> 2 files changed, 111 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index c850254..b4074fd 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -962,6 +962,8 @@ enum punit_power_well {
> #define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
> #define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
> #define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
> +#define VLV_PCBR_ADDR_SHIFT 12
> +
> #define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
> #define EIR 0x020b0
> #define EMR 0x020b4
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index ebb5c88..f0359b6 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3300,6 +3300,13 @@ static void gen6_disable_rps(struct drm_device *dev)
> gen6_disable_rps_interrupts(dev);
> }
>
> +static void cherryview_disable_rps(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> +
> + I915_WRITE(GEN6_RC_CONTROL, 0);
> +}
> +
> static void valleyview_disable_rps(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3722,6 +3729,33 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
> dev_priv->vlv_pctx->stolen->start);
> }
>
> +
> +/* Check that the pcbr address is not empty. */
> +static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
> +{
> + unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
> +
> + WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
> +}
> +
> +static void cherryview_setup_pctx(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + unsigned long pctx_paddr;
> + struct i915_gtt *gtt = &dev_priv->gtt;
> + u32 pcbr;
> + int pctx_size = 32*1024;
> +
> + WARN_ON(!mutex_is_locked(&dev->struct_mutex));
> +
> + pcbr = I915_READ(VLV_PCBR);
> + if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
I admit that address zero locked by bios is prolly in
realms of paranoia. But I would still omit shift here to
get lock bit taken into consideration.
> + pctx_paddr = (dev_priv->mm.stolen_base +
> + (gtt->stolen_size - pctx_size));
> + I915_WRITE(VLV_PCBR, pctx_paddr);
In here tho I would mask the low bits out, just to be on
the safe side. If we get off by one on stolen calculation we end up
writing the lock bit.
I am thinking that we should just sanity check that bios
has set this up and that it seems to be in correct place. If not, spit a
warning and leave rc6 disabled.
The BIOS should have setup everything for us. Why do we need this
PCBR setup?
> + }
> +}
> +
> static void valleyview_setup_pctx(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3811,11 +3845,72 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
> mutex_unlock(&dev_priv->rps.hw_lock);
> }
>
> +static void cherryview_init_gt_powersave(struct drm_device *dev)
> +{
> + cherryview_setup_pctx(dev);
> +}
> +
> static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
> {
> valleyview_cleanup_pctx(dev);
> }
>
> +static void cherryview_enable_rps(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + struct intel_ring_buffer *ring;
> + u32 gtfifodbg, rc6_mode = 0, pcbr;
> + int i;
> +
> + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
> +
> + gtfifodbg = I915_READ(GTFIFODBG);
> + if (gtfifodbg) {
> + DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
> + gtfifodbg);
> + I915_WRITE(GTFIFODBG, gtfifodbg);
> + }
> +
> + cherryview_check_pctx(dev_priv);
> +
> + /* 1a & 1b: Get forcewake during program sequence. Although the driver
> + * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
> + gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
> +
I915_WRITE(GEN6_RC_CONTROL, 0);
> + /* 2a: Program RC6 thresholds.*/
> + I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
> + I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
> + I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
> +
> + for_each_ring(ring, dev_priv, i)
> + I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
> +
I915_WRITE(GEN6_RC_SLEEP, 0);
missing?
> + I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
> +
> + /* allows RC6 residency counter to work */
> + I915_WRITE(VLV_COUNTER_CONTROL,
> + _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
> + VLV_MEDIA_RC6_COUNT_EN |
> + VLV_RENDER_RC6_COUNT_EN));
> +
> + /* Todo: If BIOS has not configured PCBR
> + * then allocate in BIOS Reserved */
> +
> + /* For now we assume BIOS is allocating and populating the PCBR
> */
Both comments do not match with the code.
> + pcbr = I915_READ(VLV_PCBR);
> +
> + DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
> +
> + /* 3: Enable RC6 */
> + if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
> + (pcbr >> VLV_PCBR_ADDR_SHIFT))
> + rc6_mode = GEN6_RC_CTL_EI_MODE(1) | VLV_RC_CTL_CTX_RST_PARALLEL;
^^
Bit 24 is not used with chv.
-Mika
> +
> + I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
> +
> + gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
> +}
> +
> static void valleyview_enable_rps(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -4624,13 +4719,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
> {
> i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
>
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + cherryview_init_gt_powersave(dev);
> + else if (IS_VALLEYVIEW(dev))
> valleyview_init_gt_powersave(dev);
> }
>
> void intel_cleanup_gt_powersave(struct drm_device *dev)
> {
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + return;
> + else if (IS_VALLEYVIEW(dev))
> valleyview_cleanup_gt_powersave(dev);
> }
>
> @@ -4644,11 +4743,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
> if (IS_IRONLAKE_M(dev)) {
> ironlake_disable_drps(dev);
> ironlake_disable_rc6(dev);
> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
> + } else if (INTEL_INFO(dev)->gen >= 6) {
> cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
> cancel_work_sync(&dev_priv->rps.work);
> mutex_lock(&dev_priv->rps.hw_lock);
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + cherryview_disable_rps(dev);
> + else if (IS_VALLEYVIEW(dev))
> valleyview_disable_rps(dev);
> else
> gen6_disable_rps(dev);
> @@ -4666,7 +4767,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
>
> mutex_lock(&dev_priv->rps.hw_lock);
>
> - if (IS_VALLEYVIEW(dev)) {
> + if (IS_CHERRYVIEW(dev)) {
> + cherryview_enable_rps(dev);
> + } else if (IS_VALLEYVIEW(dev)) {
> valleyview_enable_rps(dev);
> } else if (IS_BROADWELL(dev)) {
> gen8_enable_rps(dev);
> @@ -4691,7 +4794,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
> ironlake_enable_rc6(dev);
> intel_init_emon(dev);
> mutex_unlock(&dev->struct_mutex);
> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
> + } else if (INTEL_INFO(dev)->gen >= 6) {
> /*
> * PCU communication is slow and this doesn't need to be
> * done at any specific time, so do this out of our fast path
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 26+ messages in thread* Re: [PATCH 03/10] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-09 13:19 ` Mika Kuoppala
@ 2014-05-14 15:47 ` Deepak S
0 siblings, 0 replies; 26+ messages in thread
From: Deepak S @ 2014-05-14 15:47 UTC (permalink / raw)
To: Mika Kuoppala, intel-gfx
On Friday 09 May 2014 06:49 PM, Mika Kuoppala wrote:
> Hi Deepak,
>
> deepak.s@linux.intel.com writes:
>
>> From: Deepak S <deepak.s@linux.intel.com>
>>
>> v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
>>
>> v3: Fix PCBR condition check during CHV RC6 Enable flag set
>>
>> v4: Fixup PCBR comment msg. (Chris)
>> Rebase against latest code (Deak)
>> Fixup Spurious hunk (Ben)
>>
>> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
>> Acked-by: Ben Widawsky <ben@bwidawsk.net>
>> ---
>> drivers/gpu/drm/i915/i915_reg.h | 2 +
>> drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
>> 2 files changed, 111 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
>> index c850254..b4074fd 100644
>> --- a/drivers/gpu/drm/i915/i915_reg.h
>> +++ b/drivers/gpu/drm/i915/i915_reg.h
>> @@ -962,6 +962,8 @@ enum punit_power_well {
>> #define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
>> #define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
>> #define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
>> +#define VLV_PCBR_ADDR_SHIFT 12
>> +
>> #define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
>> #define EIR 0x020b0
>> #define EMR 0x020b4
>> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
>> index ebb5c88..f0359b6 100644
>> --- a/drivers/gpu/drm/i915/intel_pm.c
>> +++ b/drivers/gpu/drm/i915/intel_pm.c
>> @@ -3300,6 +3300,13 @@ static void gen6_disable_rps(struct drm_device *dev)
>> gen6_disable_rps_interrupts(dev);
>> }
>>
>> +static void cherryview_disable_rps(struct drm_device *dev)
>> +{
>> + struct drm_i915_private *dev_priv = dev->dev_private;
>> +
>> + I915_WRITE(GEN6_RC_CONTROL, 0);
>> +}
>> +
>> static void valleyview_disable_rps(struct drm_device *dev)
>> {
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -3722,6 +3729,33 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
>> dev_priv->vlv_pctx->stolen->start);
>> }
>>
>> +
>> +/* Check that the pcbr address is not empty. */
>> +static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
>> +{
>> + unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
>> +
>> + WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
>> +}
>> +
>> +static void cherryview_setup_pctx(struct drm_device *dev)
>> +{
>> + struct drm_i915_private *dev_priv = dev->dev_private;
>> + unsigned long pctx_paddr;
>> + struct i915_gtt *gtt = &dev_priv->gtt;
>> + u32 pcbr;
>> + int pctx_size = 32*1024;
>> +
>> + WARN_ON(!mutex_is_locked(&dev->struct_mutex));
>> +
>> + pcbr = I915_READ(VLV_PCBR);
>> + if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
> I admit that address zero locked by bios is prolly in
> realms of paranoia. But I would still omit shift here to
> get lock bit taken into consideration.
Agreed, But verifying address is more important right? We are more concerned with address than lock bit right?
>> + pctx_paddr = (dev_priv->mm.stolen_base +
>> + (gtt->stolen_size - pctx_size));
>> + I915_WRITE(VLV_PCBR, pctx_paddr);
> In here tho I would mask the low bits out, just to be on
> the safe side. If we get off by one on stolen calculation we end up
> writing the lock bit.
I will add the mask bit
> I am thinking that we should just sanity check that bios
> has set this up and that it seems to be in correct place. If not, spit a
> warning and leave rc6 disabled.
>
> The BIOS should have setup everything for us. Why do we need this
> PCBR setup?
>
Nice Point, We need to make sure BIOS is setting up the PCBR properly.
>> + }
>> +}
>> +
>> static void valleyview_setup_pctx(struct drm_device *dev)
>> {
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -3811,11 +3845,72 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
>> mutex_unlock(&dev_priv->rps.hw_lock);
>> }
>>
>> +static void cherryview_init_gt_powersave(struct drm_device *dev)
>> +{
>> + cherryview_setup_pctx(dev);
>> +}
>> +
>> static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
>> {
>> valleyview_cleanup_pctx(dev);
>> }
>>
>> +static void cherryview_enable_rps(struct drm_device *dev)
>> +{
>> + struct drm_i915_private *dev_priv = dev->dev_private;
>> + struct intel_ring_buffer *ring;
>> + u32 gtfifodbg, rc6_mode = 0, pcbr;
>> + int i;
>> +
>> + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
>> +
>> + gtfifodbg = I915_READ(GTFIFODBG);
>> + if (gtfifodbg) {
>> + DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
>> + gtfifodbg);
>> + I915_WRITE(GTFIFODBG, gtfifodbg);
>> + }
>> +
>> + cherryview_check_pctx(dev_priv);
>> +
>> + /* 1a & 1b: Get forcewake during program sequence. Although the driver
>> + * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
>> + gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
>> +
> I915_WRITE(GEN6_RC_CONTROL, 0);
>
>> + /* 2a: Program RC6 thresholds.*/
>> + I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
>> + I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
>> + I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
>> +
>> + for_each_ring(ring, dev_priv, i)
>> + I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
>> +
> I915_WRITE(GEN6_RC_SLEEP, 0);
> missing?
This might not be need. let me check back. As the default is already 0. I will check the spec and add if needed.
>> + I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
>> +
>> + /* allows RC6 residency counter to work */
>> + I915_WRITE(VLV_COUNTER_CONTROL,
>> + _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
>> + VLV_MEDIA_RC6_COUNT_EN |
>> + VLV_RENDER_RC6_COUNT_EN));
>> +
>> + /* Todo: If BIOS has not configured PCBR
>> + * then allocate in BIOS Reserved */
>> +
>> + /* For now we assume BIOS is allocating and populating the PCBR
>> */
> Both comments do not match with the code.
I will address the comments
>> + pcbr = I915_READ(VLV_PCBR);
>> +
>> + DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
>> +
>> + /* 3: Enable RC6 */
>> + if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
>> + (pcbr >> VLV_PCBR_ADDR_SHIFT))
>> + rc6_mode = GEN6_RC_CTL_EI_MODE(1) | VLV_RC_CTL_CTX_RST_PARALLEL;
> ^^
> Bit 24 is not used with chv.
>
> -Mika
I will remove this :) Missed while addressing previous comments
>> +
>> + I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
>> +
>> + gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
>> +}
>> +
>> static void valleyview_enable_rps(struct drm_device *dev)
>> {
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -4624,13 +4719,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
>> {
>> i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
>>
>> - if (IS_VALLEYVIEW(dev))
>> + if (IS_CHERRYVIEW(dev))
>> + cherryview_init_gt_powersave(dev);
>> + else if (IS_VALLEYVIEW(dev))
>> valleyview_init_gt_powersave(dev);
>> }
>>
>> void intel_cleanup_gt_powersave(struct drm_device *dev)
>> {
>> - if (IS_VALLEYVIEW(dev))
>> + if (IS_CHERRYVIEW(dev))
>> + return;
>> + else if (IS_VALLEYVIEW(dev))
>> valleyview_cleanup_gt_powersave(dev);
>> }
>>
>> @@ -4644,11 +4743,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
>> if (IS_IRONLAKE_M(dev)) {
>> ironlake_disable_drps(dev);
>> ironlake_disable_rc6(dev);
>> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
>> + } else if (INTEL_INFO(dev)->gen >= 6) {
>> cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
>> cancel_work_sync(&dev_priv->rps.work);
>> mutex_lock(&dev_priv->rps.hw_lock);
>> - if (IS_VALLEYVIEW(dev))
>> + if (IS_CHERRYVIEW(dev))
>> + cherryview_disable_rps(dev);
>> + else if (IS_VALLEYVIEW(dev))
>> valleyview_disable_rps(dev);
>> else
>> gen6_disable_rps(dev);
>> @@ -4666,7 +4767,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
>>
>> mutex_lock(&dev_priv->rps.hw_lock);
>>
>> - if (IS_VALLEYVIEW(dev)) {
>> + if (IS_CHERRYVIEW(dev)) {
>> + cherryview_enable_rps(dev);
>> + } else if (IS_VALLEYVIEW(dev)) {
>> valleyview_enable_rps(dev);
>> } else if (IS_BROADWELL(dev)) {
>> gen8_enable_rps(dev);
>> @@ -4691,7 +4794,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
>> ironlake_enable_rc6(dev);
>> intel_init_emon(dev);
>> mutex_unlock(&dev->struct_mutex);
>> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
>> + } else if (INTEL_INFO(dev)->gen >= 6) {
>> /*
>> * PCU communication is slow and this doesn't need to be
>> * done at any specific time, so do this out of our fast path
>> --
>> 1.9.1
>>
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx@lists.freedesktop.org
>> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Thanks for the review.
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH v5] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-05 12:47 ` [PATCH 03/10] drm/i915/chv: Enable Render Standby (RC6) for Cherryview deepak.s
2014-05-09 13:19 ` Mika Kuoppala
@ 2014-05-15 9:57 ` deepak.s
2014-05-15 10:00 ` Deepak S
2014-05-15 10:16 ` Mika Kuoppala
1 sibling, 2 replies; 26+ messages in thread
From: deepak.s @ 2014-05-15 9:57 UTC (permalink / raw)
To: intel-gfx
From: Deepak S <deepak.s@linux.intel.com>
v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
v3: Fix PCBR condition check during CHV RC6 Enable flag set
v4: Fixup PCBR comment msg. (Chris)
Rebase against latest code (Deak)
Fixup Spurious hunk (Ben)
v5: Fix PCBR and commentis msg (mika)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
---
drivers/gpu/drm/i915/i915_reg.h | 2 +
drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
2 files changed, 111 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c850254..b4074fd 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -962,6 +962,8 @@ enum punit_power_well {
#define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
#define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
#define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
+#define VLV_PCBR_ADDR_SHIFT 12
+
#define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
#define EIR 0x020b0
#define EMR 0x020b4
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 270b659..7a6e50e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3301,6 +3301,13 @@ static void gen6_disable_rps(struct drm_device *dev)
gen6_disable_rps_interrupts(dev);
}
+static void cherryview_disable_rps(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(GEN6_RC_CONTROL, 0);
+}
+
static void valleyview_disable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3723,6 +3730,35 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
dev_priv->vlv_pctx->stolen->start);
}
+
+/* Check that the pcbr address is not empty. */
+static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
+{
+ unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
+
+ WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
+}
+
+static void cherryview_setup_pctx(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned long pctx_paddr, paddr;
+ struct i915_gtt *gtt = &dev_priv->gtt;
+ u32 pcbr;
+ int pctx_size = 32*1024;
+
+ WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+ pcbr = I915_READ(VLV_PCBR);
+ if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
+ paddr = (dev_priv->mm.stolen_base +
+ (gtt->stolen_size - pctx_size));
+
+ pctx_paddr = (paddr & (~4095));
+ I915_WRITE(VLV_PCBR, pctx_paddr);
+ }
+}
+
static void valleyview_setup_pctx(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3812,11 +3848,70 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
mutex_unlock(&dev_priv->rps.hw_lock);
}
+static void cherryview_init_gt_powersave(struct drm_device *dev)
+{
+ cherryview_setup_pctx(dev);
+}
+
static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
{
valleyview_cleanup_pctx(dev);
}
+static void cherryview_enable_rps(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_ring_buffer *ring;
+ u32 gtfifodbg, rc6_mode = 0, pcbr;
+ int i;
+
+ WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+ gtfifodbg = I915_READ(GTFIFODBG);
+ if (gtfifodbg) {
+ DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
+ gtfifodbg);
+ I915_WRITE(GTFIFODBG, gtfifodbg);
+ }
+
+ cherryview_check_pctx(dev_priv);
+
+ /* 1a & 1b: Get forcewake during program sequence. Although the driver
+ * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
+ gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+
+ /* 2a: Program RC6 thresholds.*/
+ I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+ I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+ I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+
+ for_each_ring(ring, dev_priv, i)
+ I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+ I915_WRITE(GEN6_RC_SLEEP, 0);
+
+ I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+
+ /* allows RC6 residency counter to work */
+ I915_WRITE(VLV_COUNTER_CONTROL,
+ _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+ VLV_MEDIA_RC6_COUNT_EN |
+ VLV_RENDER_RC6_COUNT_EN));
+
+ /* For now we assume BIOS is allocating and populating the PCBR */
+ pcbr = I915_READ(VLV_PCBR);
+
+ DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
+
+ /* 3: Enable RC6 */
+ if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
+ (pcbr >> VLV_PCBR_ADDR_SHIFT))
+ rc6_mode = GEN6_RC_CTL_EI_MODE(1);
+
+ I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
+
+ gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+}
+
static void valleyview_enable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4625,13 +4720,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
{
i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ cherryview_init_gt_powersave(dev);
+ else if (IS_VALLEYVIEW(dev))
valleyview_init_gt_powersave(dev);
}
void intel_cleanup_gt_powersave(struct drm_device *dev)
{
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ return;
+ else if (IS_VALLEYVIEW(dev))
valleyview_cleanup_gt_powersave(dev);
}
@@ -4645,11 +4744,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
if (IS_IRONLAKE_M(dev)) {
ironlake_disable_drps(dev);
ironlake_disable_rc6(dev);
- } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+ } else if (INTEL_INFO(dev)->gen >= 6) {
cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
cancel_work_sync(&dev_priv->rps.work);
mutex_lock(&dev_priv->rps.hw_lock);
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ cherryview_disable_rps(dev);
+ else if (IS_VALLEYVIEW(dev))
valleyview_disable_rps(dev);
else
gen6_disable_rps(dev);
@@ -4667,7 +4768,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
mutex_lock(&dev_priv->rps.hw_lock);
- if (IS_VALLEYVIEW(dev)) {
+ if (IS_CHERRYVIEW(dev)) {
+ cherryview_enable_rps(dev);
+ } else if (IS_VALLEYVIEW(dev)) {
valleyview_enable_rps(dev);
} else if (IS_BROADWELL(dev)) {
gen8_enable_rps(dev);
@@ -4692,7 +4795,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
ironlake_enable_rc6(dev);
intel_init_emon(dev);
mutex_unlock(&dev->struct_mutex);
- } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+ } else if (INTEL_INFO(dev)->gen >= 6) {
/*
* PCU communication is slow and this doesn't need to be
* done at any specific time, so do this out of our fast path
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH v5] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-15 9:57 ` [PATCH v5] " deepak.s
@ 2014-05-15 10:00 ` Deepak S
2014-05-15 10:16 ` Mika Kuoppala
1 sibling, 0 replies; 26+ messages in thread
From: Deepak S @ 2014-05-15 10:00 UTC (permalink / raw)
To: intel-gfx, Mika Kuoppala
Hi Mika,
On the PCBR check comment. I will create a separate patch to address both VLV and CHV
Thanks
Deepak
On Thursday 15 May 2014 03:27 PM, deepak.s@linux.intel.com wrote:
> From: Deepak S <deepak.s@linux.intel.com>
>
> v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
>
> v3: Fix PCBR condition check during CHV RC6 Enable flag set
>
> v4: Fixup PCBR comment msg. (Chris)
> Rebase against latest code (Deak)
> Fixup Spurious hunk (Ben)
>
> v5: Fix PCBR and commentis msg (mika)
>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
> Acked-by: Ben Widawsky <ben@bwidawsk.net>
> ---
> drivers/gpu/drm/i915/i915_reg.h | 2 +
> drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
> 2 files changed, 111 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index c850254..b4074fd 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -962,6 +962,8 @@ enum punit_power_well {
> #define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
> #define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
> #define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
> +#define VLV_PCBR_ADDR_SHIFT 12
> +
> #define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
> #define EIR 0x020b0
> #define EMR 0x020b4
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 270b659..7a6e50e 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3301,6 +3301,13 @@ static void gen6_disable_rps(struct drm_device *dev)
> gen6_disable_rps_interrupts(dev);
> }
>
> +static void cherryview_disable_rps(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> +
> + I915_WRITE(GEN6_RC_CONTROL, 0);
> +}
> +
> static void valleyview_disable_rps(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3723,6 +3730,35 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
> dev_priv->vlv_pctx->stolen->start);
> }
>
> +
> +/* Check that the pcbr address is not empty. */
> +static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
> +{
> + unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
> +
> + WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
> +}
> +
> +static void cherryview_setup_pctx(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + unsigned long pctx_paddr, paddr;
> + struct i915_gtt *gtt = &dev_priv->gtt;
> + u32 pcbr;
> + int pctx_size = 32*1024;
> +
> + WARN_ON(!mutex_is_locked(&dev->struct_mutex));
> +
> + pcbr = I915_READ(VLV_PCBR);
> + if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
> + paddr = (dev_priv->mm.stolen_base +
> + (gtt->stolen_size - pctx_size));
> +
> + pctx_paddr = (paddr & (~4095));
> + I915_WRITE(VLV_PCBR, pctx_paddr);
> + }
> +}
> +
> static void valleyview_setup_pctx(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3812,11 +3848,70 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
> mutex_unlock(&dev_priv->rps.hw_lock);
> }
>
> +static void cherryview_init_gt_powersave(struct drm_device *dev)
> +{
> + cherryview_setup_pctx(dev);
> +}
> +
> static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
> {
> valleyview_cleanup_pctx(dev);
> }
>
> +static void cherryview_enable_rps(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + struct intel_ring_buffer *ring;
> + u32 gtfifodbg, rc6_mode = 0, pcbr;
> + int i;
> +
> + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
> +
> + gtfifodbg = I915_READ(GTFIFODBG);
> + if (gtfifodbg) {
> + DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
> + gtfifodbg);
> + I915_WRITE(GTFIFODBG, gtfifodbg);
> + }
> +
> + cherryview_check_pctx(dev_priv);
> +
> + /* 1a & 1b: Get forcewake during program sequence. Although the driver
> + * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
> + gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
> +
> + /* 2a: Program RC6 thresholds.*/
> + I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
> + I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
> + I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
> +
> + for_each_ring(ring, dev_priv, i)
> + I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
> + I915_WRITE(GEN6_RC_SLEEP, 0);
> +
> + I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
> +
> + /* allows RC6 residency counter to work */
> + I915_WRITE(VLV_COUNTER_CONTROL,
> + _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
> + VLV_MEDIA_RC6_COUNT_EN |
> + VLV_RENDER_RC6_COUNT_EN));
> +
> + /* For now we assume BIOS is allocating and populating the PCBR */
> + pcbr = I915_READ(VLV_PCBR);
> +
> + DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
> +
> + /* 3: Enable RC6 */
> + if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
> + (pcbr >> VLV_PCBR_ADDR_SHIFT))
> + rc6_mode = GEN6_RC_CTL_EI_MODE(1);
> +
> + I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
> +
> + gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
> +}
> +
> static void valleyview_enable_rps(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -4625,13 +4720,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
> {
> i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
>
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + cherryview_init_gt_powersave(dev);
> + else if (IS_VALLEYVIEW(dev))
> valleyview_init_gt_powersave(dev);
> }
>
> void intel_cleanup_gt_powersave(struct drm_device *dev)
> {
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + return;
> + else if (IS_VALLEYVIEW(dev))
> valleyview_cleanup_gt_powersave(dev);
> }
>
> @@ -4645,11 +4744,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
> if (IS_IRONLAKE_M(dev)) {
> ironlake_disable_drps(dev);
> ironlake_disable_rc6(dev);
> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
> + } else if (INTEL_INFO(dev)->gen >= 6) {
> cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
> cancel_work_sync(&dev_priv->rps.work);
> mutex_lock(&dev_priv->rps.hw_lock);
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + cherryview_disable_rps(dev);
> + else if (IS_VALLEYVIEW(dev))
> valleyview_disable_rps(dev);
> else
> gen6_disable_rps(dev);
> @@ -4667,7 +4768,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
>
> mutex_lock(&dev_priv->rps.hw_lock);
>
> - if (IS_VALLEYVIEW(dev)) {
> + if (IS_CHERRYVIEW(dev)) {
> + cherryview_enable_rps(dev);
> + } else if (IS_VALLEYVIEW(dev)) {
> valleyview_enable_rps(dev);
> } else if (IS_BROADWELL(dev)) {
> gen8_enable_rps(dev);
> @@ -4692,7 +4795,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
> ironlake_enable_rc6(dev);
> intel_init_emon(dev);
> mutex_unlock(&dev->struct_mutex);
> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
> + } else if (INTEL_INFO(dev)->gen >= 6) {
> /*
> * PCU communication is slow and this doesn't need to be
> * done at any specific time, so do this out of our fast path
^ permalink raw reply [flat|nested] 26+ messages in thread* Re: [PATCH v5] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-15 9:57 ` [PATCH v5] " deepak.s
2014-05-15 10:00 ` Deepak S
@ 2014-05-15 10:16 ` Mika Kuoppala
2014-05-15 10:22 ` Mika Kuoppala
2014-05-15 12:38 ` [PATCH v5 1/8] " deepak.s
1 sibling, 2 replies; 26+ messages in thread
From: Mika Kuoppala @ 2014-05-15 10:16 UTC (permalink / raw)
To: deepak.s, intel-gfx
deepak.s@linux.intel.com writes:
> From: Deepak S <deepak.s@linux.intel.com>
>
> v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
>
> v3: Fix PCBR condition check during CHV RC6 Enable flag set
>
> v4: Fixup PCBR comment msg. (Chris)
> Rebase against latest code (Deak)
> Fixup Spurious hunk (Ben)
>
> v5: Fix PCBR and commentis msg (mika)
>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
> Acked-by: Ben Widawsky <ben@bwidawsk.net>
> ---
> drivers/gpu/drm/i915/i915_reg.h | 2 +
> drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
> 2 files changed, 111 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index c850254..b4074fd 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -962,6 +962,8 @@ enum punit_power_well {
> #define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
> #define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
> #define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
> +#define VLV_PCBR_ADDR_SHIFT 12
> +
> #define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
> #define EIR 0x020b0
> #define EMR 0x020b4
> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
> index 270b659..7a6e50e 100644
> --- a/drivers/gpu/drm/i915/intel_pm.c
> +++ b/drivers/gpu/drm/i915/intel_pm.c
> @@ -3301,6 +3301,13 @@ static void gen6_disable_rps(struct drm_device *dev)
> gen6_disable_rps_interrupts(dev);
> }
>
> +static void cherryview_disable_rps(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> +
> + I915_WRITE(GEN6_RC_CONTROL, 0);
> +}
> +
> static void valleyview_disable_rps(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3723,6 +3730,35 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
> dev_priv->vlv_pctx->stolen->start);
> }
>
> +
> +/* Check that the pcbr address is not empty. */
> +static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
> +{
> + unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
> +
> + WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
> +}
> +
> +static void cherryview_setup_pctx(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + unsigned long pctx_paddr, paddr;
> + struct i915_gtt *gtt = &dev_priv->gtt;
> + u32 pcbr;
> + int pctx_size = 32*1024;
> +
> + WARN_ON(!mutex_is_locked(&dev->struct_mutex));
> +
> + pcbr = I915_READ(VLV_PCBR);
> + if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
> + paddr = (dev_priv->mm.stolen_base +
> + (gtt->stolen_size - pctx_size));
> +
> + pctx_paddr = (paddr & (~4095));
> + I915_WRITE(VLV_PCBR, pctx_paddr);
> + }
> +}
> +
> static void valleyview_setup_pctx(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -3812,11 +3848,70 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
> mutex_unlock(&dev_priv->rps.hw_lock);
> }
>
> +static void cherryview_init_gt_powersave(struct drm_device *dev)
> +{
> + cherryview_setup_pctx(dev);
> +}
> +
> static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
> {
> valleyview_cleanup_pctx(dev);
> }
>
> +static void cherryview_enable_rps(struct drm_device *dev)
> +{
> + struct drm_i915_private *dev_priv = dev->dev_private;
> + struct intel_ring_buffer *ring;
> + u32 gtfifodbg, rc6_mode = 0, pcbr;
> + int i;
> +
> + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
> +
> + gtfifodbg = I915_READ(GTFIFODBG);
> + if (gtfifodbg) {
> + DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
> + gtfifodbg);
> + I915_WRITE(GTFIFODBG, gtfifodbg);
> + }
> +
> + cherryview_check_pctx(dev_priv);
> +
> + /* 1a & 1b: Get forcewake during program sequence. Although the driver
> + * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
> + gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
You are starting to configure rc6 with the possibility that bios
has already enabled it.
I am still convinced there should be
+ I915_WRITE(GEN6_RC_CONTROL, 0);
in here.
-Mika
> + /* 2a: Program RC6 thresholds.*/
> + I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
> + I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
> + I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
> +
> + for_each_ring(ring, dev_priv, i)
> + I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
> + I915_WRITE(GEN6_RC_SLEEP, 0);
> +
> + I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
> +
> + /* allows RC6 residency counter to work */
> + I915_WRITE(VLV_COUNTER_CONTROL,
> + _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
> + VLV_MEDIA_RC6_COUNT_EN |
> + VLV_RENDER_RC6_COUNT_EN));
> +
> + /* For now we assume BIOS is allocating and populating the PCBR */
> + pcbr = I915_READ(VLV_PCBR);
> +
> + DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
> +
> + /* 3: Enable RC6 */
> + if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
> + (pcbr >> VLV_PCBR_ADDR_SHIFT))
> + rc6_mode = GEN6_RC_CTL_EI_MODE(1);
> +
> + I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
> +
> + gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
> +}
> +
> static void valleyview_enable_rps(struct drm_device *dev)
> {
> struct drm_i915_private *dev_priv = dev->dev_private;
> @@ -4625,13 +4720,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
> {
> i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
>
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + cherryview_init_gt_powersave(dev);
> + else if (IS_VALLEYVIEW(dev))
> valleyview_init_gt_powersave(dev);
> }
>
> void intel_cleanup_gt_powersave(struct drm_device *dev)
> {
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + return;
> + else if (IS_VALLEYVIEW(dev))
> valleyview_cleanup_gt_powersave(dev);
> }
>
> @@ -4645,11 +4744,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
> if (IS_IRONLAKE_M(dev)) {
> ironlake_disable_drps(dev);
> ironlake_disable_rc6(dev);
> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
> + } else if (INTEL_INFO(dev)->gen >= 6) {
> cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
> cancel_work_sync(&dev_priv->rps.work);
> mutex_lock(&dev_priv->rps.hw_lock);
> - if (IS_VALLEYVIEW(dev))
> + if (IS_CHERRYVIEW(dev))
> + cherryview_disable_rps(dev);
> + else if (IS_VALLEYVIEW(dev))
> valleyview_disable_rps(dev);
> else
> gen6_disable_rps(dev);
> @@ -4667,7 +4768,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
>
> mutex_lock(&dev_priv->rps.hw_lock);
>
> - if (IS_VALLEYVIEW(dev)) {
> + if (IS_CHERRYVIEW(dev)) {
> + cherryview_enable_rps(dev);
> + } else if (IS_VALLEYVIEW(dev)) {
> valleyview_enable_rps(dev);
> } else if (IS_BROADWELL(dev)) {
> gen8_enable_rps(dev);
> @@ -4692,7 +4795,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
> ironlake_enable_rc6(dev);
> intel_init_emon(dev);
> mutex_unlock(&dev->struct_mutex);
> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
> + } else if (INTEL_INFO(dev)->gen >= 6) {
> /*
> * PCU communication is slow and this doesn't need to be
> * done at any specific time, so do this out of our fast path
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 26+ messages in thread* Re: [PATCH v5] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-15 10:16 ` Mika Kuoppala
@ 2014-05-15 10:22 ` Mika Kuoppala
2014-05-15 12:38 ` [PATCH v5 1/8] " deepak.s
1 sibling, 0 replies; 26+ messages in thread
From: Mika Kuoppala @ 2014-05-15 10:22 UTC (permalink / raw)
To: deepak.s, intel-gfx
Mika Kuoppala <mika.kuoppala@linux.intel.com> writes:
> deepak.s@linux.intel.com writes:
>
>> From: Deepak S <deepak.s@linux.intel.com>
>>
>> v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
>>
>> v3: Fix PCBR condition check during CHV RC6 Enable flag set
>>
>> v4: Fixup PCBR comment msg. (Chris)
>> Rebase against latest code (Deak)
>> Fixup Spurious hunk (Ben)
>>
>> v5: Fix PCBR and commentis msg (mika)
>>
>> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
>> Acked-by: Ben Widawsky <ben@bwidawsk.net>
>> ---
>> drivers/gpu/drm/i915/i915_reg.h | 2 +
>> drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
>> 2 files changed, 111 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
>> index c850254..b4074fd 100644
>> --- a/drivers/gpu/drm/i915/i915_reg.h
>> +++ b/drivers/gpu/drm/i915/i915_reg.h
>> @@ -962,6 +962,8 @@ enum punit_power_well {
>> #define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
>> #define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
>> #define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
>> +#define VLV_PCBR_ADDR_SHIFT 12
>> +
>> #define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
>> #define EIR 0x020b0
>> #define EMR 0x020b4
>> diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
>> index 270b659..7a6e50e 100644
>> --- a/drivers/gpu/drm/i915/intel_pm.c
>> +++ b/drivers/gpu/drm/i915/intel_pm.c
>> @@ -3301,6 +3301,13 @@ static void gen6_disable_rps(struct drm_device *dev)
>> gen6_disable_rps_interrupts(dev);
>> }
>>
>> +static void cherryview_disable_rps(struct drm_device *dev)
>> +{
>> + struct drm_i915_private *dev_priv = dev->dev_private;
>> +
>> + I915_WRITE(GEN6_RC_CONTROL, 0);
>> +}
>> +
>> static void valleyview_disable_rps(struct drm_device *dev)
>> {
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -3723,6 +3730,35 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
>> dev_priv->vlv_pctx->stolen->start);
>> }
>>
>> +
>> +/* Check that the pcbr address is not empty. */
>> +static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
>> +{
>> + unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
>> +
>> + WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
>> +}
>> +
>> +static void cherryview_setup_pctx(struct drm_device *dev)
>> +{
>> + struct drm_i915_private *dev_priv = dev->dev_private;
>> + unsigned long pctx_paddr, paddr;
>> + struct i915_gtt *gtt = &dev_priv->gtt;
>> + u32 pcbr;
>> + int pctx_size = 32*1024;
>> +
>> + WARN_ON(!mutex_is_locked(&dev->struct_mutex));
>> +
>> + pcbr = I915_READ(VLV_PCBR);
>> + if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
>> + paddr = (dev_priv->mm.stolen_base +
>> + (gtt->stolen_size - pctx_size));
>> +
>> + pctx_paddr = (paddr & (~4095));
>> + I915_WRITE(VLV_PCBR, pctx_paddr);
>> + }
>> +}
>> +
>> static void valleyview_setup_pctx(struct drm_device *dev)
>> {
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -3812,11 +3848,70 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
>> mutex_unlock(&dev_priv->rps.hw_lock);
>> }
>>
>> +static void cherryview_init_gt_powersave(struct drm_device *dev)
>> +{
>> + cherryview_setup_pctx(dev);
>> +}
>> +
>> static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
>> {
>> valleyview_cleanup_pctx(dev);
>> }
>>
>> +static void cherryview_enable_rps(struct drm_device *dev)
>> +{
>> + struct drm_i915_private *dev_priv = dev->dev_private;
>> + struct intel_ring_buffer *ring;
>> + u32 gtfifodbg, rc6_mode = 0, pcbr;
>> + int i;
>> +
>> + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
>> +
>> + gtfifodbg = I915_READ(GTFIFODBG);
>> + if (gtfifodbg) {
>> + DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
>> + gtfifodbg);
>> + I915_WRITE(GTFIFODBG, gtfifodbg);
>> + }
>> +
>> + cherryview_check_pctx(dev_priv);
>> +
>> + /* 1a & 1b: Get forcewake during program sequence. Although the driver
>> + * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
>> + gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
>
> You are starting to configure rc6 with the possibility that bios
> has already enabled it.
>
> I am still convinced there should be
>
> + I915_WRITE(GEN6_RC_CONTROL, 0);
>
> in here.
I forgot to mention that with that addition made,
you can add
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
> -Mika
>
>> + /* 2a: Program RC6 thresholds.*/
>> + I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
>> + I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
>> + I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
>> +
>> + for_each_ring(ring, dev_priv, i)
>> + I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
>> + I915_WRITE(GEN6_RC_SLEEP, 0);
>> +
>> + I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
>> +
>> + /* allows RC6 residency counter to work */
>> + I915_WRITE(VLV_COUNTER_CONTROL,
>> + _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
>> + VLV_MEDIA_RC6_COUNT_EN |
>> + VLV_RENDER_RC6_COUNT_EN));
>> +
>> + /* For now we assume BIOS is allocating and populating the PCBR */
>> + pcbr = I915_READ(VLV_PCBR);
>> +
>> + DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
>> +
>> + /* 3: Enable RC6 */
>> + if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
>> + (pcbr >> VLV_PCBR_ADDR_SHIFT))
>> + rc6_mode = GEN6_RC_CTL_EI_MODE(1);
>> +
>> + I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
>> +
>> + gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
>> +}
>> +
>> static void valleyview_enable_rps(struct drm_device *dev)
>> {
>> struct drm_i915_private *dev_priv = dev->dev_private;
>> @@ -4625,13 +4720,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
>> {
>> i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
>>
>> - if (IS_VALLEYVIEW(dev))
>> + if (IS_CHERRYVIEW(dev))
>> + cherryview_init_gt_powersave(dev);
>> + else if (IS_VALLEYVIEW(dev))
>> valleyview_init_gt_powersave(dev);
>> }
>>
>> void intel_cleanup_gt_powersave(struct drm_device *dev)
>> {
>> - if (IS_VALLEYVIEW(dev))
>> + if (IS_CHERRYVIEW(dev))
>> + return;
>> + else if (IS_VALLEYVIEW(dev))
>> valleyview_cleanup_gt_powersave(dev);
>> }
>>
>> @@ -4645,11 +4744,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
>> if (IS_IRONLAKE_M(dev)) {
>> ironlake_disable_drps(dev);
>> ironlake_disable_rc6(dev);
>> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
>> + } else if (INTEL_INFO(dev)->gen >= 6) {
>> cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
>> cancel_work_sync(&dev_priv->rps.work);
>> mutex_lock(&dev_priv->rps.hw_lock);
>> - if (IS_VALLEYVIEW(dev))
>> + if (IS_CHERRYVIEW(dev))
>> + cherryview_disable_rps(dev);
>> + else if (IS_VALLEYVIEW(dev))
>> valleyview_disable_rps(dev);
>> else
>> gen6_disable_rps(dev);
>> @@ -4667,7 +4768,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
>>
>> mutex_lock(&dev_priv->rps.hw_lock);
>>
>> - if (IS_VALLEYVIEW(dev)) {
>> + if (IS_CHERRYVIEW(dev)) {
>> + cherryview_enable_rps(dev);
>> + } else if (IS_VALLEYVIEW(dev)) {
>> valleyview_enable_rps(dev);
>> } else if (IS_BROADWELL(dev)) {
>> gen8_enable_rps(dev);
>> @@ -4692,7 +4795,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
>> ironlake_enable_rc6(dev);
>> intel_init_emon(dev);
>> mutex_unlock(&dev->struct_mutex);
>> - } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
>> + } else if (INTEL_INFO(dev)->gen >= 6) {
>> /*
>> * PCU communication is slow and this doesn't need to be
>> * done at any specific time, so do this out of our fast path
>> --
>> 1.9.1
>>
>> _______________________________________________
>> Intel-gfx mailing list
>> Intel-gfx@lists.freedesktop.org
>> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 26+ messages in thread* [PATCH v5 1/8] drm/i915/chv: Enable Render Standby (RC6) for Cherryview
2014-05-15 10:16 ` Mika Kuoppala
2014-05-15 10:22 ` Mika Kuoppala
@ 2014-05-15 12:38 ` deepak.s
1 sibling, 0 replies; 26+ messages in thread
From: deepak.s @ 2014-05-15 12:38 UTC (permalink / raw)
To: intel-gfx
From: Deepak S <deepak.s@linux.intel.com>
v2: Configure PCBR if BIOS fails allocate pcbr (deepak)
v3: Fix PCBR condition check during CHV RC6 Enable flag set
v4: Fixup PCBR comment msg. (Chris)
Rebase against latest code (Deak)
Fixup Spurious hunk (Ben)
v5: Fix PCBR and commentis msg (mika)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
drivers/gpu/drm/i915/i915_reg.h | 2 +
drivers/gpu/drm/i915/intel_pm.c | 115 +++++++++++++++++++++++++++++++++++++---
2 files changed, 111 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c850254..b4074fd 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -962,6 +962,8 @@ enum punit_power_well {
#define VLV_IMR (VLV_DISPLAY_BASE + 0x20a8)
#define VLV_ISR (VLV_DISPLAY_BASE + 0x20ac)
#define VLV_PCBR (VLV_DISPLAY_BASE + 0x2120)
+#define VLV_PCBR_ADDR_SHIFT 12
+
#define DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
#define EIR 0x020b0
#define EMR 0x020b4
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 270b659..7a6e50e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3301,6 +3301,13 @@ static void gen6_disable_rps(struct drm_device *dev)
gen6_disable_rps_interrupts(dev);
}
+static void cherryview_disable_rps(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(GEN6_RC_CONTROL, 0);
+}
+
static void valleyview_disable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3723,6 +3730,35 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
dev_priv->vlv_pctx->stolen->start);
}
+
+/* Check that the pcbr address is not empty. */
+static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
+{
+ unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
+
+ WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
+}
+
+static void cherryview_setup_pctx(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned long pctx_paddr, paddr;
+ struct i915_gtt *gtt = &dev_priv->gtt;
+ u32 pcbr;
+ int pctx_size = 32*1024;
+
+ WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+ pcbr = I915_READ(VLV_PCBR);
+ if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
+ paddr = (dev_priv->mm.stolen_base +
+ (gtt->stolen_size - pctx_size));
+
+ pctx_paddr = (paddr & (~4095));
+ I915_WRITE(VLV_PCBR, pctx_paddr);
+ }
+}
+
static void valleyview_setup_pctx(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3812,11 +3848,70 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
mutex_unlock(&dev_priv->rps.hw_lock);
}
+static void cherryview_init_gt_powersave(struct drm_device *dev)
+{
+ cherryview_setup_pctx(dev);
+}
+
static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
{
valleyview_cleanup_pctx(dev);
}
+static void cherryview_enable_rps(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_ring_buffer *ring;
+ u32 gtfifodbg, rc6_mode = 0, pcbr;
+ int i;
+
+ WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+ gtfifodbg = I915_READ(GTFIFODBG);
+ if (gtfifodbg) {
+ DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
+ gtfifodbg);
+ I915_WRITE(GTFIFODBG, gtfifodbg);
+ }
+
+ cherryview_check_pctx(dev_priv);
+
+ /* 1a & 1b: Get forcewake during program sequence. Although the driver
+ * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
+ gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+
+ /* 2a: Program RC6 thresholds.*/
+ I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+ I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+ I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+
+ for_each_ring(ring, dev_priv, i)
+ I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+ I915_WRITE(GEN6_RC_SLEEP, 0);
+
+ I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+
+ /* allows RC6 residency counter to work */
+ I915_WRITE(VLV_COUNTER_CONTROL,
+ _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+ VLV_MEDIA_RC6_COUNT_EN |
+ VLV_RENDER_RC6_COUNT_EN));
+
+ /* For now we assume BIOS is allocating and populating the PCBR */
+ pcbr = I915_READ(VLV_PCBR);
+
+ DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
+
+ /* 3: Enable RC6 */
+ if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
+ (pcbr >> VLV_PCBR_ADDR_SHIFT))
+ rc6_mode = GEN6_RC_CTL_EI_MODE(1);
+
+ I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
+
+ gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+}
+
static void valleyview_enable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4625,13 +4720,17 @@ void intel_init_gt_powersave(struct drm_device *dev)
{
i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ cherryview_init_gt_powersave(dev);
+ else if (IS_VALLEYVIEW(dev))
valleyview_init_gt_powersave(dev);
}
void intel_cleanup_gt_powersave(struct drm_device *dev)
{
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ return;
+ else if (IS_VALLEYVIEW(dev))
valleyview_cleanup_gt_powersave(dev);
}
@@ -4645,11 +4744,13 @@ void intel_disable_gt_powersave(struct drm_device *dev)
if (IS_IRONLAKE_M(dev)) {
ironlake_disable_drps(dev);
ironlake_disable_rc6(dev);
- } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+ } else if (INTEL_INFO(dev)->gen >= 6) {
cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
cancel_work_sync(&dev_priv->rps.work);
mutex_lock(&dev_priv->rps.hw_lock);
- if (IS_VALLEYVIEW(dev))
+ if (IS_CHERRYVIEW(dev))
+ cherryview_disable_rps(dev);
+ else if (IS_VALLEYVIEW(dev))
valleyview_disable_rps(dev);
else
gen6_disable_rps(dev);
@@ -4667,7 +4768,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
mutex_lock(&dev_priv->rps.hw_lock);
- if (IS_VALLEYVIEW(dev)) {
+ if (IS_CHERRYVIEW(dev)) {
+ cherryview_enable_rps(dev);
+ } else if (IS_VALLEYVIEW(dev)) {
valleyview_enable_rps(dev);
} else if (IS_BROADWELL(dev)) {
gen8_enable_rps(dev);
@@ -4692,7 +4795,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
ironlake_enable_rc6(dev);
intel_init_emon(dev);
mutex_unlock(&dev->struct_mutex);
- } else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+ } else if (INTEL_INFO(dev)->gen >= 6) {
/*
* PCU communication is slow and this doesn't need to be
* done at any specific time, so do this out of our fast path
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread
* [PATCH 04/10] drm/i915/chv: Added CHV specific register read and write
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (2 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 03/10] drm/i915/chv: Enable Render Standby (RC6) for Cherryview deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-16 14:46 ` Mika Kuoppala
2014-05-05 12:47 ` [PATCH 05/10] drm/i915/chv: Streamline CHV forcewake stuff deepak.s
` (6 subsequent siblings)
10 siblings, 1 reply; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Deepak S <deepak.s@linux.intel.com>
Support to individually control Media/Render well based on the register access.
Add CHV specific write function to habdle difference between registers
that are sadowed vs those that need forcewake even for writes.
v2: Drop write FIFO for CHV and add comman well forcewake (Ville)
v3: Fix for decrementing fw count in chv read/write. (Deepak)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
[vsyrjala: Move the register range macros into intel_uncore.c]
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
drivers/gpu/drm/i915/intel_uncore.c | 133 +++++++++++++++++++++++++++++++++---
1 file changed, 125 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 76dc185..4f1f199 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -495,6 +495,31 @@ void assert_force_wake_inactive(struct drm_i915_private *dev_priv)
((reg) >= 0x22000 && (reg) < 0x24000) ||\
((reg) >= 0x30000 && (reg) < 0x40000))
+#define FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg) \
+ (((reg) >= 0x2000 && (reg) < 0x4000) ||\
+ ((reg) >= 0x5000 && (reg) < 0x8000) ||\
+ ((reg) >= 0x8300 && (reg) < 0x8500) ||\
+ ((reg) >= 0xB000 && (reg) < 0xC000) ||\
+ ((reg) >= 0xE000 && (reg) < 0xE800))
+
+#define FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)\
+ (((reg) >= 0x8800 && (reg) < 0x8900) ||\
+ ((reg) >= 0xD000 && (reg) < 0xD800) ||\
+ ((reg) >= 0x12000 && (reg) < 0x14000) ||\
+ ((reg) >= 0x1A000 && (reg) < 0x1C000) ||\
+ ((reg) >= 0x1E800 && (reg) < 0x1EA00) ||\
+ ((reg) >= 0x30000 && (reg) < 0x40000))
+
+#define FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)\
+ (((reg) >= 0x4000 && (reg) < 0x5000) ||\
+ ((reg) >= 0x8000 && (reg) < 0x8300) ||\
+ ((reg) >= 0x8500 && (reg) < 0x8600) ||\
+ ((reg) >= 0x9000 && (reg) < 0xB000) ||\
+ ((reg) >= 0xC000 && (reg) < 0xc800) ||\
+ ((reg) >= 0xF000 && (reg) < 0x10000) ||\
+ ((reg) >= 0x14000 && (reg) < 0x14400) ||\
+ ((reg) >= 0x22000 && (reg) < 0x24000))
+
static void
ilk_dummy_write(struct drm_i915_private *dev_priv)
{
@@ -588,7 +613,45 @@ vlv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
REG_READ_FOOTER; \
}
+#define __chv_read(x) \
+static u##x \
+chv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
+ unsigned fwengine = 0; \
+ REG_READ_HEADER(x); \
+ if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) \
+ fwengine = FORCEWAKE_RENDER; \
+ else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) \
+ fwengine = FORCEWAKE_MEDIA; \
+ else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) \
+ fwengine = FORCEWAKE_ALL; \
+ if (FORCEWAKE_RENDER & fwengine) { \
+ if (dev_priv->uncore.fw_rendercount++ == 0) \
+ (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
+ fwengine); \
+ } \
+ if (FORCEWAKE_MEDIA & fwengine) { \
+ if (dev_priv->uncore.fw_mediacount++ == 0) \
+ (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
+ fwengine); \
+ } \
+ val = __raw_i915_read##x(dev_priv, reg); \
+ if (FORCEWAKE_RENDER & fwengine) { \
+ if (--dev_priv->uncore.fw_rendercount == 0) \
+ (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
+ fwengine); \
+ } \
+ if (FORCEWAKE_MEDIA & fwengine) { \
+ if (--dev_priv->uncore.fw_mediacount == 0) \
+ (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
+ fwengine); \
+ } \
+ REG_READ_FOOTER; \
+}
+__chv_read(8)
+__chv_read(16)
+__chv_read(32)
+__chv_read(64)
__vlv_read(8)
__vlv_read(16)
__vlv_read(32)
@@ -606,6 +669,7 @@ __gen4_read(16)
__gen4_read(32)
__gen4_read(64)
+#undef __chv_read
#undef __vlv_read
#undef __gen6_read
#undef __gen5_read
@@ -710,6 +774,46 @@ gen8_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace
REG_WRITE_FOOTER; \
}
+#define __chv_write(x) \
+static void \
+chv_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
+ unsigned fwengine = 0; \
+ bool __needs_put = !is_gen8_shadowed(dev_priv, reg); \
+ REG_WRITE_HEADER; \
+ if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) \
+ fwengine = FORCEWAKE_RENDER; \
+ else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) \
+ fwengine = FORCEWAKE_MEDIA; \
+ else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) \
+ fwengine = FORCEWAKE_ALL; \
+ if (__needs_put && (FORCEWAKE_RENDER & fwengine)) { \
+ if (dev_priv->uncore.fw_rendercount++ == 0) \
+ (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
+ fwengine); \
+ } \
+ if (__needs_put && (FORCEWAKE_MEDIA & fwengine)) { \
+ if (dev_priv->uncore.fw_mediacount++ == 0) \
+ (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
+ fwengine); \
+ } \
+ __raw_i915_write##x(dev_priv, reg, val); \
+ if (__needs_put && (FORCEWAKE_RENDER & fwengine)) { \
+ if (--dev_priv->uncore.fw_rendercount == 0) \
+ (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
+ fwengine); \
+ } \
+ if (__needs_put && (FORCEWAKE_MEDIA & fwengine)) { \
+ if (--dev_priv->uncore.fw_mediacount == 0) \
+ (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
+ fwengine); \
+ } \
+ REG_WRITE_FOOTER; \
+}
+
+__chv_write(8)
+__chv_write(16)
+__chv_write(32)
+__chv_write(64)
__gen8_write(8)
__gen8_write(16)
__gen8_write(32)
@@ -731,6 +835,7 @@ __gen4_write(16)
__gen4_write(32)
__gen4_write(64)
+#undef __chv_write
#undef __gen8_write
#undef __hsw_write
#undef __gen6_write
@@ -794,14 +899,26 @@ void intel_uncore_init(struct drm_device *dev)
switch (INTEL_INFO(dev)->gen) {
default:
- dev_priv->uncore.funcs.mmio_writeb = gen8_write8;
- dev_priv->uncore.funcs.mmio_writew = gen8_write16;
- dev_priv->uncore.funcs.mmio_writel = gen8_write32;
- dev_priv->uncore.funcs.mmio_writeq = gen8_write64;
- dev_priv->uncore.funcs.mmio_readb = gen6_read8;
- dev_priv->uncore.funcs.mmio_readw = gen6_read16;
- dev_priv->uncore.funcs.mmio_readl = gen6_read32;
- dev_priv->uncore.funcs.mmio_readq = gen6_read64;
+ if (IS_CHERRYVIEW(dev)) {
+ dev_priv->uncore.funcs.mmio_writeb = chv_write8;
+ dev_priv->uncore.funcs.mmio_writew = chv_write16;
+ dev_priv->uncore.funcs.mmio_writel = chv_write32;
+ dev_priv->uncore.funcs.mmio_writeq = chv_write64;
+ dev_priv->uncore.funcs.mmio_readb = chv_read8;
+ dev_priv->uncore.funcs.mmio_readw = chv_read16;
+ dev_priv->uncore.funcs.mmio_readl = chv_read32;
+ dev_priv->uncore.funcs.mmio_readq = chv_read64;
+
+ } else {
+ dev_priv->uncore.funcs.mmio_writeb = gen8_write8;
+ dev_priv->uncore.funcs.mmio_writew = gen8_write16;
+ dev_priv->uncore.funcs.mmio_writel = gen8_write32;
+ dev_priv->uncore.funcs.mmio_writeq = gen8_write64;
+ dev_priv->uncore.funcs.mmio_readb = gen6_read8;
+ dev_priv->uncore.funcs.mmio_readw = gen6_read16;
+ dev_priv->uncore.funcs.mmio_readl = gen6_read32;
+ dev_priv->uncore.funcs.mmio_readq = gen6_read64;
+ }
break;
case 7:
case 6:
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH 04/10] drm/i915/chv: Added CHV specific register read and write
2014-05-05 12:47 ` [PATCH 04/10] drm/i915/chv: Added CHV specific register read and write deepak.s
@ 2014-05-16 14:46 ` Mika Kuoppala
0 siblings, 0 replies; 26+ messages in thread
From: Mika Kuoppala @ 2014-05-16 14:46 UTC (permalink / raw)
To: deepak.s, intel-gfx; +Cc: fafael.barbalho
deepak.s@linux.intel.com writes:
> From: Deepak S <deepak.s@linux.intel.com>
>
> Support to individually control Media/Render well based on the register access.
> Add CHV specific write function to habdle difference between registers
> that are sadowed vs those that need forcewake even for writes.
>
> v2: Drop write FIFO for CHV and add comman well forcewake (Ville)
>
> v3: Fix for decrementing fw count in chv read/write. (Deepak)
>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
> [vsyrjala: Move the register range macros into intel_uncore.c]
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> ---
> drivers/gpu/drm/i915/intel_uncore.c | 133 +++++++++++++++++++++++++++++++++---
> 1 file changed, 125 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
> index 76dc185..4f1f199 100644
> --- a/drivers/gpu/drm/i915/intel_uncore.c
> +++ b/drivers/gpu/drm/i915/intel_uncore.c
> @@ -495,6 +495,31 @@ void assert_force_wake_inactive(struct drm_i915_private *dev_priv)
> ((reg) >= 0x22000 && (reg) < 0x24000) ||\
> ((reg) >= 0x30000 && (reg) < 0x40000))
>
> +#define FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg) \
> + (((reg) >= 0x2000 && (reg) < 0x4000) ||\
> + ((reg) >= 0x5000 && (reg) < 0x8000) ||\
> + ((reg) >= 0x8300 && (reg) < 0x8500) ||\
> + ((reg) >= 0xB000 && (reg) < 0xC000) ||\
> + ((reg) >= 0xE000 && (reg) < 0xE800))
> +
> +#define FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)\
> + (((reg) >= 0x8800 && (reg) < 0x8900) ||\
> + ((reg) >= 0xD000 && (reg) < 0xD800) ||\
> + ((reg) >= 0x12000 && (reg) < 0x14000) ||\
> + ((reg) >= 0x1A000 && (reg) < 0x1C000) ||\
> + ((reg) >= 0x1E800 && (reg) < 0x1EA00) ||\
> + ((reg) >= 0x30000 && (reg) < 0x40000))
> +
> +#define FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)\
> + (((reg) >= 0x4000 && (reg) < 0x5000) ||\
> + ((reg) >= 0x8000 && (reg) < 0x8300) ||\
> + ((reg) >= 0x8500 && (reg) < 0x8600) ||\
> + ((reg) >= 0x9000 && (reg) < 0xB000) ||\
> + ((reg) >= 0xC000 && (reg) < 0xc800) ||\
> + ((reg) >= 0xF000 && (reg) < 0x10000) ||\
> + ((reg) >= 0x14000 && (reg) < 0x14400) ||\
> + ((reg) >= 0x22000 && (reg) < 0x24000))
> +
For these two last register ranges I couldnt find an indication
if we really need to take fw. I guess it doesnt hurt but
please re-check if these are truely needed.
> static void
> ilk_dummy_write(struct drm_i915_private *dev_priv)
> {
> @@ -588,7 +613,45 @@ vlv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
> REG_READ_FOOTER; \
> }
>
> +#define __chv_read(x) \
> +static u##x \
> +chv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
> + unsigned fwengine = 0; \
> + REG_READ_HEADER(x); \
> + if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) \
> + fwengine = FORCEWAKE_RENDER; \
> + else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) \
> + fwengine = FORCEWAKE_MEDIA; \
> + else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) \
> + fwengine = FORCEWAKE_ALL; \
> + if (FORCEWAKE_RENDER & fwengine) { \
> + if (dev_priv->uncore.fw_rendercount++ == 0) \
> + (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
> + fwengine); \
> + } \
> + if (FORCEWAKE_MEDIA & fwengine) { \
> + if (dev_priv->uncore.fw_mediacount++ == 0) \
> + (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
> + fwengine); \
> + } \
This patch introduces a bug in here because we end up waking up
the same well twice in a row, by delivering fwengine into the wake func.
The following patch in the series fixes this bug. You should
squash these two into a single patch.
-Mika
> + val = __raw_i915_read##x(dev_priv, reg); \
> + if (FORCEWAKE_RENDER & fwengine) { \
> + if (--dev_priv->uncore.fw_rendercount == 0) \
> + (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
> + fwengine); \
> + } \
> + if (FORCEWAKE_MEDIA & fwengine) { \
> + if (--dev_priv->uncore.fw_mediacount == 0) \
> + (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
> + fwengine); \
> + } \
> + REG_READ_FOOTER; \
> +}
>
> +__chv_read(8)
> +__chv_read(16)
> +__chv_read(32)
> +__chv_read(64)
> __vlv_read(8)
> __vlv_read(16)
> __vlv_read(32)
> @@ -606,6 +669,7 @@ __gen4_read(16)
> __gen4_read(32)
> __gen4_read(64)
>
> +#undef __chv_read
> #undef __vlv_read
> #undef __gen6_read
> #undef __gen5_read
> @@ -710,6 +774,46 @@ gen8_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace
> REG_WRITE_FOOTER; \
> }
>
> +#define __chv_write(x) \
> +static void \
> +chv_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
> + unsigned fwengine = 0; \
> + bool __needs_put = !is_gen8_shadowed(dev_priv, reg); \
> + REG_WRITE_HEADER; \
> + if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) \
> + fwengine = FORCEWAKE_RENDER; \
> + else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) \
> + fwengine = FORCEWAKE_MEDIA; \
> + else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) \
> + fwengine = FORCEWAKE_ALL; \
> + if (__needs_put && (FORCEWAKE_RENDER & fwengine)) { \
> + if (dev_priv->uncore.fw_rendercount++ == 0) \
> + (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
> + fwengine); \
> + } \
> + if (__needs_put && (FORCEWAKE_MEDIA & fwengine)) { \
> + if (dev_priv->uncore.fw_mediacount++ == 0) \
> + (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
> + fwengine); \
> + } \
> + __raw_i915_write##x(dev_priv, reg, val); \
> + if (__needs_put && (FORCEWAKE_RENDER & fwengine)) { \
> + if (--dev_priv->uncore.fw_rendercount == 0) \
> + (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
> + fwengine); \
> + } \
> + if (__needs_put && (FORCEWAKE_MEDIA & fwengine)) { \
> + if (--dev_priv->uncore.fw_mediacount == 0) \
> + (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
> + fwengine); \
> + } \
> + REG_WRITE_FOOTER; \
> +}
> +
> +__chv_write(8)
> +__chv_write(16)
> +__chv_write(32)
> +__chv_write(64)
> __gen8_write(8)
> __gen8_write(16)
> __gen8_write(32)
> @@ -731,6 +835,7 @@ __gen4_write(16)
> __gen4_write(32)
> __gen4_write(64)
>
> +#undef __chv_write
> #undef __gen8_write
> #undef __hsw_write
> #undef __gen6_write
> @@ -794,14 +899,26 @@ void intel_uncore_init(struct drm_device *dev)
>
> switch (INTEL_INFO(dev)->gen) {
> default:
> - dev_priv->uncore.funcs.mmio_writeb = gen8_write8;
> - dev_priv->uncore.funcs.mmio_writew = gen8_write16;
> - dev_priv->uncore.funcs.mmio_writel = gen8_write32;
> - dev_priv->uncore.funcs.mmio_writeq = gen8_write64;
> - dev_priv->uncore.funcs.mmio_readb = gen6_read8;
> - dev_priv->uncore.funcs.mmio_readw = gen6_read16;
> - dev_priv->uncore.funcs.mmio_readl = gen6_read32;
> - dev_priv->uncore.funcs.mmio_readq = gen6_read64;
> + if (IS_CHERRYVIEW(dev)) {
> + dev_priv->uncore.funcs.mmio_writeb = chv_write8;
> + dev_priv->uncore.funcs.mmio_writew = chv_write16;
> + dev_priv->uncore.funcs.mmio_writel = chv_write32;
> + dev_priv->uncore.funcs.mmio_writeq = chv_write64;
> + dev_priv->uncore.funcs.mmio_readb = chv_read8;
> + dev_priv->uncore.funcs.mmio_readw = chv_read16;
> + dev_priv->uncore.funcs.mmio_readl = chv_read32;
> + dev_priv->uncore.funcs.mmio_readq = chv_read64;
> +
> + } else {
> + dev_priv->uncore.funcs.mmio_writeb = gen8_write8;
> + dev_priv->uncore.funcs.mmio_writew = gen8_write16;
> + dev_priv->uncore.funcs.mmio_writel = gen8_write32;
> + dev_priv->uncore.funcs.mmio_writeq = gen8_write64;
> + dev_priv->uncore.funcs.mmio_readb = gen6_read8;
> + dev_priv->uncore.funcs.mmio_readw = gen6_read16;
> + dev_priv->uncore.funcs.mmio_readl = gen6_read32;
> + dev_priv->uncore.funcs.mmio_readq = gen6_read64;
> + }
> break;
> case 7:
> case 6:
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply [flat|nested] 26+ messages in thread
* [PATCH 05/10] drm/i915/chv: Streamline CHV forcewake stuff
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (3 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 04/10] drm/i915/chv: Added CHV specific register read and write deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-05 12:47 ` [PATCH 06/10] drm/i915/chv: Enable RPS (Turbo) for Cherryview deepak.s
` (5 subsequent siblings)
10 siblings, 0 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Deepak S <deepak.s@linux.intel.com>
Streamline the CHV forcewake functions just like was done for VLV.
This will also fix a bug in accessing the common well registers,
where we'd end up trying to wake up the wells too many times
since we'd call force_wake_get/put twice per register access, with
FORCEFAKE_ALL both times.
v2: Re-factor CHV/VLV Forcewake offsets (Ben)
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
---
drivers/gpu/drm/i915/intel_uncore.c | 148 ++++++++++++++++--------------------
1 file changed, 66 insertions(+), 82 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 4f1f199..d1a8c72 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -484,41 +484,43 @@ void assert_force_wake_inactive(struct drm_i915_private *dev_priv)
#define NEEDS_FORCE_WAKE(dev_priv, reg) \
((reg) < 0x40000 && (reg) != FORCEWAKE)
+#define REG_RANGE(reg, start, end) ((reg) >= (start) && (reg) < (end))
+
#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \
- (((reg) >= 0x2000 && (reg) < 0x4000) ||\
- ((reg) >= 0x5000 && (reg) < 0x8000) ||\
- ((reg) >= 0xB000 && (reg) < 0x12000) ||\
- ((reg) >= 0x2E000 && (reg) < 0x30000))
+ (REG_RANGE((reg), 0x2000, 0x4000) || \
+ REG_RANGE((reg), 0x5000, 0x8000) || \
+ REG_RANGE((reg), 0xB000, 0x12000) || \
+ REG_RANGE((reg), 0x2E000, 0x30000))
-#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)\
- (((reg) >= 0x12000 && (reg) < 0x14000) ||\
- ((reg) >= 0x22000 && (reg) < 0x24000) ||\
- ((reg) >= 0x30000 && (reg) < 0x40000))
+#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg) \
+ (REG_RANGE((reg), 0x12000, 0x14000) || \
+ REG_RANGE((reg), 0x22000, 0x24000) || \
+ REG_RANGE((reg), 0x30000, 0x40000))
#define FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg) \
- (((reg) >= 0x2000 && (reg) < 0x4000) ||\
- ((reg) >= 0x5000 && (reg) < 0x8000) ||\
- ((reg) >= 0x8300 && (reg) < 0x8500) ||\
- ((reg) >= 0xB000 && (reg) < 0xC000) ||\
- ((reg) >= 0xE000 && (reg) < 0xE800))
-
-#define FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)\
- (((reg) >= 0x8800 && (reg) < 0x8900) ||\
- ((reg) >= 0xD000 && (reg) < 0xD800) ||\
- ((reg) >= 0x12000 && (reg) < 0x14000) ||\
- ((reg) >= 0x1A000 && (reg) < 0x1C000) ||\
- ((reg) >= 0x1E800 && (reg) < 0x1EA00) ||\
- ((reg) >= 0x30000 && (reg) < 0x40000))
-
-#define FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)\
- (((reg) >= 0x4000 && (reg) < 0x5000) ||\
- ((reg) >= 0x8000 && (reg) < 0x8300) ||\
- ((reg) >= 0x8500 && (reg) < 0x8600) ||\
- ((reg) >= 0x9000 && (reg) < 0xB000) ||\
- ((reg) >= 0xC000 && (reg) < 0xc800) ||\
- ((reg) >= 0xF000 && (reg) < 0x10000) ||\
- ((reg) >= 0x14000 && (reg) < 0x14400) ||\
- ((reg) >= 0x22000 && (reg) < 0x24000))
+ (REG_RANGE((reg), 0x2000, 0x4000) || \
+ REG_RANGE((reg), 0x5000, 0x8000) || \
+ REG_RANGE((reg), 0x8300, 0x8500) || \
+ REG_RANGE((reg), 0xB000, 0xC000) || \
+ REG_RANGE((reg), 0xE000, 0xE800))
+
+#define FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg) \
+ (REG_RANGE((reg), 0x8800, 0x8900) || \
+ REG_RANGE((reg), 0xD000, 0xD800) || \
+ REG_RANGE((reg), 0x12000, 0x14000) || \
+ REG_RANGE((reg), 0x1A000, 0x1C000) || \
+ REG_RANGE((reg), 0x1E800, 0x1EA00) || \
+ REG_RANGE((reg), 0x30000, 0x40000))
+
+#define FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg) \
+ (REG_RANGE((reg), 0x4000, 0x5000) || \
+ REG_RANGE((reg), 0x8000, 0x8300) || \
+ REG_RANGE((reg), 0x8500, 0x8600) || \
+ REG_RANGE((reg), 0x9000, 0xB000) || \
+ REG_RANGE((reg), 0xC000, 0xC800) || \
+ REG_RANGE((reg), 0xF000, 0x10000) || \
+ REG_RANGE((reg), 0x14000, 0x14400) || \
+ REG_RANGE((reg), 0x22000, 0x24000))
static void
ilk_dummy_write(struct drm_i915_private *dev_priv)
@@ -618,33 +620,23 @@ static u##x \
chv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
unsigned fwengine = 0; \
REG_READ_HEADER(x); \
- if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) \
- fwengine = FORCEWAKE_RENDER; \
- else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) \
- fwengine = FORCEWAKE_MEDIA; \
- else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) \
- fwengine = FORCEWAKE_ALL; \
- if (FORCEWAKE_RENDER & fwengine) { \
- if (dev_priv->uncore.fw_rendercount++ == 0) \
- (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
- fwengine); \
- } \
- if (FORCEWAKE_MEDIA & fwengine) { \
- if (dev_priv->uncore.fw_mediacount++ == 0) \
- (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
- fwengine); \
+ if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) { \
+ if (dev_priv->uncore.fw_rendercount == 0) \
+ fwengine = FORCEWAKE_RENDER; \
+ } else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) { \
+ if (dev_priv->uncore.fw_mediacount == 0) \
+ fwengine = FORCEWAKE_MEDIA; \
+ } else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) { \
+ if (dev_priv->uncore.fw_rendercount == 0) \
+ fwengine |= FORCEWAKE_RENDER; \
+ if (dev_priv->uncore.fw_mediacount == 0) \
+ fwengine |= FORCEWAKE_MEDIA; \
} \
+ if (fwengine) \
+ dev_priv->uncore.funcs.force_wake_get(dev_priv, fwengine); \
val = __raw_i915_read##x(dev_priv, reg); \
- if (FORCEWAKE_RENDER & fwengine) { \
- if (--dev_priv->uncore.fw_rendercount == 0) \
- (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
- fwengine); \
- } \
- if (FORCEWAKE_MEDIA & fwengine) { \
- if (--dev_priv->uncore.fw_mediacount == 0) \
- (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
- fwengine); \
- } \
+ if (fwengine) \
+ dev_priv->uncore.funcs.force_wake_put(dev_priv, fwengine); \
REG_READ_FOOTER; \
}
@@ -778,35 +770,27 @@ gen8_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace
static void \
chv_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
unsigned fwengine = 0; \
- bool __needs_put = !is_gen8_shadowed(dev_priv, reg); \
+ bool shadowed = is_gen8_shadowed(dev_priv, reg); \
REG_WRITE_HEADER; \
- if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) \
- fwengine = FORCEWAKE_RENDER; \
- else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) \
- fwengine = FORCEWAKE_MEDIA; \
- else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) \
- fwengine = FORCEWAKE_ALL; \
- if (__needs_put && (FORCEWAKE_RENDER & fwengine)) { \
- if (dev_priv->uncore.fw_rendercount++ == 0) \
- (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
- fwengine); \
- } \
- if (__needs_put && (FORCEWAKE_MEDIA & fwengine)) { \
- if (dev_priv->uncore.fw_mediacount++ == 0) \
- (dev_priv)->uncore.funcs.force_wake_get(dev_priv, \
- fwengine); \
+ if (!shadowed) { \
+ if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) { \
+ if (dev_priv->uncore.fw_rendercount == 0) \
+ fwengine = FORCEWAKE_RENDER; \
+ } else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) { \
+ if (dev_priv->uncore.fw_mediacount == 0) \
+ fwengine = FORCEWAKE_MEDIA; \
+ } else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) { \
+ if (dev_priv->uncore.fw_rendercount == 0) \
+ fwengine |= FORCEWAKE_RENDER; \
+ if (dev_priv->uncore.fw_mediacount == 0) \
+ fwengine |= FORCEWAKE_MEDIA; \
+ } \
} \
+ if (fwengine) \
+ dev_priv->uncore.funcs.force_wake_get(dev_priv, fwengine); \
__raw_i915_write##x(dev_priv, reg, val); \
- if (__needs_put && (FORCEWAKE_RENDER & fwengine)) { \
- if (--dev_priv->uncore.fw_rendercount == 0) \
- (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
- fwengine); \
- } \
- if (__needs_put && (FORCEWAKE_MEDIA & fwengine)) { \
- if (--dev_priv->uncore.fw_mediacount == 0) \
- (dev_priv)->uncore.funcs.force_wake_put(dev_priv, \
- fwengine); \
- } \
+ if (fwengine) \
+ dev_priv->uncore.funcs.force_wake_put(dev_priv, fwengine); \
REG_WRITE_FOOTER; \
}
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH 06/10] drm/i915/chv: Enable RPS (Turbo) for Cherryview
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (4 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 05/10] drm/i915/chv: Streamline CHV forcewake stuff deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-05 12:47 ` [PATCH 07/10] drm/i915/chv: CHV doesn't need WaRsForcewakeWaitTC0 deepak.s
` (4 subsequent siblings)
10 siblings, 0 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: Daniel Vetter, fafael.barbalho
From: Deepak S <deepak.s@linux.intel.com>
v2: Disable media turbo and Add DOWN_IDLE_AVG support (Ville)
v3: Mass rename of the dev_priv->rps variables in upstream.
v4: Rebase against latest code. (Deepak)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
drivers/gpu/drm/i915/i915_drv.h | 1 +
drivers/gpu/drm/i915/i915_reg.h | 10 ++++
drivers/gpu/drm/i915/intel_pm.c | 95 ++++++++++++++++++++++++++++++++++-
drivers/gpu/drm/i915/intel_sideband.c | 15 ++++++
4 files changed, 120 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5f4f631..e70a9f0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2552,6 +2552,7 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, u8 mbox, u32 val)
u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr);
void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val);
u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr);
+u32 chv_nc_read(struct drm_i915_private *dev_priv, u8 addr);
u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg);
void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b4074fd..3ff34c4 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -475,6 +475,7 @@
#define VLV_IOSF_DATA (VLV_DISPLAY_BASE + 0x2104)
#define VLV_IOSF_ADDR (VLV_DISPLAY_BASE + 0x2108)
+#define CHV_IOSF_PORT_NC 0x04
/* See configdb bunit SB addr map */
#define BUNIT_REG_BISOC 0x11
@@ -520,6 +521,14 @@ enum punit_power_well {
#define PUNIT_FUSE_BUS2 0xf6 /* bits 47:40 */
#define PUNIT_FUSE_BUS1 0xf5 /* bits 55:48 */
+#define CHV_IOSF_NC_FB_GFX_FREQ_FUSE 0xdb
+#define CHV_FB_GFX_MAX_FREQ_FUSE_SHIFT 16
+#define CHV_FB_GFX_MAX_FREQ_FUSE_MASK 0xff
+
+#define CHV_IOSF_NC_FB_GFX_RPE_FUSE 0xdf
+#define CHV_FB_RPE_FREQ_SHIFT 8
+#define CHV_FB_RPE_FREQ_MASK 0xff
+
#define IOSF_NC_FB_GFX_FREQ_FUSE 0x1c
#define FB_GFX_MAX_FREQ_FUSE_SHIFT 3
#define FB_GFX_MAX_FREQ_FUSE_MASK 0x000007f8
@@ -747,6 +756,7 @@ enum punit_power_well {
#define SANDYBRIDGE_FENCE_PITCH_SHIFT 32
#define GEN7_FENCE_MAX_PITCH_VAL 0x0800
+
/* control register for cpu gtt access */
#define TILECTL 0x101000
#define TILECTL_SWZCTL (1 << 0)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f0359b6..dedbdf3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3690,6 +3690,38 @@ void gen6_update_ring_freq(struct drm_device *dev)
mutex_unlock(&dev_priv->rps.hw_lock);
}
+int cherryview_rps_max_freq(struct drm_i915_private *dev_priv)
+{
+ u32 val, rp0;
+
+ val = chv_nc_read(dev_priv, CHV_IOSF_NC_FB_GFX_FREQ_FUSE);
+
+ rp0 = (val >> CHV_FB_GFX_MAX_FREQ_FUSE_SHIFT) &
+ CHV_FB_GFX_MAX_FREQ_FUSE_MASK;
+
+ return rp0;
+}
+
+static int cherryview_rps_rpe_freq(struct drm_i915_private *dev_priv)
+{
+ u32 val, rpe;
+
+ val = chv_nc_read(dev_priv, CHV_IOSF_NC_FB_GFX_RPE_FUSE);
+ rpe = (val >> CHV_FB_RPE_FREQ_SHIFT) & CHV_FB_RPE_FREQ_MASK;
+
+ return rpe;
+}
+
+int cherryview_rps_min_freq(struct drm_i915_private *dev_priv)
+{
+ u32 val, rpn;
+
+ val = chv_nc_read(dev_priv, CHV_IOSF_NC_FB_GFX_FREQ_FUSE);
+ rpn = (val >> CHV_FB_RPE_FREQ_SHIFT) & CHV_FB_RPE_FREQ_MASK;
+
+ return rpn;
+}
+
int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
{
u32 val, rp0;
@@ -3847,7 +3879,36 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
static void cherryview_init_gt_powersave(struct drm_device *dev)
{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
cherryview_setup_pctx(dev);
+
+ mutex_lock(&dev_priv->rps.hw_lock);
+
+ dev_priv->rps.max_freq = cherryview_rps_max_freq(dev_priv);
+ dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
+ DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
+ vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
+ dev_priv->rps.max_freq);
+
+ dev_priv->rps.efficient_freq = cherryview_rps_rpe_freq(dev_priv);
+ DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
+ vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+ dev_priv->rps.efficient_freq);
+
+ dev_priv->rps.min_freq = cherryview_rps_min_freq(dev_priv);
+ DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
+ vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
+ dev_priv->rps.min_freq);
+
+ /* Preserve min/max settings in case of re-init */
+ if (dev_priv->rps.max_freq_softlimit == 0)
+ dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
+
+ if (dev_priv->rps.min_freq_softlimit == 0)
+ dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+
+ mutex_unlock(&dev_priv->rps.hw_lock);
}
static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
@@ -3859,7 +3920,7 @@ static void cherryview_enable_rps(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_ring_buffer *ring;
- u32 gtfifodbg, rc6_mode = 0, pcbr;
+ u32 gtfifodbg, val, rc6_mode = 0, pcbr;
int i;
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
@@ -3908,6 +3969,38 @@ static void cherryview_enable_rps(struct drm_device *dev)
I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
+ /* 4 Program defaults and thresholds for RPS*/
+ I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
+ I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
+ I915_WRITE(GEN6_RP_UP_EI, 66000);
+ I915_WRITE(GEN6_RP_DOWN_EI, 350000);
+
+ I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
+
+ /* 5: Enable RPS */
+ I915_WRITE(GEN6_RP_CONTROL,
+ GEN6_RP_MEDIA_HW_NORMAL_MODE |
+ GEN6_RP_MEDIA_IS_GFX |
+ GEN6_RP_ENABLE |
+ GEN6_RP_UP_BUSY_AVG |
+ GEN6_RP_DOWN_IDLE_AVG);
+
+ val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+
+ DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
+ DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
+
+ dev_priv->rps.cur_freq = (val >> 8) & 0xff;
+ DRM_DEBUG_DRIVER("current GPU freq: %d MHz (%u)\n",
+ vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+ dev_priv->rps.cur_freq);
+
+ DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
+ vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+ dev_priv->rps.efficient_freq);
+
+ valleyview_set_rps(dev_priv->dev, dev_priv->rps.efficient_freq);
+
gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
}
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index b1a5514..8f6904d 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -106,6 +106,21 @@ void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
PUNIT_OPCODE_REG_WRITE, reg, &val);
}
+u32 chv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
+{
+ u32 val = 0;
+
+ WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+ mutex_lock(&dev_priv->dpio_lock);
+ vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), CHV_IOSF_PORT_NC,
+ PUNIT_OPCODE_REG_READ, addr, &val);
+ mutex_unlock(&dev_priv->dpio_lock);
+
+ return val;
+}
+
+
u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
{
u32 val = 0;
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH 07/10] drm/i915/chv: CHV doesn't need WaRsForcewakeWaitTC0
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (5 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 06/10] drm/i915/chv: Enable RPS (Turbo) for Cherryview deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-05 12:47 ` [PATCH 08/10] drm/i915/chv: Skip gen6_gt_check_fifodbg() on CHV deepak.s
` (3 subsequent siblings)
10 siblings, 0 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Skip __gen6_gt_wait_for_thread_c0() on CHV.
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
drivers/gpu/drm/i915/intel_uncore.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index d1a8c72..b719c51 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -229,8 +229,8 @@ static void __vlv_force_wake_get(struct drm_i915_private *dev_priv,
}
/* WaRsForcewakeWaitTC0:vlv */
- __gen6_gt_wait_for_thread_c0(dev_priv);
-
+ if (!IS_CHERRYVIEW(dev_priv->dev))
+ __gen6_gt_wait_for_thread_c0(dev_priv);
}
static void __vlv_force_wake_put(struct drm_i915_private *dev_priv,
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH 08/10] drm/i915/chv: Skip gen6_gt_check_fifodbg() on CHV
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (6 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 07/10] drm/i915/chv: CHV doesn't need WaRsForcewakeWaitTC0 deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-05 12:47 ` [PATCH 09/10] drm/i915/chv: Added CHV specific DDR fetch into init_clock_gating deepak.s
` (2 subsequent siblings)
10 siblings, 0 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
CHV uses the gen8 shadow register mechanism so we shouldn't be
checking the GT FIFO status.
This effectively removes the posting read, so add an explicit
posting read using FORCEWAKE_ACK_VLV (which is what use in
vlv_forcewake_reset()).
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
drivers/gpu/drm/i915/intel_uncore.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index b719c51..fa6e01e 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -248,9 +248,10 @@ static void __vlv_force_wake_put(struct drm_i915_private *dev_priv,
__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
_MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
- /* The below doubles as a POSTING_READ */
- gen6_gt_check_fifodbg(dev_priv);
-
+ /* something from same cacheline, but !FORCEWAKE_VLV */
+ __raw_posting_read(dev_priv, FORCEWAKE_ACK_VLV);
+ if (!IS_CHERRYVIEW(dev_priv->dev))
+ gen6_gt_check_fifodbg(dev_priv);
}
static void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH 09/10] drm/i915/chv: Added CHV specific DDR fetch into init_clock_gating
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (7 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 08/10] drm/i915/chv: Skip gen6_gt_check_fifodbg() on CHV deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-05 12:47 ` [PATCH 10/10] drm/i915/chv: Freq(opcode) request for CHV deepak.s
2014-05-15 21:22 ` [PATCH 00/10] Enable RC6/Turbo on CHV Daniel Vetter
10 siblings, 0 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Deepak S <deepak.s@linux.intel.com>
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
[vsyrjala: Fix merge fubmle where the code ended up in
g4x_disable_trickle_feed() instead of cherryview_init_clock_gating()]
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
---
drivers/gpu/drm/i915/intel_pm.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index dedbdf3..0d9b831 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3985,7 +3985,18 @@ static void cherryview_enable_rps(struct drm_device *dev)
GEN6_RP_UP_BUSY_AVG |
GEN6_RP_DOWN_IDLE_AVG);
+ /* ToDo: Update the mem freq based on latest spec [CHV]*/
val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+ switch ((val >> 6) & 3) {
+ case 0:
+ case 1:
+ case 2:
+ dev_priv->mem_freq = 1600;
+ break;
+ case 3:
+ dev_priv->mem_freq = 2000;
+ break;
+ }
DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
--
1.9.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
^ permalink raw reply related [flat|nested] 26+ messages in thread* [PATCH 10/10] drm/i915/chv: Freq(opcode) request for CHV.
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (8 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 09/10] drm/i915/chv: Added CHV specific DDR fetch into init_clock_gating deepak.s
@ 2014-05-05 12:47 ` deepak.s
2014-05-07 14:23 ` Ville Syrjälä
2014-05-12 13:53 ` [PATCH v2] " deepak.s
2014-05-15 21:22 ` [PATCH 00/10] Enable RC6/Turbo on CHV Daniel Vetter
10 siblings, 2 replies; 26+ messages in thread
From: deepak.s @ 2014-05-05 12:47 UTC (permalink / raw)
To: intel-gfx; +Cc: fafael.barbalho
From: Deepak S <deepak.s@linux.intel.com>
On CHV, All the freq request should be even. So, we need to make sure we
request the opcode accordingly.
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
---
drivers/gpu/drm/i915/i915_drv.h | 1 +
drivers/gpu/drm/i915/i915_irq.c | 9 +++++++--
drivers/gpu/drm/i915/i915_reg.h | 3 +++
3 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e70a9f0..3966ff2 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1318,6 +1318,7 @@ struct drm_i915_private {
u32 gt_irq_mask;
u32 pm_irq_mask;
u32 pm_rps_events;
+ u32 pm_rps_freq_req;
u32 pipestat_irq_mask[I915_MAX_PIPES];
struct work_struct hotplug_work;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6af51ad..3e8bcca 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1162,7 +1162,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
if (adj > 0)
adj *= 2;
else
- adj = 1;
+ adj = dev_priv->pm_rps_freq_req;
new_delay = dev_priv->rps.cur_freq + adj;
/*
@@ -1181,7 +1181,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
if (adj < 0)
adj *= 2;
else
- adj = -1;
+ adj = -1 * dev_priv->pm_rps_freq_req;
new_delay = dev_priv->rps.cur_freq + adj;
} else { /* unknown event */
new_delay = dev_priv->rps.cur_freq;
@@ -4088,6 +4088,11 @@ void intel_irq_init(struct drm_device *dev)
/* Let's track the enabled rps events */
dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
+ if (IS_CHERRYVIEW(dev))
+ dev_priv->pm_rps_freq_req = CHV_GPU_FREQ_REQ;
+ else
+ dev_priv->pm_rps_freq_req = GEN6_GPU_FREQ_REQ;
+
setup_timer(&dev_priv->gpu_error.hangcheck_timer,
i915_hangcheck_elapsed,
(unsigned long) dev);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3ff34c4..4998d6b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -529,6 +529,9 @@ enum punit_power_well {
#define CHV_FB_RPE_FREQ_SHIFT 8
#define CHV_FB_RPE_FREQ_MASK 0xff
+#define CHV_GPU_FREQ_REQ 2
+#define GEN6_GPU_FREQ_REQ 1
+
#define IOSF_NC_FB_GFX_FREQ_FUSE 0x1c
#define FB_GFX_MAX_FREQ_FUSE_SHIFT 3
#define FB_GFX_MAX_FREQ_FUSE_MASK 0x000007f8
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread* Re: [PATCH 10/10] drm/i915/chv: Freq(opcode) request for CHV.
2014-05-05 12:47 ` [PATCH 10/10] drm/i915/chv: Freq(opcode) request for CHV deepak.s
@ 2014-05-07 14:23 ` Ville Syrjälä
2014-05-12 13:53 ` [PATCH v2] " deepak.s
1 sibling, 0 replies; 26+ messages in thread
From: Ville Syrjälä @ 2014-05-07 14:23 UTC (permalink / raw)
To: deepak.s; +Cc: intel-gfx, fafael.barbalho
On Mon, May 05, 2014 at 06:17:39PM +0530, deepak.s@linux.intel.com wrote:
> From: Deepak S <deepak.s@linux.intel.com>
>
> On CHV, All the freq request should be even. So, we need to make sure we
> request the opcode accordingly.
>
> Signed-off-by: Deepak S <deepak.s@linux.intel.com>
> Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
> ---
> drivers/gpu/drm/i915/i915_drv.h | 1 +
> drivers/gpu/drm/i915/i915_irq.c | 9 +++++++--
> drivers/gpu/drm/i915/i915_reg.h | 3 +++
> 3 files changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index e70a9f0..3966ff2 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -1318,6 +1318,7 @@ struct drm_i915_private {
> u32 gt_irq_mask;
> u32 pm_irq_mask;
> u32 pm_rps_events;
> + u32 pm_rps_freq_req;
> u32 pipestat_irq_mask[I915_MAX_PIPES];
>
> struct work_struct hotplug_work;
> diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
> index 6af51ad..3e8bcca 100644
> --- a/drivers/gpu/drm/i915/i915_irq.c
> +++ b/drivers/gpu/drm/i915/i915_irq.c
> @@ -1162,7 +1162,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
> if (adj > 0)
> adj *= 2;
> else
> - adj = 1;
> + adj = dev_priv->pm_rps_freq_req;
> new_delay = dev_priv->rps.cur_freq + adj;
>
> /*
> @@ -1181,7 +1181,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
> if (adj < 0)
> adj *= 2;
> else
> - adj = -1;
> + adj = -1 * dev_priv->pm_rps_freq_req;
I'm not sure pm_rps_freq_req is very descriptive. Maybe it's better to
just open code the thing and add a few comments. Eg.:
/* CHV requires even values */
adj = IS_CHERRYVIEW(dev) ? 2 : 1;
...
/* CHV requires even values */
adj = IS_CHERRYVIEW(dev) ? -2 : -1;
> new_delay = dev_priv->rps.cur_freq + adj;
In any case this doesn't seem to enough to guarantee an even value.
You'd also need to make sure efficient_freq, min_freq_softlimit and
max_freq_softlimit are even.
The alternative is to just make the final value even in
valleyview_set_rps(), but then you might still trip these
WARN_ON(val > dev_priv->rps.max_freq_softlimit);
WARN_ON(val < dev_priv->rps.min_freq_softlimit);
in there. So I guess it's back to option 1 and making sure all the
limits are also even. Also leaving it up to valleyview_set_rps() could
introduce a slight delay before the frequency starts to change since it
could effectively ignore the first interrupt (depending on which way
it's going and which we we would round the final value).
> } else { /* unknown event */
> new_delay = dev_priv->rps.cur_freq;
> @@ -4088,6 +4088,11 @@ void intel_irq_init(struct drm_device *dev)
> /* Let's track the enabled rps events */
> dev_priv->pm_rps_events = GEN6_PM_RPS_EVENTS;
>
> + if (IS_CHERRYVIEW(dev))
> + dev_priv->pm_rps_freq_req = CHV_GPU_FREQ_REQ;
> + else
> + dev_priv->pm_rps_freq_req = GEN6_GPU_FREQ_REQ;
> +
> setup_timer(&dev_priv->gpu_error.hangcheck_timer,
> i915_hangcheck_elapsed,
> (unsigned long) dev);
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index 3ff34c4..4998d6b 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -529,6 +529,9 @@ enum punit_power_well {
> #define CHV_FB_RPE_FREQ_SHIFT 8
> #define CHV_FB_RPE_FREQ_MASK 0xff
>
> +#define CHV_GPU_FREQ_REQ 2
> +#define GEN6_GPU_FREQ_REQ 1
I don't think these defines buy us anything. Instead I think just
adding a comment or two to where the even vs. odd magic happens
should be a better option.
> +
> #define IOSF_NC_FB_GFX_FREQ_FUSE 0x1c
> #define FB_GFX_MAX_FREQ_FUSE_SHIFT 3
> #define FB_GFX_MAX_FREQ_FUSE_MASK 0x000007f8
> --
> 1.9.1
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Ville Syrjälä
Intel OTC
^ permalink raw reply [flat|nested] 26+ messages in thread* [PATCH v2] drm/i915/chv: Freq(opcode) request for CHV.
2014-05-05 12:47 ` [PATCH 10/10] drm/i915/chv: Freq(opcode) request for CHV deepak.s
2014-05-07 14:23 ` Ville Syrjälä
@ 2014-05-12 13:53 ` deepak.s
1 sibling, 0 replies; 26+ messages in thread
From: deepak.s @ 2014-05-12 13:53 UTC (permalink / raw)
To: intel-gfx
From: Deepak S <deepak.s@linux.intel.com>
On CHV, All the freq request should be even. So, we need to make sure we
request the opcode accordingly.
v2: Avoid vairable for freq request (ville)
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
---
drivers/gpu/drm/i915/i915_irq.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6af51ad..56e93e8 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1161,8 +1161,10 @@ static void gen6_pm_rps_work(struct work_struct *work)
if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
if (adj > 0)
adj *= 2;
- else
- adj = 1;
+ else {
+ /* CHV needs even encode values */
+ adj = IS_CHERRYVIEW(dev_priv->dev) ? 2 : 1;
+ }
new_delay = dev_priv->rps.cur_freq + adj;
/*
@@ -1180,8 +1182,10 @@ static void gen6_pm_rps_work(struct work_struct *work)
} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
if (adj < 0)
adj *= 2;
- else
- adj = -1;
+ else {
+ /* CHV needs even encode values */
+ adj = IS_CHERRYVIEW(dev_priv->dev) ? -2 : -1;
+ }
new_delay = dev_priv->rps.cur_freq + adj;
} else { /* unknown event */
new_delay = dev_priv->rps.cur_freq;
--
1.9.1
^ permalink raw reply related [flat|nested] 26+ messages in thread
* Re: [PATCH 00/10] Enable RC6/Turbo on CHV
2014-05-05 12:47 [PATCH 00/10] Enable RC6/Turbo on CHV deepak.s
` (9 preceding siblings ...)
2014-05-05 12:47 ` [PATCH 10/10] drm/i915/chv: Freq(opcode) request for CHV deepak.s
@ 2014-05-15 21:22 ` Daniel Vetter
10 siblings, 0 replies; 26+ messages in thread
From: Daniel Vetter @ 2014-05-15 21:22 UTC (permalink / raw)
To: deepak.s; +Cc: intel-gfx, fafael.barbalho
On Mon, May 05, 2014 at 06:17:29PM +0530, deepak.s@linux.intel.com wrote:
> From: Deepak S <deepak.s@linux.intel.com>
>
> Squashed some of the patches and created a new patch series. Addressed review comments on most of the patches.
>
> Ben Widawsky (1):
> drm/i915/bdw: Implement a basic PM interrupt handler
>
> Deepak S (7):
> drm/i915: Enable PM Interrupts target via Display Interface.
> drm/i915/chv: Enable Render Standby (RC6) for Cherryview
> drm/i915/chv: Added CHV specific register read and write
> drm/i915/chv: Streamline CHV forcewake stuff
> drm/i915/chv: Enable RPS (Turbo) for Cherryview
> drm/i915/chv: Added CHV specific DDR fetch into init_clock_gating
> drm/i915/chv: Freq(opcode) request for CHV.
>
> Ville Syrjälä (2):
> drm/i915/chv: CHV doesn't need WaRsForcewakeWaitTC0
> drm/i915/chv: Skip gen6_gt_check_fifodbg() on CHV
Just for coordination: I've just pulled in the bdw-only series from Mika,
so I guess you need to rebase the chv patches on top of drm-intel-nightly.
I think -nightly has now enough of the chv stuff merged that this should
work out. Otherwise I need to beat up the reviewers to not slack off this
much :(
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
^ permalink raw reply [flat|nested] 26+ messages in thread