drm/i915: Tweak RPS thresholds to more aggressively downclock

After applying wait-boost we often find ourselves stuck at higher clocks
than required. The current threshold value requires the GPU to be
continuously and completely idle for 313ms before it is dropped by one
bin. Conversely, we require the GPU to be busy for an average of 90% over
a 84ms period before we upclock. So the current thresholds almost never
downclock the GPU, and respond very slowly to sudden demands for more
power. It is easy to observe that we currently lock into the wrong bin
and both underperform in benchmarks and consume more power than optimal
(just by repeating the task and measuring the different results).

An alternative approach, as discussed in the bspec, is to use a
continuous threshold for upclocking, and an average value for downclocking.
This is good for quickly detecting and reacting to state changes within a
frame, however it fails with the common throttling method of waiting
upon the outstanding frame - at least it is difficult to choose a
threshold that works well at 15,000fps and at 60fps. So continue to use
average busy/idle loads to determine frequency change.

v2: Use 3 power zones to keep frequencies low in steady-state mostly
idle (e.g. scrolling, interactive 2D drawing), and frequencies high
for demanding games. In between those end-states, we use a
fast-reclocking algorithm to converge more quickly on the desired bin.

v3: Bug fixes - make sure we reset adj after switching power zones.

v4: Tune - drop the continuous busy thresholds as it prevents us from
choosing the right frequency for glxgears style swap benchmarks. Instead
the goal is to be able to find the right clocks irrespective of the
wait-boost.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Stéphane Marchesin <stephane.marchesin@gmail.com>
Cc: Owen Taylor <otaylor@redhat.com>
Cc: "Meng, Mengmeng" <mengmeng.meng@intel.com>
Cc: "Zhuang, Lena" <lena.zhuang@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

4 files changed, 143 insertions, 47 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d1c6b92edae0..5118ac300c42 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -850,8 +850,13 @@ struct intel_gen6_power_mgmt {
 	u8 min_delay;
 	u8 max_delay;
 	u8 rpe_delay;
+	u8 rp1_delay;
+	u8 rp0_delay;
 	u8 hw_max;
 
+	int last_adj;
+	enum { LOW_POWER, BETWEEN, HIGH_POWER } power;
+
 	struct delayed_work delayed_resume_work;
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6ee557280e11..418ad642c742 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -818,7 +818,7 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
 						    rps.work);
 	u32 pm_iir;
-	u8 new_delay;
+	int new_delay, adj;
 
 	spin_lock_irq(&dev_priv->irq_lock);
 	pm_iir = dev_priv->rps.pm_iir;
@@ -835,29 +835,49 @@ static void gen6_pm_rps_work(struct work_struct *work)
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
+	adj = dev_priv->rps.last_adj;
 	if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
-		new_delay = dev_priv->rps.cur_delay + 1;
+		if (adj > 0)
+			adj *= 2;
+		else
+			adj = 1;
+		new_delay = dev_priv->rps.cur_delay + adj;
 
 		/*
 		 * For better performance, jump directly
 		 * to RPe if we're below it.
 		 */
-		if (IS_VALLEYVIEW(dev_priv->dev) &&
-		    dev_priv->rps.cur_delay < dev_priv->rps.rpe_delay)
+		if (new_delay < dev_priv->rps.rpe_delay)
+			new_delay = dev_priv->rps.rpe_delay;
+	} else if (pm_iir & GEN6_PM_RP_DOWN_TIMEOUT) {
+		if (dev_priv->rps.cur_delay > dev_priv->rps.rpe_delay)
 			new_delay = dev_priv->rps.rpe_delay;
-	} else
-		new_delay = dev_priv->rps.cur_delay - 1;
+		else
+			new_delay = dev_priv->rps.min_delay;
+		adj = 0;
+	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
+		if (adj < 0)
+			adj *= 2;
+		else
+			adj = -1;
+		new_delay = dev_priv->rps.cur_delay + adj;
+	} else { /* unknown event */
+		new_delay = dev_priv->rps.cur_delay;
+	}
 
 	/* sysfs frequency interfaces may have snuck in while servicing the
 	 * interrupt
 	 */
-	if (new_delay >= dev_priv->rps.min_delay &&
-	    new_delay <= dev_priv->rps.max_delay) {
-		if (IS_VALLEYVIEW(dev_priv->dev))
-			valleyview_set_rps(dev_priv->dev, new_delay);
-		else
-			gen6_set_rps(dev_priv->dev, new_delay);
-	}
+	if (new_delay < (int)dev_priv->rps.min_delay)
+		new_delay = dev_priv->rps.min_delay;
+	if (new_delay > (int)dev_priv->rps.max_delay)
+		new_delay = dev_priv->rps.max_delay;
+	dev_priv->rps.last_adj = new_delay - dev_priv->rps.cur_delay;
+
+	if (IS_VALLEYVIEW(dev_priv->dev))
+		valleyview_set_rps(dev_priv->dev, new_delay);
+	else
+		gen6_set_rps(dev_priv->dev, new_delay);
 
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 96fd2ce6aa02..daaabe788f21 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4687,7 +4687,7 @@
 #define   GEN6_RP_UP_IDLE_MIN			(0x1<<3)
 #define   GEN6_RP_UP_BUSY_AVG			(0x2<<3)
 #define   GEN6_RP_UP_BUSY_CONT			(0x4<<3)
-#define   GEN7_RP_DOWN_IDLE_AVG			(0x2<<0)
+#define   GEN6_RP_DOWN_IDLE_AVG			(0x2<<0)
 #define   GEN6_RP_DOWN_IDLE_CONT		(0x1<<0)
 #define GEN6_RP_UP_THRESHOLD			0xA02C
 #define GEN6_RP_DOWN_THRESHOLD			0xA030
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ca063c25ad32..b08a96cd9c94 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3312,6 +3312,98 @@ static u32 gen6_rps_limits(struct drm_i915_private *dev_priv, u8 *val)
 	return limits;
 }
 
+static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
+{
+	int new_power;
+
+	new_power = dev_priv->rps.power;
+	switch (dev_priv->rps.power) {
+	case LOW_POWER:
+		if (val > dev_priv->rps.rpe_delay + 1 && val > dev_priv->rps.cur_delay)
+			new_power = BETWEEN;
+		break;
+
+	case BETWEEN:
+		if (val <= dev_priv->rps.rpe_delay && val < dev_priv->rps.cur_delay)
+			new_power = LOW_POWER;
+		else if (val >= dev_priv->rps.rp0_delay && val > dev_priv->rps.cur_delay)
+			new_power = HIGH_POWER;
+		break;
+
+	case HIGH_POWER:
+		if (val < (dev_priv->rps.rp1_delay + dev_priv->rps.rp0_delay) >> 1 && val < dev_priv->rps.cur_delay)
+			new_power = BETWEEN;
+		break;
+	}
+	/* Max/min bins are special */
+	if (val == dev_priv->rps.min_delay)
+		new_power = LOW_POWER;
+	if (val == dev_priv->rps.max_delay)
+		new_power = HIGH_POWER;
+	if (new_power == dev_priv->rps.power)
+		return;
+
+	/* Note the units here are not exactly 1us, but 1280ns. */
+	switch (new_power) {
+	case LOW_POWER:
+		/* Upclock if more than 95% busy over 16ms */
+		I915_WRITE(GEN6_RP_UP_EI, 12500);
+		I915_WRITE(GEN6_RP_UP_THRESHOLD, 11800);
+
+		/* Downclock if less than 85% busy over 32ms */
+		I915_WRITE(GEN6_RP_DOWN_EI, 25000);
+		I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 21250);
+
+		I915_WRITE(GEN6_RP_CONTROL,
+			   GEN6_RP_MEDIA_TURBO |
+			   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+			   GEN6_RP_MEDIA_IS_GFX |
+			   GEN6_RP_ENABLE |
+			   GEN6_RP_UP_BUSY_AVG |
+			   GEN6_RP_DOWN_IDLE_AVG);
+		break;
+
+	case BETWEEN:
+		/* Upclock if more than 90% busy over 13ms */
+		I915_WRITE(GEN6_RP_UP_EI, 10250);
+		I915_WRITE(GEN6_RP_UP_THRESHOLD, 9225);
+
+		/* Downclock if less than 75% busy over 32ms */
+		I915_WRITE(GEN6_RP_DOWN_EI, 25000);
+		I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 18750);
+
+		I915_WRITE(GEN6_RP_CONTROL,
+			   GEN6_RP_MEDIA_TURBO |
+			   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+			   GEN6_RP_MEDIA_IS_GFX |
+			   GEN6_RP_ENABLE |
+			   GEN6_RP_UP_BUSY_AVG |
+			   GEN6_RP_DOWN_IDLE_AVG);
+		break;
+
+	case HIGH_POWER:
+		/* Upclock if more than 85% busy over 10ms */
+		I915_WRITE(GEN6_RP_UP_EI, 8000);
+		I915_WRITE(GEN6_RP_UP_THRESHOLD, 6800);
+
+		/* Downclock if less than 60% busy over 32ms */
+		I915_WRITE(GEN6_RP_DOWN_EI, 25000);
+		I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 15000);
+
+		I915_WRITE(GEN6_RP_CONTROL,
+			   GEN6_RP_MEDIA_TURBO |
+			   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+			   GEN6_RP_MEDIA_IS_GFX |
+			   GEN6_RP_ENABLE |
+			   GEN6_RP_UP_BUSY_AVG |
+			   GEN6_RP_DOWN_IDLE_AVG);
+		break;
+	}
+
+	dev_priv->rps.power = new_power;
+	dev_priv->rps.last_adj = 0;
+}
+
 void gen6_set_rps(struct drm_device *dev, u8 val)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3324,6 +3416,8 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 	if (val == dev_priv->rps.cur_delay)
 		return;
 
+	gen6_set_rps_thresholds(dev_priv, val);
+
 	if (IS_HASWELL(dev))
 		I915_WRITE(GEN6_RPNSWREQ,
 			   HSW_FREQUENCY(val));
@@ -3352,6 +3446,7 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv)
 		valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
 	else
 		gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
+	dev_priv->rps.last_adj = 0;
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
@@ -3362,6 +3457,7 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv)
 		valleyview_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
 	else
 		gen6_set_rps(dev_priv->dev, dev_priv->rps.max_delay);
+	dev_priv->rps.last_adj = 0;
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
@@ -3546,7 +3642,10 @@ static void gen6_enable_rps(struct drm_device *dev)
 
 	/* In units of 50MHz */
 	dev_priv->rps.hw_max = dev_priv->rps.max_delay = rp_state_cap & 0xff;
-	dev_priv->rps.min_delay = (rp_state_cap & 0xff0000) >> 16;
+	dev_priv->rps.min_delay = (rp_state_cap >> 16) & 0xff;
+	dev_priv->rps.rp1_delay = (rp_state_cap >>  8) & 0xff;
+	dev_priv->rps.rp0_delay = (rp_state_cap >>  0) & 0xff;
+	dev_priv->rps.rpe_delay = dev_priv->rps.rp1_delay;
 	dev_priv->rps.cur_delay = 0;
 
 	/* disable the counters and set deterministic thresholds */
@@ -3594,38 +3693,9 @@ static void gen6_enable_rps(struct drm_device *dev)
 		   GEN6_RC_CTL_EI_MODE(1) |
 		   GEN6_RC_CTL_HW_ENABLE);
 
-	if (IS_HASWELL(dev)) {
-		I915_WRITE(GEN6_RPNSWREQ,
-			   HSW_FREQUENCY(10));
-		I915_WRITE(GEN6_RC_VIDEO_FREQ,
-			   HSW_FREQUENCY(12));
-	} else {
-		I915_WRITE(GEN6_RPNSWREQ,
-			   GEN6_FREQUENCY(10) |
-			   GEN6_OFFSET(0) |
-			   GEN6_AGGRESSIVE_TURBO);
-		I915_WRITE(GEN6_RC_VIDEO_FREQ,
-			   GEN6_FREQUENCY(12));
-	}
-
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
-	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
-		   dev_priv->rps.max_delay << 24 |
-		   dev_priv->rps.min_delay << 16);
-
-	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);
-
+	/* Power down if completely idle for over 50ms */
+	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 50000);
 	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-	I915_WRITE(GEN6_RP_CONTROL,
-		   GEN6_RP_MEDIA_TURBO |
-		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		   GEN6_RP_MEDIA_IS_GFX |
-		   GEN6_RP_ENABLE |
-		   GEN6_RP_UP_BUSY_AVG |
-		   (IS_HASWELL(dev) ? GEN7_RP_DOWN_IDLE_AVG : GEN6_RP_DOWN_IDLE_CONT));
 
 	ret = sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_MIN_FREQ_TABLE, 0);
 	if (!ret) {
@@ -3641,7 +3711,8 @@ static void gen6_enable_rps(struct drm_device *dev)
 		DRM_DEBUG_DRIVER("Failed to set the min frequency\n");
 	}
 
-	gen6_set_rps(dev_priv->dev, (gt_perf_status & 0xff00) >> 8);
+	dev_priv->rps.power = HIGH_POWER; /* force a reset */
+	gen6_set_rps(dev_priv->dev, dev_priv->rps.min_delay);
 
 	gen6_enable_rps_interrupts(dev);