drm/i915: move gen6 rps handling to workqueue

The render P-state handling code requires reading from a GT register.
This means that FORCEWAKE must be written to, a resource which is shared
and should be protected by struct_mutex. Hence we can not manipulate
that register from within the interrupt handling and so must delegate
the task to a workqueue.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>

5 files changed, 58 insertions, 9 deletions

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 01ca0e97beb..b1ddcdc0748 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -2038,6 +2038,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 
 	spin_lock_init(&dev_priv->irq_lock);
 	spin_lock_init(&dev_priv->error_lock);
+	spin_lock_init(&dev_priv->rps_lock);
 
 	if (IS_MOBILE(dev) || !IS_GEN2(dev))
 		dev_priv->num_pipe = 2;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bafb387dd41..e9d824326a0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -682,6 +682,10 @@ typedef struct drm_i915_private {
 
 	bool mchbar_need_disable;
 
+	struct work_struct rps_work;
+	spinlock_t rps_lock;
+	u32 pm_iir;
+
 	u8 cur_delay;
 	u8 min_delay;
 	u8 max_delay;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index edd208e4730..5be2aa0f54a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -367,22 +367,30 @@ static void notify_ring(struct drm_device *dev,
 		  jiffies + msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD));
 }
 
-static void gen6_pm_irq_handler(struct drm_device *dev)
+static void gen6_pm_rps_work(struct work_struct *work)
 {
-	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
+						    rps_work);
 	u8 new_delay = dev_priv->cur_delay;
-	u32 pm_iir;
+	u32 pm_iir, pm_imr;
+
+	spin_lock_irq(&dev_priv->rps_lock);
+	pm_iir = dev_priv->pm_iir;
+	dev_priv->pm_iir = 0;
+	pm_imr = I915_READ(GEN6_PMIMR);
+	spin_unlock_irq(&dev_priv->rps_lock);
 
-	pm_iir = I915_READ(GEN6_PMIIR);
 	if (!pm_iir)
 		return;
 
+	mutex_lock(&dev_priv->dev->struct_mutex);
 	if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
 		if (dev_priv->cur_delay != dev_priv->max_delay)
 			new_delay = dev_priv->cur_delay + 1;
 		if (new_delay > dev_priv->max_delay)
 			new_delay = dev_priv->max_delay;
 	} else if (pm_iir & (GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT)) {
+		gen6_gt_force_wake_get(dev_priv);
 		if (dev_priv->cur_delay != dev_priv->min_delay)
 			new_delay = dev_priv->cur_delay - 1;
 		if (new_delay < dev_priv->min_delay) {
@@ -396,12 +404,19 @@ static void gen6_pm_irq_handler(struct drm_device *dev)
 			I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
 				   I915_READ(GEN6_RP_INTERRUPT_LIMITS) & ~0x3f0000);
 		}
+		gen6_gt_force_wake_put(dev_priv);
 	}
 
-	gen6_set_rps(dev, new_delay);
+	gen6_set_rps(dev_priv->dev, new_delay);
 	dev_priv->cur_delay = new_delay;
 
-	I915_WRITE(GEN6_PMIIR, pm_iir);
+	/*
+	 * rps_lock not held here because clearing is non-destructive. There is
+	 * an *extremely* unlikely race with gen6_rps_enable() that is prevented
+	 * by holding struct_mutex for the duration of the write.
+	 */
+	I915_WRITE(GEN6_PMIMR, pm_imr & ~pm_iir);
+	mutex_unlock(&dev_priv->dev->struct_mutex);
 }
 
 static void pch_irq_handler(struct drm_device *dev)
@@ -525,13 +540,30 @@ static irqreturn_t ironlake_irq_handler(struct drm_device *dev)
 		i915_handle_rps_change(dev);
 	}
 
-	if (IS_GEN6(dev))
-		gen6_pm_irq_handler(dev);
+	if (IS_GEN6(dev) && pm_iir & GEN6_PM_DEFERRED_EVENTS) {
+		/*
+		 * IIR bits should never already be set because IMR should
+		 * prevent an interrupt from being shown in IIR. The warning
+		 * displays a case where we've unsafely cleared
+		 * dev_priv->pm_iir. Although missing an interrupt of the same
+		 * type is not a problem, it displays a problem in the logic.
+		 *
+		 * The mask bit in IMR is cleared by rps_work.
+		 */
+		unsigned long flags;
+		spin_lock_irqsave(&dev_priv->rps_lock, flags);
+		WARN(dev_priv->pm_iir & pm_iir, "Missed a PM interrupt\n");
+		I915_WRITE(GEN6_PMIMR, pm_iir);
+		dev_priv->pm_iir |= pm_iir;
+		spin_unlock_irqrestore(&dev_priv->rps_lock, flags);
+		queue_work(dev_priv->wq, &dev_priv->rps_work);
+	}
 
 	/* should clear PCH hotplug event before clear CPU irq */
 	I915_WRITE(SDEIIR, pch_iir);
 	I915_WRITE(GTIIR, gt_iir);
 	I915_WRITE(DEIIR, de_iir);
+	I915_WRITE(GEN6_PMIIR, pm_iir);
 
 done:
 	I915_WRITE(DEIER, de_ier);
@@ -1658,6 +1690,7 @@ void i915_driver_irq_preinstall(struct drm_device * dev)
 
 	INIT_WORK(&dev_priv->hotplug_work, i915_hotplug_work_func);
 	INIT_WORK(&dev_priv->error_work, i915_error_work_func);
+	INIT_WORK(&dev_priv->rps_work, gen6_pm_rps_work);
 
 	if (HAS_PCH_SPLIT(dev)) {
 		ironlake_irq_preinstall(dev);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f39ac3a0fa9..289adaa9c92 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3386,7 +3386,7 @@
 #define GEN6_PMINTRMSK				0xA168
 
 #define GEN6_PMISR				0x44020
-#define GEN6_PMIMR				0x44024
+#define GEN6_PMIMR				0x44024 /* rps_lock */
 #define GEN6_PMIIR				0x44028
 #define GEN6_PMIER				0x4402C
 #define  GEN6_PM_MBOX_EVENT			(1<<25)
@@ -3396,6 +3396,9 @@
 #define  GEN6_PM_RP_DOWN_THRESHOLD		(1<<4)
 #define  GEN6_PM_RP_UP_EI_EXPIRED		(1<<2)
 #define  GEN6_PM_RP_DOWN_EI_EXPIRED		(1<<1)
+#define  GEN6_PM_DEFERRED_EVENTS		(GEN6_PM_RP_UP_THRESHOLD | \
+						 GEN6_PM_RP_DOWN_THRESHOLD | \
+						 GEN6_PM_RP_DOWN_TIMEOUT)
 
 #define GEN6_PCODE_MAILBOX			0x138124
 #define   GEN6_PCODE_READY			(1<<31)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5504ff2a109..784e52c6e19 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6876,6 +6876,11 @@ void gen6_disable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
 	I915_WRITE(GEN6_PMIER, 0);
+
+	spin_lock_irq(&dev_priv->rps_lock);
+	dev_priv->pm_iir = 0;
+	spin_unlock_irq(&dev_priv->rps_lock);
+
 	I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
 }
 
@@ -7078,7 +7083,10 @@ void gen6_enable_rps(struct drm_i915_private *dev_priv)
 		   GEN6_PM_RP_DOWN_THRESHOLD |
 		   GEN6_PM_RP_UP_EI_EXPIRED |
 		   GEN6_PM_RP_DOWN_EI_EXPIRED);
+	spin_lock_irq(&dev_priv->rps_lock);
+	WARN_ON(dev_priv->pm_iir != 0);
 	I915_WRITE(GEN6_PMIMR, 0);
+	spin_unlock_irq(&dev_priv->rps_lock);
 	/* enable all PM interrupts */
 	I915_WRITE(GEN6_PMINTRMSK, 0);