[Intel-gfx] [PATCH 2/2] drm/i915: protect force_wake_(get|put) with the gt_lock

[Daniel Vetter]

We don't have any read in a fastpath that needs forcewake, so I've
decided to not care much about overhead.

This prevents tests/gem_hangcheck_forcewake from i-g-t from killing my
snb on recent kernels - something must have slightly changed the
timings.

Signed-Off-by: Daniel Vetter <daniel.vetter at ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c |    8 ++++++--
 drivers/gpu/drm/i915/i915_drv.c     |   19 +++++++++++++------
 drivers/gpu/drm/i915/i915_drv.h     |    3 ++-
 3 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 5ba63ad..51b21eb 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1320,9 +1320,13 @@ static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned forcewake_count;
 
-	seq_printf(m, "forcewake count = %d\n",
-		   atomic_read(&dev_priv->forcewake_count));
+	spin_lock_irq(&dev_priv->gt_lock);
+	forcewake_count = dev_priv->forcewake_count;
+	spin_unlock_irq(&dev_priv->gt_lock);
+
+	seq_printf(m, "forcewake count = %d\n", forcewake_count);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index cefc3b9..14753f5 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -351,11 +351,12 @@ static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
  */
 void gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
 {
-	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
+	unsigned long irqflags;
 
-	/* Forcewake is atomic in case we get in here without the lock */
-	if (atomic_add_return(1, &dev_priv->forcewake_count) == 1)
+	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
+	if (dev_priv->forcewake_count++ == 0)
 		__gen6_gt_force_wake_get(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 }
 
 static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
@@ -369,10 +370,13 @@ static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
  */
 void gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
 {
-	WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
 
-	if (atomic_dec_and_test(&dev_priv->forcewake_count))
+	if (--dev_priv->forcewake_count == 0)
 		__gen6_gt_force_wake_put(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 }
 
 void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
@@ -615,6 +619,7 @@ int i915_reset(struct drm_device *dev, u8 flags)
 	 * need to
 	 */
 	bool need_display = true;
+	unsigned long irqflags;
 	int ret;
 
 	if (!i915_try_reset)
@@ -633,8 +638,10 @@ int i915_reset(struct drm_device *dev, u8 flags)
 	case 6:
 		ret = gen6_do_reset(dev, flags);
 		/* If reset with a user forcewake, try to restore */
-		if (atomic_read(&dev_priv->forcewake_count))
+		spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
+		if (dev_priv->forcewake_count)
 			__gen6_gt_force_wake_get(dev_priv);
+		spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 		break;
 	case 5:
 		ret = ironlake_do_reset(dev, flags);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 74cf78e..cbac640 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -278,7 +278,8 @@ typedef struct drm_i915_private {
 	void __iomem *regs;
 	/** Concurrent writes to gt_fifo_count are protected by gt_lock */
 	atomic_t gt_fifo_count;
-	atomic_t forcewake_count;
+	/** forcewake_count is protected by gt_lock */
+	unsigned forcewake_count;
 	/** gt_lock is taking in irq contexts. */
 	struct spinlock gt_lock;
 
-- 
1.7.6.4