drm/i915: protect force_wake_(get|put) with the gt_lock

The problem this patch solves is that the forcewake accounting
necessary for register reads is protected by dev->struct_mutex. But the
hangcheck and error_capture code need to access registers without
grabbing this mutex because we hold it while waiting for the gpu.
So a new lock is required. Because currently the error_state capture
is called from the error irq handler and the hangcheck code runs from
a timer, it needs to be an irqsafe spinlock (note that the registers
used by the irq handler (neglecting the error handling part) only uses
registers that don't need the forcewake dance).

We could tune this down to a normal spinlock when we rework the
error_state capture and hangcheck code to run from a workqueue.  But
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. On previous kernels it only trigger a WARN about the broken
locking.

v2: Drop the previous patch for the register writes.

v3: Improve the commit message per Chris Wilson's suggestions.

Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Keith Packard <keithp@keithp.com>

1 files changed, 12 insertions, 6 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 46c36f5cafb1..bdf6a1b36223 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -368,11 +368,12 @@ void __gen6_gt_force_wake_mt_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)
 		dev_priv->display.force_wake_get(dev_priv);
+	spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 }
 
 void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
@@ -392,10 +393,12 @@ void __gen6_gt_force_wake_mt_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;
 
-	if (atomic_dec_and_test(&dev_priv->forcewake_count))
+	spin_lock_irqsave(&dev_priv->gt_lock, irqflags);
+	if (--dev_priv->forcewake_count == 0)
 		dev_priv->display.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)
@@ -626,6 +629,7 @@ int i915_reset(struct drm_device *dev, u8 flags)
 	 * need to
 	 */
 	bool need_display = true;
+	unsigned long irqflags;
 	int ret;
 
 	if (!i915_try_reset)
@@ -644,8 +648,10 @@ 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)
 			dev_priv->display.force_wake_get(dev_priv);
+		spin_unlock_irqrestore(&dev_priv->gt_lock, irqflags);
 		break;
 	case 5:
 		ret = ironlake_do_reset(dev, flags);