drm/i915: Separate out reset flags from the reset counter

In preparation for introducing a per-engine reset, we can first separate
the mixing of the reset state from the global reset counter.

The loss of atomicity in updating the reset state poses a small problem
for handling the waiters. For requests, this is solved by advancing the
seqno so that a waiter waking up after the reset knows the request is
complete. For pending flips, we still rely on the increment of the
global reset epoch (as well as the reset-in-progress flag) to signify
when the hardware was reset.

The advantage, now that we do not inspect the reset state during reset
itself i.e. we no longer emit requests during reset, is that we can use
the atomic updates of the state flags to ensure that only one reset
worker is active.

v2: Mika spotted that I transformed the i915_gem_wait_for_error() wakeup
into a waiter wakeup.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Arun Siluvery <arun.siluvery@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470414607-32453-6-git-send-email-arun.siluvery@linux.intel.com
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-7-chris@chris-wilson.co.uk

1 files changed, 5 insertions, 11 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 02c34d6996ea..47a676d859db 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1579,7 +1579,7 @@ static int i915_drm_resume(struct drm_device *dev)
 	mutex_lock(&dev->struct_mutex);
 	if (i915_gem_init_hw(dev)) {
 		DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
-		atomic_or(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
+		set_bit(I915_WEDGED, &dev_priv->gpu_error.flags);
 	}
 	mutex_unlock(&dev->struct_mutex);
 
@@ -1741,20 +1741,13 @@ int i915_reset(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 	struct i915_gpu_error *error = &dev_priv->gpu_error;
-	unsigned reset_counter;
 	int ret;
 
 	mutex_lock(&dev->struct_mutex);
 
 	/* Clear any previous failed attempts at recovery. Time to try again. */
-	atomic_andnot(I915_WEDGED, &error->reset_counter);
-
-	/* Clear the reset-in-progress flag and increment the reset epoch. */
-	reset_counter = atomic_inc_return(&error->reset_counter);
-	if (WARN_ON(__i915_reset_in_progress(reset_counter))) {
-		ret = -EIO;
-		goto error;
-	}
+	__clear_bit(I915_WEDGED, &error->flags);
+	error->reset_count++;
 
 	pr_notice("drm/i915: Resetting chip after gpu hang\n");
 
@@ -1791,6 +1784,7 @@ int i915_reset(struct drm_i915_private *dev_priv)
 		goto error;
 	}
 
+	clear_bit(I915_RESET_IN_PROGRESS, &error->flags);
 	mutex_unlock(&dev->struct_mutex);
 
 	/*
@@ -1805,7 +1799,7 @@ int i915_reset(struct drm_i915_private *dev_priv)
 	return 0;
 
 error:
-	atomic_or(I915_WEDGED, &error->reset_counter);
+	set_bit(I915_WEDGED, &error->flags);
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
 }