[Intel-gfx] [PATCH] drm/i915: Restore fences after resume and GPU resets

[Chris Wilson]

Stéphane Marchesin found that fences for pinned objects (i.e. the
scanout) were not being restored upon resume, leading to corruption on
the display and reference counting issues. This is due to a bug in

commit 312817a39f17dbb4de000165b5b724e3728cd91c [2.6.38]
Author: Chris Wilson <chris at chris-wilson.co.uk>
Date:   Mon Nov 22 11:50:11 2010 +0000

    drm/i915: Only save and restore fences for UMS

that zapped the pinned fences even though they were in use.
Fortuitously, whilst we forced a VT switch during suspend and resume,
no fences were ever pinned at the time. However, we now can do
switchless S3 transitions and so the old bug finally surfaces.

Reported-by: Stéphane Marchesin <marcheu at chromium.org>
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter at ffwll.ch>
Cc: Stéphane Marchesin <marcheu at chromium.org>
---
 drivers/gpu/drm/i915/i915_drv.h     |    2 ++
 drivers/gpu/drm/i915/i915_gem.c     |   22 +++++-----------------
 drivers/gpu/drm/i915/i915_suspend.c |    1 +
 3 files changed, 8 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bacc2fe..1a67216 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1793,6 +1793,8 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 				struct drm_gem_object *gem_obj, int flags);
 
+void i915_gem_restore_fences(struct drm_device *dev);
+
 /* i915_gem_context.c */
 void i915_gem_context_init(struct drm_device *dev);
 void i915_gem_context_fini(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 61956a1..773c8f4 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2142,25 +2142,15 @@ static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv,
 		ring->sync_seqno[i] = 0;
 }
 
-static void i915_gem_reset_fences(struct drm_device *dev)
+void i915_gem_restore_fences(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
 	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
-
-		if (reg->obj)
-			i915_gem_object_fence_lost(reg->obj);
-
-		i915_gem_write_fence(dev, i, NULL);
-
-		reg->pin_count = 0;
-		reg->obj = NULL;
-		INIT_LIST_HEAD(&reg->lru_list);
+		i915_gem_write_fence(dev, i, reg->obj);
 	}
-
-	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
 }
 
 void i915_gem_reset(struct drm_device *dev)
@@ -2187,8 +2177,7 @@ void i915_gem_reset(struct drm_device *dev)
 		obj->base.read_domains &= ~I915_GEM_GPU_DOMAINS;
 	}
 
-	/* The fence registers are invalidated so clear them out */
-	i915_gem_reset_fences(dev);
+	i915_gem_restore_fences(dev);
 }
 
 /**
@@ -3922,8 +3911,6 @@ i915_gem_idle(struct drm_device *dev)
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		i915_gem_evict_everything(dev);
 
-	i915_gem_reset_fences(dev);
-
 	/* Hack!  Don't let anybody do execbuf while we don't control the chip.
 	 * We need to replace this with a semaphore, or something.
 	 * And not confound mm.suspended!
@@ -4259,7 +4246,8 @@ i915_gem_load(struct drm_device *dev)
 		dev_priv->num_fence_regs = 8;
 
 	/* Initialize fence registers to zero */
-	i915_gem_reset_fences(dev);
+	INIT_LIST_HEAD(&dev_priv->mm.fence_list);
+	i915_gem_restore_fences(dev);
 
 	i915_gem_detect_bit_6_swizzle(dev);
 	init_waitqueue_head(&dev_priv->pending_flip_queue);
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 88b9a66..70db618 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -394,6 +394,7 @@ int i915_restore_state(struct drm_device *dev)
 
 	mutex_lock(&dev->struct_mutex);
 
+	i915_gem_restore_fences(dev);
 	i915_restore_display(dev);
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET)) {
-- 
1.7.10.4