[PATCH] drm/i915: Ironlake GPU with VT-d fix

[Ben Widawsky <ben@bwidawsk.net>]

Under certain circumstances, an IOTLB flush never completes and the hardware
just locks up.  The fix is meant to idle the GPU both before and after
any map or unmap occurs.

It requires an additional IOMMU patch.

Cc: Dave Airlie <airlied@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Keith Packard <keithp@keithp.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/char/agp/intel-gtt.c        |   10 +++++++
 drivers/gpu/drm/i915/i915_gem.c     |    2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c |   50 +++++++++++++++++++++++++++++++++++
 include/drm/intel-gtt.h             |    2 +
 4 files changed, 63 insertions(+), 1 deletions(-)

diff --git a/drivers/char/agp/intel-gtt.c b/drivers/char/agp/intel-gtt.c
index 8515101..9d939f0 100644
--- a/drivers/char/agp/intel-gtt.c
+++ b/drivers/char/agp/intel-gtt.c
@@ -650,6 +650,7 @@ static void intel_gtt_cleanup(void)
 static int intel_gtt_init(void)
 {
 	u32 gtt_map_size;
+	const unsigned short gpu_devid = intel_private.pcidev->device;
 	int ret;
 
 	ret = intel_private.driver->setup();
@@ -688,6 +689,11 @@ static int intel_gtt_init(void)
 
 	intel_private.base.needs_dmar = USE_PCI_DMA_API && INTEL_GTT_GEN > 2;
 
+	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB ||
+	     gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
+	     intel_private.base.needs_dmar)
+		intel_private.base.do_idle_maps = 1;
+
 	ret = intel_gtt_setup_scratch_page();
 	if (ret != 0) {
 		intel_gtt_cleanup();
@@ -923,6 +929,8 @@ static int intel_fake_agp_insert_entries(struct agp_memory *mem,
 {
 	int ret = -EINVAL;
 
+	BUG_ON(intel_private.base.do_idle_maps);
+
 	if (intel_private.clear_fake_agp) {
 		int start = intel_private.base.stolen_size / PAGE_SIZE;
 		int end = intel_private.base.gtt_mappable_entries;
@@ -985,6 +993,8 @@ static int intel_fake_agp_remove_entries(struct agp_memory *mem,
 	if (mem->page_count == 0)
 		return 0;
 
+	BUG_ON(intel_private.base.do_idle_maps);
+
 	intel_gtt_clear_range(pg_start, mem->page_count);
 
 	if (intel_private.base.needs_dmar) {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a546a71..785b84a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2277,7 +2277,7 @@ i915_gpu_idle(struct drm_device *dev)
 
 	lists_empty = (list_empty(&dev_priv->mm.flushing_list) &&
 		       list_empty(&dev_priv->mm.active_list));
-	if (lists_empty)
+	if (lists_empty && !!dev_priv->mm.gtt->do_idle_maps)
 		return 0;
 
 	/* Flush everything onto the inactive list. */
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7a709cd..c11ec60 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -49,10 +49,41 @@ static unsigned int cache_level_to_agp_type(struct drm_device *dev,
 	}
 }
 
+static bool do_idling(struct drm_i915_private *dev_priv)
+{
+	bool ret = dev_priv->mm.interruptible;
+
+	if (dev_priv->mm.gtt->do_idle_maps) {
+		dev_priv->mm.interruptible = false;
+		if (i915_gpu_idle(dev_priv->dev))
+			DRM_ERROR("couldn't idle GPU %d\n", ret);
+	}
+
+	return ret;
+}
+
+static void undo_idling(struct drm_i915_private *dev_priv, bool idle)
+{
+	int ret;
+	if (!dev_priv->mm.gtt->do_idle_maps)
+		return;
+
+	/*NB: since GTT mappings don't actually touch the GPU, this is not
+	 * strictly necessary.
+	 */
+	ret = i915_gpu_idle(dev_priv->dev);
+	if (ret)
+		DRM_ERROR("couldn't idle GPU %d\n", ret);
+	dev_priv->mm.interruptible = idle;
+}
+
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
+	bool idle;
+
+	idle = do_idling(dev_priv);
 
 	/* First fill our portion of the GTT with scratch pages */
 	intel_gtt_clear_range(dev_priv->mm.gtt_start / PAGE_SIZE,
@@ -64,6 +95,8 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	}
 
 	intel_gtt_chipset_flush();
+
+	undo_idling(dev_priv, idle);
 }
 
 int i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj)
@@ -71,8 +104,11 @@ int i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj)
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned int agp_type = cache_level_to_agp_type(dev, obj->cache_level);
+	bool idle;
 	int ret;
 
+	idle = do_idling(dev_priv);
+
 	if (dev_priv->mm.gtt->needs_dmar) {
 		ret = intel_gtt_map_memory(obj->pages,
 					   obj->base.size >> PAGE_SHIFT,
@@ -91,6 +127,7 @@ int i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj)
 				       obj->pages,
 				       agp_type);
 
+	undo_idling(dev_priv, idle);
 	return 0;
 }
 
@@ -100,6 +137,9 @@ void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj,
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned int agp_type = cache_level_to_agp_type(dev, cache_level);
+	bool idle;
+
+	idle = do_idling(dev_priv);
 
 	if (dev_priv->mm.gtt->needs_dmar) {
 		BUG_ON(!obj->sg_list);
@@ -113,10 +153,18 @@ void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj,
 				       obj->base.size >> PAGE_SHIFT,
 				       obj->pages,
 				       agp_type);
+
+	undo_idling(dev_priv, idle);
 }
 
 void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 {
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	bool idle;
+
+	idle = do_idling(dev_priv);
+
 	intel_gtt_clear_range(obj->gtt_space->start >> PAGE_SHIFT,
 			      obj->base.size >> PAGE_SHIFT);
 
@@ -124,4 +172,6 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 		intel_gtt_unmap_memory(obj->sg_list, obj->num_sg);
 		obj->sg_list = NULL;
 	}
+
+	undo_idling(dev_priv, idle);
 }
diff --git a/include/drm/intel-gtt.h b/include/drm/intel-gtt.h
index 9e343c0..b174620 100644
--- a/include/drm/intel-gtt.h
+++ b/include/drm/intel-gtt.h
@@ -13,6 +13,8 @@ const struct intel_gtt {
 	unsigned int gtt_mappable_entries;
 	/* Whether i915 needs to use the dmar apis or not. */
 	unsigned int needs_dmar : 1;
+	/* Whether we idle the gpu before mapping/unmapping */
+	unsigned int do_idle_maps : 1;
 } *intel_gtt_get(void);
 
 void intel_gtt_chipset_flush(void);
-- 
1.7.6.3