drm/i915: ILK + VT-d workaround

Idle the GPU before doing any unmaps. We know if VT-d is in use through
an exported variable from iommu code.

This should avoid a known HW issue.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Keith Packard <keithp@keithp.com>

drivers/char/agp/intel-gtt.c

@@ -923,6 +923,9 @@ static int intel_fake_agp_insert_entries(struct agp_memory *mem,
 {
 	int ret = -EINVAL;
 
+	if (intel_private.base.do_idle_maps)
+		return -ENODEV;
+
 	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 +988,9 @@ static int intel_fake_agp_remove_entries(struct agp_memory *mem,
 	if (mem->page_count == 0)
 		return 0;
 
+	if (intel_private.base.do_idle_maps)
+		return -ENODEV;
+
 	intel_gtt_clear_range(pg_start, mem->page_count);
 
 	if (intel_private.base.needs_dmar) {
@@ -1177,6 +1183,25 @@ static void gen6_cleanup(void)
 {
 }
 
+/* Certain Gen5 chipsets require require idling the GPU before
+ * unmapping anything from the GTT when VT-d is enabled.
+ */
+extern int intel_iommu_gfx_mapped;
+static inline int needs_idle_maps(void)
+{
+	const unsigned short gpu_devid = intel_private.pcidev->device;
+
+	/* Query intel_iommu to see if we need the workaround. Presumably that
+	 * was loaded first.
+	 */
+	if ((gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB ||
+	     gpu_devid == PCI_DEVICE_ID_INTEL_IRONLAKE_M_IG) &&
+	     intel_iommu_gfx_mapped)
+		return 1;
+
+	return 0;
+}
+
 static int i9xx_setup(void)
 {
 	u32 reg_addr;
@@ -1211,6 +1236,9 @@ static int i9xx_setup(void)
 		intel_private.gtt_bus_addr = reg_addr + gtt_offset;
 	}
 
+	if (needs_idle_maps());
+		intel_private.base.do_idle_maps = 1;
+
 	intel_i9xx_setup_flush();
 
 	return 0;

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -49,6 +49,28 @@ 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 (unlikely(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\n");
+			/* Wait a bit, in hopes it avoids the hang */
+			udelay(10);
+		}
+	}
+
+	return ret;
+}
+
+static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible)
+{
+	if (unlikely(dev_priv->mm.gtt->do_idle_maps))
+		dev_priv->mm.interruptible = interruptible;
+}
+
 void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -117,6 +139,12 @@ void i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj,
 
 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 interruptible;
+
+	interruptible = do_idling(dev_priv);
+
 	intel_gtt_clear_range(obj->gtt_space->start >> PAGE_SHIFT,
 			      obj->base.size >> PAGE_SHIFT);
 
@@ -124,4 +152,6 @@ 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, interruptible);
 }

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);