add commented out versions of unused functions present in the original

files to reduce the diff to linux.

4 files changed, 2072 insertions, 32 deletions

diff --git a/sys/dev/pci/drm/i915/i915_gem.c b/sys/dev/pci/drm/i915/i915_gem.c
index 0d83ee19abb..21f903171fb 100644
--- a/sys/dev/pci/drm/i915/i915_gem.c
+++ b/sys/dev/pci/drm/i915/i915_gem.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: i915_gem.c,v 1.31 2013/08/07 19:49:06 kettenis Exp $	*/
+/*	$OpenBSD: i915_gem.c,v 1.32 2013/08/09 07:55:42 jsg Exp $	*/
 /*
  * Copyright (c) 2008-2009 Owain G. Ainsworth <oga@openbsd.org>
  *
@@ -315,6 +315,252 @@ i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
 		obj->tiling_mode != I915_TILING_NONE;
 }
 
+#ifdef notyet
+static inline int
+__copy_to_user_swizzled(char __user *cpu_vaddr,
+			const char *gpu_vaddr, int gpu_offset,
+			int length)
+{
+	int ret, cpu_offset = 0;
+
+	while (length > 0) {
+		int cacheline_end = ALIGN(gpu_offset + 1, 64);
+		int this_length = min(cacheline_end - gpu_offset, length);
+		int swizzled_gpu_offset = gpu_offset ^ 64;
+
+		ret = __copy_to_user(cpu_vaddr + cpu_offset,
+				     gpu_vaddr + swizzled_gpu_offset,
+				     this_length);
+		if (ret)
+			return ret + length;
+
+		cpu_offset += this_length;
+		gpu_offset += this_length;
+		length -= this_length;
+	}
+
+	return 0;
+}
+
+static inline int
+__copy_from_user_swizzled(char *gpu_vaddr, int gpu_offset,
+			  const char __user *cpu_vaddr,
+			  int length)
+{
+	int ret, cpu_offset = 0;
+
+	while (length > 0) {
+		int cacheline_end = ALIGN(gpu_offset + 1, 64);
+		int this_length = min(cacheline_end - gpu_offset, length);
+		int swizzled_gpu_offset = gpu_offset ^ 64;
+
+		ret = __copy_from_user(gpu_vaddr + swizzled_gpu_offset,
+				       cpu_vaddr + cpu_offset,
+				       this_length);
+		if (ret)
+			return ret + length;
+
+		cpu_offset += this_length;
+		gpu_offset += this_length;
+		length -= this_length;
+	}
+
+	return 0;
+}
+
+/* Per-page copy function for the shmem pread fastpath.
+ * Flushes invalid cachelines before reading the target if
+ * needs_clflush is set. */
+static int
+shmem_pread_fast(struct page *page, int shmem_page_offset, int page_length,
+		 char __user *user_data,
+		 bool page_do_bit17_swizzling, bool needs_clflush)
+{
+	char *vaddr;
+	int ret;
+
+	if (unlikely(page_do_bit17_swizzling))
+		return -EINVAL;
+
+	vaddr = kmap_atomic(page);
+	if (needs_clflush)
+		drm_clflush_virt_range(vaddr + shmem_page_offset,
+				       page_length);
+	ret = __copy_to_user_inatomic(user_data,
+				      vaddr + shmem_page_offset,
+				      page_length);
+	kunmap_atomic(vaddr);
+
+	return ret ? -EFAULT : 0;
+}
+
+static void
+shmem_clflush_swizzled_range(char *addr, unsigned long length,
+			     bool swizzled)
+{
+	if (unlikely(swizzled)) {
+		unsigned long start = (unsigned long) addr;
+		unsigned long end = (unsigned long) addr + length;
+
+		/* For swizzling simply ensure that we always flush both
+		 * channels. Lame, but simple and it works. Swizzled
+		 * pwrite/pread is far from a hotpath - current userspace
+		 * doesn't use it at all. */
+		start = round_down(start, 128);
+		end = round_up(end, 128);
+
+		drm_clflush_virt_range((void *)start, end - start);
+	} else {
+		drm_clflush_virt_range(addr, length);
+	}
+
+}
+
+/* Only difference to the fast-path function is that this can handle bit17
+ * and uses non-atomic copy and kmap functions. */
+static int
+shmem_pread_slow(struct page *page, int shmem_page_offset, int page_length,
+		 char __user *user_data,
+		 bool page_do_bit17_swizzling, bool needs_clflush)
+{
+	char *vaddr;
+	int ret;
+
+	vaddr = kmap(page);
+	if (needs_clflush)
+		shmem_clflush_swizzled_range(vaddr + shmem_page_offset,
+					     page_length,
+					     page_do_bit17_swizzling);
+
+	if (page_do_bit17_swizzling)
+		ret = __copy_to_user_swizzled(user_data,
+					      vaddr, shmem_page_offset,
+					      page_length);
+	else
+		ret = __copy_to_user(user_data,
+				     vaddr + shmem_page_offset,
+				     page_length);
+	kunmap(page);
+
+	return ret ? - EFAULT : 0;
+}
+
+static int
+i915_gem_shmem_pread(struct drm_device *dev,
+		     struct drm_i915_gem_object *obj,
+		     struct drm_i915_gem_pread *args,
+		     struct drm_file *file)
+{
+	char __user *user_data;
+	ssize_t remain;
+	loff_t offset;
+	int shmem_page_offset, page_length, ret = 0;
+	int obj_do_bit17_swizzling, page_do_bit17_swizzling;
+	int hit_slowpath = 0;
+	int prefaulted = 0;
+	int needs_clflush = 0;
+	struct scatterlist *sg;
+	int i;
+
+	user_data = (char __user *) (uintptr_t) args->data_ptr;
+	remain = args->size;
+
+	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
+
+	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)) {
+		/* If we're not in the cpu read domain, set ourself into the gtt
+		 * read domain and manually flush cachelines (if required). This
+		 * optimizes for the case when the gpu will dirty the data
+		 * anyway again before the next pread happens. */
+		if (obj->cache_level == I915_CACHE_NONE)
+			needs_clflush = 1;
+		if (obj->gtt_space) {
+			ret = i915_gem_object_set_to_gtt_domain(obj, false);
+			if (ret)
+				return ret;
+		}
+	}
+
+	ret = i915_gem_object_get_pages(obj);
+	if (ret)
+		return ret;
+
+	i915_gem_object_pin_pages(obj);
+
+	offset = args->offset;
+
+	for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) {
+		struct page *page;
+
+		if (i < offset >> PAGE_SHIFT)
+			continue;
+
+		if (remain <= 0)
+			break;
+
+		/* Operation in this page
+		 *
+		 * shmem_page_offset = offset within page in shmem file
+		 * page_length = bytes to copy for this page
+		 */
+		shmem_page_offset = offset_in_page(offset);
+		page_length = remain;
+		if ((shmem_page_offset + page_length) > PAGE_SIZE)
+			page_length = PAGE_SIZE - shmem_page_offset;
+
+		page = sg_page(sg);
+		page_do_bit17_swizzling = obj_do_bit17_swizzling &&
+			(page_to_phys(page) & (1 << 17)) != 0;
+
+		ret = shmem_pread_fast(page, shmem_page_offset, page_length,
+				       user_data, page_do_bit17_swizzling,
+				       needs_clflush);
+		if (ret == 0)
+			goto next_page;
+
+		hit_slowpath = 1;
+		mutex_unlock(&dev->struct_mutex);
+
+		if (!prefaulted) {
+			ret = fault_in_multipages_writeable(user_data, remain);
+			/* Userspace is tricking us, but we've already clobbered
+			 * its pages with the prefault and promised to write the
+			 * data up to the first fault. Hence ignore any errors
+			 * and just continue. */
+			(void)ret;
+			prefaulted = 1;
+		}
+
+		ret = shmem_pread_slow(page, shmem_page_offset, page_length,
+				       user_data, page_do_bit17_swizzling,
+				       needs_clflush);
+
+		mutex_lock(&dev->struct_mutex);
+
+next_page:
+		mark_page_accessed(page);
+
+		if (ret)
+			goto out;
+
+		remain -= page_length;
+		user_data += page_length;
+		offset += page_length;
+	}
+
+out:
+	i915_gem_object_unpin_pages(obj);
+
+	if (hit_slowpath) {
+		/* Fixup: Kill any reinstated backing storage pages */
+		if (obj->madv == __I915_MADV_PURGED)
+			i915_gem_object_truncate(obj);
+	}
+
+	return ret;
+}
+#endif /* notyet */
+
 /**
  * Reads data from the object referenced by handle.
  *
@@ -382,6 +628,295 @@ out:
 	return ret;
 }
 
+#ifdef notyet
+/* This is the fast write path which cannot handle
+ * page faults in the source data
+ */
+
+static inline int
+fast_user_write(struct io_mapping *mapping,
+		loff_t page_base, int page_offset,
+		char __user *user_data,
+		int length)
+{
+	void __iomem *vaddr_atomic;
+	void *vaddr;
+	unsigned long unwritten;
+
+	vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base);
+	/* We can use the cpu mem copy function because this is X86. */
+	vaddr = (void __force*)vaddr_atomic + page_offset;
+	unwritten = __copy_from_user_inatomic_nocache(vaddr,
+						      user_data, length);
+	io_mapping_unmap_atomic(vaddr_atomic);
+	return unwritten;
+}
+
+/**
+ * This is the fast pwrite path, where we copy the data directly from the
+ * user into the GTT, uncached.
+ */
+static int
+i915_gem_gtt_pwrite_fast(struct drm_device *dev,
+			 struct drm_i915_gem_object *obj,
+			 struct drm_i915_gem_pwrite *args,
+			 struct drm_file *file)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	ssize_t remain;
+	loff_t offset, page_base;
+	char __user *user_data;
+	int page_offset, page_length, ret;
+
+	ret = i915_gem_object_pin(obj, 0, true, true);
+	if (ret)
+		goto out;
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, true);
+	if (ret)
+		goto out_unpin;
+
+	ret = i915_gem_object_put_fence(obj);
+	if (ret)
+		goto out_unpin;
+
+	user_data = (char __user *) (uintptr_t) args->data_ptr;
+	remain = args->size;
+
+	offset = obj->gtt_offset + args->offset;
+
+	while (remain > 0) {
+		/* Operation in this page
+		 *
+		 * page_base = page offset within aperture
+		 * page_offset = offset within page
+		 * page_length = bytes to copy for this page
+		 */
+		page_base = offset & PAGE_MASK;
+		page_offset = offset_in_page(offset);
+		page_length = remain;
+		if ((page_offset + remain) > PAGE_SIZE)
+			page_length = PAGE_SIZE - page_offset;
+
+		/* If we get a fault while copying data, then (presumably) our
+		 * source page isn't available.  Return the error and we'll
+		 * retry in the slow path.
+		 */
+		if (fast_user_write(dev_priv->mm.gtt_mapping, page_base,
+				    page_offset, user_data, page_length)) {
+			ret = -EFAULT;
+			goto out_unpin;
+		}
+
+		remain -= page_length;
+		user_data += page_length;
+		offset += page_length;
+	}
+
+out_unpin:
+	i915_gem_object_unpin(obj);
+out:
+	return ret;
+}
+
+/* Per-page copy function for the shmem pwrite fastpath.
+ * Flushes invalid cachelines before writing to the target if
+ * needs_clflush_before is set and flushes out any written cachelines after
+ * writing if needs_clflush is set. */
+static int
+shmem_pwrite_fast(struct page *page, int shmem_page_offset, int page_length,
+		  char __user *user_data,
+		  bool page_do_bit17_swizzling,
+		  bool needs_clflush_before,
+		  bool needs_clflush_after)
+{
+	char *vaddr;
+	int ret;
+
+	if (unlikely(page_do_bit17_swizzling))
+		return -EINVAL;
+
+	vaddr = kmap_atomic(page);
+	if (needs_clflush_before)
+		drm_clflush_virt_range(vaddr + shmem_page_offset,
+				       page_length);
+	ret = __copy_from_user_inatomic_nocache(vaddr + shmem_page_offset,
+						user_data,
+						page_length);
+	if (needs_clflush_after)
+		drm_clflush_virt_range(vaddr + shmem_page_offset,
+				       page_length);
+	kunmap_atomic(vaddr);
+
+	return ret ? -EFAULT : 0;
+}
+
+/* Only difference to the fast-path function is that this can handle bit17
+ * and uses non-atomic copy and kmap functions. */
+static int
+shmem_pwrite_slow(struct page *page, int shmem_page_offset, int page_length,
+		  char __user *user_data,
+		  bool page_do_bit17_swizzling,
+		  bool needs_clflush_before,
+		  bool needs_clflush_after)
+{
+	char *vaddr;
+	int ret;
+
+	vaddr = kmap(page);
+	if (unlikely(needs_clflush_before || page_do_bit17_swizzling))
+		shmem_clflush_swizzled_range(vaddr + shmem_page_offset,
+					     page_length,
+					     page_do_bit17_swizzling);
+	if (page_do_bit17_swizzling)
+		ret = __copy_from_user_swizzled(vaddr, shmem_page_offset,
+						user_data,
+						page_length);
+	else
+		ret = __copy_from_user(vaddr + shmem_page_offset,
+				       user_data,
+				       page_length);
+	if (needs_clflush_after)
+		shmem_clflush_swizzled_range(vaddr + shmem_page_offset,
+					     page_length,
+					     page_do_bit17_swizzling);
+	kunmap(page);
+
+	return ret ? -EFAULT : 0;
+}
+
+static int
+i915_gem_shmem_pwrite(struct drm_device *dev,
+		      struct drm_i915_gem_object *obj,
+		      struct drm_i915_gem_pwrite *args,
+		      struct drm_file *file)
+{
+	ssize_t remain;
+	loff_t offset;
+	char __user *user_data;
+	int shmem_page_offset, page_length, ret = 0;
+	int obj_do_bit17_swizzling, page_do_bit17_swizzling;
+	int hit_slowpath = 0;
+	int needs_clflush_after = 0;
+	int needs_clflush_before = 0;
+	int i;
+	struct scatterlist *sg;
+
+	user_data = (char __user *) (uintptr_t) args->data_ptr;
+	remain = args->size;
+
+	obj_do_bit17_swizzling = i915_gem_object_needs_bit17_swizzle(obj);
+
+	if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+		/* If we're not in the cpu write domain, set ourself into the gtt
+		 * write domain and manually flush cachelines (if required). This
+		 * optimizes for the case when the gpu will use the data
+		 * right away and we therefore have to clflush anyway. */
+		if (obj->cache_level == I915_CACHE_NONE)
+			needs_clflush_after = 1;
+		if (obj->gtt_space) {
+			ret = i915_gem_object_set_to_gtt_domain(obj, true);
+			if (ret)
+				return ret;
+		}
+	}
+	/* Same trick applies for invalidate partially written cachelines before
+	 * writing.  */
+	if (!(obj->base.read_domains & I915_GEM_DOMAIN_CPU)
+	    && obj->cache_level == I915_CACHE_NONE)
+		needs_clflush_before = 1;
+
+	ret = i915_gem_object_get_pages(obj);
+	if (ret)
+		return ret;
+
+	i915_gem_object_pin_pages(obj);
+
+	offset = args->offset;
+	obj->dirty = 1;
+
+	for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) {
+		struct page *page;
+		int partial_cacheline_write;
+
+		if (i < offset >> PAGE_SHIFT)
+			continue;
+
+		if (remain <= 0)
+			break;
+
+		/* Operation in this page
+		 *
+		 * shmem_page_offset = offset within page in shmem file
+		 * page_length = bytes to copy for this page
+		 */
+		shmem_page_offset = offset_in_page(offset);
+
+		page_length = remain;
+		if ((shmem_page_offset + page_length) > PAGE_SIZE)
+			page_length = PAGE_SIZE - shmem_page_offset;
+
+		/* If we don't overwrite a cacheline completely we need to be
+		 * careful to have up-to-date data by first clflushing. Don't
+		 * overcomplicate things and flush the entire patch. */
+		partial_cacheline_write = needs_clflush_before &&
+			((shmem_page_offset | page_length)
+				& (boot_cpu_data.x86_clflush_size - 1));
+
+		page = sg_page(sg);
+		page_do_bit17_swizzling = obj_do_bit17_swizzling &&
+			(page_to_phys(page) & (1 << 17)) != 0;
+
+		ret = shmem_pwrite_fast(page, shmem_page_offset, page_length,
+					user_data, page_do_bit17_swizzling,
+					partial_cacheline_write,
+					needs_clflush_after);
+		if (ret == 0)
+			goto next_page;
+
+		hit_slowpath = 1;
+		mutex_unlock(&dev->struct_mutex);
+		ret = shmem_pwrite_slow(page, shmem_page_offset, page_length,
+					user_data, page_do_bit17_swizzling,
+					partial_cacheline_write,
+					needs_clflush_after);
+
+		mutex_lock(&dev->struct_mutex);
+
+next_page:
+		set_page_dirty(page);
+		mark_page_accessed(page);
+
+		if (ret)
+			goto out;
+
+		remain -= page_length;
+		user_data += page_length;
+		offset += page_length;
+	}
+
+out:
+	i915_gem_object_unpin_pages(obj);
+
+	if (hit_slowpath) {
+		/* Fixup: Kill any reinstated backing storage pages */
+		if (obj->madv == __I915_MADV_PURGED)
+			i915_gem_object_truncate(obj);
+		/* and flush dirty cachelines in case the object isn't in the cpu write
+		 * domain anymore. */
+		if (obj->base.write_domain != I915_GEM_DOMAIN_CPU) {
+			i915_gem_clflush_object(obj);
+			i915_gem_chipset_flush(dev);
+		}
+	}
+
+	if (needs_clflush_after)
+		i915_gem_chipset_flush(dev);
+
+	return ret;
+}
+#endif /* notyet */
+
 /**
  * Writes data to the object referenced by handle.
  *
@@ -1241,9 +1776,57 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
-// __i915_gem_shrink
-// i915_gem_purge
-// i915_gem_shrink_all
+#ifdef notyet
+static long
+__i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
+		  bool purgeable_only)
+{
+	struct drm_i915_gem_object *obj, *next;
+	long count = 0;
+
+	list_for_each_entry_safe(obj, next,
+				 &dev_priv->mm.unbound_list,
+				 gtt_list) {
+		if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
+		    i915_gem_object_put_pages(obj) == 0) {
+			count += obj->base.size >> PAGE_SHIFT;
+			if (count >= target)
+				return count;
+		}
+	}
+
+	list_for_each_entry_safe(obj, next,
+				 &dev_priv->mm.inactive_list,
+				 mm_list) {
+		if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
+		    i915_gem_object_unbind(obj) == 0 &&
+		    i915_gem_object_put_pages(obj) == 0) {
+			count += obj->base.size >> PAGE_SHIFT;
+			if (count >= target)
+				return count;
+		}
+	}
+
+	return count;
+}
+
+static long
+i915_gem_purge(struct drm_i915_private *dev_priv, long target)
+{
+	return __i915_gem_shrink(dev_priv, target, true);
+}
+
+static void
+i915_gem_shrink_all(struct drm_i915_private *dev_priv)
+{
+	struct drm_i915_gem_object *obj, *next;
+
+	i915_gem_evict_everything(dev_priv->dev);
+
+	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list, gtt_list)
+		i915_gem_object_put_pages(obj);
+}
+#endif /* notyet */
 
 int
 i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj)
@@ -1804,7 +2387,91 @@ i915_gem_object_flush_active(struct drm_i915_gem_object *obj)
 	return 0;
 }
 
-// i915_gem_wait_ioctl
+#ifdef notyet
+/**
+ * i915_gem_wait_ioctl - implements DRM_IOCTL_I915_GEM_WAIT
+ * @DRM_IOCTL_ARGS: standard ioctl arguments
+ *
+ * Returns 0 if successful, else an error is returned with the remaining time in
+ * the timeout parameter.
+ *  -ETIME: object is still busy after timeout
+ *  -ERESTARTSYS: signal interrupted the wait
+ *  -ENONENT: object doesn't exist
+ * Also possible, but rare:
+ *  -EAGAIN: GPU wedged
+ *  -ENOMEM: damn
+ *  -ENODEV: Internal IRQ fail
+ *  -E?: The add request failed
+ *
+ * The wait ioctl with a timeout of 0 reimplements the busy ioctl. With any
+ * non-zero timeout parameter the wait ioctl will wait for the given number of
+ * nanoseconds on an object becoming unbusy. Since the wait itself does so
+ * without holding struct_mutex the object may become re-busied before this
+ * function completes. A similar but shorter * race condition exists in the busy
+ * ioctl
+ */
+int
+i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_i915_gem_wait *args = data;
+	struct drm_i915_gem_object *obj;
+	struct intel_ring_buffer *ring = NULL;
+	struct timespec timeout_stack, *timeout = NULL;
+	u32 seqno = 0;
+	int ret = 0;
+
+	if (args->timeout_ns >= 0) {
+		timeout_stack = ns_to_timespec(args->timeout_ns);
+		timeout = &timeout_stack;
+	}
+
+	ret = i915_mutex_lock_interruptible(dev);
+	if (ret)
+		return ret;
+
+	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->bo_handle));
+	if (&obj->base == NULL) {
+		mutex_unlock(&dev->struct_mutex);
+		return -ENOENT;
+	}
+
+	/* Need to make sure the object gets inactive eventually. */
+	ret = i915_gem_object_flush_active(obj);
+	if (ret)
+		goto out;
+
+	if (obj->active) {
+		seqno = obj->last_read_seqno;
+		ring = obj->ring;
+	}
+
+	if (seqno == 0)
+		 goto out;
+
+	/* Do this after OLR check to make sure we make forward progress polling
+	 * on this IOCTL with a 0 timeout (like busy ioctl)
+	 */
+	if (!args->timeout_ns) {
+		ret = -ETIME;
+		goto out;
+	}
+
+	drm_gem_object_unreference(&obj->base);
+	mutex_unlock(&dev->struct_mutex);
+
+	ret = __wait_seqno(ring, seqno, true, timeout);
+	if (timeout) {
+		WARN_ON(!timespec_valid(timeout));
+		args->timeout_ns = timespec_to_ns(timeout);
+	}
+	return ret;
+
+out:
+	drm_gem_object_unreference(&obj->base);
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+#endif /* notyet */
 
 /**
  * i915_gem_object_sync - sync an object to a ring.
@@ -3061,7 +3728,14 @@ unlock:
 	return ret;
 }
 
-// i915_gem_throttle_ioctl
+#ifdef notyet
+int
+i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
+{
+	return i915_gem_ring_throttle(dev, file_priv);
+}
+#endif
 
 int
 i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
@@ -3247,7 +3921,39 @@ i915_gem_idle(struct drm_device *dev)
 	return 0;
 }
 
-// i915_gem_l3_remap
+#ifdef notyet
+void i915_gem_l3_remap(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	u32 misccpctl;
+	int i;
+
+	if (!HAS_L3_GPU_CACHE(dev))
+		return;
+
+	if (!dev_priv->l3_parity.remap_info)
+		return;
+
+	misccpctl = I915_READ(GEN7_MISCCPCTL);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
+	POSTING_READ(GEN7_MISCCPCTL);
+
+	for (i = 0; i < GEN7_L3LOG_SIZE; i += 4) {
+		u32 remap = I915_READ(GEN7_L3LOG_BASE + i);
+		if (remap && remap != dev_priv->l3_parity.remap_info[i/4])
+			DRM_DEBUG("0x%x was already programmed to %x\n",
+				  GEN7_L3LOG_BASE + i, remap);
+		if (remap && !dev_priv->l3_parity.remap_info[i/4])
+			DRM_DEBUG_DRIVER("Clearing remapped register\n");
+		I915_WRITE(GEN7_L3LOG_BASE + i, dev_priv->l3_parity.remap_info[i/4]);
+	}
+
+	/* Make sure all the writes land before disabling dop clock gating */
+	POSTING_READ(GEN7_L3LOG_BASE);
+
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+}
+#endif /* notyet */
 
 void
 i915_gem_init_swizzling(struct drm_device *dev)
@@ -3343,7 +4049,22 @@ cleanup_render_ring:
 	return ret;
 }
 
-// intel_enable_ppgtt
+#ifdef notyet
+static bool
+intel_enable_ppgtt(struct drm_device *dev)
+{
+	if (i915_enable_ppgtt >= 0)
+		return i915_enable_ppgtt;
+
+#ifdef CONFIG_INTEL_IOMMU
+	/* Disable ppgtt on SNB if VT-d is on. */
+	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped)
+		return false;
+#endif
+
+	return true;
+}
+#endif /* notyet */
 
 int
 i915_gem_init(struct drm_device *dev)
@@ -3454,7 +4175,20 @@ i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
 	return i915_gem_idle(dev);
 }
 
-// i915_gem_lastclose
+#ifdef notyet
+void
+i915_gem_lastclose(struct drm_device *dev)
+{
+	int ret;
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	ret = i915_gem_idle(dev);
+	if (ret)
+		DRM_ERROR("failed to idle hardware: %d\n", ret);
+}
+#endif /* notyet */
 
 void
 init_ring_lists(struct intel_ring_buffer *ring)
@@ -3554,8 +4288,36 @@ kfree_obj:
 	return ret;
 }
 
-// i915_gem_free_phys_object
-// i915_gem_free_all_phys_object
+#ifdef notyet
+static void i915_gem_free_phys_object(struct drm_device *dev, int id)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_phys_object *phys_obj;
+
+	if (!dev_priv->mm.phys_objs[id - 1])
+		return;
+
+	phys_obj = dev_priv->mm.phys_objs[id - 1];
+	if (phys_obj->cur_obj) {
+		i915_gem_detach_phys_object(dev, phys_obj->cur_obj);
+	}
+
+#ifdef CONFIG_X86
+	set_memory_wb((unsigned long)phys_obj->handle->vaddr, phys_obj->handle->size / PAGE_SIZE);
+#endif
+	drm_pci_free(dev, phys_obj->handle);
+	kfree(phys_obj);
+	dev_priv->mm.phys_objs[id - 1] = NULL;
+}
+
+void i915_gem_free_all_phys_object(struct drm_device *dev)
+{
+	int i;
+
+	for (i = I915_GEM_PHYS_CURSOR_0; i <= I915_MAX_PHYS_OBJECT; i++)
+		i915_gem_free_phys_object(dev, i);
+}
+#endif /* notyet */
 
 void i915_gem_detach_phys_object(struct drm_device *dev,
 				 struct drm_i915_gem_object *obj)
@@ -3689,5 +4451,62 @@ i915_gem_release(struct drm_device *dev, struct drm_file *file)
 	mtx_leave(&file_priv->mm.lock);
 }
 
-// mutex_is_locked_by
-// i915_gem_inactive_shrink
+#ifdef notyet
+static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
+{
+	if (!mutex_is_locked(mutex))
+		return false;
+
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+	return mutex->owner == task;
+#else
+	/* Since UP may be pre-empted, we cannot assume that we own the lock */
+	return false;
+#endif
+}
+
+static int
+i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(shrinker,
+			     struct drm_i915_private,
+			     mm.inactive_shrinker);
+	struct drm_device *dev = dev_priv->dev;
+	struct drm_i915_gem_object *obj;
+	int nr_to_scan = sc->nr_to_scan;
+	bool unlock = true;
+	int cnt;
+
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		if (!mutex_is_locked_by(&dev->struct_mutex, current))
+			return 0;
+
+		if (dev_priv->mm.shrinker_no_lock_stealing)
+			return 0;
+
+		unlock = false;
+	}
+
+	if (nr_to_scan) {
+		nr_to_scan -= i915_gem_purge(dev_priv, nr_to_scan);
+		if (nr_to_scan > 0)
+			nr_to_scan -= __i915_gem_shrink(dev_priv, nr_to_scan,
+							false);
+		if (nr_to_scan > 0)
+			i915_gem_shrink_all(dev_priv);
+	}
+
+	cnt = 0;
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, gtt_list)
+		if (obj->pages_pin_count == 0)
+			cnt += obj->base.size >> PAGE_SHIFT;
+	list_for_each_entry(obj, &dev_priv->mm.inactive_list, gtt_list)
+		if (obj->pin_count == 0 && obj->pages_pin_count == 0)
+			cnt += obj->base.size >> PAGE_SHIFT;
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+	return cnt;
+}
+#endif /* notyet */
diff --git a/sys/dev/pci/drm/i915/i915_gem_execbuffer.c b/sys/dev/pci/drm/i915/i915_gem_execbuffer.c
index 4331121c238..2646f5c25a1 100644
--- a/sys/dev/pci/drm/i915/i915_gem_execbuffer.c
+++ b/sys/dev/pci/drm/i915/i915_gem_execbuffer.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: i915_gem_execbuffer.c,v 1.10 2013/08/08 21:35:56 kettenis Exp $	*/
+/*	$OpenBSD: i915_gem_execbuffer.c,v 1.11 2013/08/09 07:55:42 jsg Exp $	*/
 /*
  * Copyright (c) 2008-2009 Owain G. Ainsworth <oga@openbsd.org>
  *
@@ -66,12 +66,66 @@ int	need_reloc_mappable(struct drm_i915_gem_object *);
 int	i915_gem_execbuffer_reserve(struct intel_ring_buffer *,
 	    struct drm_file *, struct list_head *);
 
-// struct eb_objects {
-// eb_create
-// eb_reset
-// eb_add_object
-// eb_get_object
-// eb_destroy
+#ifdef notyet
+struct eb_objects {
+	int and;
+	struct hlist_head buckets[0];
+};
+
+static struct eb_objects *
+eb_create(int size)
+{
+	struct eb_objects *eb;
+	int count = PAGE_SIZE / sizeof(struct hlist_head) / 2;
+	BUILD_BUG_ON_NOT_POWER_OF_2(PAGE_SIZE / sizeof(struct hlist_head));
+	while (count > size)
+		count >>= 1;
+	eb = kzalloc(count*sizeof(struct hlist_head) +
+		     sizeof(struct eb_objects),
+		     GFP_KERNEL);
+	if (eb == NULL)
+		return eb;
+
+	eb->and = count - 1;
+	return eb;
+}
+
+static void
+eb_reset(struct eb_objects *eb)
+{
+	memset(eb->buckets, 0, (eb->and+1)*sizeof(struct hlist_head));
+}
+
+static void
+eb_add_object(struct eb_objects *eb, struct drm_i915_gem_object *obj)
+{
+	hlist_add_head(&obj->exec_node,
+		       &eb->buckets[obj->exec_handle & eb->and]);
+}
+
+static struct drm_i915_gem_object *
+eb_get_object(struct eb_objects *eb, unsigned long handle)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct drm_i915_gem_object *obj;
+
+	head = &eb->buckets[handle & eb->and];
+	hlist_for_each(node, head) {
+		obj = hlist_entry(node, struct drm_i915_gem_object, exec_node);
+		if (obj->exec_handle == handle)
+			return obj;
+	}
+
+	return NULL;
+}
+
+static void
+eb_destroy(struct eb_objects *eb)
+{
+	kfree(eb);
+}
+#endif /* notyet */
 
 static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 {
@@ -80,10 +134,231 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 		obj->cache_level != I915_CACHE_NONE);
 }
 
-// i915_gem_execbuffer_relocate_entry
-// i915_gem_execbuffer_relocate_object
-// i915_gem_execbuffer_relocate_object_slow
-// i915_gem_execbuffer_relocate
+#ifdef notyet
+static int
+i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
+				   struct eb_objects *eb,
+				   struct drm_i915_gem_relocation_entry *reloc)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_gem_object *target_obj;
+	struct drm_i915_gem_object *target_i915_obj;
+	uint32_t target_offset;
+	int ret = -EINVAL;
+
+	/* we've already hold a reference to all valid objects */
+	target_obj = &eb_get_object(eb, reloc->target_handle)->base;
+	if (unlikely(target_obj == NULL))
+		return -ENOENT;
+
+	target_i915_obj = to_intel_bo(target_obj);
+	target_offset = target_i915_obj->gtt_offset;
+
+	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
+	 * pipe_control writes because the gpu doesn't properly redirect them
+	 * through the ppgtt for non_secure batchbuffers. */
+	if (unlikely(IS_GEN6(dev) &&
+	    reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
+	    !target_i915_obj->has_global_gtt_mapping)) {
+		i915_gem_gtt_bind_object(target_i915_obj,
+					 target_i915_obj->cache_level);
+	}
+
+	/* Validate that the target is in a valid r/w GPU domain */
+	if (unlikely(reloc->write_domain & (reloc->write_domain - 1))) {
+		DRM_DEBUG("reloc with multiple write domains: "
+			  "obj %p target %d offset %d "
+			  "read %08x write %08x",
+			  obj, reloc->target_handle,
+			  (int) reloc->offset,
+			  reloc->read_domains,
+			  reloc->write_domain);
+		return ret;
+	}
+	if (unlikely((reloc->write_domain | reloc->read_domains)
+		     & ~I915_GEM_GPU_DOMAINS)) {
+		DRM_DEBUG("reloc with read/write non-GPU domains: "
+			  "obj %p target %d offset %d "
+			  "read %08x write %08x",
+			  obj, reloc->target_handle,
+			  (int) reloc->offset,
+			  reloc->read_domains,
+			  reloc->write_domain);
+		return ret;
+	}
+	if (unlikely(reloc->write_domain && target_obj->pending_write_domain &&
+		     reloc->write_domain != target_obj->pending_write_domain)) {
+		DRM_DEBUG("Write domain conflict: "
+			  "obj %p target %d offset %d "
+			  "new %08x old %08x\n",
+			  obj, reloc->target_handle,
+			  (int) reloc->offset,
+			  reloc->write_domain,
+			  target_obj->pending_write_domain);
+		return ret;
+	}
+
+	target_obj->pending_read_domains |= reloc->read_domains;
+	target_obj->pending_write_domain |= reloc->write_domain;
+
+	/* If the relocation already has the right value in it, no
+	 * more work needs to be done.
+	 */
+	if (target_offset == reloc->presumed_offset)
+		return 0;
+
+	/* Check that the relocation address is valid... */
+	if (unlikely(reloc->offset > obj->base.size - 4)) {
+		DRM_DEBUG("Relocation beyond object bounds: "
+			  "obj %p target %d offset %d size %d.\n",
+			  obj, reloc->target_handle,
+			  (int) reloc->offset,
+			  (int) obj->base.size);
+		return ret;
+	}
+	if (unlikely(reloc->offset & 3)) {
+		DRM_DEBUG("Relocation not 4-byte aligned: "
+			  "obj %p target %d offset %d.\n",
+			  obj, reloc->target_handle,
+			  (int) reloc->offset);
+		return ret;
+	}
+
+	/* We can't wait for rendering with pagefaults disabled */
+	if (obj->active && in_atomic())
+		return -EFAULT;
+
+	reloc->delta += target_offset;
+	if (use_cpu_reloc(obj)) {
+		uint32_t page_offset = reloc->offset & ~PAGE_MASK;
+		char *vaddr;
+
+		ret = i915_gem_object_set_to_cpu_domain(obj, 1);
+		if (ret)
+			return ret;
+
+		vaddr = kmap_atomic(i915_gem_object_get_page(obj,
+							     reloc->offset >> PAGE_SHIFT));
+		*(uint32_t *)(vaddr + page_offset) = reloc->delta;
+		kunmap_atomic(vaddr);
+	} else {
+		struct drm_i915_private *dev_priv = dev->dev_private;
+		uint32_t __iomem *reloc_entry;
+		void __iomem *reloc_page;
+
+		ret = i915_gem_object_set_to_gtt_domain(obj, true);
+		if (ret)
+			return ret;
+
+		ret = i915_gem_object_put_fence(obj);
+		if (ret)
+			return ret;
+
+		/* Map the page containing the relocation we're going to perform.  */
+		reloc->offset += obj->gtt_offset;
+		reloc_page = io_mapping_map_atomic_wc(dev_priv->mm.gtt_mapping,
+						      reloc->offset & PAGE_MASK);
+		reloc_entry = (uint32_t __iomem *)
+			(reloc_page + (reloc->offset & ~PAGE_MASK));
+		iowrite32(reloc->delta, reloc_entry);
+		io_mapping_unmap_atomic(reloc_page);
+	}
+
+	/* and update the user's relocation entry */
+	reloc->presumed_offset = target_offset;
+
+	return 0;
+}
+
+static int
+i915_gem_execbuffer_relocate_object(struct drm_i915_gem_object *obj,
+				    struct eb_objects *eb)
+{
+#define N_RELOC(x) ((x) / sizeof(struct drm_i915_gem_relocation_entry))
+	struct drm_i915_gem_relocation_entry stack_reloc[N_RELOC(512)];
+	struct drm_i915_gem_relocation_entry __user *user_relocs;
+	struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
+	int remain, ret;
+
+	user_relocs = (void __user *)(uintptr_t)entry->relocs_ptr;
+
+	remain = entry->relocation_count;
+	while (remain) {
+		struct drm_i915_gem_relocation_entry *r = stack_reloc;
+		int count = remain;
+		if (count > ARRAY_SIZE(stack_reloc))
+			count = ARRAY_SIZE(stack_reloc);
+		remain -= count;
+
+		if (__copy_from_user_inatomic(r, user_relocs, count*sizeof(r[0])))
+			return -EFAULT;
+
+		do {
+			u64 offset = r->presumed_offset;
+
+			ret = i915_gem_execbuffer_relocate_entry(obj, eb, r);
+			if (ret)
+				return ret;
+
+			if (r->presumed_offset != offset &&
+			    __copy_to_user_inatomic(&user_relocs->presumed_offset,
+						    &r->presumed_offset,
+						    sizeof(r->presumed_offset))) {
+				return -EFAULT;
+			}
+
+			user_relocs++;
+			r++;
+		} while (--count);
+	}
+
+	return 0;
+#undef N_RELOC
+}
+
+static int
+i915_gem_execbuffer_relocate_object_slow(struct drm_i915_gem_object *obj,
+					 struct eb_objects *eb,
+					 struct drm_i915_gem_relocation_entry *relocs)
+{
+	const struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
+	int i, ret;
+
+	for (i = 0; i < entry->relocation_count; i++) {
+		ret = i915_gem_execbuffer_relocate_entry(obj, eb, &relocs[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+i915_gem_execbuffer_relocate(struct drm_device *dev,
+			     struct eb_objects *eb,
+			     struct list_head *objects)
+{
+	struct drm_i915_gem_object *obj;
+	int ret = 0;
+
+	/* This is the fast path and we cannot handle a pagefault whilst
+	 * holding the struct mutex lest the user pass in the relocations
+	 * contained within a mmaped bo. For in such a case we, the page
+	 * fault handler would call i915_gem_fault() and we would try to
+	 * acquire the struct mutex again. Obviously this is bad and so
+	 * lockdep complains vehemently.
+	 */
+	pagefault_disable();
+	list_for_each_entry(obj, objects, exec_list) {
+		ret = i915_gem_execbuffer_relocate_object(obj, eb);
+		if (ret)
+			break;
+	}
+	pagefault_enable();
+
+	return ret;
+}
+#endif /* notyet */
 
 #define  __EXEC_OBJECT_HAS_PIN (1<<31)
 #define  __EXEC_OBJECT_HAS_FENCE (1<<30)
@@ -264,6 +539,132 @@ err:		/* Decrement pin count for bound objects */
 	} while (1);
 }
 
+#ifdef notyet
+static int
+i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
+				  struct drm_file *file,
+				  struct intel_ring_buffer *ring,
+				  struct list_head *objects,
+				  struct eb_objects *eb,
+				  struct drm_i915_gem_exec_object2 *exec,
+				  int count)
+{
+	struct drm_i915_gem_relocation_entry *reloc;
+	struct drm_i915_gem_object *obj;
+	int *reloc_offset;
+	int i, total, ret;
+
+	/* We may process another execbuffer during the unlock... */
+	while (!list_empty(objects)) {
+		obj = list_first_entry(objects,
+				       struct drm_i915_gem_object,
+				       exec_list);
+		list_del_init(&obj->exec_list);
+		drm_gem_object_unreference(&obj->base);
+	}
+
+	mutex_unlock(&dev->struct_mutex);
+
+	total = 0;
+	for (i = 0; i < count; i++)
+		total += exec[i].relocation_count;
+
+	reloc_offset = drm_malloc_ab(count, sizeof(*reloc_offset));
+	reloc = drm_malloc_ab(total, sizeof(*reloc));
+	if (reloc == NULL || reloc_offset == NULL) {
+		drm_free_large(reloc);
+		drm_free_large(reloc_offset);
+		mutex_lock(&dev->struct_mutex);
+		return -ENOMEM;
+	}
+
+	total = 0;
+	for (i = 0; i < count; i++) {
+		struct drm_i915_gem_relocation_entry __user *user_relocs;
+		u64 invalid_offset = (u64)-1;
+		int j;
+
+		user_relocs = (void __user *)(uintptr_t)exec[i].relocs_ptr;
+
+		if (copy_from_user(reloc+total, user_relocs,
+				   exec[i].relocation_count * sizeof(*reloc))) {
+			ret = -EFAULT;
+			mutex_lock(&dev->struct_mutex);
+			goto err;
+		}
+
+		/* As we do not update the known relocation offsets after
+		 * relocating (due to the complexities in lock handling),
+		 * we need to mark them as invalid now so that we force the
+		 * relocation processing next time. Just in case the target
+		 * object is evicted and then rebound into its old
+		 * presumed_offset before the next execbuffer - if that
+		 * happened we would make the mistake of assuming that the
+		 * relocations were valid.
+		 */
+		for (j = 0; j < exec[i].relocation_count; j++) {
+			if (copy_to_user(&user_relocs[j].presumed_offset,
+					 &invalid_offset,
+					 sizeof(invalid_offset))) {
+				ret = -EFAULT;
+				mutex_lock(&dev->struct_mutex);
+				goto err;
+			}
+		}
+
+		reloc_offset[i] = total;
+		total += exec[i].relocation_count;
+	}
+
+	ret = i915_mutex_lock_interruptible(dev);
+	if (ret) {
+		mutex_lock(&dev->struct_mutex);
+		goto err;
+	}
+
+	/* reacquire the objects */
+	eb_reset(eb);
+	for (i = 0; i < count; i++) {
+		obj = to_intel_bo(drm_gem_object_lookup(dev, file,
+							exec[i].handle));
+		if (&obj->base == NULL) {
+			DRM_DEBUG("Invalid object handle %d at index %d\n",
+				   exec[i].handle, i);
+			ret = -ENOENT;
+			goto err;
+		}
+
+		list_add_tail(&obj->exec_list, objects);
+		obj->exec_handle = exec[i].handle;
+		obj->exec_entry = &exec[i];
+		eb_add_object(eb, obj);
+	}
+
+	ret = i915_gem_execbuffer_reserve(ring, file, objects);
+	if (ret)
+		goto err;
+
+	list_for_each_entry(obj, objects, exec_list) {
+		int offset = obj->exec_entry - exec;
+		ret = i915_gem_execbuffer_relocate_object_slow(obj, eb,
+							       reloc + reloc_offset[offset]);
+		if (ret)
+			goto err;
+	}
+
+	/* Leave the user relocations as are, this is the painfully slow path,
+	 * and we want to avoid the complication of dropping the lock whilst
+	 * having buffers reserved in the aperture and so causing spurious
+	 * ENOSPC for random operations.
+	 */
+
+err:
+	drm_free_large(reloc);
+	drm_free_large(reloc_offset);
+	return ret;
+}
+#endif /* notyet */
+
 int
 i915_gem_execbuffer_wait_for_flips(struct intel_ring_buffer *ring, u32 flips)
 {
@@ -338,8 +739,49 @@ i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
 	return intel_ring_invalidate_all_caches(ring);
 }
 
-// i915_gem_check_execbuffer
-// validate_exec_list
+#ifdef notyet
+static bool
+i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
+{
+	return ((exec->batch_start_offset | exec->batch_len) & 0x7) == 0;
+}
+
+static int
+validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
+		   int count)
+{
+	int i;
+	int relocs_total = 0;
+	int relocs_max = INT_MAX / sizeof(struct drm_i915_gem_relocation_entry);
+
+	for (i = 0; i < count; i++) {
+		char __user *ptr = (char __user *)(uintptr_t)exec[i].relocs_ptr;
+		int length; /* limited by fault_in_pages_readable() */
+
+		/* First check for malicious input causing overflow in
+		 * the worst case where we need to allocate the entire
+		 * relocation tree as a single array.
+		 */
+		if (exec[i].relocation_count > relocs_max - relocs_total)
+			return -EINVAL;
+		relocs_total += exec[i].relocation_count;
+
+		length = exec[i].relocation_count *
+			sizeof(struct drm_i915_gem_relocation_entry);
+		if (!access_ok(VERIFY_READ, ptr, length))
+			return -EFAULT;
+
+		/* we may also need to update the presumed offsets */
+		if (!access_ok(VERIFY_WRITE, ptr, length))
+			return -EFAULT;
+
+		if (fault_in_multipages_readable(ptr, length))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+#endif /* notyet */
 
 void
 i915_gem_execbuffer_move_to_active(struct drm_obj **object_list,
@@ -383,8 +825,6 @@ i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 	i915_add_request(ring, file, NULL);
 }
 
-// i915_gem_fix_mi_batchbuffer_end
-
 int
 i915_reset_gen7_sol_offsets(struct drm_device *dev,
 			    struct intel_ring_buffer *ring)
diff --git a/sys/dev/pci/drm/i915/i915_gem_gtt.c b/sys/dev/pci/drm/i915/i915_gem_gtt.c
index 79c125b4b30..7924b75f125 100644
--- a/sys/dev/pci/drm/i915/i915_gem_gtt.c
+++ b/sys/dev/pci/drm/i915/i915_gem_gtt.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: i915_gem_gtt.c,v 1.1 2013/03/18 12:36:52 jsg Exp $	*/
+/*	$OpenBSD: i915_gem_gtt.c,v 1.2 2013/08/09 07:55:42 jsg Exp $	*/
 /*
  * Copyright © 2010 Daniel Vetter
  *
@@ -26,14 +26,375 @@
 #include <dev/pci/drm/drmP.h>
 #include <dev/pci/drm/drm.h>
 #include "i915_drv.h"
+#include "i915_trace.h"
 #include "intel_drv.h"
 
-void
-i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev)
+#ifdef notyet
+typedef uint32_t gtt_pte_t;
+
+/* PPGTT stuff */
+#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
+
+#define GEN6_PDE_VALID			(1 << 0)
+/* gen6+ has bit 11-4 for physical addr bit 39-32 */
+#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+
+#define GEN6_PTE_VALID			(1 << 0)
+#define GEN6_PTE_UNCACHED		(1 << 1)
+#define HSW_PTE_UNCACHED		(0)
+#define GEN6_PTE_CACHE_LLC		(2 << 1)
+#define GEN6_PTE_CACHE_LLC_MLC		(3 << 1)
+#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+
+static inline gtt_pte_t pte_encode(struct drm_device *dev,
+				   dma_addr_t addr,
+				   enum i915_cache_level level)
+{
+	gtt_pte_t pte = GEN6_PTE_VALID;
+	pte |= GEN6_PTE_ADDR_ENCODE(addr);
+
+	switch (level) {
+	case I915_CACHE_LLC_MLC:
+		/* Haswell doesn't set L3 this way */
+		if (IS_HASWELL(dev))
+			pte |= GEN6_PTE_CACHE_LLC;
+		else
+			pte |= GEN6_PTE_CACHE_LLC_MLC;
+		break;
+	case I915_CACHE_LLC:
+		pte |= GEN6_PTE_CACHE_LLC;
+		break;
+	case I915_CACHE_NONE:
+		if (IS_HASWELL(dev))
+			pte |= HSW_PTE_UNCACHED;
+		else
+			pte |= GEN6_PTE_UNCACHED;
+		break;
+	default:
+		BUG();
+	}
+
+
+	return pte;
+}
+
+/* PPGTT support for Sandybdrige/Gen6 and later */
+static void i915_ppgtt_clear_range(struct i915_hw_ppgtt *ppgtt,
+				   unsigned first_entry,
+				   unsigned num_entries)
+{
+	gtt_pte_t *pt_vaddr;
+	gtt_pte_t scratch_pte;
+	unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES;
+	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
+	unsigned last_pte, i;
+
+	scratch_pte = pte_encode(ppgtt->dev, ppgtt->scratch_page_dma_addr,
+				 I915_CACHE_LLC);
+
+	while (num_entries) {
+		last_pte = first_pte + num_entries;
+		if (last_pte > I915_PPGTT_PT_ENTRIES)
+			last_pte = I915_PPGTT_PT_ENTRIES;
+
+		pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]);
+
+		for (i = first_pte; i < last_pte; i++)
+			pt_vaddr[i] = scratch_pte;
+
+		kunmap_atomic(pt_vaddr);
+
+		num_entries -= last_pte - first_pte;
+		first_pte = 0;
+		act_pd++;
+	}
+}
+
+int i915_gem_init_aliasing_ppgtt(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_hw_ppgtt *ppgtt;
+	unsigned first_pd_entry_in_global_pt;
+	int i;
+	int ret = -ENOMEM;
+
+	/* ppgtt PDEs reside in the global gtt pagetable, which has 512*1024
+	 * entries. For aliasing ppgtt support we just steal them at the end for
+	 * now. */
+	first_pd_entry_in_global_pt = dev_priv->mm.gtt->gtt_total_entries - I915_PPGTT_PD_ENTRIES;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ret;
+
+	ppgtt->dev = dev;
+	ppgtt->num_pd_entries = I915_PPGTT_PD_ENTRIES;
+	ppgtt->pt_pages = kzalloc(sizeof(struct page *)*ppgtt->num_pd_entries,
+				  GFP_KERNEL);
+	if (!ppgtt->pt_pages)
+		goto err_ppgtt;
+
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		ppgtt->pt_pages[i] = alloc_page(GFP_KERNEL);
+		if (!ppgtt->pt_pages[i])
+			goto err_pt_alloc;
+	}
+
+	if (dev_priv->mm.gtt->needs_dmar) {
+		ppgtt->pt_dma_addr = kzalloc(sizeof(dma_addr_t)
+						*ppgtt->num_pd_entries,
+					     GFP_KERNEL);
+		if (!ppgtt->pt_dma_addr)
+			goto err_pt_alloc;
+
+		for (i = 0; i < ppgtt->num_pd_entries; i++) {
+			dma_addr_t pt_addr;
+
+			pt_addr = pci_map_page(dev->pdev, ppgtt->pt_pages[i],
+					       0, 4096,
+					       PCI_DMA_BIDIRECTIONAL);
+
+			if (pci_dma_mapping_error(dev->pdev,
+						  pt_addr)) {
+				ret = -EIO;
+				goto err_pd_pin;
+
+			}
+			ppgtt->pt_dma_addr[i] = pt_addr;
+		}
+	}
+
+	ppgtt->scratch_page_dma_addr = dev_priv->mm.gtt->scratch_page_dma;
+
+	i915_ppgtt_clear_range(ppgtt, 0,
+			       ppgtt->num_pd_entries*I915_PPGTT_PT_ENTRIES);
+
+	ppgtt->pd_offset = (first_pd_entry_in_global_pt)*sizeof(gtt_pte_t);
+
+	dev_priv->mm.aliasing_ppgtt = ppgtt;
+
+	return 0;
+
+err_pd_pin:
+	if (ppgtt->pt_dma_addr) {
+		for (i--; i >= 0; i--)
+			pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i],
+				       4096, PCI_DMA_BIDIRECTIONAL);
+	}
+err_pt_alloc:
+	kfree(ppgtt->pt_dma_addr);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		if (ppgtt->pt_pages[i])
+			__free_page(ppgtt->pt_pages[i]);
+	}
+	kfree(ppgtt->pt_pages);
+err_ppgtt:
+	kfree(ppgtt);
+
+	return ret;
+}
+#endif /* notyet */
+
+void i915_gem_cleanup_aliasing_ppgtt(struct drm_device *dev)
 {
 	printf("%s stub\n", __func__);
+#ifdef notyet
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	int i;
+
+	if (!ppgtt)
+		return;
+
+	if (ppgtt->pt_dma_addr) {
+		for (i = 0; i < ppgtt->num_pd_entries; i++)
+			pci_unmap_page(dev->pdev, ppgtt->pt_dma_addr[i],
+				       4096, PCI_DMA_BIDIRECTIONAL);
+	}
+
+	kfree(ppgtt->pt_dma_addr);
+	for (i = 0; i < ppgtt->num_pd_entries; i++)
+		__free_page(ppgtt->pt_pages[i]);
+	kfree(ppgtt->pt_pages);
+	kfree(ppgtt);
+#endif
 }
 
+#ifdef notyet
+static void i915_ppgtt_insert_sg_entries(struct i915_hw_ppgtt *ppgtt,
+					 const struct sg_table *pages,
+					 unsigned first_entry,
+					 enum i915_cache_level cache_level)
+{
+	gtt_pte_t *pt_vaddr;
+	unsigned act_pd = first_entry / I915_PPGTT_PT_ENTRIES;
+	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
+	unsigned i, j, m, segment_len;
+	dma_addr_t page_addr;
+	struct scatterlist *sg;
+
+	/* init sg walking */
+	sg = pages->sgl;
+	i = 0;
+	segment_len = sg_dma_len(sg) >> PAGE_SHIFT;
+	m = 0;
+
+	while (i < pages->nents) {
+		pt_vaddr = kmap_atomic(ppgtt->pt_pages[act_pd]);
+
+		for (j = first_pte; j < I915_PPGTT_PT_ENTRIES; j++) {
+			page_addr = sg_dma_address(sg) + (m << PAGE_SHIFT);
+			pt_vaddr[j] = pte_encode(ppgtt->dev, page_addr,
+						 cache_level);
+
+			/* grab the next page */
+			if (++m == segment_len) {
+				if (++i == pages->nents)
+					break;
+
+				sg = sg_next(sg);
+				segment_len = sg_dma_len(sg) >> PAGE_SHIFT;
+				m = 0;
+			}
+		}
+
+		kunmap_atomic(pt_vaddr);
+
+		first_pte = 0;
+		act_pd++;
+	}
+}
+
+void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
+			    struct drm_i915_gem_object *obj,
+			    enum i915_cache_level cache_level)
+{
+	i915_ppgtt_insert_sg_entries(ppgtt,
+				     obj->pages,
+				     obj->gtt_space->start >> PAGE_SHIFT,
+				     cache_level);
+}
+
+void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
+			      struct drm_i915_gem_object *obj)
+{
+	i915_ppgtt_clear_range(ppgtt,
+			       obj->gtt_space->start >> PAGE_SHIFT,
+			       obj->base.size >> PAGE_SHIFT);
+}
+
+void i915_gem_init_ppgtt(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t pd_offset;
+	struct intel_ring_buffer *ring;
+	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
+	uint32_t __iomem *pd_addr;
+	uint32_t pd_entry;
+	int i;
+
+	if (!dev_priv->mm.aliasing_ppgtt)
+		return;
+
+
+	pd_addr = dev_priv->mm.gtt->gtt + ppgtt->pd_offset/sizeof(uint32_t);
+	for (i = 0; i < ppgtt->num_pd_entries; i++) {
+		dma_addr_t pt_addr;
+
+		if (dev_priv->mm.gtt->needs_dmar)
+			pt_addr = ppgtt->pt_dma_addr[i];
+		else
+			pt_addr = page_to_phys(ppgtt->pt_pages[i]);
+
+		pd_entry = GEN6_PDE_ADDR_ENCODE(pt_addr);
+		pd_entry |= GEN6_PDE_VALID;
+
+		writel(pd_entry, pd_addr + i);
+	}
+	readl(pd_addr);
+
+	pd_offset = ppgtt->pd_offset;
+	pd_offset /= 64; /* in cachelines, */
+	pd_offset <<= 16;
+
+	if (INTEL_INFO(dev)->gen == 6) {
+		uint32_t ecochk, gab_ctl, ecobits;
+
+		ecobits = I915_READ(GAC_ECO_BITS);
+		I915_WRITE(GAC_ECO_BITS, ecobits | ECOBITS_PPGTT_CACHE64B);
+
+		gab_ctl = I915_READ(GAB_CTL);
+		I915_WRITE(GAB_CTL, gab_ctl | GAB_CTL_CONT_AFTER_PAGEFAULT);
+
+		ecochk = I915_READ(GAM_ECOCHK);
+		I915_WRITE(GAM_ECOCHK, ecochk | ECOCHK_SNB_BIT |
+				       ECOCHK_PPGTT_CACHE64B);
+		I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+	} else if (INTEL_INFO(dev)->gen >= 7) {
+		I915_WRITE(GAM_ECOCHK, ECOCHK_PPGTT_CACHE64B);
+		/* GFX_MODE is per-ring on gen7+ */
+	}
+
+	for_each_ring(ring, dev_priv, i) {
+		if (INTEL_INFO(dev)->gen >= 7)
+			I915_WRITE(RING_MODE_GEN7(ring),
+				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+
+		I915_WRITE(RING_PP_DIR_DCLV(ring), PP_DIR_DCLV_2G);
+		I915_WRITE(RING_PP_DIR_BASE(ring), pd_offset);
+	}
+}
+
+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;
+}
+
+
+static void i915_ggtt_clear_range(struct drm_device *dev,
+				 unsigned first_entry,
+				 unsigned num_entries)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	gtt_pte_t scratch_pte;
+	gtt_pte_t __iomem *gtt_base = dev_priv->mm.gtt->gtt + first_entry;
+	const int max_entries = dev_priv->mm.gtt->gtt_total_entries - first_entry;
+	int i;
+
+	if (INTEL_INFO(dev)->gen < 6) {
+		intel_gtt_clear_range(first_entry, num_entries);
+		return;
+	}
+
+	if (WARN(num_entries > max_entries,
+		 "First entry = %d; Num entries = %d (max=%d)\n",
+		 first_entry, num_entries, max_entries))
+		num_entries = max_entries;
+
+	scratch_pte = pte_encode(dev, dev_priv->mm.gtt->scratch_page_dma, I915_CACHE_LLC);
+	for (i = 0; i < num_entries; i++)
+		iowrite32(scratch_pte, &gtt_base[i]);
+	readl(gtt_base);
+}
+#endif /* notyet */
+
 void
 i915_gem_restore_gtt_mappings(struct drm_device *dev)
 {
@@ -48,6 +409,311 @@ i915_gem_restore_gtt_mappings(struct drm_device *dev)
 	i915_gem_chipset_flush(dev);
 }
 
+#ifdef notyet
+int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
+{
+	if (obj->has_dma_mapping)
+		return 0;
+
+	if (!dma_map_sg(&obj->base.dev->pdev->dev,
+			obj->pages->sgl, obj->pages->nents,
+			PCI_DMA_BIDIRECTIONAL))
+		return -ENOSPC;
+
+	return 0;
+}
+
+/*
+ * Binds an object into the global gtt with the specified cache level. The object
+ * will be accessible to the GPU via commands whose operands reference offsets
+ * within the global GTT as well as accessible by the GPU through the GMADR
+ * mapped BAR (dev_priv->mm.gtt->gtt).
+ */
+static void gen6_ggtt_bind_object(struct drm_i915_gem_object *obj,
+				  enum i915_cache_level level)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct sg_table *st = obj->pages;
+	struct scatterlist *sg = st->sgl;
+	const int first_entry = obj->gtt_space->start >> PAGE_SHIFT;
+	const int max_entries = dev_priv->mm.gtt->gtt_total_entries - first_entry;
+	gtt_pte_t __iomem *gtt_entries = dev_priv->mm.gtt->gtt + first_entry;
+	int unused, i = 0;
+	unsigned int len, m = 0;
+	dma_addr_t addr;
+
+	for_each_sg(st->sgl, sg, st->nents, unused) {
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		for (m = 0; m < len; m++) {
+			addr = sg_dma_address(sg) + (m << PAGE_SHIFT);
+			iowrite32(pte_encode(dev, addr, level), &gtt_entries[i]);
+			i++;
+		}
+	}
+
+	BUG_ON(i > max_entries);
+	BUG_ON(i != obj->base.size / PAGE_SIZE);
+
+	/* XXX: This serves as a posting read to make sure that the PTE has
+	 * actually been updated. There is some concern that even though
+	 * registers and PTEs are within the same BAR that they are potentially
+	 * of NUMA access patterns. Therefore, even with the way we assume
+	 * hardware should work, we must keep this posting read for paranoia.
+	 */
+	if (i != 0)
+		WARN_ON(readl(&gtt_entries[i-1]) != pte_encode(dev, addr, level));
+
+	/* This next bit makes the above posting read even more important. We
+	 * want to flush the TLBs only after we're certain all the PTE updates
+	 * have finished.
+	 */
+	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+}
+
+void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
+			      enum i915_cache_level cache_level)
+{
+	struct drm_device *dev = obj->base.dev;
+	if (INTEL_INFO(dev)->gen < 6) {
+		unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+			AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+		intel_gtt_insert_sg_entries(obj->pages,
+					    obj->gtt_space->start >> PAGE_SHIFT,
+					    flags);
+	} else {
+		gen6_ggtt_bind_object(obj, cache_level);
+	}
+
+	obj->has_global_gtt_mapping = 1;
+}
+
+void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
+{
+	i915_ggtt_clear_range(obj->base.dev,
+			      obj->gtt_space->start >> PAGE_SHIFT,
+			      obj->base.size >> PAGE_SHIFT);
+
+	obj->has_global_gtt_mapping = 0;
+}
+
+void i915_gem_gtt_finish_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);
+
+	if (!obj->has_dma_mapping)
+		dma_unmap_sg(&dev->pdev->dev,
+			     obj->pages->sgl, obj->pages->nents,
+			     PCI_DMA_BIDIRECTIONAL);
+
+	undo_idling(dev_priv, interruptible);
+}
+
+static void i915_gtt_color_adjust(struct drm_mm_node *node,
+				  unsigned long color,
+				  unsigned long *start,
+				  unsigned long *end)
+{
+	if (node->color != color)
+		*start += 4096;
+
+	if (!list_empty(&node->node_list)) {
+		node = list_entry(node->node_list.next,
+				  struct drm_mm_node,
+				  node_list);
+		if (node->allocated && node->color != color)
+			*end -= 4096;
+	}
+}
+
+void i915_gem_init_global_gtt(struct drm_device *dev,
+			      unsigned long start,
+			      unsigned long mappable_end,
+			      unsigned long end)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	/* Substract the guard page ... */
+	drm_mm_init(&dev_priv->mm.gtt_space, start, end - start - PAGE_SIZE);
+	if (!HAS_LLC(dev))
+		dev_priv->mm.gtt_space.color_adjust = i915_gtt_color_adjust;
+
+	dev_priv->mm.gtt_start = start;
+	dev_priv->mm.gtt_mappable_end = mappable_end;
+	dev_priv->mm.gtt_end = end;
+	dev_priv->mm.gtt_total = end - start;
+	dev_priv->mm.mappable_gtt_total = min(end, mappable_end) - start;
+
+	/* ... but ensure that we clear the entire range. */
+	i915_ggtt_clear_range(dev, start / PAGE_SIZE, (end-start) / PAGE_SIZE);
+}
+
+static int setup_scratch_page(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct page *page;
+	dma_addr_t dma_addr;
+
+	page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
+	if (page == NULL)
+		return -ENOMEM;
+	get_page(page);
+	set_pages_uc(page, 1);
+
+#ifdef CONFIG_INTEL_IOMMU
+	dma_addr = pci_map_page(dev->pdev, page, 0, PAGE_SIZE,
+				PCI_DMA_BIDIRECTIONAL);
+	if (pci_dma_mapping_error(dev->pdev, dma_addr))
+		return -EINVAL;
+#else
+	dma_addr = page_to_phys(page);
+#endif
+	dev_priv->mm.gtt->scratch_page = page;
+	dev_priv->mm.gtt->scratch_page_dma = dma_addr;
+
+	return 0;
+}
+
+static void teardown_scratch_page(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	set_pages_wb(dev_priv->mm.gtt->scratch_page, 1);
+	pci_unmap_page(dev->pdev, dev_priv->mm.gtt->scratch_page_dma,
+		       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	put_page(dev_priv->mm.gtt->scratch_page);
+	__free_page(dev_priv->mm.gtt->scratch_page);
+}
+
+static inline unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
+{
+	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
+	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
+	return snb_gmch_ctl << 20;
+}
+
+static inline unsigned int gen6_get_stolen_size(u16 snb_gmch_ctl)
+{
+	snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT;
+	snb_gmch_ctl &= SNB_GMCH_GMS_MASK;
+	return snb_gmch_ctl << 25; /* 32 MB units */
+}
+
+static inline unsigned int gen7_get_stolen_size(u16 snb_gmch_ctl)
+{
+	static const int stolen_decoder[] = {
+		0, 0, 0, 0, 0, 32, 48, 64, 128, 256, 96, 160, 224, 352};
+	snb_gmch_ctl >>= IVB_GMCH_GMS_SHIFT;
+	snb_gmch_ctl &= IVB_GMCH_GMS_MASK;
+	return stolen_decoder[snb_gmch_ctl] << 20;
+}
+
+int i915_gem_gtt_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	phys_addr_t gtt_bus_addr;
+	u16 snb_gmch_ctl;
+	int ret;
+
+	/* On modern platforms we need not worry ourself with the legacy
+	 * hostbridge query stuff. Skip it entirely
+	 */
+	if (INTEL_INFO(dev)->gen < 6) {
+		ret = intel_gmch_probe(dev_priv->bridge_dev, dev->pdev, NULL);
+		if (!ret) {
+			DRM_ERROR("failed to set up gmch\n");
+			return -EIO;
+		}
+
+		dev_priv->mm.gtt = intel_gtt_get();
+		if (!dev_priv->mm.gtt) {
+			DRM_ERROR("Failed to initialize GTT\n");
+			intel_gmch_remove();
+			return -ENODEV;
+		}
+		return 0;
+	}
+
+	dev_priv->mm.gtt = kzalloc(sizeof(*dev_priv->mm.gtt), GFP_KERNEL);
+	if (!dev_priv->mm.gtt)
+		return -ENOMEM;
+
+	if (!pci_set_dma_mask(dev->pdev, DMA_BIT_MASK(40)))
+		pci_set_consistent_dma_mask(dev->pdev, DMA_BIT_MASK(40));
+
+#ifdef CONFIG_INTEL_IOMMU
+	dev_priv->mm.gtt->needs_dmar = 1;
+#endif
+
+	/* For GEN6+ the PTEs for the ggtt live at 2MB + BAR0 */
+	gtt_bus_addr = pci_resource_start(dev->pdev, 0) + (2<<20);
+	dev_priv->mm.gtt->gma_bus_addr = pci_resource_start(dev->pdev, 2);
+
+	/* i9xx_setup */
+	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+	dev_priv->mm.gtt->gtt_total_entries =
+		gen6_get_total_gtt_size(snb_gmch_ctl) / sizeof(gtt_pte_t);
+	if (INTEL_INFO(dev)->gen < 7)
+		dev_priv->mm.gtt->stolen_size = gen6_get_stolen_size(snb_gmch_ctl);
+	else
+		dev_priv->mm.gtt->stolen_size = gen7_get_stolen_size(snb_gmch_ctl);
+
+	dev_priv->mm.gtt->gtt_mappable_entries = pci_resource_len(dev->pdev, 2) >> PAGE_SHIFT;
+	/* 64/512MB is the current min/max we actually know of, but this is just a
+	 * coarse sanity check.
+	 */
+	if ((dev_priv->mm.gtt->gtt_mappable_entries >> 8) < 64 ||
+	    dev_priv->mm.gtt->gtt_mappable_entries > dev_priv->mm.gtt->gtt_total_entries) {
+		DRM_ERROR("Unknown GMADR entries (%d)\n",
+			  dev_priv->mm.gtt->gtt_mappable_entries);
+		ret = -ENXIO;
+		goto err_out;
+	}
+
+	ret = setup_scratch_page(dev);
+	if (ret) {
+		DRM_ERROR("Scratch setup failed\n");
+		goto err_out;
+	}
+
+	dev_priv->mm.gtt->gtt = ioremap_wc(gtt_bus_addr,
+					   dev_priv->mm.gtt->gtt_total_entries * sizeof(gtt_pte_t));
+	if (!dev_priv->mm.gtt->gtt) {
+		DRM_ERROR("Failed to map the gtt page table\n");
+		teardown_scratch_page(dev);
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
+	/* GMADR is the PCI aperture used by SW to access tiled GFX surfaces in a linear fashion. */
+	DRM_INFO("Memory usable by graphics device = %dM\n", dev_priv->mm.gtt->gtt_total_entries >> 8);
+	DRM_DEBUG_DRIVER("GMADR size = %dM\n", dev_priv->mm.gtt->gtt_mappable_entries >> 8);
+	DRM_DEBUG_DRIVER("GTT stolen size = %dM\n", dev_priv->mm.gtt->stolen_size >> 20);
+
+	return 0;
+
+err_out:
+	kfree(dev_priv->mm.gtt);
+	if (INTEL_INFO(dev)->gen < 6)
+		intel_gmch_remove();
+	return ret;
+}
+
+void i915_gem_gtt_fini(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	iounmap(dev_priv->mm.gtt->gtt);
+	teardown_scratch_page(dev);
+	if (INTEL_INFO(dev)->gen < 6)
+		intel_gmch_remove();
+	kfree(dev_priv->mm.gtt);
+}
+#endif /* notyet */
+
 void
 i915_gem_gtt_rebind_object(struct drm_i915_gem_object *obj,
 			   enum i915_cache_level cache_level)
diff --git a/sys/dev/pci/drm/i915/intel_display.c b/sys/dev/pci/drm/i915/intel_display.c
index b5a0a9afe35..8843a5afae5 100644
--- a/sys/dev/pci/drm/i915/intel_display.c
+++ b/sys/dev/pci/drm/i915/intel_display.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: intel_display.c,v 1.9 2013/07/08 09:47:45 jsg Exp $	*/
+/*	$OpenBSD: intel_display.c,v 1.10 2013/08/09 07:55:42 jsg Exp $	*/
 /*
  * Copyright © 2006-2007 Intel Corporation
  *
@@ -10075,3 +10075,118 @@ intel_modeset_vga_set_state(struct drm_device *dev, bool state)
 	return 0;
 #endif
 }
+
+#ifdef CONFIG_DEBUG_FS
+#include <linux/seq_file.h>
+
+struct intel_display_error_state {
+	struct intel_cursor_error_state {
+		u32 control;
+		u32 position;
+		u32 base;
+		u32 size;
+	} cursor[I915_MAX_PIPES];
+
+	struct intel_pipe_error_state {
+		u32 conf;
+		u32 source;
+
+		u32 htotal;
+		u32 hblank;
+		u32 hsync;
+		u32 vtotal;
+		u32 vblank;
+		u32 vsync;
+	} pipe[I915_MAX_PIPES];
+
+	struct intel_plane_error_state {
+		u32 control;
+		u32 stride;
+		u32 size;
+		u32 pos;
+		u32 addr;
+		u32 surface;
+		u32 tile_offset;
+	} plane[I915_MAX_PIPES];
+};
+
+struct intel_display_error_state *
+intel_display_capture_error_state(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct intel_display_error_state *error;
+	enum transcoder cpu_transcoder;
+	int i;
+
+	error = kmalloc(sizeof(*error), GFP_ATOMIC);
+	if (error == NULL)
+		return NULL;
+
+	for_each_pipe(i) {
+		cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv, i);
+
+		error->cursor[i].control = I915_READ(CURCNTR(i));
+		error->cursor[i].position = I915_READ(CURPOS(i));
+		error->cursor[i].base = I915_READ(CURBASE(i));
+
+		error->plane[i].control = I915_READ(DSPCNTR(i));
+		error->plane[i].stride = I915_READ(DSPSTRIDE(i));
+		error->plane[i].size = I915_READ(DSPSIZE(i));
+		error->plane[i].pos = I915_READ(DSPPOS(i));
+		error->plane[i].addr = I915_READ(DSPADDR(i));
+		if (INTEL_INFO(dev)->gen >= 4) {
+			error->plane[i].surface = I915_READ(DSPSURF(i));
+			error->plane[i].tile_offset = I915_READ(DSPTILEOFF(i));
+		}
+
+		error->pipe[i].conf = I915_READ(PIPECONF(cpu_transcoder));
+		error->pipe[i].source = I915_READ(PIPESRC(i));
+		error->pipe[i].htotal = I915_READ(HTOTAL(cpu_transcoder));
+		error->pipe[i].hblank = I915_READ(HBLANK(cpu_transcoder));
+		error->pipe[i].hsync = I915_READ(HSYNC(cpu_transcoder));
+		error->pipe[i].vtotal = I915_READ(VTOTAL(cpu_transcoder));
+		error->pipe[i].vblank = I915_READ(VBLANK(cpu_transcoder));
+		error->pipe[i].vsync = I915_READ(VSYNC(cpu_transcoder));
+	}
+
+	return error;
+}
+
+void
+intel_display_print_error_state(struct seq_file *m,
+				struct drm_device *dev,
+				struct intel_display_error_state *error)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	int i;
+
+	seq_printf(m, "Num Pipes: %d\n", dev_priv->num_pipe);
+	for_each_pipe(i) {
+		seq_printf(m, "Pipe [%d]:\n", i);
+		seq_printf(m, "  CONF: %08x\n", error->pipe[i].conf);
+		seq_printf(m, "  SRC: %08x\n", error->pipe[i].source);
+		seq_printf(m, "  HTOTAL: %08x\n", error->pipe[i].htotal);
+		seq_printf(m, "  HBLANK: %08x\n", error->pipe[i].hblank);
+		seq_printf(m, "  HSYNC: %08x\n", error->pipe[i].hsync);
+		seq_printf(m, "  VTOTAL: %08x\n", error->pipe[i].vtotal);
+		seq_printf(m, "  VBLANK: %08x\n", error->pipe[i].vblank);
+		seq_printf(m, "  VSYNC: %08x\n", error->pipe[i].vsync);
+
+		seq_printf(m, "Plane [%d]:\n", i);
+		seq_printf(m, "  CNTR: %08x\n", error->plane[i].control);
+		seq_printf(m, "  STRIDE: %08x\n", error->plane[i].stride);
+		seq_printf(m, "  SIZE: %08x\n", error->plane[i].size);
+		seq_printf(m, "  POS: %08x\n", error->plane[i].pos);
+		seq_printf(m, "  ADDR: %08x\n", error->plane[i].addr);
+		if (INTEL_INFO(dev)->gen >= 4) {
+			seq_printf(m, "  SURF: %08x\n", error->plane[i].surface);
+			seq_printf(m, "  TILEOFF: %08x\n", error->plane[i].tile_offset);
+		}
+
+		seq_printf(m, "Cursor [%d]:\n", i);
+		seq_printf(m, "  CNTR: %08x\n", error->cursor[i].control);
+		seq_printf(m, "  POS: %08x\n", error->cursor[i].position);
+		seq_printf(m, "  BASE: %08x\n", error->cursor[i].base);
+	}
+}
+#endif