Patch "drm/i915: Recreate internal objects with single page segments if dmar fails" has been added to the 4.10-stable tree

This is a note to let you know that I've just added the patch titled

drm/i915: Recreate internal objects with single page segments if dmar fails

to the 4.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
drm-i915-recreate-internal-objects-with-single-page-segments-if-dmar-fails.patch
and it can be found in the queue-4.10 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

From: Chris Wilson <[email protected]>
Date: Thu, 2 Feb 2017 13:27:21 +0000
Subject: drm/i915: Recreate internal objects with single page segments if dmar fails

From: Chris Wilson <[email protected]>

commit 2d2cfc12b1270c8451edc7d2dd5f79097b3a17d8 upstream.

If we fail to dma-map the object, the most common cause is lack of space inside the SW-IOTLB due to fragmentation. If we recreate the_sg_table using segments of PAGE_SIZE (and single page allocations), we may succeed in remapping the scatterlist.

First became a significant problem for the mock selftests after commit 5584f1b1d73e ("drm/i915: fix i915 running as dom0 under Xen") increased the max_order.

---
 drivers/gpu/drm/i915/i915_gem_internal.c |   37 +++++++++++++++++++------------
 1 file changed, 23 insertions(+), 14 deletions(-)

@@ -46,24 +46,12 @@ static struct sg_table *
 i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	unsigned int npages = obj->base.size / PAGE_SIZE;
 	struct sg_table *st;
 	struct scatterlist *sg;
+	unsigned int npages;
 	int max_order;
 	gfp_t gfp;
 
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st)
-		return ERR_PTR(-ENOMEM);
-
-	if (sg_alloc_table(st, npages, GFP_KERNEL)) {
-		kfree(st);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	sg = st->sgl;
-	st->nents = 0;
-
 	max_order = MAX_ORDER;
 #ifdef CONFIG_SWIOTLB
 	if (swiotlb_nr_tbl()) {

@@ -85,6 +73,20 @@ i915_gem_object_get_pages_internal(struc
 		gfp |= __GFP_DMA32;
 	}
 
+create_st:
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return ERR_PTR(-ENOMEM);
+
+	npages = obj->base.size / PAGE_SIZE;
+	if (sg_alloc_table(st, npages, GFP_KERNEL)) {
+		kfree(st);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	sg = st->sgl;
+	st->nents = 0;
+
 	do {
 		int order = min(fls(npages) - 1, max_order);
 		struct page *page;

@@ -112,8 +114,15 @@ i915_gem_object_get_pages_internal(struc
 		sg = __sg_next(sg);
 	} while (1);
 
-	if (i915_gem_gtt_prepare_pages(obj, st))
+	if (i915_gem_gtt_prepare_pages(obj, st)) {
+		/* Failed to dma-map try again with single page sg segments */
+		if (get_order(st->sgl->length)) {
+			internal_free_pages(st);
+			max_order = 0;
+			goto create_st;
+		}
 		goto err;
+	}
 
 	/* Mark the pages as dontneed whilst they are still pinned. As soon
 	 * as they are unpinned they are allowed to be reaped by the shrinker,

Patches currently in stable-queue which might be from [email protected] are

queue-4.10/drm-i915-recreate-internal-objects-with-single-page-segments-if-dmar-fails.patch queue-4.10/drm-cancel-drm_fb_helper_dirty_work-on-unload.patch queue-4.10/drm-i915-gvt-disable-access-to-stolen-memory-as-a-guest.patch queue-4.10/drm-i915-check-for-timeout-completion-when-waiting-for-the-rq-to-submitted.patch queue-4.10/drm-cancel-drm_fb_helper_resume_work-on-unload.patch queue-4.10/drm-i915-pass-timeout-0-on-to-i915_gem_object_wait_fence.patch