mm, vmalloc: fix high order __GFP_NOFAIL allocations

[ Upstream commit e9c3cda ]

Gao Xiang has reported that the page allocator complains about high order
__GFP_NOFAIL request coming from the vmalloc core:

 __alloc_pages+0x1cb/0x5b0 mm/page_alloc.c:5549
 alloc_pages+0x1aa/0x270 mm/mempolicy.c:2286
 vm_area_alloc_pages mm/vmalloc.c:2989 [inline]
 __vmalloc_area_node mm/vmalloc.c:3057 [inline]
 __vmalloc_node_range+0x978/0x13c0 mm/vmalloc.c:3227
 kvmalloc_node+0x156/0x1a0 mm/util.c:606
 kvmalloc include/linux/slab.h:737 [inline]
 kvmalloc_array include/linux/slab.h:755 [inline]
 kvcalloc include/linux/slab.h:760 [inline]

it seems that I have completely missed high order allocation backing
vmalloc areas case when implementing __GFP_NOFAIL support.  This means
that [k]vmalloc at al.  can allocate higher order allocations with
__GFP_NOFAIL which can trigger OOM killer for non-costly orders easily or
cause a lot of reclaim/compaction activity if those requests cannot be
satisfied.

Fix the issue by falling back to zero order allocations for __GFP_NOFAIL
requests if the high order request fails.

Link: https://lkml.kernel.org/r/[email protected]
Fixes: 9376130 ("mm/vmalloc: add support for __GFP_NOFAIL")
Reported-by: Gao Xiang <[email protected]>
  Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Michal Hocko <[email protected]>
Reviewed-by: Uladzislau Rezki (Sony) <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Cc: Baoquan He <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Mel Gorman <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Stable-dep-of: 8e0545c ("mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL")
Signed-off-by: Sasha Levin <[email protected]>

Author: Michal Hocko

mm/vmalloc.c

@@ -2923,6 +2923,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 		unsigned int order, unsigned int nr_pages, struct page **pages)
 {
 	unsigned int nr_allocated = 0;
+	gfp_t alloc_gfp = gfp;
+	bool nofail = false;
 	struct page *page;
 	int i;
 
@@ -2933,6 +2935,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * more permissive.
 	 */
 	if (!order) {
+		/* bulk allocator doesn't support nofail req. officially */
 		gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL;
 
 		while (nr_allocated < nr_pages) {
@@ -2971,20 +2974,35 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			if (nr != nr_pages_request)
 				break;
 		}
+	} else if (gfp & __GFP_NOFAIL) {
+		/*
+		 * Higher order nofail allocations are really expensive and
+		 * potentially dangerous (pre-mature OOM, disruptive reclaim
+		 * and compaction etc.
+		 */
+		alloc_gfp &= ~__GFP_NOFAIL;
+		nofail = true;
 	}
 
 	/* High-order pages or fallback path if "bulk" fails. */
-
 	while (nr_allocated < nr_pages) {
 		if (fatal_signal_pending(current))
 			break;
 
 		if (nid == NUMA_NO_NODE)
-			page = alloc_pages(gfp, order);
+			page = alloc_pages(alloc_gfp, order);
 		else
-			page = alloc_pages_node(nid, gfp, order);
-		if (unlikely(!page))
-			break;
+			page = alloc_pages_node(nid, alloc_gfp, order);
+		if (unlikely(!page)) {
+			if (!nofail)
+				break;
+
+			/* fall back to the zero order allocations */
+			alloc_gfp |= __GFP_NOFAIL;
+			order = 0;
+			continue;
+		}
+
 		/*
 		 * Higher order allocations must be able to be treated as
 		 * indepdenent small pages by callers (as they can with