mm: help __GFP_NOFAIL allocations which do not trigger OOM killer

Now that __GFP_NOFAIL doesn't override decisions to skip the oom killer
we are left with requests which require to loop inside the allocator
without invoking the oom killer (e.g.  GFP_NOFS|__GFP_NOFAIL used by fs
code) and so they might, in very unlikely situations, loop for ever -
e.g.  other parallel request could starve them.

This patch tries to limit the likelihood of such a lockup by giving
these __GFP_NOFAIL requests a chance to move on by consuming a small
part of memory reserves.  We are using ALLOC_HARDER which should be
enough to prevent from the starvation by regular allocation requests,
yet it shouldn't consume enough from the reserves to disrupt high
priority requests (ALLOC_HIGH).

While we are at it, let's introduce a helper __alloc_pages_cpuset_fallback
which enforces the cpusets but allows to fallback to ignore them if the
first attempt fails.  __GFP_NOFAIL requests can be considered important
enough to allow cpuset runaway in order for the system to move on.  It
is highly unlikely that any of these will be GFP_USER anyway.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Michal Hocko <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Hillf Danton <[email protected]>
Cc: Tetsuo Handa <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

mm/page_alloc.c

@@ -3055,6 +3055,26 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
 	warn_alloc_show_mem(gfp_mask, nm);
 }
 
+static inline struct page *
+__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order,
+			      unsigned int alloc_flags,
+			      const struct alloc_context *ac)
+{
+	struct page *page;
+
+	page = get_page_from_freelist(gfp_mask, order,
+			alloc_flags|ALLOC_CPUSET, ac);
+	/*
+	 * fallback to ignore cpuset restriction if our nodes
+	 * are depleted
+	 */
+	if (!page)
+		page = get_page_from_freelist(gfp_mask, order,
+				alloc_flags, ac);
+
+	return page;
+}
+
 static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	const struct alloc_context *ac, unsigned long *did_some_progress)
@@ -3119,17 +3139,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
 		*did_some_progress = 1;
 
-		if (gfp_mask & __GFP_NOFAIL) {
-			page = get_page_from_freelist(gfp_mask, order,
-					ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac);
-			/*
-			 * fallback to ignore cpuset restriction if our nodes
-			 * are depleted
-			 */
-			if (!page)
-				page = get_page_from_freelist(gfp_mask, order,
+		/*
+		 * Help non-failing allocations by giving them access to memory
+		 * reserves
+		 */
+		if (gfp_mask & __GFP_NOFAIL)
+			page = __alloc_pages_cpuset_fallback(gfp_mask, order,
 					ALLOC_NO_WATERMARKS, ac);
-		}
 	}
 out:
 	mutex_unlock(&oom_lock);
@@ -3785,6 +3801,16 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		 */
 		WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
 
+		/*
+		 * Help non-failing allocations by giving them access to memory
+		 * reserves but do not use ALLOC_NO_WATERMARKS because this
+		 * could deplete whole memory reserves which would just make
+		 * the situation worse
+		 */
+		page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
+		if (page)
+			goto got_pg;
+
 		cond_resched();
 		goto retry;
 	}