---

yaml
---
r: 282997
b: refs/heads/master
c: f90ac39
h: refs/heads/master
i:
  282995: 2ea35dd
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 938929f14cb595f43cd1a4e63e22d36cab1e4a1f
+refs/heads/master: f90ac3982a78d36f894824636beeef13361d7c59

trunk/include/linux/gfp.h

@@ -368,9 +368,25 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
 void drain_all_pages(void);
 void drain_local_pages(void *dummy);
 
+/*
+ * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
+ * GFP flags are used before interrupts are enabled. Once interrupts are
+ * enabled, it is set to __GFP_BITS_MASK while the system is running. During
+ * hibernation, it is used by PM to avoid I/O during memory allocation while
+ * devices are suspended.
+ */
 extern gfp_t gfp_allowed_mask;
 
 extern void pm_restrict_gfp_mask(void);
 extern void pm_restore_gfp_mask(void);
 
+#ifdef CONFIG_PM_SLEEP
+extern bool pm_suspended_storage(void);
+#else
+static inline bool pm_suspended_storage(void)
+{
+	return false;
+}
+#endif /* CONFIG_PM_SLEEP */
+
 #endif /* __LINUX_GFP_H */

trunk/mm/page_alloc.c

@@ -127,6 +127,13 @@ void pm_restrict_gfp_mask(void)
 	saved_gfp_mask = gfp_allowed_mask;
 	gfp_allowed_mask &= ~GFP_IOFS;
 }
+
+bool pm_suspended_storage(void)
+{
+	if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+		return false;
+	return true;
+}
 #endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -1786,12 +1793,25 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 
 static inline int
 should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+				unsigned long did_some_progress,
 				unsigned long pages_reclaimed)
 {
 	/* Do not loop if specifically requested */
 	if (gfp_mask & __GFP_NORETRY)
 		return 0;
 
+	/* Always retry if specifically requested */
+	if (gfp_mask & __GFP_NOFAIL)
+		return 1;
+
+	/*
+	 * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim
+	 * making forward progress without invoking OOM. Suspend also disables
+	 * storage devices so kswapd will not help. Bail if we are suspending.
+	 */
+	if (!did_some_progress && pm_suspended_storage())
+		return 0;
+
 	/*
 	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
 	 * means __GFP_NOFAIL, but that may not be true in other
@@ -1810,13 +1830,6 @@ should_alloc_retry(gfp_t gfp_mask, unsigned int order,
 	if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
 		return 1;
 
-	/*
-	 * Don't let big-order allocations loop unless the caller
-	 * explicitly requests that.
-	 */
-	if (gfp_mask & __GFP_NOFAIL)
-		return 1;
-
 	return 0;
 }
 
@@ -2209,7 +2222,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 
 	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
-	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+	if (should_alloc_retry(gfp_mask, order, did_some_progress,
+						pages_reclaimed)) {
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto rebalance;

trunk/mm/swapfile.c

@@ -667,10 +667,10 @@ int try_to_free_swap(struct page *page)
 	 * original page might be freed under memory pressure, then
 	 * later read back in from swap, now with the wrong data.
 	 *
-	 * Hibernation clears bits from gfp_allowed_mask to prevent
-	 * memory reclaim from writing to disk, so check that here.
+	 * Hibration suspends storage while it is writing the image
+	 * to disk so check that here.
 	 */
-	if (!(gfp_allowed_mask & __GFP_IO))
+	if (pm_suspended_storage())
 		return 0;
 
 	delete_from_swap_cache(page);