1 files changed, 97 insertions, 41 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index d487f8dc6d39..501820c815b3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -521,6 +521,52 @@ static const char *action_name[] = {
 	[RECOVERED] = "Recovered",
 };
 
+enum action_page_type {
+	MSG_KERNEL,
+	MSG_KERNEL_HIGH_ORDER,
+	MSG_SLAB,
+	MSG_DIFFERENT_COMPOUND,
+	MSG_POISONED_HUGE,
+	MSG_HUGE,
+	MSG_FREE_HUGE,
+	MSG_UNMAP_FAILED,
+	MSG_DIRTY_SWAPCACHE,
+	MSG_CLEAN_SWAPCACHE,
+	MSG_DIRTY_MLOCKED_LRU,
+	MSG_CLEAN_MLOCKED_LRU,
+	MSG_DIRTY_UNEVICTABLE_LRU,
+	MSG_CLEAN_UNEVICTABLE_LRU,
+	MSG_DIRTY_LRU,
+	MSG_CLEAN_LRU,
+	MSG_TRUNCATED_LRU,
+	MSG_BUDDY,
+	MSG_BUDDY_2ND,
+	MSG_UNKNOWN,
+};
+
+static const char * const action_page_types[] = {
+	[MSG_KERNEL]			= "reserved kernel page",
+	[MSG_KERNEL_HIGH_ORDER]		= "high-order kernel page",
+	[MSG_SLAB]			= "kernel slab page",
+	[MSG_DIFFERENT_COMPOUND]	= "different compound page after locking",
+	[MSG_POISONED_HUGE]		= "huge page already hardware poisoned",
+	[MSG_HUGE]			= "huge page",
+	[MSG_FREE_HUGE]			= "free huge page",
+	[MSG_UNMAP_FAILED]		= "unmapping failed page",
+	[MSG_DIRTY_SWAPCACHE]		= "dirty swapcache page",
+	[MSG_CLEAN_SWAPCACHE]		= "clean swapcache page",
+	[MSG_DIRTY_MLOCKED_LRU]		= "dirty mlocked LRU page",
+	[MSG_CLEAN_MLOCKED_LRU]		= "clean mlocked LRU page",
+	[MSG_DIRTY_UNEVICTABLE_LRU]	= "dirty unevictable LRU page",
+	[MSG_CLEAN_UNEVICTABLE_LRU]	= "clean unevictable LRU page",
+	[MSG_DIRTY_LRU]			= "dirty LRU page",
+	[MSG_CLEAN_LRU]			= "clean LRU page",
+	[MSG_TRUNCATED_LRU]		= "already truncated LRU page",
+	[MSG_BUDDY]			= "free buddy page",
+	[MSG_BUDDY_2ND]			= "free buddy page (2nd try)",
+	[MSG_UNKNOWN]			= "unknown page",
+};
+
 /*
  * XXX: It is possible that a page is isolated from LRU cache,
  * and then kept in swap cache or failed to remove from page cache.
@@ -777,10 +823,10 @@ static int me_huge_page(struct page *p, unsigned long pfn)
 static struct page_state {
 	unsigned long mask;
 	unsigned long res;
-	char *msg;
+	enum action_page_type type;
 	int (*action)(struct page *p, unsigned long pfn);
 } error_states[] = {
-	{ reserved,	reserved,	"reserved kernel",	me_kernel },
+	{ reserved,	reserved,	MSG_KERNEL,	me_kernel },
 	/*
 	 * free pages are specially detected outside this table:
 	 * PG_buddy pages only make a small fraction of all free pages.
@@ -791,31 +837,31 @@ static struct page_state {
 	 * currently unused objects without touching them. But just
 	 * treat it as standard kernel for now.
 	 */
-	{ slab,		slab,		"kernel slab",	me_kernel },
+	{ slab,		slab,		MSG_SLAB,	me_kernel },
 
 #ifdef CONFIG_PAGEFLAGS_EXTENDED
-	{ head,		head,		"huge",		me_huge_page },
-	{ tail,		tail,		"huge",		me_huge_page },
+	{ head,		head,		MSG_HUGE,		me_huge_page },
+	{ tail,		tail,		MSG_HUGE,		me_huge_page },
 #else
-	{ compound,	compound,	"huge",		me_huge_page },
+	{ compound,	compound,	MSG_HUGE,		me_huge_page },
 #endif
 
-	{ sc|dirty,	sc|dirty,	"dirty swapcache",	me_swapcache_dirty },
-	{ sc|dirty,	sc,		"clean swapcache",	me_swapcache_clean },
+	{ sc|dirty,	sc|dirty,	MSG_DIRTY_SWAPCACHE,	me_swapcache_dirty },
+	{ sc|dirty,	sc,		MSG_CLEAN_SWAPCACHE,	me_swapcache_clean },
 
-	{ mlock|dirty,	mlock|dirty,	"dirty mlocked LRU",	me_pagecache_dirty },
-	{ mlock|dirty,	mlock,		"clean mlocked LRU",	me_pagecache_clean },
+	{ mlock|dirty,	mlock|dirty,	MSG_DIRTY_MLOCKED_LRU,	me_pagecache_dirty },
+	{ mlock|dirty,	mlock,		MSG_CLEAN_MLOCKED_LRU,	me_pagecache_clean },
 
-	{ unevict|dirty, unevict|dirty,	"dirty unevictable LRU", me_pagecache_dirty },
-	{ unevict|dirty, unevict,	"clean unevictable LRU", me_pagecache_clean },
+	{ unevict|dirty, unevict|dirty,	MSG_DIRTY_UNEVICTABLE_LRU,	me_pagecache_dirty },
+	{ unevict|dirty, unevict,	MSG_CLEAN_UNEVICTABLE_LRU,	me_pagecache_clean },
 
-	{ lru|dirty,	lru|dirty,	"dirty LRU",	me_pagecache_dirty },
-	{ lru|dirty,	lru,		"clean LRU",	me_pagecache_clean },
+	{ lru|dirty,	lru|dirty,	MSG_DIRTY_LRU,	me_pagecache_dirty },
+	{ lru|dirty,	lru,		MSG_CLEAN_LRU,	me_pagecache_clean },
 
 	/*
 	 * Catchall entry: must be at end.
 	 */
-	{ 0,		0,		"unknown page state",	me_unknown },
+	{ 0,		0,		MSG_UNKNOWN,	me_unknown },
 };
 
 #undef dirty
@@ -835,10 +881,10 @@ static struct page_state {
  * "Dirty/Clean" indication is not 100% accurate due to the possibility of
  * setting PG_dirty outside page lock. See also comment above set_page_dirty().
  */
-static void action_result(unsigned long pfn, char *msg, int result)
+static void action_result(unsigned long pfn, enum action_page_type type, int result)
 {
-	pr_err("MCE %#lx: %s page recovery: %s\n",
-		pfn, msg, action_name[result]);
+	pr_err("MCE %#lx: recovery action for %s: %s\n",
+		pfn, action_page_types[type], action_name[result]);
 }
 
 static int page_action(struct page_state *ps, struct page *p,
@@ -854,11 +900,11 @@ static int page_action(struct page_state *ps, struct page *p,
 		count--;
 	if (count != 0) {
 		printk(KERN_ERR
-		       "MCE %#lx: %s page still referenced by %d users\n",
-		       pfn, ps->msg, count);
+		       "MCE %#lx: %s still referenced by %d users\n",
+		       pfn, action_page_types[ps->type], count);
 		result = FAILED;
 	}
-	action_result(pfn, ps->msg, result);
+	action_result(pfn, ps->type, result);
 
 	/* Could do more checks here if page looks ok */
 	/*
@@ -1106,7 +1152,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	if (!(flags & MF_COUNT_INCREASED) &&
 		!get_page_unless_zero(hpage)) {
 		if (is_free_buddy_page(p)) {
-			action_result(pfn, "free buddy", DELAYED);
+			action_result(pfn, MSG_BUDDY, DELAYED);
 			return 0;
 		} else if (PageHuge(hpage)) {
 			/*
@@ -1123,12 +1169,12 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			}
 			set_page_hwpoison_huge_page(hpage);
 			res = dequeue_hwpoisoned_huge_page(hpage);
-			action_result(pfn, "free huge",
+			action_result(pfn, MSG_FREE_HUGE,
 				      res ? IGNORED : DELAYED);
 			unlock_page(hpage);
 			return res;
 		} else {
-			action_result(pfn, "high order kernel", IGNORED);
+			action_result(pfn, MSG_KERNEL_HIGH_ORDER, IGNORED);
 			return -EBUSY;
 		}
 	}
@@ -1141,18 +1187,19 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
 	 */
-	if (!PageHuge(p) && !PageTransTail(p)) {
-		if (!PageLRU(p))
-			shake_page(p, 0);
-		if (!PageLRU(p)) {
+	if (!PageHuge(p)) {
+		if (!PageLRU(hpage))
+			shake_page(hpage, 0);
+		if (!PageLRU(hpage)) {
 			/*
 			 * shake_page could have turned it free.
 			 */
 			if (is_free_buddy_page(p)) {
 				if (flags & MF_COUNT_INCREASED)
-					action_result(pfn, "free buddy", DELAYED);
+					action_result(pfn, MSG_BUDDY, DELAYED);
 				else
-					action_result(pfn, "free buddy, 2nd try", DELAYED);
+					action_result(pfn, MSG_BUDDY_2ND,
+						      DELAYED);
 				return 0;
 			}
 		}
@@ -1165,7 +1212,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * If this happens just bail out.
 	 */
 	if (compound_head(p) != hpage) {
-		action_result(pfn, "different compound page after locking", IGNORED);
+		action_result(pfn, MSG_DIFFERENT_COMPOUND, IGNORED);
 		res = -EBUSY;
 		goto out;
 	}
@@ -1205,8 +1252,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * on the head page to show that the hugepage is hwpoisoned
 	 */
 	if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) {
-		action_result(pfn, "hugepage already hardware poisoned",
-				IGNORED);
+		action_result(pfn, MSG_POISONED_HUGE, IGNORED);
 		unlock_page(hpage);
 		put_page(hpage);
 		return 0;
@@ -1235,7 +1281,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
 	    != SWAP_SUCCESS) {
-		action_result(pfn, "unmapping failed", IGNORED);
+		action_result(pfn, MSG_UNMAP_FAILED, IGNORED);
 		res = -EBUSY;
 		goto out;
 	}
@@ -1244,7 +1290,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 * Torn down by someone else?
 	 */
 	if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
-		action_result(pfn, "already truncated LRU", IGNORED);
+		action_result(pfn, MSG_TRUNCATED_LRU, IGNORED);
 		res = -EBUSY;
 		goto out;
 	}
@@ -1540,8 +1586,18 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	}
 	unlock_page(hpage);
 
-	/* Keep page count to indicate a given hugepage is isolated. */
-	list_move(&hpage->lru, &pagelist);
+	ret = isolate_huge_page(hpage, &pagelist);
+	if (ret) {
+		/*
+		 * get_any_page() and isolate_huge_page() takes a refcount each,
+		 * so need to drop one here.
+		 */
+		put_page(hpage);
+	} else {
+		pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
+		return -EBUSY;
+	}
+
 	ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 				MIGRATE_SYNC, MR_MEMORY_FAILURE);
 	if (ret) {
@@ -1721,12 +1777,12 @@ int soft_offline_page(struct page *page, int flags)
 	} else if (ret == 0) { /* for free pages */
 		if (PageHuge(page)) {
 			set_page_hwpoison_huge_page(hpage);
-			dequeue_hwpoisoned_huge_page(hpage);
-			atomic_long_add(1 << compound_order(hpage),
+			if (!dequeue_hwpoisoned_huge_page(hpage))
+				atomic_long_add(1 << compound_order(hpage),
 					&num_poisoned_pages);
 		} else {
-			SetPageHWPoison(page);
-			atomic_long_inc(&num_poisoned_pages);
+			if (!TestSetPageHWPoison(page))
+				atomic_long_inc(&num_poisoned_pages);
 		}
 	}
 	unset_migratetype_isolate(page, MIGRATE_MOVABLE);