Merge branch 'akpm' (Fixes from Andrew)

Merge misc fixes from Andrew Morton: "Seven fixes, some of them fingers-crossed :(" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (7 patches) drivers/rtc/rtc-tps65910.c: fix invalid pointer access on _remove() mm: soft offline: split thp at the beginning of soft_offline_page() mm: avoid waking kswapd for THP allocations when compaction is deferred or contended revert "Revert "mm: remove __GFP_NO_KSWAPD"" mm: vmscan: fix endless loop in kswapd balancing mm/vmemmap: fix wrong use of virt_to_page mm: compaction: fix return value of capture_free_page()
yi-yang · Nov 30, 2012 · 50a53bb · 50a53bb
2 parents 73efd00 + 1430e17
commit 50a53bb
Show file tree

Hide file tree

Showing 8 changed files with 68 additions and 43 deletions.
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
@@ -1077,8 +1077,7 @@ EXPORT_SYMBOL_GPL(mtd_writev);
  * until the request succeeds or until the allocation size falls below
  * the system page size. This attempts to make sure it does not adversely
  * impact system performance, so when allocating more than one page, we
- * ask the memory allocator to avoid re-trying, swapping, writing back
- * or performing I/O.
+ * ask the memory allocator to avoid re-trying.
  *
  * Note, this function also makes sure that the allocated buffer is aligned to
  * the MTD device's min. I/O unit, i.e. the "mtd->writesize" value.
@@ -1092,8 +1091,7 @@ EXPORT_SYMBOL_GPL(mtd_writev);
  */
 void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size)
 {
-	gfp_t flags = __GFP_NOWARN | __GFP_WAIT |
-		       __GFP_NORETRY | __GFP_NO_KSWAPD;
+	gfp_t flags = __GFP_NOWARN | __GFP_WAIT | __GFP_NORETRY;
 	size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE);
 	void *kbuf;
 

diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c
@@ -288,11 +288,11 @@ static int __devinit tps65910_rtc_probe(struct platform_device *pdev)
 static int __devexit tps65910_rtc_remove(struct platform_device *pdev)
 {
 	/* leave rtc running, but disable irqs */
-	struct rtc_device *rtc = platform_get_drvdata(pdev);
+	struct tps65910_rtc *tps_rtc = platform_get_drvdata(pdev);
 
-	tps65910_rtc_alarm_irq_enable(&rtc->dev, 0);
+	tps65910_rtc_alarm_irq_enable(&pdev->dev, 0);
 
-	rtc_device_unregister(rtc);
+	rtc_device_unregister(tps_rtc->rtc);
 	return 0;
 }
 

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
@@ -30,10 +30,9 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL		0x20000u
 #define ___GFP_THISNODE		0x40000u
 #define ___GFP_RECLAIMABLE	0x80000u
-#define ___GFP_NOTRACK		0x200000u
-#define ___GFP_NO_KSWAPD	0x400000u
-#define ___GFP_OTHER_NODE	0x800000u
-#define ___GFP_WRITE		0x1000000u
+#define ___GFP_NOTRACK		0x100000u
+#define ___GFP_OTHER_NODE	0x200000u
+#define ___GFP_WRITE		0x400000u
 
 /*
  * GFP bitmasks..
@@ -86,7 +85,6 @@ struct vm_area_struct;
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
 #define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)  /* Don't track with kmemcheck */
 
-#define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */
 
@@ -96,7 +94,7 @@ struct vm_area_struct;
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 25	/* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 23	/* Room for N __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /* This equals 0, but use constants in case they ever change */
@@ -116,8 +114,7 @@ struct vm_area_struct;
 				 __GFP_MOVABLE)
 #define GFP_IOFS	(__GFP_IO | __GFP_FS)
 #define GFP_TRANSHUGE	(GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
-			 __GFP_NO_KSWAPD)
+			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN)
 
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)

diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
@@ -36,7 +36,6 @@
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
 	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
-	{(unsigned long)__GFP_NO_KSWAPD,	"GFP_NO_KSWAPD"},	\
 	{(unsigned long)__GFP_OTHER_NODE,	"GFP_OTHER_NODE"}	\
 	) : "GFP_NOWAIT"
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
@@ -1476,9 +1476,17 @@ int soft_offline_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
+	struct page *hpage = compound_trans_head(page);
 
 	if (PageHuge(page))
 		return soft_offline_huge_page(page, flags);
+	if (PageTransHuge(hpage)) {
+		if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
+			pr_info("soft offline: %#lx: failed to split THP\n",
+				pfn);
+			return -EBUSY;
+		}
+	}
 
 	ret = get_any_page(page, pfn, flags);
 	if (ret < 0)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
@@ -1422,7 +1422,7 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 		}
 	}
 
-	return 1UL << order;
+	return 1UL << alloc_order;
 }
 
 /*
@@ -2378,6 +2378,15 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
 	return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
 }
 
+/* Returns true if the allocation is likely for THP */
+static bool is_thp_alloc(gfp_t gfp_mask, unsigned int order)
+{
+	if (order == pageblock_order &&
+	    (gfp_mask & (__GFP_MOVABLE|__GFP_REPEAT)) == __GFP_MOVABLE)
+		return true;
+	return false;
+}
+
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
@@ -2416,9 +2425,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		goto nopage;
 
 restart:
-	if (!(gfp_mask & __GFP_NO_KSWAPD))
+	/* The decision whether to wake kswapd for THP is made later */
+	if (!is_thp_alloc(gfp_mask, order))
 		wake_all_kswapd(order, zonelist, high_zoneidx,
-						zone_idx(preferred_zone));
+					zone_idx(preferred_zone));
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -2488,15 +2498,21 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		goto got_pg;
 	sync_migration = true;
 
-	/*
-	 * If compaction is deferred for high-order allocations, it is because
-	 * sync compaction recently failed. In this is the case and the caller
-	 * requested a movable allocation that does not heavily disrupt the
-	 * system then fail the allocation instead of entering direct reclaim.
-	 */
-	if ((deferred_compaction || contended_compaction) &&
-						(gfp_mask & __GFP_NO_KSWAPD))
-		goto nopage;
+	if (is_thp_alloc(gfp_mask, order)) {
+		/*
+		 * If compaction is deferred for high-order allocations, it is
+		 * because sync compaction recently failed. If this is the case
+		 * and the caller requested a movable allocation that does not
+		 * heavily disrupt the system then fail the allocation instead
+		 * of entering direct reclaim.
+		 */
+		if (deferred_compaction || contended_compaction)
+			goto nopage;
+
+		/* If process is willing to reclaim/compact then wake kswapd */
+		wake_all_kswapd(order, zonelist, high_zoneidx,
+					zone_idx(preferred_zone));
+	}
 
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,

diff --git a/mm/sparse.c b/mm/sparse.c
@@ -617,7 +617,7 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 {
 	return; /* XXX: Not implemented yet */
 }
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 {
 }
 #else
@@ -658,10 +658,11 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 			   get_order(sizeof(struct page) * nr_pages));
 }
 
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
 	unsigned long magic;
+	struct page *page = virt_to_page(memmap);
 
 	for (i = 0; i < nr_pages; i++, page++) {
 		magic = (unsigned long) page->lru.next;
@@ -710,13 +711,10 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	 */
 
 	if (memmap) {
-		struct page *memmap_page;
-		memmap_page = virt_to_page(memmap);
-
 		nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
 			>> PAGE_SHIFT;
 
-		free_map_bootmem(memmap_page, nr_pages);
+		free_map_bootmem(memmap, nr_pages);
 	}
 }
 

diff --git a/mm/vmscan.c b/mm/vmscan.c
@@ -2414,6 +2414,19 @@ static void age_active_anon(struct zone *zone, struct scan_control *sc)
 	} while (memcg);
 }
 
+static bool zone_balanced(struct zone *zone, int order,
+			  unsigned long balance_gap, int classzone_idx)
+{
+	if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone) +
+				    balance_gap, classzone_idx, 0))
+		return false;
+
+	if (COMPACTION_BUILD && order && !compaction_suitable(zone, order))
+		return false;
+
+	return true;
+}
+
 /*
  * pgdat_balanced is used when checking if a node is balanced for high-order
  * allocations. Only zones that meet watermarks and are in a zone allowed
@@ -2492,8 +2505,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
 			continue;
 		}
 
-		if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
-							i, 0))
+		if (!zone_balanced(zone, order, 0, i))
 			all_zones_ok = false;
 		else
 			balanced += zone->present_pages;
@@ -2602,8 +2614,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				break;
 			}
 
-			if (!zone_watermark_ok_safe(zone, order,
-					high_wmark_pages(zone), 0, 0)) {
+			if (!zone_balanced(zone, order, 0, 0)) {
 				end_zone = i;
 				break;
 			} else {
@@ -2679,9 +2690,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				testorder = 0;
 
 			if ((buffer_heads_over_limit && is_highmem_idx(i)) ||
-				    !zone_watermark_ok_safe(zone, testorder,
-					high_wmark_pages(zone) + balance_gap,
-					end_zone, 0)) {
+			    !zone_balanced(zone, testorder,
+					   balance_gap, end_zone)) {
 				shrink_zone(zone, &sc);
 
 				reclaim_state->reclaimed_slab = 0;
@@ -2708,8 +2718,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 				continue;
 			}
 
-			if (!zone_watermark_ok_safe(zone, testorder,
-					high_wmark_pages(zone), end_zone, 0)) {
+			if (!zone_balanced(zone, testorder, 0, end_zone)) {
 				all_zones_ok = 0;
 				/*
 				 * We are still under min water mark.  This