Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "9 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/vmstat: fix overflow in mod_zone_page_state()
  ocfs2/dlm: clear migration_pending when migration target goes down
  mm/memory_hotplug.c: check for missing sections in test_pages_in_a_zone()
  ocfs2: fix flock panic issue
  m32r: add io*_rep helpers
  m32r: fix build failure
  arch/x86/xen/suspend.c: include xen/xen.h
  mm: memcontrol: fix possible memcg leak due to interrupted reclaim
  ocfs2: fix BUG when calculate new backup super

10 files changed, 102 insertions, 39 deletions

diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index fd104bd221ce..860e440611c9 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -3,6 +3,7 @@ generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
+generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += module.h
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 61b8931bc192..4b0f5e001d4d 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -168,13 +168,21 @@ static inline void _writel(unsigned long l, unsigned long addr)
 #define writew_relaxed writew
 #define writel_relaxed writel
 
-#define ioread8 read
+#define ioread8 readb
 #define ioread16 readw
 #define ioread32 readl
 #define iowrite8 writeb
 #define iowrite16 writew
 #define iowrite32 writel
 
+#define ioread8_rep(p, dst, count) insb((unsigned long)(p), (dst), (count))
+#define ioread16_rep(p, dst, count) insw((unsigned long)(p), (dst), (count))
+#define ioread32_rep(p, dst, count) insl((unsigned long)(p), (dst), (count))
+
+#define iowrite8_rep(p, src, count) outsb((unsigned long)(p), (src), (count))
+#define iowrite16_rep(p, src, count) outsw((unsigned long)(p), (src), (count))
+#define iowrite32_rep(p, src, count) outsl((unsigned long)(p), (src), (count))
+
 #define ioread16be(addr)	be16_to_cpu(readw(addr))
 #define ioread32be(addr)	be32_to_cpu(readl(addr))
 #define iowrite16be(v, addr)	writew(cpu_to_be16(v), (addr))
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 3705eabd7e22..df0c40559583 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -1,6 +1,7 @@
 #include <linux/types.h>
 #include <linux/tick.h>
 
+#include <xen/xen.h>
 #include <xen/interface/xen.h>
 #include <xen/grant_table.h>
 #include <xen/events.h>
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index ce38b4ccc9ab..84f2f8079466 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2843,6 +2843,8 @@ again:
 	res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY;
 	if (!ret)
 		BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING));
+	else
+		res->migration_pending = 0;
 	spin_unlock(&res->spinlock);
 
 	/*
diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c
index 652ece4a9d9e..d56f0079b858 100644
--- a/fs/ocfs2/locks.c
+++ b/fs/ocfs2/locks.c
@@ -67,7 +67,10 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode,
 		 */
 
 		locks_lock_file_wait(file,
-				     &(struct file_lock){.fl_type = F_UNLCK});
+				&(struct file_lock) {
+					.fl_type = F_UNLCK,
+					.fl_flags = FL_FLOCK
+				});
 
 		ocfs2_file_unlock(file);
 	}
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index d5da6f624142..79b8021302b3 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -54,11 +54,12 @@
 static u16 ocfs2_calc_new_backup_super(struct inode *inode,
 				       struct ocfs2_group_desc *gd,
 				       u16 cl_cpg,
+				       u16 old_bg_clusters,
 				       int set)
 {
 	int i;
 	u16 backups = 0;
-	u32 cluster;
+	u32 cluster, lgd_cluster;
 	u64 blkno, gd_blkno, lgd_blkno = le64_to_cpu(gd->bg_blkno);
 
 	for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) {
@@ -71,6 +72,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode,
 		else if (gd_blkno > lgd_blkno)
 			break;
 
+		/* check if already done backup super */
+		lgd_cluster = ocfs2_blocks_to_clusters(inode->i_sb, lgd_blkno);
+		lgd_cluster += old_bg_clusters;
+		if (lgd_cluster >= cluster)
+			continue;
+
 		if (set)
 			ocfs2_set_bit(cluster % cl_cpg,
 				      (unsigned long *)gd->bg_bitmap);
@@ -99,6 +106,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 	u16 chain, num_bits, backups = 0;
 	u16 cl_bpc = le16_to_cpu(cl->cl_bpc);
 	u16 cl_cpg = le16_to_cpu(cl->cl_cpg);
+	u16 old_bg_clusters;
 
 	trace_ocfs2_update_last_group_and_inode(new_clusters,
 						first_new_cluster);
@@ -112,6 +120,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 
 	group = (struct ocfs2_group_desc *)group_bh->b_data;
 
+	old_bg_clusters = le16_to_cpu(group->bg_bits) / cl_bpc;
 	/* update the group first. */
 	num_bits = new_clusters * cl_bpc;
 	le16_add_cpu(&group->bg_bits, num_bits);
@@ -125,7 +134,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
 				     OCFS2_FEATURE_COMPAT_BACKUP_SB)) {
 		backups = ocfs2_calc_new_backup_super(bm_inode,
 						     group,
-						     cl_cpg, 1);
+						     cl_cpg, old_bg_clusters, 1);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
 	}
 
@@ -163,7 +172,7 @@ out_rollback:
 	if (ret < 0) {
 		ocfs2_calc_new_backup_super(bm_inode,
 					    group,
-					    cl_cpg, 0);
+					    cl_cpg, old_bg_clusters, 0);
 		le16_add_cpu(&group->bg_free_bits_count, backups);
 		le16_add_cpu(&group->bg_bits, -1 * num_bits);
 		le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 5dbc8b0ee567..3e5d9075960f 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -176,11 +176,11 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
 
 #ifdef CONFIG_SMP
-void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
+void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
 void __inc_zone_page_state(struct page *, enum zone_stat_item);
 void __dec_zone_page_state(struct page *, enum zone_stat_item);
 
-void mod_zone_page_state(struct zone *, enum zone_stat_item, int);
+void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
 void inc_zone_page_state(struct page *, enum zone_stat_item);
 void dec_zone_page_state(struct page *, enum zone_stat_item);
 
@@ -205,7 +205,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
  * The functions directly modify the zone and global counters.
  */
 static inline void __mod_zone_page_state(struct zone *zone,
-			enum zone_stat_item item, int delta)
+			enum zone_stat_item item, long delta)
 {
 	zone_page_state_add(delta, zone, item);
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e234c21a5e6c..fc10620967c7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -903,14 +903,20 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		if (prev && reclaim->generation != iter->generation)
 			goto out_unlock;
 
-		do {
+		while (1) {
 			pos = READ_ONCE(iter->position);
+			if (!pos || css_tryget(&pos->css))
+				break;
 			/*
-			 * A racing update may change the position and
-			 * put the last reference, hence css_tryget(),
-			 * or retry to see the updated position.
+			 * css reference reached zero, so iter->position will
+			 * be cleared by ->css_released. However, we should not
+			 * rely on this happening soon, because ->css_released
+			 * is called from a work queue, and by busy-waiting we
+			 * might block it. So we clear iter->position right
+			 * away.
 			 */
-		} while (pos && !css_tryget(&pos->css));
+			(void)cmpxchg(&iter->position, pos, NULL);
+		}
 	}
 
 	if (pos)
@@ -956,17 +962,13 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	}
 
 	if (reclaim) {
-		if (cmpxchg(&iter->position, pos, memcg) == pos) {
-			if (memcg)
-				css_get(&memcg->css);
-			if (pos)
-				css_put(&pos->css);
-		}
-
 		/*
-		 * pairs with css_tryget when dereferencing iter->position
-		 * above.
+		 * The position could have already been updated by a competing
+		 * thread, so check that the value hasn't changed since we read
+		 * it to avoid reclaiming from the same cgroup twice.
 		 */
+		(void)cmpxchg(&iter->position, pos, memcg);
+
 		if (pos)
 			css_put(&pos->css);
 
@@ -999,6 +1001,28 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
 		css_put(&prev->css);
 }
 
+static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+{
+	struct mem_cgroup *memcg = dead_memcg;
+	struct mem_cgroup_reclaim_iter *iter;
+	struct mem_cgroup_per_zone *mz;
+	int nid, zid;
+	int i;
+
+	while ((memcg = parent_mem_cgroup(memcg))) {
+		for_each_node(nid) {
+			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+				mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
+				for (i = 0; i <= DEF_PRIORITY; i++) {
+					iter = &mz->iter[i];
+					cmpxchg(&iter->position,
+						dead_memcg, NULL);
+				}
+			}
+		}
+	}
+}
+
 /*
  * Iteration constructs for visiting all cgroups (under a tree).  If
  * loops are exited prematurely (break), mem_cgroup_iter_break() must
@@ -4324,6 +4348,13 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	wb_memcg_offline(memcg);
 }
 
+static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	invalidate_reclaim_iterators(memcg);
+}
+
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
@@ -5185,6 +5216,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.css_alloc = mem_cgroup_css_alloc,
 	.css_online = mem_cgroup_css_online,
 	.css_offline = mem_cgroup_css_offline,
+	.css_released = mem_cgroup_css_released,
 	.css_free = mem_cgroup_css_free,
 	.css_reset = mem_cgroup_css_reset,
 	.can_attach = mem_cgroup_can_attach,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 67d488ab495e..a042a9d537bb 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1375,23 +1375,30 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
  */
 int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 {
-	unsigned long pfn;
+	unsigned long pfn, sec_end_pfn;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
-	for (pfn = start_pfn;
+	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
 	     pfn < end_pfn;
-	     pfn += MAX_ORDER_NR_PAGES) {
-		i = 0;
-		/* This is just a CONFIG_HOLES_IN_ZONE check.*/
-		while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i))
-			i++;
-		if (i == MAX_ORDER_NR_PAGES)
+	     pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+		/* Make sure the memory section is present first */
+		if (!present_section_nr(pfn_to_section_nr(pfn)))
 			continue;
-		page = pfn_to_page(pfn + i);
-		if (zone && page_zone(page) != zone)
-			return 0;
-		zone = page_zone(page);
+		for (; pfn < sec_end_pfn && pfn < end_pfn;
+		     pfn += MAX_ORDER_NR_PAGES) {
+			i = 0;
+			/* This is just a CONFIG_HOLES_IN_ZONE check.*/
+			while ((i < MAX_ORDER_NR_PAGES) &&
+				!pfn_valid_within(pfn + i))
+				i++;
+			if (i == MAX_ORDER_NR_PAGES)
+				continue;
+			page = pfn_to_page(pfn + i);
+			if (zone && page_zone(page) != zone)
+				return 0;
+			zone = page_zone(page);
+		}
 	}
 	return 1;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0d5712b0206c..4ebc17d948cb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -219,7 +219,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat,
  * particular counter cannot be updated from interrupt context.
  */
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-				int delta)
+			   long delta)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
 	s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -318,8 +318,8 @@ EXPORT_SYMBOL(__dec_zone_page_state);
  *     1       Overstepping half of threshold
  *     -1      Overstepping minus half of threshold
 */
-static inline void mod_state(struct zone *zone,
-       enum zone_stat_item item, int delta, int overstep_mode)
+static inline void mod_state(struct zone *zone, enum zone_stat_item item,
+			     long delta, int overstep_mode)
 {
 	struct per_cpu_pageset __percpu *pcp = zone->pageset;
 	s8 __percpu *p = pcp->vm_stat_diff + item;
@@ -357,7 +357,7 @@ static inline void mod_state(struct zone *zone,
 }
 
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
+			 long delta)
 {
 	mod_state(zone, item, delta, 0);
 }
@@ -384,7 +384,7 @@ EXPORT_SYMBOL(dec_zone_page_state);
  * Use interrupt disable to serialize counter updates
  */
 void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
+			 long delta)
 {
 	unsigned long flags;