Merge tag 'v3.4-rc5' into next

Linux 3.4-rc5

Merge to pull in prerequisite change for Smack:
86812bb0de1a3758dc6c7aa01a763158a7c0638a

Requested by Casey.

11 files changed, 138 insertions, 56 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b8ce6f45095..5a16423a512 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -532,7 +532,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve)
 {
-	struct page *page;
+	struct page *page = NULL;
 	struct mempolicy *mpol;
 	nodemask_t *nodemask;
 	struct zonelist *zonelist;
@@ -2791,6 +2791,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * so no worry about deadlock.
 	 */
 	page = pte_page(entry);
+	get_page(page);
 	if (page != pagecache_page)
 		lock_page(page);
 
@@ -2822,6 +2823,7 @@ out_page_table_lock:
 	}
 	if (page != pagecache_page)
 		unlock_page(page);
+	put_page(page);
 
 out_mutex:
 	mutex_unlock(&hugetlb_instantiation_mutex);
diff --git a/mm/memblock.c b/mm/memblock.c
index 99f28559950..a44eab3157f 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -330,6 +330,9 @@ static int __init_memblock memblock_add_region(struct memblock_type *type,
 	phys_addr_t end = base + memblock_cap_size(base, &size);
 	int i, nr_new;
 
+	if (!size)
+		return 0;
+
 	/* special case for empty array */
 	if (type->regions[0].size == 0) {
 		WARN_ON(type->cnt != 1 || type->total_size);
@@ -430,6 +433,9 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 
 	*start_rgn = *end_rgn = 0;
 
+	if (!size)
+		return 0;
+
 	/* we'll create at most two more regions */
 	while (type->cnt + 2 > type->max)
 		if (memblock_double_array(type) < 0)
@@ -514,7 +520,6 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 		     (unsigned long long)base,
 		     (unsigned long long)base + size,
 		     (void *)_RET_IP_);
-	BUG_ON(0 == size);
 
 	return memblock_add_region(_rgn, base, size, MAX_NUMNODES);
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7d698df4a06..31ab9c3f017 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2165,7 +2165,7 @@ static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	if (action == CPU_ONLINE)
 		return NOTIFY_OK;
 
-	if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
 
 	for_each_mem_cgroup(iter)
@@ -2476,10 +2476,10 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 				       struct page *page,
 				       unsigned int nr_pages,
-				       struct page_cgroup *pc,
 				       enum charge_type ctype,
 				       bool lrucare)
 {
+	struct page_cgroup *pc = lookup_page_cgroup(page);
 	struct zone *uninitialized_var(zone);
 	bool was_on_lru = false;
 	bool anon;
@@ -2716,7 +2716,6 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 {
 	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
-	struct page_cgroup *pc;
 	bool oom = true;
 	int ret;
 
@@ -2730,11 +2729,10 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		oom = false;
 	}
 
-	pc = lookup_page_cgroup(page);
 	ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom);
 	if (ret == -ENOMEM)
 		return ret;
-	__mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype, false);
+	__mem_cgroup_commit_charge(memcg, page, nr_pages, ctype, false);
 	return 0;
 }
 
@@ -2831,16 +2829,13 @@ static void
 __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 					enum charge_type ctype)
 {
-	struct page_cgroup *pc;
-
 	if (mem_cgroup_disabled())
 		return;
 	if (!memcg)
 		return;
 	cgroup_exclude_rmdir(&memcg->css);
 
-	pc = lookup_page_cgroup(page);
-	__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype, true);
+	__mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
 	/*
 	 * Now swap is on-memory. This means this page may be
 	 * counted both as mem and swap....double count.
@@ -3298,14 +3293,13 @@ int mem_cgroup_prepare_migration(struct page *page,
 	 * page. In the case new page is migrated but not remapped, new page's
 	 * mapcount will be finally 0 and we call uncharge in end_migration().
 	 */
-	pc = lookup_page_cgroup(newpage);
 	if (PageAnon(page))
 		ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
 	else if (page_is_file_cache(page))
 		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
 	else
 		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype, false);
+	__mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false);
 	return ret;
 }
 
@@ -3392,7 +3386,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
 	 * LRU while we overwrite pc->mem_cgroup.
 	 */
-	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, type, true);
+	__mem_cgroup_commit_charge(memcg, newpage, 1, type, true);
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -3763,7 +3757,7 @@ move_account:
 			goto try_to_free;
 		cond_resched();
 	/* "ret" should also be checked to ensure all lists are empty. */
-	} while (memcg->res.usage > 0 || ret);
+	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
 out:
 	css_put(&memcg->css);
 	return ret;
@@ -3778,7 +3772,7 @@ try_to_free:
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
 	shrink = 1;
-	while (nr_retries && memcg->res.usage > 0) {
+	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
 		int progress;
 
 		if (signal_pending(current)) {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index cfb6c867875..b1956913752 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1361,11 +1361,14 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 
 	mm = get_task_mm(task);
 	put_task_struct(task);
-	if (mm)
-		err = do_migrate_pages(mm, old, new,
-			capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
-	else
+
+	if (!mm) {
 		err = -EINVAL;
+		goto out;
+	}
+
+	err = do_migrate_pages(mm, old, new,
+		capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
 
 	mmput(mm);
 out:
diff --git a/mm/migrate.c b/mm/migrate.c
index 51c08a0c6f6..11072383ae1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1388,14 +1388,14 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
 	mm = get_task_mm(task);
 	put_task_struct(task);
 
-	if (mm) {
-		if (nodes)
-			err = do_pages_move(mm, task_nodes, nr_pages, pages,
-					    nodes, status, flags);
-		else
-			err = do_pages_stat(mm, nr_pages, pages, status);
-	} else
-		err = -EINVAL;
+	if (!mm)
+		return -EINVAL;
+
+	if (nodes)
+		err = do_pages_move(mm, task_nodes, nr_pages, pages,
+				    nodes, status, flags);
+	else
+		err = do_pages_stat(mm, nr_pages, pages, status);
 
 	mmput(mm);
 	return err;
diff --git a/mm/mmap.c b/mm/mmap.c
index a7bf6a31c9f..848ef52d960 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -240,6 +240,8 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	return next;
 }
 
+static unsigned long do_brk(unsigned long addr, unsigned long len);
+
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long rlim, retval;
@@ -951,7 +953,7 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
  * The caller must hold down_write(&current->mm->mmap_sem).
  */
 
-unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+static unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
 			unsigned long flags, unsigned long pgoff)
 {
@@ -1087,7 +1089,32 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 
 	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
 }
-EXPORT_SYMBOL(do_mmap_pgoff);
+
+unsigned long do_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	if (unlikely(offset + PAGE_ALIGN(len) < offset))
+		return -EINVAL;
+	if (unlikely(offset & ~PAGE_MASK))
+		return -EINVAL;
+	return do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(do_mmap);
+
+unsigned long vm_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	unsigned long ret;
+	struct mm_struct *mm = current->mm;
+
+	down_write(&mm->mmap_sem);
+	ret = do_mmap(file, addr, len, prot, flag, offset);
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(vm_mmap);
 
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
@@ -2105,21 +2132,25 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 
 	return 0;
 }
-
 EXPORT_SYMBOL(do_munmap);
 
-SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+int vm_munmap(unsigned long start, size_t len)
 {
 	int ret;
 	struct mm_struct *mm = current->mm;
 
-	profile_munmap(addr);
-
 	down_write(&mm->mmap_sem);
-	ret = do_munmap(mm, addr, len);
+	ret = do_munmap(mm, start, len);
 	up_write(&mm->mmap_sem);
 	return ret;
 }
+EXPORT_SYMBOL(vm_munmap);
+
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+{
+	profile_munmap(addr);
+	return vm_munmap(addr, len);
+}
 
 static inline void verify_mm_writelocked(struct mm_struct *mm)
 {
@@ -2136,7 +2167,7 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-unsigned long do_brk(unsigned long addr, unsigned long len)
+static unsigned long do_brk(unsigned long addr, unsigned long len)
 {
 	struct mm_struct * mm = current->mm;
 	struct vm_area_struct * vma, * prev;
@@ -2232,7 +2263,17 @@ out:
 	return addr;
 }
 
-EXPORT_SYMBOL(do_brk);
+unsigned long vm_brk(unsigned long addr, unsigned long len)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long ret;
+
+	down_write(&mm->mmap_sem);
+	ret = do_brk(addr, len);
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(vm_brk);
 
 /* Release all mmaps. */
 void exit_mmap(struct mm_struct *mm)
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 24f0fc1a56d..e53bb8a256b 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -298,13 +298,19 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
+again:
 	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
 					 goal, -1ULL);
 	if (ptr)
 		return ptr;
 
-	return __alloc_memory_core_early(MAX_NUMNODES, size, align,
-					 goal, -1ULL);
+	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align,
+					goal, -1ULL);
+	if (!ptr && goal) {
+		goal = 0;
+		goto again;
+	}
+	return ptr;
 }
 
 void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
diff --git a/mm/nommu.c b/mm/nommu.c
index f59e170fceb..bb8f4f004a8 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1233,7 +1233,7 @@ enomem:
 /*
  * handle mapping creation for uClinux
  */
-unsigned long do_mmap_pgoff(struct file *file,
+static unsigned long do_mmap_pgoff(struct file *file,
 			    unsigned long addr,
 			    unsigned long len,
 			    unsigned long prot,
@@ -1470,7 +1470,32 @@ error_getting_region:
 	show_free_areas(0);
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(do_mmap_pgoff);
+
+unsigned long do_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	if (unlikely(offset + PAGE_ALIGN(len) < offset))
+		return -EINVAL;
+	if (unlikely(offset & ~PAGE_MASK))
+		return -EINVAL;
+	return do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(do_mmap);
+
+unsigned long vm_mmap(struct file *file, unsigned long addr,
+	unsigned long len, unsigned long prot,
+	unsigned long flag, unsigned long offset)
+{
+	unsigned long ret;
+	struct mm_struct *mm = current->mm;
+
+	down_write(&mm->mmap_sem);
+	ret = do_mmap(file, addr, len, prot, flag, offset);
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+EXPORT_SYMBOL(vm_mmap);
 
 SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
@@ -1709,16 +1734,22 @@ erase_whole_vma:
 }
 EXPORT_SYMBOL(do_munmap);
 
-SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+int vm_munmap(unsigned long addr, size_t len)
 {
-	int ret;
 	struct mm_struct *mm = current->mm;
+	int ret;
 
 	down_write(&mm->mmap_sem);
 	ret = do_munmap(mm, addr, len);
 	up_write(&mm->mmap_sem);
 	return ret;
 }
+EXPORT_SYMBOL(vm_munmap);
+
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
+{
+	return vm_munmap(addr, len);
+}
 
 /*
  * release all the mappings made in a process's VM space
@@ -1744,7 +1775,7 @@ void exit_mmap(struct mm_struct *mm)
 	kleave("");
 }
 
-unsigned long do_brk(unsigned long addr, unsigned long len)
+unsigned long vm_brk(unsigned long addr, unsigned long len)
 {
 	return -ENOMEM;
 }
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 9d3dd3763cf..4c5ff7f284d 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -26,7 +26,7 @@
  */
 static const struct address_space_operations swap_aops = {
 	.writepage	= swap_writepage,
-	.set_page_dirty	= __set_page_dirty_nobuffers,
+	.set_page_dirty	= __set_page_dirty_no_writeback,
 	.migratepage	= migrate_page,
 };
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 33c332bbab7..33dc256033b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1568,9 +1568,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 	reclaim_stat->recent_scanned[0] += nr_anon;
 	reclaim_stat->recent_scanned[1] += nr_file;
 
-	if (current_is_kswapd())
-		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
-	__count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
+	if (global_reclaim(sc)) {
+		if (current_is_kswapd())
+			__count_zone_vm_events(PGSTEAL_KSWAPD, zone,
+					       nr_reclaimed);
+		else
+			__count_zone_vm_events(PGSTEAL_DIRECT, zone,
+					       nr_reclaimed);
+	}
 
 	putback_inactive_pages(mz, &page_list);
 
@@ -2107,12 +2112,7 @@ restart:
 		 * with multiple processes reclaiming pages, the total
 		 * freeing target can get unreasonably large.
 		 */
-		if (nr_reclaimed >= nr_to_reclaim)
-			nr_to_reclaim = 0;
-		else
-			nr_to_reclaim -= nr_reclaimed;
-
-		if (!nr_to_reclaim && priority < DEF_PRIORITY)
+		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
 	blk_finish_plug(&plug);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f600557a765..7db1b9bab49 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -738,7 +738,8 @@ const char * const vmstat_text[] = {
 	"pgmajfault",
 
 	TEXTS_FOR_ZONES("pgrefill")
-	TEXTS_FOR_ZONES("pgsteal")
+	TEXTS_FOR_ZONES("pgsteal_kswapd")
+	TEXTS_FOR_ZONES("pgsteal_direct")
 	TEXTS_FOR_ZONES("pgscan_kswapd")
 	TEXTS_FOR_ZONES("pgscan_direct")
 
@@ -747,7 +748,6 @@ const char * const vmstat_text[] = {
 #endif
 	"pginodesteal",
 	"slabs_scanned",
-	"kswapd_steal",
 	"kswapd_inodesteal",
 	"kswapd_low_wmark_hit_quickly",
 	"kswapd_high_wmark_hit_quickly",