Merge branch 'linus' into core/iommu

22 files changed, 272 insertions, 175 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index 736ba7f..b6ec85a 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -198,7 +198,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 			flags &= MAP_NONBLOCK;
 			get_file(file);
 			addr = mmap_region(file, start, size,
-					flags, vma->vm_flags, pgoff, 1);
+					flags, vma->vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 618e983..107da3d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2269,12 +2269,18 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 
 int hugetlb_reserve_pages(struct inode *inode,
 					long from, long to,
-					struct vm_area_struct *vma)
+					struct vm_area_struct *vma,
+					int acctflag)
 {
 	long ret, chg;
 	struct hstate *h = hstate_inode(inode);
 
-	if (vma && vma->vm_flags & VM_NORESERVE)
+	/*
+	 * Only apply hugepage reservation if asked. At fault time, an
+	 * attempt will be made for VM_NORESERVE to allocate a page
+	 * and filesystem quota without using reserves
+	 */
+	if (acctflag & VM_NORESERVE)
 		return 0;
 
 	/*
@@ -2299,13 +2305,31 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (chg < 0)
 		return chg;
 
+	/* There must be enough filesystem quota for the mapping */
 	if (hugetlb_get_quota(inode->i_mapping, chg))
 		return -ENOSPC;
+
+	/*
+	 * Check enough hugepages are available for the reservation.
+	 * Hand back the quota if there are not
+	 */
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugetlb_put_quota(inode->i_mapping, chg);
 		return ret;
 	}
+
+	/*
+	 * Account for the reservations made. Shared mappings record regions
+	 * that have reservations as they are shared by multiple VMAs.
+	 * When the last VMA disappears, the region map says how much
+	 * the reservation was and the page cache tells how much of
+	 * the reservation was consumed. Private mappings are per-VMA and
+	 * only the consumed reservations are tracked. When the VMA
+	 * disappears, the original reservation is the VMA size and the
+	 * consumed reservations are stored in the map. Hence, nothing
+	 * else has to be done for private mappings here
+	 */
 	if (!vma || vma->vm_flags & VM_SHARED)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4d0ea3c..8e4be9c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -202,6 +202,7 @@ pcg_default_flags[NR_CHARGE_TYPE] = {
 
 static void mem_cgroup_get(struct mem_cgroup *mem);
 static void mem_cgroup_put(struct mem_cgroup *mem);
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 					 struct page_cgroup *pc,
@@ -1684,7 +1685,7 @@ move_account:
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
 		ret = 0;
-		for_each_node_state(node, N_POSSIBLE) {
+		for_each_node_state(node, N_HIGH_MEMORY) {
 			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
 				enum lru_list l;
 				for_each_lru(l) {
@@ -2193,10 +2194,23 @@ static void mem_cgroup_get(struct mem_cgroup *mem)
 
 static void mem_cgroup_put(struct mem_cgroup *mem)
 {
-	if (atomic_dec_and_test(&mem->refcnt))
+	if (atomic_dec_and_test(&mem->refcnt)) {
+		struct mem_cgroup *parent = parent_mem_cgroup(mem);
 		__mem_cgroup_free(mem);
+		if (parent)
+			mem_cgroup_put(parent);
+	}
 }
 
+/*
+ * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
+ */
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem)
+{
+	if (!mem->res.parent)
+		return NULL;
+	return mem_cgroup_from_res_counter(mem->res.parent, res);
+}
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 static void __init enable_swap_cgroup(void)
@@ -2235,6 +2249,13 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	if (parent && parent->use_hierarchy) {
 		res_counter_init(&mem->res, &parent->res);
 		res_counter_init(&mem->memsw, &parent->memsw);
+		/*
+		 * We increment refcnt of the parent to ensure that we can
+		 * safely access it on res_counter_charge/uncharge.
+		 * This refcnt will be decremented when freeing this
+		 * mem_cgroup(see mem_cgroup_put).
+		 */
+		mem_cgroup_get(parent);
 	} else {
 		res_counter_init(&mem->res, NULL);
 		res_counter_init(&mem->memsw, NULL);
diff --git a/mm/memory.c b/mm/memory.c
index 22bfa7a..baa999e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1999,7 +1999,7 @@ gotten:
 	 * Don't let another task, with possibly unlocked vma,
 	 * keep the mlocked page.
 	 */
-	if (vma->vm_flags & VM_LOCKED) {
+	if ((vma->vm_flags & VM_LOCKED) && old_page) {
 		lock_page(old_page);	/* for LRU manipulation */
 		clear_page_mlock(old_page);
 		unlock_page(old_page);
diff --git a/mm/migrate.c b/mm/migrate.c
index 2bb4e1d..a9eff3f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1129,7 +1129,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
  	struct vm_area_struct *vma;
  	int err = 0;
 
- 	for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) {
+	for (vma = mm->mmap; vma && !err; vma = vma->vm_next) {
  		if (vma->vm_ops && vma->vm_ops->migrate) {
  			err = vma->vm_ops->migrate(vma, to, from, flags);
  			if (err)
diff --git a/mm/mlock.c b/mm/mlock.c
index 2904a34..cbe9e05 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -294,14 +294,10 @@ static inline int __mlock_posix_error_return(long retval)
  *
  * return number of pages [> 0] to be removed from locked_vm on success
  * of "special" vmas.
- *
- * return negative error if vma spanning @start-@range disappears while
- * mmap semaphore is dropped.  Unlikely?
  */
 long mlock_vma_pages_range(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	int nr_pages = (end - start) / PAGE_SIZE;
 	BUG_ON(!(vma->vm_flags & VM_LOCKED));
 
@@ -314,20 +310,11 @@ long mlock_vma_pages_range(struct vm_area_struct *vma,
 	if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
 			is_vm_hugetlb_page(vma) ||
 			vma == get_gate_vma(current))) {
-		long error;
-		downgrade_write(&mm->mmap_sem);
 
-		error = __mlock_vma_pages_range(vma, start, end, 1);
+		__mlock_vma_pages_range(vma, start, end, 1);
 
-		up_read(&mm->mmap_sem);
-		/* vma can change or disappear */
-		down_write(&mm->mmap_sem);
-		vma = find_vma(mm, start);
-		/* non-NULL vma must contain @start, but need to check @end */
-		if (!vma ||  end > vma->vm_end)
-			return -ENOMEM;
-
-		return 0;	/* hide other errors from mmap(), et al */
+		/* Hide errors from mmap() and other callers */
+		return 0;
 	}
 
 	/*
@@ -438,41 +425,14 @@ success:
 	vma->vm_flags = newflags;
 
 	if (lock) {
-		/*
-		 * mmap_sem is currently held for write.  Downgrade the write
-		 * lock to a read lock so that other faults, mmap scans, ...
-		 * while we fault in all pages.
-		 */
-		downgrade_write(&mm->mmap_sem);
-
 		ret = __mlock_vma_pages_range(vma, start, end, 1);
 
-		/*
-		 * Need to reacquire mmap sem in write mode, as our callers
-		 * expect this.  We have no support for atomically upgrading
-		 * a sem to write, so we need to check for ranges while sem
-		 * is unlocked.
-		 */
-		up_read(&mm->mmap_sem);
-		/* vma can change or disappear */
-		down_write(&mm->mmap_sem);
-		*prev = find_vma(mm, start);
-		/* non-NULL *prev must contain @start, but need to check @end */
-		if (!(*prev) || end > (*prev)->vm_end)
-			ret = -ENOMEM;
-		else if (ret > 0) {
+		if (ret > 0) {
 			mm->locked_vm -= ret;
 			ret = 0;
 		} else
 			ret = __mlock_posix_error_return(ret); /* translate if needed */
 	} else {
-		/*
-		 * TODO:  for unlocking, pages will already be resident, so
-		 * we don't need to wait for allocations/reclaim/pagein, ...
-		 * However, unlocking a very large region can still take a
-		 * while.  Should we downgrade the semaphore for both lock
-		 * AND unlock ?
-		 */
 		__mlock_vma_pages_range(vma, start, end, 0);
 	}
 
@@ -700,7 +660,7 @@ void *alloc_locked_buffer(size_t size)
 	return buffer;
 }
 
-void free_locked_buffer(void *buffer, size_t size)
+void release_locked_buffer(void *buffer, size_t size)
 {
 	unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
 
@@ -710,6 +670,11 @@ void free_locked_buffer(void *buffer, size_t size)
 	current->mm->locked_vm -= pgsz;
 
 	up_write(&current->mm->mmap_sem);
+}
+
+void free_locked_buffer(void *buffer, size_t size)
+{
+	release_locked_buffer(buffer, size);
 
 	kfree(buffer);
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 8d95902..00ced3e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -658,6 +658,9 @@ again:			remove_next = 1 + (end > next->vm_end);
 	validate_mm(mm);
 }
 
+/* Flags that can be inherited from an existing mapping when merging */
+#define VM_MERGEABLE_FLAGS (VM_CAN_NONLINEAR)
+
 /*
  * If the vma has a ->close operation then the driver probably needs to release
  * per-vma resources, so we don't attempt to merge those.
@@ -665,7 +668,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags)
 {
-	if (vma->vm_flags != vm_flags)
+	if ((vma->vm_flags ^ vm_flags) & ~VM_MERGEABLE_FLAGS)
 		return 0;
 	if (vma->vm_file != file)
 		return 0;
@@ -915,7 +918,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	struct inode *inode;
 	unsigned int vm_flags;
 	int error;
-	int accountable = 1;
 	unsigned long reqprot = prot;
 
 	/*
@@ -1016,8 +1018,6 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 					return -EPERM;
 				vm_flags &= ~VM_MAYEXEC;
 			}
-			if (is_file_hugepages(file))
-				accountable = 0;
 
 			if (!file->f_op || !file->f_op->mmap)
 				return -ENODEV;
@@ -1050,8 +1050,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	if (error)
 		return error;
 
-	return mmap_region(file, addr, len, flags, vm_flags, pgoff,
-			   accountable);
+	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
 
@@ -1087,10 +1086,25 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 		mapping_cap_account_dirty(vma->vm_file->f_mapping);
 }
 
+/*
+ * We account for memory if it's a private writeable mapping,
+ * not hugepages and VM_NORESERVE wasn't set.
+ */
+static inline int accountable_mapping(struct file *file, unsigned int vm_flags)
+{
+	/*
+	 * hugetlb has its own accounting separate from the core VM
+	 * VM_HUGETLB may not be set yet so we cannot check for that flag.
+	 */
+	if (file && is_file_hugepages(file))
+		return 0;
+
+	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
+}
+
 unsigned long mmap_region(struct file *file, unsigned long addr,
 			  unsigned long len, unsigned long flags,
-			  unsigned int vm_flags, unsigned long pgoff,
-			  int accountable)
+			  unsigned int vm_flags, unsigned long pgoff)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
@@ -1114,38 +1128,38 @@ munmap_back:
 	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
 		return -ENOMEM;
 
-	if (flags & MAP_NORESERVE)
-		vm_flags |= VM_NORESERVE;
+	/*
+	 * Set 'VM_NORESERVE' if we should not account for the
+	 * memory use of this mapping.
+	 */
+	if ((flags & MAP_NORESERVE)) {
+		/* We honor MAP_NORESERVE if allowed to overcommit */
+		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+			vm_flags |= VM_NORESERVE;
 
-	if (accountable && (!(flags & MAP_NORESERVE) ||
-			    sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
-		if (vm_flags & VM_SHARED) {
-			/* Check memory availability in shmem_file_setup? */
-			vm_flags |= VM_ACCOUNT;
-		} else if (vm_flags & VM_WRITE) {
-			/*
-			 * Private writable mapping: check memory availability
-			 */
-			charged = len >> PAGE_SHIFT;
-			if (security_vm_enough_memory(charged))
-				return -ENOMEM;
-			vm_flags |= VM_ACCOUNT;
-		}
+		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
+		if (file && is_file_hugepages(file))
+			vm_flags |= VM_NORESERVE;
 	}
 
 	/*
-	 * Can we just expand an old private anonymous mapping?
-	 * The VM_SHARED test is necessary because shmem_zero_setup
-	 * will create the file object for a shared anonymous map below.
+	 * Private writable mapping: check memory availability
 	 */
-	if (!file && !(vm_flags & VM_SHARED)) {
-		vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
-					NULL, NULL, pgoff, NULL);
-		if (vma)
-			goto out;
+	if (accountable_mapping(file, vm_flags)) {
+		charged = len >> PAGE_SHIFT;
+		if (security_vm_enough_memory(charged))
+			return -ENOMEM;
+		vm_flags |= VM_ACCOUNT;
 	}
 
 	/*
+	 * Can we just expand an old mapping?
+	 */
+	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
+	if (vma)
+		goto out;
+
+	/*
 	 * Determine the object being mapped and call the appropriate
 	 * specific mapper. the address has already been validated, but
 	 * not unmapped, but the maps are removed from the list.
@@ -1186,14 +1200,6 @@ munmap_back:
 			goto free_vma;
 	}
 
-	/* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
-	 * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
-	 * that memory reservation must be checked; but that reservation
-	 * belongs to shared memory object, not to vma: so now clear it.
-	 */
-	if ((vm_flags & (VM_SHARED|VM_ACCOUNT)) == (VM_SHARED|VM_ACCOUNT))
-		vma->vm_flags &= ~VM_ACCOUNT;
-
 	/* Can addr have changed??
 	 *
 	 * Answer: Yes, several device drivers can do it in their
@@ -1206,17 +1212,8 @@ munmap_back:
 	if (vma_wants_writenotify(vma))
 		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
 
-	if (file && vma_merge(mm, prev, addr, vma->vm_end,
-			vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
-		mpol_put(vma_policy(vma));
-		kmem_cache_free(vm_area_cachep, vma);
-		fput(file);
-		if (vm_flags & VM_EXECUTABLE)
-			removed_exe_file_vma(mm);
-	} else {
-		vma_link(mm, vma, prev, rb_link, rb_parent);
-		file = vma->vm_file;
-	}
+	vma_link(mm, vma, prev, rb_link, rb_parent);
+	file = vma->vm_file;
 
 	/* Once vma denies write, undo our temporary denial count */
 	if (correct_wcount)
@@ -2087,12 +2084,8 @@ void exit_mmap(struct mm_struct *mm)
 	unsigned long end;
 
 	/* mm's last user has gone, and its about to be pulled down */
-	arch_exit_mmap(mm);
 	mmu_notifier_release(mm);
 
-	if (!mm->mmap)	/* Can happen if dup_mmap() received an OOM */
-		return;
-
 	if (mm->locked_vm) {
 		vma = mm->mmap;
 		while (vma) {
@@ -2101,7 +2094,13 @@ void exit_mmap(struct mm_struct *mm)
 			vma = vma->vm_next;
 		}
 	}
+
+	arch_exit_mmap(mm);
+
 	vma = mm->mmap;
+	if (!vma)	/* Can happen if dup_mmap() received an OOM */
+		return;
+
 	lru_add_drain();
 	flush_cache_mm(mm);
 	tlb = tlb_gather_mmu(mm, 1);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index abe2694..258197b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -151,10 +151,11 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
-	 * make it unwritable again.
+	 * make it unwritable again. hugetlb mapping were accounted for
+	 * even if read-only so there is no need to account for them here
 	 */
 	if (newflags & VM_WRITE) {
-		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|
+		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
 						VM_SHARED|VM_NORESERVE))) {
 			charged = nrpages;
 			if (security_vm_enough_memory(charged))
diff --git a/mm/nommu.c b/mm/nommu.c
index 8cee8c8..2fcf47d 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -10,7 +10,7 @@
  *  Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
  *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
  *  Copyright (c) 2002      Greg Ungerer <gerg@snapgear.com>
- *  Copyright (c) 2007-2008 Paul Mundt <lethal@linux-sh.org>
+ *  Copyright (c) 2007-2009 Paul Mundt <lethal@linux-sh.org>
  */
 
 #include <linux/module.h>
@@ -394,6 +394,24 @@ void vunmap(const void *addr)
 }
 EXPORT_SYMBOL(vunmap);
 
+void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
+{
+	BUG();
+	return NULL;
+}
+EXPORT_SYMBOL(vm_map_ram);
+
+void vm_unmap_ram(const void *mem, unsigned int count)
+{
+	BUG();
+}
+EXPORT_SYMBOL(vm_unmap_ram);
+
+void vm_unmap_aliases(void)
+{
+}
+EXPORT_SYMBOL_GPL(vm_unmap_aliases);
+
 /*
  * Implement a stub for vmalloc_sync_all() if the architecture chose not to
  * have one.
@@ -1143,8 +1161,8 @@ error_free:
 	return ret;
 
 enomem:
-	printk("Allocation of length %lu from process %d failed\n",
-	       len, current->pid);
+	printk("Allocation of length %lu from process %d (%s) failed\n",
+	       len, current->pid, current->comm);
 	show_free_areas();
 	return -ENOMEM;
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b493db7..74dc57c 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -209,7 +209,7 @@ int dirty_bytes_handler(struct ctl_table *table, int write,
 		struct file *filp, void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
-	int old_bytes = vm_dirty_bytes;
+	unsigned long old_bytes = vm_dirty_bytes;
 	int ret;
 
 	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
@@ -240,7 +240,7 @@ void bdi_writeout_inc(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL_GPL(bdi_writeout_inc);
 
-static inline void task_dirty_inc(struct task_struct *tsk)
+void task_dirty_inc(struct task_struct *tsk)
 {
 	prop_inc_single(&vm_dirties, &tsk->dirties);
 }
@@ -1051,13 +1051,25 @@ continue_unlock:
 				}
  			}
 
-			if (wbc->sync_mode == WB_SYNC_NONE) {
-				wbc->nr_to_write--;
-				if (wbc->nr_to_write <= 0) {
+			if (nr_to_write > 0) {
+				nr_to_write--;
+				if (nr_to_write == 0 &&
+				    wbc->sync_mode == WB_SYNC_NONE) {
+					/*
+					 * We stop writing back only if we are
+					 * not doing integrity sync. In case of
+					 * integrity sync we have to keep going
+					 * because someone may be concurrently
+					 * dirtying pages, and we might have
+					 * synced a lot of newly appeared dirty
+					 * pages, but have not synced all of the
+					 * old dirty pages.
+					 */
 					done = 1;
 					break;
 				}
 			}
+
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
 				done = 1;
@@ -1067,7 +1079,7 @@ continue_unlock:
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-	if (!cycled) {
+	if (!cycled && !done) {
 		/*
 		 * range_cyclic:
 		 * We hit the last page and there is more work to be done: wrap
@@ -1218,6 +1230,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 				__inc_zone_page_state(page, NR_FILE_DIRTY);
 				__inc_bdi_stat(mapping->backing_dev_info,
 						BDI_RECLAIMABLE);
+				task_dirty_inc(current);
 				task_io_account_write(PAGE_CACHE_SIZE);
 			}
 			radix_tree_tag_set(&mapping->page_tree,
@@ -1250,7 +1263,7 @@ EXPORT_SYMBOL(redirty_page_for_writepage);
  * If the mapping doesn't provide a set_page_dirty a_op, then
  * just fall through and assume that it wants buffer_heads.
  */
-static int __set_page_dirty(struct page *page)
+int set_page_dirty(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
@@ -1268,14 +1281,6 @@ static int __set_page_dirty(struct page *page)
 	}
 	return 0;
 }
-
-int set_page_dirty(struct page *page)
-{
-	int ret = __set_page_dirty(page);
-	if (ret)
-		task_dirty_inc(current);
-	return ret;
-}
 EXPORT_SYMBOL(set_page_dirty);
 
 /*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5675b30..5c44ed4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2989,7 +2989,7 @@ static int __meminit next_active_region_index_in_nid(int index, int nid)
  * was used and there are no special requirements, this is a convenient
  * alternative
  */
-int __meminit early_pfn_to_nid(unsigned long pfn)
+int __meminit __early_pfn_to_nid(unsigned long pfn)
 {
 	int i;
 
@@ -3000,10 +3000,33 @@ int __meminit early_pfn_to_nid(unsigned long pfn)
 		if (start_pfn <= pfn && pfn < end_pfn)
 			return early_node_map[i].nid;
 	}
+	/* This is a memory hole */
+	return -1;
+}
+#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+
+int __meminit early_pfn_to_nid(unsigned long pfn)
+{
+	int nid;
 
+	nid = __early_pfn_to_nid(pfn);
+	if (nid >= 0)
+		return nid;
+	/* just returns 0 */
 	return 0;
 }
-#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+
+#ifdef CONFIG_NODES_SPAN_OTHER_NODES
+bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
+{
+	int nid;
+
+	nid = __early_pfn_to_nid(pfn);
+	if (nid >= 0 && nid != node)
+		return false;
+	return true;
+}
+#endif
 
 /* Basic iterator support to walk early_node_map[] */
 #define for_each_active_range_index_in_nid(i, nid) \
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 7006a11..ceecfbb 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -114,7 +114,8 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn)
 		nid = page_to_nid(pfn_to_page(pfn));
 		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
 		if (slab_is_available()) {
-			base = kmalloc_node(table_size, GFP_KERNEL, nid);
+			base = kmalloc_node(table_size,
+					GFP_KERNEL | __GFP_NOWARN, nid);
 			if (!base)
 				base = vmalloc_node(table_size, nid);
 		} else {
diff --git a/mm/page_io.c b/mm/page_io.c
index dc6ce0a..3023c47 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -111,7 +111,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		goto out;
 	}
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		rw |= (1 << BIO_RW_SYNC);
+		rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
 	count_vm_event(PSWPOUT);
 	set_page_writeback(page);
 	unlock_page(page);
diff --git a/mm/rmap.c b/mm/rmap.c
index ac4af8c..1652166 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1072,7 +1072,8 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
 	spin_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		if (MLOCK_PAGES && unlikely(unlock)) {
-			if (!(vma->vm_flags & VM_LOCKED))
+			if (!((vma->vm_flags & VM_LOCKED) &&
+						page_mapped_in_vma(page, vma)))
 				continue;	/* must visit all vmas */
 			ret = SWAP_MLOCK;
 		} else {
diff --git a/mm/shmem.c b/mm/shmem.c
index 5d0de96..4103a23 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -169,13 +169,13 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
  */
 static inline int shmem_acct_size(unsigned long flags, loff_t size)
 {
-	return (flags & VM_ACCOUNT) ?
-		security_vm_enough_memory_kern(VM_ACCT(size)) : 0;
+	return (flags & VM_NORESERVE) ?
+		0 : security_vm_enough_memory_kern(VM_ACCT(size));
 }
 
 static inline void shmem_unacct_size(unsigned long flags, loff_t size)
 {
-	if (flags & VM_ACCOUNT)
+	if (!(flags & VM_NORESERVE))
 		vm_unacct_memory(VM_ACCT(size));
 }
 
@@ -187,13 +187,13 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size)
  */
 static inline int shmem_acct_block(unsigned long flags)
 {
-	return (flags & VM_ACCOUNT) ?
-		0 : security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE));
+	return (flags & VM_NORESERVE) ?
+		security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0;
 }
 
 static inline void shmem_unacct_blocks(unsigned long flags, long pages)
 {
-	if (!(flags & VM_ACCOUNT))
+	if (flags & VM_NORESERVE)
 		vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
 }
 
@@ -1515,8 +1515,8 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
-static struct inode *
-shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
+static struct inode *shmem_get_inode(struct super_block *sb, int mode,
+					dev_t dev, unsigned long flags)
 {
 	struct inode *inode;
 	struct shmem_inode_info *info;
@@ -1537,6 +1537,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
 		info = SHMEM_I(inode);
 		memset(info, 0, (char *)inode - (char *)info);
 		spin_lock_init(&info->lock);
+		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->swaplist);
 
 		switch (mode & S_IFMT) {
@@ -1779,9 +1780,10 @@ static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
 static int
 shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 {
-	struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev);
+	struct inode *inode;
 	int error = -ENOSPC;
 
+	inode = shmem_get_inode(dir->i_sb, mode, dev, VM_NORESERVE);
 	if (inode) {
 		error = security_inode_init_security(inode, dir, NULL, NULL,
 						     NULL);
@@ -1920,7 +1922,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 	if (len > PAGE_CACHE_SIZE)
 		return -ENAMETOOLONG;
 
-	inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
+	inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE);
 	if (!inode)
 		return -ENOSPC;
 
@@ -2332,7 +2334,7 @@ static int shmem_fill_super(struct super_block *sb,
 	sb->s_flags |= MS_POSIXACL;
 #endif
 
-	inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0);
+	inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
 	if (!inode)
 		goto failed;
 	inode->i_uid = sbinfo->uid;
@@ -2574,12 +2576,12 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
 	return 0;
 }
 
-#define shmem_file_operations ramfs_file_operations
-#define shmem_vm_ops generic_file_vm_ops
-#define shmem_get_inode ramfs_get_inode
-#define shmem_acct_size(a, b) 0
-#define shmem_unacct_size(a, b) do {} while (0)
-#define SHMEM_MAX_BYTES LLONG_MAX
+#define shmem_vm_ops				generic_file_vm_ops
+#define shmem_file_operations			ramfs_file_operations
+#define shmem_get_inode(sb, mode, dev, flags)	ramfs_get_inode(sb, mode, dev)
+#define shmem_acct_size(flags, size)		0
+#define shmem_unacct_size(flags, size)		do {} while (0)
+#define SHMEM_MAX_BYTES				LLONG_MAX
 
 #endif /* CONFIG_SHMEM */
 
@@ -2589,7 +2591,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
  * shmem_file_setup - get an unlinked file living in tmpfs
  * @name: name for dentry (to be seen in /proc/<pid>/maps
  * @size: size to be set for the file
- * @flags: vm_flags
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
  */
 struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 {
@@ -2623,13 +2625,10 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 		goto put_dentry;
 
 	error = -ENOSPC;
-	inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
+	inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0, flags);
 	if (!inode)
 		goto close_file;
 
-#ifdef CONFIG_SHMEM
-	SHMEM_I(inode)->flags = flags & VM_ACCOUNT;
-#endif
 	d_instantiate(dentry, inode);
 	inode->i_size = size;
 	inode->i_nlink = 0;	/* It is unlinked */
diff --git a/mm/slab.c b/mm/slab.c
index ddc41f3..4d00855 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4457,3 +4457,4 @@ size_t ksize(const void *objp)
 
 	return obj_size(virt_to_cache(objp));
 }
+EXPORT_SYMBOL(ksize);
diff --git a/mm/slob.c b/mm/slob.c
index bf7e8fc..52bc8a2 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -521,6 +521,7 @@ size_t ksize(const void *block)
 	} else
 		return sp->page.private;
 }
+EXPORT_SYMBOL(ksize);
 
 struct kmem_cache {
 	unsigned int size, align;
diff --git a/mm/slub.c b/mm/slub.c
index 6392ae5..0280eee 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1996,7 +1996,7 @@ static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,
 static void free_kmem_cache_cpu(struct kmem_cache_cpu *c, int cpu)
 {
 	if (c < per_cpu(kmem_cache_cpu, cpu) ||
-			c > per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
+			c >= per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
 		kfree(c);
 		return;
 	}
@@ -2736,6 +2736,7 @@ size_t ksize(const void *object)
 	 */
 	return s->size;
 }
+EXPORT_SYMBOL(ksize);
 
 void kfree(const void *x)
 {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f48b831..312fafe 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -635,7 +635,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 
 		if (!bdev) {
 			if (bdev_p)
-				*bdev_p = sis->bdev;
+				*bdev_p = bdget(sis->bdev->bd_dev);
 
 			spin_unlock(&swap_lock);
 			return i;
@@ -647,7 +647,7 @@ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
 					struct swap_extent, list);
 			if (se->start_block == offset) {
 				if (bdev_p)
-					*bdev_p = sis->bdev;
+					*bdev_p = bdget(sis->bdev->bd_dev);
 
 				spin_unlock(&swap_lock);
 				bdput(bdev);
@@ -698,8 +698,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	pte_t *pte;
 	int ret = 1;
 
-	if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr))
+	if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr)) {
 		ret = -ENOMEM;
+		goto out_nolock;
+	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
@@ -723,6 +725,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	activate_page(page);
 out:
 	pte_unmap_unlock(pte, ptl);
+out_nolock:
 	return ret;
 }
 
diff --git a/mm/util.c b/mm/util.c
index cb00b74..37eaccd 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -129,6 +129,26 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags)
 }
 EXPORT_SYMBOL(krealloc);
 
+/**
+ * kzfree - like kfree but zero memory
+ * @p: object to free memory of
+ *
+ * The memory of the object @p points to is zeroed before freed.
+ * If @p is %NULL, kzfree() does nothing.
+ */
+void kzfree(const void *p)
+{
+	size_t ks;
+	void *mem = (void *)p;
+
+	if (unlikely(ZERO_OR_NULL_PTR(mem)))
+		return;
+	ks = ksize(mem);
+	memset(mem, 0, ks);
+	kfree(mem);
+}
+EXPORT_SYMBOL(kzfree);
+
 /*
  * strndup_user - duplicate an existing string from user space
  * @s: The string to duplicate
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 75f49d3..520a759 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -323,6 +323,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	unsigned long addr;
 	int purged = 0;
 
+	BUG_ON(!size);
 	BUG_ON(size & ~PAGE_MASK);
 
 	va = kmalloc_node(sizeof(struct vmap_area),
@@ -334,6 +335,9 @@ retry:
 	addr = ALIGN(vstart, align);
 
 	spin_lock(&vmap_area_lock);
+	if (addr + size - 1 < addr)
+		goto overflow;
+
 	/* XXX: could have a last_hole cache */
 	n = vmap_area_root.rb_node;
 	if (n) {
@@ -365,6 +369,8 @@ retry:
 
 		while (addr + size > first->va_start && addr + size <= vend) {
 			addr = ALIGN(first->va_end + PAGE_SIZE, align);
+			if (addr + size - 1 < addr)
+				goto overflow;
 
 			n = rb_next(&first->rb_node);
 			if (n)
@@ -375,6 +381,7 @@ retry:
 	}
 found:
 	if (addr + size > vend) {
+overflow:
 		spin_unlock(&vmap_area_lock);
 		if (!purged) {
 			purge_vmap_area_lazy();
@@ -498,6 +505,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
 	static DEFINE_SPINLOCK(purge_lock);
 	LIST_HEAD(valist);
 	struct vmap_area *va;
+	struct vmap_area *n_va;
 	int nr = 0;
 
 	/*
@@ -537,7 +545,7 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
 
 	if (nr) {
 		spin_lock(&vmap_area_lock);
-		list_for_each_entry(va, &valist, purge_list)
+		list_for_each_entry_safe(va, n_va, &valist, purge_list)
 			__free_vmap_area(va);
 		spin_unlock(&vmap_area_lock);
 	}
@@ -1012,6 +1020,8 @@ void __init vmalloc_init(void)
 void unmap_kernel_range(unsigned long addr, unsigned long size)
 {
 	unsigned long end = addr + size;
+
+	flush_cache_vunmap(addr, end);
 	vunmap_page_range(addr, end);
 	flush_tlb_kernel_range(addr, end);
 }
@@ -1106,6 +1116,14 @@ struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 }
 EXPORT_SYMBOL_GPL(__get_vm_area);
 
+struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
+				       unsigned long start, unsigned long end,
+				       void *caller)
+{
+	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
+				  caller);
+}
+
 /**
  *	get_vm_area  -  reserve a contiguous kernel virtual area
  *	@size:		size of the area
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9a27c44..6177e3b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2057,31 +2057,31 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 				      int pass, struct scan_control *sc)
 {
 	struct zone *zone;
-	unsigned long nr_to_scan, ret = 0;
-	enum lru_list l;
+	unsigned long ret = 0;
 
 	for_each_zone(zone) {
+		enum lru_list l;
 
 		if (!populated_zone(zone))
 			continue;
-
 		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
 			continue;
 
 		for_each_evictable_lru(l) {
+			enum zone_stat_item ls = NR_LRU_BASE + l;
+			unsigned long lru_pages = zone_page_state(zone, ls);
+
 			/* For pass = 0, we don't shrink the active list */
-			if (pass == 0 &&
-				(l == LRU_ACTIVE || l == LRU_ACTIVE_FILE))
+			if (pass == 0 && (l == LRU_ACTIVE_ANON ||
+						l == LRU_ACTIVE_FILE))
 				continue;
 
-			zone->lru[l].nr_scan +=
-				(zone_page_state(zone, NR_LRU_BASE + l)
-								>> prio) + 1;
+			zone->lru[l].nr_scan += (lru_pages >> prio) + 1;
 			if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
+				unsigned long nr_to_scan;
+
 				zone->lru[l].nr_scan = 0;
-				nr_to_scan = min(nr_pages,
-					zone_page_state(zone,
-							NR_LRU_BASE + l));
+				nr_to_scan = min(nr_pages, lru_pages);
 				ret += shrink_list(l, nr_to_scan, zone,
 								sc, prio);
 				if (ret >= nr_pages)
@@ -2089,7 +2089,6 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 			}
 		}
 	}
-
 	return ret;
 }
 
@@ -2112,7 +2111,6 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 		.may_swap = 0,
 		.swap_cluster_max = nr_pages,
 		.may_writepage = 1,
-		.swappiness = vm_swappiness,
 		.isolate_pages = isolate_pages_global,
 	};
 
@@ -2146,10 +2144,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 		int prio;
 
 		/* Force reclaiming mapped pages in the passes #3 and #4 */
-		if (pass > 2) {
+		if (pass > 2)
 			sc.may_swap = 1;
-			sc.swappiness = 100;
-		}
 
 		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
 			unsigned long nr_to_scan = nr_pages - ret;