Merge branch 'master' into for-2.6.35

Conflicts:
	fs/block_dev.c

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

6 files changed, 69 insertions, 25 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f13e067e1467..707d0dc6da0f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -11,6 +11,8 @@
 #include <linux/writeback.h>
 #include <linux/device.h>
 
+static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
 void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
 {
 }
@@ -25,6 +27,11 @@ struct backing_dev_info default_backing_dev_info = {
 };
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
+struct backing_dev_info noop_backing_dev_info = {
+	.name		= "noop",
+};
+EXPORT_SYMBOL_GPL(noop_backing_dev_info);
+
 static struct class *bdi_class;
 
 /*
@@ -715,6 +722,33 @@ void bdi_destroy(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_destroy);
 
+/*
+ * For use from filesystems to quickly init and register a bdi associated
+ * with dirty writeback
+ */
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
+			   unsigned int cap)
+{
+	char tmp[32];
+	int err;
+
+	bdi->name = name;
+	bdi->capabilities = cap;
+	err = bdi_init(bdi);
+	if (err)
+		return err;
+
+	sprintf(tmp, "%.28s%s", name, "-%d");
+	err = bdi_register(bdi, NULL, tmp, atomic_long_inc_return(&bdi_seq));
+	if (err) {
+		bdi_destroy(bdi);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(bdi_setup_and_register);
+
 static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6034dc9e9796..ffbdfc86aedf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -546,6 +546,7 @@ static void free_huge_page(struct page *page)
 
 	mapping = (struct address_space *) page_private(page);
 	set_page_private(page, 0);
+	page->mapping = NULL;
 	BUG_ON(page_count(page));
 	INIT_LIST_HEAD(&page->lru);
 
@@ -2447,8 +2448,10 @@ retry:
 			spin_lock(&inode->i_lock);
 			inode->i_blocks += blocks_per_huge_page(h);
 			spin_unlock(&inode->i_lock);
-		} else
+		} else {
 			lock_page(page);
+			page->mapping = HUGETLB_POISON;
+		}
 	}
 
 	/*
diff --git a/mm/ksm.c b/mm/ksm.c
index 8cdfc2a1e8bf..956880f2ff49 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -365,7 +365,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 	do {
 		cond_resched();
 		page = follow_page(vma, addr, FOLL_GET);
-		if (!page)
+		if (IS_ERR_OR_NULL(page))
 			break;
 		if (PageKsm(page))
 			ret = handle_mm_fault(vma->vm_mm, vma, addr,
@@ -447,7 +447,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 		goto out;
 
 	page = follow_page(vma, addr, FOLL_GET);
-	if (!page)
+	if (IS_ERR_OR_NULL(page))
 		goto out;
 	if (PageAnon(page)) {
 		flush_anon_page(vma, page, addr);
@@ -1086,7 +1086,7 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
 		cond_resched();
 		tree_rmap_item = rb_entry(*new, struct rmap_item, node);
 		tree_page = get_mergeable_page(tree_rmap_item);
-		if (!tree_page)
+		if (IS_ERR_OR_NULL(tree_page))
 			return NULL;
 
 		/*
@@ -1294,7 +1294,7 @@ next_mm:
 			if (ksm_test_exit(mm))
 				break;
 			*page = follow_page(vma, ksm_scan.address, FOLL_GET);
-			if (*page && PageAnon(*page)) {
+			if (!IS_ERR_OR_NULL(*page) && PageAnon(*page)) {
 				flush_anon_page(vma, *page, ksm_scan.address);
 				flush_dcache_page(*page);
 				rmap_item = get_next_rmap_item(slot,
@@ -1308,7 +1308,7 @@ next_mm:
 				up_read(&mm->mmap_sem);
 				return rmap_item;
 			}
-			if (*page)
+			if (!IS_ERR_OR_NULL(*page))
 				put_page(*page);
 			ksm_scan.address += PAGE_SIZE;
 			cond_resched();
@@ -1367,7 +1367,7 @@ next_mm:
 static void ksm_do_scan(unsigned int scan_npages)
 {
 	struct rmap_item *rmap_item;
-	struct page *page;
+	struct page *uninitialized_var(page);
 
 	while (scan_npages--) {
 		cond_resched();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f4ede99c8b9b..6c755de385f7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2429,11 +2429,11 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
 	}
 	unlock_page_cgroup(pc);
 
+	*ptr = mem;
 	if (mem) {
-		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
+		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false);
 		css_put(&mem->css);
 	}
-	*ptr = mem;
 	return ret;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index f90ea92f755a..456ec6f27889 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1977,7 +1977,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
 		return 0;
 
 	/* Clean everything up if vma_adjust failed. */
-	new->vm_ops->close(new);
+	if (new->vm_ops && new->vm_ops->close)
+		new->vm_ops->close(new);
 	if (new->vm_file) {
 		if (vma->vm_flags & VM_EXECUTABLE)
 			removed_exe_file_vma(mm);
diff --git a/mm/rmap.c b/mm/rmap.c
index 4bad3267537a..07fc94758799 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -133,8 +133,8 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 				goto out_enomem_free_avc;
 			allocated = anon_vma;
 		}
-		spin_lock(&anon_vma->lock);
 
+		spin_lock(&anon_vma->lock);
 		/* page_table_lock to protect against threads */
 		spin_lock(&mm->page_table_lock);
 		if (likely(!vma->anon_vma)) {
@@ -144,14 +144,15 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 			list_add(&avc->same_vma, &vma->anon_vma_chain);
 			list_add(&avc->same_anon_vma, &anon_vma->head);
 			allocated = NULL;
+			avc = NULL;
 		}
 		spin_unlock(&mm->page_table_lock);
-
 		spin_unlock(&anon_vma->lock);
-		if (unlikely(allocated)) {
+
+		if (unlikely(allocated))
 			anon_vma_free(allocated);
+		if (unlikely(avc))
 			anon_vma_chain_free(avc);
-		}
 	}
 	return 0;
 
@@ -730,23 +731,28 @@ void page_move_anon_rmap(struct page *page,
  * @page:	the page to add the mapping to
  * @vma:	the vm area in which the mapping is added
  * @address:	the user virtual address mapped
+ * @exclusive:	the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct page *page,
-	struct vm_area_struct *vma, unsigned long address)
+	struct vm_area_struct *vma, unsigned long address, int exclusive)
 {
-	struct anon_vma_chain *avc;
-	struct anon_vma *anon_vma;
+	struct anon_vma *anon_vma = vma->anon_vma;
 
-	BUG_ON(!vma->anon_vma);
+	BUG_ON(!anon_vma);
 
 	/*
-	 * We must use the _oldest_ possible anon_vma for the page mapping!
+	 * If the page isn't exclusively mapped into this vma,
+	 * we must use the _oldest_ possible anon_vma for the
+	 * page mapping!
 	 *
-	 * So take the last AVC chain entry in the vma, which is the deepest
-	 * ancestor, and use the anon_vma from that.
+	 * So take the last AVC chain entry in the vma, which is
+	 * the deepest ancestor, and use the anon_vma from that.
 	 */
-	avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma);
-	anon_vma = avc->anon_vma;
+	if (!exclusive) {
+		struct anon_vma_chain *avc;
+		avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma);
+		anon_vma = avc->anon_vma;
+	}
 
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	page->mapping = (struct address_space *) anon_vma;
@@ -802,7 +808,7 @@ void page_add_anon_rmap(struct page *page,
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	if (first)
-		__page_set_anon_rmap(page, vma, address);
+		__page_set_anon_rmap(page, vma, address, 0);
 	else
 		__page_check_anon_rmap(page, vma, address);
 }
@@ -824,7 +830,7 @@ void page_add_new_anon_rmap(struct page *page,
 	SetPageSwapBacked(page);
 	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
 	__inc_zone_page_state(page, NR_ANON_PAGES);
-	__page_set_anon_rmap(page, vma, address);
+	__page_set_anon_rmap(page, vma, address, 1);
 	if (page_evictable(page, vma))
 		lru_cache_add_lru(page, LRU_ACTIVE_ANON);
 	else