1 files changed, 86 insertions, 24 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index aa68206bd517..0e5ec371ce72 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -356,7 +356,7 @@ static void free_more_memory(void)
 	for_each_online_pgdat(pgdat) {
 		zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones;
 		if (*zones)
-			try_to_free_pages(zones, GFP_NOFS);
+			try_to_free_pages(zones, 0, GFP_NOFS);
 	}
 }
 
@@ -676,6 +676,39 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
 EXPORT_SYMBOL(mark_buffer_dirty_inode);
 
 /*
+ * Mark the page dirty, and set it dirty in the radix tree, and mark the inode
+ * dirty.
+ *
+ * If warn is true, then emit a warning if the page is not uptodate and has
+ * not been truncated.
+ */
+static int __set_page_dirty(struct page *page,
+		struct address_space *mapping, int warn)
+{
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	if (TestSetPageDirty(page))
+		return 0;
+
+	write_lock_irq(&mapping->tree_lock);
+	if (page->mapping) {	/* Race with truncate? */
+		WARN_ON_ONCE(warn && !PageUptodate(page));
+
+		if (mapping_cap_account_dirty(mapping)) {
+			__inc_zone_page_state(page, NR_FILE_DIRTY);
+			task_io_account_write(PAGE_CACHE_SIZE);
+		}
+		radix_tree_tag_set(&mapping->page_tree,
+				page_index(page), PAGECACHE_TAG_DIRTY);
+	}
+	write_unlock_irq(&mapping->tree_lock);
+	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+
+	return 1;
+}
+
+/*
  * Add a page to the dirty page list.
  *
  * It is a sad fact of life that this function is called from several places
@@ -702,7 +735,7 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
  */
 int __set_page_dirty_buffers(struct page *page)
 {
-	struct address_space * const mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping(page);
 
 	if (unlikely(!mapping))
 		return !TestSetPageDirty(page);
@@ -719,21 +752,7 @@ int __set_page_dirty_buffers(struct page *page)
 	}
 	spin_unlock(&mapping->private_lock);
 
-	if (TestSetPageDirty(page))
-		return 0;
-
-	write_lock_irq(&mapping->tree_lock);
-	if (page->mapping) {	/* Race with truncate? */
-		if (mapping_cap_account_dirty(mapping)) {
-			__inc_zone_page_state(page, NR_FILE_DIRTY);
-			task_io_account_write(PAGE_CACHE_SIZE);
-		}
-		radix_tree_tag_set(&mapping->page_tree,
-				page_index(page), PAGECACHE_TAG_DIRTY);
-	}
-	write_unlock_irq(&mapping->tree_lock);
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-	return 1;
+	return __set_page_dirty(page, mapping, 1);
 }
 EXPORT_SYMBOL(__set_page_dirty_buffers);
 
@@ -982,7 +1001,7 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	struct buffer_head *bh;
 
 	page = find_or_create_page(inode->i_mapping, index,
-		mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
+		(mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE);
 	if (!page)
 		return NULL;
 
@@ -1026,11 +1045,6 @@ failed:
 /*
  * Create buffers for the specified block device block's page.  If
  * that page was dirty, the buffers are set dirty also.
- *
- * Except that's a bug.  Attaching dirty buffers to a dirty
- * blockdev's page can result in filesystem corruption, because
- * some of those buffers may be aliases of filesystem data.
- * grow_dev_page() will go BUG() if this happens.
  */
 static int
 grow_buffers(struct block_device *bdev, sector_t block, int size)
@@ -1137,8 +1151,9 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
  */
 void fastcall mark_buffer_dirty(struct buffer_head *bh)
 {
+	WARN_ON_ONCE(!buffer_uptodate(bh));
 	if (!buffer_dirty(bh) && !test_set_buffer_dirty(bh))
-		__set_page_dirty_nobuffers(bh->b_page);
+		__set_page_dirty(bh->b_page, page_mapping(bh->b_page), 0);
 }
 
 /*
@@ -2179,6 +2194,52 @@ int generic_commit_write(struct file *file, struct page *page,
 	return 0;
 }
 
+/*
+ * block_page_mkwrite() is not allowed to change the file size as it gets
+ * called from a page fault handler when a page is first dirtied. Hence we must
+ * be careful to check for EOF conditions here. We set the page up correctly
+ * for a written page which means we get ENOSPC checking when writing into
+ * holes and correct delalloc and unwritten extent mapping on filesystems that
+ * support these features.
+ *
+ * We are not allowed to take the i_mutex here so we have to play games to
+ * protect against truncate races as the page could now be beyond EOF.  Because
+ * vmtruncate() writes the inode size before removing pages, once we have the
+ * page lock we can determine safely if the page is beyond EOF. If it is not
+ * beyond EOF, then the page is guaranteed safe against truncation until we
+ * unlock the page.
+ */
+int
+block_page_mkwrite(struct vm_area_struct *vma, struct page *page,
+		   get_block_t get_block)
+{
+	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+	unsigned long end;
+	loff_t size;
+	int ret = -EINVAL;
+
+	lock_page(page);
+	size = i_size_read(inode);
+	if ((page->mapping != inode->i_mapping) ||
+	    (page_offset(page) > size)) {
+		/* page got truncated out from underneath us */
+		goto out_unlock;
+	}
+
+	/* page is wholly or partially inside EOF */
+	if (((page->index + 1) << PAGE_CACHE_SHIFT) > size)
+		end = size & ~PAGE_CACHE_MASK;
+	else
+		end = PAGE_CACHE_SIZE;
+
+	ret = block_prepare_write(page, 0, end, get_block);
+	if (!ret)
+		ret = block_commit_write(page, 0, end);
+
+out_unlock:
+	unlock_page(page);
+	return ret;
+}
 
 /*
  * nobh_prepare_write()'s prereads are special: the buffer_heads are freed
@@ -2962,6 +3023,7 @@ EXPORT_SYMBOL(__brelse);
 EXPORT_SYMBOL(__wait_on_buffer);
 EXPORT_SYMBOL(block_commit_write);
 EXPORT_SYMBOL(block_prepare_write);
+EXPORT_SYMBOL(block_page_mkwrite);
 EXPORT_SYMBOL(block_read_full_page);
 EXPORT_SYMBOL(block_sync_page);
 EXPORT_SYMBOL(block_truncate_page);