1 files changed, 45 insertions, 88 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index c9c266db0624..50efa339e051 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -275,6 +275,7 @@ void invalidate_bdev(struct block_device *bdev)
 		return;
 
 	invalidate_bh_lrus();
+	lru_add_drain_all();	/* make sure all lru add caches are flushed */
 	invalidate_mapping_pages(mapping, 0, -1);
 }
 EXPORT_SYMBOL(invalidate_bdev);
@@ -560,26 +561,17 @@ repeat:
 	return err;
 }
 
-static void do_thaw_all(struct work_struct *work)
+static void do_thaw_one(struct super_block *sb, void *unused)
 {
-	struct super_block *sb;
 	char b[BDEVNAME_SIZE];
+	while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+		printk(KERN_WARNING "Emergency Thaw on %s\n",
+		       bdevname(sb->s_bdev, b));
+}
 
-	spin_lock(&sb_lock);
-restart:
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		sb->s_count++;
-		spin_unlock(&sb_lock);
-		down_read(&sb->s_umount);
-		while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
-			printk(KERN_WARNING "Emergency Thaw on %s\n",
-			       bdevname(sb->s_bdev, b));
-		up_read(&sb->s_umount);
-		spin_lock(&sb_lock);
-		if (__put_super_and_need_restart(sb))
-			goto restart;
-	}
-	spin_unlock(&sb_lock);
+static void do_thaw_all(struct work_struct *work)
+{
+	iterate_supers(do_thaw_one, NULL);
 	kfree(work);
 	printk(KERN_WARNING "Emergency Thaw complete\n");
 }
@@ -1841,9 +1833,10 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to)
 }
 EXPORT_SYMBOL(page_zero_new_buffers);
 
-static int __block_prepare_write(struct inode *inode, struct page *page,
-		unsigned from, unsigned to, get_block_t *get_block)
+int block_prepare_write(struct page *page, unsigned from, unsigned to,
+		get_block_t *get_block)
 {
+	struct inode *inode = page->mapping->host;
 	unsigned block_start, block_end;
 	sector_t block;
 	int err = 0;
@@ -1916,10 +1909,13 @@ static int __block_prepare_write(struct inode *inode, struct page *page,
 		if (!buffer_uptodate(*wait_bh))
 			err = -EIO;
 	}
-	if (unlikely(err))
+	if (unlikely(err)) {
 		page_zero_new_buffers(page, from, to);
+		ClearPageUptodate(page);
+	}
 	return err;
 }
+EXPORT_SYMBOL(block_prepare_write);
 
 static int __block_commit_write(struct inode *inode, struct page *page,
 		unsigned from, unsigned to)
@@ -1956,62 +1952,40 @@ static int __block_commit_write(struct inode *inode, struct page *page,
 	return 0;
 }
 
+int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+		get_block_t *get_block)
+{
+	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
+
+	return block_prepare_write(page, start, start + len, get_block);
+}
+EXPORT_SYMBOL(__block_write_begin);
+
 /*
  * block_write_begin takes care of the basic task of block allocation and
  * bringing partial write blocks uptodate first.
  *
- * If *pagep is not NULL, then block_write_begin uses the locked page
- * at *pagep rather than allocating its own. In this case, the page will
- * not be unlocked or deallocated on failure.
+ * The filesystem needs to handle block truncation upon failure.
  */
-int block_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
-			struct page **pagep, void **fsdata,
-			get_block_t *get_block)
+int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
+		unsigned flags, struct page **pagep, get_block_t *get_block)
 {
-	struct inode *inode = mapping->host;
-	int status = 0;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	struct page *page;
-	pgoff_t index;
-	unsigned start, end;
-	int ownpage = 0;
+	int status;
 
-	index = pos >> PAGE_CACHE_SHIFT;
-	start = pos & (PAGE_CACHE_SIZE - 1);
-	end = start + len;
-
-	page = *pagep;
-	if (page == NULL) {
-		ownpage = 1;
-		page = grab_cache_page_write_begin(mapping, index, flags);
-		if (!page) {
-			status = -ENOMEM;
-			goto out;
-		}
-		*pagep = page;
-	} else
-		BUG_ON(!PageLocked(page));
+	page = grab_cache_page_write_begin(mapping, index, flags);
+	if (!page)
+		return -ENOMEM;
 
-	status = __block_prepare_write(inode, page, start, end, get_block);
+	status = __block_write_begin(page, pos, len, get_block);
 	if (unlikely(status)) {
-		ClearPageUptodate(page);
-
-		if (ownpage) {
-			unlock_page(page);
-			page_cache_release(page);
-			*pagep = NULL;
-
-			/*
-			 * prepare_write() may have instantiated a few blocks
-			 * outside i_size.  Trim these off again. Don't need
-			 * i_size_read because we hold i_mutex.
-			 */
-			if (pos + len > inode->i_size)
-				vmtruncate(inode, inode->i_size);
-		}
+		unlock_page(page);
+		page_cache_release(page);
+		page = NULL;
 	}
 
-out:
+	*pagep = page;
 	return status;
 }
 EXPORT_SYMBOL(block_write_begin);
@@ -2344,7 +2318,7 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 
 	err = cont_expand_zero(file, mapping, pos, bytes);
 	if (err)
-		goto out;
+		return err;
 
 	zerofrom = *bytes & ~PAGE_CACHE_MASK;
 	if (pos+len > *bytes && zerofrom & (blocksize-1)) {
@@ -2352,25 +2326,10 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 		(*bytes)++;
 	}
 
-	*pagep = NULL;
-	err = block_write_begin(file, mapping, pos, len,
-				flags, pagep, fsdata, get_block);
-out:
-	return err;
+	return block_write_begin(mapping, pos, len, flags, pagep, get_block);
 }
 EXPORT_SYMBOL(cont_write_begin);
 
-int block_prepare_write(struct page *page, unsigned from, unsigned to,
-			get_block_t *get_block)
-{
-	struct inode *inode = page->mapping->host;
-	int err = __block_prepare_write(inode, page, from, to, get_block);
-	if (err)
-		ClearPageUptodate(page);
-	return err;
-}
-EXPORT_SYMBOL(block_prepare_write);
-
 int block_commit_write(struct page *page, unsigned from, unsigned to)
 {
 	struct inode *inode = page->mapping->host;
@@ -2389,7 +2348,7 @@ EXPORT_SYMBOL(block_commit_write);
  *
  * 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
+ * truncate 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.
@@ -2474,8 +2433,9 @@ static void attach_nobh_buffers(struct page *page, struct buffer_head *head)
 /*
  * On entry, the page is fully not uptodate.
  * On exit the page is fully uptodate in the areas outside (from,to)
+ * The filesystem needs to handle block truncation upon failure.
  */
-int nobh_write_begin(struct file *file, struct address_space *mapping,
+int nobh_write_begin(struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata,
 			get_block_t *get_block)
@@ -2508,8 +2468,8 @@ int nobh_write_begin(struct file *file, struct address_space *mapping,
 		unlock_page(page);
 		page_cache_release(page);
 		*pagep = NULL;
-		return block_write_begin(file, mapping, pos, len, flags, pagep,
-					fsdata, get_block);
+		return block_write_begin(mapping, pos, len, flags, pagep,
+					 get_block);
 	}
 
 	if (PageMappedToDisk(page))
@@ -2613,9 +2573,6 @@ out_release:
 	page_cache_release(page);
 	*pagep = NULL;
 
-	if (pos + len > inode->i_size)
-		vmtruncate(inode, inode->i_size);
-
 	return ret;
 }
 EXPORT_SYMBOL(nobh_write_begin);