[PATCH 2/8] vfs: Protect write paths by sb_start_write - sb_end_write

[Jan Kara]

There are three entry points which dirty pages in a filesystem.  mmap (handled
by block_page_mkwrite()), buffered write (handled by
__generic_file_aio_write()), and truncate (it can dirty last partial page -
handled inside each filesystem separately). Protect these places with
sb_start_write() and sb_end_write().

Acked-by: "Theodore Ts'o" <tytso@xxxxxxx>
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
 fs/buffer.c  |   22 ++++------------------
 mm/filemap.c |    3 ++-
 2 files changed, 6 insertions(+), 19 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 19d8eb7..550714d 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2338,8 +2338,8 @@ EXPORT_SYMBOL(block_commit_write);
  * beyond EOF, then the page is guaranteed safe against truncation until we
  * unlock the page.
  *
- * Direct callers of this function should call vfs_check_frozen() so that page
- * fault does not busyloop until the fs is thawed.
+ * Direct callers of this function should protect against filesystem freezing
+ * using sb_start_write() - sb_end_write() functions.
  */
 int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 			 get_block_t get_block)
@@ -2371,18 +2371,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	if (unlikely(ret < 0))
 		goto out_unlock;
-	/*
-	 * Freezing in progress? We check after the page is marked dirty and
-	 * with page lock held so if the test here fails, we are sure freezing
-	 * code will wait during syncing until the page fault is done - at that
-	 * point page will be dirty and unlocked so freezing code will write it
-	 * and writeprotect it again.
-	 */
 	set_page_dirty(page);
-	if (inode->i_sb->s_frozen != SB_UNFROZEN) {
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
 	wait_on_page_writeback(page);
 	return 0;
 out_unlock:
@@ -2397,12 +2386,9 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	int ret;
 	struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb;
 
-	/*
-	 * This check is racy but catches the common case. The check in
-	 * __block_page_mkwrite() is reliable.
-	 */
-	vfs_check_frozen(sb, SB_FREEZE_WRITE);
+	sb_start_write(sb, SB_FREEZE_WRITE);
 	ret = __block_page_mkwrite(vma, vmf, get_block);
+	sb_end_write(sb, SB_FREEZE_WRITE);
 	return block_page_mkwrite_return(ret);
 }
 EXPORT_SYMBOL(block_page_mkwrite);
diff --git a/mm/filemap.c b/mm/filemap.c
index c0018f2..471b9ae 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2529,7 +2529,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	count = ocount;
 	pos = *ppos;
 
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb, SB_FREEZE_WRITE);
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -2601,6 +2601,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 				pos, ppos, count, written);
 	}
 out:
+	sb_end_write(inode->i_sb, SB_FREEZE_WRITE);
 	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/