ext4: fix races between buffered IO and collapse / insert range

Current code implementing FALLOC_FL_COLLAPSE_RANGE and
FALLOC_FL_INSERT_RANGE is prone to races with buffered writes and page
faults. If buffered write or write via mmap manages to squeeze between
filemap_write_and_wait_range() and truncate_pagecache() in the fallocate
implementations, the written data is simply discarded by
truncate_pagecache() although it should have been shifted.

Fix the problem by moving filemap_write_and_wait_range() call inside
i_mutex and i_mmap_sem. That way we are protected against races with
both buffered writes and page faults.

Signed-off-by: Jan Kara <jack@suse.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 65b5ada2833f0f9bc347cb07ee4cf3ceaa1de85d..4b105c96df082e916209417348ded03d3ac599b5 100644 (file)
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5487,21 +5487,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
                        return ret;
        }
 
-       /*
-        * Need to round down offset to be aligned with page size boundary
-        * for page size > block size.
-        */
-       ioffset = round_down(offset, PAGE_SIZE);
-
-       /* Write out all dirty pages */
-       ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-                                          LLONG_MAX);
-       if (ret)
-               return ret;
-
-       /* Take mutex lock */
        mutex_lock(&inode->i_mutex);
-
        /*
         * There is no need to overlap collapse range with EOF, in which case
         * it is effectively a truncate operation
@@ -5526,6 +5512,27 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
         * page cache.
         */
        down_write(&EXT4_I(inode)->i_mmap_sem);
+       /*
+        * Need to round down offset to be aligned with page size boundary
+        * for page size > block size.
+        */
+       ioffset = round_down(offset, PAGE_SIZE);
+       /*
+        * Write tail of the last page before removed range since it will get
+        * removed from the page cache below.
+        */
+       ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, offset);
+       if (ret)
+               goto out_mmap;
+       /*
+        * Write data that will be shifted to preserve them when discarding
+        * page cache below. We are also protected from pages becoming dirty
+        * by i_mmap_sem.
+        */
+       ret = filemap_write_and_wait_range(inode->i_mapping, offset + len,
+                                          LLONG_MAX);
+       if (ret)
+               goto out_mmap;
        truncate_pagecache(inode, ioffset);
 
        credits = ext4_writepage_trans_blocks(inode);
@@ -5626,21 +5633,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
                        return ret;
        }
 
-       /*
-        * Need to round down to align start offset to page size boundary
-        * for page size > block size.
-        */
-       ioffset = round_down(offset, PAGE_SIZE);
-
-       /* Write out all dirty pages */
-       ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-                       LLONG_MAX);
-       if (ret)
-               return ret;
-
-       /* Take mutex lock */
        mutex_lock(&inode->i_mutex);
-
        /* Currently just for extent based files */
        if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
                ret = -EOPNOTSUPP;
@@ -5668,6 +5661,16 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
         * page cache.
         */
        down_write(&EXT4_I(inode)->i_mmap_sem);
+       /*
+        * Need to round down to align start offset to page size boundary
+        * for page size > block size.
+        */
+       ioffset = round_down(offset, PAGE_SIZE);
+       /* Write out all dirty pages */
+       ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+                       LLONG_MAX);
+       if (ret)
+               goto out_mmap;
        truncate_pagecache(inode, ioffset);
 
        credits = ext4_writepage_trans_blocks(inode);