linux-kernel - [PATCH] ext4: Fix i_disksize exceeding i_size problem in paritally written case

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:   Fri, 17 Mar 2023 09:35:53 +0800
From:   Zhihao Cheng <chengzhihao1@...wei.com>
To:     <tytso@....edu>, <adilger.kernel@...ger.ca>, <jack@...e.com>,
        <tudor.ambarus@...aro.org>
CC:     <linux-ext4@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        <chengzhihao1@...wei.com>, <yi.zhang@...wei.com>
Subject: [PATCH] ext4: Fix i_disksize exceeding i_size problem in paritally written case

Following process makes i_disksize exceed i_size:

generic_perform_write
 copied = iov_iter_copy_from_user_atomic(len) // copied < len
 ext4_da_write_end
 | ext4_update_i_disksize
 |  new_i_size = pos + copied;
 |  WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize) // update i_disksize
 | generic_write_end
 |  copied = block_write_end(copied, len) // copied = 0
 |   if (unlikely(copied < len))
 |    if (!PageUptodate(page))
 |     copied = 0;
 |  if (pos + copied > inode->i_size) // return false
 if (unlikely(copied == 0))
  goto again;
 if (unlikely(iov_iter_fault_in_readable(i, bytes))) {
  status = -EFAULT;
  break;
 }

We get i_disksize greater than i_size here, which could trigger WARNING
check 'i_size_read(inode) < EXT4_I(inode)->i_disksize' while doing dio:

ext4_dio_write_iter
 iomap_dio_rw
  __iomap_dio_rw // return err, length is not aligned to 512
 ext4_handle_inode_extension
  WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize) // Oops

 WARNING: CPU: 2 PID: 2609 at fs/ext4/file.c:319
 CPU: 2 PID: 2609 Comm: aa Not tainted 6.3.0-rc2
 RIP: 0010:ext4_file_write_iter+0xbc7
 Call Trace:
  vfs_write+0x3b1
  ksys_write+0x77
  do_syscall_64+0x39

Fix it by putting block_write_end() before i_disksize updating just
like ext4_write_end() does.

Fetch a reproducer in [Link].

Link: https://bugzilla.kernel.org/show_bug.cgi?id=217209
Fixes: 64769240bd07f ("ext4: Add delayed allocation support in data=writeback mode")
Signed-off-by: Zhihao Cheng <chengzhihao1@...wei.com>
---
 fs/ext4/inode.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bf0b7dea4900..577dc23f3b78 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3136,6 +3136,8 @@ static int ext4_da_write_end(struct file *file,
 	loff_t new_i_size;
 	unsigned long start, end;
 	int write_mode = (int)(unsigned long)fsdata;
+	bool i_size_changed = false;
+	loff_t old_size = inode->i_size;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC)
 		return ext4_write_end(file, mapping, pos,
@@ -3148,6 +3150,8 @@ static int ext4_da_write_end(struct file *file,
 	    ext4_has_inline_data(inode))
 		return ext4_write_inline_data_end(inode, pos, len, copied, page);
 
+	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
 	start = pos & (PAGE_SIZE - 1);
 	end = start + copied - 1;
 
@@ -3162,16 +3166,30 @@ static int ext4_da_write_end(struct file *file,
 	 * check), we need to update i_disksize here as neither
 	 * ext4_writepage() nor certain ext4_writepages() paths not
 	 * allocating blocks update i_disksize.
-	 *
-	 * Note that we defer inode dirtying to generic_write_end() /
-	 * ext4_da_write_inline_data_end().
 	 */
 	new_i_size = pos + copied;
-	if (copied && new_i_size > inode->i_size &&
-	    ext4_da_should_update_i_disksize(page, end))
-		ext4_update_i_disksize(inode, new_i_size);
+	if (new_i_size > inode->i_size) {
+		i_size_write(inode, new_i_size);
+		i_size_changed = true;
+		if (copied && ext4_da_should_update_i_disksize(page, end))
+			ext4_update_i_disksize(inode, new_i_size);
+	}
+
+	unlock_page(page);
+	put_page(page);
+
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		mark_inode_dirty(inode);
 
-	return generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	return copied;
 }
 
 /*
-- 
2.31.1