[6.1,CANDIDATE,15/26] xfs: fix ag count overflow during growfs

Commit Message

Leah Rumancik Sept. 5, 2024, 6:21 p.m. UTC

From: Long Li <[e-mail]>

[ Upstream commit c3b880acadc95d6e019eae5d669e072afda24f1b ]

I found a corruption during growfs:

 XFS (loop0): Internal error agbno >= mp->m_sb.sb_agblocks at line 3661 of
   file fs/xfs/libxfs/xfs_alloc.c.  Caller __xfs_free_extent+0x28e/0x3c0
 CPU: 0 PID: 573 Comm: xfs_growfs Not tainted 6.3.0-rc7-next-20230420-00001-gda8c95746257
 Call Trace:
  <TASK>
  dump_stack_lvl+0x50/0x70
  xfs_corruption_error+0x134/0x150
  __xfs_free_extent+0x2c1/0x3c0
  xfs_ag_extend_space+0x291/0x3e0
  xfs_growfs_data+0xd72/0xe90
  xfs_file_ioctl+0x5f9/0x14a0
  __x64_sys_ioctl+0x13e/0x1c0
  do_syscall_64+0x39/0x80
  entry_SYSCALL_64_after_hwframe+0x63/0xcd
 XFS (loop0): Corruption detected. Unmount and run xfs_repair
 XFS (loop0): Internal error xfs_trans_cancel at line 1097 of file
   fs/xfs/xfs_trans.c.  Caller xfs_growfs_data+0x691/0xe90
 CPU: 0 PID: 573 Comm: xfs_growfs Not tainted 6.3.0-rc7-next-20230420-00001-gda8c95746257
 Call Trace:
  <TASK>
  dump_stack_lvl+0x50/0x70
  xfs_error_report+0x93/0xc0
  xfs_trans_cancel+0x2c0/0x350
  xfs_growfs_data+0x691/0xe90
  xfs_file_ioctl+0x5f9/0x14a0
  __x64_sys_ioctl+0x13e/0x1c0
  do_syscall_64+0x39/0x80
  entry_SYSCALL_64_after_hwframe+0x63/0xcd
 RIP: 0033:0x7f2d86706577

The bug can be reproduced with the following sequence:

 # truncate -s  1073741824 xfs_test.img
 # mkfs.xfs -f -b size=1024 -d agcount=4 xfs_test.img
 # truncate -s 2305843009213693952  xfs_test.img
 # mount -o loop xfs_test.img /mnt/test
 # xfs_growfs -D  1125899907891200  /mnt/test

The root cause is that during growfs, user space passed in a large value
of newblcoks to xfs_growfs_data_private(), due to current sb_agblocks is
too small, new AG count will exceed UINT_MAX. Because of AG number type
is unsigned int and it would overflow, that caused nagcount much smaller
than the actual value. During AG extent space, delta blocks in
xfs_resizefs_init_new_ags() will much larger than the actual value due to
incorrect nagcount, even exceed UINT_MAX. This will cause corruption and
be detected in __xfs_free_extent. Fix it by growing the filesystem to up
to the maximally allowed AGs and not return EINVAL when new AG count
overflow.

Signed-off-by: Long Li <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
Signed-off-by: Darrick J. Wong <[e-mail]>
Signed-off-by: Leah Rumancik <[e-mail]>
---
 fs/xfs/libxfs/xfs_fs.h |  2 ++
 fs/xfs/xfs_fsops.c     | 13 +++++++++----
 2 files changed, 11 insertions(+), 4 deletions(-)

Patch

diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 1cfd5bc6520a..9c60ebb328b4 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -257,6 +257,8 @@  typedef struct xfs_fsop_resblks {
 #define XFS_MAX_AG_BLOCKS	(XFS_MAX_AG_BYTES / XFS_MIN_BLOCKSIZE)
 #define XFS_MAX_CRC_AG_BLOCKS	(XFS_MAX_AG_BYTES / XFS_MIN_CRC_BLOCKSIZE)
 
+#define XFS_MAX_AGNUMBER	((xfs_agnumber_t)(NULLAGNUMBER - 1))
+
 /* keep the maximum size under 2^31 by a small amount */
 #define XFS_MAX_LOG_BYTES \
 	((2 * 1024 * 1024 * 1024ULL) - XFS_MIN_LOG_BYTES)
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 332da0d7b85c..77b14f788214 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -115,11 +115,16 @@  xfs_growfs_data_private(
 
 	nb_div = nb;
 	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
-	nagcount = nb_div + (nb_mod != 0);
-	if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
-		nagcount--;
-		nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks;
+	if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS)
+		nb_div++;
+	else if (nb_mod)
+		nb = nb_div * mp->m_sb.sb_agblocks;
+
+	if (nb_div > XFS_MAX_AGNUMBER + 1) {
+		nb_div = XFS_MAX_AGNUMBER + 1;
+		nb = nb_div * mp->m_sb.sb_agblocks;
 	}
+	nagcount = nb_div;
 	delta = nb - mp->m_sb.sb_dblocks;
 	/*
 	 * Reject filesystems with a single AG because they are not