xfs: add agf freeblocks verify in xfs_agf_verify

[ Upstream commit d0c7feaf87678371c2c09b3709400be416b2dc62 ]

We recently used fuzz(hydra) to test XFS and automatically generate
tmp.img(XFS v5 format, but some metadata is wrong)

xfs_repair information(just one AG):
agf_freeblks 0, counted 3224 in ag 0
agf_longest 536874136, counted 3224 in ag 0
sb_fdblocks 613, counted 3228

Test as follows:
mount tmp.img tmpdir
cp file1M tmpdir
sync

In 4.19-stable, sync will stuck, the reason is:
xfs_mountfs
  xfs_check_summary_counts
    if ((!xfs_sb_version_haslazysbcount(&mp->m_sb) ||
       XFS_LAST_UNMOUNT_WAS_CLEAN(mp)) &&
       !xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS))
	return 0;  -->just return, incore sb_fdblocks still be 613
    xfs_initialize_perag_data

cp file1M tmpdir -->ok(write file to pagecache)
sync -->stuck(write pagecache to disk)
xfs_map_blocks
  xfs_iomap_write_allocate
    while (count_fsb != 0) {
      nimaps = 0;
      while (nimaps == 0) { --> endless loop
         nimaps = 1;
         xfs_bmapi_write(..., &nimaps) --> nimaps becomes 0 again
xfs_bmapi_write
  xfs_bmap_alloc
    xfs_bmap_btalloc
      xfs_alloc_vextent
        xfs_alloc_fix_freelist
          xfs_alloc_space_available -->fail(agf_freeblks is 0)

In linux-next, sync not stuck, cause commit c2b3164320b5 ("xfs:
use the latest extent at writeback delalloc conversion time") remove
the above while, dmesg is as follows:
[   55.250114] XFS (loop0): page discard on page ffffea0008bc7380, inode 0x1b0c, offset 0.

Users do not know why this page is discard, the better soultion is:
1. Like xfs_repair, make sure sb_fdblocks is equal to counted
(xfs_initialize_perag_data did this, who is not called at this mount)
2. Add agf verify, if fail, will tell users to repair

This patch use the second soultion.

Signed-off-by: Zheng Bin <zhengbin13@huawei.com>
Signed-off-by: Ren Xudong <renxudong1@huawei.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 16 insertions, 0 deletions

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 533b04aaf6f6..0a36f532cf86 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2598,6 +2598,13 @@ xfs_agf_verify(
 	      be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp)))
 		return __this_address;
 
+	if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks)
+		return __this_address;
+
+	if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) ||
+	    be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length))
+		return __this_address;
+
 	if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
 	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
 	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > XFS_BTREE_MAXLEVELS ||
@@ -2609,6 +2616,10 @@ xfs_agf_verify(
 	     be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > XFS_BTREE_MAXLEVELS))
 		return __this_address;
 
+	if (xfs_sb_version_hasrmapbt(&mp->m_sb) &&
+	    be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length))
+		return __this_address;
+
 	/*
 	 * during growfs operations, the perag is not fully initialised,
 	 * so we can't use it for any useful checking. growfs ensures we can't
@@ -2623,6 +2634,11 @@ xfs_agf_verify(
 		return __this_address;
 
 	if (xfs_sb_version_hasreflink(&mp->m_sb) &&
+	    be32_to_cpu(agf->agf_refcount_blocks) >
+	    be32_to_cpu(agf->agf_length))
+		return __this_address;
+
+	if (xfs_sb_version_hasreflink(&mp->m_sb) &&
 	    (be32_to_cpu(agf->agf_refcount_level) < 1 ||
 	     be32_to_cpu(agf->agf_refcount_level) > XFS_BTREE_MAXLEVELS))
 		return __this_address;