ocfs2: detect released suballocator BG for fh_to_[dentry|parent]

After ocfs2 gained the ability to reclaim suballocator free block group
(BGs), a suballocator block group may be released.  This change causes the
xfstest case generic/426 to fail.

generic/426 expects return value -ENOENT or -ESTALE, but the current code
triggers -EROFS.

Call stack before ocfs2 gained the ability to reclaim bg:

ocfs2_fh_to_dentry //or ocfs2_fh_to_parent
 ocfs2_get_dentry
  + ocfs2_test_inode_bit
  |  ocfs2_test_suballoc_bit
  |   + ocfs2_read_group_descriptor //Since ocfs2 never releases the bg,
  |   |                             //the bg block was always found.
  |   + *res = ocfs2_test_bit //unlink was called, and the bit is zero
  |
  + if (!set) //because the above *res is 0
     status = -ESTALE //the generic/426 expected return value

Current call stack that triggers -EROFS:

ocfs2_get_dentry
 ocfs2_test_inode_bit
  ocfs2_test_suballoc_bit
   ocfs2_read_group_descriptor
    + if reading a released bg, validation fails and triggers -EROFS

How to fix:
Since the read BG is already released, we must avoid triggering -EROFS.
With this commit, we use ocfs2_read_hint_group_descriptor() to detect the
released BG block.  This approach quietly handles this type of error and
returns -EINVAL, which triggers the caller's existing conversion path to
-ESTALE.

[dan.carpenter@linaro.org: fix uninitialized variable]
Link: https://lkml.kernel.org/r/dc37519fd2470909f8c65e26c5131b8b6dde2a5c.1766043917.git.dan.carpenter@linaro.org
Link: https://lkml.kernel.org/r/20251212074505.25962-3-heming.zhao@suse.com
Signed-off-by: Heming Zhao <heming.zhao@suse.com>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Su Yue <glass.su@suse.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Cc: Heming Zhao <heming.zhao@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index b95724b767e150e991ae4b8ea5d0505c1ae95984..9c2665dd24e218a2d8978166056ec851d1bc92d5 100644 (file)
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -74,8 +74,9 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb,
                         * nice
                         */
                        status = -ESTALE;
-               } else
+               } else if (status != -ESTALE) {
                        mlog(ML_ERROR, "test inode bit failed %d\n", status);
+               }
                goto unlock_nfs_sync;
        }
 
@@ -162,8 +163,9 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
        if (status < 0) {
                if (status == -EINVAL) {
                        status = -ESTALE;
-               } else
+               } else if (status != -ESTALE) {
                        mlog(ML_ERROR, "test inode bit failed %d\n", status);
+               }
                parent = ERR_PTR(status);
                goto bail_unlock;
        }

diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index aac2f96bee439aff693b93bed10b4512f5720cec..79d1325b21115e708f00ad30605c17d1722ccac2 100644 (file)
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -3163,7 +3163,7 @@ static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb,
        struct ocfs2_group_desc *group;
        struct buffer_head *group_bh = NULL;
        u64 bg_blkno;
-       int status;
+       int status, quiet = 0, released = 0;
 
        trace_ocfs2_test_suballoc_bit((unsigned long long)blkno,
                                      (unsigned int)bit);
@@ -3179,9 +3179,13 @@ static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb,
 
        bg_blkno = group_blkno ? group_blkno :
                   ocfs2_which_suballoc_group(blkno, bit);
-       status = ocfs2_read_group_descriptor(suballoc, alloc_di, bg_blkno,
-                                            &group_bh);
-       if (status < 0) {
+       status = ocfs2_read_hint_group_descriptor(suballoc, alloc_di, bg_blkno,
+                                            &group_bh, &released);
+       if (released) {
+               quiet = 1;
+               status = -ESTALE;
+               goto bail;
+       } else if (status < 0) {
                mlog(ML_ERROR, "read group %llu failed %d\n",
                     (unsigned long long)bg_blkno, status);
                goto bail;
@@ -3193,7 +3197,7 @@ static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb,
 bail:
        brelse(group_bh);
 
-       if (status)
+       if (status && !quiet)
                mlog_errno(status);
        return status;
 }
@@ -3213,7 +3217,7 @@ bail:
  */
 int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
 {
-       int status;
+       int status, quiet = 0;
        u64 group_blkno = 0;
        u16 suballoc_bit = 0, suballoc_slot = 0;
        struct inode *inode_alloc_inode;
@@ -3255,8 +3259,12 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
 
        status = ocfs2_test_suballoc_bit(osb, inode_alloc_inode, alloc_bh,
                                         group_blkno, blkno, suballoc_bit, res);
-       if (status < 0)
-               mlog(ML_ERROR, "test suballoc bit failed %d\n", status);
+       if (status < 0) {
+               if (status == -ESTALE)
+                       quiet = 1;
+               else
+                       mlog(ML_ERROR, "test suballoc bit failed %d\n", status);
+       }
 
        ocfs2_inode_unlock(inode_alloc_inode, 0);
        inode_unlock(inode_alloc_inode);
@@ -3264,7 +3272,7 @@ int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
        iput(inode_alloc_inode);
        brelse(alloc_bh);
 bail:
-       if (status)
+       if (status && !quiet)
                mlog_errno(status);
        return status;
 }