mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Heming Zhao <heming.zhao@suse.com>
To: joseph.qi@linux.alibaba.com, mark@fasheh.com, jlbec@evilplan.org
Cc: Heming Zhao <heming.zhao@suse.com>,
	ocfs2-devel@lists.linux.dev, linux-kernel@vger.kernel.org,
	glass.su@suse.com
Subject: [PATCH v4 2/2] ocfs2: detect released suballocator BG for fh_to_[dentry|parent]
Date: Fri, 21 Nov 2025 15:40:25 +0800	[thread overview]
Message-ID: <20251121074030.12014-3-heming.zhao@suse.com> (raw)
In-Reply-To: <20251121074030.12014-1-heming.zhao@suse.com>

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.

Signed-off-by: Heming Zhao <heming.zhao@suse.com>
Reviewed-by: Su Yue <glass.su@suse.com>
---
 fs/ocfs2/suballoc.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index de2f09217142..a126d83ddb1c 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -3152,7 +3152,7 @@ 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;
 
 	trace_ocfs2_test_suballoc_bit((unsigned long long)blkno,
 				      (unsigned int)bit);
@@ -3168,11 +3168,15 @@ 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 = -EINVAL;
+		goto bail;
+	} else if (status < 0) {
 		mlog(ML_ERROR, "read group %llu failed %d\n",
-		     (unsigned long long)bg_blkno, status);
+				(unsigned long long)bg_blkno, status);
 		goto bail;
 	}
 
@@ -3182,7 +3186,7 @@ static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb,
 bail:
 	brelse(group_bh);
 
-	if (status)
+	if (status && (!quiet))
 		mlog_errno(status);
 	return status;
 }
@@ -3202,7 +3206,7 @@ static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb,
  */
 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;
@@ -3244,8 +3248,12 @@ 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 == -EINVAL)
+			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);
@@ -3253,7 +3261,7 @@ 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;
 }
-- 
2.43.0


  parent reply	other threads:[~2025-11-21  7:40 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-21  7:40 [PATCH v4 0/2] ocfs2: give ocfs2 the ability to reclaim suballocator free bg Heming Zhao
2025-11-21  7:40 ` [PATCH v4 1/2] " Heming Zhao
2025-11-21  7:40 ` Heming Zhao [this message]
2025-11-21  9:50 ` [PATCH v4 0/2] " Heming Zhao

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20251121074030.12014-3-heming.zhao@suse.com \
    --to=heming.zhao@suse.com \
    --cc=glass.su@suse.com \
    --cc=jlbec@evilplan.org \
    --cc=joseph.qi@linux.alibaba.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark@fasheh.com \
    --cc=ocfs2-devel@lists.linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®