Skip to contentSkip to conversation

FAILED: patch "[PATCH] xfs: don't livelock in scrub on a circular unlinked list" failed to apply to 6.18-stable tree

PATCH New [email protected] 2 participants 3 messages Aug 20 – Aug 24

Subsystems (2)
Stable branch XFS filesystem
lore
Share & tools
lore

[email protected]

author maintainer
#0 lore raw

The patch below does not apply to the 6.18-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x 527eaaefddb6ec5c83a06c9a1559960dd6361753
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026082043-rely-pentagram-07de@gregkh' --subject-prefix 'PATCH 6.18.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 527eaaefddb6ec5c83a06c9a1559960dd6361753 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <[email protected]>
Date: Sun, 26 Jul 2026 22:24:48 -0700
Subject: [PATCH] xfs: don't livelock in scrub on a circular unlinked list

LOLLM points out that online fsck can livelock if an unlinked inode list contains a loop. Use a bitmap to detect cycles.

Cc [email protected] # v4.15
Fixes a12890aebb8959 ("xfs: scrub the AGI")
Signed-off-by Darrick J. Wong <[email protected]>
Assisted-by LOLLM # finding obvious bugs
Reviewed-by Christoph Hellwig <[email protected]>
Signed-off-by Carlos Maiolino <[email protected]>
fs/xfs/scrub/agheader.c +36 -8
index cecf034ef989..1fa66aa68e16 100644
@@ -18,6 +18,8 @@
 #include "xfs_inode.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/bitmap.h"
+#include "scrub/agino_bitmap.h"
 
 int
 xchk_setup_agheader(

@@ -935,7 +937,8 @@ xchk_agi_xref(
 /*
  * Walk the incore unlinked list for a particular AGI bucket to construct
  * the unlinked inode bitmap for later reconstruction of the unlinked list.
- * Returns 1 if we should keep checking, or 0 to stop checking.
+ * Returns 1 if we should keep checking, 0 to stop checking, or a negative
+ * errno.
  */
 static int
 xchk_iunlink_bucket(

@@ -943,36 +946,57 @@ xchk_iunlink_bucket(
 	unsigned int			bucket,
 	xfs_agino_t			agino)
 {
+	struct xagino_bitmap		seen;
+	int				ret;
+
+	xagino_bitmap_init(&seen);
+
 	while (agino != NULLAGINO) {
 		struct xfs_inode	*ip;
+		unsigned int		len = 1;
 
 		if (agino % XFS_AGI_UNLINKED_BUCKETS != bucket) {
 			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-			return 0;
+			goto bad;
+		}
+
+		if (xagino_bitmap_test(&seen, agino, &len)) {
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+			goto bad;
 		}
 
 		ip = xfs_iunlink_lookup(sc->sa.pag, agino);
 		if (!ip) {
 			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-			return 0;
+			goto bad;
 		}
 
 		if (!xfs_inode_on_unlinked_list(ip)) {
 			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-			return 0;
+			goto bad;
 		}
 
+		ret = xagino_bitmap_set(&seen, agino, 1);
+		if (ret)
+			goto out_bitmap;
+
 		agino = ip->i_next_unlinked;
 	}
+	ret = 1;
 
-	return 1;
+out_bitmap:
+	xagino_bitmap_destroy(&seen);
+	return ret;
+bad:
+	ret = 0;
+	goto out_bitmap;
 }
 
 /*
  * Check the unlinked buckets for links to bad inodes.  We hold the AGI, so
  * there cannot be any threads updating unlinked list pointers in this AG.
  */
-STATIC void
+STATIC int
 xchk_iunlink(
 	struct xfs_scrub	*sc,
 	struct xfs_agi		*agi)

@@ -985,8 +1009,10 @@ xchk_iunlink(
 		ret = xchk_iunlink_bucket(sc, i,
 				be32_to_cpu(agi->agi_unlinked[i]));
 		if (ret < 1)
-			return;
+			return ret;
 	}
+
+	return 0;
 }
 
 /* Scrub the AGI. */

@@ -1073,7 +1099,9 @@ xchk_agi(
 	if (pag->pagi_freecount != be32_to_cpu(agi->agi_freecount))
 		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
-	xchk_iunlink(sc, agi);
+	error = xchk_iunlink(sc, agi);
+	if (error)
+		goto out;
 
 	xchk_agi_xref(sc);
 out:
fs/xfs/scrub/agheader_repair.c +15 -2
index 2554494847ff..13074d5e319c 100644
@@ -1080,18 +1080,22 @@ xrep_iunlink_walk_ondisk_bucket(
 	struct xrep_agi		*ragi,
 	unsigned int		bucket)
 {
+	struct xagino_bitmap	seen;
 	struct xfs_scrub	*sc = ragi->sc;
 	struct xfs_agi		*agi = sc->sa.agi_bp->b_addr;
 	xfs_agino_t		prev_agino = NULLAGINO;
 	xfs_agino_t		next_agino;
 	int			error = 0;
 
+	xagino_bitmap_init(&seen);
+
 	next_agino = be32_to_cpu(agi->agi_unlinked[bucket]);
 	while (next_agino != NULLAGINO) {
 		xfs_agino_t	agino = next_agino;
+		unsigned int	len = 1;
 
 		if (xchk_should_terminate(ragi->sc, &error))
-			return error;
+			goto out_bitmap;
 
 		trace_xrep_iunlink_walk_ondisk_bucket(sc->sa.pag, bucket,
 				prev_agino, agino);

@@ -1099,15 +1103,24 @@ xrep_iunlink_walk_ondisk_bucket(
 		if (bucket != agino % XFS_AGI_UNLINKED_BUCKETS)
 			break;
 
+		if (xagino_bitmap_test(&seen, agino, &len))
+			break;
+
 		next_agino = xrep_iunlink_next(sc, agino);
 		if (!next_agino)
 			next_agino = xrep_iunlink_reload_next(ragi, prev_agino,
 					agino);
 
+		error = xagino_bitmap_set(&seen, agino, 1);
+		if (error)
+			goto out_bitmap;
+
 		prev_agino = agino;
 	}
 
-	return 0;
+out_bitmap:
+	xagino_bitmap_destroy(&seen);
+	return error;
 }
 
 /* Decide if this is an unlinked inode in this AG. */
maintainer
#1 lore raw

PATCH 1/2 xfs: hoist per-bucket unlinked list check to helper

From: "Darrick J. Wong" <[email protected]>

[ Upstream commit 7cdafd8f10ebdf745ba6046b9fa67490c343a17f ]

In the next patch we're going to make this loop more exciting, so hoist the code to a helper function to reduce clutter in the resulting code.

Signed-off-by Darrick J. Wong <[email protected]>
Reviewed-by Christoph Hellwig <[email protected]>
Signed-off-by Carlos Maiolino <[email protected]>

Stable-dep-of: 527eaaefddb6 ("xfs: don't livelock in scrub on a circular unlinked list")

Signed-off-by Sasha Levin <[email protected]>
---
 fs/xfs/scrub/agheader.c | 64 +++++++++++++++++++++++++++--------------
 1 file changed, 42 insertions(+), 22 deletions(-)
fs/xfs/scrub/agheader.c +42 -22
index 2ac2125b83172..7c44ea7a26c95 100644
@@ -932,6 +932,42 @@ xchk_agi_xref(
 	/* scrub teardown will take care of sc->sa for us */
 }
 
+/*
+ * Walk the incore unlinked list for a particular AGI bucket to construct
+ * the unlinked inode bitmap for later reconstruction of the unlinked list.
+ * Returns 1 if we should keep checking, or 0 to stop checking.
+ */
+static int
+xchk_iunlink_bucket(
+	struct xfs_scrub		*sc,
+	unsigned int			bucket,
+	xfs_agino_t			agino)
+{
+	while (agino != NULLAGINO) {
+		struct xfs_inode	*ip;
+
+		if (agino % XFS_AGI_UNLINKED_BUCKETS != bucket) {
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+			return 0;
+		}
+
+		ip = xfs_iunlink_lookup(sc->sa.pag, agino);
+		if (!ip) {
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+			return 0;
+		}
+
+		if (!xfs_inode_on_unlinked_list(ip)) {
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+			return 0;
+		}
+
+		agino = ip->i_next_unlinked;
+	}
+
+	return 1;
+}
+
 /*
  * Check the unlinked buckets for links to bad inodes.  We hold the AGI, so
  * there cannot be any threads updating unlinked list pointers in this AG.

@@ -942,30 +978,14 @@ xchk_iunlink(
 	struct xfs_agi		*agi)
 {
 	unsigned int		i;
-	struct xfs_inode	*ip;
 
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
-		xfs_agino_t	agino = be32_to_cpu(agi->agi_unlinked[i]);
-
-		while (agino != NULLAGINO) {
-			if (agino % XFS_AGI_UNLINKED_BUCKETS != i) {
-				xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-				return;
-			}
-
-			ip = xfs_iunlink_lookup(sc->sa.pag, agino);
-			if (!ip) {
-				xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-				return;
-			}
-
-			if (!xfs_inode_on_unlinked_list(ip)) {
-				xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-				return;
-			}
-
-			agino = ip->i_next_unlinked;
-		}
+		int		ret;
+
+		ret = xchk_iunlink_bucket(sc, i,
+				be32_to_cpu(agi->agi_unlinked[i]));
+		if (ret < 1)
+			return;
 	}
 }
Signature · 1 line
2.53.0
maintainer
#2 lore raw

PATCH 2/2 xfs: don't livelock in scrub on a circular unlinked list

From: "Darrick J. Wong" <[email protected]>

[ Upstream commit 527eaaefddb6ec5c83a06c9a1559960dd6361753 ]

LOLLM points out that online fsck can livelock if an unlinked inode list contains a loop. Use a bitmap to detect cycles.

Cc [email protected] # v4.15
Fixes a12890aebb8959 ("xfs: scrub the AGI")
Signed-off-by Darrick J. Wong <[email protected]>
Assisted-by LOLLM # finding obvious bugs
Reviewed-by Christoph Hellwig <[email protected]>
Signed-off-by Carlos Maiolino <[email protected]>
Signed-off-by Sasha Levin <[email protected]>
---
 fs/xfs/scrub/agheader.c        | 46 +++++++++++++++++++++++++++-------
 fs/xfs/scrub/agheader_repair.c | 17 +++++++++++--
 2 files changed, 52 insertions(+), 11 deletions(-)
fs/xfs/scrub/agheader.c +37 -9
index 7c44ea7a26c95..fb403a7bf4310 100644
@@ -18,6 +18,8 @@
 #include "xfs_inode.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/bitmap.h"
+#include "scrub/agino_bitmap.h"
 
 int
 xchk_setup_agheader(

@@ -935,7 +937,8 @@ xchk_agi_xref(
 /*
  * Walk the incore unlinked list for a particular AGI bucket to construct
  * the unlinked inode bitmap for later reconstruction of the unlinked list.
- * Returns 1 if we should keep checking, or 0 to stop checking.
+ * Returns 1 if we should keep checking, 0 to stop checking, or a negative
+ * errno.
  */
 static int
 xchk_iunlink_bucket(

@@ -943,36 +946,57 @@ xchk_iunlink_bucket(
 	unsigned int			bucket,
 	xfs_agino_t			agino)
 {
+	struct xagino_bitmap		seen;
+	int				ret;
+
+	xagino_bitmap_init(&seen);
+
 	while (agino != NULLAGINO) {
 		struct xfs_inode	*ip;
+		unsigned int		len = 1;
 
 		if (agino % XFS_AGI_UNLINKED_BUCKETS != bucket) {
 			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-			return 0;
+			goto bad;
+		}
+
+		if (xagino_bitmap_test(&seen, agino, &len)) {
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
+			goto bad;
 		}
 
 		ip = xfs_iunlink_lookup(sc->sa.pag, agino);
 		if (!ip) {
 			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-			return 0;
+			goto bad;
 		}
 
 		if (!xfs_inode_on_unlinked_list(ip)) {
 			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
-			return 0;
+			goto bad;
 		}
 
+		ret = xagino_bitmap_set(&seen, agino, 1);
+		if (ret)
+			goto out_bitmap;
+
 		agino = ip->i_next_unlinked;
 	}
-
-	return 1;
+	ret = 1;
+
+out_bitmap:
+	xagino_bitmap_destroy(&seen);
+	return ret;
+bad:
+	ret = 0;
+	goto out_bitmap;
 }
 
 /*
  * Check the unlinked buckets for links to bad inodes.  We hold the AGI, so
  * there cannot be any threads updating unlinked list pointers in this AG.
  */
-STATIC void
+STATIC int
 xchk_iunlink(
 	struct xfs_scrub	*sc,
 	struct xfs_agi		*agi)

@@ -985,8 +1009,10 @@ xchk_iunlink(
 		ret = xchk_iunlink_bucket(sc, i,
 				be32_to_cpu(agi->agi_unlinked[i]));
 		if (ret < 1)
-			return;
+			return ret;
 	}
+
+	return 0;
 }
 
 /* Scrub the AGI. */

@@ -1073,7 +1099,9 @@ xchk_agi(
 	if (pag->pagi_freecount != be32_to_cpu(agi->agi_freecount))
 		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
-	xchk_iunlink(sc, agi);
+	error = xchk_iunlink(sc, agi);
+	if (error)
+		goto out;
 
 	xchk_agi_xref(sc);
 out:
fs/xfs/scrub/agheader_repair.c +15 -2
index d18944449b3a9..6ed9c6fa52116 100644
@@ -1096,18 +1096,22 @@ xrep_iunlink_walk_ondisk_bucket(
 	struct xrep_agi		*ragi,
 	unsigned int		bucket)
 {
+	struct xagino_bitmap	seen;
 	struct xfs_scrub	*sc = ragi->sc;
 	struct xfs_agi		*agi = ragi->agi_bp->b_addr;
 	xfs_agino_t		prev_agino = NULLAGINO;
 	xfs_agino_t		next_agino;
 	int			error = 0;
 
+	xagino_bitmap_init(&seen);
+
 	next_agino = be32_to_cpu(agi->agi_unlinked[bucket]);
 	while (next_agino != NULLAGINO) {
 		xfs_agino_t	agino = next_agino;
+		unsigned int	len = 1;
 
 		if (xchk_should_terminate(ragi->sc, &error))
-			return error;
+			goto out_bitmap;
 
 		trace_xrep_iunlink_walk_ondisk_bucket(sc->sa.pag, bucket,
 				prev_agino, agino);

@@ -1115,6 +1119,9 @@ xrep_iunlink_walk_ondisk_bucket(
 		if (bucket != agino % XFS_AGI_UNLINKED_BUCKETS)
 			break;
 
+		if (xagino_bitmap_test(&seen, agino, &len))
+			break;
+
 		next_agino = xrep_iunlink_next(sc, agino);
 		if (!next_agino) {
 			error = xrep_iunlink_reload_next(ragi, prev_agino,

@@ -1123,10 +1130,16 @@ xrep_iunlink_walk_ondisk_bucket(
 				break;
 		}
 
+		error = xagino_bitmap_set(&seen, agino, 1);
+		if (error)
+			goto out_bitmap;
+
 		prev_agino = agino;
 	}
 
-	return 0;
+out_bitmap:
+	xagino_bitmap_destroy(&seen);
+	return error;
 }
 
 /* Decide if this is an unlinked inode in this AG. */
Signature · 1 line
2.53.0