Linux kernel -stable discussions
 help / color / mirror / Atom feed
* FAILED: patch "[PATCH] jbd2: bound shrinker scans by examined checkpoint buffers" failed to apply to 5.15-stable tree
@ 2026-09-03 13:59 gregkh
  2026-09-08 16:15 ` [PATCH 5.15.y 1/3] jbd2: use shrink_type type instead of bool type for __jbd2_journal_clean_checkpoint_list() Sasha Levin
  0 siblings, 1 reply; 5+ messages in thread
From: gregkh @ 2026-09-03 13:59 UTC (permalink / raw)
  To: max.kellermann, jack, tytso, yi.zhang; +Cc: stable


The patch below does not apply to the 5.15-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 <stable@vger.kernel.org>.

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-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x 15cb16496446b94e67f7abcb049b8e2c75cd3d02
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026090325-massive-fabulous-a27d@gregkh' --subject-prefix 'PATCH 5.15.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

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

From 15cb16496446b94e67f7abcb049b8e2c75cd3d02 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Mon, 13 Jul 2026 12:22:29 +0200
Subject: [PATCH] jbd2: bound shrinker scans by examined checkpoint buffers

The jbd2 shrinker currently accounts only checkpoint buffers that it
successfully releases against nr_to_scan.  Busy buffers therefore do not
consume the scan budget.

If a checkpoint transaction contains mostly busy buffers, the shrinker
can scan its entire checkpoint list while holding journal->j_list_lock.
Large checkpoint lists can result in excessive lock hold times and leave
other CPUs spinning on j_list_lock, causing soft lockups or RCU stalls.

Pass nr_to_scan into journal_shrink_one_cp_list() and decrement it for
every buffer examined, including busy buffers.  Pass NULL from checkpoint
cleanup paths so their existing full-list behavior is preserved.

This restores the scan-budget semantics that existed before
journal_shrink_one_cp_list() was changed to always scan a complete
checkpoint list.

Fixes: b98dba273a0e ("jbd2: remove journal_clean_one_cp_list()")
Cc: stable@vger.kernel.org
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260713102229.1598812-3-max.kellermann@ionos.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 5266017565ac..513273712010 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -358,15 +358,16 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 /*
  * journal_shrink_one_cp_list
  *
- * Find all the written-back checkpoint buffers in the given list
- * and try to release them. If the whole transaction is released, set
- * the 'released' parameter. Return the number of released checkpointed
- * buffers.
+ * Find written-back checkpoint buffers in the given list and try to release
+ * them. If 'nr_to_scan' is set, scan at most that many buffers. If the whole
+ * transaction is released, set the 'released' parameter. Return the number of
+ * released checkpointed buffers.
  *
  * Called with j_list_lock held.
  */
 static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 						enum jbd2_shrink_type type,
+						unsigned long *nr_to_scan,
 						bool *released)
 {
 	struct journal_head *last_jh;
@@ -375,13 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 	int ret;
 
 	*released = false;
-	if (!jh)
+	if (!jh || (nr_to_scan && !*nr_to_scan))
 		return 0;
 
 	last_jh = jh->b_cpprev;
 	do {
 		jh = next_jh;
 		next_jh = jh->b_cpnext;
+		if (nr_to_scan)
+			(*nr_to_scan)--;
 
 		if (type == JBD2_SHRINK_DESTROY) {
 			ret = __jbd2_journal_remove_checkpoint(jh);
@@ -403,7 +406,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 next:
 		if (need_resched())
 			break;
-	} while (jh != last_jh);
+	} while (jh != last_jh && (!nr_to_scan || *nr_to_scan));
 
 	return nr_freed;
 }
@@ -425,7 +428,6 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 	tid_t first_tid = 0, last_tid = 0, next_tid = 0;
 	tid_t tid = 0;
 	unsigned long nr_freed = 0;
-	unsigned long freed;
 	bool first_set = false;
 
 again:
@@ -458,10 +460,9 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
 		next_transaction = transaction->t_cpnext;
 		tid = transaction->t_tid;
 
-		freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list,
-						   JBD2_SHRINK_BUSY_SKIP, &released);
-		nr_freed += freed;
-		(*nr_to_scan) -= min(*nr_to_scan, freed);
+		nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list,
+						       JBD2_SHRINK_BUSY_SKIP,
+						       nr_to_scan, &released);
 		if (*nr_to_scan == 0)
 			break;
 		if (need_resched() || spin_needbreak(&journal->j_list_lock))
@@ -517,7 +518,7 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal,
 		transaction = next_transaction;
 		next_transaction = transaction->t_cpnext;
 		journal_shrink_one_cp_list(transaction->t_checkpoint_list,
-					   type, &released);
+					   type, NULL, &released);
 		/*
 		 * This function only frees up some memory if possible so we
 		 * dont have an obligation to finish processing. Bail out if


^ permalink raw reply related	[flat|nested] 5+ messages in thread
* FAILED: patch "[PATCH] jbd2: check need_resched() when skipping busy checkpoint" failed to apply to 5.15-stable tree
@ 2026-09-03 13:59 gregkh
  2026-09-08 16:06 ` [PATCH 5.15.y 1/3] jbd2: use shrink_type type instead of bool type for __jbd2_journal_clean_checkpoint_list() Sasha Levin
  0 siblings, 1 reply; 5+ messages in thread
From: gregkh @ 2026-09-03 13:59 UTC (permalink / raw)
  To: max.kellermann, jack, tytso, yi.zhang; +Cc: stable


The patch below does not apply to the 5.15-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 <stable@vger.kernel.org>.

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-5.15.y
git checkout FETCH_HEAD
git cherry-pick -x f213e12ff5c9590b1034ae8da0e6d09665c772d0
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026090337-absolve-bonnet-5b19@gregkh' --subject-prefix 'PATCH 5.15.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

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

From f213e12ff5c9590b1034ae8da0e6d09665c772d0 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Mon, 13 Jul 2026 12:22:28 +0200
Subject: [PATCH] jbd2: check need_resched() when skipping busy checkpoint
 buffers

journal_shrink_one_cp_list() skips busy checkpoint buffers when called
with JBD2_SHRINK_BUSY_SKIP.  The continue statement on this path also
skips the need_resched() check at the end of the loop body.

Consequently, when a checkpoint list contains mostly busy buffers, the
shrinker can walk the entire list while holding journal->j_list_lock,
even when a reschedule has been requested.  Large checkpoint lists under
memory pressure can therefore cause long lock hold times and leave other
CPUs spinning on j_list_lock, resulting in soft lockups or RCU stalls.

Route the busy-buffer path through the need_resched() check so that the
shrinker can release j_list_lock and reschedule promptly, restoring
parity with the clean-buffer path, which already checks need_resched().
This does not change which checkpoint buffers are eligible for removal.

Fixes: b98dba273a0e ("jbd2: remove journal_clean_one_cp_list()")
Cc: stable@vger.kernel.org
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20260713102229.1598812-2-max.kellermann@ionos.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 1508e2f54462..5266017565ac 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -389,7 +389,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 			ret = jbd2_journal_try_remove_checkpoint(jh);
 			if (ret < 0) {
 				if (type == JBD2_SHRINK_BUSY_SKIP)
-					continue;
+					goto next;
 				break;
 			}
 		}
@@ -400,6 +400,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
 			break;
 		}
 
+next:
 		if (need_resched())
 			break;
 	} while (jh != last_jh);


^ permalink raw reply related	[flat|nested] 5+ messages in thread
end of thread, other threads:[~2026-09-08 16:15 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-09-03 13:59 FAILED: patch "[PATCH] jbd2: bound shrinker scans by examined checkpoint buffers" failed to apply to 5.15-stable tree gregkh
2026-09-08 16:15 ` [PATCH 5.15.y 1/3] jbd2: use shrink_type type instead of bool type for __jbd2_journal_clean_checkpoint_list() Sasha Levin
2026-09-08 16:15   ` [PATCH 5.15.y 2/3] jbd2: add prefix 'jbd2' for 'shrink_type' Sasha Levin
2026-09-08 16:15   ` [PATCH 5.15.y 3/3] jbd2: bound shrinker scans by examined checkpoint buffers Sasha Levin
  -- strict thread matches above, loose matches on Subject: below --
2026-09-03 13:59 FAILED: patch "[PATCH] jbd2: check need_resched() when skipping busy checkpoint" failed to apply to 5.15-stable tree gregkh
2026-09-08 16:06 ` [PATCH 5.15.y 1/3] jbd2: use shrink_type type instead of bool type for __jbd2_journal_clean_checkpoint_list() Sasha Levin

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox