[PATCH 2/2] jbd2: bound shrinker scans by examined checkpoint buffers

[Max Kellermann]

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@xxxxxxxxxxxxxxx
Signed-off-by: Max Kellermann <max.kellermann@xxxxxxxxx>
---
 fs/jbd2/checkpoint.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

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
-- 
2.47.3