[PATCH] slab: distinguish lock and trylock for sheaf_flush_main()

[Vlastimil Babka]

sheaf_flush_main() can be called from __pcs_replace_full_main() where
the trylock can in theory fail, and pcs_flush_all() where it's not
expected to and it would be actually a problem if it failed and left the
main sheaf not flushed.

To make this explicit, split the function into sheaf_flush_main() (using
local_lock()) and sheaf_try_flush_main() (using local_trylock()) where
both call __sheaf_flush_main_batch() to flush a single batch of objects.
This will allow lockdep to verify our assumptions.

Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
---
 mm/slub.c | 47 +++++++++++++++++++++++++++++++++++++----------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 18c30872d196..12912b29f5bb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2844,19 +2844,19 @@ static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p);
  * object pointers are moved to a on-stack array under the lock. To bound the
  * stack usage, limit each batch to PCS_BATCH_MAX.
  *
- * returns true if at least partially flushed
+ * Must be called with s->cpu_sheaves->lock locked, returns with the lock
+ * unlocked.
+ *
+ * Returns how many objects are remaining to be flushed
  */
-static bool sheaf_flush_main(struct kmem_cache *s)
+static unsigned int __sheaf_flush_main_batch(struct kmem_cache *s)
 {
 	struct slub_percpu_sheaves *pcs;
 	unsigned int batch, remaining;
 	void *objects[PCS_BATCH_MAX];
 	struct slab_sheaf *sheaf;
-	bool ret = false;
 
-next_batch:
-	if (!local_trylock(&s->cpu_sheaves->lock))
-		return ret;
+	lockdep_assert_held(this_cpu_ptr(&s->cpu_sheaves->lock));
 
 	pcs = this_cpu_ptr(s->cpu_sheaves);
 	sheaf = pcs->main;
@@ -2874,10 +2874,37 @@ static bool sheaf_flush_main(struct kmem_cache *s)
 
 	stat_add(s, SHEAF_FLUSH, batch);
 
-	ret = true;
+	return remaining;
+}
 
-	if (remaining)
-		goto next_batch;
+static void sheaf_flush_main(struct kmem_cache *s)
+{
+	unsigned int remaining;
+
+	do {
+		local_lock(&s->cpu_sheaves->lock);
+
+		remaining = __sheaf_flush_main_batch(s);
+
+	} while (remaining);
+}
+
+/*
+ * Returns true if the main sheaf was at least partially flushed.
+ */
+static bool sheaf_try_flush_main(struct kmem_cache *s)
+{
+	unsigned int remaining;
+	bool ret = false;
+
+	do {
+		if (!local_trylock(&s->cpu_sheaves->lock))
+			return ret;
+
+		ret = true;
+		remaining = __sheaf_flush_main_batch(s);
+
+	} while (remaining);
 
 	return ret;
 }
@@ -5685,7 +5712,7 @@ __pcs_replace_full_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs,
 	if (put_fail)
 		 stat(s, BARN_PUT_FAIL);
 
-	if (!sheaf_flush_main(s))
+	if (!sheaf_try_flush_main(s))
 		return NULL;
 
 	if (!local_trylock(&s->cpu_sheaves->lock))

---
base-commit: 27125df9a5d3b4cfd03bce3a8ec405a368cc9aae
change-id: 20260211-b4-sheaf-flush-2eb99a9c8bfb

Best regards,
-- 
Vlastimil Babka <vbabka@xxxxxxx>