[PATCH v2] memcg: cache obj_stock by memcg, not by objcg pointer

[Shakeel Butt <shakeel.butt@linux.dev>]

Commit 01b9da291c49 ("mm: memcontrol: convert objcg to be per-memcg
per-node type") split a memcg's single obj_cgroup into one per NUMA
node, but the per-CPU obj_stock_pcp still keys cached_objcg by
pointer. Cross-NUMA workloads now see a drain on every refill and a
miss on every consume that targets a sibling per-node objcg of the
same memcg, producing the 67.7% stress-ng switch-mq regression
reported by LKP.

stock->nr_bytes are fungible across per-node objcgs of one memcg.
Treat the cache as keyed by memcg in __consume_obj_stock() and
__refill_obj_stock() so siblings share the reserve. Compare via
READ_ONCE(objcg->memcg) directly: pointer-compare only, no deref, so
the rcu_read_lock contract on obj_cgroup_memcg() does not apply.

In the same-memcg refill path also fold the incoming objcg's
nr_charged_bytes into the stock; otherwise sub-page residue
accumulates on whichever sibling was cached at drain time and
obj_cgroup_release() silently drops it, leaking up to nr_node_ids *
(PAGE_SIZE - 1) bytes per memcg lifecycle from the page_counter.
This issue was reported by Sashiko.

Update the now-stale invariant comment on __account_obj_stock().

Qi Zheng built a specialized reproducer [1] for the corner case and
confirmed the fix.

Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202605121641.b6a60cb0-lkp@intel.com
Fixes: 01b9da291c49 ("mm: memcontrol: convert objcg to be per-memcg per-node type")
Link: https://lore.kernel.org/19693be6-7132-446e-b3fc-b7e9f56e5949@linux.dev/ [1]
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Debugged-by: Qi Zheng <qi.zheng@linux.dev>
Tested-by: Qi Zheng <qi.zheng@linux.dev>
---

Changes since v1:
- Fix the rcu warning (Sashiko).
- Fix the page counter possible underflow warning (Sashiko).

 mm/memcontrol.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d978e18b9b2d..e22ffa3b3319 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3152,7 +3152,12 @@ static void unlock_stock(struct obj_stock_pcp *stock)
 		local_unlock(&obj_stock.lock);
 }
 
-/* Call after __refill_obj_stock() to ensure stock->cached_objg == objcg */
+/*
+ * Call after __consume_obj_stock() / __refill_obj_stock(). The stock may be
+ * cached for a sibling per-node objcg of the same memcg; in that case the
+ * vmstat batching slot does not match objcg and we fall through to the
+ * direct path.
+ */
 static void __account_obj_stock(struct obj_cgroup *objcg,
 				struct obj_stock_pcp *stock, int nr,
 				struct pglist_data *pgdat, enum node_stat_item idx)
@@ -3210,7 +3215,11 @@ static bool __consume_obj_stock(struct obj_cgroup *objcg,
 				struct obj_stock_pcp *stock,
 				unsigned int nr_bytes)
 {
-	if (objcg == READ_ONCE(stock->cached_objcg) &&
+	struct obj_cgroup *cached = READ_ONCE(stock->cached_objcg);
+
+	/* Sibling per-node objcgs share the reserve. */
+	if ((cached == objcg ||
+	     (cached && READ_ONCE(cached->memcg) == READ_ONCE(objcg->memcg))) &&
 	    stock->nr_bytes >= nr_bytes) {
 		stock->nr_bytes -= nr_bytes;
 		return true;
@@ -3318,6 +3327,7 @@ static void __refill_obj_stock(struct obj_cgroup *objcg,
 			       unsigned int nr_bytes,
 			       bool allow_uncharge)
 {
+	struct obj_cgroup *cached;
 	unsigned int nr_pages = 0;
 
 	if (!stock) {
@@ -3327,7 +3337,11 @@ static void __refill_obj_stock(struct obj_cgroup *objcg,
 		goto out;
 	}
 
-	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
+	cached = READ_ONCE(stock->cached_objcg);
+	if (cached == objcg)
+		goto add_bytes;
+	/* Direct READ_ONCE due to just pointer comparison. */
+	if (!cached || READ_ONCE(cached->memcg) != READ_ONCE(objcg->memcg)) {
 		drain_obj_stock(stock);
 		obj_cgroup_get(objcg);
 		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
@@ -3335,7 +3349,12 @@ static void __refill_obj_stock(struct obj_cgroup *objcg,
 		WRITE_ONCE(stock->cached_objcg, objcg);
 
 		allow_uncharge = true;	/* Allow uncharge when objcg changes */
+	} else if (atomic_read(&objcg->nr_charged_bytes)) {
+		/* Fold sibling's stranded ncb into stock; else release leaks it. */
+		stock->nr_bytes += atomic_xchg(&objcg->nr_charged_bytes, 0);
+		allow_uncharge = true;
 	}
+add_bytes:
 	stock->nr_bytes += nr_bytes;
 
 	if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) {
-- 
2.53.0-Meta