[PATCH 2/4] memcg: uint16_t for nr_bytes in obj_stock_pcp

[Shakeel Butt]

Currently struct obj_stock_pcp stores nr_bytes in an 'unsigned int'
which is 4 bytes on 64-bit machines. Switch the field to uint16_t to
shrink the per-CPU cache.

The kernel supports PAGE_SIZE_4KB, _8KB, _16KB, _32KB, _64KB and
_256KB (see HAVE_PAGE_SIZE_* in arch/Kconfig). After the
PAGE_SIZE-aligned flush in __refill_obj_stock(), the sub-page
remainder fits in uint16_t up through 64KiB pages where PAGE_SIZE - 1
== U16_MAX, but on 256KiB pages PAGE_SIZE - 1 == 0x3FFFF exceeds
U16_MAX. The accumulator also needs to stay within uint16_t between
page-aligned flushes on 64KiB pages where PAGE_SIZE itself is
U16_MAX + 1.

Accumulate the new total in an 'unsigned int' local, then:

  1. Flush whenever the accumulator would hit U16_MAX. Together with
     the existing allow_uncharge flush at PAGE_SIZE, this keeps the
     uint16_t safe on PAGE_SIZE <= 64KiB.

  2. On configs with PAGE_SHIFT > 16 (PAGE_SIZE_256KB on hexagon and
     powerpc 44x), push any sub-page remainder above U16_MAX into
     objcg->nr_charged_bytes via atomic_add before storing back, so
     the store cannot silently truncate. The PAGE_SHIFT > 16 guard
     folds the branch out at compile time on smaller page sizes.

Signed-off-by: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Tested-by: kernel test robot <oliver.sang@xxxxxxxxx>
---
 mm/memcontrol.c | 33 +++++++++++++++++++++++++++------
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d7c162946719..b3d63d9f267c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2019,7 +2019,7 @@ static DEFINE_PER_CPU_ALIGNED(struct memcg_stock_pcp, memcg_stock) = {
 
 struct obj_stock_pcp {
 	local_trylock_t lock;
-	unsigned int nr_bytes;
+	uint16_t nr_bytes;
 	struct obj_cgroup *cached_objcg;
 	int16_t node_id;
 	int nr_slab_reclaimable_b;
@@ -3331,6 +3331,7 @@ static void __refill_obj_stock(struct obj_cgroup *objcg,
 			       bool allow_uncharge)
 {
 	unsigned int nr_pages = 0;
+	unsigned int stock_nr_bytes;
 
 	if (!stock) {
 		nr_pages = nr_bytes >> PAGE_SHIFT;
@@ -3339,21 +3340,41 @@ static void __refill_obj_stock(struct obj_cgroup *objcg,
 		goto out;
 	}
 
+	stock_nr_bytes = stock->nr_bytes;
 	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
 		drain_obj_stock(stock);
 		obj_cgroup_get(objcg);
-		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
+		stock_nr_bytes = atomic_read(&objcg->nr_charged_bytes)
 				? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
 		WRITE_ONCE(stock->cached_objcg, objcg);
 
 		allow_uncharge = true;	/* Allow uncharge when objcg changes */
 	}
-	stock->nr_bytes += nr_bytes;
+	stock_nr_bytes += nr_bytes;
+
+	/* Since stock->nr_bytes is uint16_t, don't refill >= U16_MAX */
+	if ((allow_uncharge && (stock_nr_bytes > PAGE_SIZE)) ||
+	    stock_nr_bytes >= U16_MAX) {
+		nr_pages = stock_nr_bytes >> PAGE_SHIFT;
+		stock_nr_bytes &= (PAGE_SIZE - 1);
+
+		/*
+		 * On configs with PAGE_SHIFT > 16 (PAGE_SIZE_256KB on
+		 * hexagon and powerpc 44x), the sub-page remainder can
+		 * still exceed U16_MAX. Push the excess back to
+		 * objcg->nr_charged_bytes so the store into uint16_t
+		 * cannot silently truncate; folded out at compile time
+		 * on smaller page sizes.
+		 */
+		if (PAGE_SHIFT > 16 && stock_nr_bytes > U16_MAX) {
+			unsigned int kept = stock_nr_bytes & U16_MAX;
 
-	if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) {
-		nr_pages = stock->nr_bytes >> PAGE_SHIFT;
-		stock->nr_bytes &= (PAGE_SIZE - 1);
+			atomic_add(stock_nr_bytes - kept,
+				   &objcg->nr_charged_bytes);
+			stock_nr_bytes = kept;
+		}
 	}
+	stock->nr_bytes = stock_nr_bytes;
 
 out:
 	if (nr_pages)
-- 
2.53.0-Meta