memcg: uint16_t for nr_bytes in obj_stock_pcp

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 on PAGE_SHIFT <=
16 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 configs with PAGE_SHIFT > 16 (PAGE_SIZE_256KB on hexagon and powerpc
44x, both 32-bit), uint16_t cannot represent the sub-page remainder.
Define obj_stock_bytes_t as 'unsigned int' on those archs so nr_bytes can
hold the full remainder and the normal page-boundary flush in
__refill_obj_stock() and the page extraction in drain_obj_stock() both
work correctly.

The single-cache-line layout target only applies to PAGE_SHIFT <= 16;
those archs are 32-bit embedded and not the optimization target.

Link: https://lore.kernel.org/20260526033931.1760588-3-shakeel.butt@linux.dev
Fixes: 01b9da291c49 ("mm: memcontrol: convert objcg to be per-memcg per-node type")
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Tested-by: kernel test robot <oliver.sang@intel.com>
Reviewed-by: Harry Yoo (Oracle) <harry@kernel.org>
Acked-by: Qi Zheng <qi.zheng@linux.dev>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e983fa590af8c3d335341cddb8281559a3cfee2e..8bbcc7bc42e3dc367fd3f9453e13bbba3cefec4a 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2020,8 +2020,17 @@ static DEFINE_PER_CPU_ALIGNED(struct memcg_stock_pcp, memcg_stock) = {
 
 struct obj_stock_pcp {
        local_trylock_t lock;
-       unsigned int nr_bytes;
        struct obj_cgroup *cached_objcg;
+#if PAGE_SHIFT > 16
+       /*
+        * On rare archs with 256KiB base page size (hexagon and powerpc 44x)
+        * keep nr_bytes to unsigned int as uint16_t cannot represent the full
+        * sub-page remainder.
+        */
+       unsigned int nr_bytes;
+#else
+       uint16_t nr_bytes;
+#endif
        int16_t node_id;
        int nr_slab_reclaimable_b;
        int nr_slab_unreclaimable_b;
@@ -3334,6 +3343,7 @@ 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;
@@ -3342,21 +3352,24 @@ 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;
 
-       if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) {
-               nr_pages = stock->nr_bytes >> PAGE_SHIFT;
-               stock->nr_bytes &= (PAGE_SIZE - 1);
+       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);
        }
+       stock->nr_bytes = stock_nr_bytes;
 
 out:
        if (nr_pages)