Linux cgroups development
 help / color / mirror / Atom feed
From: Shakeel Butt <shakeel.butt@linux.dev>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Roman Gushchin <roman.gushchin@linux.dev>,
	Muchun Song <muchun.song@linux.dev>,
	Qi Zheng <qi.zheng@linux.dev>, Alexandre Ghiti <alex@ghiti.fr>,
	Joshua Hahn <joshua.hahnjy@gmail.com>,
	Harry Yoo <harry@kernel.org>,
	David Laight <david.laight.linux@gmail.com>,
	Meta kernel team <kernel-team@meta.com>,
	linux-mm@kvack.org, cgroups@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	kernel test robot <oliver.sang@intel.com>
Subject: [PATCH v3 2/4] memcg: uint16_t for nr_bytes in obj_stock_pcp
Date: Mon, 25 May 2026 20:39:29 -0700	[thread overview]
Message-ID: <20260526033931.1760588-3-shakeel.butt@linux.dev> (raw)
In-Reply-To: <20260526033931.1760588-1-shakeel.butt@linux.dev>

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.

Fixes: 01b9da291c49 ("mm: memcontrol: convert objcg to be per-memcg per-node type")
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>
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
---
Changes since v2:
- Based on Sashiko's concern regarding archs with 256KiB base pages, added
  special handling for such arch and simplify the code overall.
- Updated commit message.
- Have kept the review tags as overall code remains same mostly. 

Changes since v1:
- Collected tags
- Rearrange fields of obj_stock_pcp (David Laight)
- Fix comparison operator (Harry)

 mm/memcontrol.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9bee9031171f..8c1b65e6da5d 100644
--- 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)
-- 
2.53.0-Meta


  parent reply	other threads:[~2026-05-26  3:40 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-26  3:39 [PATCH v3 0/4] memcg: shrink obj_stock_pcp and cache multiple objcgs Shakeel Butt
2026-05-26  3:39 ` [PATCH v3 1/4] memcg: store node_id instead of pglist_data pointer Shakeel Butt
2026-05-26  3:39 ` Shakeel Butt [this message]
2026-05-26  3:39 ` [PATCH v3 3/4] memcg: int16_t for cached slab stats Shakeel Butt
2026-05-26  3:39 ` [PATCH v3 4/4] memcg: multi objcg charge support Shakeel Butt
2026-05-26  5:44   ` Harry Yoo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260526033931.1760588-3-shakeel.butt@linux.dev \
    --to=shakeel.butt@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=alex@ghiti.fr \
    --cc=cgroups@vger.kernel.org \
    --cc=david.laight.linux@gmail.com \
    --cc=hannes@cmpxchg.org \
    --cc=harry@kernel.org \
    --cc=joshua.hahnjy@gmail.com \
    --cc=kernel-team@meta.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=oliver.sang@intel.com \
    --cc=qi.zheng@linux.dev \
    --cc=roman.gushchin@linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox