linux-mm.kvack.org archive mirror
 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>,
	 Vlastimil Babka <vbabka@suse.cz>,
	Jakub Kicinski <kuba@kernel.org>,
	 Eric Dumazet <edumazet@google.com>,
	Soheil Hassas Yeganeh <soheil@google.com>,
	linux-mm@kvack.org,  cgroups@vger.kernel.org,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	 Meta kernel team <kernel-team@meta.com>
Subject: Re: [PATCH] memcg: multi-memcg percpu charge cache
Date: Fri, 25 Apr 2025 13:18:36 -0700	[thread overview]
Message-ID: <as5cdsm4lraxupg3t6onep2ixql72za25hvd4x334dsoyo4apr@zyzl4vkuevuv> (raw)
In-Reply-To: <20250416180229.2902751-1-shakeel.butt@linux.dev>

Hi Andrew,

Another fix for this patch. Basically simplification of refill_stock and
avoiding multiple cached entries of a memcg.

From 6f6f7736799ad8ca5fee48eca7b7038f6c9bb5b9 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeel.butt@linux.dev>
Date: Fri, 25 Apr 2025 13:10:43 -0700
Subject: [PATCH] memcg: multi-memcg percpu charge cache - fix 2

Simplify refill_stock by avoiding goto and doing the operations inline
and make sure the given memcg is not cached multiple times.

Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
---
 mm/memcontrol.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 997e2da5d2ca..9dfdbb2fcccc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1907,7 +1907,8 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	struct mem_cgroup *cached;
 	uint8_t stock_pages;
 	unsigned long flags;
-	bool evict = true;
+	bool success = false;
+	int empty_slot = -1;
 	int i;
 
 	/*
@@ -1931,26 +1932,28 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 	stock = this_cpu_ptr(&memcg_stock);
 	for (i = 0; i < NR_MEMCG_STOCK; ++i) {
-again:
 		cached = READ_ONCE(stock->cached[i]);
-		if (!cached) {
-			css_get(&memcg->css);
-			WRITE_ONCE(stock->cached[i], memcg);
-		}
-		if (!cached || memcg == READ_ONCE(stock->cached[i])) {
+		if (!cached && empty_slot == -1)
+			empty_slot = i;
+		if (memcg == READ_ONCE(stock->cached[i])) {
 			stock_pages = READ_ONCE(stock->nr_pages[i]) + nr_pages;
 			WRITE_ONCE(stock->nr_pages[i], stock_pages);
 			if (stock_pages > MEMCG_CHARGE_BATCH)
 				drain_stock(stock, i);
-			evict = false;
+			success = true;
 			break;
 		}
 	}
 
-	if (evict) {
-		i = get_random_u32_below(NR_MEMCG_STOCK);
-		drain_stock(stock, i);
-		goto again;
+	if (!success) {
+		i = empty_slot;
+		if (i == -1) {
+			i = get_random_u32_below(NR_MEMCG_STOCK);
+			drain_stock(stock, i);
+		}
+		css_get(&memcg->css);
+		WRITE_ONCE(stock->cached[i], memcg);
+		WRITE_ONCE(stock->nr_pages[i], stock_pages);
 	}
 
 	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
-- 
2.47.1



  parent reply	other threads:[~2025-04-25 20:18 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-04-16 18:02 Shakeel Butt
2025-04-23  1:10 ` Jakub Kicinski
2025-04-23 22:16   ` Shakeel Butt
2025-04-23 22:30     ` Jakub Kicinski
2025-04-23 22:59       ` Shakeel Butt
2025-04-23 23:14 ` Shakeel Butt
2025-04-25 20:18 ` Shakeel Butt [this message]
2025-04-29  9:40   ` Hugh Dickins
2025-04-29 14:50     ` Shakeel Butt
2025-04-30 10:05   ` Vlastimil Babka
2025-04-30 15:16     ` Shakeel Butt
2025-04-29 12:13 ` Michal Hocko
2025-04-29 18:43   ` Shakeel Butt
2025-04-30  6:48     ` Michal Hocko
2025-04-30  9:57 ` Vlastimil Babka
2025-04-30 15:05   ` Shakeel Butt
2025-04-30 15:32 ` Shakeel Butt

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=as5cdsm4lraxupg3t6onep2ixql72za25hvd4x334dsoyo4apr@zyzl4vkuevuv \
    --to=shakeel.butt@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=edumazet@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=kernel-team@meta.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=netdev@vger.kernel.org \
    --cc=roman.gushchin@linux.dev \
    --cc=soheil@google.com \
    --cc=vbabka@suse.cz \
    /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