linux-kernel - [PATCH v2 1/7] memcg: memcg_rstat_updated re-entrant safe against irqs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250514184158.3471331-2-shakeel.butt@linux.dev>
Date: Wed, 14 May 2025 11:41:52 -0700
From: Shakeel Butt <shakeel.butt@...ux.dev>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Johannes Weiner <hannes@...xchg.org>,
	Michal Hocko <mhocko@...nel.org>,
	Roman Gushchin <roman.gushchin@...ux.dev>,
	Muchun Song <muchun.song@...ux.dev>,
	Vlastimil Babka <vbabka@...e.cz>,
	Alexei Starovoitov <ast@...nel.org>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
	Harry Yoo <harry.yoo@...cle.com>,
	Yosry Ahmed <yosry.ahmed@...ux.dev>,
	bpf@...r.kernel.org,
	linux-mm@...ck.org,
	cgroups@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Meta kernel team <kernel-team@...a.com>
Subject: [PATCH v2 1/7] memcg: memcg_rstat_updated re-entrant safe against irqs

The function memcg_rstat_updated() is used to track the memcg stats
updates for optimizing the flushes. At the moment, it is not re-entrant
safe and the callers disabled irqs before calling. However to achieve
the goal of updating memcg stats without irqs, memcg_rstat_updated()
needs to be re-entrant safe against irqs.

This patch makes memcg_rstat_updated() re-entrant safe using this_cpu_*
ops. On archs with CONFIG_ARCH_HAS_NMI_SAFE_THIS_CPU_OPS, this patch is
also making memcg_rstat_updated() nmi safe.

Signed-off-by: Shakeel Butt <shakeel.butt@...ux.dev>
Reviewed-by: Vlastimil Babka <vbabka@...e.cz>
---
 mm/memcontrol.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 89476a71a18d..2464a58fbf17 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -505,8 +505,8 @@ struct memcg_vmstats_percpu {
 	unsigned int			stats_updates;
 
 	/* Cached pointers for fast iteration in memcg_rstat_updated() */
-	struct memcg_vmstats_percpu	*parent;
-	struct memcg_vmstats		*vmstats;
+	struct memcg_vmstats_percpu __percpu	*parent_pcpu;
+	struct memcg_vmstats			*vmstats;
 
 	/* The above should fit a single cacheline for memcg_rstat_updated() */
 
@@ -588,16 +588,21 @@ static bool memcg_vmstats_needs_flush(struct memcg_vmstats *vmstats)
 
 static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 {
+	struct memcg_vmstats_percpu __percpu *statc_pcpu;
 	struct memcg_vmstats_percpu *statc;
-	int cpu = smp_processor_id();
+	int cpu;
 	unsigned int stats_updates;
 
 	if (!val)
 		return;
 
+	/* Don't assume callers have preemption disabled. */
+	cpu = get_cpu();
+
 	cgroup_rstat_updated(memcg->css.cgroup, cpu);
-	statc = this_cpu_ptr(memcg->vmstats_percpu);
-	for (; statc; statc = statc->parent) {
+	statc_pcpu = memcg->vmstats_percpu;
+	for (; statc_pcpu; statc_pcpu = statc->parent_pcpu) {
+		statc = this_cpu_ptr(statc_pcpu);
 		/*
 		 * If @memcg is already flushable then all its ancestors are
 		 * flushable as well and also there is no need to increase
@@ -606,14 +611,15 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val)
 		if (memcg_vmstats_needs_flush(statc->vmstats))
 			break;
 
-		stats_updates = READ_ONCE(statc->stats_updates) + abs(val);
-		WRITE_ONCE(statc->stats_updates, stats_updates);
+		stats_updates = this_cpu_add_return(statc_pcpu->stats_updates,
+						    abs(val));
 		if (stats_updates < MEMCG_CHARGE_BATCH)
 			continue;
 
+		stats_updates = this_cpu_xchg(statc_pcpu->stats_updates, 0);
 		atomic64_add(stats_updates, &statc->vmstats->stats_updates);
-		WRITE_ONCE(statc->stats_updates, 0);
 	}
+	put_cpu();
 }
 
 static void __mem_cgroup_flush_stats(struct mem_cgroup *memcg, bool force)
@@ -3691,7 +3697,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 
 static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 {
-	struct memcg_vmstats_percpu *statc, *pstatc;
+	struct memcg_vmstats_percpu *statc, __percpu *pstatc_pcpu;
 	struct mem_cgroup *memcg;
 	int node, cpu;
 	int __maybe_unused i;
@@ -3722,9 +3728,9 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 
 	for_each_possible_cpu(cpu) {
 		if (parent)
-			pstatc = per_cpu_ptr(parent->vmstats_percpu, cpu);
+			pstatc_pcpu = parent->vmstats_percpu;
 		statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
-		statc->parent = parent ? pstatc : NULL;
+		statc->parent_pcpu = parent ? pstatc_pcpu : NULL;
 		statc->vmstats = memcg->vmstats;
 	}
 
-- 
2.47.1