From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Morton Subject: [patch 075/155] mm, memcg: prevent memory.max load tearing Date: Wed, 01 Apr 2020 21:07:20 -0700 Message-ID: <20200402040720.t76zXBOZv%akpm@linux-foundation.org> References: <20200401210155.09e3b9742e1c6e732f5a7250@linux-foundation.org> Reply-To: linux-kernel@vger.kernel.org Return-path: Received: from mail.kernel.org ([198.145.29.99]:58310 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726963AbgDBEHW (ORCPT ); Thu, 2 Apr 2020 00:07:22 -0400 In-Reply-To: <20200401210155.09e3b9742e1c6e732f5a7250@linux-foundation.org> Sender: mm-commits-owner@vger.kernel.org List-Id: mm-commits@vger.kernel.org To: akpm@linux-foundation.org, chris@chrisdown.name, guro@fb.com, hannes@cmpxchg.org, linux-mm@kvack.org, mhocko@suse.com, mm-commits@vger.kernel.org, tj@kernel.org, torvalds@linux-foundation.org From: Chris Down Subject: mm, memcg: prevent memory.max load tearing This one is a bit more nuanced because we have memcg_max_mutex, which is mostly just used for enforcing invariants, but we still need to READ_ONCE since (despite its name) it doesn't really protect memory.max access. On write (page_counter_set_max() and memory_max_write()) we use xchg(), which uses smp_mb(), so that's already fine. Link: http://lkml.kernel.org/r/50a31e5f39f8ae6c8fb73966ba1455f0924e8f44.1584034301.git.chris@chrisdown.name Signed-off-by: Chris Down Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Roman Gushchin Cc: Tejun Heo Signed-off-by: Andrew Morton --- mm/memcontrol.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) --- a/mm/memcontrol.c~mm-memcg-prevent-memorymax-load-tearing +++ a/mm/memcontrol.c @@ -1521,7 +1521,7 @@ void mem_cgroup_print_oom_meminfo(struct pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memory)), - K((u64)memcg->memory.max), memcg->memory.failcnt); + K((u64)READ_ONCE(memcg->memory.max)), memcg->memory.failcnt); if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) pr_info("swap: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->swap)), @@ -1552,7 +1552,7 @@ unsigned long mem_cgroup_get_max(struct { unsigned long max; - max = memcg->memory.max; + max = READ_ONCE(memcg->memory.max); if (mem_cgroup_swappiness(memcg)) { unsigned long memsw_max; unsigned long swap_max; @@ -3068,7 +3068,7 @@ static int mem_cgroup_resize_max(struct * Make sure that the new limit (memsw or memory limit) doesn't * break our basic invariant rule memory.max <= memsw.max. */ - limits_invariant = memsw ? max >= memcg->memory.max : + limits_invariant = memsw ? max >= READ_ONCE(memcg->memory.max) : max <= memcg->memsw.max; if (!limits_invariant) { mutex_unlock(&memcg_max_mutex); @@ -3815,8 +3815,8 @@ static int memcg_stat_show(struct seq_fi /* Hierarchical information */ memory = memsw = PAGE_COUNTER_MAX; for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) { - memory = min(memory, mi->memory.max); - memsw = min(memsw, mi->memsw.max); + memory = min(memory, READ_ONCE(mi->memory.max)); + memsw = min(memsw, READ_ONCE(mi->memsw.max)); } seq_printf(m, "hierarchical_memory_limit %llu\n", (u64)memory * PAGE_SIZE); @@ -4325,7 +4325,7 @@ void mem_cgroup_wb_stats(struct bdi_writ *pheadroom = PAGE_COUNTER_MAX; while ((parent = parent_mem_cgroup(memcg))) { - unsigned long ceiling = min(memcg->memory.max, + unsigned long ceiling = min(READ_ONCE(memcg->memory.max), READ_ONCE(memcg->high)); unsigned long used = page_counter_read(&memcg->memory); _