From: Shakeel Butt shakeelb@google.com
mainline inclusion from mainline-v5.16-rc1 commit fd25a9e0e23b995fd0ba5e2f00a1099452cbc3cf category: feature bugzilla: 185803 https://gitee.com/openeuler/kernel/issues/I4JOG9?from=project-issue CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
---------------------------------------------------------------------
The memcg stats can be flushed in multiple context and potentially in parallel too. For example multiple parallel user space readers for memcg stats will contend on the rstat locks with each other. There is no need for that. We just need one flusher and everyone else can benefit.
In addition after aa48e47e3906 ("memcg: infrastructure to flush memcg stats") the kernel periodically flush the memcg stats from the root, so, the other flushers will potentially have much less work to do.
Link: https://lkml.kernel.org/r/20211001190040.48086-2-shakeelb@google.com Signed-off-by: Shakeel Butt shakeelb@google.com Acked-by: Johannes Weiner hannes@cmpxchg.org Cc: Michal Hocko mhocko@kernel.org Cc: "Michal Koutný" mkoutny@suse.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Lu Jialin lujialin4@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- mm/memcontrol.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7d08d38bee6c..f05321e7caa9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -666,12 +666,14 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg)
static void __mem_cgroup_flush_stats(void) { - if (!spin_trylock(&stats_flush_lock)) + unsigned long flag; + + if (!spin_trylock_irqsave(&stats_flush_lock, flag)) return;
cgroup_rstat_flush_irqsafe(root_mem_cgroup->css.cgroup); atomic_set(&stats_flush_threshold, 0); - spin_unlock(&stats_flush_lock); + spin_unlock_irqrestore(&stats_flush_lock, flag); }
void mem_cgroup_flush_stats(void) @@ -1508,7 +1510,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) * * Current memory state: */ - cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats();
for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { u64 size; @@ -3491,8 +3493,7 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) unsigned long val;
if (mem_cgroup_is_root(memcg)) { - /* mem_cgroup_threshold() calls here from irqsafe context */ - cgroup_rstat_flush_irqsafe(memcg->css.cgroup); + mem_cgroup_flush_stats(); val = memcg_page_state(memcg, NR_FILE_PAGES) + memcg_page_state(memcg, NR_ANON_MAPPED); if (swap) @@ -4055,7 +4056,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) int nid; struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats();
for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { seq_printf(m, "%s=%lu", stat->name, @@ -4127,7 +4128,7 @@ static int memcg_stat_show(struct seq_file *m, void *v)
BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats));
- cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats();
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { unsigned long nr; @@ -4638,7 +4639,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent;
- cgroup_rstat_flush_irqsafe(memcg->css.cgroup); + mem_cgroup_flush_stats();
*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); @@ -6559,7 +6560,7 @@ static int memory_numa_stat_show(struct seq_file *m, void *v) int i; struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
- cgroup_rstat_flush(memcg->css.cgroup); + mem_cgroup_flush_stats();
for (i = 0; i < ARRAY_SIZE(memory_stats); i++) { int nid;