From f77bd4b14ccfd38dfcfe67eecad517b8ec1b7f37 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Jul 2024 20:31:08 +0000 Subject: [PATCH] mm: memcg: don't call propagate_protected_usage() needlessly Patch series "mm: memcg: page counters optimizations", v3. This patchset contains 3 independent small optimizations of page counters. This patch (of 3): Memory protection (min/low) requires a constant tracking of protected memory usage. propagate_protected_usage() is called on each page counters update and does a number of operations even in cases when the actual memory protection functionality is not supported (e.g. hugetlb cgroups or memcg swap counters). It's obviously inefficient and leads to a waste of CPU cycles. It can be addressed by calling propagate_protected_usage() only for the counters which do support memory guarantees. As of now it's only memcg->memory - the unified memory memcg counter. Link: https://lkml.kernel.org/r/20240726203110.1577216-2-roman.gushchin@linux.dev Signed-off-by: Roman Gushchin Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton --- include/linux/page_counter.h | 8 +++++++- mm/hugetlb_cgroup.c | 4 ++-- mm/memcontrol.c | 16 ++++++++-------- mm/page_counter.c | 17 ++++++++++++++--- 4 files changed, 31 insertions(+), 14 deletions(-) diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 904c52f97284..0b8e993f9163 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -31,6 +31,7 @@ struct page_counter { /* Keep all the read most fields in a separete cacheline. */ CACHELINE_PADDING(_pad2_); + bool protection_support; unsigned long min; unsigned long low; unsigned long high; @@ -44,12 +45,17 @@ struct page_counter { #define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE) #endif +/* + * Protection is supported only for the first counter (with id 0). + */ static inline void page_counter_init(struct page_counter *counter, - struct page_counter *parent) + struct page_counter *parent, + bool protection_support) { atomic_long_set(&counter->usage, 0); counter->max = PAGE_COUNTER_MAX; counter->parent = parent; + counter->protection_support = protection_support; } static inline unsigned long page_counter_read(struct page_counter *counter) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 4ff238ba1250..e716c4671a15 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -114,10 +114,10 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, } page_counter_init(hugetlb_cgroup_counter_from_cgroup(h_cgroup, idx), - fault_parent); + fault_parent, false); page_counter_init( hugetlb_cgroup_counter_from_cgroup_rsvd(h_cgroup, idx), - rsvd_parent); + rsvd_parent, false); limit = round_down(PAGE_COUNTER_MAX, pages_per_huge_page(&hstates[idx])); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c0ee0f2f8176..f92578f13b2e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3596,21 +3596,21 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (parent) { WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent)); - page_counter_init(&memcg->memory, &parent->memory); - page_counter_init(&memcg->swap, &parent->swap); + page_counter_init(&memcg->memory, &parent->memory, true); + page_counter_init(&memcg->swap, &parent->swap, false); #ifdef CONFIG_MEMCG_V1 WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable)); - page_counter_init(&memcg->kmem, &parent->kmem); - page_counter_init(&memcg->tcpmem, &parent->tcpmem); + page_counter_init(&memcg->kmem, &parent->kmem, false); + page_counter_init(&memcg->tcpmem, &parent->tcpmem, false); #endif } else { init_memcg_stats(); init_memcg_events(); - page_counter_init(&memcg->memory, NULL); - page_counter_init(&memcg->swap, NULL); + page_counter_init(&memcg->memory, NULL, true); + page_counter_init(&memcg->swap, NULL, false); #ifdef CONFIG_MEMCG_V1 - page_counter_init(&memcg->kmem, NULL); - page_counter_init(&memcg->tcpmem, NULL); + page_counter_init(&memcg->kmem, NULL, false); + page_counter_init(&memcg->tcpmem, NULL, false); #endif root_mem_cgroup = memcg; return &memcg->css; diff --git a/mm/page_counter.c b/mm/page_counter.c index 0153f5bb3161..dd242245bee2 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -13,6 +13,11 @@ #include #include +static bool track_protection(struct page_counter *c) +{ + return c->protection_support; +} + static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { @@ -57,7 +62,8 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) new = 0; atomic_long_set(&counter->usage, new); } - propagate_protected_usage(counter, new); + if (track_protection(counter)) + propagate_protected_usage(counter, new); } /** @@ -70,12 +76,14 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; + bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); - propagate_protected_usage(c, new); + if (protection) + propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. @@ -99,6 +107,7 @@ bool page_counter_try_charge(struct page_counter *counter, struct page_counter **fail) { struct page_counter *c; + bool protection = track_protection(counter); for (c = counter; c; c = c->parent) { long new; @@ -128,7 +137,9 @@ bool page_counter_try_charge(struct page_counter *counter, *fail = c; goto failed; } - propagate_protected_usage(c, new); + if (protection) + propagate_protected_usage(c, new); + /* * Just like with failcnt, we can live with some * inaccuracy in the watermark.