Commit f77bd4b1 authored by Roman Gushchin's avatar Roman Gushchin Committed by Andrew Morton
Browse files

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: default avatarRoman Gushchin <roman.gushchin@linux.dev>
Acked-by: default avatarShakeel Butt <shakeel.butt@linux.dev>
Acked-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 6c469957
Loading
Loading
Loading
Loading
+7 −1
Original line number Diff line number Diff line
@@ -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)
+2 −2
Original line number Diff line number Diff line
@@ -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]));
+8 −8
Original line number Diff line number Diff line
@@ -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;
+14 −3
Original line number Diff line number Diff line
@@ -13,6 +13,11 @@
#include <linux/bug.h>
#include <asm/page.h>

static bool track_protection(struct page_counter *c)
{
	return c->protection_support;
}

static void propagate_protected_usage(struct page_counter *c,
				      unsigned long usage)
{
@@ -57,6 +62,7 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
		new = 0;
		atomic_long_set(&counter->usage, new);
	}
	if (track_protection(counter))
		propagate_protected_usage(counter, new);
}

@@ -70,11 +76,13 @@ 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);
		if (protection)
			propagate_protected_usage(c, new);
		/*
		 * This is indeed racy, but we can live with some
@@ -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;
		}
		if (protection)
			propagate_protected_usage(c, new);

		/*
		 * Just like with failcnt, we can live with some
		 * inaccuracy in the watermark.