2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-24 13:13:57 +08:00
linux-next/mm/page_counter.c
Michal Koutný a6f23d14ec mm/page_counter.c: fix protection usage propagation
When workload runs in cgroups that aren't directly below root cgroup and
their parent specifies reclaim protection, it may end up ineffective.

The reason is that propagate_protected_usage() is not called in all
hierarchy up.  All the protected usage is incorrectly accumulated in the
workload's parent.  This means that siblings_low_usage is overestimated
and effective protection underestimated.  Even though it is transitional
phenomenon (uncharge path does correct propagation and fixes the wrong
children_low_usage), it can undermine the intended protection
unexpectedly.

We have noticed this problem while seeing a swap out in a descendant of a
protected memcg (intermediate node) while the parent was conveniently
under its protection limit and the memory pressure was external to that
hierarchy.  Michal has pinpointed this down to the wrong
siblings_low_usage which led to the unwanted reclaim.

The fix is simply updating children_low_usage in respective ancestors also
in the charging path.

Fixes: 230671533d ("mm: memory.low hierarchical behavior")
Signed-off-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org>	[4.18+]
Link: http://lkml.kernel.org/r/20200803153231.15477-1-mhocko@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 11:33:26 -07:00

262 lines
6.6 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Lockless hierarchical page accounting & limiting
*
* Copyright (C) 2014 Red Hat, Inc., Johannes Weiner
*/
#include <linux/page_counter.h>
#include <linux/atomic.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/bug.h>
#include <asm/page.h>
static void propagate_protected_usage(struct page_counter *c,
unsigned long usage)
{
unsigned long protected, old_protected;
unsigned long low, min;
long delta;
if (!c->parent)
return;
min = READ_ONCE(c->min);
if (min || atomic_long_read(&c->min_usage)) {
protected = min(usage, min);
old_protected = atomic_long_xchg(&c->min_usage, protected);
delta = protected - old_protected;
if (delta)
atomic_long_add(delta, &c->parent->children_min_usage);
}
low = READ_ONCE(c->low);
if (low || atomic_long_read(&c->low_usage)) {
protected = min(usage, low);
old_protected = atomic_long_xchg(&c->low_usage, protected);
delta = protected - old_protected;
if (delta)
atomic_long_add(delta, &c->parent->children_low_usage);
}
}
/**
* page_counter_cancel - take pages out of the local counter
* @counter: counter
* @nr_pages: number of pages to cancel
*/
void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
{
long new;
new = atomic_long_sub_return(nr_pages, &counter->usage);
propagate_protected_usage(counter, new);
/* More uncharges than charges? */
WARN_ON_ONCE(new < 0);
}
/**
* page_counter_charge - hierarchically charge pages
* @counter: counter
* @nr_pages: number of pages to charge
*
* NOTE: This does not consider any configured counter limits.
*/
void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
for (c = counter; c; c = c->parent) {
long new;
new = atomic_long_add_return(nr_pages, &c->usage);
propagate_protected_usage(c, new);
/*
* This is indeed racy, but we can live with some
* inaccuracy in the watermark.
*/
if (new > c->watermark)
c->watermark = new;
}
}
/**
* page_counter_try_charge - try to hierarchically charge pages
* @counter: counter
* @nr_pages: number of pages to charge
* @fail: points first counter to hit its limit, if any
*
* Returns %true on success, or %false and @fail if the counter or one
* of its ancestors has hit its configured limit.
*/
bool page_counter_try_charge(struct page_counter *counter,
unsigned long nr_pages,
struct page_counter **fail)
{
struct page_counter *c;
for (c = counter; c; c = c->parent) {
long new;
/*
* Charge speculatively to avoid an expensive CAS. If
* a bigger charge fails, it might falsely lock out a
* racing smaller charge and send it into reclaim
* early, but the error is limited to the difference
* between the two sizes, which is less than 2M/4M in
* case of a THP locking out a regular page charge.
*
* The atomic_long_add_return() implies a full memory
* barrier between incrementing the count and reading
* the limit. When racing with page_counter_limit(),
* we either see the new limit or the setter sees the
* counter has changed and retries.
*/
new = atomic_long_add_return(nr_pages, &c->usage);
if (new > c->max) {
atomic_long_sub(nr_pages, &c->usage);
propagate_protected_usage(c, new);
/*
* This is racy, but we can live with some
* inaccuracy in the failcnt.
*/
c->failcnt++;
*fail = c;
goto failed;
}
propagate_protected_usage(c, new);
/*
* Just like with failcnt, we can live with some
* inaccuracy in the watermark.
*/
if (new > c->watermark)
c->watermark = new;
}
return true;
failed:
for (c = counter; c != *fail; c = c->parent)
page_counter_cancel(c, nr_pages);
return false;
}
/**
* page_counter_uncharge - hierarchically uncharge pages
* @counter: counter
* @nr_pages: number of pages to uncharge
*/
void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
for (c = counter; c; c = c->parent)
page_counter_cancel(c, nr_pages);
}
/**
* page_counter_set_max - set the maximum number of pages allowed
* @counter: counter
* @nr_pages: limit to set
*
* Returns 0 on success, -EBUSY if the current number of pages on the
* counter already exceeds the specified limit.
*
* The caller must serialize invocations on the same counter.
*/
int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages)
{
for (;;) {
unsigned long old;
long usage;
/*
* Update the limit while making sure that it's not
* below the concurrently-changing counter value.
*
* The xchg implies two full memory barriers before
* and after, so the read-swap-read is ordered and
* ensures coherency with page_counter_try_charge():
* that function modifies the count before checking
* the limit, so if it sees the old limit, we see the
* modified counter and retry.
*/
usage = atomic_long_read(&counter->usage);
if (usage > nr_pages)
return -EBUSY;
old = xchg(&counter->max, nr_pages);
if (atomic_long_read(&counter->usage) <= usage)
return 0;
counter->max = old;
cond_resched();
}
}
/**
* page_counter_set_min - set the amount of protected memory
* @counter: counter
* @nr_pages: value to set
*
* The caller must serialize invocations on the same counter.
*/
void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
WRITE_ONCE(counter->min, nr_pages);
for (c = counter; c; c = c->parent)
propagate_protected_usage(c, atomic_long_read(&c->usage));
}
/**
* page_counter_set_low - set the amount of protected memory
* @counter: counter
* @nr_pages: value to set
*
* The caller must serialize invocations on the same counter.
*/
void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages)
{
struct page_counter *c;
WRITE_ONCE(counter->low, nr_pages);
for (c = counter; c; c = c->parent)
propagate_protected_usage(c, atomic_long_read(&c->usage));
}
/**
* page_counter_memparse - memparse() for page counter limits
* @buf: string to parse
* @max: string meaning maximum possible value
* @nr_pages: returns the result in number of pages
*
* Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be
* limited to %PAGE_COUNTER_MAX.
*/
int page_counter_memparse(const char *buf, const char *max,
unsigned long *nr_pages)
{
char *end;
u64 bytes;
if (!strcmp(buf, max)) {
*nr_pages = PAGE_COUNTER_MAX;
return 0;
}
bytes = memparse(buf, &end);
if (*end != '\0')
return -EINVAL;
*nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX);
return 0;
}