mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 17:30:02 +00:00
![Johannes Weiner](/assets/img/avatar_default.png)
When the unsigned page_counter underflows, even just by a few pages, a cgroup will not be able to run anything afterwards and trigger the OOM killer in a loop. Underflows shouldn't happen, but when they do in practice, we may just be off by a small amount that doesn't interfere with the normal operation - consequences don't need to be that dire. Reset the page_counter to 0 upon underflow. We'll issue a warning that the accounting will be off and then try to keep limping along. [ We used to do this with the original res_counter, where it was a more straight-forward correction inside the spinlock section. I didn't carry it forward into the lockless page counters for simplicity, but it turns out this is quite useful in practice. ] Link: https://lkml.kernel.org/r/20210408143155.2679744-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Chris Down <chris@chrisdown.name> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
266 lines
6.8 KiB
C
266 lines
6.8 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);
|
|
/* More uncharges than charges? */
|
|
if (WARN_ONCE(new < 0, "page_counter underflow: %ld nr_pages=%lu\n",
|
|
new, nr_pages)) {
|
|
new = 0;
|
|
atomic_long_set(&counter->usage, new);
|
|
}
|
|
propagate_protected_usage(counter, new);
|
|
}
|
|
|
|
/**
|
|
* 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 > READ_ONCE(c->watermark))
|
|
WRITE_ONCE(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_set_max(),
|
|
* 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 which is only used
|
|
* to report stats.
|
|
*/
|
|
data_race(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 > READ_ONCE(c->watermark))
|
|
WRITE_ONCE(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 = page_counter_read(counter);
|
|
|
|
if (usage > nr_pages)
|
|
return -EBUSY;
|
|
|
|
old = xchg(&counter->max, nr_pages);
|
|
|
|
if (page_counter_read(counter) <= 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;
|
|
}
|