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)
page_counter_try_charge() currently returns 0 on success and -ENOMEM on failure, which is surprising behavior given the function name. Make it follow the expected pattern of try_stuff() functions that return a boolean true to indicate success, or false for failure. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Vladimir Davydov <vdavydov@virtuozzo.com Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
193 lines
4.8 KiB
C
193 lines
4.8 KiB
C
/*
|
|
* 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>
|
|
|
|
/**
|
|
* 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->count);
|
|
/* 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->count);
|
|
/*
|
|
* 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->count);
|
|
if (new > c->limit) {
|
|
atomic_long_sub(nr_pages, &c->count);
|
|
/*
|
|
* This is racy, but we can live with some
|
|
* inaccuracy in the failcnt.
|
|
*/
|
|
c->failcnt++;
|
|
*fail = c;
|
|
goto failed;
|
|
}
|
|
/*
|
|
* 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_limit - limit the number of pages allowed
|
|
* @counter: counter
|
|
* @limit: 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_limit(struct page_counter *counter, unsigned long limit)
|
|
{
|
|
for (;;) {
|
|
unsigned long old;
|
|
long count;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
count = atomic_long_read(&counter->count);
|
|
|
|
if (count > limit)
|
|
return -EBUSY;
|
|
|
|
old = xchg(&counter->limit, limit);
|
|
|
|
if (atomic_long_read(&counter->count) <= count)
|
|
return 0;
|
|
|
|
counter->limit = old;
|
|
cond_resched();
|
|
}
|
|
}
|
|
|
|
/**
|
|
* 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;
|
|
}
|