Revision 03049269de433cb5fe2859be9ae4469ceb1163ed authored by Michal Hocko on 25 March 2016, 21:20:33 UTC, committed by Linus Torvalds on 25 March 2016, 23:37:42 UTC
wake_oom_reaper has allowed only 1 oom victim to be queued.  The main
reason for that was the simplicity as other solutions would require some
way of queuing.  The current approach is racy and that was deemed
sufficient as the oom_reaper is considered a best effort approach to
help with oom handling when the OOM victim cannot terminate in a
reasonable time.  The race could lead to missing an oom victim which can
get stuck

out_of_memory
  wake_oom_reaper
    cmpxchg // OK
    			oom_reaper
			  oom_reap_task
			    __oom_reap_task
oom_victim terminates
			      atomic_inc_not_zero // fail
out_of_memory
  wake_oom_reaper
    cmpxchg // fails
			  task_to_reap = NULL

This race requires 2 OOM invocations in a short time period which is not
very likely but certainly not impossible.  E.g.  the original victim
might have not released a lot of memory for some reason.

The situation would improve considerably if wake_oom_reaper used a more
robust queuing.  This is what this patch implements.  This means adding
oom_reaper_list list_head into task_struct (eat a hole before embeded
thread_struct for that purpose) and a oom_reaper_lock spinlock for
queuing synchronization.  wake_oom_reaper will then add the task on the
queue and oom_reaper will dequeue it.

Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Andrea Argangeli <andrea@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent bc448e8
Raw File
find_bit.c
/* bit search implementation
 *
 * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * Copyright (C) 2008 IBM Corporation
 * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au>
 * (Inspired by David Howell's find_next_bit implementation)
 *
 * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
 * size and improve performance, 2015.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/bitops.h>
#include <linux/bitmap.h>
#include <linux/export.h>
#include <linux/kernel.h>

#if !defined(find_next_bit) || !defined(find_next_zero_bit)

/*
 * This is a common helper function for find_next_bit and
 * find_next_zero_bit.  The difference is the "invert" argument, which
 * is XORed with each fetched word before searching it for one bits.
 */
static unsigned long _find_next_bit(const unsigned long *addr,
		unsigned long nbits, unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (!nbits || start >= nbits)
		return nbits;

	tmp = addr[start / BITS_PER_LONG] ^ invert;

	/* Handle 1st word. */
	tmp &= BITMAP_FIRST_WORD_MASK(start);
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr[start / BITS_PER_LONG] ^ invert;
	}

	return min(start + __ffs(tmp), nbits);
}
#endif

#ifndef find_next_bit
/*
 * Find the next set bit in a memory region.
 */
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
			    unsigned long offset)
{
	return _find_next_bit(addr, size, offset, 0UL);
}
EXPORT_SYMBOL(find_next_bit);
#endif

#ifndef find_next_zero_bit
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
				 unsigned long offset)
{
	return _find_next_bit(addr, size, offset, ~0UL);
}
EXPORT_SYMBOL(find_next_zero_bit);
#endif

#ifndef find_first_bit
/*
 * Find the first set bit in a memory region.
 */
unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
{
	unsigned long idx;

	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
		if (addr[idx])
			return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
	}

	return size;
}
EXPORT_SYMBOL(find_first_bit);
#endif

#ifndef find_first_zero_bit
/*
 * Find the first cleared bit in a memory region.
 */
unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
{
	unsigned long idx;

	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
		if (addr[idx] != ~0UL)
			return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
	}

	return size;
}
EXPORT_SYMBOL(find_first_zero_bit);
#endif

#ifndef find_last_bit
unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
{
	if (size) {
		unsigned long val = BITMAP_LAST_WORD_MASK(size);
		unsigned long idx = (size-1) / BITS_PER_LONG;

		do {
			val &= addr[idx];
			if (val)
				return idx * BITS_PER_LONG + __fls(val);

			val = ~0ul;
		} while (idx--);
	}
	return size;
}
EXPORT_SYMBOL(find_last_bit);
#endif

#ifdef __BIG_ENDIAN

/* include/linux/byteorder does not support "unsigned long" type */
static inline unsigned long ext2_swab(const unsigned long y)
{
#if BITS_PER_LONG == 64
	return (unsigned long) __swab64((u64) y);
#elif BITS_PER_LONG == 32
	return (unsigned long) __swab32((u32) y);
#else
#error BITS_PER_LONG not defined
#endif
}

#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
static unsigned long _find_next_bit_le(const unsigned long *addr,
		unsigned long nbits, unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (!nbits || start >= nbits)
		return nbits;

	tmp = addr[start / BITS_PER_LONG] ^ invert;

	/* Handle 1st word. */
	tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr[start / BITS_PER_LONG] ^ invert;
	}

	return min(start + __ffs(ext2_swab(tmp)), nbits);
}
#endif

#ifndef find_next_zero_bit_le
unsigned long find_next_zero_bit_le(const void *addr, unsigned
		long size, unsigned long offset)
{
	return _find_next_bit_le(addr, size, offset, ~0UL);
}
EXPORT_SYMBOL(find_next_zero_bit_le);
#endif

#ifndef find_next_bit_le
unsigned long find_next_bit_le(const void *addr, unsigned
		long size, unsigned long offset)
{
	return _find_next_bit_le(addr, size, offset, 0UL);
}
EXPORT_SYMBOL(find_next_bit_le);
#endif

#endif /* __BIG_ENDIAN */
back to top