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
xor.c
/*
 * xor.c : Multiple Devices driver for Linux
 *
 * Copyright (C) 1996, 1997, 1998, 1999, 2000,
 * Ingo Molnar, Matti Aarnio, Jakub Jelinek, Richard Henderson.
 *
 * Dispatch optimized RAID-5 checksumming functions.
 *
 * 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, or (at your option)
 * any later version.
 *
 * You should have received a copy of the GNU General Public License
 * (for example /usr/src/linux/COPYING); if not, write to the Free
 * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

#define BH_TRACE 0
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/raid/xor.h>
#include <linux/jiffies.h>
#include <linux/preempt.h>
#include <asm/xor.h>

/* The xor routines to use.  */
static struct xor_block_template *active_template;

void
xor_blocks(unsigned int src_count, unsigned int bytes, void *dest, void **srcs)
{
	unsigned long *p1, *p2, *p3, *p4;

	p1 = (unsigned long *) srcs[0];
	if (src_count == 1) {
		active_template->do_2(bytes, dest, p1);
		return;
	}

	p2 = (unsigned long *) srcs[1];
	if (src_count == 2) {
		active_template->do_3(bytes, dest, p1, p2);
		return;
	}

	p3 = (unsigned long *) srcs[2];
	if (src_count == 3) {
		active_template->do_4(bytes, dest, p1, p2, p3);
		return;
	}

	p4 = (unsigned long *) srcs[3];
	active_template->do_5(bytes, dest, p1, p2, p3, p4);
}
EXPORT_SYMBOL(xor_blocks);

/* Set of all registered templates.  */
static struct xor_block_template *__initdata template_list;

#define BENCH_SIZE (PAGE_SIZE)

static void __init
do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
{
	int speed;
	unsigned long now, j;
	int i, count, max;

	tmpl->next = template_list;
	template_list = tmpl;

	preempt_disable();

	/*
	 * Count the number of XORs done during a whole jiffy, and use
	 * this to calculate the speed of checksumming.  We use a 2-page
	 * allocation to have guaranteed color L1-cache layout.
	 */
	max = 0;
	for (i = 0; i < 5; i++) {
		j = jiffies;
		count = 0;
		while ((now = jiffies) == j)
			cpu_relax();
		while (time_before(jiffies, now + 1)) {
			mb(); /* prevent loop optimzation */
			tmpl->do_2(BENCH_SIZE, b1, b2);
			mb();
			count++;
			mb();
		}
		if (count > max)
			max = count;
	}

	preempt_enable();

	speed = max * (HZ * BENCH_SIZE / 1024);
	tmpl->speed = speed;

	printk(KERN_INFO "   %-10s: %5d.%03d MB/sec\n", tmpl->name,
	       speed / 1000, speed % 1000);
}

static int __init
calibrate_xor_blocks(void)
{
	void *b1, *b2;
	struct xor_block_template *f, *fastest;

	/*
	 * Note: Since the memory is not actually used for _anything_ but to
	 * test the XOR speed, we don't really want kmemcheck to warn about
	 * reading uninitialized bytes here.
	 */
	b1 = (void *) __get_free_pages(GFP_KERNEL | __GFP_NOTRACK, 2);
	if (!b1) {
		printk(KERN_WARNING "xor: Yikes!  No memory available.\n");
		return -ENOMEM;
	}
	b2 = b1 + 2*PAGE_SIZE + BENCH_SIZE;

	/*
	 * If this arch/cpu has a short-circuited selection, don't loop through
	 * all the possible functions, just test the best one
	 */

	fastest = NULL;

#ifdef XOR_SELECT_TEMPLATE
		fastest = XOR_SELECT_TEMPLATE(fastest);
#endif

#define xor_speed(templ)	do_xor_speed((templ), b1, b2)

	if (fastest) {
		printk(KERN_INFO "xor: automatically using best "
				 "checksumming function:\n");
		xor_speed(fastest);
		goto out;
	} else {
		printk(KERN_INFO "xor: measuring software checksum speed\n");
		XOR_TRY_TEMPLATES;
		fastest = template_list;
		for (f = fastest; f; f = f->next)
			if (f->speed > fastest->speed)
				fastest = f;
	}

	printk(KERN_INFO "xor: using function: %s (%d.%03d MB/sec)\n",
	       fastest->name, fastest->speed / 1000, fastest->speed % 1000);

#undef xor_speed

 out:
	free_pages((unsigned long)b1, 2);

	active_template = fastest;
	return 0;
}

static __exit void xor_exit(void) { }

MODULE_LICENSE("GPL");

/* when built-in xor.o must initialize before drivers/md/md.o */
core_initcall(calibrate_xor_blocks);
module_exit(xor_exit);
back to top