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
blk-exec.c
/*
 * Functions related to setting various queue properties from drivers
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/sched/sysctl.h>

#include "blk.h"

/*
 * for max sense size
 */
#include <scsi/scsi_cmnd.h>

/**
 * blk_end_sync_rq - executes a completion event on a request
 * @rq: request to complete
 * @error: end I/O status of the request
 */
static void blk_end_sync_rq(struct request *rq, int error)
{
	struct completion *waiting = rq->end_io_data;

	rq->end_io_data = NULL;

	/*
	 * complete last, if this is a stack request the process (and thus
	 * the rq pointer) could be invalid right after this complete()
	 */
	complete(waiting);
}

/**
 * blk_execute_rq_nowait - insert a request into queue for execution
 * @q:		queue to insert the request in
 * @bd_disk:	matching gendisk
 * @rq:		request to insert
 * @at_head:    insert request at head or tail of queue
 * @done:	I/O completion handler
 *
 * Description:
 *    Insert a fully prepared request at the back of the I/O scheduler queue
 *    for execution.  Don't wait for completion.
 *
 * Note:
 *    This function will invoke @done directly if the queue is dead.
 */
void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
			   struct request *rq, int at_head,
			   rq_end_io_fn *done)
{
	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;

	WARN_ON(irqs_disabled());
	WARN_ON(rq->cmd_type == REQ_TYPE_FS);

	rq->rq_disk = bd_disk;
	rq->end_io = done;

	/*
	 * don't check dying flag for MQ because the request won't
	 * be resued after dying flag is set
	 */
	if (q->mq_ops) {
		blk_mq_insert_request(rq, at_head, true, false);
		return;
	}

	spin_lock_irq(q->queue_lock);

	if (unlikely(blk_queue_dying(q))) {
		rq->cmd_flags |= REQ_QUIET; 
		rq->errors = -ENXIO;
		__blk_end_request_all(rq, rq->errors);
		spin_unlock_irq(q->queue_lock);
		return;
	}

	__elv_add_request(q, rq, where);
	__blk_run_queue(q);
	spin_unlock_irq(q->queue_lock);
}
EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);

/**
 * blk_execute_rq - insert a request into queue for execution
 * @q:		queue to insert the request in
 * @bd_disk:	matching gendisk
 * @rq:		request to insert
 * @at_head:    insert request at head or tail of queue
 *
 * Description:
 *    Insert a fully prepared request at the back of the I/O scheduler queue
 *    for execution and wait for completion.
 */
int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
		   struct request *rq, int at_head)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	char sense[SCSI_SENSE_BUFFERSIZE];
	int err = 0;
	unsigned long hang_check;

	if (!rq->sense) {
		memset(sense, 0, sizeof(sense));
		rq->sense = sense;
		rq->sense_len = 0;
	}

	rq->end_io_data = &wait;
	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);

	/* Prevent hang_check timer from firing at us during very long I/O */
	hang_check = sysctl_hung_task_timeout_secs;
	if (hang_check)
		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
	else
		wait_for_completion_io(&wait);

	if (rq->errors)
		err = -EIO;

	if (rq->sense == sense)	{
		rq->sense = NULL;
		rq->sense_len = 0;
	}

	return err;
}
EXPORT_SYMBOL(blk_execute_rq);
back to top