Revision 73223e4e2e3867ebf033a5a8eb2e5df0158ccc99 authored by zhong jiang on 18 August 2017, 22:16:24 UTC, committed by Linus Torvalds on 18 August 2017, 22:32:02 UTC
I hit a use after free issue when executing trinity and repoduced it
with KASAN enabled.  The related call trace is as follows.

  BUG: KASan: use after free in SyS_get_mempolicy+0x3c8/0x960 at addr ffff8801f582d766
  Read of size 2 by task syz-executor1/798

  INFO: Allocated in mpol_new.part.2+0x74/0x160 age=3 cpu=1 pid=799
     __slab_alloc+0x768/0x970
     kmem_cache_alloc+0x2e7/0x450
     mpol_new.part.2+0x74/0x160
     mpol_new+0x66/0x80
     SyS_mbind+0x267/0x9f0
     system_call_fastpath+0x16/0x1b
  INFO: Freed in __mpol_put+0x2b/0x40 age=4 cpu=1 pid=799
     __slab_free+0x495/0x8e0
     kmem_cache_free+0x2f3/0x4c0
     __mpol_put+0x2b/0x40
     SyS_mbind+0x383/0x9f0
     system_call_fastpath+0x16/0x1b
  INFO: Slab 0xffffea0009cb8dc0 objects=23 used=8 fp=0xffff8801f582de40 flags=0x200000000004080
  INFO: Object 0xffff8801f582d760 @offset=5984 fp=0xffff8801f582d600

  Bytes b4 ffff8801f582d750: ae 01 ff ff 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a  ........ZZZZZZZZ
  Object ffff8801f582d760: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b  kkkkkkkkkkkkkkkk
  Object ffff8801f582d770: 6b 6b 6b 6b 6b 6b 6b a5                          kkkkkkk.
  Redzone ffff8801f582d778: bb bb bb bb bb bb bb bb                          ........
  Padding ffff8801f582d8b8: 5a 5a 5a 5a 5a 5a 5a 5a                          ZZZZZZZZ
  Memory state around the buggy address:
  ffff8801f582d600: fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc fc
  ffff8801f582d680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  >ffff8801f582d700: fc fc fc fc fc fc fc fc fc fc fc fc fb fb fb fc

!shared memory policy is not protected against parallel removal by other
thread which is normally protected by the mmap_sem.  do_get_mempolicy,
however, drops the lock midway while we can still access it later.

Early premature up_read is a historical artifact from times when
put_user was called in this path see https://lwn.net/Articles/124754/
but that is gone since 8bccd85ffbaf ("[PATCH] Implement sys_* do_*
layering in the memory policy layer.").  but when we have the the
current mempolicy ref count model.  The issue was introduced
accordingly.

Fix the issue by removing the premature release.

Link: http://lkml.kernel.org/r/1502950924-27521-1-git-send-email-zhongjiang@huawei.com
Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: <stable@vger.kernel.org>	[2.6+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent da094e4
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"
#include "blk-mq-sched.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, blk_status_t 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(!blk_rq_is_passthrough(rq));

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

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

	spin_lock_irq(q->queue_lock);

	if (unlikely(blk_queue_dying(q))) {
		rq->rq_flags |= RQF_QUIET;
		__blk_end_request_all(rq, BLK_STS_IOERR);
		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.
 */
void blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
		   struct request *rq, int at_head)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	unsigned long hang_check;

	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);
}
EXPORT_SYMBOL(blk_execute_rq);
back to top