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-wbt.h
#ifndef WB_THROTTLE_H
#define WB_THROTTLE_H

#include <linux/kernel.h>
#include <linux/atomic.h>
#include <linux/wait.h>
#include <linux/timer.h>
#include <linux/ktime.h>

#include "blk-stat.h"

enum wbt_flags {
	WBT_TRACKED		= 1,	/* write, tracked for throttling */
	WBT_READ		= 2,	/* read */
	WBT_KSWAPD		= 4,	/* write, from kswapd */

	WBT_NR_BITS		= 3,	/* number of bits */
};

enum {
	WBT_NUM_RWQ		= 2,
};

/*
 * Enable states. Either off, or on by default (done at init time),
 * or on through manual setup in sysfs.
 */
enum {
	WBT_STATE_ON_DEFAULT	= 1,
	WBT_STATE_ON_MANUAL	= 2,
};

static inline void wbt_clear_state(struct blk_issue_stat *stat)
{
	stat->stat &= ~BLK_STAT_RES_MASK;
}

static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
{
	return (stat->stat & BLK_STAT_RES_MASK) >> BLK_STAT_RES_SHIFT;
}

static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
{
	stat->stat |= ((u64) wb_acct) << BLK_STAT_RES_SHIFT;
}

static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
{
	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_TRACKED;
}

static inline bool wbt_is_read(struct blk_issue_stat *stat)
{
	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_READ;
}

struct rq_wait {
	wait_queue_head_t wait;
	atomic_t inflight;
};

struct rq_wb {
	/*
	 * Settings that govern how we throttle
	 */
	unsigned int wb_background;		/* background writeback */
	unsigned int wb_normal;			/* normal writeback */
	unsigned int wb_max;			/* max throughput writeback */
	int scale_step;
	bool scaled_max;

	short enable_state;			/* WBT_STATE_* */

	/*
	 * Number of consecutive periods where we don't have enough
	 * information to make a firm scale up/down decision.
	 */
	unsigned int unknown_cnt;

	u64 win_nsec;				/* default window size */
	u64 cur_win_nsec;			/* current window size */

	struct blk_stat_callback *cb;

	s64 sync_issue;
	void *sync_cookie;

	unsigned int wc;
	unsigned int queue_depth;

	unsigned long last_issue;		/* last non-throttled issue */
	unsigned long last_comp;		/* last non-throttled comp */
	unsigned long min_lat_nsec;
	struct request_queue *queue;
	struct rq_wait rq_wait[WBT_NUM_RWQ];
};

static inline unsigned int wbt_inflight(struct rq_wb *rwb)
{
	unsigned int i, ret = 0;

	for (i = 0; i < WBT_NUM_RWQ; i++)
		ret += atomic_read(&rwb->rq_wait[i].inflight);

	return ret;
}

#ifdef CONFIG_BLK_WBT

void __wbt_done(struct rq_wb *, enum wbt_flags);
void wbt_done(struct rq_wb *, struct blk_issue_stat *);
enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
int wbt_init(struct request_queue *);
void wbt_exit(struct request_queue *);
void wbt_update_limits(struct rq_wb *);
void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
void wbt_disable_default(struct request_queue *);
void wbt_enable_default(struct request_queue *);

void wbt_set_queue_depth(struct rq_wb *, unsigned int);
void wbt_set_write_cache(struct rq_wb *, bool);

u64 wbt_default_latency_nsec(struct request_queue *);

#else

static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
{
}
static inline void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat)
{
}
static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
				      spinlock_t *lock)
{
	return 0;
}
static inline int wbt_init(struct request_queue *q)
{
	return -EINVAL;
}
static inline void wbt_exit(struct request_queue *q)
{
}
static inline void wbt_update_limits(struct rq_wb *rwb)
{
}
static inline void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat)
{
}
static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
{
}
static inline void wbt_disable_default(struct request_queue *q)
{
}
static inline void wbt_enable_default(struct request_queue *q)
{
}
static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
{
}
static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
{
}
static inline u64 wbt_default_latency_nsec(struct request_queue *q)
{
	return 0;
}

#endif /* CONFIG_BLK_WBT */

#endif
back to top