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
badblocks.c
/*
 * Bad block management
 *
 * - Heavily based on MD badblocks code from Neil Brown
 *
 * Copyright (c) 2015, Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */

#include <linux/badblocks.h>
#include <linux/seqlock.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/stddef.h>
#include <linux/types.h>
#include <linux/slab.h>

/**
 * badblocks_check() - check a given range for bad sectors
 * @bb:		the badblocks structure that holds all badblock information
 * @s:		sector (start) at which to check for badblocks
 * @sectors:	number of sectors to check for badblocks
 * @first_bad:	pointer to store location of the first badblock
 * @bad_sectors: pointer to store number of badblocks after @first_bad
 *
 * We can record which blocks on each device are 'bad' and so just
 * fail those blocks, or that stripe, rather than the whole device.
 * Entries in the bad-block table are 64bits wide.  This comprises:
 * Length of bad-range, in sectors: 0-511 for lengths 1-512
 * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes)
 *  A 'shift' can be set so that larger blocks are tracked and
 *  consequently larger devices can be covered.
 * 'Acknowledged' flag - 1 bit. - the most significant bit.
 *
 * Locking of the bad-block table uses a seqlock so badblocks_check
 * might need to retry if it is very unlucky.
 * We will sometimes want to check for bad blocks in a bi_end_io function,
 * so we use the write_seqlock_irq variant.
 *
 * When looking for a bad block we specify a range and want to
 * know if any block in the range is bad.  So we binary-search
 * to the last range that starts at-or-before the given endpoint,
 * (or "before the sector after the target range")
 * then see if it ends after the given start.
 *
 * Return:
 *  0: there are no known bad blocks in the range
 *  1: there are known bad block which are all acknowledged
 * -1: there are bad blocks which have not yet been acknowledged in metadata.
 * plus the start/length of the first bad section we overlap.
 */
int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
			sector_t *first_bad, int *bad_sectors)
{
	int hi;
	int lo;
	u64 *p = bb->page;
	int rv;
	sector_t target = s + sectors;
	unsigned seq;

	if (bb->shift > 0) {
		/* round the start down, and the end up */
		s >>= bb->shift;
		target += (1<<bb->shift) - 1;
		target >>= bb->shift;
		sectors = target - s;
	}
	/* 'target' is now the first block after the bad range */

retry:
	seq = read_seqbegin(&bb->lock);
	lo = 0;
	rv = 0;
	hi = bb->count;

	/* Binary search between lo and hi for 'target'
	 * i.e. for the last range that starts before 'target'
	 */
	/* INVARIANT: ranges before 'lo' and at-or-after 'hi'
	 * are known not to be the last range before target.
	 * VARIANT: hi-lo is the number of possible
	 * ranges, and decreases until it reaches 1
	 */
	while (hi - lo > 1) {
		int mid = (lo + hi) / 2;
		sector_t a = BB_OFFSET(p[mid]);

		if (a < target)
			/* This could still be the one, earlier ranges
			 * could not.
			 */
			lo = mid;
		else
			/* This and later ranges are definitely out. */
			hi = mid;
	}
	/* 'lo' might be the last that started before target, but 'hi' isn't */
	if (hi > lo) {
		/* need to check all range that end after 's' to see if
		 * any are unacknowledged.
		 */
		while (lo >= 0 &&
		       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
			if (BB_OFFSET(p[lo]) < target) {
				/* starts before the end, and finishes after
				 * the start, so they must overlap
				 */
				if (rv != -1 && BB_ACK(p[lo]))
					rv = 1;
				else
					rv = -1;
				*first_bad = BB_OFFSET(p[lo]);
				*bad_sectors = BB_LEN(p[lo]);
			}
			lo--;
		}
	}

	if (read_seqretry(&bb->lock, seq))
		goto retry;

	return rv;
}
EXPORT_SYMBOL_GPL(badblocks_check);

static void badblocks_update_acked(struct badblocks *bb)
{
	u64 *p = bb->page;
	int i;
	bool unacked = false;

	if (!bb->unacked_exist)
		return;

	for (i = 0; i < bb->count ; i++) {
		if (!BB_ACK(p[i])) {
			unacked = true;
			break;
		}
	}

	if (!unacked)
		bb->unacked_exist = 0;
}

/**
 * badblocks_set() - Add a range of bad blocks to the table.
 * @bb:		the badblocks structure that holds all badblock information
 * @s:		first sector to mark as bad
 * @sectors:	number of sectors to mark as bad
 * @acknowledged: weather to mark the bad sectors as acknowledged
 *
 * This might extend the table, or might contract it if two adjacent ranges
 * can be merged. We binary-search to find the 'insertion' point, then
 * decide how best to handle it.
 *
 * Return:
 *  0: success
 *  1: failed to set badblocks (out of space)
 */
int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
			int acknowledged)
{
	u64 *p;
	int lo, hi;
	int rv = 0;
	unsigned long flags;

	if (bb->shift < 0)
		/* badblocks are disabled */
		return 0;

	if (bb->shift) {
		/* round the start down, and the end up */
		sector_t next = s + sectors;

		s >>= bb->shift;
		next += (1<<bb->shift) - 1;
		next >>= bb->shift;
		sectors = next - s;
	}

	write_seqlock_irqsave(&bb->lock, flags);

	p = bb->page;
	lo = 0;
	hi = bb->count;
	/* Find the last range that starts at-or-before 's' */
	while (hi - lo > 1) {
		int mid = (lo + hi) / 2;
		sector_t a = BB_OFFSET(p[mid]);

		if (a <= s)
			lo = mid;
		else
			hi = mid;
	}
	if (hi > lo && BB_OFFSET(p[lo]) > s)
		hi = lo;

	if (hi > lo) {
		/* we found a range that might merge with the start
		 * of our new range
		 */
		sector_t a = BB_OFFSET(p[lo]);
		sector_t e = a + BB_LEN(p[lo]);
		int ack = BB_ACK(p[lo]);

		if (e >= s) {
			/* Yes, we can merge with a previous range */
			if (s == a && s + sectors >= e)
				/* new range covers old */
				ack = acknowledged;
			else
				ack = ack && acknowledged;

			if (e < s + sectors)
				e = s + sectors;
			if (e - a <= BB_MAX_LEN) {
				p[lo] = BB_MAKE(a, e-a, ack);
				s = e;
			} else {
				/* does not all fit in one range,
				 * make p[lo] maximal
				 */
				if (BB_LEN(p[lo]) != BB_MAX_LEN)
					p[lo] = BB_MAKE(a, BB_MAX_LEN, ack);
				s = a + BB_MAX_LEN;
			}
			sectors = e - s;
		}
	}
	if (sectors && hi < bb->count) {
		/* 'hi' points to the first range that starts after 's'.
		 * Maybe we can merge with the start of that range
		 */
		sector_t a = BB_OFFSET(p[hi]);
		sector_t e = a + BB_LEN(p[hi]);
		int ack = BB_ACK(p[hi]);

		if (a <= s + sectors) {
			/* merging is possible */
			if (e <= s + sectors) {
				/* full overlap */
				e = s + sectors;
				ack = acknowledged;
			} else
				ack = ack && acknowledged;

			a = s;
			if (e - a <= BB_MAX_LEN) {
				p[hi] = BB_MAKE(a, e-a, ack);
				s = e;
			} else {
				p[hi] = BB_MAKE(a, BB_MAX_LEN, ack);
				s = a + BB_MAX_LEN;
			}
			sectors = e - s;
			lo = hi;
			hi++;
		}
	}
	if (sectors == 0 && hi < bb->count) {
		/* we might be able to combine lo and hi */
		/* Note: 's' is at the end of 'lo' */
		sector_t a = BB_OFFSET(p[hi]);
		int lolen = BB_LEN(p[lo]);
		int hilen = BB_LEN(p[hi]);
		int newlen = lolen + hilen - (s - a);

		if (s >= a && newlen < BB_MAX_LEN) {
			/* yes, we can combine them */
			int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]);

			p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack);
			memmove(p + hi, p + hi + 1,
				(bb->count - hi - 1) * 8);
			bb->count--;
		}
	}
	while (sectors) {
		/* didn't merge (it all).
		 * Need to add a range just before 'hi'
		 */
		if (bb->count >= MAX_BADBLOCKS) {
			/* No room for more */
			rv = 1;
			break;
		} else {
			int this_sectors = sectors;

			memmove(p + hi + 1, p + hi,
				(bb->count - hi) * 8);
			bb->count++;

			if (this_sectors > BB_MAX_LEN)
				this_sectors = BB_MAX_LEN;
			p[hi] = BB_MAKE(s, this_sectors, acknowledged);
			sectors -= this_sectors;
			s += this_sectors;
		}
	}

	bb->changed = 1;
	if (!acknowledged)
		bb->unacked_exist = 1;
	else
		badblocks_update_acked(bb);
	write_sequnlock_irqrestore(&bb->lock, flags);

	return rv;
}
EXPORT_SYMBOL_GPL(badblocks_set);

/**
 * badblocks_clear() - Remove a range of bad blocks to the table.
 * @bb:		the badblocks structure that holds all badblock information
 * @s:		first sector to mark as bad
 * @sectors:	number of sectors to mark as bad
 *
 * This may involve extending the table if we spilt a region,
 * but it must not fail.  So if the table becomes full, we just
 * drop the remove request.
 *
 * Return:
 *  0: success
 *  1: failed to clear badblocks
 */
int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
{
	u64 *p;
	int lo, hi;
	sector_t target = s + sectors;
	int rv = 0;

	if (bb->shift > 0) {
		/* When clearing we round the start up and the end down.
		 * This should not matter as the shift should align with
		 * the block size and no rounding should ever be needed.
		 * However it is better the think a block is bad when it
		 * isn't than to think a block is not bad when it is.
		 */
		s += (1<<bb->shift) - 1;
		s >>= bb->shift;
		target >>= bb->shift;
		sectors = target - s;
	}

	write_seqlock_irq(&bb->lock);

	p = bb->page;
	lo = 0;
	hi = bb->count;
	/* Find the last range that starts before 'target' */
	while (hi - lo > 1) {
		int mid = (lo + hi) / 2;
		sector_t a = BB_OFFSET(p[mid]);

		if (a < target)
			lo = mid;
		else
			hi = mid;
	}
	if (hi > lo) {
		/* p[lo] is the last range that could overlap the
		 * current range.  Earlier ranges could also overlap,
		 * but only this one can overlap the end of the range.
		 */
		if ((BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) &&
		    (BB_OFFSET(p[lo]) < target)) {
			/* Partial overlap, leave the tail of this range */
			int ack = BB_ACK(p[lo]);
			sector_t a = BB_OFFSET(p[lo]);
			sector_t end = a + BB_LEN(p[lo]);

			if (a < s) {
				/* we need to split this range */
				if (bb->count >= MAX_BADBLOCKS) {
					rv = -ENOSPC;
					goto out;
				}
				memmove(p+lo+1, p+lo, (bb->count - lo) * 8);
				bb->count++;
				p[lo] = BB_MAKE(a, s-a, ack);
				lo++;
			}
			p[lo] = BB_MAKE(target, end - target, ack);
			/* there is no longer an overlap */
			hi = lo;
			lo--;
		}
		while (lo >= 0 &&
		       (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) &&
		       (BB_OFFSET(p[lo]) < target)) {
			/* This range does overlap */
			if (BB_OFFSET(p[lo]) < s) {
				/* Keep the early parts of this range. */
				int ack = BB_ACK(p[lo]);
				sector_t start = BB_OFFSET(p[lo]);

				p[lo] = BB_MAKE(start, s - start, ack);
				/* now low doesn't overlap, so.. */
				break;
			}
			lo--;
		}
		/* 'lo' is strictly before, 'hi' is strictly after,
		 * anything between needs to be discarded
		 */
		if (hi - lo > 1) {
			memmove(p+lo+1, p+hi, (bb->count - hi) * 8);
			bb->count -= (hi - lo - 1);
		}
	}

	badblocks_update_acked(bb);
	bb->changed = 1;
out:
	write_sequnlock_irq(&bb->lock);
	return rv;
}
EXPORT_SYMBOL_GPL(badblocks_clear);

/**
 * ack_all_badblocks() - Acknowledge all bad blocks in a list.
 * @bb:		the badblocks structure that holds all badblock information
 *
 * This only succeeds if ->changed is clear.  It is used by
 * in-kernel metadata updates
 */
void ack_all_badblocks(struct badblocks *bb)
{
	if (bb->page == NULL || bb->changed)
		/* no point even trying */
		return;
	write_seqlock_irq(&bb->lock);

	if (bb->changed == 0 && bb->unacked_exist) {
		u64 *p = bb->page;
		int i;

		for (i = 0; i < bb->count ; i++) {
			if (!BB_ACK(p[i])) {
				sector_t start = BB_OFFSET(p[i]);
				int len = BB_LEN(p[i]);

				p[i] = BB_MAKE(start, len, 1);
			}
		}
		bb->unacked_exist = 0;
	}
	write_sequnlock_irq(&bb->lock);
}
EXPORT_SYMBOL_GPL(ack_all_badblocks);

/**
 * badblocks_show() - sysfs access to bad-blocks list
 * @bb:		the badblocks structure that holds all badblock information
 * @page:	buffer received from sysfs
 * @unack:	weather to show unacknowledged badblocks
 *
 * Return:
 *  Length of returned data
 */
ssize_t badblocks_show(struct badblocks *bb, char *page, int unack)
{
	size_t len;
	int i;
	u64 *p = bb->page;
	unsigned seq;

	if (bb->shift < 0)
		return 0;

retry:
	seq = read_seqbegin(&bb->lock);

	len = 0;
	i = 0;

	while (len < PAGE_SIZE && i < bb->count) {
		sector_t s = BB_OFFSET(p[i]);
		unsigned int length = BB_LEN(p[i]);
		int ack = BB_ACK(p[i]);

		i++;

		if (unack && ack)
			continue;

		len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n",
				(unsigned long long)s << bb->shift,
				length << bb->shift);
	}
	if (unack && len == 0)
		bb->unacked_exist = 0;

	if (read_seqretry(&bb->lock, seq))
		goto retry;

	return len;
}
EXPORT_SYMBOL_GPL(badblocks_show);

/**
 * badblocks_store() - sysfs access to bad-blocks list
 * @bb:		the badblocks structure that holds all badblock information
 * @page:	buffer received from sysfs
 * @len:	length of data received from sysfs
 * @unack:	weather to show unacknowledged badblocks
 *
 * Return:
 *  Length of the buffer processed or -ve error.
 */
ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
			int unack)
{
	unsigned long long sector;
	int length;
	char newline;

	switch (sscanf(page, "%llu %d%c", &sector, &length, &newline)) {
	case 3:
		if (newline != '\n')
			return -EINVAL;
		/* fall through */
	case 2:
		if (length <= 0)
			return -EINVAL;
		break;
	default:
		return -EINVAL;
	}

	if (badblocks_set(bb, sector, length, !unack))
		return -ENOSPC;
	else
		return len;
}
EXPORT_SYMBOL_GPL(badblocks_store);

static int __badblocks_init(struct device *dev, struct badblocks *bb,
		int enable)
{
	bb->dev = dev;
	bb->count = 0;
	if (enable)
		bb->shift = 0;
	else
		bb->shift = -1;
	if (dev)
		bb->page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL);
	else
		bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL);
	if (!bb->page) {
		bb->shift = -1;
		return -ENOMEM;
	}
	seqlock_init(&bb->lock);

	return 0;
}

/**
 * badblocks_init() - initialize the badblocks structure
 * @bb:		the badblocks structure that holds all badblock information
 * @enable:	weather to enable badblocks accounting
 *
 * Return:
 *  0: success
 *  -ve errno: on error
 */
int badblocks_init(struct badblocks *bb, int enable)
{
	return __badblocks_init(NULL, bb, enable);
}
EXPORT_SYMBOL_GPL(badblocks_init);

int devm_init_badblocks(struct device *dev, struct badblocks *bb)
{
	if (!bb)
		return -EINVAL;
	return __badblocks_init(dev, bb, 1);
}
EXPORT_SYMBOL_GPL(devm_init_badblocks);

/**
 * badblocks_exit() - free the badblocks structure
 * @bb:		the badblocks structure that holds all badblock information
 */
void badblocks_exit(struct badblocks *bb)
{
	if (!bb)
		return;
	if (bb->dev)
		devm_kfree(bb->dev, bb->page);
	else
		kfree(bb->page);
	bb->page = NULL;
}
EXPORT_SYMBOL_GPL(badblocks_exit);
back to top