Revision 03cdadb04077b9311bbc67d98cc5401aff76482d authored by Dan Williams on 26 February 2016, 23:19:43 UTC, committed by Linus Torvalds on 27 February 2016, 18:28:52 UTC
The recent *sync enabling discovered that we are inserting into the
block_device pagecache counter to the expectations of the dirty data
tracking for dax mappings.  This can lead to data corruption.

We want to support DAX for block devices eventually, but it requires
wider changes to properly manage the pagecache.

   dump_stack+0x85/0xc2
   dax_writeback_mapping_range+0x60/0xe0
   blkdev_writepages+0x3f/0x50
   do_writepages+0x21/0x30
   __filemap_fdatawrite_range+0xc6/0x100
   filemap_write_and_wait+0x4a/0xa0
   set_blocksize+0x70/0xd0
   sb_set_blocksize+0x1d/0x50
   ext4_fill_super+0x75b/0x3360
   mount_bdev+0x180/0x1b0
   ext4_mount+0x15/0x20
   mount_fs+0x38/0x170

Mark the support broken so its disabled by default, but otherwise still
available for testing.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Reported-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@fb.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent a4a8481
Raw File
find_bit.c
/* bit search implementation
 *
 * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * Copyright (C) 2008 IBM Corporation
 * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au>
 * (Inspired by David Howell's find_next_bit implementation)
 *
 * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease
 * size and improve performance, 2015.
 *
 * 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 of the License, or (at your option) any later version.
 */

#include <linux/bitops.h>
#include <linux/bitmap.h>
#include <linux/export.h>
#include <linux/kernel.h>

#if !defined(find_next_bit) || !defined(find_next_zero_bit)

/*
 * This is a common helper function for find_next_bit and
 * find_next_zero_bit.  The difference is the "invert" argument, which
 * is XORed with each fetched word before searching it for one bits.
 */
static unsigned long _find_next_bit(const unsigned long *addr,
		unsigned long nbits, unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (!nbits || start >= nbits)
		return nbits;

	tmp = addr[start / BITS_PER_LONG] ^ invert;

	/* Handle 1st word. */
	tmp &= BITMAP_FIRST_WORD_MASK(start);
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr[start / BITS_PER_LONG] ^ invert;
	}

	return min(start + __ffs(tmp), nbits);
}
#endif

#ifndef find_next_bit
/*
 * Find the next set bit in a memory region.
 */
unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
			    unsigned long offset)
{
	return _find_next_bit(addr, size, offset, 0UL);
}
EXPORT_SYMBOL(find_next_bit);
#endif

#ifndef find_next_zero_bit
unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
				 unsigned long offset)
{
	return _find_next_bit(addr, size, offset, ~0UL);
}
EXPORT_SYMBOL(find_next_zero_bit);
#endif

#ifndef find_first_bit
/*
 * Find the first set bit in a memory region.
 */
unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
{
	unsigned long idx;

	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
		if (addr[idx])
			return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size);
	}

	return size;
}
EXPORT_SYMBOL(find_first_bit);
#endif

#ifndef find_first_zero_bit
/*
 * Find the first cleared bit in a memory region.
 */
unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
{
	unsigned long idx;

	for (idx = 0; idx * BITS_PER_LONG < size; idx++) {
		if (addr[idx] != ~0UL)
			return min(idx * BITS_PER_LONG + ffz(addr[idx]), size);
	}

	return size;
}
EXPORT_SYMBOL(find_first_zero_bit);
#endif

#ifndef find_last_bit
unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
{
	if (size) {
		unsigned long val = BITMAP_LAST_WORD_MASK(size);
		unsigned long idx = (size-1) / BITS_PER_LONG;

		do {
			val &= addr[idx];
			if (val)
				return idx * BITS_PER_LONG + __fls(val);

			val = ~0ul;
		} while (idx--);
	}
	return size;
}
EXPORT_SYMBOL(find_last_bit);
#endif

#ifdef __BIG_ENDIAN

/* include/linux/byteorder does not support "unsigned long" type */
static inline unsigned long ext2_swab(const unsigned long y)
{
#if BITS_PER_LONG == 64
	return (unsigned long) __swab64((u64) y);
#elif BITS_PER_LONG == 32
	return (unsigned long) __swab32((u32) y);
#else
#error BITS_PER_LONG not defined
#endif
}

#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
static unsigned long _find_next_bit_le(const unsigned long *addr,
		unsigned long nbits, unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (!nbits || start >= nbits)
		return nbits;

	tmp = addr[start / BITS_PER_LONG] ^ invert;

	/* Handle 1st word. */
	tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr[start / BITS_PER_LONG] ^ invert;
	}

	return min(start + __ffs(ext2_swab(tmp)), nbits);
}
#endif

#ifndef find_next_zero_bit_le
unsigned long find_next_zero_bit_le(const void *addr, unsigned
		long size, unsigned long offset)
{
	return _find_next_bit_le(addr, size, offset, ~0UL);
}
EXPORT_SYMBOL(find_next_zero_bit_le);
#endif

#ifndef find_next_bit_le
unsigned long find_next_bit_le(const void *addr, unsigned
		long size, unsigned long offset)
{
	return _find_next_bit_le(addr, size, offset, 0UL);
}
EXPORT_SYMBOL(find_next_bit_le);
#endif

#endif /* __BIG_ENDIAN */
back to top