Revision a742994aa2e271eb8cd8e043d276515ec858ed73 authored by Filipe Manana on 13 February 2015, 16:56:14 UTC, committed by Chris Mason on 14 February 2015, 16:22:49 UTC
If we are recording in the tree log that an inode has new names (new hard
links were added), we would drop items, belonging to the inode, that we
shouldn't:
1) When the flag BTRFS_INODE_COPY_EVERYTHING is set in the inode's runtime
flags, we ended up dropping all the extent and xattr items that were
previously logged. This was done only in memory, since logging a new
name doesn't imply syncing the log;
2) When the flag BTRFS_INODE_COPY_EVERYTHING is set in the inode's runtime
flags, we ended up dropping all the xattr items that were previously
logged. Like the case before, this was done only in memory because
logging a new name doesn't imply syncing the log.
This led to some surprises in scenarios such as the following:
1) write some extents to an inode;
2) fsync the inode;
3) truncate the inode or delete/modify some of its xattrs
4) add a new hard link for that inode
5) fsync some other file, to force the log tree to be durably persisted
6) power failure happens
The next time the fs is mounted, the fsync log replay code is executed,
and the resulting file doesn't have the content it had when the last fsync
against it was performed, instead if has a content matching what it had
when the last transaction commit happened.
So change the behaviour such that when a new name is logged, only the inode
item and reference items are processed.
This is easy to reproduce with the test I just made for xfstests, whose
main body is:
_scratch_mkfs >> $seqres.full 2>&1
_init_flakey
_mount_flakey
# Create our test file with some data.
$XFS_IO_PROG -f -c "pwrite -S 0xaa -b 8K 0 8K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Make sure the file is durably persisted.
sync
# Append some data to our file, to increase its size.
$XFS_IO_PROG -f -c "pwrite -S 0xcc -b 4K 8K 4K" \
$SCRATCH_MNT/foo | _filter_xfs_io
# Fsync the file, so from this point on if a crash/power failure happens, our
# new data is guaranteed to be there next time the fs is mounted.
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/foo
# Now shrink our file to 5000 bytes.
$XFS_IO_PROG -c "truncate 5000" $SCRATCH_MNT/foo
# Now do an expanding truncate to a size larger than what we had when we last
# fsync'ed our file. This is just to verify that after power failure and
# replaying the fsync log, our file matches what it was when we last fsync'ed
# it - 12Kb size, first 8Kb of data had a value of 0xaa and the last 4Kb of
# data had a value of 0xcc.
$XFS_IO_PROG -c "truncate 32K" $SCRATCH_MNT/foo
# Add one hard link to our file. This made btrfs drop all of our file's
# metadata from the fsync log, including the metadata relative to the
# extent we just wrote and fsync'ed. This change was made only to the fsync
# log in memory, so adding the hard link alone doesn't change the persisted
# fsync log. This happened because the previous truncates set the runtime
# flag BTRFS_INODE_NEEDS_FULL_SYNC in the btrfs inode structure.
ln $SCRATCH_MNT/foo $SCRATCH_MNT/foo_link
# Now make sure the in memory fsync log is durably persisted.
# Creating and fsync'ing another file will do it.
# After this our persisted fsync log will no longer have metadata for our file
# foo that points to the extent we wrote and fsync'ed before.
touch $SCRATCH_MNT/bar
$XFS_IO_PROG -c "fsync" $SCRATCH_MNT/bar
# As expected, before the crash/power failure, we should be able to see a file
# with a size of 32Kb, with its first 5000 bytes having the value 0xaa and all
# the remaining bytes with value 0x00.
echo "File content before:"
od -t x1 $SCRATCH_MNT/foo
# Simulate a crash/power loss.
_load_flakey_table $FLAKEY_DROP_WRITES
_unmount_flakey
_load_flakey_table $FLAKEY_ALLOW_WRITES
_mount_flakey
# After mounting the fs again, the fsync log was replayed.
# The expected result is to see a file with a size of 12Kb, with its first 8Kb
# of data having the value 0xaa and its last 4Kb of data having a value of 0xcc.
# The btrfs bug used to leave the file as it used te be as of the last
# transaction commit - that is, with a size of 8Kb with all bytes having a
# value of 0xaa.
echo "File content after:"
od -t x1 $SCRATCH_MNT/foo
The test case for xfstests follows soon.
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>
1 parent 1a4bcf4
kstrtox.c
/*
* Convert integer string representation to an integer.
* If an integer doesn't fit into specified type, -E is returned.
*
* Integer starts with optional sign.
* kstrtou*() functions do not accept sign "-".
*
* Radix 0 means autodetection: leading "0x" implies radix 16,
* leading "0" implies radix 8, otherwise radix is 10.
* Autodetection hints work after optional sign, but not before.
*
* If -E is returned, result is not touched.
*/
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/math64.h>
#include <linux/export.h>
#include <linux/types.h>
#include <asm/uaccess.h>
#include "kstrtox.h"
const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
{
if (*base == 0) {
if (s[0] == '0') {
if (_tolower(s[1]) == 'x' && isxdigit(s[2]))
*base = 16;
else
*base = 8;
} else
*base = 10;
}
if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x')
s += 2;
return s;
}
/*
* Convert non-negative integer string representation in explicitly given radix
* to an integer.
* Return number of characters consumed maybe or-ed with overflow bit.
* If overflow occurs, result integer (incorrect) is still returned.
*
* Don't you dare use this function.
*/
unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p)
{
unsigned long long res;
unsigned int rv;
int overflow;
res = 0;
rv = 0;
overflow = 0;
while (*s) {
unsigned int val;
if ('0' <= *s && *s <= '9')
val = *s - '0';
else if ('a' <= _tolower(*s) && _tolower(*s) <= 'f')
val = _tolower(*s) - 'a' + 10;
else
break;
if (val >= base)
break;
/*
* Check for overflow only if we are within range of
* it in the max base we support (16)
*/
if (unlikely(res & (~0ull << 60))) {
if (res > div_u64(ULLONG_MAX - val, base))
overflow = 1;
}
res = res * base + val;
rv++;
s++;
}
*p = res;
if (overflow)
rv |= KSTRTOX_OVERFLOW;
return rv;
}
static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
{
unsigned long long _res;
unsigned int rv;
s = _parse_integer_fixup_radix(s, &base);
rv = _parse_integer(s, base, &_res);
if (rv & KSTRTOX_OVERFLOW)
return -ERANGE;
if (rv == 0)
return -EINVAL;
s += rv;
if (*s == '\n')
s++;
if (*s)
return -EINVAL;
*res = _res;
return 0;
}
/**
* kstrtoull - convert a string to an unsigned long long
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign, but not a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Used as a replacement for the obsolete simple_strtoull. Return code must
* be checked.
*/
int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
{
if (s[0] == '+')
s++;
return _kstrtoull(s, base, res);
}
EXPORT_SYMBOL(kstrtoull);
/**
* kstrtoll - convert a string to a long long
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign or a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Used as a replacement for the obsolete simple_strtoull. Return code must
* be checked.
*/
int kstrtoll(const char *s, unsigned int base, long long *res)
{
unsigned long long tmp;
int rv;
if (s[0] == '-') {
rv = _kstrtoull(s + 1, base, &tmp);
if (rv < 0)
return rv;
if ((long long)(-tmp) >= 0)
return -ERANGE;
*res = -tmp;
} else {
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if ((long long)tmp < 0)
return -ERANGE;
*res = tmp;
}
return 0;
}
EXPORT_SYMBOL(kstrtoll);
/* Internal, do not use. */
int _kstrtoul(const char *s, unsigned int base, unsigned long *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (unsigned long long)(unsigned long)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(_kstrtoul);
/* Internal, do not use. */
int _kstrtol(const char *s, unsigned int base, long *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (long long)(long)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(_kstrtol);
/**
* kstrtouint - convert a string to an unsigned int
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign, but not a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Used as a replacement for the obsolete simple_strtoull. Return code must
* be checked.
*/
int kstrtouint(const char *s, unsigned int base, unsigned int *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (unsigned long long)(unsigned int)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtouint);
/**
* kstrtoint - convert a string to an int
* @s: The start of the string. The string must be null-terminated, and may also
* include a single newline before its terminating null. The first character
* may also be a plus sign or a minus sign.
* @base: The number base to use. The maximum supported base is 16. If base is
* given as 0, then the base of the string is automatically detected with the
* conventional semantics - If it begins with 0x the number will be parsed as a
* hexadecimal (case insensitive), if it otherwise begins with 0, it will be
* parsed as an octal number. Otherwise it will be parsed as a decimal.
* @res: Where to write the result of the conversion on success.
*
* Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error.
* Used as a replacement for the obsolete simple_strtoull. Return code must
* be checked.
*/
int kstrtoint(const char *s, unsigned int base, int *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (long long)(int)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtoint);
int kstrtou16(const char *s, unsigned int base, u16 *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (unsigned long long)(u16)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtou16);
int kstrtos16(const char *s, unsigned int base, s16 *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (long long)(s16)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtos16);
int kstrtou8(const char *s, unsigned int base, u8 *res)
{
unsigned long long tmp;
int rv;
rv = kstrtoull(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (unsigned long long)(u8)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtou8);
int kstrtos8(const char *s, unsigned int base, s8 *res)
{
long long tmp;
int rv;
rv = kstrtoll(s, base, &tmp);
if (rv < 0)
return rv;
if (tmp != (long long)(s8)tmp)
return -ERANGE;
*res = tmp;
return 0;
}
EXPORT_SYMBOL(kstrtos8);
#define kstrto_from_user(f, g, type) \
int f(const char __user *s, size_t count, unsigned int base, type *res) \
{ \
/* sign, base 2 representation, newline, terminator */ \
char buf[1 + sizeof(type) * 8 + 1 + 1]; \
\
count = min(count, sizeof(buf) - 1); \
if (copy_from_user(buf, s, count)) \
return -EFAULT; \
buf[count] = '\0'; \
return g(buf, base, res); \
} \
EXPORT_SYMBOL(f)
kstrto_from_user(kstrtoull_from_user, kstrtoull, unsigned long long);
kstrto_from_user(kstrtoll_from_user, kstrtoll, long long);
kstrto_from_user(kstrtoul_from_user, kstrtoul, unsigned long);
kstrto_from_user(kstrtol_from_user, kstrtol, long);
kstrto_from_user(kstrtouint_from_user, kstrtouint, unsigned int);
kstrto_from_user(kstrtoint_from_user, kstrtoint, int);
kstrto_from_user(kstrtou16_from_user, kstrtou16, u16);
kstrto_from_user(kstrtos16_from_user, kstrtos16, s16);
kstrto_from_user(kstrtou8_from_user, kstrtou8, u8);
kstrto_from_user(kstrtos8_from_user, kstrtos8, s8);
Computing file changes ...
