linux-stable/fs/xfs/libxfs/xfs_symlink_remote.c

234 lines
5.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* Copyright (c) 2012-2013 Red Hat, Inc.
* All rights reserved.
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_shared.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
xfs: validate metadata LSNs against log on v5 superblocks Since the onset of v5 superblocks, the LSN of the last modification has been included in a variety of on-disk data structures. This LSN is used to provide log recovery ordering guarantees (e.g., to ensure an older log recovery item is not replayed over a newer target data structure). While this works correctly from the point a filesystem is formatted and mounted, userspace tools have some problematic behaviors that defeat this mechanism. For example, xfs_repair historically zeroes out the log unconditionally (regardless of whether corruption is detected). If this occurs, the LSN of the filesystem is reset and the log is now in a problematic state with respect to on-disk metadata structures that might have a larger LSN. Until either the log catches up to the highest previously used metadata LSN or each affected data structure is modified and written out without incident (which resets the metadata LSN), log recovery is susceptible to filesystem corruption. This problem is ultimately addressed and repaired in the associated userspace tools. The kernel is still responsible to detect the problem and notify the user that something is wrong. Check the superblock LSN at mount time and fail the mount if it is invalid. From that point on, trigger verifier failure on any metadata I/O where an invalid LSN is detected. This results in a filesystem shutdown and guarantees that we do not log metadata changes with invalid LSNs on disk. Since this is a known issue with a known recovery path, present a warning to instruct the user how to recover. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-10-12 04:59:25 +00:00
#include "xfs_log.h"
/*
* Each contiguous block has a header, so it is not just a simple pathlen
* to FSB conversion.
*/
int
xfs_symlink_blocks(
struct xfs_mount *mp,
int pathlen)
{
int buflen = XFS_SYMLINK_BUF_SPACE(mp, mp->m_sb.sb_blocksize);
return (pathlen + buflen - 1) / buflen;
}
int
xfs_symlink_hdr_set(
struct xfs_mount *mp,
xfs_ino_t ino,
uint32_t offset,
uint32_t size,
struct xfs_buf *bp)
{
struct xfs_dsymlink_hdr *dsl = bp->b_addr;
if (!xfs_has_crc(mp))
return 0;
xfs: validate metadata LSNs against log on v5 superblocks Since the onset of v5 superblocks, the LSN of the last modification has been included in a variety of on-disk data structures. This LSN is used to provide log recovery ordering guarantees (e.g., to ensure an older log recovery item is not replayed over a newer target data structure). While this works correctly from the point a filesystem is formatted and mounted, userspace tools have some problematic behaviors that defeat this mechanism. For example, xfs_repair historically zeroes out the log unconditionally (regardless of whether corruption is detected). If this occurs, the LSN of the filesystem is reset and the log is now in a problematic state with respect to on-disk metadata structures that might have a larger LSN. Until either the log catches up to the highest previously used metadata LSN or each affected data structure is modified and written out without incident (which resets the metadata LSN), log recovery is susceptible to filesystem corruption. This problem is ultimately addressed and repaired in the associated userspace tools. The kernel is still responsible to detect the problem and notify the user that something is wrong. Check the superblock LSN at mount time and fail the mount if it is invalid. From that point on, trigger verifier failure on any metadata I/O where an invalid LSN is detected. This results in a filesystem shutdown and guarantees that we do not log metadata changes with invalid LSNs on disk. Since this is a known issue with a known recovery path, present a warning to instruct the user how to recover. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-10-12 04:59:25 +00:00
memset(dsl, 0, sizeof(struct xfs_dsymlink_hdr));
dsl->sl_magic = cpu_to_be32(XFS_SYMLINK_MAGIC);
dsl->sl_offset = cpu_to_be32(offset);
dsl->sl_bytes = cpu_to_be32(size);
uuid_copy(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid);
dsl->sl_owner = cpu_to_be64(ino);
dsl->sl_blkno = cpu_to_be64(xfs_buf_daddr(bp));
bp->b_ops = &xfs_symlink_buf_ops;
return sizeof(struct xfs_dsymlink_hdr);
}
/*
* Checking of the symlink header is split into two parts. the verifier does
* CRC, location and bounds checking, the unpacking function checks the path
* parameters and owner.
*/
bool
xfs_symlink_hdr_ok(
xfs_ino_t ino,
uint32_t offset,
uint32_t size,
struct xfs_buf *bp)
{
struct xfs_dsymlink_hdr *dsl = bp->b_addr;
if (offset != be32_to_cpu(dsl->sl_offset))
return false;
if (size != be32_to_cpu(dsl->sl_bytes))
return false;
if (ino != be64_to_cpu(dsl->sl_owner))
return false;
/* ok */
return true;
}
static xfs_failaddr_t
xfs_symlink_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_dsymlink_hdr *dsl = bp->b_addr;
if (!xfs_has_crc(mp))
return __this_address;
if (!xfs_verify_magic(bp, dsl->sl_magic))
return __this_address;
if (!uuid_equal(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid))
return __this_address;
if (xfs_buf_daddr(bp) != be64_to_cpu(dsl->sl_blkno))
return __this_address;
if (be32_to_cpu(dsl->sl_offset) +
be32_to_cpu(dsl->sl_bytes) >= XFS_SYMLINK_MAXLEN)
return __this_address;
if (dsl->sl_owner == 0)
return __this_address;
xfs: validate metadata LSNs against log on v5 superblocks Since the onset of v5 superblocks, the LSN of the last modification has been included in a variety of on-disk data structures. This LSN is used to provide log recovery ordering guarantees (e.g., to ensure an older log recovery item is not replayed over a newer target data structure). While this works correctly from the point a filesystem is formatted and mounted, userspace tools have some problematic behaviors that defeat this mechanism. For example, xfs_repair historically zeroes out the log unconditionally (regardless of whether corruption is detected). If this occurs, the LSN of the filesystem is reset and the log is now in a problematic state with respect to on-disk metadata structures that might have a larger LSN. Until either the log catches up to the highest previously used metadata LSN or each affected data structure is modified and written out without incident (which resets the metadata LSN), log recovery is susceptible to filesystem corruption. This problem is ultimately addressed and repaired in the associated userspace tools. The kernel is still responsible to detect the problem and notify the user that something is wrong. Check the superblock LSN at mount time and fail the mount if it is invalid. From that point on, trigger verifier failure on any metadata I/O where an invalid LSN is detected. This results in a filesystem shutdown and guarantees that we do not log metadata changes with invalid LSNs on disk. Since this is a known issue with a known recovery path, present a warning to instruct the user how to recover. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-10-12 04:59:25 +00:00
if (!xfs_log_check_lsn(mp, be64_to_cpu(dsl->sl_lsn)))
return __this_address;
return NULL;
}
static void
xfs_symlink_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
xfs_failaddr_t fa;
/* no verification of non-crc buffers */
if (!xfs_has_crc(mp))
return;
if (!xfs_buf_verify_cksum(bp, XFS_SYMLINK_CRC_OFF))
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_symlink_verify(bp);
if (fa)
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
}
}
static void
xfs_symlink_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_buf_log_item *bip = bp->b_log_item;
xfs_failaddr_t fa;
/* no verification of non-crc buffers */
if (!xfs_has_crc(mp))
return;
fa = xfs_symlink_verify(bp);
if (fa) {
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
if (bip) {
struct xfs_dsymlink_hdr *dsl = bp->b_addr;
dsl->sl_lsn = cpu_to_be64(bip->bli_item.li_lsn);
}
xfs_buf_update_cksum(bp, XFS_SYMLINK_CRC_OFF);
}
const struct xfs_buf_ops xfs_symlink_buf_ops = {
.name = "xfs_symlink",
.magic = { 0, cpu_to_be32(XFS_SYMLINK_MAGIC) },
.verify_read = xfs_symlink_read_verify,
.verify_write = xfs_symlink_write_verify,
.verify_struct = xfs_symlink_verify,
};
void
xfs_symlink_local_to_remote(
struct xfs_trans *tp,
struct xfs_buf *bp,
struct xfs_inode *ip,
struct xfs_ifork *ifp)
{
struct xfs_mount *mp = ip->i_mount;
char *buf;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
if (!xfs_has_crc(mp)) {
bp->b_ops = NULL;
memcpy(bp->b_addr, ifp->if_u1.if_data, ifp->if_bytes);
xfs_trans_log_buf(tp, bp, 0, ifp->if_bytes - 1);
return;
}
/*
* As this symlink fits in an inode literal area, it must also fit in
* the smallest buffer the filesystem supports.
*/
ASSERT(BBTOB(bp->b_length) >=
ifp->if_bytes + sizeof(struct xfs_dsymlink_hdr));
bp->b_ops = &xfs_symlink_buf_ops;
buf = bp->b_addr;
buf += xfs_symlink_hdr_set(mp, ip->i_ino, 0, ifp->if_bytes, bp);
memcpy(buf, ifp->if_u1.if_data, ifp->if_bytes);
xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsymlink_hdr) +
ifp->if_bytes - 1);
}
xfs: zero length symlinks are not valid A log recovery failure has been reproduced where a symlink inode has a zero length in extent form. It was caused by a shutdown during a combined fstress+fsmark workload. The underlying problem is the issue in xfs_inactive_symlink(): the inode is unlocked between the symlink inactivation/truncation and the inode being freed. This opens a window for the inode to be written to disk before it xfs_ifree() removes it from the unlinked list, marks it free in the inobt and zeros the mode. For shortform inodes, the fix is simple. xfs_ifree() clears the data fork state, so there's no need to do it in xfs_inactive_symlink(). This means the shortform fork verifier will not see a zero length data fork as it mirrors the inode size through to xfs_ifree()), and hence if the inode gets written back and the fork verifiers are run they will still see a fork that matches the on-disk inode size. For extent form (remote) symlinks, it is a little more tricky. Here we explicitly set the inode size to zero, so the above race can lead to zero length symlinks on disk. Because the inode is unlinked at this point (i.e. on the unlinked list) and unreferenced, it can never be seen again by a user. Hence when we set the inode size to zeor, also change the type to S_IFREG. xfs_ifree() expects S_IFREG inodes to be of zero length, and so this avoids all the problems of zero length symlinks ever hitting the disk. It also avoids the problem of needing to handle zero length symlink inodes in log recovery to replay the extent free intents and the remaining deferops to free the extents the symlink used. Also add a couple of asserts to warn us if zero length symlinks end up in either the symlink create or inactivation paths. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-12-12 16:46:21 +00:00
/*
* Verify the in-memory consistency of an inline symlink data fork. This
* does not do on-disk format checks.
*/
xfs_failaddr_t
xfs_symlink_shortform_verify(
struct xfs_inode *ip)
{
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
char *sfp = (char *)ifp->if_u1.if_data;
int size = ifp->if_bytes;
char *endp = sfp + size;
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
xfs: zero length symlinks are not valid A log recovery failure has been reproduced where a symlink inode has a zero length in extent form. It was caused by a shutdown during a combined fstress+fsmark workload. The underlying problem is the issue in xfs_inactive_symlink(): the inode is unlocked between the symlink inactivation/truncation and the inode being freed. This opens a window for the inode to be written to disk before it xfs_ifree() removes it from the unlinked list, marks it free in the inobt and zeros the mode. For shortform inodes, the fix is simple. xfs_ifree() clears the data fork state, so there's no need to do it in xfs_inactive_symlink(). This means the shortform fork verifier will not see a zero length data fork as it mirrors the inode size through to xfs_ifree()), and hence if the inode gets written back and the fork verifiers are run they will still see a fork that matches the on-disk inode size. For extent form (remote) symlinks, it is a little more tricky. Here we explicitly set the inode size to zero, so the above race can lead to zero length symlinks on disk. Because the inode is unlinked at this point (i.e. on the unlinked list) and unreferenced, it can never be seen again by a user. Hence when we set the inode size to zeor, also change the type to S_IFREG. xfs_ifree() expects S_IFREG inodes to be of zero length, and so this avoids all the problems of zero length symlinks ever hitting the disk. It also avoids the problem of needing to handle zero length symlink inodes in log recovery to replay the extent free intents and the remaining deferops to free the extents the symlink used. Also add a couple of asserts to warn us if zero length symlinks end up in either the symlink create or inactivation paths. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-12-12 16:46:21 +00:00
/*
* Zero length symlinks should never occur in memory as they are
* never allowed to exist on disk.
xfs: zero length symlinks are not valid A log recovery failure has been reproduced where a symlink inode has a zero length in extent form. It was caused by a shutdown during a combined fstress+fsmark workload. The underlying problem is the issue in xfs_inactive_symlink(): the inode is unlocked between the symlink inactivation/truncation and the inode being freed. This opens a window for the inode to be written to disk before it xfs_ifree() removes it from the unlinked list, marks it free in the inobt and zeros the mode. For shortform inodes, the fix is simple. xfs_ifree() clears the data fork state, so there's no need to do it in xfs_inactive_symlink(). This means the shortform fork verifier will not see a zero length data fork as it mirrors the inode size through to xfs_ifree()), and hence if the inode gets written back and the fork verifiers are run they will still see a fork that matches the on-disk inode size. For extent form (remote) symlinks, it is a little more tricky. Here we explicitly set the inode size to zero, so the above race can lead to zero length symlinks on disk. Because the inode is unlinked at this point (i.e. on the unlinked list) and unreferenced, it can never be seen again by a user. Hence when we set the inode size to zeor, also change the type to S_IFREG. xfs_ifree() expects S_IFREG inodes to be of zero length, and so this avoids all the problems of zero length symlinks ever hitting the disk. It also avoids the problem of needing to handle zero length symlink inodes in log recovery to replay the extent free intents and the remaining deferops to free the extents the symlink used. Also add a couple of asserts to warn us if zero length symlinks end up in either the symlink create or inactivation paths. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2018-12-12 16:46:21 +00:00
*/
if (!size)
return __this_address;
/* No negative sizes or overly long symlink targets. */
if (size < 0 || size > XFS_SYMLINK_MAXLEN)
return __this_address;
/* No NULLs in the target either. */
if (memchr(sfp, 0, size - 1))
return __this_address;
/* We /did/ null-terminate the buffer, right? */
if (*endp != 0)
return __this_address;
return NULL;
}