OpenCloudOS-Kernel/fs/xfs/xfs_symlink.c

505 lines
12 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_shared.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_mount.h"
#include "xfs_dir2.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
#include "xfs_bmap_btree.h"
#include "xfs_quota.h"
#include "xfs_symlink.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
#include "xfs_trans.h"
/* ----- Kernel only functions below ----- */
int
xfs_readlink_bmap_ilocked(
struct xfs_inode *ip,
char *link)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
struct xfs_buf *bp;
xfs_daddr_t d;
char *cur_chunk;
int pathlen = ip->i_disk_size;
int nmaps = XFS_SYMLINK_MAPS;
int byte_cnt;
int n;
int error = 0;
int fsblocks = 0;
int offset;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
fsblocks = xfs_symlink_blocks(mp, pathlen);
error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
if (error)
goto out;
offset = 0;
for (n = 0; n < nmaps; n++) {
d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0,
&bp, &xfs_symlink_buf_ops);
if (error)
return error;
byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
if (pathlen < byte_cnt)
byte_cnt = pathlen;
cur_chunk = bp->b_addr;
if (xfs_sb_version_hascrc(&mp->m_sb)) {
if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
byte_cnt, bp)) {
error = -EFSCORRUPTED;
xfs_alert(mp,
"symlink header does not match required off/len/owner (0x%x/Ox%x,0x%llx)",
offset, byte_cnt, ip->i_ino);
xfs_buf_relse(bp);
goto out;
}
cur_chunk += sizeof(struct xfs_dsymlink_hdr);
}
memcpy(link + offset, cur_chunk, byte_cnt);
pathlen -= byte_cnt;
offset += byte_cnt;
xfs_buf_relse(bp);
}
ASSERT(pathlen == 0);
link[ip->i_disk_size] = '\0';
error = 0;
out:
return error;
}
int
xfs_readlink(
struct xfs_inode *ip,
char *link)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fsize_t pathlen;
int error = 0;
trace_xfs_readlink(ip);
ASSERT(!(ip->i_df.if_flags & XFS_IFINLINE));
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_ilock(ip, XFS_ILOCK_SHARED);
pathlen = ip->i_disk_size;
if (!pathlen)
goto out;
if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)",
__func__, (unsigned long long) ip->i_ino,
(long long) pathlen);
ASSERT(0);
error = -EFSCORRUPTED;
goto out;
}
error = xfs_readlink_bmap_ilocked(ip, link);
out:
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return error;
}
int
xfs_symlink(
struct user_namespace *mnt_userns,
struct xfs_inode *dp,
struct xfs_name *link_name,
const char *target_path,
umode_t mode,
struct xfs_inode **ipp)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_trans *tp = NULL;
struct xfs_inode *ip = NULL;
int error = 0;
int pathlen;
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
bool unlock_dp_on_error = false;
xfs_fileoff_t first_fsb;
xfs_filblks_t fs_blocks;
int nmaps;
struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
xfs_daddr_t d;
const char *cur_chunk;
int byte_cnt;
int n;
struct xfs_buf *bp;
prid_t prid;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
struct xfs_dquot *pdqp = NULL;
uint resblks;
*ipp = NULL;
trace_xfs_symlink(dp, link_name);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Check component lengths of the target path name.
*/
pathlen = strlen(target_path);
if (pathlen >= XFS_SYMLINK_MAXLEN) /* total string too long */
return -ENAMETOOLONG;
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>
2018-12-13 00:46:21 +08:00
ASSERT(pathlen > 0);
prid = xfs_get_initial_prid(dp);
/*
* Make sure that we have allocated dquot(s) on disk.
*/
error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
fsgid_into_mnt(mnt_userns), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
if (error)
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
return error;
/*
* The symlink will fit into the inode data fork?
* There can't be any attributes so we get the whole variable part.
*/
if (pathlen <= XFS_LITINO(mp))
fs_blocks = 0;
else
fs_blocks = xfs_symlink_blocks(mp, pathlen);
resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks);
error = xfs_trans_alloc_icreate(mp, &M_RES(mp)->tr_symlink, udqp, gdqp,
pdqp, resblks, &tp);
if (error)
goto out_release_dquots;
xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
unlock_dp_on_error = true;
/*
* Check whether the directory allows new symlinks or not.
*/
if (dp->i_diflags & XFS_DIFLAG_NOSYMLINKS) {
error = -EPERM;
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
goto out_trans_cancel;
}
error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK,
XFS_IEXT_DIR_MANIP_CNT(mp));
if (error)
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
goto out_trans_cancel;
/*
* Allocate an inode for the symlink.
*/
error = xfs_dir_ialloc(mnt_userns, &tp, dp, S_IFLNK | (mode & ~S_IFMT),
xfs: initialise attr fork on inode create When we allocate a new inode, we often need to add an attribute to the inode as part of the create. This can happen as a result of needing to add default ACLs or security labels before the inode is made visible to userspace. This is highly inefficient right now. We do the create transaction to allocate the inode, then we do an "add attr fork" transaction to modify the just created empty inode to set the inode fork offset to allow attributes to be stored, then we go and do the attribute creation. This means 3 transactions instead of 1 to allocate an inode, and this greatly increases the load on the CIL commit code, resulting in excessive contention on the CIL spin locks and performance degradation: 18.99% [kernel] [k] __pv_queued_spin_lock_slowpath 3.57% [kernel] [k] do_raw_spin_lock 2.51% [kernel] [k] __raw_callee_save___pv_queued_spin_unlock 2.48% [kernel] [k] memcpy 2.34% [kernel] [k] xfs_log_commit_cil The typical profile resulting from running fsmark on a selinux enabled filesytem is adds this overhead to the create path: - 15.30% xfs_init_security - 15.23% security_inode_init_security - 13.05% xfs_initxattrs - 12.94% xfs_attr_set - 6.75% xfs_bmap_add_attrfork - 5.51% xfs_trans_commit - 5.48% __xfs_trans_commit - 5.35% xfs_log_commit_cil - 3.86% _raw_spin_lock - do_raw_spin_lock __pv_queued_spin_lock_slowpath - 0.70% xfs_trans_alloc 0.52% xfs_trans_reserve - 5.41% xfs_attr_set_args - 5.39% xfs_attr_set_shortform.constprop.0 - 4.46% xfs_trans_commit - 4.46% __xfs_trans_commit - 4.33% xfs_log_commit_cil - 2.74% _raw_spin_lock - do_raw_spin_lock __pv_queued_spin_lock_slowpath 0.60% xfs_inode_item_format 0.90% xfs_attr_try_sf_addname - 1.99% selinux_inode_init_security - 1.02% security_sid_to_context_force - 1.00% security_sid_to_context_core - 0.92% sidtab_entry_to_string - 0.90% sidtab_sid2str_get 0.59% sidtab_sid2str_put.part.0 - 0.82% selinux_determine_inode_label - 0.77% security_transition_sid 0.70% security_compute_sid.part.0 And fsmark creation rate performance drops by ~25%. The key point to note here is that half the additional overhead comes from adding the attribute fork to the newly created inode. That's crazy, considering we can do this same thing at inode create time with a couple of lines of code and no extra overhead. So, if we know we are going to add an attribute immediately after creating the inode, let's just initialise the attribute fork inside the create transaction and chop that whole chunk of code out of the create fast path. This completely removes the performance drop caused by enabling SELinux, and the profile looks like: - 8.99% xfs_init_security - 9.00% security_inode_init_security - 6.43% xfs_initxattrs - 6.37% xfs_attr_set - 5.45% xfs_attr_set_args - 5.42% xfs_attr_set_shortform.constprop.0 - 4.51% xfs_trans_commit - 4.54% __xfs_trans_commit - 4.59% xfs_log_commit_cil - 2.67% _raw_spin_lock - 3.28% do_raw_spin_lock 3.08% __pv_queued_spin_lock_slowpath 0.66% xfs_inode_item_format - 0.90% xfs_attr_try_sf_addname - 0.60% xfs_trans_alloc - 2.35% selinux_inode_init_security - 1.25% security_sid_to_context_force - 1.21% security_sid_to_context_core - 1.19% sidtab_entry_to_string - 1.20% sidtab_sid2str_get - 0.86% sidtab_sid2str_put.part.0 - 0.62% _raw_spin_lock_irqsave - 0.77% do_raw_spin_lock __pv_queued_spin_lock_slowpath - 0.84% selinux_determine_inode_label - 0.83% security_transition_sid 0.86% security_compute_sid.part.0 Which indicates the XFS overhead of creating the selinux xattr has been halved. This doesn't fix the CIL lock contention problem, just means it's not a limiting factor for this workload. Lock contention in the security subsystems is going to be an issue soon, though... Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> [djwong: fix compilation error when CONFIG_SECURITY=n] Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Gao Xiang <hsiangkao@redhat.com>
2021-03-23 00:52:03 +08:00
1, 0, prid, false, &ip);
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
if (error)
goto out_trans_cancel;
/*
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
* Now we join the directory inode to the transaction. We do not do it
* earlier because xfs_dir_ialloc might commit the previous transaction
* (and release all the locks). An error from here on will result in
* the transaction cancel unlocking dp so don't do it explicitly in the
* error path.
*/
xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
unlock_dp_on_error = false;
/*
* Also attach the dquot(s) to it, if applicable.
*/
xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
resblks -= XFS_IALLOC_SPACE_RES(mp);
/*
* If the symlink will fit into the inode, write it inline.
*/
if (pathlen <= XFS_IFORK_DSIZE(ip)) {
xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
ip->i_disk_size = pathlen;
ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
} else {
int offset;
first_fsb = 0;
nmaps = XFS_SYMLINK_MAPS;
error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
XFS_BMAPI_METADATA, resblks, mval, &nmaps);
if (error)
goto out_trans_cancel;
resblks -= fs_blocks;
ip->i_disk_size = pathlen;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
cur_chunk = target_path;
offset = 0;
for (n = 0; n < nmaps; n++) {
char *buf;
d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
BTOBB(byte_cnt), 0, &bp);
if (error)
goto out_trans_cancel;
bp->b_ops = &xfs_symlink_buf_ops;
byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
byte_cnt = min(byte_cnt, pathlen);
buf = bp->b_addr;
buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset,
byte_cnt, bp);
memcpy(buf, cur_chunk, byte_cnt);
cur_chunk += byte_cnt;
pathlen -= byte_cnt;
offset += byte_cnt;
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
(char *)bp->b_addr);
}
ASSERT(pathlen == 0);
}
i_size_write(VFS_I(ip), ip->i_disk_size);
/*
* Create the directory entry for the symlink.
*/
error = xfs_dir_createname(tp, dp, link_name, ip->i_ino, resblks);
if (error)
goto out_trans_cancel;
xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
/*
* If this is a synchronous mount, make sure that the
* symlink transaction goes to disk before returning to
* the user.
*/
if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
xfs_trans_set_sync(tp);
}
error = xfs_trans_commit(tp);
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
if (error)
goto out_release_inode;
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
*ipp = ip;
return 0;
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
out_trans_cancel:
xfs_trans_cancel(tp);
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
out_release_inode:
/*
* Wait until after the current transaction is aborted to finish the
* setup of the inode and release the inode. This prevents recursive
* transactions and deadlocks from xfs_inactive.
*/
if (ip) {
xfs_finish_inode_setup(ip);
xfs_irele(ip);
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
}
out_release_dquots:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
if (unlock_dp_on_error)
xfs_iunlock(dp, XFS_ILOCK_EXCL);
return error;
}
/*
* Free a symlink that has blocks associated with it.
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>
2018-12-13 00:46:21 +08:00
*
* Note: zero length symlinks are not allowed to exist. When we set the size to
* zero, also change it to a regular file so that it does not get written to
* disk as a zero length symlink. The inode is on the unlinked list already, so
* userspace cannot find this inode anymore, so this change is not user visible
* but allows us to catch corrupt zero-length symlinks in the verifiers.
*/
STATIC int
xfs_inactive_symlink_rmt(
struct xfs_inode *ip)
{
struct xfs_buf *bp;
int done;
int error;
int i;
xfs_mount_t *mp;
xfs_bmbt_irec_t mval[XFS_SYMLINK_MAPS];
int nmaps;
int size;
xfs_trans_t *tp;
mp = ip->i_mount;
ASSERT(ip->i_df.if_flags & XFS_IFEXTENTS);
/*
* We're freeing a symlink that has some
* blocks allocated to it. Free the
* blocks here. We know that we've got
* either 1 or 2 extents and that we can
* free them all in one bunmapi call.
*/
ASSERT(ip->i_df.if_nextents > 0 && ip->i_df.if_nextents <= 2);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
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>
2018-12-13 00:46:21 +08:00
* Lock the inode, fix the size, turn it into a regular file and join it
* to the transaction. Hold it so in the normal path, we still have it
* locked for the second transaction. In the error paths we need it
* held so the cancel won't rele it, see below.
*/
size = (int)ip->i_disk_size;
ip->i_disk_size = 0;
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>
2018-12-13 00:46:21 +08:00
VFS_I(ip)->i_mode = (VFS_I(ip)->i_mode & ~S_IFMT) | S_IFREG;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
/*
* Find the block(s) so we can inval and unmap them.
*/
done = 0;
nmaps = ARRAY_SIZE(mval);
error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
mval, &nmaps, 0);
if (error)
goto error_trans_cancel;
/*
* Invalidate the block(s). No validation is done.
*/
for (i = 0; i < nmaps; i++) {
error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, mval[i].br_startblock),
XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0,
&bp);
if (error)
goto error_trans_cancel;
xfs_trans_binval(tp, bp);
}
/*
* Unmap the dead block(s) to the dfops.
*/
error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &done);
if (error)
goto error_trans_cancel;
ASSERT(done);
/*
* Commit the transaction. This first logs the EFI and the inode, then
* rolls and commits the transaction that frees the extents.
*/
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_trans_commit(tp);
if (error) {
ASSERT(XFS_FORCED_SHUTDOWN(mp));
goto error_unlock;
}
/*
* Remove the memory for extent descriptions (just bookkeeping).
*/
if (ip->i_df.if_bytes)
xfs_idata_realloc(ip, -ip->i_df.if_bytes, XFS_DATA_FORK);
ASSERT(ip->i_df.if_bytes == 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
error_trans_cancel:
xfs_trans_cancel(tp);
error_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
/*
* xfs_inactive_symlink - free a symlink
*/
int
xfs_inactive_symlink(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
int pathlen;
trace_xfs_inactive_symlink(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
xfs_ilock(ip, XFS_ILOCK_EXCL);
pathlen = (int)ip->i_disk_size;
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>
2018-12-13 00:46:21 +08:00
ASSERT(pathlen);
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>
2018-12-13 00:46:21 +08:00
if (pathlen <= 0 || pathlen > XFS_SYMLINK_MAXLEN) {
xfs_alert(mp, "%s: inode (0x%llx) bad symlink length (%d)",
__func__, (unsigned long long)ip->i_ino, pathlen);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
ASSERT(0);
return -EFSCORRUPTED;
}
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>
2018-12-13 00:46:21 +08:00
/*
* Inline fork state gets removed by xfs_difree() so we have nothing to
* do here in that case.
*/
if (ip->i_df.if_flags & XFS_IFINLINE) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
return 0;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* remove the remote symlink */
return xfs_inactive_symlink_rmt(ip);
}