STATIC int
xfs_vn_link(
struct dentry *old_dentry,
struct inode *dir,
struct dentry *dentry)
{
struct inode *inode; /* inode of guy being linked to */
struct xfs_name name;
int error;
inode = old_dentry->d_inode;
xfs_dentry_to_name(&name, dentry);
igrab(inode);
error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
if (unlikely(error)) {
iput(inode);
return -error;
}
xfs_iflags_set(XFS_I(dir), XFS_IMODIFIED);
xfs_validate_fields(inode);
d_instantiate(dentry, inode);
return 0;
}
/*
* Hook in SELinux. This is not quite correct yet, what we really need
* here (as we do for default ACLs) is a mechanism by which creation of
* these attrs can be journalled at inode creation time (along with the
* inode, of course, such that log replay can't cause these to be lost).
*/
STATIC int
xfs_init_security(
bhv_vnode_t *vp,
struct inode *dir)
{
struct inode *ip = vn_to_inode(vp);
size_t length;
void *value;
char *name;
int error;
error = security_inode_init_security(ip, dir, &name, &value, &length);
if (error) {
if (error == -EOPNOTSUPP)
return 0;
return -error;
}
error = xfs_attr_set(XFS_I(ip), name, value,
length, ATTR_SECURE);
if (!error)
xfs_iflags_set(XFS_I(ip), XFS_IMODIFIED);
kfree(name);
kfree(value);
return error;
}
STATIC long
xfs_file_ioctl_invis(
struct file *filp,
unsigned int cmd,
unsigned long p)
{
int error;
struct inode *inode = filp->f_path.dentry->d_inode;
error = xfs_ioctl(XFS_I(inode), filp, IO_INVIS, cmd, (void __user *)p);
xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);
/* NOTE: some of the ioctl's return positive #'s as a
* byte count indicating success, such as
* readlink_by_handle. So we don't "sign flip"
* like most other routines. This means true
* errors need to be returned as a negative value.
*/
return error;
}
STATIC int
xfs_vn_link(
struct dentry *old_dentry,
struct inode *dir,
struct dentry *dentry)
{
struct inode *ip; /* inode of guy being linked to */
bhv_vnode_t *vp; /* vp of name being linked */
int error;
ip = old_dentry->d_inode; /* inode being linked to */
vp = vn_from_inode(ip);
VN_HOLD(vp);
error = xfs_link(XFS_I(dir), vp, dentry);
if (unlikely(error)) {
VN_RELE(vp);
} else {
xfs_iflags_set(XFS_I(dir), XFS_IMODIFIED);
xfs_validate_fields(ip);
d_instantiate(dentry, ip);
}
return -error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Now we can make the changes. Before we join the inode to the
* transaction, take care of the part of the truncation that must be
* done without the inode lock. This needs to be done before joining
* the inode to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (newsize > oldsize) {
/*
* Do the first part of growing a file: zero any data in the
* last block that is beyond the old EOF. We need to do this
* before the inode is joined to the transaction to modify
* i_size.
*/
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
return error;
}
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
return error;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, newsize);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_abort;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
static int
xfs_iget_cache_miss(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_trans_t *tp,
xfs_ino_t ino,
struct xfs_inode **ipp,
int flags,
int lock_flags)
{
struct xfs_inode *ip;
int error;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino);
int iflags;
ip = xfs_inode_alloc(mp, ino);
if (!ip)
return ENOMEM;
error = xfs_iread(mp, tp, ip, flags);
if (error)
goto out_destroy;
trace_xfs_iget_miss(ip);
if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
error = ENOENT;
goto out_destroy;
}
/*
* Preload the radix tree so we can insert safely under the
* write spinlock. Note that we cannot sleep inside the preload
* region.
*/
if (radix_tree_preload(GFP_KERNEL)) {
error = EAGAIN;
goto out_destroy;
}
/*
* Because the inode hasn't been added to the radix-tree yet it can't
* be found by another thread, so we can do the non-sleeping lock here.
*/
if (lock_flags) {
if (!xfs_ilock_nowait(ip, lock_flags))
BUG();
}
/*
* These values must be set before inserting the inode into the radix
* tree as the moment it is inserted a concurrent lookup (allowed by the
* RCU locking mechanism) can find it and that lookup must see that this
* is an inode currently under construction (i.e. that XFS_INEW is set).
* The ip->i_flags_lock that protects the XFS_INEW flag forms the
* memory barrier that ensures this detection works correctly at lookup
* time.
*/
iflags = XFS_INEW;
if (flags & XFS_IGET_DONTCACHE)
iflags |= XFS_IDONTCACHE;
ip->i_udquot = ip->i_gdquot = NULL;
xfs_iflags_set(ip, iflags);
/* insert the new inode */
spin_lock(&pag->pag_ici_lock);
error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
if (unlikely(error)) {
WARN_ON(error != -EEXIST);
XFS_STATS_INC(xs_ig_dup);
error = EAGAIN;
goto out_preload_end;
}
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
*ipp = ip;
return 0;
out_preload_end:
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
__destroy_inode(VFS_I(ip));
xfs_inode_free(ip);
return error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
bool did_zeroing = false;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -EROFS;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
error = inode_change_ok(inode, iattr);
if (error)
return error;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
ASSERT(S_ISREG(inode->i_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
/*
* File data changes must be complete before we start the transaction to
* modify the inode. This needs to be done before joining the inode to
* the transaction because the inode cannot be unlocked once it is a
* part of the transaction.
*
* Start with zeroing any data beyond EOF that we may expose on file
* extension, or zeroing out the rest of the block on a downward
* truncate.
*/
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
} else {
error = iomap_truncate_page(inode, newsize, &did_zeroing,
&xfs_iomap_ops);
}
if (error)
return error;
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem. Note that this includes any block zeroing we did above;
* otherwise those blocks may not be zeroed after a crash.
*/
if (did_zeroing ||
(newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* We've already locked out new page faults, so now we can safely remove
* pages from the page cache knowing they won't get refaulted until we
* drop the XFS_MMAP_EXCL lock after the extent manipulations are
* complete. The truncate_setsize() call also cleans partial EOF page
* PTEs on extending truncates and hence ensures sub-page block size
* filesystems are correctly handled, too.
*
* We have to do all the page cache truncate work outside the
* transaction context as the "lock" order is page lock->log space
* reservation as defined by extent allocation in the writeback path.
* Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but
* having already truncated the in-memory version of the file (i.e. made
* user visible changes). There's not much we can do about this, except
* to hope that the caller sees ENOMEM and retries the truncate
* operation.
*/
truncate_setsize(inode, newsize);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_cancel;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
goto out_unlock;
}
/*
* Process a bmap update intent item that was recovered from the log.
* We need to update some inode's bmbt.
*/
int
xfs_bui_recover(
struct xfs_mount *mp,
struct xfs_bui_log_item *buip,
struct xfs_defer_ops *dfops)
{
int error = 0;
unsigned int bui_type;
struct xfs_map_extent *bmap;
xfs_fsblock_t startblock_fsb;
xfs_fsblock_t inode_fsb;
xfs_filblks_t count;
bool op_ok;
struct xfs_bud_log_item *budp;
enum xfs_bmap_intent_type type;
int whichfork;
xfs_exntst_t state;
struct xfs_trans *tp;
struct xfs_inode *ip = NULL;
struct xfs_bmbt_irec irec;
ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
/* Only one mapping operation per BUI... */
if (buip->bui_format.bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
xfs_bui_release(buip);
return -EIO;
}
/*
* First check the validity of the extent described by the
* BUI. If anything is bad, then toss the BUI.
*/
bmap = &buip->bui_format.bui_extents[0];
startblock_fsb = XFS_BB_TO_FSB(mp,
XFS_FSB_TO_DADDR(mp, bmap->me_startblock));
inode_fsb = XFS_BB_TO_FSB(mp, XFS_FSB_TO_DADDR(mp,
XFS_INO_TO_FSB(mp, bmap->me_owner)));
switch (bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK) {
case XFS_BMAP_MAP:
case XFS_BMAP_UNMAP:
op_ok = true;
break;
default:
op_ok = false;
break;
}
if (!op_ok || startblock_fsb == 0 ||
bmap->me_len == 0 ||
inode_fsb == 0 ||
startblock_fsb >= mp->m_sb.sb_dblocks ||
bmap->me_len >= mp->m_sb.sb_agblocks ||
inode_fsb >= mp->m_sb.sb_dblocks ||
(bmap->me_flags & ~XFS_BMAP_EXTENT_FLAGS)) {
/*
* This will pull the BUI from the AIL and
* free the memory associated with it.
*/
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
xfs_bui_release(buip);
return -EIO;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
if (error)
return error;
budp = xfs_trans_get_bud(tp, buip);
/* Grab the inode. */
error = xfs_iget(mp, tp, bmap->me_owner, 0, XFS_ILOCK_EXCL, &ip);
if (error)
goto err_inode;
if (VFS_I(ip)->i_nlink == 0)
xfs_iflags_set(ip, XFS_IRECOVERY);
/* Process deferred bmap item. */
state = (bmap->me_flags & XFS_BMAP_EXTENT_UNWRITTEN) ?
XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
whichfork = (bmap->me_flags & XFS_BMAP_EXTENT_ATTR_FORK) ?
XFS_ATTR_FORK : XFS_DATA_FORK;
bui_type = bmap->me_flags & XFS_BMAP_EXTENT_TYPE_MASK;
switch (bui_type) {
case XFS_BMAP_MAP:
case XFS_BMAP_UNMAP:
type = bui_type;
break;
default:
error = -EFSCORRUPTED;
goto err_inode;
}
xfs_trans_ijoin(tp, ip, 0);
count = bmap->me_len;
error = xfs_trans_log_finish_bmap_update(tp, budp, dfops, type,
ip, whichfork, bmap->me_startoff,
bmap->me_startblock, &count, state);
if (error)
goto err_inode;
if (count > 0) {
ASSERT(type == XFS_BMAP_UNMAP);
irec.br_startblock = bmap->me_startblock;
irec.br_blockcount = count;
irec.br_startoff = bmap->me_startoff;
irec.br_state = state;
error = xfs_bmap_unmap_extent(tp->t_mountp, dfops, ip, &irec);
if (error)
goto err_inode;
}
set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
return error;
err_inode:
xfs_trans_cancel(tp);
if (ip) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
IRELE(ip);
}
return error;
}
static int
xfs_iget_cache_miss(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_trans_t *tp,
xfs_ino_t ino,
struct xfs_inode **ipp,
int flags,
int lock_flags)
{
struct xfs_inode *ip;
int error;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino);
ip = xfs_inode_alloc(mp, ino);
if (!ip)
return ENOMEM;
error = xfs_iread(mp, tp, ip, flags);
if (error)
goto out_destroy;
trace_xfs_iget_miss(ip);
if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
error = ENOENT;
goto out_destroy;
}
/*
* Preload the radix tree so we can insert safely under the
* write spinlock. Note that we cannot sleep inside the preload
* region.
*/
if (radix_tree_preload(GFP_KERNEL)) {
error = EAGAIN;
goto out_destroy;
}
/*
* Because the inode hasn't been added to the radix-tree yet it can't
* be found by another thread, so we can do the non-sleeping lock here.
*/
if (lock_flags) {
if (!xfs_ilock_nowait(ip, lock_flags))
BUG();
}
spin_lock(&pag->pag_ici_lock);
/* insert the new inode */
error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
if (unlikely(error)) {
WARN_ON(error != -EEXIST);
XFS_STATS_INC(xs_ig_dup);
error = EAGAIN;
goto out_preload_end;
}
/* These values _must_ be set before releasing the radix tree lock! */
ip->i_udquot = ip->i_gdquot = NULL;
xfs_iflags_set(ip, XFS_INEW);
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
*ipp = ip;
return 0;
out_preload_end:
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
__destroy_inode(VFS_I(ip));
xfs_inode_free(ip);
return error;
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
int mode,
dev_t rdev)
{
struct inode *ip;
bhv_vnode_t *vp = NULL, *dvp = vn_from_inode(dir);
xfs_acl_t *default_acl = NULL;
attrexists_t test_default_acl = _ACL_DEFAULT_EXISTS;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
if (unlikely(test_default_acl && test_default_acl(dvp))) {
if (!_ACL_ALLOC(default_acl)) {
return -ENOMEM;
}
if (!_ACL_GET_DEFAULT(dvp, default_acl)) {
_ACL_FREE(default_acl);
default_acl = NULL;
}
}
if (IS_POSIXACL(dir) && !default_acl && xfs_has_fs_struct(current))
mode &= ~current->fs->umask;
switch (mode & S_IFMT) {
case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK:
rdev = sysv_encode_dev(rdev);
case S_IFREG:
error = xfs_create(XFS_I(dir), dentry, mode, rdev, &vp, NULL);
break;
case S_IFDIR:
error = xfs_mkdir(XFS_I(dir), dentry, mode, &vp, NULL);
break;
default:
error = EINVAL;
break;
}
if (unlikely(!error)) {
error = xfs_init_security(vp, dir);
if (error)
xfs_cleanup_inode(dir, vp, dentry, mode);
}
if (unlikely(default_acl)) {
if (!error) {
error = _ACL_INHERIT(vp, mode, default_acl);
if (!error)
xfs_iflags_set(XFS_I(vp), XFS_IMODIFIED);
else
xfs_cleanup_inode(dir, vp, dentry, mode);
}
_ACL_FREE(default_acl);
}
if (likely(!error)) {
ASSERT(vp);
ip = vn_to_inode(vp);
if (S_ISDIR(mode))
xfs_validate_fields(ip);
d_instantiate(dentry, ip);
xfs_validate_fields(dir);
}
return -error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
struct xfs_trans *tp;
int error;
uint lock_flags;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
lock_flags = XFS_ILOCK_EXCL;
if (!(flags & XFS_ATTR_NOLOCK))
lock_flags |= XFS_IOLOCK_EXCL;
xfs_ilock(ip, lock_flags);
/*
* Short circuit the truncate case for zero length files.
*/
if (iattr->ia_size == 0 &&
ip->i_size == 0 && ip->i_d.di_nextents == 0) {
if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
goto out_unlock;
/*
* Use the regular setattr path to update the timestamps.
*/
xfs_iunlock(ip, lock_flags);
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
goto out_unlock;
/*
* Now we can make the changes. Before we join the inode to the
* transaction, take care of the part of the truncation that must be
* done without the inode lock. This needs to be done before joining
* the inode to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (iattr->ia_size > ip->i_size) {
/*
* Do the first part of growing a file: zero any data in the
* last block that is beyond the old EOF. We need to do this
* before the inode is joined to the transaction to modify
* i_size.
*/
error = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (ip->i_size != ip->i_d.di_size && iattr->ia_size > ip->i_d.di_size) {
error = xfs_flush_pages(ip, ip->i_d.di_size, iattr->ia_size,
XBF_ASYNC, FI_NONE);
if (error)
goto out_unlock;
}
/*
* Wait for all I/O to complete.
*/
xfs_ioend_wait(ip);
error = -block_truncate_page(inode->i_mapping, iattr->ia_size,
xfs_get_blocks);
if (error)
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, iattr->ia_size);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (iattr->ia_size != ip->i_size &&
(!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
mask |= ATTR_CTIME | ATTR_MTIME;
}
if (iattr->ia_size > ip->i_size) {
ip->i_d.di_size = iattr->ia_size;
ip->i_size = iattr->ia_size;
} else if (iattr->ia_size <= ip->i_size ||
(iattr->ia_size == 0 && ip->i_d.di_nextents)) {
error = xfs_itruncate_data(&tp, ip, iattr->ia_size);
if (error)
goto out_trans_abort;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
ip->i_update_core = 1;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
ip->i_update_core = 1;
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
lock_flags = XFS_ILOCK_EXCL;
if (!(flags & XFS_ATTR_NOLOCK))
lock_flags |= XFS_IOLOCK_EXCL;
xfs_ilock(ip, lock_flags);
oldsize = inode->i_size;
newsize = iattr->ia_size;
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
goto out_unlock;
xfs_iunlock(ip, lock_flags);
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
goto out_unlock;
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
error = xfs_flush_pages(ip, ip->i_d.di_size, newsize, 0,
FI_NONE);
if (error)
goto out_unlock;
}
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, newsize);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
mask |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_abort;
xfs_iflags_set(ip, XFS_ITRUNCATED);
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
STATIC long
xfs_compat_ioctl(
int mode,
struct file *file,
unsigned cmd,
unsigned long arg)
{
struct inode *inode = file->f_path.dentry->d_inode;
int error;
switch (cmd) {
case XFS_IOC_DIOINFO:
case XFS_IOC_FSGEOMETRY:
case XFS_IOC_GETVERSION:
case XFS_IOC_GETXFLAGS:
case XFS_IOC_SETXFLAGS:
case XFS_IOC_FSGETXATTR:
case XFS_IOC_FSSETXATTR:
case XFS_IOC_FSGETXATTRA:
case XFS_IOC_FSSETDM:
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
case XFS_IOC_GETBMAPX:
/* not handled
case XFS_IOC_FSSETDM_BY_HANDLE:
case XFS_IOC_ATTRLIST_BY_HANDLE:
case XFS_IOC_ATTRMULTI_BY_HANDLE:
*/
case XFS_IOC_FSCOUNTS:
case XFS_IOC_SET_RESBLKS:
case XFS_IOC_GET_RESBLKS:
case XFS_IOC_FSGROWFSDATA:
case XFS_IOC_FSGROWFSLOG:
case XFS_IOC_FSGROWFSRT:
case XFS_IOC_FREEZE:
case XFS_IOC_THAW:
case XFS_IOC_GOINGDOWN:
case XFS_IOC_ERROR_INJECTION:
case XFS_IOC_ERROR_CLEARALL:
break;
#ifdef BROKEN_X86_ALIGNMENT
/* xfs_flock_t has wrong u32 vs u64 alignment */
case XFS_IOC_ALLOCSP_32:
case XFS_IOC_FREESP_32:
case XFS_IOC_ALLOCSP64_32:
case XFS_IOC_FREESP64_32:
case XFS_IOC_RESVSP_32:
case XFS_IOC_UNRESVSP_32:
case XFS_IOC_RESVSP64_32:
case XFS_IOC_UNRESVSP64_32:
arg = xfs_ioctl32_flock(arg);
cmd = _NATIVE_IOC(cmd, struct xfs_flock64);
break;
case XFS_IOC_FSGEOMETRY_V1_32:
arg = xfs_ioctl32_geom_v1(arg);
cmd = _NATIVE_IOC(cmd, struct xfs_fsop_geom_v1);
break;
#else /* These are handled fine if no alignment issues */
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
case XFS_IOC_FSGEOMETRY_V1:
break;
/* xfs_bstat_t still has wrong u32 vs u64 alignment */
case XFS_IOC_SWAPEXT:
break;
#endif
case XFS_IOC_FSBULKSTAT_32:
case XFS_IOC_FSBULKSTAT_SINGLE_32:
case XFS_IOC_FSINUMBERS_32:
cmd = _NATIVE_IOC(cmd, struct xfs_fsop_bulkreq);
return xfs_ioc_bulkstat_compat(XFS_I(inode)->i_mount,
cmd, (void __user*)arg);
case XFS_IOC_FD_TO_HANDLE_32:
case XFS_IOC_PATH_TO_HANDLE_32:
case XFS_IOC_PATH_TO_FSHANDLE_32:
case XFS_IOC_OPEN_BY_HANDLE_32:
case XFS_IOC_READLINK_BY_HANDLE_32:
arg = xfs_ioctl32_fshandle(arg);
cmd = _NATIVE_IOC(cmd, struct xfs_fsop_handlereq);
break;
default:
return -ENOIOCTLCMD;
}
error = xfs_ioctl(XFS_I(inode), file, mode, cmd, (void __user *)arg);
xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);
return error;
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
int mode,
dev_t rdev)
{
struct inode *inode;
struct xfs_inode *ip = NULL;
xfs_acl_t *default_acl = NULL;
struct xfs_name name;
attrexists_t test_default_acl = _ACL_DEFAULT_EXISTS;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
return -EINVAL;
if (test_default_acl && test_default_acl(dir)) {
if (!_ACL_ALLOC(default_acl)) {
return -ENOMEM;
}
if (!_ACL_GET_DEFAULT(dir, default_acl)) {
_ACL_FREE(default_acl);
default_acl = NULL;
}
}
xfs_dentry_to_name(&name, dentry);
if (IS_POSIXACL(dir) && !default_acl)
mode &= ~current->fs->umask;
switch (mode & S_IFMT) {
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
rdev = sysv_encode_dev(rdev);
case S_IFREG:
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
break;
case S_IFDIR:
error = xfs_mkdir(XFS_I(dir), &name, mode, &ip, NULL);
break;
default:
error = EINVAL;
break;
}
if (unlikely(error))
goto out_free_acl;
inode = ip->i_vnode;
error = xfs_init_security(inode, dir);
if (unlikely(error))
goto out_cleanup_inode;
if (default_acl) {
error = _ACL_INHERIT(inode, mode, default_acl);
if (unlikely(error))
goto out_cleanup_inode;
xfs_iflags_set(ip, XFS_IMODIFIED);
_ACL_FREE(default_acl);
}
if (S_ISDIR(mode))
xfs_validate_fields(inode);
d_instantiate(dentry, inode);
xfs_validate_fields(dir);
return -error;
out_cleanup_inode:
xfs_cleanup_inode(dir, inode, dentry, mode);
out_free_acl:
if (default_acl)
_ACL_FREE(default_acl);
return -error;
}
static int
xfs_iget_cache_miss(
struct xfs_mount *mp,
struct xfs_perag *pag,
xfs_trans_t *tp,
xfs_ino_t ino,
struct xfs_inode **ipp,
int flags,
int lock_flags)
{
struct xfs_inode *ip;
int error;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ino);
int iflags;
ip = xfs_inode_alloc(mp, ino);
if (!ip)
return ENOMEM;
error = xfs_iread(mp, tp, ip, flags);
if (error)
goto out_destroy;
trace_xfs_iget_miss(ip);
if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
error = ENOENT;
goto out_destroy;
}
if (radix_tree_preload(GFP_KERNEL)) {
error = EAGAIN;
goto out_destroy;
}
if (lock_flags) {
if (!xfs_ilock_nowait(ip, lock_flags))
BUG();
}
iflags = XFS_INEW;
if (flags & XFS_IGET_DONTCACHE)
iflags |= XFS_IDONTCACHE;
ip->i_udquot = ip->i_gdquot = NULL;
xfs_iflags_set(ip, iflags);
spin_lock(&pag->pag_ici_lock);
error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
if (unlikely(error)) {
WARN_ON(error != -EEXIST);
XFS_STATS_INC(xs_ig_dup);
error = EAGAIN;
goto out_preload_end;
}
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
*ipp = ip;
return 0;
out_preload_end:
spin_unlock(&pag->pag_ici_lock);
radix_tree_preload_end();
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
__destroy_inode(VFS_I(ip));
xfs_inode_free(ip);
return error;
}
