static inline void fuse_update_ctime(struct inode *inode)
{
if (!IS_NOCMTIME(inode)) {
inode->i_ctime = current_fs_time(inode->i_sb);
mark_inode_dirty_sync(inode);
}
}
/*
* Transactional inode timestamp update. Requires the inode to be locked and
* joined to the transaction supplied. Relies on the transaction subsystem to
* track dirty state and update/writeback the inode accordingly.
*/
void
xfs_trans_ichgtime(
struct xfs_trans *tp,
struct xfs_inode *ip,
int flags)
{
struct inode *inode = VFS_I(ip);
timespec_t tv;
ASSERT(tp);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
tv = current_fs_time(inode->i_sb);
if ((flags & XFS_ICHGTIME_MOD) &&
!timespec_equal(&inode->i_mtime, &tv)) {
inode->i_mtime = tv;
ip->i_d.di_mtime.t_sec = tv.tv_sec;
ip->i_d.di_mtime.t_nsec = tv.tv_nsec;
}
if ((flags & XFS_ICHGTIME_CHG) &&
!timespec_equal(&inode->i_ctime, &tv)) {
inode->i_ctime = tv;
ip->i_d.di_ctime.t_sec = tv.tv_sec;
ip->i_d.di_ctime.t_nsec = tv.tv_nsec;
}
}
/*
* @value: "" makes the attribute to empty, NULL removes it
*/
int __btrfs_setxattr(struct btrfs_trans_handle *trans,
struct inode *inode, const char *name,
const void *value, size_t size, int flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
if (trans)
return do_setxattr(trans, inode, name, value, size, flags);
trans = btrfs_start_transaction(root, 2);
if (IS_ERR(trans))
return PTR_ERR(trans);
ret = do_setxattr(trans, inode, name, value, size, flags);
if (ret)
goto out;
inode_inc_iversion(inode);
inode->i_ctime = current_fs_time(inode->i_sb);
set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
ret = btrfs_update_inode(trans, root, inode);
BUG_ON(ret);
out:
btrfs_end_transaction(trans, root);
return ret;
}
/*
* Change the requested timestamp in the given inode.
* We don't lock across timestamp updates, and we don't log them but
* we do record the fact that there is dirty information in core.
*/
void
xfs_ichgtime(
xfs_inode_t *ip,
int flags)
{
struct inode *inode = VFS_I(ip);
timespec_t tv;
int sync_it = 0;
tv = current_fs_time(inode->i_sb);
if ((flags & XFS_ICHGTIME_MOD) &&
!timespec_equal(&inode->i_mtime, &tv)) {
inode->i_mtime = tv;
sync_it = 1;
}
if ((flags & XFS_ICHGTIME_CHG) &&
!timespec_equal(&inode->i_ctime, &tv)) {
inode->i_ctime = tv;
sync_it = 1;
}
/*
* Update complete - now make sure everyone knows that the inode
* is dirty.
*/
if (sync_it)
xfs_mark_inode_dirty_sync(ip);
}
void make_bad_inode(struct inode *inode)
{
remove_inode_hash(inode);
inode->i_mode = S_IFREG;
inode->i_atime = inode->i_mtime = inode->i_ctime =
current_fs_time(inode->i_sb);
inode->i_op = &bad_inode_ops;
inode->i_fop = &bad_file_ops;
}
static void update_ctime(struct inode *inode)
{
struct timespec now = current_fs_time(inode->i_sb);
if (inode_unhashed(inode) || !inode->i_nlink ||
timespec_equal(&inode->i_ctime, &now))
return;
inode->i_ctime = CURRENT_TIME_SEC;
mark_inode_dirty(inode);
}
static __be32
nfsd4_block_proc_layoutcommit(struct inode *inode,
struct nfsd4_layoutcommit *lcp)
{
loff_t new_size = lcp->lc_last_wr + 1;
struct iattr iattr = { .ia_valid = 0 };
struct iomap *iomaps;
int nr_iomaps;
int error;
nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
if (nr_iomaps < 0)
return nfserrno(nr_iomaps);
if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
lcp->lc_mtime = current_fs_time(inode->i_sb);
iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
if (new_size > i_size_read(inode)) {
iattr.ia_valid |= ATTR_SIZE;
iattr.ia_size = new_size;
}
error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
nr_iomaps, &iattr);
kfree(iomaps);
return nfserrno(error);
}
const struct nfsd4_layout_ops bl_layout_ops = {
/*
* Pretend that we send notification to the client. This is a blatant
* lie to force recent Linux clients to cache our device IDs.
* We rarely ever change the device ID, so the harm of leaking deviceids
* for a while isn't too bad. Unfortunately RFC5661 is a complete mess
* in this regard, but I filed errata 4119 for this a while ago, and
* hopefully the Linux client will eventually start caching deviceids
* without this again.
*/
.notify_types =
NOTIFY_DEVICEID4_DELETE | NOTIFY_DEVICEID4_CHANGE,
.proc_getdeviceinfo = nfsd4_block_proc_getdeviceinfo,
.encode_getdeviceinfo = nfsd4_block_encode_getdeviceinfo,
.proc_layoutget = nfsd4_block_proc_layoutget,
.encode_layoutget = nfsd4_block_encode_layoutget,
.proc_layoutcommit = nfsd4_block_proc_layoutcommit,
};
/*
* Write a page synchronously.
* Offset is the data offset within the page.
*/
static int
smb_writepage_sync(struct inode *inode, struct page *page,
unsigned long pageoffset, unsigned int count)
{
loff_t offset;
char *buffer = kmap(page) + pageoffset;
struct smb_sb_info *server = server_from_inode(inode);
unsigned int wsize = smb_get_wsize(server);
int ret = 0;
offset = ((loff_t)page->index << PAGE_CACHE_SHIFT) + pageoffset;
VERBOSE("file ino=%ld, fileid=%d, count=%d@%Ld, wsize=%d\n",
inode->i_ino, SMB_I(inode)->fileid, count, offset, wsize);
do {
int write_ret;
if (count < wsize)
wsize = count;
write_ret = server->ops->write(inode, offset, wsize, buffer);
if (write_ret < 0) {
PARANOIA("failed write, wsize=%d, write_ret=%d\n",
wsize, write_ret);
ret = write_ret;
break;
}
/* N.B. what if result < wsize?? */
#ifdef SMBFS_PARANOIA
if (write_ret < wsize)
PARANOIA("short write, wsize=%d, write_ret=%d\n",
wsize, write_ret);
#endif
buffer += wsize;
offset += wsize;
count -= wsize;
/*
* Update the inode now rather than waiting for a refresh.
*/
inode->i_mtime = inode->i_atime = current_fs_time(inode->i_sb);
SMB_I(inode)->flags |= SMB_F_LOCALWRITE;
if (offset > inode->i_size)
inode->i_size = offset;
} while (count);
kunmap(page);
return ret;
}
int
zpl_init_acl(struct inode *ip, struct inode *dir)
{
struct posix_acl *acl = NULL;
int error = 0;
if (ITOZSB(ip)->z_acl_type != ZFS_ACLTYPE_POSIXACL)
return (0);
if (!S_ISLNK(ip->i_mode)) {
if (ITOZSB(ip)->z_acl_type == ZFS_ACLTYPE_POSIXACL) {
acl = zpl_get_acl(dir, ACL_TYPE_DEFAULT);
if (IS_ERR(acl))
return (PTR_ERR(acl));
}
if (!acl) {
ip->i_mode &= ~current_umask();
ip->i_ctime = current_fs_time(ITOZSB(ip)->z_sb);
mark_inode_dirty(ip);
return (0);
}
}
if ((ITOZSB(ip)->z_acl_type == ZFS_ACLTYPE_POSIXACL) && acl) {
umode_t mode;
if (S_ISDIR(ip->i_mode)) {
error = zpl_set_acl(ip, ACL_TYPE_DEFAULT, acl);
if (error)
goto out;
}
mode = ip->i_mode;
error = posix_acl_create(&acl,GFP_KERNEL, &mode);
if (error >= 0) {
ip->i_mode = mode;
mark_inode_dirty(ip);
if (error > 0)
error = zpl_set_acl(ip, ACL_TYPE_ACCESS, acl);
}
}
out:
zpl_posix_acl_release(acl);
return (error);
}
static int
xfs_set_mode(struct inode *inode, umode_t mode)
{
int error = 0;
if (mode != inode->i_mode) {
struct iattr iattr;
iattr.ia_valid = ATTR_MODE | ATTR_CTIME;
iattr.ia_mode = mode;
iattr.ia_ctime = current_fs_time(inode->i_sb);
error = -xfs_setattr_nonsize(XFS_I(inode), &iattr, XFS_ATTR_NOACL);
}
return error;
}
/**
* sysfs_chmod_file - update the modified mode value on an object attribute.
* @kobj: object we're acting for.
* @attr: attribute descriptor.
* @mode: file permissions.
*
*/
int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode)
{
struct sysfs_dirent *victim_sd = NULL;
struct dentry *victim = NULL;
struct inode * inode;
struct iattr newattrs;
int rc;
rc = -ENOENT;
victim_sd = sysfs_get_dirent(kobj->sd, attr->name);
if (!victim_sd)
goto out;
mutex_lock(&sysfs_rename_mutex);
victim = sysfs_get_dentry(victim_sd);
mutex_unlock(&sysfs_rename_mutex);
if (IS_ERR(victim)) {
rc = PTR_ERR(victim);
victim = NULL;
goto out;
}
inode = victim->d_inode;
mutex_lock(&inode->i_mutex);
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
newattrs.ia_ctime = current_fs_time(inode->i_sb);
rc = sysfs_setattr(victim, &newattrs);
if (rc == 0) {
fsnotify_change(victim, newattrs.ia_valid);
mutex_lock(&sysfs_mutex);
victim_sd->s_mode = newattrs.ia_mode;
mutex_unlock(&sysfs_mutex);
}
mutex_unlock(&inode->i_mutex);
out:
dput(victim);
sysfs_put(victim_sd);
return rc;
}
/*
* Read a page synchronously.
*/
static int
smb_readpage_sync(struct dentry *dentry, struct page *page)
{
char *buffer = kmap(page);
loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
struct smb_sb_info *server = server_from_dentry(dentry);
unsigned int rsize = smb_get_rsize(server);
int count = PAGE_SIZE;
int result;
VERBOSE("file %s/%s, count=%d@%Ld, rsize=%d\n",
DENTRY_PATH(dentry), count, offset, rsize);
result = smb_open(dentry, SMB_O_RDONLY);
if (result < 0)
goto io_error;
do {
if (count < rsize)
rsize = count;
result = server->ops->read(dentry->d_inode,offset,rsize,buffer);
if (result < 0)
goto io_error;
count -= result;
offset += result;
buffer += result;
dentry->d_inode->i_atime =
current_fs_time(dentry->d_inode->i_sb);
if (result < rsize)
break;
} while (count);
memset(buffer, 0, count);
flush_dcache_page(page);
SetPageUptodate(page);
result = 0;
io_error:
kunmap(page);
unlock_page(page);
return result;
}
int cifs_rmdir(struct inode *inode, struct dentry *direntry)
{
int rc = 0;
int xid;
struct cifs_sb_info *cifs_sb;
struct cifsTconInfo *pTcon;
char *full_path = NULL;
struct cifsInodeInfo *cifsInode;
cFYI(1, (" cifs_rmdir, inode = 0x%p with ", inode));
xid = GetXid();
cifs_sb = CIFS_SB(inode->i_sb);
pTcon = cifs_sb->tcon;
down(&inode->i_sb->s_vfs_rename_sem);
full_path = build_path_from_dentry(direntry);
up(&inode->i_sb->s_vfs_rename_sem);
if (full_path == NULL) {
FreeXid(xid);
return -ENOMEM;
}
rc = CIFSSMBRmDir(xid, pTcon, full_path, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
if (!rc) {
inode->i_nlink--;
i_size_write(direntry->d_inode,0);
direntry->d_inode->i_nlink = 0;
}
cifsInode = CIFS_I(direntry->d_inode);
cifsInode->time = 0; /* force revalidate to go get info when
needed */
direntry->d_inode->i_ctime = inode->i_ctime = inode->i_mtime =
current_fs_time(inode->i_sb);
kfree(full_path);
FreeXid(xid);
return rc;
}
/*
* Transactional inode timestamp update. Requires the inode to be locked and
* joined to the transaction supplied. Relies on the transaction subsystem to
* track dirty state and update/writeback the inode accordingly.
*/
void
xfs_trans_ichgtime(
struct xfs_trans *tp,
struct xfs_inode *ip,
int flags)
{
struct inode *inode = VFS_I(ip);
struct timespec tv;
ASSERT(tp);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
tv = current_fs_time(inode->i_sb);
if (flags & XFS_ICHGTIME_MOD)
inode->i_mtime = tv;
if (flags & XFS_ICHGTIME_CHG)
inode->i_ctime = tv;
}
/* return 0 on success; non-zero otherwise */
static int orangefs_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
int ret;
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: called on %s\n"
" (inode %pU): Parent is %pU | fs_id %d\n",
__func__,
dentry->d_name.name,
get_khandle_from_ino(inode),
&parent->refn.khandle,
parent->refn.fs_id);
new_op = op_alloc(ORANGEFS_VFS_OP_REMOVE);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.remove.parent_refn = parent->refn;
strncpy(new_op->upcall.req.remove.d_name, dentry->d_name.name,
ORANGEFS_NAME_MAX);
ret = service_operation(new_op, "orangefs_unlink",
get_interruptible_flag(inode));
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: service_operation returned:%d:\n",
__func__,
ret);
op_release(new_op);
if (!ret) {
drop_nlink(inode);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
mark_inode_dirty_sync(dir);
}
return ret;
}
/*
* Change the requested timestamp in the given inode.
* We don't lock across timestamp updates, and we don't log them but
* we do record the fact that there is dirty information in core.
*/
void
xfs_ichgtime(
xfs_inode_t *ip,
int flags)
{
struct inode *inode = VFS_I(ip);
timespec_t tv;
int sync_it = 0;
tv = current_fs_time(inode->i_sb);
if ((flags & XFS_ICHGTIME_MOD) &&
!timespec_equal(&inode->i_mtime, &tv)) {
inode->i_mtime = tv;
ip->i_d.di_mtime.t_sec = (__int32_t)tv.tv_sec;
ip->i_d.di_mtime.t_nsec = (__int32_t)tv.tv_nsec;
sync_it = 1;
}
if ((flags & XFS_ICHGTIME_CHG) &&
!timespec_equal(&inode->i_ctime, &tv)) {
inode->i_ctime = tv;
ip->i_d.di_ctime.t_sec = (__int32_t)tv.tv_sec;
ip->i_d.di_ctime.t_nsec = (__int32_t)tv.tv_nsec;
sync_it = 1;
}
/*
* We update the i_update_core field _after_ changing
* the timestamps in order to coordinate properly with
* xfs_iflush() so that we don't lose timestamp updates.
* This keeps us from having to hold the inode lock
* while doing this. We use the SYNCHRONIZE macro to
* ensure that the compiler does not reorder the update
* of i_update_core above the timestamp updates above.
*/
if (sync_it) {
SYNCHRONIZE();
ip->i_update_core = 1;
xfs_mark_inode_dirty_sync(ip);
}
}
static __be32
nfsd4_block_proc_layoutcommit(struct inode *inode,
struct nfsd4_layoutcommit *lcp)
{
loff_t new_size = lcp->lc_last_wr + 1;
struct iattr iattr = { .ia_valid = 0 };
struct iomap *iomaps;
int nr_iomaps;
int error;
nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
if (nr_iomaps < 0)
return nfserrno(nr_iomaps);
if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
lcp->lc_mtime = current_fs_time(inode->i_sb);
iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
if (new_size > i_size_read(inode)) {
iattr.ia_valid |= ATTR_SIZE;
iattr.ia_size = new_size;
}
error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
nr_iomaps, &iattr);
kfree(iomaps);
return nfserrno(error);
}
const struct nfsd4_layout_ops bl_layout_ops = {
.proc_getdeviceinfo = nfsd4_block_proc_getdeviceinfo,
.encode_getdeviceinfo = nfsd4_block_encode_getdeviceinfo,
.proc_layoutget = nfsd4_block_proc_layoutget,
.encode_layoutget = nfsd4_block_encode_layoutget,
.proc_layoutcommit = nfsd4_block_proc_layoutcommit,
};
/** \<\<private\>\> Read function for TTY
* @TODO: Why is this copied here from kernel?
*
* @param *file - pointer to file we wanted to read from
* @param *buf - pointer to buffer in kernelspace witch will be filled with data
* @param count - buffer size
* @param *ppos - pointer to file offset
*
* @return Amount of bytes read or error
*/
static ssize_t proxyfs_tty_real_file_tty_read(struct file * file, char *buf, size_t count, loff_t *ppos)
{
int i;
struct tty_struct * tty;
struct inode *inode;
struct tty_ldisc *ld = NULL;
int state;
tty = (struct tty_struct *)file->private_data;
inode = file->f_path.dentry->d_inode;
//if (tty_paranoia_check(tty, inode, "tty_read"))
// return -EIO;
if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags)))
return -EIO;
/* We not want to wait for the line discipline to sort out in this
situation */
ld = tty_ldisc_ref(tty);
if(ld){
lock_kernel();
if (ld->ops->read){
state = current->state;
i = (ld->ops->read)(tty,file,buf,count);
current->state = state;
}
else
i = -EIO;
tty_ldisc_deref(ld);
unlock_kernel();
if (i > 0)
inode->i_atime = current_fs_time(inode->i_sb);
return i;
}
else
return -EAGAIN;
}
static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
int ret;
new_op = op_alloc(ORANGEFS_VFS_OP_MKDIR);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.mkdir.parent_refn = parent->refn;
fill_default_sys_attrs(new_op->upcall.req.mkdir.attributes,
ORANGEFS_TYPE_DIRECTORY, mode);
strncpy(new_op->upcall.req.mkdir.d_name,
dentry->d_name.name, ORANGEFS_NAME_MAX);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
"Mkdir Got ORANGEFS handle %pU on fsid %d\n",
&new_op->downcall.resp.mkdir.refn.khandle,
new_op->downcall.resp.mkdir.refn.fs_id);
if (ret < 0) {
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: failed with error code %d\n",
__func__, ret);
goto out;
}
inode = orangefs_new_inode(dir->i_sb, dir, S_IFDIR | mode, 0,
&new_op->downcall.resp.mkdir.refn);
if (IS_ERR(inode)) {
gossip_err("*** Failed to allocate orangefs dir inode\n");
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
"Assigned dir inode new number of %pU\n",
get_khandle_from_ino(inode));
d_instantiate(dentry, inode);
unlock_new_inode(inode);
dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"Inode (Directory) %pU -> %s\n",
get_khandle_from_ino(inode),
dentry->d_name.name);
/*
* NOTE: we have no good way to keep nlink consistent for directories
* across clients; keep constant at 1.
*/
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
mark_inode_dirty_sync(dir);
out:
op_release(new_op);
return ret;
}
/**
* notify_change - modify attributes of a filesytem object
* @dentry: object affected
* @iattr: new attributes
* @delegated_inode: returns inode, if the inode is delegated
*
* The caller must hold the i_mutex on the affected object.
*
* If notify_change discovers a delegation in need of breaking,
* it will return -EWOULDBLOCK and return a reference to the inode in
* delegated_inode. The caller should then break the delegation and
* retry. Because breaking a delegation may take a long time, the
* caller should drop the i_mutex before doing so.
*
* Alternatively, a caller may pass NULL for delegated_inode. This may
* be appropriate for callers that expect the underlying filesystem not
* to be NFS exported. Also, passing NULL is fine for callers holding
* the file open for write, as there can be no conflicting delegation in
* that case.
*/
int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode)
{
struct inode *inode = dentry->d_inode;
umode_t mode = inode->i_mode;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
WARN_ON_ONCE(!inode_is_locked(inode));
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
/*
* If utimes(2) and friends are called with times == NULL (or both
* times are UTIME_NOW), then we need to check for write permission
*/
if (ia_valid & ATTR_TOUCH) {
if (IS_IMMUTABLE(inode))
return -EPERM;
if (!inode_owner_or_capable(inode)) {
error = inode_permission(inode, MAY_WRITE);
if (error)
return error;
}
}
if ((ia_valid & ATTR_MODE)) {
umode_t amode = attr->ia_mode;
/* Flag setting protected by i_mutex */
if (is_sxid(amode))
inode->i_flags &= ~S_NOSEC;
}
now = current_fs_time(inode->i_sb);
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_PRIV) {
attr->ia_valid &= ~ATTR_KILL_PRIV;
ia_valid &= ~ATTR_KILL_PRIV;
error = security_inode_need_killpriv(dentry);
if (error > 0)
error = security_inode_killpriv(dentry);
if (error)
return error;
}
/*
* We now pass ATTR_KILL_S*ID to the lower level setattr function so
* that the function has the ability to reinterpret a mode change
* that's due to these bits. This adds an implicit restriction that
* no function will ever call notify_change with both ATTR_MODE and
* ATTR_KILL_S*ID set.
*/
if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
(ia_valid & ATTR_MODE))
BUG();
if (ia_valid & ATTR_KILL_SUID) {
if (mode & S_ISUID) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = (inode->i_mode & ~S_ISUID);
}
}
if (ia_valid & ATTR_KILL_SGID) {
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
return 0;
/*
* Verify that uid/gid changes are valid in the target
* namespace of the superblock.
*/
if (ia_valid & ATTR_UID &&
!kuid_has_mapping(inode->i_sb->s_user_ns, attr->ia_uid))
return -EOVERFLOW;
if (ia_valid & ATTR_GID &&
!kgid_has_mapping(inode->i_sb->s_user_ns, attr->ia_gid))
return -EOVERFLOW;
/* Don't allow modifications of files with invalid uids or
* gids unless those uids & gids are being made valid.
*/
if (!(ia_valid & ATTR_UID) && !uid_valid(inode->i_uid))
return -EOVERFLOW;
if (!(ia_valid & ATTR_GID) && !gid_valid(inode->i_gid))
return -EOVERFLOW;
error = security_inode_setattr(dentry, attr);
if (error)
return error;
error = try_break_deleg(inode, delegated_inode);
if (error)
return error;
if (inode->i_op->setattr)
error = inode->i_op->setattr(dentry, attr);
else
error = simple_setattr(dentry, attr);
if (!error) {
fsnotify_change(dentry, ia_valid);
ima_inode_post_setattr(dentry);
evm_inode_post_setattr(dentry, ia_valid);
}
return error;
}
static int orangefs_symlink(struct inode *dir,
struct dentry *dentry,
const char *symname)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
int mode = 755;
int ret;
gossip_debug(GOSSIP_NAME_DEBUG, "%s: called\n", __func__);
if (!symname)
return -EINVAL;
if (strlen(symname)+1 > ORANGEFS_NAME_MAX)
return -ENAMETOOLONG;
new_op = op_alloc(ORANGEFS_VFS_OP_SYMLINK);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.sym.parent_refn = parent->refn;
fill_default_sys_attrs(new_op->upcall.req.sym.attributes,
ORANGEFS_TYPE_SYMLINK,
mode);
strncpy(new_op->upcall.req.sym.entry_name,
dentry->d_name.name,
ORANGEFS_NAME_MAX);
strncpy(new_op->upcall.req.sym.target, symname, ORANGEFS_NAME_MAX);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
"Symlink Got ORANGEFS handle %pU on fsid %d (ret=%d)\n",
&new_op->downcall.resp.sym.refn.khandle,
new_op->downcall.resp.sym.refn.fs_id, ret);
if (ret < 0) {
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: failed with error code %d\n",
__func__, ret);
goto out;
}
inode = orangefs_new_inode(dir->i_sb, dir, S_IFLNK | mode, 0,
&new_op->downcall.resp.sym.refn);
if (IS_ERR(inode)) {
gossip_err
("*** Failed to allocate orangefs symlink inode\n");
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
"Assigned symlink inode new number of %pU\n",
get_khandle_from_ino(inode));
d_instantiate(dentry, inode);
unlock_new_inode(inode);
dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"Inode (Symlink) %pU -> %s\n",
get_khandle_from_ino(inode),
dentry->d_name.name);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
mark_inode_dirty_sync(dir);
ret = 0;
out:
op_release(new_op);
return ret;
}
/*
* 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;
}
/*
* Get a newly allocated inode to go with a negative dentry.
*/
static int orangefs_create(struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool exclusive)
{
struct orangefs_inode_s *parent = ORANGEFS_I(dir);
struct orangefs_kernel_op_s *new_op;
struct inode *inode;
int ret;
gossip_debug(GOSSIP_NAME_DEBUG, "%s: %s\n",
__func__,
dentry->d_name.name);
new_op = op_alloc(ORANGEFS_VFS_OP_CREATE);
if (!new_op)
return -ENOMEM;
new_op->upcall.req.create.parent_refn = parent->refn;
fill_default_sys_attrs(new_op->upcall.req.create.attributes,
ORANGEFS_TYPE_METAFILE, mode);
strncpy(new_op->upcall.req.create.d_name,
dentry->d_name.name, ORANGEFS_NAME_MAX);
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: %s: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
__func__,
dentry->d_name.name,
&new_op->downcall.resp.create.refn.khandle,
new_op->downcall.resp.create.refn.fs_id,
new_op,
ret);
if (ret < 0)
goto out;
inode = orangefs_new_inode(dir->i_sb, dir, S_IFREG | mode, 0,
&new_op->downcall.resp.create.refn);
if (IS_ERR(inode)) {
gossip_err("%s: Failed to allocate inode for file :%s:\n",
__func__,
dentry->d_name.name);
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: Assigned inode :%pU: for file :%s:\n",
__func__,
get_khandle_from_ino(inode),
dentry->d_name.name);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: dentry instantiated for %s\n",
__func__,
dentry->d_name.name);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
mark_inode_dirty_sync(dir);
ret = 0;
out:
op_release(new_op);
gossip_debug(GOSSIP_NAME_DEBUG,
"%s: %s: returning %d\n",
__func__,
dentry->d_name.name,
ret);
return ret;
}
/*
* Allocate a new inode with the passed id and ops.
*/
static struct inode *
zfsctl_inode_alloc(zfs_sb_t *zsb, uint64_t id,
const struct file_operations *fops, const struct inode_operations *ops)
{
struct timespec now = current_fs_time(zsb->z_sb);
struct inode *ip;
znode_t *zp;
ip = new_inode(zsb->z_sb);
if (ip == NULL)
return (NULL);
zp = ITOZ(ip);
ASSERT3P(zp->z_dirlocks, ==, NULL);
ASSERT3P(zp->z_acl_cached, ==, NULL);
ASSERT3P(zp->z_xattr_cached, ==, NULL);
zp->z_id = id;
zp->z_unlinked = 0;
zp->z_atime_dirty = 0;
zp->z_zn_prefetch = 0;
zp->z_moved = 0;
zp->z_sa_hdl = NULL;
zp->z_blksz = 0;
zp->z_seq = 0;
zp->z_mapcnt = 0;
zp->z_gen = 0;
zp->z_size = 0;
zp->z_atime[0] = 0;
zp->z_atime[1] = 0;
zp->z_links = 0;
zp->z_pflags = 0;
zp->z_uid = 0;
zp->z_gid = 0;
zp->z_mode = 0;
zp->z_sync_cnt = 0;
zp->z_is_zvol = B_FALSE;
zp->z_is_mapped = B_FALSE;
zp->z_is_ctldir = B_TRUE;
zp->z_is_sa = B_FALSE;
zp->z_is_stale = B_FALSE;
ip->i_ino = id;
ip->i_mode = (S_IFDIR | S_IRUGO | S_IXUGO);
ip->i_uid = SUID_TO_KUID(0);
ip->i_gid = SGID_TO_KGID(0);
ip->i_blkbits = SPA_MINBLOCKSHIFT;
ip->i_atime = now;
ip->i_mtime = now;
ip->i_ctime = now;
ip->i_fop = fops;
ip->i_op = ops;
if (insert_inode_locked(ip)) {
unlock_new_inode(ip);
iput(ip);
return (NULL);
}
mutex_enter(&zsb->z_znodes_lock);
list_insert_tail(&zsb->z_all_znodes, zp);
zsb->z_nr_znodes++;
membar_producer();
mutex_exit(&zsb->z_znodes_lock);
unlock_new_inode(ip);
return (ip);
}
/*
* 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;
}
int
zpl_set_acl(struct inode *ip, int type, struct posix_acl *acl)
{
struct super_block *sb = ITOZSB(ip)->z_sb;
char *name, *value = NULL;
int error = 0;
size_t size = 0;
if (S_ISLNK(ip->i_mode))
return (-EOPNOTSUPP);
switch(type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
if (acl) {
zpl_equivmode_t mode = ip->i_mode;
error = posix_acl_equiv_mode(acl, &mode);
if (error < 0) {
return (error);
} else {
/*
* The mode bits will have been set by
* ->zfs_setattr()->zfs_acl_chmod_setattr()
* using the ZFS ACL conversion. If they
* differ from the Posix ACL conversion dirty
* the inode to write the Posix mode bits.
*/
if (ip->i_mode != mode) {
ip->i_mode = mode;
ip->i_ctime = current_fs_time(sb);
mark_inode_dirty(ip);
}
if (error == 0)
acl = NULL;
}
}
break;
case ACL_TYPE_DEFAULT:
name = POSIX_ACL_XATTR_DEFAULT;
if (!S_ISDIR(ip->i_mode))
return (acl ? -EACCES : 0);
break;
default:
return (-EINVAL);
}
if (acl) {
size = posix_acl_xattr_size(acl->a_count);
value = kmem_alloc(size, KM_SLEEP);
error = zpl_acl_to_xattr(acl, value, size);
if (error < 0) {
kmem_free(value, size);
return (error);
}
}
error = zpl_xattr_set(ip, name, value, size, 0);
if (value)
kmem_free(value, size);
if (!error) {
if (acl)
zpl_set_cached_acl(ip, type, acl);
else
zpl_forget_cached_acl(ip, type);
}
return (error);
}
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
mode_t mode;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
mode = inode->i_mode;
now = current_fs_time(inode->i_sb);
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_SUID) {
attr->ia_valid &= ~ATTR_KILL_SUID;
if (mode & S_ISUID) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISUID;
}
}
if (ia_valid & ATTR_KILL_SGID) {
attr->ia_valid &= ~ ATTR_KILL_SGID;
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!attr->ia_valid)
return 0;
if (ia_valid & ATTR_SIZE)
down_write(&dentry->d_inode->i_alloc_sem);
if (inode->i_op && inode->i_op->setattr) {
error = security_inode_setattr(dentry, attr);
if (!error)
error = inode->i_op->setattr(dentry, attr);
} else {
error = inode_change_ok(inode, attr);
if (!error)
error = security_inode_setattr(dentry, attr);
if (!error) {
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid))
error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
if (!error)
error = inode_setattr(inode, attr);
}
}
if (ia_valid & ATTR_SIZE)
up_write(&dentry->d_inode->i_alloc_sem);
if (!error)
fsnotify_change(dentry, ia_valid);
return error;
}
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
umode_t mode = inode->i_mode;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
if ((ia_valid & ATTR_SIZE) && IS_I_VERSION(inode)) {
if (attr->ia_size != inode->i_size)
inode_inc_iversion(inode);
}
if ((ia_valid & ATTR_MODE)) {
umode_t amode = attr->ia_mode;
/* Flag setting protected by i_mutex */
if (is_sxid(amode))
inode->i_flags &= ~S_NOSEC;
}
now = current_fs_time(inode->i_sb);
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_PRIV) {
attr->ia_valid &= ~ATTR_KILL_PRIV;
ia_valid &= ~ATTR_KILL_PRIV;
error = security_inode_need_killpriv(dentry);
if (error > 0)
error = security_inode_killpriv(dentry);
if (error)
return error;
}
/*
* We now pass ATTR_KILL_S*ID to the lower level setattr function so
* that the function has the ability to reinterpret a mode change
* that's due to these bits. This adds an implicit restriction that
* no function will ever call notify_change with both ATTR_MODE and
* ATTR_KILL_S*ID set.
*/
if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
(ia_valid & ATTR_MODE))
BUG();
if (ia_valid & ATTR_KILL_SUID) {
if (mode & S_ISUID) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = (inode->i_mode & ~S_ISUID);
}
}
if (ia_valid & ATTR_KILL_SGID) {
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
return 0;
error = security_inode_setattr(dentry, attr);
if (error)
return error;
if (inode->i_op->setattr)
error = inode->i_op->setattr(dentry, attr);
else
error = simple_setattr(dentry, attr);
if (!error) {
fsnotify_change(dentry, ia_valid);
ima_inode_post_setattr(dentry);
evm_inode_post_setattr(dentry, ia_valid);
}
return error;
}
/*
* NAME: jfs_rename
*
* FUNCTION: rename a file or directory
*/
static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct btstack btstack;
ino_t ino;
struct component_name new_dname;
struct inode *new_ip;
struct component_name old_dname;
struct inode *old_ip;
int rc;
tid_t tid;
struct tlock *tlck;
struct dt_lock *dtlck;
struct lv *lv;
int ipcount;
struct inode *iplist[4];
struct tblock *tblk;
s64 new_size = 0;
int commit_flag;
jfs_info("jfs_rename: %s %s", old_dentry->d_name.name,
new_dentry->d_name.name);
dquot_initialize(old_dir);
dquot_initialize(new_dir);
old_ip = old_dentry->d_inode;
new_ip = new_dentry->d_inode;
if ((rc = get_UCSname(&old_dname, old_dentry)))
goto out1;
if ((rc = get_UCSname(&new_dname, new_dentry)))
goto out2;
/*
* Make sure source inode number is what we think it is
*/
rc = dtSearch(old_dir, &old_dname, &ino, &btstack, JFS_LOOKUP);
if (rc || (ino != old_ip->i_ino)) {
rc = -ENOENT;
goto out3;
}
/*
* Make sure dest inode number (if any) is what we think it is
*/
rc = dtSearch(new_dir, &new_dname, &ino, &btstack, JFS_LOOKUP);
if (!rc) {
if ((!new_ip) || (ino != new_ip->i_ino)) {
rc = -ESTALE;
goto out3;
}
} else if (rc != -ENOENT)
goto out3;
else if (new_ip) {
/* no entry exists, but one was expected */
rc = -ESTALE;
goto out3;
}
if (S_ISDIR(old_ip->i_mode)) {
if (new_ip) {
if (!dtEmpty(new_ip)) {
rc = -ENOTEMPTY;
goto out3;
}
} else if ((new_dir != old_dir) &&
(new_dir->i_nlink == JFS_LINK_MAX)) {
rc = -EMLINK;
goto out3;
}
} else if (new_ip) {
IWRITE_LOCK(new_ip, RDWRLOCK_NORMAL);
/* Init inode for quota operations. */
dquot_initialize(new_ip);
}
/*
* The real work starts here
*/
tid = txBegin(new_dir->i_sb, 0);
/*
* How do we know the locking is safe from deadlocks?
* The vfs does the hard part for us. Any time we are taking nested
* commit_mutexes, the vfs already has i_mutex held on the parent.
* Here, the vfs has already taken i_mutex on both old_dir and new_dir.
*/
mutex_lock_nested(&JFS_IP(new_dir)->commit_mutex, COMMIT_MUTEX_PARENT);
mutex_lock_nested(&JFS_IP(old_ip)->commit_mutex, COMMIT_MUTEX_CHILD);
if (old_dir != new_dir)
mutex_lock_nested(&JFS_IP(old_dir)->commit_mutex,
COMMIT_MUTEX_SECOND_PARENT);
if (new_ip) {
mutex_lock_nested(&JFS_IP(new_ip)->commit_mutex,
COMMIT_MUTEX_VICTIM);
/*
* Change existing directory entry to new inode number
*/
ino = new_ip->i_ino;
rc = dtModify(tid, new_dir, &new_dname, &ino,
old_ip->i_ino, JFS_RENAME);
if (rc)
goto out4;
drop_nlink(new_ip);
if (S_ISDIR(new_ip->i_mode)) {
drop_nlink(new_ip);
if (new_ip->i_nlink) {
mutex_unlock(&JFS_IP(new_ip)->commit_mutex);
if (old_dir != new_dir)
mutex_unlock(&JFS_IP(old_dir)->commit_mutex);
mutex_unlock(&JFS_IP(old_ip)->commit_mutex);
mutex_unlock(&JFS_IP(new_dir)->commit_mutex);
if (!S_ISDIR(old_ip->i_mode) && new_ip)
IWRITE_UNLOCK(new_ip);
jfs_error(new_ip->i_sb,
"jfs_rename: new_ip->i_nlink != 0");
return -EIO;
}
tblk = tid_to_tblock(tid);
tblk->xflag |= COMMIT_DELETE;
tblk->u.ip = new_ip;
} else if (new_ip->i_nlink == 0) {
assert(!test_cflag(COMMIT_Nolink, new_ip));
/* free block resources */
if ((new_size = commitZeroLink(tid, new_ip)) < 0) {
txAbort(tid, 1); /* Marks FS Dirty */
rc = new_size;
goto out4;
}
tblk = tid_to_tblock(tid);
tblk->xflag |= COMMIT_DELETE;
tblk->u.ip = new_ip;
} else {
new_ip->i_ctime = CURRENT_TIME;
mark_inode_dirty(new_ip);
}
} else {
/*
* Add new directory entry
*/
rc = dtSearch(new_dir, &new_dname, &ino, &btstack,
JFS_CREATE);
if (rc) {
jfs_err("jfs_rename didn't expect dtSearch to fail "
"w/rc = %d", rc);
goto out4;
}
ino = old_ip->i_ino;
rc = dtInsert(tid, new_dir, &new_dname, &ino, &btstack);
if (rc) {
if (rc == -EIO)
jfs_err("jfs_rename: dtInsert returned -EIO");
goto out4;
}
if (S_ISDIR(old_ip->i_mode))
inc_nlink(new_dir);
}
/*
* Remove old directory entry
*/
ino = old_ip->i_ino;
rc = dtDelete(tid, old_dir, &old_dname, &ino, JFS_REMOVE);
if (rc) {
jfs_err("jfs_rename did not expect dtDelete to return rc = %d",
rc);
txAbort(tid, 1); /* Marks Filesystem dirty */
goto out4;
}
if (S_ISDIR(old_ip->i_mode)) {
drop_nlink(old_dir);
if (old_dir != new_dir) {
/*
* Change inode number of parent for moved directory
*/
JFS_IP(old_ip)->i_dtroot.header.idotdot =
cpu_to_le32(new_dir->i_ino);
/* Linelock header of dtree */
tlck = txLock(tid, old_ip,
(struct metapage *) &JFS_IP(old_ip)->bxflag,
tlckDTREE | tlckBTROOT | tlckRELINK);
dtlck = (struct dt_lock *) & tlck->lock;
ASSERT(dtlck->index == 0);
lv = & dtlck->lv[0];
lv->offset = 0;
lv->length = 1;
dtlck->index++;
}
}
/*
* Update ctime on changed/moved inodes & mark dirty
*/
old_ip->i_ctime = CURRENT_TIME;
mark_inode_dirty(old_ip);
new_dir->i_ctime = new_dir->i_mtime = current_fs_time(new_dir->i_sb);
mark_inode_dirty(new_dir);
/* Build list of inodes modified by this transaction */
ipcount = 0;
iplist[ipcount++] = old_ip;
if (new_ip)
iplist[ipcount++] = new_ip;
iplist[ipcount++] = old_dir;
if (old_dir != new_dir) {
iplist[ipcount++] = new_dir;
old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME;
mark_inode_dirty(old_dir);
}
/*
* Incomplete truncate of file data can
* result in timing problems unless we synchronously commit the
* transaction.
*/
if (new_size)
commit_flag = COMMIT_SYNC;
else
commit_flag = 0;
rc = txCommit(tid, ipcount, iplist, commit_flag);
out4:
txEnd(tid);
if (new_ip)
mutex_unlock(&JFS_IP(new_ip)->commit_mutex);
if (old_dir != new_dir)
mutex_unlock(&JFS_IP(old_dir)->commit_mutex);
mutex_unlock(&JFS_IP(old_ip)->commit_mutex);
mutex_unlock(&JFS_IP(new_dir)->commit_mutex);
while (new_size && (rc == 0)) {
tid = txBegin(new_ip->i_sb, 0);
mutex_lock(&JFS_IP(new_ip)->commit_mutex);
new_size = xtTruncate_pmap(tid, new_ip, new_size);
if (new_size < 0) {
txAbort(tid, 1);
rc = new_size;
} else
rc = txCommit(tid, 1, &new_ip, COMMIT_SYNC);
txEnd(tid);
mutex_unlock(&JFS_IP(new_ip)->commit_mutex);
}
if (new_ip && (new_ip->i_nlink == 0))
set_cflag(COMMIT_Nolink, new_ip);
out3:
free_UCSname(&new_dname);
out2:
free_UCSname(&old_dname);
out1:
if (new_ip && !S_ISDIR(new_ip->i_mode))
IWRITE_UNLOCK(new_ip);
/*
* Truncating the directory index table is not guaranteed. It
* may need to be done iteratively
*/
if (test_cflag(COMMIT_Stale, old_dir)) {
if (old_dir->i_size > 1)
jfs_truncate_nolock(old_dir, 0);
clear_cflag(COMMIT_Stale, old_dir);
}
jfs_info("jfs_rename: returning %d", rc);
return rc;
}
struct inode *udf_new_inode(struct inode *dir, umode_t mode, int *err)
{
struct super_block *sb = dir->i_sb;
struct udf_sb_info *sbi = UDF_SB(sb);
struct inode *inode;
int block;
uint32_t start = UDF_I(dir)->i_location.logicalBlockNum;
struct udf_inode_info *iinfo;
struct udf_inode_info *dinfo = UDF_I(dir);
inode = new_inode(sb);
if (!inode) {
*err = -ENOMEM;
return NULL;
}
*err = -ENOSPC;
iinfo = UDF_I(inode);
if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_EXTENDED_FE)) {
iinfo->i_efe = 1;
if (UDF_VERS_USE_EXTENDED_FE > sbi->s_udfrev)
sbi->s_udfrev = UDF_VERS_USE_EXTENDED_FE;
iinfo->i_ext.i_data = kzalloc(inode->i_sb->s_blocksize -
sizeof(struct extendedFileEntry),
GFP_KERNEL);
} else {
iinfo->i_efe = 0;
iinfo->i_ext.i_data = kzalloc(inode->i_sb->s_blocksize -
sizeof(struct fileEntry),
GFP_KERNEL);
}
if (!iinfo->i_ext.i_data) {
iput(inode);
*err = -ENOMEM;
return NULL;
}
block = udf_new_block(dir->i_sb, NULL,
dinfo->i_location.partitionReferenceNum,
start, err);
if (*err) {
iput(inode);
return NULL;
}
if (sbi->s_lvid_bh) {
struct logicalVolIntegrityDescImpUse *lvidiu;
iinfo->i_unique = lvid_get_unique_id(sb);
mutex_lock(&sbi->s_alloc_mutex);
lvidiu = udf_sb_lvidiu(sbi);
if (S_ISDIR(mode))
le32_add_cpu(&lvidiu->numDirs, 1);
else
le32_add_cpu(&lvidiu->numFiles, 1);
udf_updated_lvid(sb);
mutex_unlock(&sbi->s_alloc_mutex);
}
inode_init_owner(inode, dir, mode);
iinfo->i_location.logicalBlockNum = block;
iinfo->i_location.partitionReferenceNum =
dinfo->i_location.partitionReferenceNum;
inode->i_ino = udf_get_lb_pblock(sb, &iinfo->i_location, 0);
inode->i_blocks = 0;
iinfo->i_lenEAttr = 0;
iinfo->i_lenAlloc = 0;
iinfo->i_use = 0;
iinfo->i_checkpoint = 1;
if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_AD_IN_ICB))
iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
else if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
else
iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
inode->i_mtime = inode->i_atime = inode->i_ctime =
iinfo->i_crtime = current_fs_time(inode->i_sb);
insert_inode_hash(inode);
mark_inode_dirty(inode);
*err = 0;
return inode;
}
