static int propagate_one(struct mount *m)
{
struct mount *child;
int type;
/* skip ones added by this propagate_mnt() */
if (IS_MNT_NEW(m))
return 0;
/* skip if mountpoint isn't covered by it */
if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
return 0;
if (m->mnt_group_id == last_dest->mnt_group_id) {
type = CL_MAKE_SHARED;
} else {
struct mount *n, *p;
for (n = m; ; n = p) {
p = n->mnt_master;
if (p == dest_master || IS_MNT_MARKED(p)) {
while (last_dest->mnt_master != p) {
last_source = last_source->mnt_master;
last_dest = last_source->mnt_parent;
}
if (n->mnt_group_id != last_dest->mnt_group_id) {
last_source = last_source->mnt_master;
last_dest = last_source->mnt_parent;
}
break;
}
}
type = CL_SLAVE;
/* beginning of peer group among the slaves? */
if (IS_MNT_SHARED(m))
type |= CL_MAKE_SHARED;
}
/* Notice when we are propagating across user namespaces */
if (m->mnt_ns->user_ns != user_ns)
type |= CL_UNPRIVILEGED;
child = copy_tree(last_source, last_source->mnt.mnt_root, type);
if (IS_ERR(child))
return PTR_ERR(child);
child->mnt.mnt_flags &= ~MNT_LOCKED;
mnt_set_mountpoint(m, mp, child);
last_dest = m;
last_source = child;
if (m->mnt_master != dest_master) {
read_seqlock_excl(&mount_lock);
SET_MNT_MARK(m->mnt_master);
read_sequnlock_excl(&mount_lock);
}
hlist_add_head(&child->mnt_hash, list);
return 0;
}
/*
* mount 'source_mnt' under the destination 'dest_mnt' at
* dentry 'dest_dentry'. And propagate that mount to
* all the peer and slave mounts of 'dest_mnt'.
* Link all the new mounts into a propagation tree headed at
* source_mnt. Also link all the new mounts using ->mnt_list
* headed at source_mnt's ->mnt_list
*
* @dest_mnt: destination mount.
* @dest_dentry: destination dentry.
* @source_mnt: source mount.
* @tree_list : list of heads of trees to be attached.
*/
int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
struct mount *source_mnt, struct hlist_head *tree_list)
{
struct mount *m, *n;
int ret = 0;
/*
* we don't want to bother passing tons of arguments to
* propagate_one(); everything is serialized by namespace_sem,
* so globals will do just fine.
*/
user_ns = current->nsproxy->mnt_ns->user_ns;
last_dest = dest_mnt;
last_source = source_mnt;
mp = dest_mp;
list = tree_list;
dest_master = dest_mnt->mnt_master;
/* all peers of dest_mnt, except dest_mnt itself */
for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
ret = propagate_one(n);
if (ret)
goto out;
}
/* all slave groups */
for (m = next_group(dest_mnt, dest_mnt); m;
m = next_group(m, dest_mnt)) {
/* everything in that slave group */
n = m;
do {
ret = propagate_one(n);
if (ret)
goto out;
n = next_peer(n);
} while (n != m);
}
out:
read_seqlock_excl(&mount_lock);
hlist_for_each_entry(n, tree_list, mnt_hash) {
m = n->mnt_parent;
if (m->mnt_master != dest_mnt->mnt_master)
CLEAR_MNT_MARK(m->mnt_master);
}
/*
* validate a vnode/inode
* - there are several things we need to check
* - parent dir data changes (rm, rmdir, rename, mkdir, create, link,
* symlink)
* - parent dir metadata changed (security changes)
* - dentry data changed (write, truncate)
* - dentry metadata changed (security changes)
*/
int afs_validate(struct afs_vnode *vnode, struct key *key)
{
time64_t now = ktime_get_real_seconds();
bool valid = false;
int ret;
_enter("{v={%x:%u} fl=%lx},%x",
vnode->fid.vid, vnode->fid.vnode, vnode->flags,
key_serial(key));
/* Quickly check the callback state. Ideally, we'd use read_seqbegin
* here, but we have no way to pass the net namespace to the RCU
* cleanup for the server record.
*/
read_seqlock_excl(&vnode->cb_lock);
if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break) {
vnode->cb_s_break = vnode->cb_interest->server->cb_s_break;
} else if (!test_bit(AFS_VNODE_DIR_MODIFIED, &vnode->flags) &&
!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) &&
vnode->cb_expires_at - 10 > now) {
valid = true;
}
} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
valid = true;
}
read_sequnlock_excl(&vnode->cb_lock);
if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
clear_nlink(&vnode->vfs_inode);
if (valid)
goto valid;
mutex_lock(&vnode->validate_lock);
/* if the promise has expired, we need to check the server again to get
* a new promise - note that if the (parent) directory's metadata was
* changed then the security may be different and we may no longer have
* access */
if (!test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
_debug("not promised");
ret = afs_fetch_status(vnode, key);
if (ret < 0) {
if (ret == -ENOENT) {
set_bit(AFS_VNODE_DELETED, &vnode->flags);
ret = -ESTALE;
}
goto error_unlock;
}
_debug("new promise [fl=%lx]", vnode->flags);
}
if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
_debug("file already deleted");
ret = -ESTALE;
goto error_unlock;
}
/* if the vnode's data version number changed then its contents are
* different */
if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
afs_zap_data(vnode);
clear_bit(AFS_VNODE_DIR_MODIFIED, &vnode->flags);
mutex_unlock(&vnode->validate_lock);
valid:
_leave(" = 0");
return 0;
error_unlock:
mutex_unlock(&vnode->validate_lock);
_leave(" = %d", ret);
return ret;
}
/*
* Manage the records of cells known to a network namespace. This includes
* updating the DNS records and garbage collecting unused cells that were
* automatically added.
*
* Note that constructed cell records may only be removed from net->cells by
* this work item, so it is safe for this work item to stash a cursor pointing
* into the tree and then return to caller (provided it skips cells that are
* still under construction).
*
* Note also that we were given an increment on net->cells_outstanding by
* whoever queued us that we need to deal with before returning.
*/
void afs_manage_cells(struct work_struct *work)
{
struct afs_net *net = container_of(work, struct afs_net, cells_manager);
struct rb_node *cursor;
time64_t now = ktime_get_real_seconds(), next_manage = TIME64_MAX;
bool purging = !net->live;
_enter("");
/* Trawl the cell database looking for cells that have expired from
* lack of use and cells whose DNS results have expired and dispatch
* their managers.
*/
read_seqlock_excl(&net->cells_lock);
for (cursor = rb_first(&net->cells); cursor; cursor = rb_next(cursor)) {
struct afs_cell *cell =
rb_entry(cursor, struct afs_cell, net_node);
unsigned usage;
bool sched_cell = false;
usage = atomic_read(&cell->usage);
_debug("manage %s %u", cell->name, usage);
ASSERTCMP(usage, >=, 1);
if (purging) {
if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags))
usage = atomic_dec_return(&cell->usage);
ASSERTCMP(usage, ==, 1);
}
if (usage == 1) {
time64_t expire_at = cell->last_inactive;
if (!test_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags) &&
!test_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags))
expire_at += afs_cell_gc_delay;
if (purging || expire_at <= now)
sched_cell = true;
else if (expire_at < next_manage)
next_manage = expire_at;
}
if (!purging) {
if (cell->dns_expiry <= now)
sched_cell = true;
else if (cell->dns_expiry <= next_manage)
next_manage = cell->dns_expiry;
}
if (sched_cell)
queue_work(afs_wq, &cell->manager);
}
read_sequnlock_excl(&net->cells_lock);
/* Update the timer on the way out. We have to pass an increment on
* cells_outstanding in the namespace that we are in to the timer or
* the work scheduler.
*/
if (!purging && next_manage < TIME64_MAX) {
now = ktime_get_real_seconds();
if (next_manage - now <= 0) {
if (queue_work(afs_wq, &net->cells_manager))
atomic_inc(&net->cells_outstanding);
} else {
afs_set_cell_timer(net, next_manage - now);
}
}
afs_dec_cells_outstanding(net);
_leave(" [%d]", atomic_read(&net->cells_outstanding));
}
/*
* map the AFS file status to the inode member variables
*/
static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
{
struct inode *inode = AFS_VNODE_TO_I(vnode);
bool changed;
_debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu",
vnode->status.type,
vnode->status.nlink,
(unsigned long long) vnode->status.size,
vnode->status.data_version,
vnode->status.mode);
read_seqlock_excl(&vnode->cb_lock);
switch (vnode->status.type) {
case AFS_FTYPE_FILE:
inode->i_mode = S_IFREG | vnode->status.mode;
inode->i_op = &afs_file_inode_operations;
inode->i_fop = &afs_file_operations;
break;
case AFS_FTYPE_DIR:
inode->i_mode = S_IFDIR | vnode->status.mode;
inode->i_op = &afs_dir_inode_operations;
inode->i_fop = &afs_dir_file_operations;
break;
case AFS_FTYPE_SYMLINK:
/* Symlinks with a mode of 0644 are actually mountpoints. */
if ((vnode->status.mode & 0777) == 0644) {
inode->i_flags |= S_AUTOMOUNT;
set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
inode->i_mode = S_IFDIR | 0555;
inode->i_op = &afs_mntpt_inode_operations;
inode->i_fop = &afs_mntpt_file_operations;
} else {
inode->i_mode = S_IFLNK | vnode->status.mode;
inode->i_op = &afs_symlink_inode_operations;
}
inode_nohighmem(inode);
break;
default:
printk("kAFS: AFS vnode with undefined type\n");
read_sequnlock_excl(&vnode->cb_lock);
return -EBADMSG;
}
changed = (vnode->status.size != inode->i_size);
set_nlink(inode, vnode->status.nlink);
inode->i_uid = vnode->status.owner;
inode->i_gid = vnode->status.group;
inode->i_size = vnode->status.size;
inode->i_ctime.tv_sec = vnode->status.mtime_client;
inode->i_ctime.tv_nsec = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime;
inode->i_blocks = 0;
inode->i_generation = vnode->fid.unique;
inode_set_iversion_raw(inode, vnode->status.data_version);
inode->i_mapping->a_ops = &afs_fs_aops;
read_sequnlock_excl(&vnode->cb_lock);
#ifdef CONFIG_AFS_FSCACHE
if (changed)
fscache_attr_changed(vnode->cache);
#endif
return 0;
}