*/
#include <linux/config.h>
+#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/smp_lock.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/mount.h>
-#include <linux/vs_base.h>
+#include <linux/vserver/namespace.h>
+#include <linux/vserver/xid.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#endif
/* spinlock for vfsmount related operations, inplace of dcache_lock */
-spinlock_t vfsmount_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
+ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
static struct list_head *mount_hashtable;
static int hash_mask, hash_bits;
INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_mounts);
INIT_LIST_HEAD(&mnt->mnt_list);
+ INIT_LIST_HEAD(&mnt->mnt_fslink);
if (name) {
int size = strlen(name)+1;
char *newname = kmalloc(size, GFP_KERNEL);
return found;
}
-EXPORT_SYMBOL(lookup_mnt);
-
-static int check_mnt(struct vfsmount *mnt)
+static inline int check_mnt(struct vfsmount *mnt)
{
- spin_lock(&vfsmount_lock);
- while (mnt->mnt_parent != mnt)
- mnt = mnt->mnt_parent;
- spin_unlock(&vfsmount_lock);
- return mnt == current->namespace->root;
+ return mnt->mnt_namespace == current->namespace;
}
static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd)
mnt->mnt_root = dget(root);
mnt->mnt_mountpoint = mnt->mnt_root;
mnt->mnt_parent = mnt;
+ mnt->mnt_namespace = old->mnt_namespace;
+ mnt->mnt_xid = old->mnt_xid;
+
+ /* stick the duplicate mount on the same expiry list
+ * as the original if that was on one */
+ spin_lock(&vfsmount_lock);
+ if (!list_empty(&old->mnt_fslink))
+ list_add(&mnt->mnt_fslink, &old->mnt_fslink);
+ spin_unlock(&vfsmount_lock);
}
return mnt;
}
seq_escape(m, s, " \t\n\\");
}
+static int mnt_is_reachable(struct vfsmount *mnt)
+{
+ struct vfsmount *root_mnt;
+ struct dentry *root, *point;
+ int ret;
+
+ if (!mnt)
+ return 1;
+ if (mnt == mnt->mnt_namespace->root)
+ return 1;
+
+ spin_lock(&dcache_lock);
+ root_mnt = current->fs->rootmnt;
+ root = current->fs->root;
+ point = root;
+
+ while ((mnt != mnt->mnt_parent) && (mnt != root_mnt)) {
+ point = mnt->mnt_mountpoint;
+ mnt = mnt->mnt_parent;
+ }
+
+ ret = (mnt == root_mnt) && is_subdir(point, root);
+
+ spin_unlock(&dcache_lock);
+
+ return ret;
+}
+
static int show_vfsmnt(struct seq_file *m, void *v)
{
struct vfsmount *mnt = v;
{ MS_MANDLOCK, ",mand" },
{ MS_NOATIME, ",noatime" },
{ MS_NODIRATIME, ",nodiratime" },
+ { MS_TAGXID, ",tagxid" },
{ 0, NULL }
};
static struct proc_fs_info mnt_info[] = {
{ MNT_NOEXEC, ",noexec" },
{ 0, NULL }
};
+
struct proc_fs_info *fs_infop;
+ unsigned long s_flags = mnt->mnt_sb->s_flags;
+ int mnt_flags = mnt->mnt_flags;
if (vx_flags(VXF_HIDE_MOUNT, 0))
return 0;
+ if (!mnt_is_reachable(mnt))
+ return 0;
- mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
- seq_putc(m, ' ');
- seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
- seq_putc(m, ' ');
+ if (!vx_check(0, VX_ADMIN|VX_WATCH) &&
+ mnt == current->fs->rootmnt) {
+ seq_puts(m, "/dev/root / ");
+ } else {
+ mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+ seq_putc(m, ' ');
+ seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
+ seq_putc(m, ' ');
+ }
mangle(m, mnt->mnt_sb->s_type->name);
seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
if (mnt->mnt_flags & fs_infop->flag)
seq_puts(m, fs_infop->str);
}
+ if (mnt->mnt_flags & MNT_XID)
+ seq_printf(m, ",xid=%d", mnt->mnt_xid);
if (mnt->mnt_sb->s_op->show_options)
err = mnt->mnt_sb->s_op->show_options(m, mnt);
seq_puts(m, " 0 0\n");
EXPORT_SYMBOL(may_umount);
-static inline void __umount_tree(struct vfsmount *mnt, struct list_head *kill)
+static inline void __umount_list(struct list_head *kill)
{
+ struct vfsmount *mnt;
+
while (!list_empty(kill)) {
mnt = list_entry(kill->next, struct vfsmount, mnt_list);
list_del_init(&mnt->mnt_list);
+ list_del_init(&mnt->mnt_fslink);
if (mnt->mnt_parent == mnt) {
spin_unlock(&vfsmount_lock);
} else {
list_del(&p->mnt_list);
list_add(&p->mnt_list, &kill);
}
- __umount_tree(mnt, &kill);
+ __umount_list(&kill);
}
void umount_unused(struct vfsmount *mnt, struct fs_struct *fs)
list_del(&p->mnt_list);
list_add(&p->mnt_list, &kill);
}
- __umount_tree(mnt, &kill);
+ __umount_list(&kill);
}
static int do_umount(struct vfsmount *mnt, int flags)
if (retval)
return retval;
+ /*
+ * Allow userspace to request a mountpoint be expired rather than
+ * unmounting unconditionally. Unmount only happens if:
+ * (1) the mark is already set (the mark is cleared by mntput())
+ * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
+ */
+ if (flags & MNT_EXPIRE) {
+ if (mnt == current->fs->rootmnt ||
+ flags & (MNT_FORCE | MNT_DETACH))
+ return -EINVAL;
+
+ if (atomic_read(&mnt->mnt_count) != 2)
+ return -EBUSY;
+
+ if (!xchg(&mnt->mnt_expiry_mark, 1))
+ return -EAGAIN;
+ }
+
/*
* If we may have to abort operations to get out of this
* mount, and they will themselves hold resources we must
down_write(&sb->s_umount);
if (!(sb->s_flags & MS_RDONLY)) {
lock_kernel();
- retval = do_remount_sb(sb, MS_RDONLY, 0, 0);
+ DQUOT_OFF(sb);
+ retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
unlock_kernel();
}
up_write(&sb->s_umount);
retval = do_umount(nd.mnt, flags);
dput_and_out:
- path_release(&nd);
+ path_release_on_umount(&nd);
out:
return retval;
}
/*
* do loopback mount.
*/
-static int do_loopback(struct nameidata *nd, char *old_name, int recurse)
+static int do_loopback(struct nameidata *nd, char *old_name, xid_t xid, int flags)
{
struct nameidata old_nd;
struct vfsmount *mnt = NULL;
int err = mount_is_safe(nd);
+ int recurse = flags & MS_REC;
if (err)
return err;
if (!old_name || !*old_name)
}
if (mnt) {
+ /* stop bind mounts from expiring */
+ spin_lock(&vfsmount_lock);
+ list_del_init(&mnt->mnt_fslink);
+ spin_unlock(&vfsmount_lock);
+
+ if (flags & MS_XID) {
+ mnt->mnt_xid = xid;
+ mnt->mnt_flags |= MNT_XID;
+ }
err = graft_tree(mnt, nd);
if (err) {
spin_lock(&vfsmount_lock);
* on it - tough luck.
*/
-static int do_remount(struct nameidata *nd,int flags,int mnt_flags,void *data)
+static int do_remount(struct nameidata *nd, int flags, int mnt_flags,
+ void *data, xid_t xid)
{
int err;
struct super_block * sb = nd->mnt->mnt_sb;
- if (!capable(CAP_SYS_ADMIN))
+ if (!capable(CAP_SYS_ADMIN) && !vx_ccaps(VXC_SECURE_REMOUNT))
return -EPERM;
if (!check_mnt(nd->mnt))
if (nd->dentry != nd->mnt->mnt_root)
return -EINVAL;
+ if (vx_ccaps(VXC_SECURE_REMOUNT))
+ mnt_flags |= MNT_NODEV;
down_write(&sb->s_umount);
err = do_remount_sb(sb, flags, data, 0);
- if (!err)
+ if (!err) {
nd->mnt->mnt_flags=mnt_flags;
+ if (flags & MS_XID)
+ nd->mnt->mnt_xid = xid;
+ }
up_write(&sb->s_umount);
if (!err)
security_sb_post_remount(nd->mnt, flags, data);
struct nameidata old_nd, parent_nd;
struct vfsmount *p;
int err = 0;
- if (!capable(CAP_SYS_ADMIN))
+ if (!capable(CAP_SYS_ADMIN) && !vx_ccaps(VXC_SECURE_MOUNT))
return -EPERM;
if (!old_name || !*old_name)
return -EINVAL;
detach_mnt(old_nd.mnt, &parent_nd);
attach_mnt(old_nd.mnt, nd);
+
+ /* if the mount is moved, it should no longer be expire
+ * automatically */
+ list_del_init(&old_nd.mnt->mnt_fslink);
out2:
spin_unlock(&vfsmount_lock);
out1:
return err;
}
-static int do_add_mount(struct nameidata *nd, char *type, int flags,
+/*
+ * create a new mount for userspace and request it to be added into the
+ * namespace's tree
+ */
+static int do_new_mount(struct nameidata *nd, char *type, int flags,
int mnt_flags, char *name, void *data)
{
struct vfsmount *mnt;
- int err;
if (!type || !memchr(type, 0, PAGE_SIZE))
return -EINVAL;
return -EPERM;
mnt = do_kern_mount(type, flags, name, data);
- err = PTR_ERR(mnt);
if (IS_ERR(mnt))
- goto out;
+ return PTR_ERR(mnt);
+
+ return do_add_mount(mnt, nd, mnt_flags, NULL);
+}
+
+/*
+ * add a mount into a namespace's mount tree
+ * - provide the option of adding the new mount to an expiration list
+ */
+int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
+ int mnt_flags, struct list_head *fslist)
+{
+ int err;
down_write(¤t->namespace->sem);
/* Something was mounted here while we slept */
/* Refuse the same filesystem on the same mount point */
err = -EBUSY;
- if (nd->mnt->mnt_sb == mnt->mnt_sb && nd->mnt->mnt_root == nd->dentry)
+ if (nd->mnt->mnt_sb == newmnt->mnt_sb &&
+ nd->mnt->mnt_root == nd->dentry)
goto unlock;
err = -EINVAL;
- if (S_ISLNK(mnt->mnt_root->d_inode->i_mode))
+ if (S_ISLNK(newmnt->mnt_root->d_inode->i_mode))
goto unlock;
- mnt->mnt_flags = mnt_flags;
- err = graft_tree(mnt, nd);
+ newmnt->mnt_flags = mnt_flags;
+ err = graft_tree(newmnt, nd);
+
+ if (err == 0 && fslist) {
+ /* add to the specified expiration list */
+ spin_lock(&vfsmount_lock);
+ list_add_tail(&newmnt->mnt_fslink, fslist);
+ spin_unlock(&vfsmount_lock);
+ }
+
unlock:
up_write(¤t->namespace->sem);
- mntput(mnt);
-out:
+ mntput(newmnt);
return err;
}
-int copy_mount_options (const void __user *data, unsigned long *where)
+EXPORT_SYMBOL_GPL(do_add_mount);
+
+/*
+ * process a list of expirable mountpoints with the intent of discarding any
+ * mountpoints that aren't in use and haven't been touched since last we came
+ * here
+ */
+void mark_mounts_for_expiry(struct list_head *mounts)
+{
+ struct namespace *namespace;
+ struct vfsmount *mnt, *next;
+ LIST_HEAD(graveyard);
+
+ if (list_empty(mounts))
+ return;
+
+ spin_lock(&vfsmount_lock);
+
+ /* extract from the expiration list every vfsmount that matches the
+ * following criteria:
+ * - only referenced by its parent vfsmount
+ * - still marked for expiry (marked on the last call here; marks are
+ * cleared by mntput())
+ */
+ list_for_each_entry_safe(mnt, next, mounts, mnt_fslink) {
+ if (!xchg(&mnt->mnt_expiry_mark, 1) ||
+ atomic_read(&mnt->mnt_count) != 1)
+ continue;
+
+ mntget(mnt);
+ list_move(&mnt->mnt_fslink, &graveyard);
+ }
+
+ /*
+ * go through the vfsmounts we've just consigned to the graveyard to
+ * - check that they're still dead
+ * - delete the vfsmount from the appropriate namespace under lock
+ * - dispose of the corpse
+ */
+ while (!list_empty(&graveyard)) {
+ mnt = list_entry(graveyard.next, struct vfsmount, mnt_fslink);
+ list_del_init(&mnt->mnt_fslink);
+
+ /* don't do anything if the namespace is dead - all the
+ * vfsmounts from it are going away anyway */
+ namespace = mnt->mnt_namespace;
+ if (!namespace || atomic_read(&namespace->count) <= 0)
+ continue;
+ get_namespace(namespace);
+
+ spin_unlock(&vfsmount_lock);
+ down_write(&namespace->sem);
+ spin_lock(&vfsmount_lock);
+
+ /* check that it is still dead: the count should now be 2 - as
+ * contributed by the vfsmount parent and the mntget above */
+ if (atomic_read(&mnt->mnt_count) == 2) {
+ struct vfsmount *xdmnt;
+ struct dentry *xdentry;
+
+ /* delete from the namespace */
+ list_del_init(&mnt->mnt_list);
+ list_del_init(&mnt->mnt_child);
+ list_del_init(&mnt->mnt_hash);
+ mnt->mnt_mountpoint->d_mounted--;
+
+ xdentry = mnt->mnt_mountpoint;
+ mnt->mnt_mountpoint = mnt->mnt_root;
+ xdmnt = mnt->mnt_parent;
+ mnt->mnt_parent = mnt;
+
+ spin_unlock(&vfsmount_lock);
+
+ mntput(xdmnt);
+ dput(xdentry);
+
+ /* now lay it to rest if this was the last ref on the
+ * superblock */
+ if (atomic_read(&mnt->mnt_sb->s_active) == 1) {
+ /* last instance - try to be smart */
+ lock_kernel();
+ DQUOT_OFF(mnt->mnt_sb);
+ acct_auto_close(mnt->mnt_sb);
+ unlock_kernel();
+ }
+
+ mntput(mnt);
+ } else {
+ /* someone brought it back to life whilst we didn't
+ * have any locks held so return it to the expiration
+ * list */
+ list_add_tail(&mnt->mnt_fslink, mounts);
+ spin_unlock(&vfsmount_lock);
+ }
+
+ up_write(&namespace->sem);
+
+ mntput(mnt);
+ put_namespace(namespace);
+
+ spin_lock(&vfsmount_lock);
+ }
+
+ spin_unlock(&vfsmount_lock);
+}
+
+EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);
+
+/*
+ * Some copy_from_user() implementations do not return the exact number of
+ * bytes remaining to copy on a fault. But copy_mount_options() requires that.
+ * Note that this function differs from copy_from_user() in that it will oops
+ * on bad values of `to', rather than returning a short copy.
+ */
+static long
+exact_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ char *t = to;
+ const char __user *f = from;
+ char c;
+
+ if (!access_ok(VERIFY_READ, from, n))
+ return n;
+
+ while (n) {
+ if (__get_user(c, f)) {
+ memset(t, 0, n);
+ break;
+ }
+ *t++ = c;
+ f++;
+ n--;
+ }
+ return n;
+}
+
+int copy_mount_options(const void __user *data, unsigned long *where)
{
int i;
unsigned long page;
if (size > PAGE_SIZE)
size = PAGE_SIZE;
- i = size - copy_from_user((void *)page, data, size);
+ i = size - exact_copy_from_user((void *)page, data, size);
if (!i) {
free_page(page);
return -EFAULT;
struct nameidata nd;
int retval = 0;
int mnt_flags = 0;
+ xid_t xid = 0;
/* Discard magic */
if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
if (data_page)
((char *)data_page)[PAGE_SIZE - 1] = 0;
+ retval = vx_parse_xid(data_page, &xid, 1);
+ if (retval) {
+ mnt_flags |= MNT_XID;
+ /* bind and re-mounts get xid flag */
+ if (flags & (MS_BIND|MS_REMOUNT))
+ flags |= MS_XID;
+ }
+
/* Separate the per-mountpoint flags */
if (flags & MS_NOSUID)
mnt_flags |= MNT_NOSUID;
if (flags & MS_REMOUNT)
retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags,
- data_page);
+ data_page, xid);
else if (flags & MS_BIND)
- retval = do_loopback(&nd, dev_name, flags & MS_REC);
+ retval = do_loopback(&nd, dev_name, xid, flags);
else if (flags & MS_MOVE)
retval = do_move_mount(&nd, dev_name);
else
- retval = do_add_mount(&nd, type_page, flags, mnt_flags,
+ retval = do_new_mount(&nd, type_page, flags, mnt_flags,
dev_name, data_page);
dput_out:
path_release(&nd);
struct namespace *new_ns;
struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
struct fs_struct *fs = tsk->fs;
+ struct vfsmount *p, *q;
if (!namespace)
return 0;
if (!(flags & CLONE_NEWNS))
return 0;
- if (!capable(CAP_SYS_ADMIN)) {
+ if (!capable(CAP_SYS_ADMIN) && !vx_ccaps(VXC_SECURE_MOUNT)) {
put_namespace(namespace);
return -EPERM;
}
list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
spin_unlock(&vfsmount_lock);
- /* Second pass: switch the tsk->fs->* elements */
- if (fs) {
- struct vfsmount *p, *q;
- write_lock(&fs->lock);
-
- p = namespace->root;
- q = new_ns->root;
- while (p) {
+ /*
+ * Second pass: switch the tsk->fs->* elements and mark new vfsmounts
+ * as belonging to new namespace. We have already acquired a private
+ * fs_struct, so tsk->fs->lock is not needed.
+ */
+ p = namespace->root;
+ q = new_ns->root;
+ while (p) {
+ q->mnt_namespace = new_ns;
+ if (fs) {
if (p == fs->rootmnt) {
rootmnt = p;
fs->rootmnt = mntget(q);
altrootmnt = p;
fs->altrootmnt = mntget(q);
}
- p = next_mnt(p, namespace->root);
- q = next_mnt(q, new_ns->root);
}
- write_unlock(&fs->lock);
+ p = next_mnt(p, namespace->root);
+ q = next_mnt(q, new_ns->root);
}
up_write(&tsk->namespace->sem);
}
}
-EXPORT_SYMBOL(set_fs_root);
-
/*
* Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
* It can block. Requires the big lock held.
}
}
-EXPORT_SYMBOL(set_fs_pwd);
-
static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd)
{
struct task_struct *g, *p;
init_rwsem(&namespace->sem);
list_add(&mnt->mnt_list, &namespace->list);
namespace->root = mnt;
+ mnt->mnt_namespace = namespace;
init_task.namespace = namespace;
read_lock(&tasklist_lock);
void __put_namespace(struct namespace *namespace)
{
+ struct vfsmount *mnt;
+
down_write(&namespace->sem);
spin_lock(&vfsmount_lock);
+
+ list_for_each_entry(mnt, &namespace->list, mnt_list) {
+ mnt->mnt_namespace = NULL;
+ }
+
umount_tree(namespace->root);
spin_unlock(&vfsmount_lock);
up_write(&namespace->sem);