#include <linux/uaccess.h>
#include <linux/proc_ns.h>
#include <linux/magic.h>
+#include <linux/bootmem.h>
#include "pnode.h"
#include "internal.h"
-#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head))
-#define HASH_SIZE (1UL << HASH_SHIFT)
+static unsigned int m_hash_mask __read_mostly;
+static unsigned int m_hash_shift __read_mostly;
+static unsigned int mp_hash_mask __read_mostly;
+static unsigned int mp_hash_shift __read_mostly;
+
+static __initdata unsigned long mhash_entries;
+static int __init set_mhash_entries(char *str)
+{
+ if (!str)
+ return 0;
+ mhash_entries = simple_strtoul(str, &str, 0);
+ return 1;
+}
+__setup("mhash_entries=", set_mhash_entries);
+
+static __initdata unsigned long mphash_entries;
+static int __init set_mphash_entries(char *str)
+{
+ if (!str)
+ return 0;
+ mphash_entries = simple_strtoul(str, &str, 0);
+ return 1;
+}
+__setup("mphash_entries=", set_mphash_entries);
static int event;
static DEFINE_IDA(mnt_id_ida);
static int mnt_id_start = 0;
static int mnt_group_start = 1;
-static struct list_head *mount_hashtable __read_mostly;
-static struct list_head *mountpoint_hashtable __read_mostly;
+static struct hlist_head *mount_hashtable __read_mostly;
+static struct hlist_head *mountpoint_hashtable __read_mostly;
static struct kmem_cache *mnt_cache __read_mostly;
static DECLARE_RWSEM(namespace_sem);
*/
__cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
-static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
+static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
{
unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
- tmp = tmp + (tmp >> HASH_SHIFT);
- return tmp & (HASH_SIZE - 1);
+ tmp = tmp + (tmp >> m_hash_shift);
+ return &mount_hashtable[tmp & m_hash_mask];
+}
+
+static inline struct hlist_head *mp_hash(struct dentry *dentry)
+{
+ unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES);
+ tmp = tmp + (tmp >> mp_hash_shift);
+ return &mountpoint_hashtable[tmp & mp_hash_mask];
}
/*
mnt->mnt_writers = 0;
#endif
- INIT_LIST_HEAD(&mnt->mnt_hash);
+ INIT_HLIST_NODE(&mnt->mnt_hash);
INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_mounts);
INIT_LIST_HEAD(&mnt->mnt_list);
*/
struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{
- struct list_head *head = mount_hashtable + hash(mnt, dentry);
+ struct hlist_head *head = m_hash(mnt, dentry);
struct mount *p;
- list_for_each_entry_rcu(p, head, mnt_hash)
+ hlist_for_each_entry_rcu(p, head, mnt_hash)
if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
return p;
return NULL;
*/
struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
{
- struct list_head *head = mount_hashtable + hash(mnt, dentry);
- struct mount *p;
-
- list_for_each_entry_reverse(p, head, mnt_hash)
- if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
- return p;
- return NULL;
+ struct mount *p, *res;
+ res = p = __lookup_mnt(mnt, dentry);
+ if (!p)
+ goto out;
+ hlist_for_each_entry_continue(p, mnt_hash) {
+ if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
+ break;
+ res = p;
+ }
+out:
+ return res;
}
/*
static struct mountpoint *new_mountpoint(struct dentry *dentry)
{
- struct list_head *chain = mountpoint_hashtable + hash(NULL, dentry);
+ struct hlist_head *chain = mp_hash(dentry);
struct mountpoint *mp;
int ret;
- list_for_each_entry(mp, chain, m_hash) {
+ hlist_for_each_entry(mp, chain, m_hash) {
if (mp->m_dentry == dentry) {
/* might be worth a WARN_ON() */
if (d_unlinked(dentry))
mp->m_dentry = dentry;
mp->m_count = 1;
- list_add(&mp->m_hash, chain);
+ hlist_add_head(&mp->m_hash, chain);
return mp;
}
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~DCACHE_MOUNTED;
spin_unlock(&dentry->d_lock);
- list_del(&mp->m_hash);
+ hlist_del(&mp->m_hash);
kfree(mp);
}
}
mnt->mnt_parent = mnt;
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
list_del_init(&mnt->mnt_child);
- list_del_init(&mnt->mnt_hash);
+ hlist_del_init_rcu(&mnt->mnt_hash);
put_mountpoint(mnt->mnt_mp);
mnt->mnt_mp = NULL;
}
struct mountpoint *mp)
{
mnt_set_mountpoint(parent, mp, mnt);
- list_add_tail(&mnt->mnt_hash, mount_hashtable +
- hash(&parent->mnt, mp->m_dentry));
+ hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
}
+static void attach_shadowed(struct mount *mnt,
+ struct mount *parent,
+ struct mount *shadows)
+{
+ if (shadows) {
+ hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
+ list_add(&mnt->mnt_child, &shadows->mnt_child);
+ } else {
+ hlist_add_head_rcu(&mnt->mnt_hash,
+ m_hash(&parent->mnt, mnt->mnt_mountpoint));
+ list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+ }
+}
+
/*
* vfsmount lock must be held for write
*/
-static void commit_tree(struct mount *mnt)
+static void commit_tree(struct mount *mnt, struct mount *shadows)
{
struct mount *parent = mnt->mnt_parent;
struct mount *m;
list_splice(&head, n->list.prev);
- list_add_tail(&mnt->mnt_hash, mount_hashtable +
- hash(&parent->mnt, mnt->mnt_mountpoint));
- list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+ attach_shadowed(mnt, parent, shadows);
touch_mnt_namespace(n);
}
goto out_free;
}
- mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+ mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
/* Don't allow unprivileged users to change mount flags */
- if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
- mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+ if (flag & CL_UNPRIVILEGED) {
+ mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
+
+ if (mnt->mnt.mnt_flags & MNT_READONLY)
+ mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
+
+ if (mnt->mnt.mnt_flags & MNT_NODEV)
+ mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
+
+ if (mnt->mnt.mnt_flags & MNT_NOSUID)
+ mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
+
+ if (mnt->mnt.mnt_flags & MNT_NOEXEC)
+ mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
+ }
/* Don't allow unprivileged users to reveal what is under a mount */
if ((flag & CL_UNPRIVILEGED) && list_empty(&old->mnt_expire))
EXPORT_SYMBOL(may_umount);
-static LIST_HEAD(unmounted); /* protected by namespace_sem */
+static HLIST_HEAD(unmounted); /* protected by namespace_sem */
static void namespace_unlock(void)
{
struct mount *mnt;
- LIST_HEAD(head);
+ struct hlist_head head = unmounted;
- if (likely(list_empty(&unmounted))) {
+ if (likely(hlist_empty(&head))) {
up_write(&namespace_sem);
return;
}
- list_splice_init(&unmounted, &head);
+ head.first->pprev = &head.first;
+ INIT_HLIST_HEAD(&unmounted);
+
+ /* undo decrements we'd done in umount_tree() */
+ hlist_for_each_entry(mnt, &head, mnt_hash)
+ if (mnt->mnt_ex_mountpoint.mnt)
+ mntget(mnt->mnt_ex_mountpoint.mnt);
+
up_write(&namespace_sem);
synchronize_rcu();
- while (!list_empty(&head)) {
- mnt = list_first_entry(&head, struct mount, mnt_hash);
- list_del_init(&mnt->mnt_hash);
+ while (!hlist_empty(&head)) {
+ mnt = hlist_entry(head.first, struct mount, mnt_hash);
+ hlist_del_init(&mnt->mnt_hash);
if (mnt->mnt_ex_mountpoint.mnt)
path_put(&mnt->mnt_ex_mountpoint);
mntput(&mnt->mnt);
*/
void umount_tree(struct mount *mnt, int how)
{
- LIST_HEAD(tmp_list);
+ HLIST_HEAD(tmp_list);
struct mount *p;
+ struct mount *last = NULL;
- for (p = mnt; p; p = next_mnt(p, mnt))
- list_move(&p->mnt_hash, &tmp_list);
+ for (p = mnt; p; p = next_mnt(p, mnt)) {
+ hlist_del_init_rcu(&p->mnt_hash);
+ hlist_add_head(&p->mnt_hash, &tmp_list);
+ }
+
+ hlist_for_each_entry(p, &tmp_list, mnt_hash)
+ list_del_init(&p->mnt_child);
if (how)
propagate_umount(&tmp_list);
- list_for_each_entry(p, &tmp_list, mnt_hash) {
+ hlist_for_each_entry(p, &tmp_list, mnt_hash) {
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
__touch_mnt_namespace(p->mnt_ns);
p->mnt_ns = NULL;
if (how < 2)
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
- list_del_init(&p->mnt_child);
if (mnt_has_parent(p)) {
put_mountpoint(p->mnt_mp);
+ mnt_add_count(p->mnt_parent, -1);
/* move the reference to mountpoint into ->mnt_ex_mountpoint */
p->mnt_ex_mountpoint.dentry = p->mnt_mountpoint;
p->mnt_ex_mountpoint.mnt = &p->mnt_parent->mnt;
p->mnt_mp = NULL;
}
change_mnt_propagation(p, MS_PRIVATE);
+ last = p;
+ }
+ if (last) {
+ last->mnt_hash.next = unmounted.first;
+ unmounted.first = tmp_list.first;
+ unmounted.first->pprev = &unmounted.first;
}
- list_splice(&tmp_list, &unmounted);
}
static void shrink_submounts(struct mount *mnt);
* Special case for "unmounting" root ...
* we just try to remount it readonly.
*/
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
down_write(&sb->s_umount);
if (!(sb->s_flags & MS_RDONLY))
retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
continue;
for (s = r; s; s = next_mnt(s, r)) {
+ struct mount *t = NULL;
if (!(flag & CL_COPY_UNBINDABLE) &&
IS_MNT_UNBINDABLE(s)) {
s = skip_mnt_tree(s);
goto out;
lock_mount_hash();
list_add_tail(&q->mnt_list, &res->mnt_list);
- attach_mnt(q, parent, p->mnt_mp);
+ mnt_set_mountpoint(parent, p->mnt_mp, q);
+ if (!list_empty(&parent->mnt_mounts)) {
+ t = list_last_entry(&parent->mnt_mounts,
+ struct mount, mnt_child);
+ if (t->mnt_mp != p->mnt_mp)
+ t = NULL;
+ }
+ attach_shadowed(q, parent, t);
unlock_mount_hash();
}
}
struct mountpoint *dest_mp,
struct path *parent_path)
{
- LIST_HEAD(tree_list);
+ HLIST_HEAD(tree_list);
struct mount *child, *p;
+ struct hlist_node *n;
int err;
if (IS_MNT_SHARED(dest_mnt)) {
err = invent_group_ids(source_mnt, true);
if (err)
goto out;
- }
- err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
- if (err)
- goto out_cleanup_ids;
-
- lock_mount_hash();
-
- if (IS_MNT_SHARED(dest_mnt)) {
+ err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+ lock_mount_hash();
+ if (err)
+ goto out_cleanup_ids;
for (p = source_mnt; p; p = next_mnt(p, source_mnt))
set_mnt_shared(p);
+ } else {
+ lock_mount_hash();
}
if (parent_path) {
detach_mnt(source_mnt, parent_path);
touch_mnt_namespace(source_mnt->mnt_ns);
} else {
mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
- commit_tree(source_mnt);
+ commit_tree(source_mnt, NULL);
}
- list_for_each_entry_safe(child, p, &tree_list, mnt_hash) {
- list_del_init(&child->mnt_hash);
- commit_tree(child);
+ hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
+ struct mount *q;
+ hlist_del_init(&child->mnt_hash);
+ q = __lookup_mnt_last(&child->mnt_parent->mnt,
+ child->mnt_mountpoint);
+ commit_tree(child, q);
}
unlock_mount_hash();
return 0;
out_cleanup_ids:
- if (IS_MNT_SHARED(dest_mnt))
- cleanup_group_ids(source_mnt, NULL);
+ while (!hlist_empty(&tree_list)) {
+ child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+ umount_tree(child, 0);
+ }
+ unlock_mount_hash();
+ cleanup_group_ids(source_mnt, NULL);
out:
return err;
}
if (readonly_request == __mnt_is_readonly(mnt))
return 0;
- if (mnt->mnt_flags & MNT_LOCK_READONLY)
- return -EPERM;
-
if (readonly_request)
error = mnt_make_readonly(real_mount(mnt));
else
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
+ /* Don't allow changing of locked mnt flags.
+ *
+ * No locks need to be held here while testing the various
+ * MNT_LOCK flags because those flags can never be cleared
+ * once they are set.
+ */
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+ !(mnt_flags & MNT_READONLY)) {
+ return -EPERM;
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+ !(mnt_flags & MNT_NODEV)) {
+ return -EPERM;
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
+ !(mnt_flags & MNT_NOSUID)) {
+ return -EPERM;
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
+ !(mnt_flags & MNT_NOEXEC)) {
+ return -EPERM;
+ }
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+ ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
+ return -EPERM;
+ }
+
err = security_sb_remount(sb, data);
if (err)
return err;
err = do_remount_sb(sb, flags, data, 0);
if (!err) {
lock_mount_hash();
- mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK;
+ mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
mnt->mnt.mnt_flags = mnt_flags;
touch_mnt_namespace(mnt->mnt_ns);
unlock_mount_hash();
struct mount *parent;
int err;
- mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
+ mnt_flags &= ~MNT_INTERNAL_FLAGS;
mp = lock_mount(path);
if (IS_ERR(mp))
*/
if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
flags |= MS_NODEV;
- mnt_flags |= MNT_NODEV;
+ mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
}
}
if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
+ /* The default atime for remount is preservation */
+ if ((flags & MS_REMOUNT) &&
+ ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
+ MS_STRICTATIME)) == 0)) {
+ mnt_flags &= ~MNT_ATIME_MASK;
+ mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
+ }
+
flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
MS_STRICTATIME);
/* make sure we can reach put_old from new_root */
if (!is_path_reachable(old_mnt, old.dentry, &new))
goto out4;
+ /* make certain new is below the root */
+ if (!is_path_reachable(new_mnt, new.dentry, &root))
+ goto out4;
root_mp->m_count++; /* pin it so it won't go away */
lock_mount_hash();
detach_mnt(new_mnt, &parent_path);
mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
- mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
- mountpoint_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC);
+ mount_hashtable = alloc_large_system_hash("Mount-cache",
+ sizeof(struct hlist_head),
+ mhash_entries, 19,
+ 0,
+ &m_hash_shift, &m_hash_mask, 0, 0);
+ mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
+ sizeof(struct hlist_head),
+ mphash_entries, 19,
+ 0,
+ &mp_hash_shift, &mp_hash_mask, 0, 0);
if (!mount_hashtable || !mountpoint_hashtable)
panic("Failed to allocate mount hash table\n");
- printk(KERN_INFO "Mount-cache hash table entries: %lu\n", HASH_SIZE);
-
- for (u = 0; u < HASH_SIZE; u++)
- INIT_LIST_HEAD(&mount_hashtable[u]);
- for (u = 0; u < HASH_SIZE; u++)
- INIT_LIST_HEAD(&mountpoint_hashtable[u]);
+ for (u = 0; u <= m_hash_mask; u++)
+ INIT_HLIST_HEAD(&mount_hashtable[u]);
+ for (u = 0; u <= mp_hash_mask; u++)
+ INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
kernfs_init();