#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched.h>
-#include <linux/smp_lock.h>
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/acct.h>
#include <linux/log2.h>
#include <linux/idr.h>
#include <linux/fs_struct.h>
+#include <linux/fsnotify.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include "pnode.h"
#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head))
#define HASH_SIZE (1UL << HASH_SHIFT)
-/* spinlock for vfsmount related operations, inplace of dcache_lock */
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
-
static int event;
static DEFINE_IDA(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
+static DEFINE_SPINLOCK(mnt_id_lock);
static int mnt_id_start = 0;
static int mnt_group_start = 1;
struct kobject *fs_kobj;
EXPORT_SYMBOL_GPL(fs_kobj);
+/*
+ * vfsmount lock may be taken for read to prevent changes to the
+ * vfsmount hash, ie. during mountpoint lookups or walking back
+ * up the tree.
+ *
+ * It should be taken for write in all cases where the vfsmount
+ * tree or hash is modified or when a vfsmount structure is modified.
+ */
+DEFINE_BRLOCK(vfsmount_lock);
+
static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
{
unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
#define MNT_WRITER_UNDERFLOW_LIMIT -(1<<16)
-/* allocation is serialized by namespace_sem */
+/*
+ * allocation is serialized by namespace_sem, but we need the spinlock to
+ * serialize with freeing.
+ */
static int mnt_alloc_id(struct vfsmount *mnt)
{
int res;
retry:
ida_pre_get(&mnt_id_ida, GFP_KERNEL);
- spin_lock(&vfsmount_lock);
+ spin_lock(&mnt_id_lock);
res = ida_get_new_above(&mnt_id_ida, mnt_id_start, &mnt->mnt_id);
if (!res)
mnt_id_start = mnt->mnt_id + 1;
- spin_unlock(&vfsmount_lock);
+ spin_unlock(&mnt_id_lock);
if (res == -EAGAIN)
goto retry;
static void mnt_free_id(struct vfsmount *mnt)
{
int id = mnt->mnt_id;
- spin_lock(&vfsmount_lock);
+ spin_lock(&mnt_id_lock);
ida_remove(&mnt_id_ida, id);
if (mnt_id_start > id)
mnt_id_start = id;
- spin_unlock(&vfsmount_lock);
+ spin_unlock(&mnt_id_lock);
}
/*
mnt->mnt_group_id = 0;
}
-struct vfsmount *alloc_vfsmnt(const char *name)
+/*
+ * vfsmount lock must be held for read
+ */
+static inline void mnt_add_count(struct vfsmount *mnt, int n)
+{
+#ifdef CONFIG_SMP
+ this_cpu_add(mnt->mnt_pcp->mnt_count, n);
+#else
+ preempt_disable();
+ mnt->mnt_count += n;
+ preempt_enable();
+#endif
+}
+
+static inline void mnt_set_count(struct vfsmount *mnt, int n)
+{
+#ifdef CONFIG_SMP
+ this_cpu_write(mnt->mnt_pcp->mnt_count, n);
+#else
+ mnt->mnt_count = n;
+#endif
+}
+
+/*
+ * vfsmount lock must be held for read
+ */
+static inline void mnt_inc_count(struct vfsmount *mnt)
+{
+ mnt_add_count(mnt, 1);
+}
+
+/*
+ * vfsmount lock must be held for read
+ */
+static inline void mnt_dec_count(struct vfsmount *mnt)
+{
+ mnt_add_count(mnt, -1);
+}
+
+/*
+ * vfsmount lock must be held for write
+ */
+unsigned int mnt_get_count(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+ unsigned int count = 0;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count;
+ }
+
+ return count;
+#else
+ return mnt->mnt_count;
+#endif
+}
+
+static struct vfsmount *alloc_vfsmnt(const char *name)
{
struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
if (mnt) {
goto out_free_id;
}
- atomic_set(&mnt->mnt_count, 1);
+#ifdef CONFIG_SMP
+ mnt->mnt_pcp = alloc_percpu(struct mnt_pcp);
+ if (!mnt->mnt_pcp)
+ goto out_free_devname;
+
+ this_cpu_add(mnt->mnt_pcp->mnt_count, 1);
+#else
+ mnt->mnt_count = 1;
+ mnt->mnt_writers = 0;
+#endif
+
INIT_LIST_HEAD(&mnt->mnt_hash);
INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_mounts);
INIT_LIST_HEAD(&mnt->mnt_share);
INIT_LIST_HEAD(&mnt->mnt_slave_list);
INIT_LIST_HEAD(&mnt->mnt_slave);
-#ifdef CONFIG_SMP
- mnt->mnt_writers = alloc_percpu(int);
- if (!mnt->mnt_writers)
- goto out_free_devname;
-#else
- mnt->mnt_writers = 0;
+#ifdef CONFIG_FSNOTIFY
+ INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
#endif
}
return mnt;
}
EXPORT_SYMBOL_GPL(__mnt_is_readonly);
-static inline void inc_mnt_writers(struct vfsmount *mnt)
+static inline void mnt_inc_writers(struct vfsmount *mnt)
{
#ifdef CONFIG_SMP
- (*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))++;
+ this_cpu_inc(mnt->mnt_pcp->mnt_writers);
#else
mnt->mnt_writers++;
#endif
}
-static inline void dec_mnt_writers(struct vfsmount *mnt)
+static inline void mnt_dec_writers(struct vfsmount *mnt)
{
#ifdef CONFIG_SMP
- (*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))--;
+ this_cpu_dec(mnt->mnt_pcp->mnt_writers);
#else
mnt->mnt_writers--;
#endif
}
-static unsigned int count_mnt_writers(struct vfsmount *mnt)
+static unsigned int mnt_get_writers(struct vfsmount *mnt)
{
#ifdef CONFIG_SMP
unsigned int count = 0;
int cpu;
for_each_possible_cpu(cpu) {
- count += *per_cpu_ptr(mnt->mnt_writers, cpu);
+ count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers;
}
return count;
int ret = 0;
preempt_disable();
- inc_mnt_writers(mnt);
+ mnt_inc_writers(mnt);
/*
- * The store to inc_mnt_writers must be visible before we pass
+ * The store to mnt_inc_writers must be visible before we pass
* MNT_WRITE_HOLD loop below, so that the slowpath can see our
* incremented count after it has set MNT_WRITE_HOLD.
*/
*/
smp_rmb();
if (__mnt_is_readonly(mnt)) {
- dec_mnt_writers(mnt);
+ mnt_dec_writers(mnt);
ret = -EROFS;
goto out;
}
if (__mnt_is_readonly(mnt))
return -EROFS;
preempt_disable();
- inc_mnt_writers(mnt);
+ mnt_inc_writers(mnt);
preempt_enable();
return 0;
}
void mnt_drop_write(struct vfsmount *mnt)
{
preempt_disable();
- dec_mnt_writers(mnt);
+ mnt_dec_writers(mnt);
preempt_enable();
}
EXPORT_SYMBOL_GPL(mnt_drop_write);
{
int ret = 0;
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
mnt->mnt_flags |= MNT_WRITE_HOLD;
/*
* After storing MNT_WRITE_HOLD, we'll read the counters. This store
* MNT_WRITE_HOLD, so it can't be decremented by another CPU while
* we're counting up here.
*/
- if (count_mnt_writers(mnt) > 0)
+ if (mnt_get_writers(mnt) > 0)
ret = -EBUSY;
else
mnt->mnt_flags |= MNT_READONLY;
*/
smp_wmb();
mnt->mnt_flags &= ~MNT_WRITE_HOLD;
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
return ret;
}
static void __mnt_unmake_readonly(struct vfsmount *mnt)
{
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
mnt->mnt_flags &= ~MNT_READONLY;
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
}
-void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
-{
- mnt->mnt_sb = sb;
- mnt->mnt_root = dget(sb->s_root);
-}
-
-EXPORT_SYMBOL(simple_set_mnt);
-
-void free_vfsmnt(struct vfsmount *mnt)
+static void free_vfsmnt(struct vfsmount *mnt)
{
kfree(mnt->mnt_devname);
mnt_free_id(mnt);
#ifdef CONFIG_SMP
- free_percpu(mnt->mnt_writers);
+ free_percpu(mnt->mnt_pcp);
#endif
kmem_cache_free(mnt_cache, mnt);
}
/*
* find the first or last mount at @dentry on vfsmount @mnt depending on
* @dir. If @dir is set return the first mount else return the last mount.
+ * vfsmount_lock must be held for read or write.
*/
struct vfsmount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
int dir)
struct vfsmount *lookup_mnt(struct path *path)
{
struct vfsmount *child_mnt;
- spin_lock(&vfsmount_lock);
+
+ br_read_lock(vfsmount_lock);
if ((child_mnt = __lookup_mnt(path->mnt, path->dentry, 1)))
mntget(child_mnt);
- spin_unlock(&vfsmount_lock);
+ br_read_unlock(vfsmount_lock);
return child_mnt;
}
return mnt->mnt_ns == current->nsproxy->mnt_ns;
}
+/*
+ * vfsmount lock must be held for write
+ */
static void touch_mnt_namespace(struct mnt_namespace *ns)
{
if (ns) {
}
}
+/*
+ * vfsmount lock must be held for write
+ */
static void __touch_mnt_namespace(struct mnt_namespace *ns)
{
if (ns && ns->event != event) {
}
}
+/*
+ * Clear dentry's mounted state if it has no remaining mounts.
+ * vfsmount_lock must be held for write.
+ */
+static void dentry_reset_mounted(struct vfsmount *mnt, struct dentry *dentry)
+{
+ unsigned u;
+
+ for (u = 0; u < HASH_SIZE; u++) {
+ struct vfsmount *p;
+
+ list_for_each_entry(p, &mount_hashtable[u], mnt_hash) {
+ if (p->mnt_mountpoint == dentry)
+ return;
+ }
+ }
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags &= ~DCACHE_MOUNTED;
+ spin_unlock(&dentry->d_lock);
+}
+
+/*
+ * vfsmount lock must be held for write
+ */
static void detach_mnt(struct vfsmount *mnt, struct path *old_path)
{
old_path->dentry = mnt->mnt_mountpoint;
mnt->mnt_mountpoint = mnt->mnt_root;
list_del_init(&mnt->mnt_child);
list_del_init(&mnt->mnt_hash);
- old_path->dentry->d_mounted--;
+ dentry_reset_mounted(old_path->mnt, old_path->dentry);
}
+/*
+ * vfsmount lock must be held for write
+ */
void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
struct vfsmount *child_mnt)
{
child_mnt->mnt_parent = mntget(mnt);
child_mnt->mnt_mountpoint = dget(dentry);
- dentry->d_mounted++;
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags |= DCACHE_MOUNTED;
+ spin_unlock(&dentry->d_lock);
}
+/*
+ * vfsmount lock must be held for write
+ */
static void attach_mnt(struct vfsmount *mnt, struct path *path)
{
mnt_set_mountpoint(path->mnt, path->dentry, mnt);
list_add_tail(&mnt->mnt_child, &path->mnt->mnt_mounts);
}
+static inline void __mnt_make_longterm(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+ atomic_inc(&mnt->mnt_longterm);
+#endif
+}
+
+/* needs vfsmount lock for write */
+static inline void __mnt_make_shortterm(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+ atomic_dec(&mnt->mnt_longterm);
+#endif
+}
+
/*
- * the caller must hold vfsmount_lock
+ * vfsmount lock must be held for write
*/
static void commit_tree(struct vfsmount *mnt)
{
BUG_ON(parent == mnt);
list_add_tail(&head, &mnt->mnt_list);
- list_for_each_entry(m, &head, mnt_list)
+ list_for_each_entry(m, &head, mnt_list) {
m->mnt_ns = n;
+ __mnt_make_longterm(m);
+ }
+
list_splice(&head, n->list.prev);
list_add_tail(&mnt->mnt_hash, mount_hashtable +
return p;
}
+struct vfsmount *
+vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
+{
+ struct vfsmount *mnt;
+ struct dentry *root;
+
+ if (!type)
+ return ERR_PTR(-ENODEV);
+
+ mnt = alloc_vfsmnt(name);
+ if (!mnt)
+ return ERR_PTR(-ENOMEM);
+
+ if (flags & MS_KERNMOUNT)
+ mnt->mnt_flags = MNT_INTERNAL;
+
+ root = mount_fs(type, flags, name, data);
+ if (IS_ERR(root)) {
+ free_vfsmnt(mnt);
+ return ERR_CAST(root);
+ }
+
+ mnt->mnt_root = root;
+ mnt->mnt_sb = root->d_sb;
+ mnt->mnt_mountpoint = mnt->mnt_root;
+ mnt->mnt_parent = mnt;
+ return mnt;
+}
+EXPORT_SYMBOL_GPL(vfs_kern_mount);
+
static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
int flag)
{
goto out_free;
}
- mnt->mnt_flags = old->mnt_flags;
+ mnt->mnt_flags = old->mnt_flags & ~MNT_WRITE_HOLD;
atomic_inc(&sb->s_active);
mnt->mnt_sb = sb;
mnt->mnt_root = dget(root);
mnt->mnt_master = old;
CLEAR_MNT_SHARED(mnt);
} else if (!(flag & CL_PRIVATE)) {
- if ((flag & CL_PROPAGATION) || IS_MNT_SHARED(old))
+ if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
list_add(&mnt->mnt_share, &old->mnt_share);
if (IS_MNT_SLAVE(old))
list_add(&mnt->mnt_slave, &old->mnt_slave);
return NULL;
}
-static inline void __mntput(struct vfsmount *mnt)
+static inline void mntfree(struct vfsmount *mnt)
{
struct super_block *sb = mnt->mnt_sb;
+
/*
* This probably indicates that somebody messed
* up a mnt_want/drop_write() pair. If this
* to make r/w->r/o transitions.
*/
/*
- * atomic_dec_and_lock() used to deal with ->mnt_count decrements
- * provides barriers, so count_mnt_writers() below is safe. AV
+ * The locking used to deal with mnt_count decrement provides barriers,
+ * so mnt_get_writers() below is safe.
*/
- WARN_ON(count_mnt_writers(mnt));
+ WARN_ON(mnt_get_writers(mnt));
+ fsnotify_vfsmount_delete(mnt);
dput(mnt->mnt_root);
free_vfsmnt(mnt);
deactivate_super(sb);
}
-void mntput_no_expire(struct vfsmount *mnt)
+static void mntput_no_expire(struct vfsmount *mnt)
{
-repeat:
- if (atomic_dec_and_lock(&mnt->mnt_count, &vfsmount_lock)) {
- if (likely(!mnt->mnt_pinned)) {
- spin_unlock(&vfsmount_lock);
- __mntput(mnt);
- return;
- }
- atomic_add(mnt->mnt_pinned + 1, &mnt->mnt_count);
+put_again:
+#ifdef CONFIG_SMP
+ br_read_lock(vfsmount_lock);
+ if (likely(atomic_read(&mnt->mnt_longterm))) {
+ mnt_dec_count(mnt);
+ br_read_unlock(vfsmount_lock);
+ return;
+ }
+ br_read_unlock(vfsmount_lock);
+
+ br_write_lock(vfsmount_lock);
+ mnt_dec_count(mnt);
+ if (mnt_get_count(mnt)) {
+ br_write_unlock(vfsmount_lock);
+ return;
+ }
+#else
+ mnt_dec_count(mnt);
+ if (likely(mnt_get_count(mnt)))
+ return;
+ br_write_lock(vfsmount_lock);
+#endif
+ if (unlikely(mnt->mnt_pinned)) {
+ mnt_add_count(mnt, mnt->mnt_pinned + 1);
mnt->mnt_pinned = 0;
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
acct_auto_close_mnt(mnt);
- security_sb_umount_close(mnt);
- goto repeat;
+ goto put_again;
}
+ br_write_unlock(vfsmount_lock);
+ mntfree(mnt);
}
-EXPORT_SYMBOL(mntput_no_expire);
+void mntput(struct vfsmount *mnt)
+{
+ if (mnt) {
+ /* avoid cacheline pingpong, hope gcc doesn't get "smart" */
+ if (unlikely(mnt->mnt_expiry_mark))
+ mnt->mnt_expiry_mark = 0;
+ mntput_no_expire(mnt);
+ }
+}
+EXPORT_SYMBOL(mntput);
+
+struct vfsmount *mntget(struct vfsmount *mnt)
+{
+ if (mnt)
+ mnt_inc_count(mnt);
+ return mnt;
+}
+EXPORT_SYMBOL(mntget);
void mnt_pin(struct vfsmount *mnt)
{
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
mnt->mnt_pinned++;
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
}
-
EXPORT_SYMBOL(mnt_pin);
void mnt_unpin(struct vfsmount *mnt)
{
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
if (mnt->mnt_pinned) {
- atomic_inc(&mnt->mnt_count);
+ mnt_inc_count(mnt);
mnt->mnt_pinned--;
}
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
}
-
EXPORT_SYMBOL(mnt_unpin);
static inline void mangle(struct seq_file *m, const char *s)
up_read(&namespace_sem);
}
+int mnt_had_events(struct proc_mounts *p)
+{
+ struct mnt_namespace *ns = p->ns;
+ int res = 0;
+
+ br_read_lock(vfsmount_lock);
+ if (p->m.poll_event != ns->event) {
+ p->m.poll_event = ns->event;
+ res = 1;
+ }
+ br_read_unlock(vfsmount_lock);
+
+ return res;
+}
+
struct proc_fs_info {
int flag;
const char *str;
{ MNT_NOATIME, ",noatime" },
{ MNT_NODIRATIME, ",nodiratime" },
{ MNT_RELATIME, ",relatime" },
- { MNT_STRICTATIME, ",strictatime" },
{ 0, NULL }
};
const struct proc_fs_info *fs_infop;
int err = 0;
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
- mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+ if (mnt->mnt_sb->s_op->show_devname) {
+ err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+ if (err)
+ goto out;
+ } else {
+ mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+ }
seq_putc(m, ' ');
seq_path(m, &mnt_path, " \t\n\\");
seq_putc(m, ' ');
seq_printf(m, "%i %i %u:%u ", mnt->mnt_id, mnt->mnt_parent->mnt_id,
MAJOR(sb->s_dev), MINOR(sb->s_dev));
- seq_dentry(m, mnt->mnt_root, " \t\n\\");
+ if (sb->s_op->show_path)
+ err = sb->s_op->show_path(m, mnt);
+ else
+ seq_dentry(m, mnt->mnt_root, " \t\n\\");
+ if (err)
+ goto out;
seq_putc(m, ' ');
seq_path_root(m, &mnt_path, &root, " \t\n\\");
if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
seq_puts(m, " - ");
show_type(m, sb);
seq_putc(m, ' ');
- mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+ if (sb->s_op->show_devname)
+ err = sb->s_op->show_devname(m, mnt);
+ else
+ mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
+ if (err)
+ goto out;
seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
err = show_sb_opts(m, sb);
if (err)
int err = 0;
/* device */
- if (mnt->mnt_devname) {
- seq_puts(m, "device ");
- mangle(m, mnt->mnt_devname);
- } else
- seq_puts(m, "no device");
+ if (mnt->mnt_sb->s_op->show_devname) {
+ err = mnt->mnt_sb->s_op->show_devname(m, mnt);
+ } else {
+ if (mnt->mnt_devname) {
+ seq_puts(m, "device ");
+ mangle(m, mnt->mnt_devname);
+ } else
+ seq_puts(m, "no device");
+ }
/* mount point */
seq_puts(m, " mounted on ");
/* optional statistics */
if (mnt->mnt_sb->s_op->show_stats) {
seq_putc(m, ' ');
- err = mnt->mnt_sb->s_op->show_stats(m, mnt);
+ if (!err)
+ err = mnt->mnt_sb->s_op->show_stats(m, mnt);
}
seq_putc(m, '\n');
int minimum_refs = 0;
struct vfsmount *p;
- spin_lock(&vfsmount_lock);
+ /* write lock needed for mnt_get_count */
+ br_write_lock(vfsmount_lock);
for (p = mnt; p; p = next_mnt(p, mnt)) {
- actual_refs += atomic_read(&p->mnt_count);
+ actual_refs += mnt_get_count(p);
minimum_refs += 2;
}
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
if (actual_refs > minimum_refs)
return 0;
int may_umount(struct vfsmount *mnt)
{
int ret = 1;
- spin_lock(&vfsmount_lock);
+ down_read(&namespace_sem);
+ br_write_lock(vfsmount_lock);
if (propagate_mount_busy(mnt, 2))
ret = 0;
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
+ up_read(&namespace_sem);
return ret;
}
if (mnt->mnt_parent != mnt) {
struct dentry *dentry;
struct vfsmount *m;
- spin_lock(&vfsmount_lock);
+
+ br_write_lock(vfsmount_lock);
dentry = mnt->mnt_mountpoint;
m = mnt->mnt_parent;
mnt->mnt_mountpoint = mnt->mnt_root;
mnt->mnt_parent = mnt;
m->mnt_ghosts--;
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
dput(dentry);
mntput(m);
}
}
}
+/*
+ * vfsmount lock must be held for write
+ * namespace_sem must be held for write
+ */
void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
{
+ LIST_HEAD(tmp_list);
struct vfsmount *p;
for (p = mnt; p; p = next_mnt(p, mnt))
- list_move(&p->mnt_hash, kill);
+ list_move(&p->mnt_hash, &tmp_list);
if (propagate)
- propagate_umount(kill);
+ propagate_umount(&tmp_list);
- list_for_each_entry(p, kill, mnt_hash) {
+ list_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;
+ __mnt_make_shortterm(p);
list_del_init(&p->mnt_child);
if (p->mnt_parent != p) {
p->mnt_parent->mnt_ghosts++;
- p->mnt_mountpoint->d_mounted--;
+ dentry_reset_mounted(p->mnt_parent, p->mnt_mountpoint);
}
change_mnt_propagation(p, MS_PRIVATE);
}
+ list_splice(&tmp_list, kill);
}
static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts);
flags & (MNT_FORCE | MNT_DETACH))
return -EINVAL;
- if (atomic_read(&mnt->mnt_count) != 2)
+ /*
+ * probably don't strictly need the lock here if we examined
+ * all race cases, but it's a slowpath.
+ */
+ br_write_lock(vfsmount_lock);
+ if (mnt_get_count(mnt) != 2) {
+ br_write_unlock(vfsmount_lock);
return -EBUSY;
+ }
+ br_write_unlock(vfsmount_lock);
if (!xchg(&mnt->mnt_expiry_mark, 1))
return -EAGAIN;
}
down_write(&namespace_sem);
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
event++;
if (!(flags & MNT_DETACH))
umount_tree(mnt, 1, &umount_list);
retval = 0;
}
- spin_unlock(&vfsmount_lock);
- if (retval)
- security_sb_umount_busy(mnt);
+ br_write_unlock(vfsmount_lock);
up_write(&namespace_sem);
release_mounts(&umount_list);
return retval;
{
struct path path;
int retval;
+ int lookup_flags = 0;
+
+ if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
+ return -EINVAL;
+
+ if (!(flags & UMOUNT_NOFOLLOW))
+ lookup_flags |= LOOKUP_FOLLOW;
- retval = user_path(name, &path);
+ retval = user_path_at(AT_FDCWD, name, lookup_flags, &path);
if (retval)
goto out;
retval = -EINVAL;
q = clone_mnt(p, p->mnt_root, flag);
if (!q)
goto Enomem;
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
list_add_tail(&q->mnt_list, &res->mnt_list);
attach_mnt(q, &path);
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
}
}
return res;
Enomem:
if (res) {
LIST_HEAD(umount_list);
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
umount_tree(res, 0, &umount_list);
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
release_mounts(&umount_list);
}
return NULL;
{
LIST_HEAD(umount_list);
down_write(&namespace_sem);
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
umount_tree(mnt, 0, &umount_list);
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
up_write(&namespace_sem);
release_mounts(&umount_list);
}
+int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
+ struct vfsmount *root)
+{
+ struct vfsmount *mnt;
+ int res = f(root, arg);
+ if (res)
+ return res;
+ list_for_each_entry(mnt, &root->mnt_list, mnt_list) {
+ res = f(mnt, arg);
+ if (res)
+ return res;
+ }
+ return 0;
+}
+
static void cleanup_group_ids(struct vfsmount *mnt, struct vfsmount *end)
{
struct vfsmount *p;
if (err)
goto out_cleanup_ids;
+ br_write_lock(vfsmount_lock);
+
if (IS_MNT_SHARED(dest_mnt)) {
for (p = source_mnt; p; p = next_mnt(p, source_mnt))
set_mnt_shared(p);
}
-
- spin_lock(&vfsmount_lock);
if (parent_path) {
detach_mnt(source_mnt, parent_path);
attach_mnt(source_mnt, path);
list_del_init(&child->mnt_hash);
commit_tree(child);
}
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
+
return 0;
out_cleanup_ids:
return err;
}
+static int lock_mount(struct path *path)
+{
+ struct vfsmount *mnt;
+retry:
+ mutex_lock(&path->dentry->d_inode->i_mutex);
+ if (unlikely(cant_mount(path->dentry))) {
+ mutex_unlock(&path->dentry->d_inode->i_mutex);
+ return -ENOENT;
+ }
+ down_write(&namespace_sem);
+ mnt = lookup_mnt(path);
+ if (likely(!mnt))
+ return 0;
+ up_write(&namespace_sem);
+ mutex_unlock(&path->dentry->d_inode->i_mutex);
+ path_put(path);
+ path->mnt = mnt;
+ path->dentry = dget(mnt->mnt_root);
+ goto retry;
+}
+
+static void unlock_mount(struct path *path)
+{
+ up_write(&namespace_sem);
+ mutex_unlock(&path->dentry->d_inode->i_mutex);
+}
+
static int graft_tree(struct vfsmount *mnt, struct path *path)
{
- int err;
if (mnt->mnt_sb->s_flags & MS_NOUSER)
return -EINVAL;
S_ISDIR(mnt->mnt_root->d_inode->i_mode))
return -ENOTDIR;
- err = -ENOENT;
- mutex_lock(&path->dentry->d_inode->i_mutex);
- if (IS_DEADDIR(path->dentry->d_inode))
- goto out_unlock;
+ if (d_unlinked(path->dentry))
+ return -ENOENT;
- err = security_sb_check_sb(mnt, path);
- if (err)
- goto out_unlock;
+ return attach_recursive_mnt(mnt, path, NULL);
+}
- err = -ENOENT;
- if (!d_unlinked(path->dentry))
- err = attach_recursive_mnt(mnt, path, NULL);
-out_unlock:
- mutex_unlock(&path->dentry->d_inode->i_mutex);
- if (!err)
- security_sb_post_addmount(mnt, path);
- return err;
+/*
+ * Sanity check the flags to change_mnt_propagation.
+ */
+
+static int flags_to_propagation_type(int flags)
+{
+ int type = flags & ~(MS_REC | MS_SILENT);
+
+ /* Fail if any non-propagation flags are set */
+ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
+ return 0;
+ /* Only one propagation flag should be set */
+ if (!is_power_of_2(type))
+ return 0;
+ return type;
}
/*
{
struct vfsmount *m, *mnt = path->mnt;
int recurse = flag & MS_REC;
- int type = flag & ~MS_REC;
+ int type;
int err = 0;
if (!capable(CAP_SYS_ADMIN))
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
+ type = flags_to_propagation_type(flag);
+ if (!type)
+ return -EINVAL;
+
down_write(&namespace_sem);
if (type == MS_SHARED) {
err = invent_group_ids(mnt, recurse);
goto out_unlock;
}
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
change_mnt_propagation(m, type);
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
out_unlock:
up_write(&namespace_sem);
static int do_loopback(struct path *path, char *old_name,
int recurse)
{
+ LIST_HEAD(umount_list);
struct path old_path;
struct vfsmount *mnt = NULL;
int err = mount_is_safe(path);
if (err)
return err;
- down_write(&namespace_sem);
+ err = lock_mount(path);
+ if (err)
+ goto out;
+
err = -EINVAL;
if (IS_MNT_UNBINDABLE(old_path.mnt))
- goto out;
+ goto out2;
if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
- goto out;
+ goto out2;
err = -ENOMEM;
if (recurse)
mnt = clone_mnt(old_path.mnt, old_path.dentry, 0);
if (!mnt)
- goto out;
+ goto out2;
err = graft_tree(mnt, path);
if (err) {
- LIST_HEAD(umount_list);
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
umount_tree(mnt, 0, &umount_list);
- spin_unlock(&vfsmount_lock);
- release_mounts(&umount_list);
+ br_write_unlock(vfsmount_lock);
}
-
+out2:
+ unlock_mount(path);
+ release_mounts(&umount_list);
out:
- up_write(&namespace_sem);
path_put(&old_path);
return err;
}
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
+ err = security_sb_remount(sb, data);
+ if (err)
+ return err;
+
down_write(&sb->s_umount);
if (flags & MS_BIND)
err = change_mount_flags(path->mnt, flags);
else
err = do_remount_sb(sb, flags, data, 0);
- if (!err)
+ if (!err) {
+ br_write_lock(vfsmount_lock);
+ mnt_flags |= path->mnt->mnt_flags & MNT_PROPAGATION_MASK;
path->mnt->mnt_flags = mnt_flags;
+ br_write_unlock(vfsmount_lock);
+ }
up_write(&sb->s_umount);
if (!err) {
- security_sb_post_remount(path->mnt, flags, data);
-
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
touch_mnt_namespace(path->mnt->mnt_ns);
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
}
return err;
}
if (err)
return err;
- down_write(&namespace_sem);
- while (d_mountpoint(path->dentry) &&
- follow_down(path))
- ;
- err = -EINVAL;
- if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
+ err = lock_mount(path);
+ if (err < 0)
goto out;
- err = -ENOENT;
- mutex_lock(&path->dentry->d_inode->i_mutex);
- if (IS_DEADDIR(path->dentry->d_inode))
+ err = -EINVAL;
+ if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
goto out1;
if (d_unlinked(path->dentry))
* automatically */
list_del_init(&old_path.mnt->mnt_expire);
out1:
- mutex_unlock(&path->dentry->d_inode->i_mutex);
+ unlock_mount(path);
out:
- up_write(&namespace_sem);
if (!err)
path_put(&parent_path);
path_put(&old_path);
return err;
}
-/*
- * create a new mount for userspace and request it to be added into the
- * namespace's tree
- */
-static int do_new_mount(struct path *path, char *type, int flags,
- int mnt_flags, char *name, void *data)
+static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
{
- struct vfsmount *mnt;
-
- if (!type)
- return -EINVAL;
+ int err;
+ const char *subtype = strchr(fstype, '.');
+ if (subtype) {
+ subtype++;
+ err = -EINVAL;
+ if (!subtype[0])
+ goto err;
+ } else
+ subtype = "";
- /* we need capabilities... */
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
+ mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
+ err = -ENOMEM;
+ if (!mnt->mnt_sb->s_subtype)
+ goto err;
+ return mnt;
- lock_kernel();
- mnt = do_kern_mount(type, flags, name, data);
- unlock_kernel();
- if (IS_ERR(mnt))
- return PTR_ERR(mnt);
+ err:
+ mntput(mnt);
+ return ERR_PTR(err);
+}
- return do_add_mount(mnt, path, mnt_flags, NULL);
+struct vfsmount *
+do_kern_mount(const char *fstype, int flags, const char *name, void *data)
+{
+ struct file_system_type *type = get_fs_type(fstype);
+ struct vfsmount *mnt;
+ if (!type)
+ return ERR_PTR(-ENODEV);
+ mnt = vfs_kern_mount(type, flags, name, data);
+ if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
+ !mnt->mnt_sb->s_subtype)
+ mnt = fs_set_subtype(mnt, fstype);
+ put_filesystem(type);
+ return mnt;
}
+EXPORT_SYMBOL_GPL(do_kern_mount);
/*
* 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 path *path,
- int mnt_flags, struct list_head *fslist)
+static int do_add_mount(struct vfsmount *newmnt, struct path *path, int mnt_flags)
{
int err;
- down_write(&namespace_sem);
- /* Something was mounted here while we slept */
- while (d_mountpoint(path->dentry) &&
- follow_down(path))
- ;
+ mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL);
+
+ err = lock_mount(path);
+ if (err)
+ return err;
+
err = -EINVAL;
if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
goto unlock;
goto unlock;
newmnt->mnt_flags = mnt_flags;
- if ((err = graft_tree(newmnt, path)))
- goto unlock;
+ err = graft_tree(newmnt, path);
- if (fslist) /* add to the specified expiration list */
- list_add_tail(&newmnt->mnt_expire, fslist);
+unlock:
+ unlock_mount(path);
+ return err;
+}
- up_write(&namespace_sem);
- return 0;
+/*
+ * create a new mount for userspace and request it to be added into the
+ * namespace's tree
+ */
+static int do_new_mount(struct path *path, char *type, int flags,
+ int mnt_flags, char *name, void *data)
+{
+ struct vfsmount *mnt;
+ int err;
-unlock:
- up_write(&namespace_sem);
- mntput(newmnt);
+ if (!type)
+ return -EINVAL;
+
+ /* we need capabilities... */
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ mnt = do_kern_mount(type, flags, name, data);
+ if (IS_ERR(mnt))
+ return PTR_ERR(mnt);
+
+ err = do_add_mount(mnt, path, mnt_flags);
+ if (err)
+ mntput(mnt);
return err;
}
-EXPORT_SYMBOL_GPL(do_add_mount);
+int finish_automount(struct vfsmount *m, struct path *path)
+{
+ int err;
+ /* The new mount record should have at least 2 refs to prevent it being
+ * expired before we get a chance to add it
+ */
+ BUG_ON(mnt_get_count(m) < 2);
+
+ if (m->mnt_sb == path->mnt->mnt_sb &&
+ m->mnt_root == path->dentry) {
+ err = -ELOOP;
+ goto fail;
+ }
+
+ err = do_add_mount(m, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
+ if (!err)
+ return 0;
+fail:
+ /* remove m from any expiration list it may be on */
+ if (!list_empty(&m->mnt_expire)) {
+ down_write(&namespace_sem);
+ br_write_lock(vfsmount_lock);
+ list_del_init(&m->mnt_expire);
+ br_write_unlock(vfsmount_lock);
+ up_write(&namespace_sem);
+ }
+ mntput(m);
+ mntput(m);
+ return err;
+}
+
+/**
+ * mnt_set_expiry - Put a mount on an expiration list
+ * @mnt: The mount to list.
+ * @expiry_list: The list to add the mount to.
+ */
+void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list)
+{
+ down_write(&namespace_sem);
+ br_write_lock(vfsmount_lock);
+
+ list_add_tail(&mnt->mnt_expire, expiry_list);
+
+ br_write_unlock(vfsmount_lock);
+ up_write(&namespace_sem);
+}
+EXPORT_SYMBOL(mnt_set_expiry);
/*
* process a list of expirable mountpoints with the intent of discarding any
return;
down_write(&namespace_sem);
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
/* extract from the expiration list every vfsmount that matches the
* following criteria:
touch_mnt_namespace(mnt->mnt_ns);
umount_tree(mnt, 1, &umounts);
}
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
up_write(&namespace_sem);
release_mounts(&umounts);
/*
* process a list of expirable mountpoints with the intent of discarding any
* submounts of a specific parent mountpoint
+ *
+ * vfsmount_lock must be held for write
*/
static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts)
{
if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
- flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
+ flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
MS_STRICTATIME);
return new_ns;
}
+void mnt_make_longterm(struct vfsmount *mnt)
+{
+ __mnt_make_longterm(mnt);
+}
+
+void mnt_make_shortterm(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+ if (atomic_add_unless(&mnt->mnt_longterm, -1, 1))
+ return;
+ br_write_lock(vfsmount_lock);
+ atomic_dec(&mnt->mnt_longterm);
+ br_write_unlock(vfsmount_lock);
+#endif
+}
+
/*
* Allocate a new namespace structure and populate it with contents
* copied from the namespace of the passed in task structure.
kfree(new_ns);
return ERR_PTR(-ENOMEM);
}
- spin_lock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
/*
* Second pass: switch the tsk->fs->* elements and mark new vfsmounts
q = new_ns->root;
while (p) {
q->mnt_ns = new_ns;
+ __mnt_make_longterm(q);
if (fs) {
if (p == fs->root.mnt) {
- rootmnt = p;
fs->root.mnt = mntget(q);
+ __mnt_make_longterm(q);
+ mnt_make_shortterm(p);
+ rootmnt = p;
}
if (p == fs->pwd.mnt) {
- pwdmnt = p;
fs->pwd.mnt = mntget(q);
+ __mnt_make_longterm(q);
+ mnt_make_shortterm(p);
+ pwdmnt = p;
}
}
p = next_mnt(p, mnt_ns->root);
new_ns = alloc_mnt_ns();
if (!IS_ERR(new_ns)) {
mnt->mnt_ns = new_ns;
+ __mnt_make_longterm(mnt);
new_ns->root = mnt;
list_add(&new_ns->list, &new_ns->root->mnt_list);
}
error = user_path_dir(new_root, &new);
if (error)
goto out0;
- error = -EINVAL;
- if (!check_mnt(new.mnt))
- goto out1;
error = user_path_dir(put_old, &old);
if (error)
goto out1;
error = security_sb_pivotroot(&old, &new);
- if (error) {
- path_put(&old);
- goto out1;
- }
+ if (error)
+ goto out2;
+
+ get_fs_root(current->fs, &root);
+ error = lock_mount(&old);
+ if (error)
+ goto out3;
- read_lock(¤t->fs->lock);
- root = current->fs->root;
- path_get(¤t->fs->root);
- read_unlock(¤t->fs->lock);
- down_write(&namespace_sem);
- mutex_lock(&old.dentry->d_inode->i_mutex);
error = -EINVAL;
if (IS_MNT_SHARED(old.mnt) ||
IS_MNT_SHARED(new.mnt->mnt_parent) ||
IS_MNT_SHARED(root.mnt->mnt_parent))
- goto out2;
- if (!check_mnt(root.mnt))
- goto out2;
+ goto out4;
+ if (!check_mnt(root.mnt) || !check_mnt(new.mnt))
+ goto out4;
error = -ENOENT;
- if (IS_DEADDIR(new.dentry->d_inode))
- goto out2;
if (d_unlinked(new.dentry))
- goto out2;
+ goto out4;
if (d_unlinked(old.dentry))
- goto out2;
+ goto out4;
error = -EBUSY;
if (new.mnt == root.mnt ||
old.mnt == root.mnt)
- goto out2; /* loop, on the same file system */
+ goto out4; /* loop, on the same file system */
error = -EINVAL;
if (root.mnt->mnt_root != root.dentry)
- goto out2; /* not a mountpoint */
+ goto out4; /* not a mountpoint */
if (root.mnt->mnt_parent == root.mnt)
- goto out2; /* not attached */
+ goto out4; /* not attached */
if (new.mnt->mnt_root != new.dentry)
- goto out2; /* not a mountpoint */
+ goto out4; /* not a mountpoint */
if (new.mnt->mnt_parent == new.mnt)
- goto out2; /* not attached */
+ goto out4; /* not attached */
/* make sure we can reach put_old from new_root */
tmp = old.mnt;
- spin_lock(&vfsmount_lock);
if (tmp != new.mnt) {
for (;;) {
if (tmp->mnt_parent == tmp)
- goto out3; /* already mounted on put_old */
+ goto out4; /* already mounted on put_old */
if (tmp->mnt_parent == new.mnt)
break;
tmp = tmp->mnt_parent;
}
if (!is_subdir(tmp->mnt_mountpoint, new.dentry))
- goto out3;
+ goto out4;
} else if (!is_subdir(old.dentry, new.dentry))
- goto out3;
+ goto out4;
+ br_write_lock(vfsmount_lock);
detach_mnt(new.mnt, &parent_path);
detach_mnt(root.mnt, &root_parent);
/* mount old root on put_old */
/* mount new_root on / */
attach_mnt(new.mnt, &root_parent);
touch_mnt_namespace(current->nsproxy->mnt_ns);
- spin_unlock(&vfsmount_lock);
+ br_write_unlock(vfsmount_lock);
chroot_fs_refs(&root, &new);
- security_sb_post_pivotroot(&root, &new);
error = 0;
- path_put(&root_parent);
- path_put(&parent_path);
-out2:
- mutex_unlock(&old.dentry->d_inode->i_mutex);
- up_write(&namespace_sem);
+out4:
+ unlock_mount(&old);
+ if (!error) {
+ path_put(&root_parent);
+ path_put(&parent_path);
+ }
+out3:
path_put(&root);
+out2:
path_put(&old);
out1:
path_put(&new);
out0:
return error;
-out3:
- spin_unlock(&vfsmount_lock);
- goto out2;
}
static void __init init_mount_tree(void)
mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
if (IS_ERR(mnt))
panic("Can't create rootfs");
+
ns = create_mnt_ns(mnt);
if (IS_ERR(ns))
panic("Can't allocate initial namespace");
if (!mount_hashtable)
panic("Failed to allocate mount hash table\n");
- printk("Mount-cache hash table entries: %lu\n", HASH_SIZE);
+ 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]);
+ br_lock_init(vfsmount_lock);
+
err = sysfs_init();
if (err)
printk(KERN_WARNING "%s: sysfs_init error: %d\n",
void put_mnt_ns(struct mnt_namespace *ns)
{
- struct vfsmount *root;
LIST_HEAD(umount_list);
- if (!atomic_dec_and_lock(&ns->count, &vfsmount_lock))
+ if (!atomic_dec_and_test(&ns->count))
return;
- root = ns->root;
- ns->root = NULL;
- spin_unlock(&vfsmount_lock);
down_write(&namespace_sem);
- spin_lock(&vfsmount_lock);
- umount_tree(root, 0, &umount_list);
- spin_unlock(&vfsmount_lock);
+ br_write_lock(vfsmount_lock);
+ umount_tree(ns->root, 0, &umount_list);
+ br_write_unlock(vfsmount_lock);
up_write(&namespace_sem);
release_mounts(&umount_list);
kfree(ns);
}
EXPORT_SYMBOL(put_mnt_ns);
+
+struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
+{
+ struct vfsmount *mnt;
+ mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
+ if (!IS_ERR(mnt)) {
+ /*
+ * it is a longterm mount, don't release mnt until
+ * we unmount before file sys is unregistered
+ */
+ mnt_make_longterm(mnt);
+ }
+ return mnt;
+}
+EXPORT_SYMBOL_GPL(kern_mount_data);
+
+void kern_unmount(struct vfsmount *mnt)
+{
+ /* release long term mount so mount point can be released */
+ if (!IS_ERR_OR_NULL(mnt)) {
+ mnt_make_shortterm(mnt);
+ mntput(mnt);
+ }
+}
+EXPORT_SYMBOL(kern_unmount);