diff options
Diffstat (limited to 'fs/namespace.c')
| -rw-r--r-- | fs/namespace.c | 829 |
1 files changed, 343 insertions, 486 deletions
diff --git a/fs/namespace.c b/fs/namespace.c index cfc6d4448aa..7e6f2c9dc7c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -9,30 +9,17 @@ */ #include <linux/syscalls.h> -#include <linux/slab.h> -#include <linux/sched.h> -#include <linux/spinlock.h> -#include <linux/percpu.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/acct.h> +#include <linux/export.h> #include <linux/capability.h> -#include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/sysfs.h> -#include <linux/seq_file.h> #include <linux/mnt_namespace.h> #include <linux/namei.h> -#include <linux/nsproxy.h> #include <linux/security.h> -#include <linux/mount.h> -#include <linux/ramfs.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 <linux/acct.h> /* acct_auto_close_mnt */ +#include <linux/ramfs.h> /* init_rootfs */ +#include <linux/fs_struct.h> /* get_fs_root et.al. */ +#include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ +#include <linux/uaccess.h> #include "pnode.h" #include "internal.h" @@ -78,7 +65,7 @@ static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) * allocation is serialized by namespace_sem, but we need the spinlock to * serialize with freeing. */ -static int mnt_alloc_id(struct vfsmount *mnt) +static int mnt_alloc_id(struct mount *mnt) { int res; @@ -95,7 +82,7 @@ retry: return res; } -static void mnt_free_id(struct vfsmount *mnt) +static void mnt_free_id(struct mount *mnt) { int id = mnt->mnt_id; spin_lock(&mnt_id_lock); @@ -110,7 +97,7 @@ static void mnt_free_id(struct vfsmount *mnt) * * mnt_group_ida is protected by namespace_sem */ -static int mnt_alloc_group_id(struct vfsmount *mnt) +static int mnt_alloc_group_id(struct mount *mnt) { int res; @@ -129,7 +116,7 @@ static int mnt_alloc_group_id(struct vfsmount *mnt) /* * Release a peer group ID */ -void mnt_release_group_id(struct vfsmount *mnt) +void mnt_release_group_id(struct mount *mnt) { int id = mnt->mnt_group_id; ida_remove(&mnt_group_ida, id); @@ -141,7 +128,7 @@ void mnt_release_group_id(struct vfsmount *mnt) /* * vfsmount lock must be held for read */ -static inline void mnt_add_count(struct vfsmount *mnt, int n) +static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); @@ -152,35 +139,10 @@ static inline void mnt_add_count(struct vfsmount *mnt, int n) #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) +unsigned int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; @@ -196,9 +158,9 @@ unsigned int mnt_get_count(struct vfsmount *mnt) #endif } -static struct vfsmount *alloc_vfsmnt(const char *name) +static struct mount *alloc_vfsmnt(const char *name) { - struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); + struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; @@ -277,7 +239,7 @@ int __mnt_is_readonly(struct vfsmount *mnt) } EXPORT_SYMBOL_GPL(__mnt_is_readonly); -static inline void mnt_inc_writers(struct vfsmount *mnt) +static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); @@ -286,7 +248,7 @@ static inline void mnt_inc_writers(struct vfsmount *mnt) #endif } -static inline void mnt_dec_writers(struct vfsmount *mnt) +static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); @@ -295,7 +257,7 @@ static inline void mnt_dec_writers(struct vfsmount *mnt) #endif } -static unsigned int mnt_get_writers(struct vfsmount *mnt) +static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; @@ -311,6 +273,15 @@ static unsigned int mnt_get_writers(struct vfsmount *mnt) #endif } +static int mnt_is_readonly(struct vfsmount *mnt) +{ + if (mnt->mnt_sb->s_readonly_remount) + return 1; + /* Order wrt setting s_flags/s_readonly_remount in do_remount() */ + smp_rmb(); + return __mnt_is_readonly(mnt); +} + /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). @@ -321,7 +292,7 @@ static unsigned int mnt_get_writers(struct vfsmount *mnt) */ /** * mnt_want_write - get write access to a mount - * @mnt: the mount on which to take a write + * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is * about to be performed to it, and makes sure that @@ -329,8 +300,9 @@ static unsigned int mnt_get_writers(struct vfsmount *mnt) * the write operation is finished, mnt_drop_write() * must be called. This is effectively a refcount. */ -int mnt_want_write(struct vfsmount *mnt) +int mnt_want_write(struct vfsmount *m) { + struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); @@ -341,7 +313,7 @@ int mnt_want_write(struct vfsmount *mnt) * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); - while (mnt->mnt_flags & MNT_WRITE_HOLD) + while (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) cpu_relax(); /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will @@ -349,7 +321,7 @@ int mnt_want_write(struct vfsmount *mnt) * MNT_WRITE_HOLD is cleared. */ smp_rmb(); - if (__mnt_is_readonly(mnt)) { + if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; goto out; @@ -378,7 +350,7 @@ int mnt_clone_write(struct vfsmount *mnt) if (__mnt_is_readonly(mnt)) return -EROFS; preempt_disable(); - mnt_inc_writers(mnt); + mnt_inc_writers(real_mount(mnt)); preempt_enable(); return 0; } @@ -412,17 +384,23 @@ EXPORT_SYMBOL_GPL(mnt_want_write_file); void mnt_drop_write(struct vfsmount *mnt) { preempt_disable(); - mnt_dec_writers(mnt); + mnt_dec_writers(real_mount(mnt)); preempt_enable(); } EXPORT_SYMBOL_GPL(mnt_drop_write); -static int mnt_make_readonly(struct vfsmount *mnt) +void mnt_drop_write_file(struct file *file) +{ + mnt_drop_write(file->f_path.mnt); +} +EXPORT_SYMBOL(mnt_drop_write_file); + +static int mnt_make_readonly(struct mount *mnt) { int ret = 0; br_write_lock(vfsmount_lock); - mnt->mnt_flags |= MNT_WRITE_HOLD; + mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. @@ -448,25 +426,61 @@ static int mnt_make_readonly(struct vfsmount *mnt) if (mnt_get_writers(mnt) > 0) ret = -EBUSY; else - mnt->mnt_flags |= MNT_READONLY; + mnt->mnt.mnt_flags |= MNT_READONLY; /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); - mnt->mnt_flags &= ~MNT_WRITE_HOLD; + mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; br_write_unlock(vfsmount_lock); return ret; } -static void __mnt_unmake_readonly(struct vfsmount *mnt) +static void __mnt_unmake_readonly(struct mount *mnt) { br_write_lock(vfsmount_lock); - mnt->mnt_flags &= ~MNT_READONLY; + mnt->mnt.mnt_flags &= ~MNT_READONLY; br_write_unlock(vfsmount_lock); } -static void free_vfsmnt(struct vfsmount *mnt) +int sb_prepare_remount_readonly(struct super_block *sb) +{ + struct mount *mnt; + int err = 0; + + /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ + if (atomic_long_read(&sb->s_remove_count)) + return -EBUSY; + + br_write_lock(vfsmount_lock); + list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { + if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { + mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; + smp_mb(); + if (mnt_get_writers(mnt) > 0) { + err = -EBUSY; + break; + } + } + } + if (!err && atomic_long_read(&sb->s_remove_count)) + err = -EBUSY; + + if (!err) { + sb->s_readonly_remount = 1; + smp_wmb(); + } + list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { + if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) + mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; + } + br_write_unlock(vfsmount_lock); + + return err; +} + +static void free_vfsmnt(struct mount *mnt) { kfree(mnt->mnt_devname); mnt_free_id(mnt); @@ -481,20 +495,20 @@ static void free_vfsmnt(struct vfsmount *mnt) * @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, +struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry, int dir) { struct list_head *head = mount_hashtable + hash(mnt, dentry); struct list_head *tmp = head; - struct vfsmount *p, *found = NULL; + struct mount *p, *found = NULL; for (;;) { tmp = dir ? tmp->next : tmp->prev; p = NULL; if (tmp == head) break; - p = list_entry(tmp, struct vfsmount, mnt_hash); - if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) { + p = list_entry(tmp, struct mount, mnt_hash); + if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) { found = p; break; } @@ -508,16 +522,21 @@ struct vfsmount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry, */ struct vfsmount *lookup_mnt(struct path *path) { - struct vfsmount *child_mnt; + struct mount *child_mnt; br_read_lock(vfsmount_lock); - if ((child_mnt = __lookup_mnt(path->mnt, path->dentry, 1))) - mntget(child_mnt); - br_read_unlock(vfsmount_lock); - return child_mnt; + child_mnt = __lookup_mnt(path->mnt, path->dentry, 1); + if (child_mnt) { + mnt_add_count(child_mnt, 1); + br_read_unlock(vfsmount_lock); + return &child_mnt->mnt; + } else { + br_read_unlock(vfsmount_lock); + return NULL; + } } -static inline int check_mnt(struct vfsmount *mnt) +static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } @@ -548,12 +567,12 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns) * 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) +static void dentry_reset_mounted(struct dentry *dentry) { unsigned u; for (u = 0; u < HASH_SIZE; u++) { - struct vfsmount *p; + struct mount *p; list_for_each_entry(p, &mount_hashtable[u], mnt_hash) { if (p->mnt_mountpoint == dentry) @@ -568,25 +587,26 @@ static void dentry_reset_mounted(struct vfsmount *mnt, struct dentry *dentry) /* * vfsmount lock must be held for write */ -static void detach_mnt(struct vfsmount *mnt, struct path *old_path) +static void detach_mnt(struct mount *mnt, struct path *old_path) { old_path->dentry = mnt->mnt_mountpoint; - old_path->mnt = mnt->mnt_parent; + old_path->mnt = &mnt->mnt_parent->mnt; mnt->mnt_parent = mnt; - mnt->mnt_mountpoint = mnt->mnt_root; + mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); list_del_init(&mnt->mnt_hash); - dentry_reset_mounted(old_path->mnt, old_path->dentry); + dentry_reset_mounted(old_path->dentry); } /* * vfsmount lock must be held for write */ -void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry, - struct vfsmount *child_mnt) +void mnt_set_mountpoint(struct mount *mnt, struct dentry *dentry, + struct mount *child_mnt) { - child_mnt->mnt_parent = mntget(mnt); + mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = dget(dentry); + child_mnt->mnt_parent = mnt; spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); @@ -595,15 +615,15 @@ void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry, /* * vfsmount lock must be held for write */ -static void attach_mnt(struct vfsmount *mnt, struct path *path) +static void attach_mnt(struct mount *mnt, struct path *path) { - mnt_set_mountpoint(path->mnt, path->dentry, mnt); + mnt_set_mountpoint(real_mount(path->mnt), path->dentry, mnt); list_add_tail(&mnt->mnt_hash, mount_hashtable + hash(path->mnt, path->dentry)); - list_add_tail(&mnt->mnt_child, &path->mnt->mnt_mounts); + list_add_tail(&mnt->mnt_child, &real_mount(path->mnt)->mnt_mounts); } -static inline void __mnt_make_longterm(struct vfsmount *mnt) +static inline void __mnt_make_longterm(struct mount *mnt) { #ifdef CONFIG_SMP atomic_inc(&mnt->mnt_longterm); @@ -611,7 +631,7 @@ static inline void __mnt_make_longterm(struct vfsmount *mnt) } /* needs vfsmount lock for write */ -static inline void __mnt_make_shortterm(struct vfsmount *mnt) +static inline void __mnt_make_shortterm(struct mount *mnt) { #ifdef CONFIG_SMP atomic_dec(&mnt->mnt_longterm); @@ -621,10 +641,10 @@ static inline void __mnt_make_shortterm(struct vfsmount *mnt) /* * vfsmount lock must be held for write */ -static void commit_tree(struct vfsmount *mnt) +static void commit_tree(struct mount *mnt) { - struct vfsmount *parent = mnt->mnt_parent; - struct vfsmount *m; + struct mount *parent = mnt->mnt_parent; + struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; @@ -639,12 +659,12 @@ static void commit_tree(struct vfsmount *mnt) list_splice(&head, n->list.prev); list_add_tail(&mnt->mnt_hash, mount_hashtable + - hash(parent, mnt->mnt_mountpoint)); + hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); touch_mnt_namespace(n); } -static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root) +static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { @@ -657,14 +677,14 @@ static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root) p = p->mnt_parent; } } - return list_entry(next, struct vfsmount, mnt_child); + return list_entry(next, struct mount, mnt_child); } -static struct vfsmount *skip_mnt_tree(struct vfsmount *p) +static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { - p = list_entry(prev, struct vfsmount, mnt_child); + p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; @@ -673,7 +693,7 @@ static struct vfsmount *skip_mnt_tree(struct vfsmount *p) struct vfsmount * vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { - struct vfsmount *mnt; + struct mount *mnt; struct dentry *root; if (!type) @@ -684,7 +704,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void return ERR_PTR(-ENOMEM); if (flags & MS_KERNMOUNT) - mnt->mnt_flags = MNT_INTERNAL; + mnt->mnt.mnt_flags = MNT_INTERNAL; root = mount_fs(type, flags, name, data); if (IS_ERR(root)) { @@ -692,19 +712,22 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void return ERR_CAST(root); } - mnt->mnt_root = root; - mnt->mnt_sb = root->d_sb; - mnt->mnt_mountpoint = mnt->mnt_root; + mnt->mnt.mnt_root = root; + mnt->mnt.mnt_sb = root->d_sb; + mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; - return mnt; + br_write_lock(vfsmount_lock); + list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts); + br_write_unlock(vfsmount_lock); + return &mnt->mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); -static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, +static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { - struct super_block *sb = old->mnt_sb; - struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname); + struct super_block *sb = old->mnt.mnt_sb; + struct mount *mnt = alloc_vfsmnt(old->mnt_devname); if (mnt) { if (flag & (CL_SLAVE | CL_PRIVATE)) @@ -718,12 +741,15 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, goto out_free; } - mnt->mnt_flags = old->mnt_flags & ~MNT_WRITE_HOLD; + mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD; atomic_inc(&sb->s_active); - mnt->mnt_sb = sb; - mnt->mnt_root = dget(root); - mnt->mnt_mountpoint = mnt->mnt_root; + mnt->mnt.mnt_sb = sb; + mnt->mnt.mnt_root = dget(root); + mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; + br_write_lock(vfsmount_lock); + list_add_tail(&mnt->mnt_instance, &sb->s_mounts); + br_write_unlock(vfsmount_lock); if (flag & CL_SLAVE) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); @@ -753,9 +779,10 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, return NULL; } -static inline void mntfree(struct vfsmount *mnt) +static inline void mntfree(struct mount *mnt) { - struct super_block *sb = mnt->mnt_sb; + struct vfsmount *m = &mnt->mnt; + struct super_block *sb = m->mnt_sb; /* * This probably indicates that somebody messed @@ -768,32 +795,32 @@ static inline void mntfree(struct vfsmount *mnt) * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); - fsnotify_vfsmount_delete(mnt); - dput(mnt->mnt_root); + fsnotify_vfsmount_delete(m); + dput(m->mnt_root); free_vfsmnt(mnt); deactivate_super(sb); } -static void mntput_no_expire(struct vfsmount *mnt) +static void mntput_no_expire(struct mount *mnt) { put_again: #ifdef CONFIG_SMP br_read_lock(vfsmount_lock); if (likely(atomic_read(&mnt->mnt_longterm))) { - mnt_dec_count(mnt); + mnt_add_count(mnt, -1); br_read_unlock(vfsmount_lock); return; } br_read_unlock(vfsmount_lock); br_write_lock(vfsmount_lock); - mnt_dec_count(mnt); + mnt_add_count(mnt, -1); if (mnt_get_count(mnt)) { br_write_unlock(vfsmount_lock); return; } #else - mnt_dec_count(mnt); + mnt_add_count(mnt, -1); if (likely(mnt_get_count(mnt))) return; br_write_lock(vfsmount_lock); @@ -802,9 +829,10 @@ put_again: mnt_add_count(mnt, mnt->mnt_pinned + 1); mnt->mnt_pinned = 0; br_write_unlock(vfsmount_lock); - acct_auto_close_mnt(mnt); + acct_auto_close_mnt(&mnt->mnt); goto put_again; } + list_del(&mnt->mnt_instance); br_write_unlock(vfsmount_lock); mntfree(mnt); } @@ -812,10 +840,11 @@ put_again: void mntput(struct vfsmount *mnt) { if (mnt) { + struct mount *m = real_mount(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); + if (unlikely(m->mnt_expiry_mark)) + m->mnt_expiry_mark = 0; + mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); @@ -823,7 +852,7 @@ EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) - mnt_inc_count(mnt); + mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); @@ -831,16 +860,17 @@ EXPORT_SYMBOL(mntget); void mnt_pin(struct vfsmount *mnt) { br_write_lock(vfsmount_lock); - mnt->mnt_pinned++; + real_mount(mnt)->mnt_pinned++; br_write_unlock(vfsmount_lock); } EXPORT_SYMBOL(mnt_pin); -void mnt_unpin(struct vfsmount *mnt) +void mnt_unpin(struct vfsmount *m) { + struct mount *mnt = real_mount(m); br_write_lock(vfsmount_lock); if (mnt->mnt_pinned) { - mnt_inc_count(mnt); + mnt_add_count(mnt, 1); mnt->mnt_pinned--; } br_write_unlock(vfsmount_lock); @@ -858,12 +888,12 @@ static inline void mangle(struct seq_file *m, const char *s) * * See also save_mount_options(). */ -int generic_show_options(struct seq_file *m, struct vfsmount *mnt) +int generic_show_options(struct seq_file *m, struct dentry *root) { const char *options; rcu_read_lock(); - options = rcu_dereference(mnt->mnt_sb->s_options); + options = rcu_dereference(root->d_sb->s_options); if (options != NULL && options[0]) { seq_putc(m, ','); @@ -907,10 +937,10 @@ void replace_mount_options(struct super_block *sb, char *options) EXPORT_SYMBOL(replace_mount_options); #ifdef CONFIG_PROC_FS -/* iterator */ +/* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { - struct proc_mounts *p = m->private; + struct proc_mounts *p = container_of(m, struct proc_mounts, m); down_read(&namespace_sem); return seq_list_start(&p->ns->list, *pos); @@ -918,7 +948,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - struct proc_mounts *p = m->private; + struct proc_mounts *p = container_of(m, struct proc_mounts, m); return seq_list_next(v, &p->ns->list, pos); } @@ -928,219 +958,18 @@ static void m_stop(struct seq_file *m, void *v) up_read(&namespace_sem); } -int mnt_had_events(struct proc_mounts *p) +static int m_show(struct seq_file *m, void *v) { - 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; -}; - -static int show_sb_opts(struct seq_file *m, struct super_block *sb) -{ - static const struct proc_fs_info fs_info[] = { - { MS_SYNCHRONOUS, ",sync" }, - { MS_DIRSYNC, ",dirsync" }, - { MS_MANDLOCK, ",mand" }, - { 0, NULL } - }; - const struct proc_fs_info *fs_infop; - - for (fs_infop = fs_info; fs_infop->flag; fs_infop++) { - if (sb->s_flags & fs_infop->flag) - seq_puts(m, fs_infop->str); - } - - return security_sb_show_options(m, sb); -} - -static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) -{ - static const struct proc_fs_info mnt_info[] = { - { MNT_NOSUID, ",nosuid" }, - { MNT_NODEV, ",nodev" }, - { MNT_NOEXEC, ",noexec" }, - { MNT_NOATIME, ",noatime" }, - { MNT_NODIRATIME, ",nodiratime" }, - { MNT_RELATIME, ",relatime" }, - { 0, NULL } - }; - const struct proc_fs_info *fs_infop; - - for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) { - if (mnt->mnt_flags & fs_infop->flag) - seq_puts(m, fs_infop->str); - } -} - -static void show_type(struct seq_file *m, struct super_block *sb) -{ - mangle(m, sb->s_type->name); - if (sb->s_subtype && sb->s_subtype[0]) { - seq_putc(m, '.'); - mangle(m, sb->s_subtype); - } -} - -static int show_vfsmnt(struct seq_file *m, void *v) -{ - struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list); - int err = 0; - struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - - 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, ' '); - show_type(m, mnt->mnt_sb); - seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw"); - err = show_sb_opts(m, mnt->mnt_sb); - if (err) - goto out; - show_mnt_opts(m, mnt); - if (mnt->mnt_sb->s_op->show_options) - err = mnt->mnt_sb->s_op->show_options(m, mnt); - seq_puts(m, " 0 0\n"); -out: - return err; + struct proc_mounts *p = container_of(m, struct proc_mounts, m); + struct mount *r = list_entry(v, struct mount, mnt_list); + return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, - .show = show_vfsmnt -}; - -static int show_mountinfo(struct seq_file *m, void *v) -{ - struct proc_mounts *p = m->private; - struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list); - struct super_block *sb = mnt->mnt_sb; - struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - struct path root = p->root; - int err = 0; - - seq_printf(m, "%i %i %u:%u ", mnt->mnt_id, mnt->mnt_parent->mnt_id, - MAJOR(sb->s_dev), MINOR(sb->s_dev)); - 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, ' '); - - /* mountpoints outside of chroot jail will give SEQ_SKIP on this */ - err = seq_path_root(m, &mnt_path, &root, " \t\n\\"); - if (err) - goto out; - - seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw"); - show_mnt_opts(m, mnt); - - /* Tagged fields ("foo:X" or "bar") */ - if (IS_MNT_SHARED(mnt)) - seq_printf(m, " shared:%i", mnt->mnt_group_id); - if (IS_MNT_SLAVE(mnt)) { - int master = mnt->mnt_master->mnt_group_id; - int dom = get_dominating_id(mnt, &p->root); - seq_printf(m, " master:%i", master); - if (dom && dom != master) - seq_printf(m, " propagate_from:%i", dom); - } - if (IS_MNT_UNBINDABLE(mnt)) - seq_puts(m, " unbindable"); - - /* Filesystem specific data */ - seq_puts(m, " - "); - show_type(m, sb); - seq_putc(m, ' '); - 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) - goto out; - if (sb->s_op->show_options) - err = sb->s_op->show_options(m, mnt); - seq_putc(m, '\n'); -out: - return err; -} - -const struct seq_operations mountinfo_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_mountinfo, -}; - -static int show_vfsstat(struct seq_file *m, void *v) -{ - struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list); - struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; - int err = 0; - - /* device */ - if (mnt->mnt_sb->s_op->show_devname) { - seq_puts(m, "device "); - 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 "); - seq_path(m, &mnt_path, " \t\n\\"); - seq_putc(m, ' '); - - /* file system type */ - seq_puts(m, "with fstype "); - show_type(m, mnt->mnt_sb); - - /* optional statistics */ - if (mnt->mnt_sb->s_op->show_stats) { - seq_putc(m, ' '); - if (!err) - err = mnt->mnt_sb->s_op->show_stats(m, mnt); - } - - seq_putc(m, '\n'); - return err; -} - -const struct seq_operations mountstats_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = show_vfsstat, + .show = m_show, }; #endif /* CONFIG_PROC_FS */ @@ -1152,11 +981,13 @@ const struct seq_operations mountstats_op = { * open files, pwds, chroots or sub mounts that are * busy. */ -int may_umount_tree(struct vfsmount *mnt) +int may_umount_tree(struct vfsmount *m) { + struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; - struct vfsmount *p; + struct mount *p; + BUG_ON(!m); /* write lock needed for mnt_get_count */ br_write_lock(vfsmount_lock); @@ -1192,7 +1023,7 @@ int may_umount(struct vfsmount *mnt) int ret = 1; down_read(&namespace_sem); br_write_lock(vfsmount_lock); - if (propagate_mount_busy(mnt, 2)) + if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; br_write_unlock(vfsmount_lock); up_read(&namespace_sem); @@ -1203,25 +1034,25 @@ EXPORT_SYMBOL(may_umount); void release_mounts(struct list_head *head) { - struct vfsmount *mnt; + struct mount *mnt; while (!list_empty(head)) { - mnt = list_first_entry(head, struct vfsmount, mnt_hash); + mnt = list_first_entry(head, struct mount, mnt_hash); list_del_init(&mnt->mnt_hash); - if (mnt->mnt_parent != mnt) { + if (mnt_has_parent(mnt)) { struct dentry *dentry; - struct vfsmount *m; + struct mount *m; br_write_lock(vfsmount_lock); dentry = mnt->mnt_mountpoint; m = mnt->mnt_parent; - mnt->mnt_mountpoint = mnt->mnt_root; + mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; m->mnt_ghosts--; br_write_unlock(vfsmount_lock); dput(dentry); - mntput(m); + mntput(&m->mnt); } - mntput(mnt); + mntput(&mnt->mnt); } } @@ -1229,10 +1060,10 @@ void release_mounts(struct list_head *head) * 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) +void umount_tree(struct mount *mnt, int propagate, struct list_head *kill) { LIST_HEAD(tmp_list); - struct vfsmount *p; + struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) list_move(&p->mnt_hash, &tmp_list); @@ -1247,24 +1078,24 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill) p->mnt_ns = NULL; __mnt_make_shortterm(p); list_del_init(&p->mnt_child); - if (p->mnt_parent != p) { + if (mnt_has_parent(p)) { p->mnt_parent->mnt_ghosts++; - dentry_reset_mounted(p->mnt_parent, p->mnt_mountpoint); + dentry_reset_mounted(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); +static void shrink_submounts(struct mount *mnt, struct list_head *umounts); -static int do_umount(struct vfsmount *mnt, int flags) +static int do_umount(struct mount *mnt, int flags) { - struct super_block *sb = mnt->mnt_sb; + struct super_block *sb = mnt->mnt.mnt_sb; int retval; LIST_HEAD(umount_list); - retval = security_sb_umount(mnt, flags); + retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; @@ -1275,7 +1106,7 @@ static int do_umount(struct vfsmount *mnt, int flags) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { - if (mnt == current->fs->root.mnt || + if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; @@ -1317,7 +1148,7 @@ static int do_umount(struct vfsmount *mnt, int flags) * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ - if (mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { + if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. @@ -1359,6 +1190,7 @@ static int do_umount(struct vfsmount *mnt, int flags) SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { struct path path; + struct mount *mnt; int retval; int lookup_flags = 0; @@ -1371,21 +1203,22 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) retval = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (retval) goto out; + mnt = real_mount(path.mnt); retval = -EINVAL; if (path.dentry != path.mnt->mnt_root) goto dput_and_out; - if (!check_mnt(path.mnt)) + if (!check_mnt(mnt)) goto dput_and_out; retval = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto dput_and_out; - retval = do_umount(path.mnt, flags); + retval = do_umount(mnt, flags); dput_and_out: /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path.dentry); - mntput_no_expire(path.mnt); + mntput_no_expire(mnt); out: return retval; } @@ -1420,10 +1253,10 @@ static int mount_is_safe(struct path *path) #endif } -struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, +struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, int flag) { - struct vfsmount *res, *p, *q, *r, *s; + struct mount *res, *p, *q, *r; struct path path; if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt)) @@ -1436,6 +1269,7 @@ struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, p = mnt; list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) { + struct mount *s; if (!is_subdir(r->mnt_mountpoint, dentry)) continue; @@ -1449,9 +1283,9 @@ struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, q = q->mnt_parent; } p = s; - path.mnt = q; + path.mnt = &q->mnt; path.dentry = p->mnt_mountpoint; - q = clone_mnt(p, p->mnt_root, flag); + q = clone_mnt(p, p->mnt.mnt_root, flag); if (!q) goto Enomem; br_write_lock(vfsmount_lock); @@ -1474,11 +1308,12 @@ Enomem: struct vfsmount *collect_mounts(struct path *path) { - struct vfsmount *tree; + struct mount *tree; down_write(&namespace_sem); - tree = copy_tree(path->mnt, path->dentry, CL_COPY_ALL | CL_PRIVATE); + tree = copy_tree(real_mount(path->mnt), path->dentry, + CL_COPY_ALL | CL_PRIVATE); up_write(&namespace_sem); - return tree; + return tree ? &tree->mnt : NULL; } void drop_collected_mounts(struct vfsmount *mnt) @@ -1486,7 +1321,7 @@ void drop_collected_mounts(struct vfsmount *mnt) LIST_HEAD(umount_list); down_write(&namespace_sem); br_write_lock(vfsmount_lock); - umount_tree(mnt, 0, &umount_list); + umount_tree(real_mount(mnt), 0, &umount_list); br_write_unlock(vfsmount_lock); up_write(&namespace_sem); release_mounts(&umount_list); @@ -1495,21 +1330,21 @@ void drop_collected_mounts(struct vfsmount *mnt) int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { - struct vfsmount *mnt; + struct mount *mnt; int res = f(root, a |