X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fnamespace.c;h=5ef336c1103c2c4a4ecbb5c9bf96cf8923e15454;hb=58637ec90b7ceed5909e726ac90118852f79d2b1;hp=4abee9ab009f2c2dd3603b982cdca1152c3dbd8e;hpb=390c684367de37e1c2f9005cf92f7a746c69fdd3;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/namespace.c b/fs/namespace.c index 4abee9a..5ef336c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -8,46 +8,41 @@ * Heavily rewritten. */ -#include #include #include #include #include #include +#include #include #include +#include #include +#include #include -#include +#include #include #include #include +#include #include #include - -extern int __init init_rootfs(void); - -#define CL_EXPIRE 0x01 - -#ifdef CONFIG_SYSFS -extern int __init sysfs_init(void); -#else -static inline int sysfs_init(void) -{ - return 0; -} -#endif +#include "pnode.h" /* spinlock for vfsmount related operations, inplace of dcache_lock */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock); static int event; -static struct list_head *mount_hashtable; +static struct list_head *mount_hashtable __read_mostly; static int hash_mask __read_mostly, hash_bits __read_mostly; -static kmem_cache_t *mnt_cache; +static struct kmem_cache *mnt_cache __read_mostly; static struct rw_semaphore namespace_sem; +/* /sys/fs */ +decl_subsys(fs, NULL, NULL); +EXPORT_SYMBOL_GPL(fs_subsys); + static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); @@ -67,6 +62,9 @@ struct vfsmount *alloc_vfsmnt(const char *name) INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); + INIT_LIST_HEAD(&mnt->mnt_share); + INIT_LIST_HEAD(&mnt->mnt_slave_list); + INIT_LIST_HEAD(&mnt->mnt_slave); if (name) { int size = strlen(name) + 1; char *newname = kmalloc(size, GFP_KERNEL); @@ -79,6 +77,15 @@ struct vfsmount *alloc_vfsmnt(const char *name) return mnt; } +int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb) +{ + mnt->mnt_sb = sb; + mnt->mnt_root = dget(sb->s_root); + return 0; +} + +EXPORT_SYMBOL(simple_set_mnt); + void free_vfsmnt(struct vfsmount *mnt) { kfree(mnt->mnt_devname); @@ -86,37 +93,50 @@ void free_vfsmnt(struct vfsmount *mnt) } /* - * Now, lookup_mnt increments the ref count before returning - * the vfsmount struct. + * 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. */ -struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) +struct vfsmount *__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; - spin_lock(&vfsmount_lock); for (;;) { - tmp = tmp->next; + 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) { - found = mntget(p); + found = p; break; } } - spin_unlock(&vfsmount_lock); return found; } +/* + * lookup_mnt increments the ref count before returning + * the vfsmount struct. + */ +struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) +{ + struct vfsmount *child_mnt; + spin_lock(&vfsmount_lock); + if ((child_mnt = __lookup_mnt(mnt, dentry, 1))) + mntget(child_mnt); + spin_unlock(&vfsmount_lock); + return child_mnt; +} + static inline int check_mnt(struct vfsmount *mnt) { - return mnt->mnt_namespace == current->namespace; + return mnt->mnt_ns == current->nsproxy->mnt_ns; } -static void touch_namespace(struct namespace *ns) +static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; @@ -124,7 +144,7 @@ static void touch_namespace(struct namespace *ns) } } -static void __touch_namespace(struct namespace *ns) +static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; @@ -143,13 +163,43 @@ static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd) old_nd->dentry->d_mounted--; } +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++; +} + static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd) { - mnt->mnt_parent = mntget(nd->mnt); - mnt->mnt_mountpoint = dget(nd->dentry); - list_add(&mnt->mnt_hash, mount_hashtable + hash(nd->mnt, nd->dentry)); + mnt_set_mountpoint(nd->mnt, nd->dentry, mnt); + list_add_tail(&mnt->mnt_hash, mount_hashtable + + hash(nd->mnt, nd->dentry)); list_add_tail(&mnt->mnt_child, &nd->mnt->mnt_mounts); - nd->dentry->d_mounted++; +} + +/* + * the caller must hold vfsmount_lock + */ +static void commit_tree(struct vfsmount *mnt) +{ + struct vfsmount *parent = mnt->mnt_parent; + struct vfsmount *m; + LIST_HEAD(head); + struct mnt_namespace *n = parent->mnt_ns; + + BUG_ON(parent == mnt); + + list_add_tail(&head, &mnt->mnt_list); + list_for_each_entry(m, &head, mnt_list) + m->mnt_ns = n; + list_splice(&head, n->list.prev); + + list_add_tail(&mnt->mnt_hash, mount_hashtable + + hash(parent, 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) @@ -168,6 +218,16 @@ static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root) return list_entry(next, struct vfsmount, mnt_child); } +static struct vfsmount *skip_mnt_tree(struct vfsmount *p) +{ + struct list_head *prev = p->mnt_mounts.prev; + while (prev != &p->mnt_mounts) { + p = list_entry(prev, struct vfsmount, mnt_child); + prev = p->mnt_mounts.prev; + } + return p; +} + static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, int flag) { @@ -181,7 +241,20 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, mnt->mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt_root; mnt->mnt_parent = mnt; - mnt->mnt_namespace = current->namespace; + + if (flag & CL_SLAVE) { + list_add(&mnt->mnt_slave, &old->mnt_slave_list); + mnt->mnt_master = old; + CLEAR_MNT_SHARED(mnt); + } else { + if ((flag & CL_PROPAGATION) || 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); + mnt->mnt_master = old->mnt_master; + } + if (flag & CL_MAKE_SHARED) + set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ @@ -247,7 +320,7 @@ EXPORT_SYMBOL(mnt_unpin); /* iterator */ static void *m_start(struct seq_file *m, loff_t *pos) { - struct namespace *n = m->private; + struct mnt_namespace *n = m->private; struct list_head *p; loff_t l = *pos; @@ -260,7 +333,7 @@ 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 namespace *n = m->private; + struct mnt_namespace *n = m->private; struct list_head *p = ((struct vfsmount *)v)->mnt_list.next; (*pos)++; return p == &n->list ? NULL : list_entry(p, struct vfsmount, mnt_list); @@ -287,14 +360,15 @@ static int show_vfsmnt(struct seq_file *m, void *v) { MS_SYNCHRONOUS, ",sync" }, { MS_DIRSYNC, ",dirsync" }, { MS_MANDLOCK, ",mand" }, - { MS_NOATIME, ",noatime" }, - { MS_NODIRATIME, ",nodiratime" }, { 0, NULL } }; static 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 } }; struct proc_fs_info *fs_infop; @@ -326,6 +400,44 @@ struct seq_operations mounts_op = { .show = show_vfsmnt }; +static int show_vfsstat(struct seq_file *m, void *v) +{ + struct vfsmount *mnt = v; + int err = 0; + + /* device */ + 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, mnt->mnt_root, " \t\n\\"); + seq_putc(m, ' '); + + /* file system type */ + seq_puts(m, "with fstype "); + mangle(m, mnt->mnt_sb->s_type->name); + + /* optional statistics */ + if (mnt->mnt_sb->s_op->show_stats) { + seq_putc(m, ' '); + err = mnt->mnt_sb->s_op->show_stats(m, mnt); + } + + seq_putc(m, '\n'); + return err; +} + +struct seq_operations mountstats_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = show_vfsstat, +}; + /** * may_umount_tree - check if a mount tree is busy * @mnt: root of mount tree @@ -348,9 +460,9 @@ int may_umount_tree(struct vfsmount *mnt) spin_unlock(&vfsmount_lock); if (actual_refs > minimum_refs) - return -EBUSY; + return 0; - return 0; + return 1; } EXPORT_SYMBOL(may_umount_tree); @@ -370,17 +482,20 @@ EXPORT_SYMBOL(may_umount_tree); */ int may_umount(struct vfsmount *mnt) { - if (atomic_read(&mnt->mnt_count) > 2) - return -EBUSY; - return 0; + int ret = 1; + spin_lock(&vfsmount_lock); + if (propagate_mount_busy(mnt, 2)) + ret = 0; + spin_unlock(&vfsmount_lock); + return ret; } EXPORT_SYMBOL(may_umount); -static void release_mounts(struct list_head *head) +void release_mounts(struct list_head *head) { struct vfsmount *mnt; - while(!list_empty(head)) { + while (!list_empty(head)) { mnt = list_entry(head->next, struct vfsmount, mnt_hash); list_del_init(&mnt->mnt_hash); if (mnt->mnt_parent != mnt) { @@ -399,23 +514,25 @@ static void release_mounts(struct list_head *head) } } -static void umount_tree(struct vfsmount *mnt, struct list_head *kill) +void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill) { struct vfsmount *p; - for (p = mnt; p; p = next_mnt(p, mnt)) { - list_del(&p->mnt_hash); - list_add(&p->mnt_hash, kill); - } + for (p = mnt; p; p = next_mnt(p, mnt)) + list_move(&p->mnt_hash, kill); + + if (propagate) + propagate_umount(kill); list_for_each_entry(p, kill, mnt_hash) { list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); - __touch_namespace(p->mnt_namespace); - p->mnt_namespace = NULL; + __touch_mnt_namespace(p->mnt_ns); + p->mnt_ns = NULL; list_del_init(&p->mnt_child); if (p->mnt_parent != p) - mnt->mnt_mountpoint->d_mounted--; + p->mnt_mountpoint->d_mounted--; + change_mnt_propagation(p, MS_PRIVATE); } } @@ -458,8 +575,8 @@ static int do_umount(struct vfsmount *mnt, int flags) */ lock_kernel(); - if ((flags & MNT_FORCE) && sb->s_op->umount_begin) - sb->s_op->umount_begin(sb); + if (sb->s_op->umount_begin) + sb->s_op->umount_begin(mnt, flags); unlock_kernel(); /* @@ -492,9 +609,9 @@ static int do_umount(struct vfsmount *mnt, int flags) event++; retval = -EBUSY; - if (atomic_read(&mnt->mnt_count) == 2 || flags & MNT_DETACH) { + if (flags & MNT_DETACH || !propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) - umount_tree(mnt, &umount_list); + umount_tree(mnt, 1, &umount_list); retval = 0; } spin_unlock(&vfsmount_lock); @@ -562,7 +679,7 @@ static int mount_is_safe(struct nameidata *nd) if (current->uid != nd->dentry->d_inode->i_uid) return -EPERM; } - if (permission(nd->dentry->d_inode, MAY_WRITE, nd)) + if (vfs_permission(nd, MAY_WRITE)) return -EPERM; return 0; #endif @@ -579,12 +696,15 @@ static int lives_below_in_same_fs(struct dentry *d, struct dentry *dentry) } } -static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, +struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, int flag) { struct vfsmount *res, *p, *q, *r, *s; struct nameidata nd; + if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt)) + return NULL; + res = q = clone_mnt(mnt, dentry, flag); if (!q) goto Enomem; @@ -596,6 +716,10 @@ static struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, continue; for (s = r; s; s = next_mnt(s, r)) { + if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(s)) { + s = skip_mnt_tree(s); + continue; + } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; @@ -617,13 +741,110 @@ Enomem: if (res) { LIST_HEAD(umount_list); spin_lock(&vfsmount_lock); - umount_tree(res, &umount_list); + umount_tree(res, 0, &umount_list); spin_unlock(&vfsmount_lock); release_mounts(&umount_list); } return NULL; } +/* + * @source_mnt : mount tree to be attached + * @nd : place the mount tree @source_mnt is attached + * @parent_nd : if non-null, detach the source_mnt from its parent and + * store the parent mount and mountpoint dentry. + * (done when source_mnt is moved) + * + * NOTE: in the table below explains the semantics when a source mount + * of a given type is attached to a destination mount of a given type. + * --------------------------------------------------------------------------- + * | BIND MOUNT OPERATION | + * |************************************************************************** + * | source-->| shared | private | slave | unbindable | + * | dest | | | | | + * | | | | | | | + * | v | | | | | + * |************************************************************************** + * | shared | shared (++) | shared (+) | shared(+++)| invalid | + * | | | | | | + * |non-shared| shared (+) | private | slave (*) | invalid | + * *************************************************************************** + * A bind operation clones the source mount and mounts the clone on the + * destination mount. + * + * (++) the cloned mount is propagated to all the mounts in the propagation + * tree of the destination mount and the cloned mount is added to + * the peer group of the source mount. + * (+) the cloned mount is created under the destination mount and is marked + * as shared. The cloned mount is added to the peer group of the source + * mount. + * (+++) the mount is propagated to all the mounts in the propagation tree + * of the destination mount and the cloned mount is made slave + * of the same master as that of the source mount. The cloned mount + * is marked as 'shared and slave'. + * (*) the cloned mount is made a slave of the same master as that of the + * source mount. + * + * --------------------------------------------------------------------------- + * | MOVE MOUNT OPERATION | + * |************************************************************************** + * | source-->| shared | private | slave | unbindable | + * | dest | | | | | + * | | | | | | | + * | v | | | | | + * |************************************************************************** + * | shared | shared (+) | shared (+) | shared(+++) | invalid | + * | | | | | | + * |non-shared| shared (+*) | private | slave (*) | unbindable | + * *************************************************************************** + * + * (+) the mount is moved to the destination. And is then propagated to + * all the mounts in the propagation tree of the destination mount. + * (+*) the mount is moved to the destination. + * (+++) the mount is moved to the destination and is then propagated to + * all the mounts belonging to the destination mount's propagation tree. + * the mount is marked as 'shared and slave'. + * (*) the mount continues to be a slave at the new location. + * + * if the source mount is a tree, the operations explained above is + * applied to each mount in the tree. + * Must be called without spinlocks held, since this function can sleep + * in allocations. + */ +static int attach_recursive_mnt(struct vfsmount *source_mnt, + struct nameidata *nd, struct nameidata *parent_nd) +{ + LIST_HEAD(tree_list); + struct vfsmount *dest_mnt = nd->mnt; + struct dentry *dest_dentry = nd->dentry; + struct vfsmount *child, *p; + + if (propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list)) + return -EINVAL; + + 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_nd) { + detach_mnt(source_mnt, parent_nd); + attach_mnt(source_mnt, nd); + touch_mnt_namespace(current->nsproxy->mnt_ns); + } else { + mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt); + commit_tree(source_mnt); + } + + list_for_each_entry_safe(child, p, &tree_list, mnt_hash) { + list_del_init(&child->mnt_hash); + commit_tree(child); + } + spin_unlock(&vfsmount_lock); + return 0; +} + static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) { int err; @@ -635,7 +856,7 @@ static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) return -ENOTDIR; err = -ENOENT; - down(&nd->dentry->d_inode->i_sem); + mutex_lock(&nd->dentry->d_inode->i_mutex); if (IS_DEADDIR(nd->dentry->d_inode)) goto out_unlock; @@ -644,25 +865,37 @@ static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) goto out_unlock; err = -ENOENT; - spin_lock(&vfsmount_lock); - if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) { - struct list_head head; - - attach_mnt(mnt, nd); - list_add_tail(&head, &mnt->mnt_list); - list_splice(&head, current->namespace->list.prev); - err = 0; - touch_namespace(current->namespace); - } - spin_unlock(&vfsmount_lock); + if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) + err = attach_recursive_mnt(mnt, nd, NULL); out_unlock: - up(&nd->dentry->d_inode->i_sem); + mutex_unlock(&nd->dentry->d_inode->i_mutex); if (!err) security_sb_post_addmount(mnt, nd); return err; } /* + * recursively change the type of the mountpoint. + */ +static int do_change_type(struct nameidata *nd, int flag) +{ + struct vfsmount *m, *mnt = nd->mnt; + int recurse = flag & MS_REC; + int type = flag & ~MS_REC; + + if (nd->dentry != nd->mnt->mnt_root) + return -EINVAL; + + down_write(&namespace_sem); + spin_lock(&vfsmount_lock); + for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) + change_mnt_propagation(m, type); + spin_unlock(&vfsmount_lock); + up_write(&namespace_sem); + return 0; +} + +/* * do loopback mount. */ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) @@ -680,6 +913,9 @@ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) down_write(&namespace_sem); err = -EINVAL; + if (IS_MNT_UNBINDABLE(old_nd.mnt)) + goto out; + if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt)) goto out; @@ -696,7 +932,7 @@ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) if (err) { LIST_HEAD(umount_list); spin_lock(&vfsmount_lock); - umount_tree(mnt, &umount_list); + umount_tree(mnt, 0, &umount_list); spin_unlock(&vfsmount_lock); release_mounts(&umount_list); } @@ -737,6 +973,16 @@ static int do_remount(struct nameidata *nd, int flags, int mnt_flags, return err; } +static inline int tree_contains_unbindable(struct vfsmount *mnt) +{ + struct vfsmount *p; + for (p = mnt; p; p = next_mnt(p, mnt)) { + if (IS_MNT_UNBINDABLE(p)) + return 1; + } + return 0; +} + static int do_move_mount(struct nameidata *nd, char *old_name) { struct nameidata old_nd, parent_nd; @@ -758,42 +1004,49 @@ static int do_move_mount(struct nameidata *nd, char *old_name) goto out; err = -ENOENT; - down(&nd->dentry->d_inode->i_sem); + mutex_lock(&nd->dentry->d_inode->i_mutex); if (IS_DEADDIR(nd->dentry->d_inode)) goto out1; - spin_lock(&vfsmount_lock); if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry)) - goto out2; + goto out1; err = -EINVAL; if (old_nd.dentry != old_nd.mnt->mnt_root) - goto out2; + goto out1; if (old_nd.mnt == old_nd.mnt->mnt_parent) - goto out2; + goto out1; if (S_ISDIR(nd->dentry->d_inode->i_mode) != S_ISDIR(old_nd.dentry->d_inode->i_mode)) - goto out2; - + goto out1; + /* + * Don't move a mount residing in a shared parent. + */ + if (old_nd.mnt->mnt_parent && IS_MNT_SHARED(old_nd.mnt->mnt_parent)) + goto out1; + /* + * Don't move a mount tree containing unbindable mounts to a destination + * mount which is shared. + */ + if (IS_MNT_SHARED(nd->mnt) && tree_contains_unbindable(old_nd.mnt)) + goto out1; err = -ELOOP; for (p = nd->mnt; p->mnt_parent != p; p = p->mnt_parent) if (p == old_nd.mnt) - goto out2; - err = 0; + goto out1; - detach_mnt(old_nd.mnt, &parent_nd); - attach_mnt(old_nd.mnt, nd); - touch_namespace(current->namespace); + if ((err = attach_recursive_mnt(old_nd.mnt, nd, &parent_nd))) + goto out1; + spin_lock(&vfsmount_lock); /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old_nd.mnt->mnt_expire); -out2: spin_unlock(&vfsmount_lock); out1: - up(&nd->dentry->d_inode->i_sem); + mutex_unlock(&nd->dentry->d_inode->i_mutex); out: up_write(&namespace_sem); if (!err) @@ -891,12 +1144,12 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts, * 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) { + if (!propagate_mount_busy(mnt, 2)) { /* delete from the namespace */ - touch_namespace(mnt->mnt_namespace); + touch_mnt_namespace(mnt->mnt_ns); list_del_init(&mnt->mnt_list); - mnt->mnt_namespace = NULL; - umount_tree(mnt, umounts); + mnt->mnt_ns = NULL; + umount_tree(mnt, 1, umounts); spin_unlock(&vfsmount_lock); } else { /* @@ -909,13 +1162,46 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts, } /* + * 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 + */ +static void expire_mount_list(struct list_head *graveyard, struct list_head *mounts) +{ + struct mnt_namespace *ns; + struct vfsmount *mnt; + + while (!list_empty(graveyard)) { + LIST_HEAD(umounts); + mnt = list_entry(graveyard->next, struct vfsmount, mnt_expire); + list_del_init(&mnt->mnt_expire); + + /* don't do anything if the namespace is dead - all the + * vfsmounts from it are going away anyway */ + ns = mnt->mnt_ns; + if (!ns || !ns->root) + continue; + get_mnt_ns(ns); + + spin_unlock(&vfsmount_lock); + down_write(&namespace_sem); + expire_mount(mnt, mounts, &umounts); + up_write(&namespace_sem); + release_mounts(&umounts); + mntput(mnt); + put_mnt_ns(ns); + spin_lock(&vfsmount_lock); + } +} + +/* * 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); @@ -939,38 +1225,79 @@ void mark_mounts_for_expiry(struct list_head *mounts) list_move(&mnt->mnt_expire, &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)) { - LIST_HEAD(umounts); - mnt = list_entry(graveyard.next, struct vfsmount, mnt_expire); - list_del_init(&mnt->mnt_expire); + expire_mount_list(&graveyard, mounts); - /* don't do anything if the namespace is dead - all the - * vfsmounts from it are going away anyway */ - namespace = mnt->mnt_namespace; - if (!namespace || !namespace->root) + spin_unlock(&vfsmount_lock); +} + +EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); + +/* + * Ripoff of 'select_parent()' + * + * search the list of submounts for a given mountpoint, and move any + * shrinkable submounts to the 'graveyard' list. + */ +static int select_submounts(struct vfsmount *parent, struct list_head *graveyard) +{ + struct vfsmount *this_parent = parent; + struct list_head *next; + int found = 0; + +repeat: + next = this_parent->mnt_mounts.next; +resume: + while (next != &this_parent->mnt_mounts) { + struct list_head *tmp = next; + struct vfsmount *mnt = list_entry(tmp, struct vfsmount, mnt_child); + + next = tmp->next; + if (!(mnt->mnt_flags & MNT_SHRINKABLE)) continue; - get_namespace(namespace); + /* + * Descend a level if the d_mounts list is non-empty. + */ + if (!list_empty(&mnt->mnt_mounts)) { + this_parent = mnt; + goto repeat; + } - spin_unlock(&vfsmount_lock); - down_write(&namespace_sem); - expire_mount(mnt, mounts, &umounts); - up_write(&namespace_sem); - release_mounts(&umounts); - mntput(mnt); - put_namespace(namespace); - spin_lock(&vfsmount_lock); + if (!propagate_mount_busy(mnt, 1)) { + mntget(mnt); + list_move_tail(&mnt->mnt_expire, graveyard); + found++; + } } + /* + * All done at this level ... ascend and resume the search + */ + if (this_parent != parent) { + next = this_parent->mnt_child.next; + this_parent = this_parent->mnt_parent; + goto resume; + } + return found; +} + +/* + * process a list of expirable mountpoints with the intent of discarding any + * submounts of a specific parent mountpoint + */ +void shrink_submounts(struct vfsmount *mountpoint, struct list_head *mounts) +{ + LIST_HEAD(graveyard); + int found; + + spin_lock(&vfsmount_lock); + + /* extract submounts of 'mountpoint' from the expiration list */ + while ((found = select_submounts(mountpoint, &graveyard)) != 0) + expire_mount_list(&graveyard, mounts); spin_unlock(&vfsmount_lock); } -EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); +EXPORT_SYMBOL_GPL(shrink_submounts); /* * Some copy_from_user() implementations do not return the exact number of @@ -1075,7 +1402,15 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; - flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE); + if (flags & MS_NOATIME) + mnt_flags |= MNT_NOATIME; + if (flags & MS_NODIRATIME) + mnt_flags |= MNT_NODIRATIME; + if (flags & MS_RELATIME) + mnt_flags |= MNT_RELATIME; + + flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | + MS_NOATIME | MS_NODIRATIME | MS_RELATIME); /* ... and get the mountpoint */ retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd); @@ -1091,6 +1426,8 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, data_page); else if (flags & MS_BIND) retval = do_loopback(&nd, dev_name, flags & MS_REC); + else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) + retval = do_change_type(&nd, flags); else if (flags & MS_MOVE) retval = do_move_mount(&nd, dev_name); else @@ -1101,30 +1438,21 @@ dput_out: return retval; } -int copy_namespace(int flags, struct task_struct *tsk) +/* + * Allocate a new namespace structure and populate it with contents + * copied from the namespace of the passed in task structure. + */ +struct mnt_namespace *dup_mnt_ns(struct task_struct *tsk, + struct fs_struct *fs) { - struct namespace *namespace = tsk->namespace; - struct namespace *new_ns; + struct mnt_namespace *mnt_ns = tsk->nsproxy->mnt_ns; + struct mnt_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; - - get_namespace(namespace); - - if (!(flags & CLONE_NEWNS)) - return 0; - - if (!capable(CAP_SYS_ADMIN)) { - put_namespace(namespace); - return -EPERM; - } - - new_ns = kmalloc(sizeof(struct namespace), GFP_KERNEL); + new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL); if (!new_ns) - goto out; + return NULL; atomic_set(&new_ns->count, 1); INIT_LIST_HEAD(&new_ns->list); @@ -1133,12 +1461,12 @@ int copy_namespace(int flags, struct task_struct *tsk) down_write(&namespace_sem); /* First pass: copy the tree topology */ - new_ns->root = copy_tree(namespace->root, namespace->root->mnt_root, - CL_EXPIRE); + new_ns->root = copy_tree(mnt_ns->root, mnt_ns->root->mnt_root, + CL_COPY_ALL | CL_EXPIRE); if (!new_ns->root) { up_write(&namespace_sem); kfree(new_ns); - goto out; + return NULL; } spin_lock(&vfsmount_lock); list_add_tail(&new_ns->list, &new_ns->root->mnt_list); @@ -1149,10 +1477,10 @@ int copy_namespace(int flags, struct task_struct *tsk) * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ - p = namespace->root; + p = mnt_ns->root; q = new_ns->root; while (p) { - q->mnt_namespace = new_ns; + q->mnt_ns = new_ns; if (fs) { if (p == fs->rootmnt) { rootmnt = p; @@ -1167,13 +1495,11 @@ int copy_namespace(int flags, struct task_struct *tsk) fs->altrootmnt = mntget(q); } } - p = next_mnt(p, namespace->root); + p = next_mnt(p, mnt_ns->root); q = next_mnt(q, new_ns->root); } up_write(&namespace_sem); - tsk->namespace = new_ns; - if (rootmnt) mntput(rootmnt); if (pwdmnt) @@ -1181,12 +1507,39 @@ int copy_namespace(int flags, struct task_struct *tsk) if (altrootmnt) mntput(altrootmnt); - put_namespace(namespace); - return 0; + return new_ns; +} + +int copy_mnt_ns(int flags, struct task_struct *tsk) +{ + struct mnt_namespace *ns = tsk->nsproxy->mnt_ns; + struct mnt_namespace *new_ns; + int err = 0; + + if (!ns) + return 0; + + get_mnt_ns(ns); + + if (!(flags & CLONE_NEWNS)) + return 0; + + if (!capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto out; + } + + new_ns = dup_mnt_ns(tsk, tsk->fs); + if (!new_ns) { + err = -ENOMEM; + goto out; + } + + tsk->nsproxy->mnt_ns = new_ns; out: - put_namespace(namespace); - return -ENOMEM; + put_mnt_ns(ns); + return err; } asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name, @@ -1313,6 +1666,10 @@ static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd) * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * + * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. + * See Documentation/filesystems/ramfs-rootfs-initramfs.txt for alternatives + * in this situation. + * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) @@ -1356,8 +1713,12 @@ asmlinkage long sys_pivot_root(const char __user * new_root, user_nd.dentry = dget(current->fs->root); read_unlock(¤t->fs->lock); down_write(&namespace_sem); - down(&old_nd.dentry->d_inode->i_sem); + mutex_lock(&old_nd.dentry->d_inode->i_mutex); error = -EINVAL; + if (IS_MNT_SHARED(old_nd.mnt) || + IS_MNT_SHARED(new_nd.mnt->mnt_parent) || + IS_MNT_SHARED(user_nd.mnt->mnt_parent)) + goto out2; if (!check_mnt(user_nd.mnt)) goto out2; error = -ENOENT; @@ -1397,7 +1758,7 @@ asmlinkage long sys_pivot_root(const char __user * new_root, detach_mnt(user_nd.mnt, &root_parent); attach_mnt(user_nd.mnt, &old_nd); /* mount old root on put_old */ attach_mnt(new_nd.mnt, &root_parent); /* mount new_root on / */ - touch_namespace(current->namespace); + touch_mnt_namespace(current->nsproxy->mnt_ns); spin_unlock(&vfsmount_lock); chroot_fs_refs(&user_nd, &new_nd); security_sb_post_pivotroot(&user_nd, &new_nd); @@ -1405,7 +1766,7 @@ asmlinkage long sys_pivot_root(const char __user * new_root, path_release(&root_parent); path_release(&parent_nd); out2: - up(&old_nd.dentry->d_inode->i_sem); + mutex_unlock(&old_nd.dentry->d_inode->i_mutex); up_write(&namespace_sem); path_release(&user_nd); path_release(&old_nd); @@ -1422,33 +1783,27 @@ out3: static void __init init_mount_tree(void) { struct vfsmount *mnt; - struct namespace *namespace; - struct task_struct *g, *p; + struct mnt_namespace *ns; mnt = do_kern_mount("rootfs", 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); - namespace = kmalloc(sizeof(*namespace), GFP_KERNEL); - if (!namespace) + ns = kmalloc(sizeof(*ns), GFP_KERNEL); + if (!ns) panic("Can't allocate initial namespace"); - atomic_set(&namespace->count, 1); - INIT_LIST_HEAD(&namespace->list); - init_waitqueue_head(&namespace->poll); - namespace->event = 0; - list_add(&mnt->mnt_list, &namespace->list); - namespace->root = mnt; - mnt->mnt_namespace = namespace; - - init_task.namespace = namespace; - read_lock(&tasklist_lock); - do_each_thread(g, p) { - get_namespace(namespace); - p->namespace = namespace; - } while_each_thread(g, p); - read_unlock(&tasklist_lock); - - set_fs_pwd(current->fs, namespace->root, namespace->root->mnt_root); - set_fs_root(current->fs, namespace->root, namespace->root->mnt_root); + atomic_set(&ns->count, 1); + INIT_LIST_HEAD(&ns->list); + init_waitqueue_head(&ns->poll); + ns->event = 0; + list_add(&mnt->mnt_list, &ns->list); + ns->root = mnt; + mnt->mnt_ns = ns; + + init_task.nsproxy->mnt_ns = ns; + get_mnt_ns(ns); + + set_fs_pwd(current->fs, ns->root, ns->root->mnt_root); + set_fs_root(current->fs, ns->root, ns->root->mnt_root); } void __init mnt_init(unsigned long mempages) @@ -1456,6 +1811,7 @@ void __init mnt_init(unsigned long mempages) struct list_head *d; unsigned int nr_hash; int i; + int err; init_rwsem(&namespace_sem); @@ -1496,22 +1852,29 @@ void __init mnt_init(unsigned long mempages) d++; i--; } while (i); - sysfs_init(); + err = sysfs_init(); + if (err) + printk(KERN_WARNING "%s: sysfs_init error: %d\n", + __FUNCTION__, err); + err = subsystem_register(&fs_subsys); + if (err) + printk(KERN_WARNING "%s: subsystem_register error: %d\n", + __FUNCTION__, err); init_rootfs(); init_mount_tree(); } -void __put_namespace(struct namespace *namespace) +void __put_mnt_ns(struct mnt_namespace *ns) { - struct vfsmount *root = namespace->root; + struct vfsmount *root = ns->root; LIST_HEAD(umount_list); - namespace->root = NULL; + ns->root = NULL; spin_unlock(&vfsmount_lock); down_write(&namespace_sem); spin_lock(&vfsmount_lock); - umount_tree(root, &umount_list); + umount_tree(root, 0, &umount_list); spin_unlock(&vfsmount_lock); up_write(&namespace_sem); release_mounts(&umount_list); - kfree(namespace); + kfree(ns); }