X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fnamespace.c;h=7953c96a20715a981032b4d7af18e428f39b3ca6;hb=689c04a3904d68343a9258e2de12412e3bb89d09;hp=f0e353f5bc3083fd38dcf19af5d8e8437e7c872e;hpb=1b1dcc1b57a49136f118a0f16367256ff9994a69;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/namespace.c b/fs/namespace.c index f0e353f..7953c96 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -8,58 +8,57 @@ * Heavily rewritten. */ -#include #include #include #include #include #include +#include #include #include +#include #include +#include #include -#include +#include #include #include #include +#include +#include #include #include #include "pnode.h" +#include "internal.h" -extern int __init init_rootfs(void); - -#ifdef CONFIG_SYSFS -extern int __init sysfs_init(void); -#else -static inline int sysfs_init(void) -{ - return 0; -} -#endif +#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 struct list_head *mount_hashtable; -static int hash_mask __read_mostly, hash_bits __read_mostly; -static kmem_cache_t *mnt_cache; +static struct list_head *mount_hashtable __read_mostly; +static struct kmem_cache *mnt_cache __read_mostly; static struct rw_semaphore namespace_sem; +/* /sys/fs */ +struct kobject *fs_kobj; +EXPORT_SYMBOL_GPL(fs_kobj); + static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); - tmp = tmp + (tmp >> hash_bits); - return tmp & hash_mask; + tmp = tmp + (tmp >> HASH_SHIFT); + return tmp & (HASH_SIZE - 1); } struct vfsmount *alloc_vfsmnt(const char *name) { - struct vfsmount *mnt = kmem_cache_alloc(mnt_cache, GFP_KERNEL); + struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { - memset(mnt, 0, sizeof(struct vfsmount)); atomic_set(&mnt->mnt_count, 1); INIT_LIST_HEAD(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); @@ -81,6 +80,15 @@ 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); @@ -128,10 +136,10 @@ struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) 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; @@ -139,7 +147,7 @@ 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; @@ -149,13 +157,13 @@ static void __touch_namespace(struct namespace *ns) static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd) { - old_nd->dentry = mnt->mnt_mountpoint; - old_nd->mnt = mnt->mnt_parent; + old_nd->path.dentry = mnt->mnt_mountpoint; + old_nd->path.mnt = mnt->mnt_parent; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt_root; list_del_init(&mnt->mnt_child); list_del_init(&mnt->mnt_hash); - old_nd->dentry->d_mounted--; + old_nd->path.dentry->d_mounted--; } void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry, @@ -168,10 +176,10 @@ void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry, static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd) { - mnt_set_mountpoint(nd->mnt, nd->dentry, mnt); + mnt_set_mountpoint(nd->path.mnt, nd->path.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); + hash(nd->path.mnt, nd->path.dentry)); + list_add_tail(&mnt->mnt_child, &nd->path.mnt->mnt_mounts); } /* @@ -182,19 +190,19 @@ static void commit_tree(struct vfsmount *mnt) struct vfsmount *parent = mnt->mnt_parent; struct vfsmount *m; LIST_HEAD(head); - struct namespace *n = parent->mnt_namespace; + 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_namespace = n; + 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_namespace(n); + touch_mnt_namespace(n); } static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root) @@ -241,7 +249,7 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root, list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); - } else { + } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_PROPAGATION) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) @@ -312,26 +320,64 @@ void mnt_unpin(struct vfsmount *mnt) EXPORT_SYMBOL(mnt_unpin); +static inline void mangle(struct seq_file *m, const char *s) +{ + seq_escape(m, s, " \t\n\\"); +} + +/* + * Simple .show_options callback for filesystems which don't want to + * implement more complex mount option showing. + * + * See also save_mount_options(). + */ +int generic_show_options(struct seq_file *m, struct vfsmount *mnt) +{ + const char *options = mnt->mnt_sb->s_options; + + if (options != NULL && options[0]) { + seq_putc(m, ','); + mangle(m, options); + } + + return 0; +} +EXPORT_SYMBOL(generic_show_options); + +/* + * If filesystem uses generic_show_options(), this function should be + * called from the fill_super() callback. + * + * The .remount_fs callback usually needs to be handled in a special + * way, to make sure, that previous options are not overwritten if the + * remount fails. + * + * Also note, that if the filesystem's .remount_fs function doesn't + * reset all options to their default value, but changes only newly + * given options, then the displayed options will not reflect reality + * any more. + */ +void save_mount_options(struct super_block *sb, char *options) +{ + kfree(sb->s_options); + sb->s_options = kstrdup(options, GFP_KERNEL); +} +EXPORT_SYMBOL(save_mount_options); + /* iterator */ static void *m_start(struct seq_file *m, loff_t *pos) { - struct namespace *n = m->private; - struct list_head *p; - loff_t l = *pos; + struct mnt_namespace *n = m->private; down_read(&namespace_sem); - list_for_each(p, &n->list) - if (!l--) - return list_entry(p, struct vfsmount, mnt_list); - return NULL; + return seq_list_start(&n->list, *pos); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { - struct 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); + struct mnt_namespace *n = m->private; + + return seq_list_next(v, &n->list, pos); } static void m_stop(struct seq_file *m, void *v) @@ -339,14 +385,9 @@ static void m_stop(struct seq_file *m, void *v) up_read(&namespace_sem); } -static inline void mangle(struct seq_file *m, const char *s) -{ - seq_escape(m, s, " \t\n\\"); -} - static int show_vfsmnt(struct seq_file *m, void *v) { - struct vfsmount *mnt = v; + struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list); int err = 0; static struct proc_fs_info { int flag; @@ -355,23 +396,29 @@ 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; + struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt }; mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none"); seq_putc(m, ' '); - seq_path(m, mnt, mnt->mnt_root, " \t\n\\"); + seq_path(m, &mnt_path, " \t\n\\"); seq_putc(m, ' '); mangle(m, mnt->mnt_sb->s_type->name); + if (mnt->mnt_sb->s_subtype && mnt->mnt_sb->s_subtype[0]) { + seq_putc(m, '.'); + mangle(m, mnt->mnt_sb->s_subtype); + } seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw"); for (fs_infop = fs_info; fs_infop->flag; fs_infop++) { if (mnt->mnt_sb->s_flags & fs_infop->flag) @@ -394,6 +441,45 @@ struct seq_operations mounts_op = { .show = show_vfsmnt }; +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_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 "); + 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 @@ -416,9 +502,9 @@ 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); @@ -438,10 +524,10 @@ EXPORT_SYMBOL(may_umount_tree); */ int may_umount(struct vfsmount *mnt) { - int ret = 0; + int ret = 1; spin_lock(&vfsmount_lock); if (propagate_mount_busy(mnt, 2)) - ret = -EBUSY; + ret = 0; spin_unlock(&vfsmount_lock); return ret; } @@ -452,7 +538,7 @@ void release_mounts(struct list_head *head) { struct vfsmount *mnt; while (!list_empty(head)) { - mnt = list_entry(head->next, struct vfsmount, mnt_hash); + mnt = list_first_entry(head, struct vfsmount, mnt_hash); list_del_init(&mnt->mnt_hash); if (mnt->mnt_parent != mnt) { struct dentry *dentry; @@ -474,10 +560,8 @@ 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); @@ -485,11 +569,11 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *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); } } @@ -511,7 +595,7 @@ 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->rootmnt || + if (mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; @@ -533,8 +617,8 @@ 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(); /* @@ -546,7 +630,7 @@ 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->rootmnt && !(flags & MNT_DETACH)) { + if (mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. @@ -597,18 +681,20 @@ asmlinkage long sys_umount(char __user * name, int flags) if (retval) goto out; retval = -EINVAL; - if (nd.dentry != nd.mnt->mnt_root) + if (nd.path.dentry != nd.path.mnt->mnt_root) goto dput_and_out; - if (!check_mnt(nd.mnt)) + if (!check_mnt(nd.path.mnt)) goto dput_and_out; retval = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto dput_and_out; - retval = do_umount(nd.mnt, flags); + retval = do_umount(nd.path.mnt, flags); dput_and_out: - path_release_on_umount(&nd); + /* we mustn't call path_put() as that would clear mnt_expiry_mark */ + dput(nd.path.dentry); + mntput_no_expire(nd.path.mnt); out: return retval; } @@ -631,10 +717,10 @@ static int mount_is_safe(struct nameidata *nd) return 0; return -EPERM; #ifdef notyet - if (S_ISLNK(nd->dentry->d_inode->i_mode)) + if (S_ISLNK(nd->path.dentry->d_inode->i_mode)) return -EPERM; - if (nd->dentry->d_inode->i_mode & S_ISVTX) { - if (current->uid != nd->dentry->d_inode->i_uid) + if (nd->path.dentry->d_inode->i_mode & S_ISVTX) { + if (current->uid != nd->path.dentry->d_inode->i_uid) return -EPERM; } if (vfs_permission(nd, MAY_WRITE)) @@ -683,8 +769,8 @@ struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry, q = q->mnt_parent; } p = s; - nd.mnt = q; - nd.dentry = p->mnt_mountpoint; + nd.path.mnt = q; + nd.path.dentry = p->mnt_mountpoint; q = clone_mnt(p, p->mnt_root, flag); if (!q) goto Enomem; @@ -706,6 +792,26 @@ Enomem: return NULL; } +struct vfsmount *collect_mounts(struct vfsmount *mnt, struct dentry *dentry) +{ + struct vfsmount *tree; + down_read(&namespace_sem); + tree = copy_tree(mnt, dentry, CL_COPY_ALL | CL_PRIVATE); + up_read(&namespace_sem); + return tree; +} + +void drop_collected_mounts(struct vfsmount *mnt) +{ + LIST_HEAD(umount_list); + down_read(&namespace_sem); + spin_lock(&vfsmount_lock); + umount_tree(mnt, 0, &umount_list); + spin_unlock(&vfsmount_lock); + up_read(&namespace_sem); + release_mounts(&umount_list); +} + /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached @@ -773,8 +879,8 @@ 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 *dest_mnt = nd->path.mnt; + struct dentry *dest_dentry = nd->path.dentry; struct vfsmount *child, *p; if (propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list)) @@ -789,7 +895,7 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt, if (parent_nd) { detach_mnt(source_mnt, parent_nd); attach_mnt(source_mnt, nd); - touch_namespace(current->namespace); + touch_mnt_namespace(current->nsproxy->mnt_ns); } else { mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt); commit_tree(source_mnt); @@ -809,13 +915,13 @@ static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) if (mnt->mnt_sb->s_flags & MS_NOUSER) return -EINVAL; - if (S_ISDIR(nd->dentry->d_inode->i_mode) != + if (S_ISDIR(nd->path.dentry->d_inode->i_mode) != S_ISDIR(mnt->mnt_root->d_inode->i_mode)) return -ENOTDIR; err = -ENOENT; - mutex_lock(&nd->dentry->d_inode->i_mutex); - if (IS_DEADDIR(nd->dentry->d_inode)) + mutex_lock(&nd->path.dentry->d_inode->i_mutex); + if (IS_DEADDIR(nd->path.dentry->d_inode)) goto out_unlock; err = security_sb_check_sb(mnt, nd); @@ -823,10 +929,10 @@ static int graft_tree(struct vfsmount *mnt, struct nameidata *nd) goto out_unlock; err = -ENOENT; - if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry)) + if (IS_ROOT(nd->path.dentry) || !d_unhashed(nd->path.dentry)) err = attach_recursive_mnt(mnt, nd, NULL); out_unlock: - mutex_unlock(&nd->dentry->d_inode->i_mutex); + mutex_unlock(&nd->path.dentry->d_inode->i_mutex); if (!err) security_sb_post_addmount(mnt, nd); return err; @@ -834,14 +940,18 @@ out_unlock: /* * recursively change the type of the mountpoint. + * noinline this do_mount helper to save do_mount stack space. */ -static int do_change_type(struct nameidata *nd, int flag) +static noinline int do_change_type(struct nameidata *nd, int flag) { - struct vfsmount *m, *mnt = nd->mnt; + struct vfsmount *m, *mnt = nd->path.mnt; int recurse = flag & MS_REC; int type = flag & ~MS_REC; - if (nd->dentry != nd->mnt->mnt_root) + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (nd->path.dentry != nd->path.mnt->mnt_root) return -EINVAL; down_write(&namespace_sem); @@ -855,8 +965,10 @@ static int do_change_type(struct nameidata *nd, int flag) /* * do loopback mount. + * noinline this do_mount helper to save do_mount stack space. */ -static int do_loopback(struct nameidata *nd, char *old_name, int recurse) +static noinline int do_loopback(struct nameidata *nd, char *old_name, + int recurse) { struct nameidata old_nd; struct vfsmount *mnt = NULL; @@ -871,17 +983,17 @@ 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 (IS_MNT_UNBINDABLE(old_nd.path.mnt)) + goto out; - if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt)) + if (!check_mnt(nd->path.mnt) || !check_mnt(old_nd.path.mnt)) goto out; err = -ENOMEM; if (recurse) - mnt = copy_tree(old_nd.mnt, old_nd.dentry, 0); + mnt = copy_tree(old_nd.path.mnt, old_nd.path.dentry, 0); else - mnt = clone_mnt(old_nd.mnt, old_nd.dentry, 0); + mnt = clone_mnt(old_nd.path.mnt, old_nd.path.dentry, 0); if (!mnt) goto out; @@ -897,7 +1009,7 @@ static int do_loopback(struct nameidata *nd, char *old_name, int recurse) out: up_write(&namespace_sem); - path_release(&old_nd); + path_put(&old_nd.path); return err; } @@ -905,29 +1017,30 @@ out: * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. + * noinline this do_mount helper to save do_mount stack space. */ -static int do_remount(struct nameidata *nd, int flags, int mnt_flags, +static noinline int do_remount(struct nameidata *nd, int flags, int mnt_flags, void *data) { int err; - struct super_block *sb = nd->mnt->mnt_sb; + struct super_block *sb = nd->path.mnt->mnt_sb; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!check_mnt(nd->mnt)) + if (!check_mnt(nd->path.mnt)) return -EINVAL; - if (nd->dentry != nd->mnt->mnt_root) + if (nd->path.dentry != nd->path.mnt->mnt_root) return -EINVAL; down_write(&sb->s_umount); err = do_remount_sb(sb, flags, data, 0); if (!err) - nd->mnt->mnt_flags = mnt_flags; + nd->path.mnt->mnt_flags = mnt_flags; up_write(&sb->s_umount); if (!err) - security_sb_post_remount(nd->mnt, flags, data); + security_sb_post_remount(nd->path.mnt, flags, data); return err; } @@ -941,7 +1054,10 @@ static inline int tree_contains_unbindable(struct vfsmount *mnt) return 0; } -static int do_move_mount(struct nameidata *nd, char *old_name) +/* + * noinline this do_mount helper to save do_mount stack space. + */ +static noinline int do_move_mount(struct nameidata *nd, char *old_name) { struct nameidata old_nd, parent_nd; struct vfsmount *p; @@ -955,69 +1071,74 @@ static int do_move_mount(struct nameidata *nd, char *old_name) return err; down_write(&namespace_sem); - while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) + while (d_mountpoint(nd->path.dentry) && + follow_down(&nd->path.mnt, &nd->path.dentry)) ; err = -EINVAL; - if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt)) + if (!check_mnt(nd->path.mnt) || !check_mnt(old_nd.path.mnt)) goto out; err = -ENOENT; - mutex_lock(&nd->dentry->d_inode->i_mutex); - if (IS_DEADDIR(nd->dentry->d_inode)) + mutex_lock(&nd->path.dentry->d_inode->i_mutex); + if (IS_DEADDIR(nd->path.dentry->d_inode)) goto out1; - if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry)) + if (!IS_ROOT(nd->path.dentry) && d_unhashed(nd->path.dentry)) goto out1; err = -EINVAL; - if (old_nd.dentry != old_nd.mnt->mnt_root) + if (old_nd.path.dentry != old_nd.path.mnt->mnt_root) goto out1; - if (old_nd.mnt == old_nd.mnt->mnt_parent) + if (old_nd.path.mnt == old_nd.path.mnt->mnt_parent) goto out1; - if (S_ISDIR(nd->dentry->d_inode->i_mode) != - S_ISDIR(old_nd.dentry->d_inode->i_mode)) + if (S_ISDIR(nd->path.dentry->d_inode->i_mode) != + S_ISDIR(old_nd.path.dentry->d_inode->i_mode)) 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)) + if (old_nd.path.mnt->mnt_parent && + IS_MNT_SHARED(old_nd.path.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)) + if (IS_MNT_SHARED(nd->path.mnt) && + tree_contains_unbindable(old_nd.path.mnt)) goto out1; err = -ELOOP; - for (p = nd->mnt; p->mnt_parent != p; p = p->mnt_parent) - if (p == old_nd.mnt) + for (p = nd->path.mnt; p->mnt_parent != p; p = p->mnt_parent) + if (p == old_nd.path.mnt) goto out1; - if ((err = attach_recursive_mnt(old_nd.mnt, nd, &parent_nd))) + err = attach_recursive_mnt(old_nd.path.mnt, nd, &parent_nd); + if (err) 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); + list_del_init(&old_nd.path.mnt->mnt_expire); spin_unlock(&vfsmount_lock); out1: - mutex_unlock(&nd->dentry->d_inode->i_mutex); + mutex_unlock(&nd->path.dentry->d_inode->i_mutex); out: up_write(&namespace_sem); if (!err) - path_release(&parent_nd); - path_release(&old_nd); + path_put(&parent_nd.path); + path_put(&old_nd.path); return err; } /* * create a new mount for userspace and request it to be added into the * namespace's tree + * noinline this do_mount helper to save do_mount stack space. */ -static int do_new_mount(struct nameidata *nd, char *type, int flags, +static noinline int do_new_mount(struct nameidata *nd, char *type, int flags, int mnt_flags, char *name, void *data) { struct vfsmount *mnt; @@ -1047,16 +1168,17 @@ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd, down_write(&namespace_sem); /* Something was mounted here while we slept */ - while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) + while (d_mountpoint(nd->path.dentry) && + follow_down(&nd->path.mnt, &nd->path.dentry)) ; err = -EINVAL; - if (!check_mnt(nd->mnt)) + if (!check_mnt(nd->path.mnt)) goto unlock; /* Refuse the same filesystem on the same mount point */ err = -EBUSY; - if (nd->mnt->mnt_sb == newmnt->mnt_sb && - nd->mnt->mnt_root == nd->dentry) + if (nd->path.mnt->mnt_sb == newmnt->mnt_sb && + nd->path.mnt->mnt_root == nd->path.dentry) goto unlock; err = -EINVAL; @@ -1104,9 +1226,9 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts, */ 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; + mnt->mnt_ns = NULL; umount_tree(mnt, 1, umounts); spin_unlock(&vfsmount_lock); } else { @@ -1120,13 +1242,46 @@ 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_first_entry(graveyard, 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); @@ -1150,38 +1305,79 @@ 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 @@ -1286,7 +1482,15 @@ 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| MS_KERNMOUNT); /* ... and get the mountpoint */ retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd); @@ -1310,34 +1514,24 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, retval = do_new_mount(&nd, type_page, flags, mnt_flags, dev_name, data_page); dput_out: - path_release(&nd); + path_put(&nd.path); 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. + */ +static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, + struct fs_struct *fs) { - struct namespace *namespace = tsk->namespace; - struct namespace *new_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 ERR_PTR(-ENOMEM); atomic_set(&new_ns->count, 1); INIT_LIST_HEAD(&new_ns->list); @@ -1346,12 +1540,12 @@ 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, + 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 ERR_PTR(-ENOMEM);; } spin_lock(&vfsmount_lock); list_add_tail(&new_ns->list, &new_ns->root->mnt_list); @@ -1362,31 +1556,29 @@ 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) { + if (p == fs->root.mnt) { rootmnt = p; - fs->rootmnt = mntget(q); + fs->root.mnt = mntget(q); } - if (p == fs->pwdmnt) { + if (p == fs->pwd.mnt) { pwdmnt = p; - fs->pwdmnt = mntget(q); + fs->pwd.mnt = mntget(q); } - if (p == fs->altrootmnt) { + if (p == fs->altroot.mnt) { altrootmnt = p; - fs->altrootmnt = mntget(q); + fs->altroot.mnt = 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) @@ -1394,12 +1586,24 @@ int copy_namespace(int flags, struct task_struct *tsk) if (altrootmnt) mntput(altrootmnt); - put_namespace(namespace); - return 0; + return new_ns; +} -out: - put_namespace(namespace); - return -ENOMEM; +struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, + struct fs_struct *new_fs) +{ + struct mnt_namespace *new_ns; + + BUG_ON(!ns); + get_mnt_ns(ns); + + if (!(flags & CLONE_NEWNS)) + return ns; + + new_ns = dup_mnt_ns(ns, new_fs); + + put_mnt_ns(ns); + return new_ns; } asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name, @@ -1448,44 +1652,35 @@ out1: * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. Requires the big lock held. */ -void set_fs_root(struct fs_struct *fs, struct vfsmount *mnt, - struct dentry *dentry) +void set_fs_root(struct fs_struct *fs, struct path *path) { - struct dentry *old_root; - struct vfsmount *old_rootmnt; + struct path old_root; + write_lock(&fs->lock); old_root = fs->root; - old_rootmnt = fs->rootmnt; - fs->rootmnt = mntget(mnt); - fs->root = dget(dentry); + fs->root = *path; + path_get(path); write_unlock(&fs->lock); - if (old_root) { - dput(old_root); - mntput(old_rootmnt); - } + if (old_root.dentry) + path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. Requires the big lock held. */ -void set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt, - struct dentry *dentry) +void set_fs_pwd(struct fs_struct *fs, struct path *path) { - struct dentry *old_pwd; - struct vfsmount *old_pwdmnt; + struct path old_pwd; write_lock(&fs->lock); old_pwd = fs->pwd; - old_pwdmnt = fs->pwdmnt; - fs->pwdmnt = mntget(mnt); - fs->pwd = dget(dentry); + fs->pwd = *path; + path_get(path); write_unlock(&fs->lock); - if (old_pwd) { - dput(old_pwd); - mntput(old_pwdmnt); - } + if (old_pwd.dentry) + path_put(&old_pwd); } static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd) @@ -1500,12 +1695,12 @@ static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd) if (fs) { atomic_inc(&fs->count); task_unlock(p); - if (fs->root == old_nd->dentry - && fs->rootmnt == old_nd->mnt) - set_fs_root(fs, new_nd->mnt, new_nd->dentry); - if (fs->pwd == old_nd->dentry - && fs->pwdmnt == old_nd->mnt) - set_fs_pwd(fs, new_nd->mnt, new_nd->dentry); + if (fs->root.dentry == old_nd->path.dentry + && fs->root.mnt == old_nd->path.mnt) + set_fs_root(fs, &new_nd->path); + if (fs->pwd.dentry == old_nd->path.dentry + && fs->pwd.mnt == old_nd->path.mnt) + set_fs_pwd(fs, &new_nd->path); put_fs_struct(fs); } else task_unlock(p); @@ -1555,7 +1750,7 @@ asmlinkage long sys_pivot_root(const char __user * new_root, if (error) goto out0; error = -EINVAL; - if (!check_mnt(new_nd.mnt)) + if (!check_mnt(new_nd.path.mnt)) goto out1; error = __user_walk(put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old_nd); @@ -1564,74 +1759,78 @@ asmlinkage long sys_pivot_root(const char __user * new_root, error = security_sb_pivotroot(&old_nd, &new_nd); if (error) { - path_release(&old_nd); + path_put(&old_nd.path); goto out1; } read_lock(¤t->fs->lock); - user_nd.mnt = mntget(current->fs->rootmnt); - user_nd.dentry = dget(current->fs->root); + user_nd.path = current->fs->root; + path_get(¤t->fs->root); read_unlock(¤t->fs->lock); down_write(&namespace_sem); - mutex_lock(&old_nd.dentry->d_inode->i_mutex); + mutex_lock(&old_nd.path.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)) + if (IS_MNT_SHARED(old_nd.path.mnt) || + IS_MNT_SHARED(new_nd.path.mnt->mnt_parent) || + IS_MNT_SHARED(user_nd.path.mnt->mnt_parent)) goto out2; - if (!check_mnt(user_nd.mnt)) + if (!check_mnt(user_nd.path.mnt)) goto out2; error = -ENOENT; - if (IS_DEADDIR(new_nd.dentry->d_inode)) + if (IS_DEADDIR(new_nd.path.dentry->d_inode)) goto out2; - if (d_unhashed(new_nd.dentry) && !IS_ROOT(new_nd.dentry)) + if (d_unhashed(new_nd.path.dentry) && !IS_ROOT(new_nd.path.dentry)) goto out2; - if (d_unhashed(old_nd.dentry) && !IS_ROOT(old_nd.dentry)) + if (d_unhashed(old_nd.path.dentry) && !IS_ROOT(old_nd.path.dentry)) goto out2; error = -EBUSY; - if (new_nd.mnt == user_nd.mnt || old_nd.mnt == user_nd.mnt) + if (new_nd.path.mnt == user_nd.path.mnt || + old_nd.path.mnt == user_nd.path.mnt) goto out2; /* loop, on the same file system */ error = -EINVAL; - if (user_nd.mnt->mnt_root != user_nd.dentry) + if (user_nd.path.mnt->mnt_root != user_nd.path.dentry) goto out2; /* not a mountpoint */ - if (user_nd.mnt->mnt_parent == user_nd.mnt) + if (user_nd.path.mnt->mnt_parent == user_nd.path.mnt) goto out2; /* not attached */ - if (new_nd.mnt->mnt_root != new_nd.dentry) + if (new_nd.path.mnt->mnt_root != new_nd.path.dentry) goto out2; /* not a mountpoint */ - if (new_nd.mnt->mnt_parent == new_nd.mnt) + if (new_nd.path.mnt->mnt_parent == new_nd.path.mnt) goto out2; /* not attached */ - tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */ + /* make sure we can reach put_old from new_root */ + tmp = old_nd.path.mnt; spin_lock(&vfsmount_lock); - if (tmp != new_nd.mnt) { + if (tmp != new_nd.path.mnt) { for (;;) { if (tmp->mnt_parent == tmp) goto out3; /* already mounted on put_old */ - if (tmp->mnt_parent == new_nd.mnt) + if (tmp->mnt_parent == new_nd.path.mnt) break; tmp = tmp->mnt_parent; } - if (!is_subdir(tmp->mnt_mountpoint, new_nd.dentry)) + if (!is_subdir(tmp->mnt_mountpoint, new_nd.path.dentry)) goto out3; - } else if (!is_subdir(old_nd.dentry, new_nd.dentry)) + } else if (!is_subdir(old_nd.path.dentry, new_nd.path.dentry)) goto out3; - detach_mnt(new_nd.mnt, &parent_nd); - 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); + detach_mnt(new_nd.path.mnt, &parent_nd); + detach_mnt(user_nd.path.mnt, &root_parent); + /* mount old root on put_old */ + attach_mnt(user_nd.path.mnt, &old_nd); + /* mount new_root on / */ + attach_mnt(new_nd.path.mnt, &root_parent); + 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); error = 0; - path_release(&root_parent); - path_release(&parent_nd); + path_put(&root_parent.path); + path_put(&parent_nd.path); out2: - mutex_unlock(&old_nd.dentry->d_inode->i_mutex); + mutex_unlock(&old_nd.path.dentry->d_inode->i_mutex); up_write(&namespace_sem); - path_release(&user_nd); - path_release(&old_nd); + path_put(&user_nd.path); + path_put(&old_nd.path); out1: - path_release(&new_nd); + path_put(&new_nd.path); out0: unlock_kernel(); return error; @@ -1643,90 +1842,69 @@ out3: static void __init init_mount_tree(void) { struct vfsmount *mnt; - struct namespace *namespace; - struct task_struct *g, *p; + struct mnt_namespace *ns; + struct path root; 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); + + root.mnt = ns->root; + root.dentry = ns->root->mnt_root; + + set_fs_pwd(current->fs, &root); + set_fs_root(current->fs, &root); } -void __init mnt_init(unsigned long mempages) +void __init mnt_init(void) { - struct list_head *d; - unsigned int nr_hash; - int i; + unsigned u; + int err; init_rwsem(&namespace_sem); mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct vfsmount), - 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL, NULL); + 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); mount_hashtable = (struct list_head *)__get_free_page(GFP_ATOMIC); if (!mount_hashtable) panic("Failed to allocate mount hash table\n"); - /* - * Find the power-of-two list-heads that can fit into the allocation.. - * We don't guarantee that "sizeof(struct list_head)" is necessarily - * a power-of-two. - */ - nr_hash = PAGE_SIZE / sizeof(struct list_head); - hash_bits = 0; - do { - hash_bits++; - } while ((nr_hash >> hash_bits) != 0); - hash_bits--; + printk("Mount-cache hash table entries: %lu\n", HASH_SIZE); - /* - * Re-calculate the actual number of entries and the mask - * from the number of bits we can fit. - */ - nr_hash = 1UL << hash_bits; - hash_mask = nr_hash - 1; - - printk("Mount-cache hash table entries: %d\n", nr_hash); - - /* And initialize the newly allocated array */ - d = mount_hashtable; - i = nr_hash; - do { - INIT_LIST_HEAD(d); - d++; - i--; - } while (i); - sysfs_init(); + for (u = 0; u < HASH_SIZE; u++) + INIT_LIST_HEAD(&mount_hashtable[u]); + + err = sysfs_init(); + if (err) + printk(KERN_WARNING "%s: sysfs_init error: %d\n", + __FUNCTION__, err); + fs_kobj = kobject_create_and_add("fs", NULL); + if (!fs_kobj) + printk(KERN_WARNING "%s: kobj create error\n", __FUNCTION__); 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); @@ -1734,5 +1912,5 @@ void __put_namespace(struct namespace *namespace) spin_unlock(&vfsmount_lock); up_write(&namespace_sem); release_mounts(&umount_list); - kfree(namespace); + kfree(ns); }