diff options
Diffstat (limited to 'fs/devpts/inode.c')
| -rw-r--r-- | fs/devpts/inode.c | 464 |
1 files changed, 244 insertions, 220 deletions
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index bff4052b05e..cfe8466f7fe 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -10,22 +10,24 @@ * * ------------------------------------------------------------------------- */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/namei.h> +#include <linux/slab.h> #include <linux/mount.h> #include <linux/tty.h> #include <linux/mutex.h> +#include <linux/magic.h> #include <linux/idr.h> #include <linux/devpts_fs.h> #include <linux/parser.h> #include <linux/fsnotify.h> #include <linux/seq_file.h> -#define DEVPTS_SUPER_MAGIC 0x1cd1 - #define DEVPTS_DEFAULT_MODE 0600 /* * ptmx is a new node in /dev/pts and will be unused in legacy (single- @@ -36,7 +38,61 @@ #define DEVPTS_DEFAULT_PTMX_MODE 0000 #define PTMX_MINOR 2 -extern int pty_limit; /* Config limit on Unix98 ptys */ +/* + * sysctl support for setting limits on the number of Unix98 ptys allocated. + * Otherwise one can eat up all kernel memory by opening /dev/ptmx repeatedly. + */ +static int pty_limit = NR_UNIX98_PTY_DEFAULT; +static int pty_reserve = NR_UNIX98_PTY_RESERVE; +static int pty_limit_min; +static int pty_limit_max = INT_MAX; +static int pty_count; + +static struct ctl_table pty_table[] = { + { + .procname = "max", + .maxlen = sizeof(int), + .mode = 0644, + .data = &pty_limit, + .proc_handler = proc_dointvec_minmax, + .extra1 = &pty_limit_min, + .extra2 = &pty_limit_max, + }, { + .procname = "reserve", + .maxlen = sizeof(int), + .mode = 0644, + .data = &pty_reserve, + .proc_handler = proc_dointvec_minmax, + .extra1 = &pty_limit_min, + .extra2 = &pty_limit_max, + }, { + .procname = "nr", + .maxlen = sizeof(int), + .mode = 0444, + .data = &pty_count, + .proc_handler = proc_dointvec, + }, + {} +}; + +static struct ctl_table pty_kern_table[] = { + { + .procname = "pty", + .mode = 0555, + .child = pty_table, + }, + {} +}; + +static struct ctl_table pty_root_table[] = { + { + .procname = "kernel", + .mode = 0555, + .child = pty_kern_table, + }, + {} +}; + static DEFINE_MUTEX(allocated_ptys_lock); static struct vfsmount *devpts_mnt; @@ -44,15 +100,16 @@ static struct vfsmount *devpts_mnt; struct pts_mount_opts { int setuid; int setgid; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; umode_t mode; umode_t ptmxmode; int newinstance; + int max; }; enum { - Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode, Opt_newinstance, + Opt_uid, Opt_gid, Opt_mode, Opt_ptmxmode, Opt_newinstance, Opt_max, Opt_err }; @@ -63,6 +120,7 @@ static const match_table_t tokens = { #ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES {Opt_ptmxmode, "ptmxmode=%o"}, {Opt_newinstance, "newinstance"}, + {Opt_max, "max=%d"}, #endif {Opt_err, NULL} }; @@ -90,16 +148,28 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode) #define PARSE_MOUNT 0 #define PARSE_REMOUNT 1 +/* + * parse_mount_options(): + * Set @opts to mount options specified in @data. If an option is not + * specified in @data, set it to its default value. The exception is + * 'newinstance' option which can only be set/cleared on a mount (i.e. + * cannot be changed during remount). + * + * Note: @data may be NULL (in which case all options are set to default). + */ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) { char *p; + kuid_t uid; + kgid_t gid; opts->setuid = 0; opts->setgid = 0; - opts->uid = 0; - opts->gid = 0; + opts->uid = GLOBAL_ROOT_UID; + opts->gid = GLOBAL_ROOT_GID; opts->mode = DEVPTS_DEFAULT_MODE; opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE; + opts->max = NR_UNIX98_PTY_MAX; /* newinstance makes sense only on initial mount */ if (op == PARSE_MOUNT) @@ -118,13 +188,19 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) case Opt_uid: if (match_int(&args[0], &option)) return -EINVAL; - opts->uid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) + return -EINVAL; + opts->uid = uid; opts->setuid = 1; break; case Opt_gid: if (match_int(&args[0], &option)) return -EINVAL; - opts->gid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) + return -EINVAL; + opts->gid = gid; opts->setgid = 1; break; case Opt_mode: @@ -143,9 +219,15 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) if (op == PARSE_MOUNT) opts->newinstance = 1; break; + case Opt_max: + if (match_int(&args[0], &option) || + option < 0 || option > NR_UNIX98_PTY_MAX) + return -EINVAL; + opts->max = option; + break; #endif default: - printk(KERN_ERR "devpts: called with bogus options\n"); + pr_err("called with bogus options\n"); return -EINVAL; } } @@ -163,6 +245,13 @@ static int mknod_ptmx(struct super_block *sb) struct dentry *root = sb->s_root; struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; + kuid_t root_uid; + kgid_t root_gid; + + root_uid = make_kuid(current_user_ns(), 0); + root_gid = make_kgid(current_user_ns(), 0); + if (!uid_valid(root_uid) || !gid_valid(root_gid)) + return -EINVAL; mutex_lock(&root->d_inode->i_mutex); @@ -174,7 +263,7 @@ static int mknod_ptmx(struct super_block *sb) dentry = d_alloc_name(root, "ptmx"); if (!dentry) { - printk(KERN_NOTICE "Unable to alloc dentry for ptmx node\n"); + pr_err("Unable to alloc dentry for ptmx node\n"); goto out; } @@ -183,7 +272,7 @@ static int mknod_ptmx(struct super_block *sb) */ inode = new_inode(sb); if (!inode) { - printk(KERN_ERR "Unable to alloc inode for ptmx node\n"); + pr_err("Unable to alloc inode for ptmx node\n"); dput(dentry); goto out; } @@ -193,6 +282,8 @@ static int mknod_ptmx(struct super_block *sb) mode = S_IFCHR|opts->ptmxmode; init_special_inode(inode, mode, MKDEV(TTYAUX_MAJOR, 2)); + inode->i_uid = root_uid; + inode->i_gid = root_gid; d_add(dentry, inode); @@ -214,7 +305,7 @@ static void update_ptmx_mode(struct pts_fs_info *fsi) #else static inline void update_ptmx_mode(struct pts_fs_info *fsi) { - return; + return; } #endif @@ -224,6 +315,7 @@ static int devpts_remount(struct super_block *sb, int *flags, char *data) struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; + sync_filesystem(sb); err = parse_mount_options(data, PARSE_REMOUNT, opts); /* @@ -237,18 +329,22 @@ static int devpts_remount(struct super_block *sb, int *flags, char *data) return err; } -static int devpts_show_options(struct seq_file *seq, struct vfsmount *vfs) +static int devpts_show_options(struct seq_file *seq, struct dentry *root) { - struct pts_fs_info *fsi = DEVPTS_SB(vfs->mnt_sb); + struct pts_fs_info *fsi = DEVPTS_SB(root->d_sb); struct pts_mount_opts *opts = &fsi->mount_opts; if (opts->setuid) - seq_printf(seq, ",uid=%u", opts->uid); + seq_printf(seq, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->uid)); if (opts->setgid) - seq_printf(seq, ",gid=%u", opts->gid); + seq_printf(seq, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->gid)); seq_printf(seq, ",mode=%03o", opts->mode); #ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode); + if (opts->max < NR_UNIX98_PTY_MAX) + seq_printf(seq, ",max=%d", opts->max); #endif return 0; @@ -292,23 +388,20 @@ devpts_fill_super(struct super_block *s, void *data, int silent) inode = new_inode(s); if (!inode) - goto free_fsi; + goto fail; inode->i_ino = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; - inode->i_nlink = 2; + set_nlink(inode, 2); - s->s_root = d_alloc_root(inode); + s->s_root = d_make_root(inode); if (s->s_root) return 0; - printk(KERN_ERR "devpts: get root dentry failed\n"); - iput(inode); + pr_err("get root dentry failed\n"); -free_fsi: - kfree(s->s_fs_info); fail: return -ENOMEM; } @@ -322,186 +415,87 @@ static int compare_init_pts_sb(struct super_block *s, void *p) } /* - * Safely parse the mount options in @data and update @opts. + * devpts_mount() * - * devpts ends up parsing options two times during mount, due to the - * two modes of operation it supports. The first parse occurs in - * devpts_get_sb() when determining the mode (single-instance or - * multi-instance mode). The second parse happens in devpts_remount() - * or new_pts_mount() depending on the mode. + * If the '-o newinstance' mount option was specified, mount a new + * (private) instance of devpts. PTYs created in this instance are + * independent of the PTYs in other devpts instances. * - * Parsing of options modifies the @data making subsequent parsing - * incorrect. So make a local copy of @data and parse it. + * If the '-o newinstance' option was not specified, mount/remount the + * initial kernel mount of devpts. This type of mount gives the + * legacy, single-instance semantics. * - * Return: 0 On success, -errno on error - */ -static int safe_parse_mount_options(void *data, struct pts_mount_opts *opts) -{ - int rc; - void *datacp; - - if (!data) - return 0; - - /* Use kstrdup() ? */ - datacp = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!datacp) - return -ENOMEM; - - memcpy(datacp, data, PAGE_SIZE); - rc = parse_mount_options((char *)datacp, PARSE_MOUNT, opts); - kfree(datacp); - - return rc; -} - -/* - * Mount a new (private) instance of devpts. PTYs created in this - * instance are independent of the PTYs in other devpts instances. - */ -static int new_pts_mount(struct file_system_type *fs_type, int flags, - void *data, struct vfsmount *mnt) -{ - int err; - struct pts_fs_info *fsi; - struct pts_mount_opts *opts; - - err = get_sb_nodev(fs_type, flags, data, devpts_fill_super, mnt); - if (err) - return err; - - fsi = DEVPTS_SB(mnt->mnt_sb); - opts = &fsi->mount_opts; - - err = parse_mount_options(data, PARSE_MOUNT, opts); - if (err) - goto fail; - - err = mknod_ptmx(mnt->mnt_sb); - if (err) - goto fail; - - return 0; - -fail: - dput(mnt->mnt_sb->s_root); - deactivate_super(mnt->mnt_sb); - return err; -} - -/* - * Check if 'newinstance' mount option was specified in @data. - * - * Return: -errno on error (eg: invalid mount options specified) - * : 1 if 'newinstance' mount option was specified - * : 0 if 'newinstance' mount option was NOT specified - */ -static int is_new_instance_mount(void *data) -{ - int rc; - struct pts_mount_opts opts; - - if (!data) - return 0; - - rc = safe_parse_mount_options(data, &opts); - if (!rc) - rc = opts.newinstance; - - return rc; -} - -/* - * get_init_pts_sb() + * The 'newinstance' option is needed to support multiple namespace + * semantics in devpts while preserving backward compatibility of the + * current 'single-namespace' semantics. i.e all mounts of devpts + * without the 'newinstance' mount option should bind to the initial + * kernel mount, like mount_single(). * - * This interface is needed to support multiple namespace semantics in - * devpts while preserving backward compatibility of the current 'single- - * namespace' semantics. i.e all mounts of devpts without the 'newinstance' - * mount option should bind to the initial kernel mount, like - * get_sb_single(). + * Mounts with 'newinstance' option create a new, private namespace. * - * Mounts with 'newinstance' option create a new private namespace. + * NOTE: * - * But for single-mount semantics, devpts cannot use get_sb_single(), - * because get_sb_single()/sget() find and use the super-block from + * For single-mount semantics, devpts cannot use mount_single(), + * because mount_single()/sget() find and use the super-block from * the most recent mount of devpts. But that recent mount may be a - * 'newinstance' mount and get_sb_single() would pick the newinstance + * 'newinstance' mount and mount_single() would pick the newinstance * super-block instead of the initial super-block. - * - * This interface is identical to get_sb_single() except that it - * consistently selects the 'single-namespace' superblock even in the - * presence of the private namespace (i.e 'newinstance') super-blocks. */ -static int get_init_pts_sb(struct file_system_type *fs_type, int flags, - void *data, struct vfsmount *mnt) +static struct dentry *devpts_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - struct super_block *s; int error; + struct pts_mount_opts opts; + struct super_block *s; + + error = parse_mount_options(data, PARSE_MOUNT, &opts); + if (error) + return ERR_PTR(error); + + /* Require newinstance for all user namespace mounts to ensure + * the mount options are not changed. + */ + if ((current_user_ns() != &init_user_ns) && !opts.newinstance) + return ERR_PTR(-EINVAL); + + if (opts.newinstance) + s = sget(fs_type, NULL, set_anon_super, flags, NULL); + else + s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags, + NULL); - s = sget(fs_type, compare_init_pts_sb, set_anon_super, NULL); if (IS_ERR(s)) - return PTR_ERR(s); + return ERR_CAST(s); if (!s->s_root) { - s->s_flags = flags; error = devpts_fill_super(s, data, flags & MS_SILENT ? 1 : 0); - if (error) { - up_write(&s->s_umount); - deactivate_super(s); - return error; - } + if (error) + goto out_undo_sget; s->s_flags |= MS_ACTIVE; } - do_remount_sb(s, flags, data, 0); - return simple_set_mnt(mnt, s); -} -/* - * Mount or remount the initial kernel mount of devpts. This type of - * mount maintains the legacy, single-instance semantics, while the - * kernel still allows multiple-instances. - */ -static int init_pts_mount(struct file_system_type *fs_type, int flags, - void *data, struct vfsmount *mnt) -{ - int err; + memcpy(&(DEVPTS_SB(s))->mount_opts, &opts, sizeof(opts)); - err = get_init_pts_sb(fs_type, flags, data, mnt); - if (err) - return err; + error = mknod_ptmx(s); + if (error) + goto out_undo_sget; - err = mknod_ptmx(mnt->mnt_sb); - if (err) { - dput(mnt->mnt_sb->s_root); - deactivate_super(mnt->mnt_sb); - } + return dget(s->s_root); - return err; +out_undo_sget: + deactivate_locked_super(s); + return ERR_PTR(error); } -static int devpts_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) -{ - int new; - - new = is_new_instance_mount(data); - if (new < 0) - return new; - - if (new) - return new_pts_mount(fs_type, flags, data, mnt); - - return init_pts_mount(fs_type, flags, data, mnt); -} #else /* * This supports only the legacy single-instance semantics (no * multiple-instance semantics) */ -static int devpts_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *data) { - return get_sb_single(fs_type, flags, data, devpts_fill_super, mnt); + return mount_single(fs_type, flags, data, devpts_fill_super); } #endif @@ -509,15 +503,18 @@ static void devpts_kill_sb(struct super_block *sb) { struct pts_fs_info *fsi = DEVPTS_SB(sb); + ida_destroy(&fsi->allocated_ptys); kfree(fsi); kill_litter_super(sb); } static struct file_system_type devpts_fs_type = { - .owner = THIS_MODULE, .name = "devpts", - .get_sb = devpts_get_sb, + .mount = devpts_mount, .kill_sb = devpts_kill_sb, +#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES + .fs_flags = FS_USERNS_MOUNT | FS_USERNS_DEV_MOUNT, +#endif }; /* @@ -537,6 +534,12 @@ retry: return -ENOMEM; mutex_lock(&allocated_ptys_lock); + if (pty_count >= pty_limit - + (fsi->mount_opts.newinstance ? pty_reserve : 0)) { + mutex_unlock(&allocated_ptys_lock); + return -ENOSPC; + } + ida_ret = ida_get_new(&fsi->allocated_ptys, &index); if (ida_ret < 0) { mutex_unlock(&allocated_ptys_lock); @@ -545,11 +548,12 @@ retry: return -EIO; } - if (index >= pty_limit) { + if (index >= fsi->mount_opts.max) { ida_remove(&fsi->allocated_ptys, index); mutex_unlock(&allocated_ptys_lock); - return -EIO; + return -ENOSPC; } + pty_count++; mutex_unlock(&allocated_ptys_lock); return index; } @@ -561,65 +565,93 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_lock(&allocated_ptys_lock); ida_remove(&fsi->allocated_ptys, idx); + pty_count--; mutex_unlock(&allocated_ptys_lock); } -int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty) +/** + * devpts_pty_new -- create a new inode in /dev/pts/ + * @ptmx_inode: inode of the master + * @device: major+minor of the node to be created + * @index: used as a name of the node + * @priv: what's given back by devpts_get_priv + * + * The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill. + */ +struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, + void *priv) { - /* tty layer puts index from devpts_new_index() in here */ - int number = tty->index; - struct tty_driver *driver = tty->driver; - dev_t device = MKDEV(driver->major, driver->minor_start+number); struct dentry *dentry; struct super_block *sb = pts_sb_from_inode(ptmx_inode); - struct inode *inode = new_inode(sb); + struct inode *inode; struct dentry *root = sb->s_root; struct pts_fs_info *fsi = DEVPTS_SB(sb); struct pts_mount_opts *opts = &fsi->mount_opts; char s[12]; - /* We're supposed to be given the slave end of a pty */ - BUG_ON(driver->type != TTY_DRIVER_TYPE_PTY); - BUG_ON(driver->subtype != PTY_TYPE_SLAVE); - + inode = new_inode(sb); if (!inode) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - inode->i_ino = number + 3; + inode->i_ino = index + 3; inode->i_uid = opts->setuid ? opts->uid : current_fsuid(); inode->i_gid = opts->setgid ? opts->gid : current_fsgid(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; init_special_inode(inode, S_IFCHR|opts->mode, device); - inode->i_private = tty; - tty->driver_data = inode; + inode->i_private = priv; - sprintf(s, "%d", number); + sprintf(s, "%d", index); mutex_lock(&root->d_inode->i_mutex); dentry = d_alloc_name(root, s); - if (!IS_ERR(dentry)) { + if (dentry) { d_add(dentry, inode); fsnotify_create(root->d_inode, dentry); + } else { + iput(inode); + inode = ERR_PTR(-ENOMEM); } mutex_unlock(&root->d_inode->i_mutex); - return 0; + return inode; } -struct tty_struct *devpts_get_tty(struct inode *pts_inode, int number) +/** + * devpts_get_priv -- get private data for a slave + * @pts_inode: inode of the slave + * + * Returns whatever was passed as priv in devpts_pty_new for a given inode. + */ +void *devpts_get_priv(struct inode *pts_inode) { + struct dentry *dentry; + void *priv = NULL; + BUG_ON(pts_inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR)); + /* Ensure dentry has not been deleted by devpts_pty_kill() */ + dentry = d_find_alias(pts_inode); + if (!dentry) + return NULL; + if (pts_inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC) - return (struct tty_struct *)pts_inode->i_private; - return NULL; + priv = pts_inode->i_private; + + dput(dentry); + + return priv; } -void devpts_pty_kill(struct tty_struct *tty) +/** + * devpts_pty_kill -- remove inode form /dev/pts/ + * @inode: inode of the slave to be removed + * + * This is an inverse operation of devpts_pty_new. + */ +void devpts_pty_kill(struct inode *inode) { - struct inode *inode = tty->driver_data; struct super_block *sb = pts_sb_from_inode(inode); struct dentry *root = sb->s_root; struct dentry *dentry; @@ -629,37 +661,29 @@ void devpts_pty_kill(struct tty_struct *tty) mutex_lock(&root->d_inode->i_mutex); dentry = d_find_alias(inode); - if (IS_ERR(dentry)) - goto out; - - if (dentry) { - inode->i_nlink--; - d_delete(dentry); - dput(dentry); /* d_alloc_name() in devpts_pty_new() */ - } + drop_nlink(inode); + d_delete(dentry); + dput(dentry); /* d_alloc_name() in devpts_pty_new() */ dput(dentry); /* d_find_alias above */ -out: + mutex_unlock(&root->d_inode->i_mutex); } static int __init init_devpts_fs(void) { int err = register_filesystem(&devpts_fs_type); + struct ctl_table_header *table; + if (!err) { + table = register_sysctl_table(pty_root_table); devpts_mnt = kern_mount(&devpts_fs_type); - if (IS_ERR(devpts_mnt)) + if (IS_ERR(devpts_mnt)) { err = PTR_ERR(devpts_mnt); + unregister_filesystem(&devpts_fs_type); + unregister_sysctl_table(table); + } } return err; } - -static void __exit exit_devpts_fs(void) -{ - unregister_filesystem(&devpts_fs_type); - mntput(devpts_mnt); -} - module_init(init_devpts_fs) -module_exit(exit_devpts_fs) -MODULE_LICENSE("GPL"); |
